Method and device for processing perception task

Abstract

The invention relates to the field of sensing communication, and provides a sensing task processing method and device. The processing method comprises the following steps: receiving a sensing task request, wherein the sensing task request comprises information of a sensing task; under the condition that the target network equipment is access network equipment, information of the sensing task is written into a first buffer area of the access network equipment, and the target network equipment is used for representing network equipment for scheduling the sensing task; and under the condition that the sensing task of the first buffer area meets the first triggering condition, performing scheduling processing on the sensing task of the first buffer area to obtain a scheduling result of the sensing task of the first buffer area. Based on the scheme, when the sensing task is scheduled, the resource utilization rate of the network equipment can be improved.

Description

Technical Field

[0001] This application relates to the field of sensory communication, and more specifically, to a method and apparatus for processing sensory tasks. Background Technology

[0002] Against the backdrop of the sixth-generation (6G) mobile communication system, 6G will be deeply integrated with artificial intelligence to build a new type of network that enables intelligent interconnection between humans, machines, and things, and efficient communication between intelligent agents; among them, sensing functions will become an important driving force for the rapid growth of the terminal and data traffic markets.

[0003] Currently, the scheduling mechanism for sensing tasks typically involves the core network device receiving a reported sensing task request and then triggering the scheduling process for the corresponding sensing task. Under this mechanism, on the one hand, the core network device only schedules a small number of currently received sensing tasks, resulting in insufficient utilization of its computing power. On the other hand, as the number of sensing tasks increases, the core network device needs to frequently schedule each received sensing task individually, generating significant signaling scheduling overhead. In summary, the current sensing task scheduling mechanism suffers from low resource utilization of network devices.

[0004] Therefore, how to schedule sensing tasks and improve the resource utilization of network devices has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method and apparatus for processing sensing tasks, which can improve the resource utilization of network devices when scheduling sensing tasks.

[0006] Firstly, a method for processing sensing tasks is provided. This method can be executed by an access network device, or by a component (e.g., a circuit, chip, or chip system) configured in the access network device, or by a logic module or software capable of implementing all or part of the functions of the access network device. This application does not limit this approach. The following description uses an access network device as an example. The processing method includes: Receive a perception task request, which includes information about the perception task; When the target network device is an access network device, the information of the sensing task is written into the first buffer area of ​​the access network device, and the target network device is used to represent the network device that schedules the sensing task. If the sensing task in the first buffer area meets the first triggering condition, the sensing task in the first buffer area is scheduled and processed to obtain the scheduling result of the sensing task in the first buffer area. The first triggering condition is obtained based on the first parameter, which includes at least one of the following: the number of sensing tasks in the first buffer area, the waiting time, and the urgency.

[0007] In the embodiments of this application, a first buffer area is set in the access network device. When the network device scheduling sensing tasks is the access network device, the first buffer area is used to buffer sensing task requests. Based on at least one parameter among the number of sensing tasks, waiting time, and urgency in the first buffer area, it is determined whether a first triggering condition is met. If the first triggering condition is met, the sensing tasks in the first buffer area of ​​the access network device are batch-scheduled. Compared with the prior art where the core network device immediately triggers single sensing task scheduling upon receiving a sensing task request, the above scheme, when the sensing tasks in the first buffer area meet the first triggering condition, can reduce the redundant overhead caused by frequent single-task scheduling by the access network device, avoid fragmented occupation of network resources, and thus effectively improve the resource utilization of the network device during the sensing task scheduling process.

[0008] In one implementation, the access network device receives a sensing task request and the status information of a sensing node; based on the sensing task information carried in the sensing task request and / or the status information of the sensing node, it determines the target network device for scheduling the sensing task. If the target network device is an access network device, the sensing task information is written into a first buffer area of ​​the access network device; if the sensing tasks in the first buffer area meet a first triggering condition, the sensing tasks in the first buffer area are scheduled to obtain the scheduling result of the sensing tasks in the first buffer area. If the target network device is a core network device, the sensing task information is sent to the core network device.

[0009] In conjunction with the first aspect, some implementations of the first aspect also include the following processing methods: Receive status information from sensing nodes; Based on the state information of the sensing nodes and / or the information of the sensing tasks, the target network device is obtained.

[0010] In one implementation, the access network device determines the target network device for scheduling the sensing task based on the state information of the sensing node and the information of the sensing task.

[0011] In another implementation, the access network device determines the target network device for scheduling the sensing task based on the information of the sensing task.

[0012] Optionally, based on the information of the sensing nodes and / or the information of the sensing tasks, a classification of the sensing tasks is obtained; based on the classification of the sensing tasks, the target network device corresponding to the sensing tasks is obtained.

[0013] The sensing tasks are categorized into single-area sensing tasks and cross-area sensing tasks. A single-area sensing task indicates that the sensing area corresponding to the task is located within the service area of ​​the access network device. A cross-area sensing task indicates that the sensing area corresponding to the task includes areas outside the service area of ​​the access network device.

[0014] Optionally, when the classification of sensing tasks is obtained based on the information of sensing nodes and sensing tasks, a single-area sensing task is used to indicate that the sensing area corresponding to the sensing task is located in the service area of ​​the access network device, and the node type of the sensing nodes in the service area matches the task type. A cross-area sensing task satisfies at least one of the following: the sensing area corresponding to the sensing task includes areas located outside the service area of ​​the access network device; or, the node type of the sensing nodes in the service area of ​​the access network device does not match the task type of the sensing task.

[0015] Optionally, based on the classification of the sensing task, the target network device corresponding to the sensing task is obtained, including: When the sensing task is classified as a single-area sensing task, the target network device for the sensing task is the access network device; when the sensing task is classified as a cross-area sensing task, the target network device for the sensing task is the core network device.

[0016] In the embodiments of this application, the access network device determines the target network device for scheduling the sensing task based on the status information of the sensing node and / or the information of the sensing task; that is, the access network device can accurately match whether the current sensing task can be scheduled through the sensing nodes covered by the access network device according to the received status information of the sensing node and / or the information of the sensing task. Compared with the method of core network device scheduling sensing tasks in the prior art, the above solution can determine the network device for scheduling the sensing task based on the characteristics and execution conditions of different sensing tasks, realize the reasonable division of labor and scheduling of sensing tasks among different network layers, and avoid the problem of low processing efficiency caused by the core network device centrally processing all sensing tasks.

[0017] In conjunction with the first aspect, in some implementations of the first aspect, the information of the sensing task includes the task type and the sensing area of ​​the sensing task, and the state information of the sensing node includes the node type of the sensing node. Based on the state information of the sensing nodes, and / or the information of the sensing task, the target network device is obtained, including: If the sensing area of ​​the sensing task is located within the first area and the task type matches the node type, the target network device is identified as an access network device. In cases where the sensing area of ​​a sensing task includes areas outside the first area, or in cases where the task type and node type do not match, the target network device is identified as a core network device. The first area is the service area of ​​the access network equipment.

[0018] In one implementation, when the sensing area of ​​the sensing task is located within a first area, and the task type matches the node type (i.e., the sensing area of ​​the sensing task is located within the service area of ​​the access network device), and the task type of the sensing task matches the node type of the sensing node within the service area of ​​the access network device, the access network device is determined as the target network device for scheduling the sensing task.

[0019] In one implementation, if the sensing area of ​​the sensing task includes an area outside the first area, that is, the sensing area of ​​the sensing task includes an area outside the service area of ​​the access network device; or if the task type does not match the node type, that is, the task type of the sensing task does not match the node type of the sensing node in the service area of ​​the access network device, the core network device is determined as the target network device for scheduling the sensing task.

[0020] In the embodiments of this application, the access network device implements hierarchical multi-network device processing of the sensing task based on the status information of the sensing node and / or the information of the sensing task. For example, sensing tasks whose sensing area is within the service range of the access network and whose task type matches the node type are scheduled and processed by the access network device; sensing tasks that cross the service area of ​​the access network or whose task type does not match the node type are scheduled and processed by the core network device. This can effectively reduce the signaling interaction and data processing pressure of the core network device; achieve load balancing between the access network device and the core network device; and improve the processing efficiency of the sensing task and the overall network resource utilization.

[0021] In conjunction with the first aspect, in some implementations of the first aspect, the processing method further includes: When the target network device is a core network device, send the sensing task information to the core network device.

[0022] In the embodiments of this application, when the target network device for scheduling the sensing task is a core network device, the access network device sends the sensing task information to the core network device. Compared to the prior art, where the core network device receives information on all sensing tasks from sensing nodes and processes the information of each sensing task separately, resulting in significant signaling scheduling overhead, the above solution implements hierarchical processing of sensing tasks. Specifically, some sensing tasks (e.g., single-area sensing tasks) are processed by the access network device, while some sensing tasks (e.g., cross-area sensing tasks) are processed by the core network device. When the access network device determines that a sensing task needs to be processed by the core network device, it sends the sensing task information to the core network device, thereby reducing signaling overhead.

[0023] In conjunction with the first aspect, in some implementations of the first aspect, the processing method further includes: When the target network device is a core network device, the information of the sensing task is written into the second buffer area of ​​the access network device; Send sensing task information to core network equipment, including: When the sensing task in the second buffer area meets the first triggering condition, the sensing task information of the second buffer area is sent to the core network equipment.

[0024] In one implementation, when the access network device determines that the target network device is a core network device based on the status information of the sensing node and / or the information of the sensing task, the access network device is triggered to report the information of the sensing task to the core network device.

[0025] In another implementation, when the access network device determines that the target network device is a core network device based on the status information of the sensing node and / or the information of the sensing task, the access network device writes the information of the sensing task into the second buffer area of ​​the access network device; when the second buffer area meets the first triggering condition, the access network device is triggered to report the information of the sensing task in the second buffer area to the core network device.

[0026] In the embodiments of this application, the information of the sensing tasks scheduled by the core network equipment is first written into a second buffer area. When the sensing tasks in the second buffer area meet the first triggering condition, the information of the sensing tasks in the second buffer area is sent to the core network equipment. Compared with the access network equipment sending the information of each sensing task to the core network equipment individually, the above scheme can reduce the resources occupied by the signaling interaction between the access network equipment and the core network equipment by sending the information of the sensing tasks to the core network equipment in batches. In addition, when the sensing tasks in the second buffer area meet the first triggering condition, reporting the information of the sensing tasks in the second buffer area to the core network equipment can fully take into account the urgency of the tasks.

[0027] In conjunction with the first aspect, in some implementations of the first aspect, the first triggering condition includes at least one of the first condition, the second condition, and the third condition; The first condition is used to indicate that the number of sensing tasks in a waiting state is greater than or equal to a first preset threshold. The second condition is used to indicate that the waiting time for the perception task is greater than or equal to a preset time threshold. The third condition is used to indicate that the urgency of the perception task is greater than or equal to a preset urgency threshold.

[0028] Optionally, the first preset threshold is related to the computing power of the access network device.

[0029] Optionally, the preset duration threshold is related to the task type of the perception task. Different task types correspond to different preset duration thresholds.

[0030] In one implementation, the first triggering condition includes a first condition. The first condition is based on the number of sensing tasks waiting to be processed in the buffer area. By using the number of sensing tasks in a waiting state as the triggering basis, the timeliness of sensing task processing can be guaranteed while achieving batch processing of sensing tasks.

[0031] In one implementation, the first triggering condition includes a second condition. The second condition is based on the waiting time of the sensing task in the buffer area. By using the waiting time of the sensing task as the triggering basis, the problem of long latency in sensing tasks can be avoided, ensuring the basic timeliness of sensing services.

[0032] In one implementation, the first triggering condition includes a third condition. The third condition is based on the urgency of the sensing task in the buffer zone. By using the urgency of the sensing task as the triggering basis, the urgency of the sensing task can be fully considered, thus avoiding long waiting times for urgent tasks.

[0033] In embodiments of this application, the first triggering condition includes at least one of a first condition, a second condition, and a third condition. By using at least one of the following as the triggering basis—the number of sensing tasks in a waiting state, the waiting time of the sensing tasks, or the urgency of the sensing tasks—it is possible to achieve batch processing of sensing tasks, improve network transmission and resource utilization efficiency, and simultaneously ensure the timeliness of sensing task processing.

[0034] In conjunction with the first aspect, in some implementations of the first aspect, when the first triggering condition includes the first condition, the second condition, and the third condition, the priority of the third condition is higher than the priority of the second condition, and the priority of the second condition is higher than the priority of the first condition.

[0035] In one implementation, if a sensing task in the first buffer area meets the third condition, there is no need to determine the first and second conditions. The third condition is used to determine whether the urgency of the sensing task is greater than or equal to a preset urgency threshold; if the urgency of the sensing task is greater than or equal to the preset urgency threshold, it indicates that the sensing task is an urgent sensing task. If there are urgent sensing tasks in the first buffer area, there is no need to determine the waiting time of the sensing tasks or the number of sensing tasks in a waiting state. The access network device is immediately triggered to schedule and process the sensing tasks in the first buffer area.

[0036] In the embodiments of this application, the priority of the third condition is higher than the priority of the second condition, and the priority of the second condition is higher than the priority of the first condition; through the priority relationship, it is ensured that while improving processing efficiency, the urgency of the perceived task is prioritized, so as to make full use of resources and take into account the urgency of the perceived task.

[0037] In conjunction with the first aspect, in some implementations of the first aspect, the processing method further includes: Based on the waiting time of the sensing task in the corresponding buffer area, the first adjustment amount is obtained, and the first adjustment amount is positively correlated with the waiting time of the sensing task in the corresponding buffer area; Based on the execution environment of the perception task, the second adjustment amount is obtained; Based on the first adjustment amount and / or the second adjustment amount, the target value of the urgency of the perception task in the corresponding buffer area is obtained. The target value of the urgency is positively correlated with the urgency of the perception task, and the corresponding buffer area is the first buffer area or the second buffer area.

[0038] In the embodiments of this application, the target value of the urgency of the sensing task, i.e., the urgency of the sensing task, is based on the waiting time of the sensing task in the buffer area and / or the execution environment of the sensing task is dynamically updated. Compared with a fixed urgency of the sensing task, the above scheme enables the urgency of the sensing task to be updated as the waiting time or execution environment of the sensing task changes. This ensures the processing efficiency of the sensing task under different waiting times or execution environments.

[0039] In conjunction with the first aspect, in certain implementations of the first aspect, a target value for the urgency of the perceived task is obtained based on a first adjustment amount and / or a second adjustment amount, including: Based on the initial value of the urgency of the perception task, the first adjustment amount, and / or the second adjustment amount, the target value of the urgency of the perception task is obtained. The initial value of the urgency of the perception task is obtained based on the task type of the perception task.

[0040] In the embodiments of this application, an initial value of the urgency of the sensing task is obtained based on the task type of the sensing task; and a target value of the urgency of the sensing task is obtained based on the initial value of the urgency of the sensing task, a first adjustment amount corresponding to the waiting time of the sensing task, and / or a second adjustment amount corresponding to the execution environment of the sensing task. This target value of the urgency of the sensing task takes into account both the task type of the sensing task and the dynamic changes in the waiting time and / or the execution environment of the sensing task, ensuring the accuracy of the urgency of the sensing task.

[0041] In conjunction with the first aspect, in certain implementations of the first aspect, the sensing tasks of the first buffer region are scheduled to obtain the scheduling results of the sensing tasks of the first buffer region, including: The first neural network model is used to schedule and process the perception tasks in the first buffer area, and the resource allocation results of the perception tasks in the first buffer area are obtained.

[0042] In one implementation, the first neural network model is: The first intelligent agent; for example, inputs the information of the sensing tasks of the first buffer area and the status information of the sensing nodes received by the access network device into the first intelligent agent, and the first intelligent agent outputs the resource allocation results of each sensing task of the first buffer area; the resource allocation results of each sensing task include the information of the sensing node executing the sensing task; for example, the identifier of the sensing node executing the sensing task.

[0043] In the embodiments of this application, a first neural network model is used to schedule and process the sensing tasks in the first buffer area and output the resource allocation results. The scheduling and processing of sensing tasks through the neural network model can improve the rationality and balance of resource allocation. At the same time, it reduces the complexity and lag of manually configuring scheduling rules and optimizes the processing efficiency of tasks and network resource utilization in the buffer area.

[0044] Secondly, a method for processing sensing tasks is provided. This method can be executed by a core network device, or by a component (e.g., a circuit, chip, or chip system) configured in the core network device, or by a logic module or software capable of implementing all or part of the functions of the core network device. This application does not limit this. The following description uses a core network device as an example. The processing method includes: When the target network device is a core network device, it receives information about sensing tasks from the access network device. The target network device is used to represent the network device that schedules the sensing tasks. Write the information of the sensing task into the third buffer area of ​​the core network device. If the sensing tasks in the third buffer region meet the second triggering condition, the sensing tasks in the third buffer region are scheduled and processed to obtain the scheduling results of the sensing tasks in the third buffer region. The second triggering condition is based on the second parameter, which includes at least one of the following: the number of sensing tasks in the third buffer area, the waiting time, and the urgency.

[0045] It should be understood that the second aspect is the implementation on the network device side, which corresponds to the first aspect. The explanations, supplements, and descriptions of the beneficial effects of the first aspect also apply to the second aspect, and will not be repeated here.

[0046] In conjunction with the second aspect, in some implementations of the second aspect, the target network device is obtained by the access network device based on the state information of the sensing node and / or the information of the sensing task.

[0047] In conjunction with the second aspect, in some implementations of the second aspect, the information of the sensing task includes the task type and the sensing area of ​​the sensing task, and the state information of the sensing node includes the node type of the sensing node. If the sensing area of ​​the sensing task is located within the first area and the task type matches the node type, the target network device is an access network device. In cases where the sensing area of ​​a sensing task includes areas outside the first area, or in cases where the task type and node type do not match, the target network device is a core network device. The first area is the service area of ​​the access network equipment.

[0048] In conjunction with the second aspect, in some implementations of the second aspect, the second triggering condition includes: at least one of the fourth condition, the second condition, and the third condition; The fourth condition indicates that the number of sensing tasks in a waiting state is greater than or equal to the second preset threshold. The second condition is used to indicate that the waiting time for the perception task is greater than or equal to a preset time threshold. The third condition is used to indicate that the urgency of the perception task is greater than or equal to a preset urgency threshold.

[0049] In conjunction with the second aspect, in some implementations of the second aspect, when the second triggering condition includes the fourth condition, the second condition, and the third condition, the priority of the third condition is higher than the priority of the second condition, and the priority of the second condition is higher than the priority of the fourth condition.

[0050] In conjunction with the second aspect, some implementations of the second aspect also include the following processing methods: Based on the duration of the perception task writing to the third buffer area, a first adjustment amount is obtained, which is positively correlated with the duration of the perception task writing to the third buffer area. Based on the execution environment of the perception task, the second adjustment amount is obtained; Based on the first adjustment amount and / or the second adjustment amount, the target value of the urgency of the perception task in the third buffer region is obtained, and the target value of the urgency is positively correlated with the urgency of the perception task.

[0051] In conjunction with the second aspect, in certain implementations of the second aspect, a target value for the urgency of the perceived task is obtained based on a first adjustment amount and / or a second adjustment amount, including: Based on the initial value of the urgency of the perception task, the first adjustment amount, and / or the second adjustment amount, the target value of the urgency of the perception task in the third buffer zone is obtained. The initial value of the urgency of the perception task is obtained based on the task type of the perception task.

[0052] In conjunction with the second aspect, in some implementations of the second aspect, receiving information from the sensing task of the access network device includes: When the sensing task in the second buffer area of ​​the access network device meets the first triggering condition, information from the sensing task of the access network device is received. The first triggering condition is obtained based on the first parameter, which includes at least one of the following: the number of sensing tasks in the first buffer area, the waiting time, and the urgency.

[0053] In conjunction with the second aspect, in some implementations of the second aspect, the first triggering condition includes at least one of the first condition, the second condition, and the third condition; The first condition is used to indicate that the number of sensing tasks in a waiting state is greater than or equal to a first preset threshold. The second condition is used to indicate that the waiting time for the perception task is greater than or equal to a preset time threshold. The third condition is used to indicate that the urgency of the perception task is greater than or equal to a preset urgency threshold.

[0054] In conjunction with the second aspect, in some implementations of the second aspect, when the first triggering condition includes a first condition, a second condition, and a third condition, the priority of the third condition is higher than the priority of the second condition, and the priority of the second condition is higher than the priority of the first condition.

[0055] In conjunction with the second aspect, some implementations of the second aspect also include the following processing methods: Receive status information from the sensing nodes of the access network equipment.

[0056] In conjunction with the second aspect, in certain implementations of the second aspect, the sensing tasks of the third buffer region are scheduled to obtain the scheduling results of the sensing tasks of the third buffer region, including: The second neural network model is used to schedule and process the perception tasks in the third buffer area, and the resource allocation results of the perception tasks in the third buffer area are obtained.

[0057] Thirdly, a processing apparatus for a perception task is provided, comprising modules or units for performing the processing method described in the first aspect or any possible implementation thereof.

[0058] In one design, the processing device is a processing chip, which may include input circuitry or interface for transmitting information or data, and output circuitry or interface for receiving information or data.

[0059] In another design, the processing device is a processing equipment, which may include a transmitter for sending information or data and a receiver for receiving information or data.

[0060] In another design, the processing device is used to execute the processing method in the first aspect or any possible implementation of the first aspect. The processing device may be configured in the access network device, or the processing device itself may be the access network device.

[0061] Fourthly, a processing apparatus for a perception task is provided, comprising modules or units for performing the processing method in the second aspect or any possible implementation thereof.

[0062] In one design, the processing device may include modules that perform the methods / operations / steps / actions described in the foregoing aspects one by one. These modules may be hardware circuits, software, or a combination of hardware circuits and software.

[0063] In one design, the processing device is a processing chip, which may include input circuitry or interface for transmitting information or data, and output circuitry or interface for receiving information or data.

[0064] In another design, the processing device is a processing equipment, which may include a transmitter for sending information or data and a receiver for receiving information or data.

[0065] In another design, the processing device is used to execute the processing method in the second aspect or any possible implementation of the second aspect described above. The processing device may be configured in the core network equipment, or the processing device itself may be the core network equipment.

[0066] It should be understood that the third aspect described above is the device-side implementation corresponding to the first aspect; the fourth aspect is the device-side implementation corresponding to the second aspect. The explanations, supplements, and descriptions of the beneficial effects of the first aspect also apply to the third aspect. The explanations, supplements, and descriptions of the beneficial effects of the second aspect also apply to the fourth aspect, and will not be repeated here.

[0067] Fifthly, a processing apparatus for a perception task is provided, including a processor; the processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the processing method in the first aspect or any possible implementation of the first aspect.

[0068] Optionally, the processing device is an access network device.

[0069] Optionally, the processing device further includes a memory. Optionally, the processing device further includes a communication interface, to which the processor is coupled.

[0070] In one implementation, the communication interface can be a transceiver, or an input / output interface.

[0071] In another implementation, the processing device is a chip configured in the access network equipment. When the processing device is a chip configured in the access network equipment, the communication interface can be an input / output interface.

[0072] Sixthly, a processing apparatus for a sensing task is provided, including a processor. The processor is coupled to a memory and can be used to execute instructions or data in the memory to implement the processing method described in the second aspect or any possible implementation thereof.

[0073] Optionally, the processing device is a core network device.

[0074] Optionally, the processing device further includes a memory. Optionally, the processing device further includes a communication interface, to which the processor is coupled.

[0075] In one implementation, the communication interface can be a transceiver, or an input / output interface.

[0076] In another implementation, the processing device is a chip configured in the core network equipment. When the processing device is a chip configured in the core network equipment, the communication interface can be an input / output interface.

[0077] In a seventh aspect, a processor is provided, comprising: an input circuit, an output circuit, and a processing circuit. The processing circuit is configured to receive signals through the input circuit and transmit signals through the output circuit, causing the processor to execute a processing method in any aspect or any possible implementation thereof.

[0078] In specific implementation, the processor can be one or more chips, the input circuit can be input pins, the output circuit can be output pins, and the processing circuit can be transistors, gate circuits, flip-flops, and various logic circuits. The input signal received by the input circuit can be, but is not limited to, a signal received and input by a receiver, and the signal output by the output circuit can be, but is not limited to, an output to a transmitter and transmitted by the transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, used as both input and output circuits at different times. This application does not limit the specific implementation of the processor and various circuits.

[0079] Eighthly, a processing apparatus for a sensing task is provided, including a processor and a memory. The processor is used to read instructions stored in the memory, receive signals via a receiver, and transmit signals via a transmitter to execute the processing method in any of the above aspects or any possible implementations of any of the above aspects.

[0080] Optionally, the processor may be one or more, and the memory may be one or more.

[0081] Alternatively, the memory can be integrated with the processor, or the memory can be set separately from the processor.

[0082] In specific implementation, the memory can be a non-transitory memory; for example, a read-only memory (ROM), which can be integrated with the processor on the same chip or set on different chips. The embodiments of this application do not limit the type of memory or the way the memory and processor are set.

[0083] It should be understood that the relevant data interaction process, such as sending indication information, can be the process of the processor outputting indication information, and receiving capability information can be the process of the processor receiving input capability information. Specifically, the data output by the processor can be sent to the transmitter, and the input data received by the processor can come from the receiver. Here, the transmitter and receiver can be collectively referred to as a transceiver.

[0084] Optionally, the processing device in the eighth aspect above can be one or more chips. The processor in the processing device can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, integrated circuit, etc.; when implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. The memory can be integrated into the processor or located outside the processor and exist independently.

[0085] Ninthly, a computer program product is provided, comprising: a computer program (also referred to as code or instructions) that, when run, causes a computer to perform the processing method in any of the above aspects or any possible implementations of any of the above aspects.

[0086] In a tenth aspect, a computer-readable storage medium is provided that stores a computer program (also referred to as code or instructions) that, when executed on a computer, causes the computer to perform the processing method in any of the foregoing aspects or any possible implementations of any of the foregoing aspects.

[0087] Eleventhly, embodiments of this application provide a chip system including one or more processors for calling and executing instructions stored in memory, causing the processing methods in any of the above aspects or possible implementations to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0088] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0089] In a twelfth aspect, a communication system is provided, including the aforementioned access network equipment and core network equipment. Optionally, the communication system may further include other equipment that communicates with the access network equipment and / or the core network equipment. Attached Figure Description

[0090] Figure 1 This is a schematic diagram of the architecture of the communication system to which the embodiments of this application apply; Figure 2 This is a schematic diagram of a processing method for a perception task provided in an embodiment of this application; Figure 3 This is a schematic diagram of a perception network architecture provided in an embodiment of this application; Figure 4 This is a schematic diagram of another processing method for a perception task provided in an embodiment of this application; Figure 5 This is a schematic diagram illustrating the determination of classification labels for a perception task provided in an embodiment of this application; Figure 6 This is a schematic diagram illustrating the processing of the progress scheduling of sensing tasks provided in an embodiment of this application; Figure 7 This is a schematic diagram of the process for determining whether the buffer area meets the first triggering condition, provided in an embodiment of this application. Figure 8 This is a schematic diagram of the process for determining whether the buffer area meets the second triggering condition, provided in an embodiment of this application. Figure 9 This is a schematic diagram of another processing method for a perception task provided in an embodiment of this application; Figure 10 This is a schematic diagram of a processing device for a sensing task provided in an embodiment of this application; Figure 11 This is a schematic diagram of another processing device for a sensing task provided in an embodiment of this application. Detailed Implementation

[0091] In the embodiments of this application, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "multiple" means two or more.

[0092] It should be noted that, in the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more.

[0093] It should also be noted that in the embodiments of this application, "preset", "fixed value", etc. can be implemented by pre-saving the corresponding code, table or other means that can be used to indicate relevant information in the electronic device. This application does not limit the specific implementation method.

[0094] It should be understood that the methods, situations, categories, and classifications of embodiments in this application are for the convenience of description only and should not constitute a special limitation. Various methods, categories, situations, and features in embodiments can be combined with each other without contradiction.

[0095] It should also be understood that, in the description of this embodiment, unless otherwise stated, "multiple" means two or more. In the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0096] The embodiments of this application are applied to communication systems, which can be second-generation (2G) communication systems, third-generation (3G) communication systems, fourth-generation (4G) systems such as long-term evolution (LTE), fifth-generation (5G) communication systems, LTE and 5G hybrid architectures, 5G new radio (5G NR) systems, and new communication systems that will emerge in the future development of communication.

[0097] Figure 1 This is a schematic diagram of the architecture of the communication system to which the embodiments of this application apply.

[0098] like Figure 1 As shown, the communication system 10 includes a wireless access network 100, a core network 20, and an Internet 30. The wireless access network 100 may include at least one access network device (such as...). Figure 1 110a and 110b, collectively referred to as 110, may also include at least one terminal (such as...). Figure 1 The following devices, 120a, 120b, 120c, 120d, 120e, 120f, 120g, 120h, 120i, and 120j, are collectively referred to as Terminal 120. Terminals 120a-120j are connected to the access network equipment wirelessly. Access network equipment 110 is connected to the core network 20 wirelessly or via a wired connection. The core network equipment in the core network and the access network equipment in the wireless access network 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and wireless access network logical functions, or they can be a single physical device integrating some core network equipment functions and some wireless access network equipment functions. Terminals can be interconnected via wired or wireless connections, and access network equipment can be interconnected via wired or wireless connections. It should be understood that... Figure 1 This is just an illustration; the communication system may also include other network devices, such as wireless repeaters and / or wireless backhaul devices. Figure 1 Not shown in the image.

[0099] The access network device 110 in the wireless access network 100 of this application embodiment is sometimes also called an access node. The access network device 110 has wireless transceiver capabilities for communicating with the terminal 120. The access network device 110 includes, but is not limited to, base stations, evolved NodeBs (eNodeBs), transmission reception points (TRPs), next-generation nodeBs (gNBs) in 5G mobile communication systems, next-generation base stations in 6th-generation (6G) mobile communication systems, access network devices or modules of access network devices in Open RAN (ORAN) systems, base stations in future mobile communication systems, or access nodes in WiFi systems. The access network device 110 can also be a module or unit capable of implementing some of the functions of a base station. For example, the access network device 110 can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), as described below. In the ORAN system, CU can also be called O-CU, DU can also be called open (O)-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CUP-UP, and RU can also be called O-RU.

[0100] Access network device 110 can be a macro base station (such as...) Figure 1 110a), micro base stations or indoor stations (such as Figure 1Access network device 110 (110b) can be a relay node or donor node, or a wireless controller in a cloud radio access network (CRAN) scenario. Optionally, access network device 110 can also be a server, wearable device, or vehicle-mounted device, etc. For example, in vehicle-to-everything (V2X) technology, access network device can be a roadside unit (RSU). Multiple access network devices in a communication system can be base stations of the same type or different types. Base stations can communicate with terminals or through relay stations. Terminals can communicate with multiple base stations in different access technologies. The embodiments of this application do not limit the specific technology or specific device form adopted by access network device 110. In this application, access network device is abbreviated as "network device". Unless otherwise specified, network device refers to access network device in this application.

[0101] A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various communication scenarios, such as device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, or smart cities. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, or smart home devices, etc. This application does not limit the device form of the terminal.

[0102] For example, such as Figure 1 The devices 120a-120j shown can be understood as communication devices with terminal functions. Specifically, 120a is a smartphone; 120b is an in-vehicle device; 120c is a mobile power bank charging station; 120d is a smart home device; 120e is a wearable device; 120f is a smart point-of-sale device or smartphone; 120g is a tablet, laptop, or PDA; 120h is a smart meter or smart printer; 120i is an in-flight device, hotspot device, or mobile device (e.g., a smartphone); and 120j is a mobile device (e.g., a smartphone).

[0103] For example, access network devices and / or terminals can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed in the air on aircraft, balloons, and satellites. This application does not limit the application scenarios of the access network devices and terminals. Furthermore, access network devices and terminals can be deployed in the same or different scenarios. For example, access network devices and terminals can be deployed simultaneously on land. Or, access network devices can be deployed on land, and terminals can be deployed on water; and so on.

[0104] Taking a base station as a network device as an example, the roles of a base station and a terminal can be relative. For instance, a flight device can be configured as a mobile base station. For a terminal 120j accessing the wireless access network 100 via 120i, terminal 120i is a base station; however, for 110a, 120i is a terminal. 110a and 120i communicate via a wireless air interface protocol, or they can communicate via a base station-to-base station interface protocol. In this case, relative to 110a, 120i is also a base station. Therefore, both base stations and terminals can be collectively referred to as communication devices. Figure 1 The 110a and 110b in the text can be referred to as communication devices with base station functions. Figure 1 The 120a-120j in the text can be referred to as communication devices with terminal functions.

[0105] In this embodiment, the communication device with access network device functionality can be an access network device, a module within an access network device (such as a chip, chip system, or software module), or a control subsystem containing access network device functionality. For example, a control subsystem containing access network device functionality can be a control center in scenarios where terminals can be applied, such as smart grids, industrial control, intelligent transportation, or smart cities.

[0106] In the embodiments of this application, the communication device with terminal function can be a terminal, or a module in the terminal (such as a chip, chip system, modem, or software model, etc.), or a device that includes terminal function. In the embodiments of this application, for ease of description, network devices (e.g., base stations) and terminals (e.g., UEs) will be used as examples for the following description.

[0107] Communication between base stations and terminals, between base stations, and between terminals can be conducted using licensed spectrum, unlicensed spectrum, or both simultaneously. Communication can be conducted using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. The embodiments of this application do not limit the spectrum resources used for wireless communication.

[0108] To facilitate understanding of the embodiments of this application, the terminology used in this application is first briefly explained. Optionally, the explanation of some terms can also be found in the 3GPP standard protocols. It should be understood that the technical terms in this application are for illustrative purposes only and not as limiting. For example, as technology evolves, technical terms may also change; where the technical meaning remains the same, other technical terms should also apply to this application.

[0109] 1. Perception Task Sensing tasks refer to the operations performed by a network using communication waveforms (e.g., 5G NR, 6G bands) to perform environmental perception, target detection, and monitoring.

[0110] Optionally, the sensing task can be performed by the UE, by the base station, or by the UE and the base station in cooperation.

[0111] In one example, the UE sends a sensing signal and receives a sensing signal (also called an echo signal) formed by the reflection of the sensing signal by a target object. Alternatively, the base station sends a sensing signal and receives a sensing signal formed by the reflection of the sensing signal by a target object. Or, the UE sends a sensing signal and the base station receives a sensing signal formed by the reflection of the sensing signal by a target object. Or, the base station sends a sensing signal and the UE receives a sensing signal formed by the reflection of the sensing signal by a target object. After receiving the sensing signal, the sensing device processes the sensing signal to generate sensing data, and then sends the sensing data to the sensing function (SF) network element. The SF network element processes the sensing data to obtain the sensing result.

[0112] Sensing signals are used to express signals that sense (or detect) a target (or object). Sensing signals are also called detection signals, linear frequency modulated signals, radar signals, radar sensing signals, radar detection signals, environmental sensing signals, etc. Sensing signals can be pulse signals or any signal that may be present in a wireless communication system. Examples include orthogonal frequency division multiplexing (OFDM) signals, channel state information reference signals (CSI-RS), or sounding reference signals (SRS). In contrast to sensing signals, signals transmitted between network devices and terminal devices can be considered communication signals. Examples include signals carried on the physical downlink shared channel (PDSCH).

[0113] The echo signal refers to the signal reflected back to the receiver after the sensing signal is emitted from the transmitter to the object; it is also called the reflected signal. By performing autocorrelation processing on the echo signal and the sensing signal, and then transforming them, the time delay of the echo signal relative to the sensing signal in the time domain can be analyzed, thus reflecting the distance of the sensing target to the transmitting source. By comparing the echo signals reflected back from the same target by different transmitted signals, the signal can be converted to the Doppler domain. Combining the Doppler and range domain analyses, the distance and velocity of the sensing target can be determined. Furthermore, the direction of the sensing target relative to the transmitting source can be determined by the beam direction of the antenna emitting the sensing signal.

[0114] 2. Heterogeneous sensing tasks Heterogeneous sensing tasks refer to sensing tasks that are completed collaboratively by different types of networks or different sensing entities (e.g., base stations, mobile phones, Wi-Fi sensors, cameras, etc.).

[0115] Optionally, heterogeneous sensing tasks include wide-area heterogeneous sensing tasks. Wide-area heterogeneous sensing tasks refer to sensing tasks that are completed collaboratively by utilizing wide-area cellular networks and non-3GPP heterogeneous sensing entities.

[0116] 3. Sensory Area A sensing area refers to the target geographical location or spatial range within which a sensing device needs to perform sensing operations. It can be represented by absolute coordinates (e.g., latitude and longitude) or relative coordinates (e.g., distance and angle relative to a base station). A sensing area is typically a specific region of interest delineated based on the physical capabilities (i.e., sensing range) of the sensing device, used to indicate the geographic space within the sensing range where sensing tasks need to be prioritized.

[0117] The shape of the sensing area can be diverse, including but not limited to rectangles, sectors, circles, polygons, etc.

[0118] Static segmentation: The sensing area can be a pre-configured fixed area whose shape and number remain unchanged. For example, roadside radar can segment a specific lane of a highway into a fixed sensing area; or it can use administrative or geographical boundaries such as residential areas, park areas, and school areas as static sensing areas.

[0119] Dynamic partitioning: The perception area can be dynamically adjusted based on real-time task requirements or environmental characteristics. For example, autonomous vehicles can dynamically adjust the size of their forward perception area based on traffic density ahead; or base stations can dynamically shrink or expand their perception area based on the current level of interference.

[0120] In multi-device collaborative scenarios, the division of the sensing area can be based on the coverage of a single sensing device or on the union of the sensing ranges of multiple sensing devices. This area division based on the union of multiple devices provides a physical basis for subsequent cross-regional sensing tasks.

[0121] 4. Single-area sensing task (single sensing service area) A single-area sensing task refers to a sensing task whose target sensing area falls entirely within the service area or jurisdiction of a single access network device (e.g., a single cell or a single base station).

[0122] Alternatively, a single-area perception task can also be called a non-cross-area perception task.

[0123] 5. Multiple sensing service areas Cross-regional sensing tasks refer to sensing tasks whose target sensing area spans the service areas of at least two access network devices (e.g., multiple cells or multiple base stations), or covers a vast area that exceeds the maximum coverage capacity of a single base station.

[0124] Optionally, cross-regional perception tasks can also be called multi-regional perception tasks.

[0125] In sixth-generation mobile communication systems, the core technological evolution direction is the deep integration of artificial intelligence and communication technologies. Relying on the network's multi-dimensional sensing capabilities across the entire domain, it expands and upgrades the scale of terminal access and data traffic services, adapting to the massive service access, highly reliable data transmission, and low-latency interaction requirements of emerging vertical industry scenarios such as drone detection and intelligent transportation. In 5G communication systems, although a core network device-centric sensing task scheduling mechanism has been proposed, this mechanism triggers the scheduling of the sensing task corresponding to the reported sensing task request upon receipt by the core network device. However, this mechanism has two drawbacks. First, the core network device only schedules a small number of currently received sensing tasks, resulting in insufficient utilization of its computing power. Second, as the number of sensing tasks increases, the core network device needs to frequently schedule each received sensing task individually, generating significant signaling scheduling overhead. In summary, the current sensing task scheduling mechanism suffers from low resource utilization of network devices.

[0126] In view of this, this application provides a method and apparatus for processing sensing tasks; the processing method includes: receiving a sensing task request, the sensing task request including sensing task information; when the target network device is an access network device, writing the sensing task information into a first buffer area of ​​the access network device, the target network device representing the network device scheduling the sensing task; when the sensing tasks in the first buffer area meet a first triggering condition, scheduling the sensing tasks in the first buffer area to obtain a scheduling result for the sensing tasks in the first buffer area; wherein, the first triggering condition is obtained based on a first parameter, the first parameter including at least one of: the number of sensing tasks in the first buffer area, the waiting time, and the urgency. Based on the above scheme, by performing batch scheduling processing of sensing tasks in the first buffer area by the access network device, the redundant overhead caused by frequent triggering of single task scheduling can be reduced, and the fragmented occupation of network resources can be avoided, thereby effectively improving the resource utilization of the network device during the sensing task scheduling process.

[0127] The following is combined Figures 2 to 9 The processing method for perception tasks provided in the embodiments of this application will be described in detail.

[0128] Figure 2 This is a schematic diagram of a processing method for a perception task provided in an embodiment of this application.

[0129] It should be understood that the subject executing this processing method can be an access network device or a core network device, or it can be a chip applied to an access network device or a chip applied to a core network device; this application does not limit this. Figure 2 The method shown includes S210 to S240, which are described in detail below.

[0130] S210. Receive a sensing task request, which includes information about the sensing task.

[0131] In one implementation, the access network device receives a sensing task request from the area server, such as... Figure 4 As shown in S303.

[0132] Optionally, the information for the sensing task includes one or more of the following: task type, task space (i.e., sensing area), sensing needs, resource needs, and urgency.

[0133] The task type is used to indicate the category of the perception task. For example, task categories include at least one of the following: intrusion detection and security monitoring, traffic management, environmental and meteorological monitoring, industrial and logistics automation, smart parking, and immersive experience and health monitoring.

[0134] Task space is used to represent the geographical location or spatial extent of performing a perception task. For example, task space includes at least one of the following: longitude, latitude, and altitude of the center location of the target or target area.

[0135] The perception requirements of a task are used to represent the parameter requirements needed for the perception task. For example, the perception requirements of a task include at least one of the following: spatial positioning accuracy, information sampling frequency, imaging type, and uploaded data format.

[0136] Resource requirements for a perception task are used to represent the hardware requirements for performing the perception task. For example, resource requirements for a perception task include at least one of the following: maximum allowable latency, minimum uplink bandwidth, minimum downlink bandwidth, minimum CPU computing power requirement, minimum GPU computing power requirement, and memory requirements.

[0137] Urgency is used to indicate the priority of a perception task.

[0138] Optionally, the above processing method further includes: The access network device receives the status information of the sensing node; based on the status information of the sensing node and / or the information of the sensing task, the access network device obtains the target network device.

[0139] Optionally, if the target network device is an access network device, S220 is executed; if the target network device is a core network device, S230 is executed.

[0140] Optionally, the state information of the sensing node includes at least one of the following: node type, spatial location, communication capability, computing resources, energy status, sensing capability, and dynamic status.

[0141] The following parameters are used to define the sensing node's capabilities: Node Type: Represents the device type of the sensing node. Spatial Location: Represents the coordinates of the sensing node. For example, spatial location includes at least one of longitude, latitude, and altitude. Communication Capability: Represents the transmission capability of the sensing node. For example, communication capability includes at least one of current uplink bandwidth, current downlink bandwidth, and maximum communication distance. Computing Resources: Represents the computing power of the sensing node. For example, computing resources include available CPU computing power or available GPU computing power. Power Status: Represents the power supply information of the sensing node. For example, power status includes at least one of current battery level, battery capacity, estimated battery life, and charging status. Sensing Capability: Represents the sensing performance of the sensing node. For example, sensing capability includes at least one of maximum frame rate, horizontal field of view, vertical field of view, maximum detection distance, distance measurement accuracy, and azimuth accuracy. Dynamic Status: Represents the real-time operating status of the sensing node. For example, dynamic status includes internal temperature or health status; health status indicates whether the sensing node is malfunctioning.

[0142] In one implementation, the access network device determines the target network device for scheduling the sensing task based on the state information of the sensing node and the information of the sensing task. The target network device refers to the network device that schedules the sensing task.

[0143] In another implementation, the access network device determines the target network device for scheduling the sensing task based on the information of the sensing task.

[0144] Optionally, in embodiments of this application, the sensing task includes: a single-area sensing task and a cross-area sensing task; the target network device for scheduling the single-area sensing task is an access network device. The target network device for scheduling the cross-area sensing task is a core network device.

[0145] Optionally, the information of the sensing task includes the task type and sensing area of ​​the sensing task, and the state information of the sensing node includes the node type of the sensing node; based on the state information of the sensing node and / or the information of the sensing task, the target network device is obtained, including: If the sensing area of ​​the sensing task is located within the first area and the task type matches the node type, the target network device is identified as an access network device. In cases where the sensing area of ​​a sensing task includes areas outside the first area, or in cases where the task type and node type do not match, the target network device is identified as a core network device. The first area is the service area of ​​the access network equipment.

[0146] In one implementation, when the sensing area of ​​the sensing task is located within a first area, and the task type matches the node type (i.e., the sensing area of ​​the sensing task is located within the service area of ​​the access network device), and the task type of the sensing task matches the node type of the sensing node within the service area of ​​the access network device, the access network device is determined as the target network device for scheduling the sensing task.

[0147] In another implementation, if the sensing area of ​​the sensing task includes an area outside the first area, that is, the sensing area of ​​the sensing task includes an area outside the service area of ​​the access network device; or if the task type does not match the node type, that is, the task type of the sensing task does not match the node type of the sensing node in the service area of ​​the access network device, the core network device is determined as the target network device for scheduling the sensing task.

[0148] S220. If the target network device is an access network device, write the information of the sensing task into the first buffer area of ​​the access network device.

[0149] Optionally, the first buffer area is used to store information about the single-area perception task, and it is a storage unit or storage space. For example, the first buffer area includes a buffer pool.

[0150] In the embodiments of this application, a buffer area is introduced in the access network device. The information of the sensing task is buffered and stored in the buffer area, which enables the temporary storage and batch processing of the information of the sensing task. This avoids the problem that the computing resources of the network device cannot be fully utilized due to the individual processing of each sensing task.

[0151] S230. If the sensing task in the first buffer area meets the first triggering condition, the sensing task in the first buffer area is scheduled and processed to obtain the scheduling result of the sensing task in the first buffer area.

[0152] The first triggering condition is obtained based on the first parameter, which includes at least one of the following: the number of sensing tasks in the first buffer area, the waiting time, and the urgency.

[0153] In this embodiment, by introducing a buffer area (e.g., a first buffer area) in the access network device, batch processing of sensing tasks can be achieved. To avoid the problem of untimely processing of sensing tasks with high urgency or strict requirements for sensing resources within the buffer area, this solution sets a judgment mechanism for buffer area trigger conditions. When the buffer area meets the corresponding trigger condition (e.g., the first trigger condition), the access network device schedules and processes sensing tasks (e.g., single-area sensing tasks) in batches. This improves service efficiency while ensuring the service quality of sensing services, achieving a better balance between service quality and service efficiency; at the same time, it makes full use of the computing resources of network devices.

[0154] Optionally, the first triggering condition includes at least one of the first condition, the second condition, and the third condition; The first condition indicates that the number of sensing tasks in a waiting state is greater than or equal to a first preset threshold; the second condition indicates that the waiting time of the sensing tasks is greater than or equal to a preset time threshold; and the third condition indicates that the urgency of the sensing tasks is greater than or equal to a preset urgency threshold.

[0155] In one implementation, the first triggering condition includes a first condition. The first condition is based on the number of sensing tasks waiting to be processed in the buffer area. By using the number of sensing tasks in a waiting state as the triggering basis, the timeliness of sensing task processing can be guaranteed while achieving batch processing of sensing tasks.

[0156] In one implementation, the first triggering condition includes a second condition. The second condition is based on the waiting time of the sensing task in the buffer area. By using the waiting time of the sensing task as the triggering basis, the problem of long latency in sensing tasks can be avoided, ensuring the basic timeliness of sensing services.

[0157] In one implementation, the first triggering condition includes a third condition. The third condition is based on the urgency of the sensing task in the buffer zone. By using the urgency of the sensing task as the triggering basis, the urgency of the sensing task can be fully considered, thus avoiding long waiting times for urgent tasks.

[0158] Optionally, if the first triggering condition includes a first condition, a second condition, and a third condition, the third condition has a higher priority than the second condition, and the second condition has a higher priority than the first condition.

[0159] Optionally, the above processing method further includes: Based on the waiting time of the sensing task in the corresponding buffer area, the first adjustment amount is obtained, and the first adjustment amount is positively correlated with the waiting time of the sensing task in the corresponding buffer area; Based on the execution environment of the perception task, the second adjustment amount is obtained; Based on the first adjustment amount and / or the second adjustment amount, the target value of the urgency of the perception task in the corresponding buffer area is obtained. The target value of the urgency is positively correlated with the urgency of the perception task, and the corresponding buffer area is the first buffer area or the second buffer area.

[0160] Optionally, based on a first adjustment amount and / or a second adjustment amount, a target value for the urgency of the perceived task is obtained, including: Based on the initial value of the urgency of the perception task, the first adjustment amount, and / or the second adjustment amount, the target value of the urgency of the perception task is obtained. The initial value of the urgency of the perception task is obtained based on the task type of the perception task.

[0161] In one implementation, a target value for the urgency of the perception task is obtained based on an initial value, a first adjustment, and a second adjustment. For example, the target value for the urgency of the perception task is obtained using the following formula: U(t) = U0 + ΔT(t) + ΔE; Where U0 represents the initial value of the urgency of the perception task; ΔT(t) represents the first adjustment of the urgency. The first adjustment of the urgency is positively correlated with the waiting time of the perception task in the corresponding buffer region; ΔT(t) = α ×(1 e -βt ); α Used to represent the maximum increment of time urgency; β The growth rate coefficient is used to represent the waiting time. ΔE represents the second adjustment factor for urgency. This second adjustment factor is related to the execution environment of the perception task. Optionally, the second adjustment factor is described in Table 3 below, and will not be repeated here.

[0162] Optionally, the maximum time urgency increment or growth rate coefficient can be determined based on the task type of the sensing task.

[0163] S240. When the target network device is a core network device, the access network device sends the sensing task information to the core network device.

[0164] In one implementation, when the target network device is a core network device, information about sensing tasks is received from the access network device.

[0165] In one implementation, when the target network device is an access network device, the access network device sends sensing task information to the core network device.

[0166] Optionally, the above processing method further includes: When the target network device is a core network device, the information of the sensing task is written into the second buffer area of ​​the access network device; Send sensing task information to core network equipment, including: When the sensing task in the second buffer area meets the first triggering condition, the sensing task information of the second buffer area is sent to the core network equipment.

[0167] Optionally, if the sensing task in the second buffer area of ​​the access network device meets the first triggering condition, the core network device receives information from the sensing task of the access network device.

[0168] In one implementation, when the access network device determines that the target network device is a core network device based on the status information of the sensing node and / or the information of the sensing task, the access network device writes the information of the sensing task into the second buffer area of ​​the access network device; when the second buffer area meets the first triggering condition, the access network device is triggered to report the information of the sensing task in the second buffer area to the core network device.

[0169] In one example, the access network device is configured with two buffer areas: a first buffer area and a second buffer area. Based on the state information of the sensing nodes and / or the information of the sensing tasks, the target network device is determined; that is, based on the state information of the sensing nodes and / or the information of the sensing tasks, the classification of the sensing tasks is determined. When the target network device is a core network device (i.e., when the sensing task is a cross-region sensing task), the sensing task information is written to the second buffer area. When the target network device is an access network device (i.e., when the sensing task is a single-region sensing task), the sensing task information is written to the first buffer area. When a first trigger condition is met in the second buffer area, the access network device reports the sensing task information of the second buffer area to the core network device. When the first trigger condition is met in the first buffer area, the access network device schedules the sensing tasks in the first buffer area to obtain the scheduling result of the sensing tasks in the first buffer area. Optionally, the above implementation method is described in detail later. Figure 4 Related descriptions.

[0170] In another implementation, when the access network device determines that the target network device is a core network device based on the status information of the sensing node and / or the information of the sensing task, it triggers the access network device to report the information of the sensing task to the core network device.

[0171] In one example, the access network device configures a first buffer area (e.g., a single-area sensing task buffer pool). After the access network device determines the classification of the sensing task, if the sensing task is a single-area sensing task, the access network device writes the sensing task information into the single-area sensing task buffer pool. If the sensing task is a cross-area sensing task, the access network device reports the cross-area sensing task information to the core network device. After receiving the cross-area sensing task information, the core network device writes the cross-area sensing task information into a third buffer area configured in the core network device (e.g., a cross-area sensing task buffer pool). If the cross-area sensing task buffer pool of the core network device meets a second triggering condition, the core network device allocates resources for the cross-area sensing task. Optionally, the above implementation method is described later. Figure 9 Related descriptions.

[0172] Optionally, the above processing method after S240 further includes: The core network equipment writes the information of the sensing tasks into the third buffer area of ​​the core network equipment; when the sensing tasks in the third buffer area meet the second triggering condition, the sensing tasks in the third buffer area are scheduled and processed to obtain the scheduling result of the sensing tasks in the third buffer area; wherein, the second triggering condition is obtained based on the second parameter, which includes at least one of the following: the number of sensing tasks in the third buffer area, the waiting time, and the urgency.

[0173] In this embodiment, by introducing a buffer area (e.g., a third buffer area) into the core network equipment, batch processing of sensing tasks can be achieved. To avoid the problem of untimely processing of sensing tasks with high urgency or strict requirements for sensing resources within the buffer area, this solution sets a judgment mechanism for buffer area trigger conditions (e.g., a second trigger condition). When the buffer area meets the corresponding trigger condition, the core network equipment schedules and processes sensing tasks (e.g., cross-regional sensing tasks) in batches. This improves service efficiency while ensuring the service quality of sensing services, achieving a better balance between service quality and service efficiency; at the same time, it makes full use of the computing resources of network equipment.

[0174] Optionally, the second triggering condition includes at least one of the following: the fourth condition, the second condition, and the third condition; The fourth condition indicates that the number of sensing tasks in a waiting state is greater than or equal to the second preset threshold; the second condition indicates that the waiting time of the sensing task is greater than or equal to the preset time threshold; and the third condition indicates that the urgency of the sensing task is greater than or equal to the preset urgency threshold.

[0175] In one implementation, the second preset threshold is greater than the first preset threshold in the first triggering condition.

[0176] It should be noted that the first preset threshold in the first triggering condition is based on the computing power of the access network equipment; the second preset threshold in the second triggering condition is based on the computing power of the core network equipment. Generally, the computing power of the core network equipment is superior to that of the access network equipment; therefore, the second preset threshold is greater than the first preset threshold.

[0177] In one implementation, the preset duration threshold is derived based on the task type of the perception task. Different task types correspond to different preset duration thresholds.

[0178] Optionally, when the second triggering condition includes: the fourth condition, the second condition and the third condition, the third condition has a higher priority than the second condition, and the second condition has a higher priority than the fourth condition.

[0179] It should be noted that the difference between the first and second triggering conditions lies in the different preset thresholds corresponding to the number of sensing tasks. In the first triggering condition, the number of sensing tasks corresponds to the first preset threshold; in the second triggering condition, the number of sensing tasks corresponds to the second preset threshold; wherein, the second preset threshold is greater than the first preset threshold.

[0180] Optionally, the above processing method further includes: The core network equipment obtains a first adjustment amount based on the duration of the sensing task being written to the third buffer area. The first adjustment amount is positively correlated with the duration of the sensing task being written to the third buffer area. The core network equipment obtains a second adjustment amount based on the execution environment of the sensing task. Based on the first adjustment amount and / or the second adjustment amount, the core network equipment obtains a target value for the urgency of the sensing task in the third buffer area. The target value for urgency is positively correlated with the urgency of the sensing task.

[0181] In the embodiments of this application, the core network device dynamically updates the urgency of sensing tasks in the third buffer area. The target value of the urgency of the sensing task, i.e., the urgency of the sensing task, is dynamically updated based on the waiting time of the sensing task in the buffer area and / or the execution environment of the sensing task. Compared to a fixed urgency of the sensing task, the above scheme enables the urgency of the sensing task to be updated as the waiting time or execution environment of the sensing task changes. This ensures the processing efficiency of the sensing task under different waiting times or execution environments.

[0182] Optionally, based on a first adjustment amount and / or a second adjustment amount, a target value for the urgency of the perceived task is obtained, including: Based on the initial value of the urgency of the perception task, the first adjustment amount, and / or the second adjustment amount, the target value of the urgency of the perception task in the third buffer zone is obtained. The initial value of the urgency of the perception task is obtained based on the task type of the perception task.

[0183] In the embodiments of this application, the core network device obtains an initial value of the urgency of the sensing task based on the task type of the sensing task; and obtains a target value of the urgency of the sensing task based on the initial value of the urgency, a first adjustment amount corresponding to the waiting time of the sensing task, and / or a second adjustment amount corresponding to the execution environment of the sensing task. This target value of the urgency of the sensing task takes into account both the task type of the sensing task and the dynamic changes in the waiting time and / or the execution environment of the sensing task, ensuring the accuracy of the urgency of the sensing task.

[0184] Optionally, the sensing tasks in the third buffer region are scheduled to obtain the scheduling results of the sensing tasks in the third buffer region, including: The second neural network model is used to schedule and process the perception tasks in the third buffer area, and the resource allocation results of the perception tasks in the third buffer area are obtained.

[0185] In one implementation, the second neural network model is a second agent; for example, the information of the perception tasks in the third buffer area and the received state information of the perception nodes are input to the second agent, and the second agent outputs the resource allocation results of each perception task in the third buffer area; the resource allocation results of each perception task include the information of the perception node that performs the perception task; for example, the identifier of the perception node that performs the perception task.

[0186] Optionally, the second intelligent agent and the first intelligent agent in the access network device are the same intelligent agent. Alternatively, the computing power of the second intelligent agent is superior to that of the first intelligent agent in the access network device.

[0187] Optionally, the above processing method further includes: Receive status information from the sensing nodes of the access network equipment.

[0188] In one implementation, when the access network device sends sensing task information to the core network device, it is triggered to send the status information of the sensing node to the core network device.

[0189] In the embodiments of this application, when the access network device sends the sensing task information to the core network device, it is triggered to send the sensing node status information to the core network device. Compared with the access network device immediately reporting the sensing node status information to the core network device after receiving the sensing node status information, the reporting mechanism in this scheme can effectively avoid the reporting of useless information and redundant transmission.

[0190] In the embodiments of this application, a first buffer area is set in the access network device. When the network device scheduling sensing tasks is the access network device, the first buffer area is used to buffer sensing task requests. Based on at least one parameter among the number of sensing tasks, waiting time, and urgency in the first buffer area, it is determined whether a first triggering condition is met. If the first triggering condition is met, the sensing tasks in the first buffer area of ​​the access network device are batch-scheduled. Compared with the prior art where the core network device immediately triggers single sensing task scheduling upon receiving a sensing task request, the above scheme, when the sensing tasks in the first buffer area meet the first triggering condition, can reduce the redundant overhead caused by frequent single-task scheduling by the access network device, avoid fragmented occupation of network resources, and thus effectively improve the resource utilization of the network device during the sensing task scheduling process.

[0191] Figure 3 This is a schematic diagram of a perception network architecture provided in an embodiment of this application.

[0192] In one example Figure 3 A hierarchical sensing network architecture is illustrated, with the core network device at the top, serving as the control center for the entire network. The core network device connects to multiple access network devices, each of which (e.g., access network device 1 to access network device n) controls the sensing nodes within its coverage area. For example, access network device 1 controls sensing node 1, sensing node 2, sensing node 3, and area server 1; access network device n controls sensing node n1, sensing node n2, sensing node n3, and area server 2. The sensing nodes are responsible for performing sensing tasks, while the area server responds to user requests to report sensing tasks to the access network devices.

[0193] Optionally, one area server can correspond to multiple access network devices. For example, area server 1 and area server 2 are the same server.

[0194] Optionally, one regional server corresponds to one access network device. For example, regional server 1 and regional server 2 are different servers.

[0195] Optionally, the access network equipment includes multi-access edge computing (MEC) devices. For example, MEC devices are deployed in the intelligent layer of a distributed sub-network area and are configured with high-performance server clusters.

[0196] Optionally, the sensing nodes are heterogeneous sensing nodes. Heterogeneous sensing nodes refer to multiple sensing nodes that differ in hardware type, sensor type, computing power, mobility, or network access method.

[0197] Optionally, Figure 3 The core network equipment in 6G can refer to the central network equipment; the access network equipment can refer to the distributed sub-network equipment in 6G.

[0198] Combination Figure 3 The perceptual network architecture shown herein provides a detailed description of the processing method for perceptual tasks provided in the embodiments of this application.

[0199] Implementation Method 1 In one implementation, the access network device is configured with two buffer zones (e.g., a single-area awareness task buffer pool and a cross-area awareness task buffer pool). The core network device is configured with one buffer zone (e.g., a cross-area awareness task buffer pool).

[0200] In one example, after the access network device determines the classification of the sensing task, it writes the information of the sensing tasks corresponding to different classifications into the corresponding buffer pools. If the sensing task is a single-area sensing task, the information is written to the single-area sensing task buffer pool. If the sensing task is a cross-area sensing task, the information is written to the cross-area sensing task buffer pool. If the single-area sensing task buffer pool meets a first triggering condition, the access network device allocates resources for the single-area sensing task. If the cross-area sensing task buffer pool meets the first triggering condition, the access network device reports the cross-area sensing task information to the core network device. After receiving the cross-area sensing task information, the core network device writes the cross-area sensing task information into a buffer pool configured in the core network device (e.g., the cross-area sensing task buffer pool). If the core network device's buffer pool meets a second triggering condition, the core network device allocates resources for the cross-area sensing task. The following section combines... Figure 4 This implementation method is described.

[0201] Figure 4 This is a schematic diagram of a processing method for a perception task provided in an embodiment of this application.

[0202] It should be understood that the subject executing this processing method can be an access network device, a core network device, a sensing node, or a regional server, or it can be a chip applied to an access network device, a core network device, a sensing node, or a regional server. This application does not limit this. Figure 4 The processing method shown includes S301 to S315, which are described in detail below.

[0203] Optionally, Figure 4 The following example uses an access network device for illustration; Figure 4 The processing method shown is also applicable to multiple access network devices; different access network devices correspond to different regions.

[0204] It should be understood that access network devices are used to represent computing units with computing or interactive capabilities. For example, access network devices are edge nodes or computing nodes. Access network devices are deployed in a distributed manner in edge areas (e.g., close to sensing nodes). Access network devices are used to process sensing data and sensing tasks in local areas. Core network devices are used to process global sensing data and sensing tasks. For example, core network devices are deployed in the cloud.

[0205] S301. The sensing node reports its status information to the access network equipment.

[0206] In one implementation, the access network device receives status information from sensing nodes in its service area.

[0207] Optionally, there may be multiple sensing nodes, and each of the multiple sensing nodes reports its status information to the access network device to which it belongs.

[0208] In one example, the sensing nodes include N (e.g., N=15) sensing nodes; wherein, the areas where sensing nodes N1 to N4 are located correspond to access network device 1; sensing nodes N5 to N6 are located in areas where access network device 1 is located. 10 The area corresponds to access network device 2; sensing node N 11 To sensing node N 15 If the area corresponds to access network device 3, then sensing nodes N1 to N4 report status information to access network device 1. 11 To sensing node N 10 Report status information to access network device 2. Sensing node N 11 To sensing node N 15 Report status information to access network device 3.

[0209] In one implementation, after completing the current sensing task, the sensing node reports its status information to the access network device.

[0210] In another implementation, the status information of the sensing node is reported to the access network device at preset time intervals. This can be understood as follows: when the time difference between the current moment and the last time the sensing node's status information was reported reaches a preset duration, the sensing node is triggered to report its status information to the access network device.

[0211] In one example, the sensing node starts monitoring with an initial time parameter t=0. It checks whether the following conditions are met: whether the time parameter t is equal to a preset duration, or whether the sensing node has completed its sensing task. If either condition is met, the sensing node reports status information to the access network device. If none of the above conditions are met (i.e., the time parameter t is less than the preset duration, and the sensing node has not completed its sensing task), the time parameter t is updated, and the updated t is checked to see if it meets the above conditions. Furthermore, after the sensing node reports its status information, the time parameter t is set to zero.

[0212] Optionally, the state information of the sensing node includes one or more of the following: Node type, spatial location, communication capabilities, computing resources, energy status, sensing capabilities, and dynamic status.

[0213] The following parameters are used to define the sensing node's capabilities: Node Type: Represents the device type of the sensing node. Spatial Location: Represents the coordinates of the sensing node. For example, spatial location includes at least one of longitude, latitude, and altitude. Communication Capability: Represents the transmission capability of the sensing node. For example, communication capability includes at least one of current uplink bandwidth, current downlink bandwidth, and maximum communication distance. Computing Resources: Represents the computing power of the sensing node. For example, computing resources include available CPU computing power or available GPU computing power. Power Status: Represents the power supply information of the sensing node. For example, power status includes at least one of current battery level, battery capacity, estimated battery life, and charging status. Sensing Capability: Represents the sensing performance of the sensing node. For example, sensing capability includes at least one of maximum frame rate, horizontal field of view, vertical field of view, maximum detection distance, distance measurement accuracy, and azimuth accuracy. Dynamic Status: Represents the real-time operating status of the sensing node. For example, dynamic status includes internal temperature or health status; health status indicates whether the sensing node is malfunctioning.

[0214] In one example, the sensing node reports its status information to the access network device in vector form. For example, Si={type, loc, comm} cap CPU, Energy Status, Sens cap , dynamic status}; where Si represents a vector of state information of the sensing node; type represents the node type of the sensing node, loc represents the spatial location of the sensing node, and comm represents the dynamic status of the sensing node. cap The term "sensor node" represents the communication capability of the sensing node; "CPU" represents the computing power of the sensing node; "energy status" represents the energy status of the sensing node; and "sens" represents the energy level of the sensing node. capThe `dynamic status` indicates the sensing capability of the sensing node, while `sensing status` indicates its dynamic state. The state information of the sensing node includes: node type, spatial location, communication capability, computing resources, energy status, sensing capability, and dynamic status. Specifically, the node type is a visible light camera, coded as [1,0, 0, 0, 0]; the spatial location includes: longitude: 120.123456; latitude: 30.123456; altitude: 150.5 meters. Communication capability includes: current uplink bandwidth of 50.0 Mbps; current downlink bandwidth of 100.0 Mbps; maximum communication distance of 5000.0 meters. Computing resources include: available CPU computing power of 150.0 GOPS; available GPU computing power of 2000.0 GFLOPS. Energy status includes: current battery level of 78.5%, battery capacity of 120.0 Wh, estimated battery life of 285 minutes, and charging status of not charging (e.g., charging status code 0). The sensing capabilities include: a maximum frame rate of 30 FPS, a horizontal field of view of 60 degrees, a vertical field of view of 90 degrees, a maximum detection range of 1000 meters, a distance measurement accuracy of 0.5 meters, and an azimuth accuracy of 0.1 degrees. Dynamic status includes an internal temperature of 45.5 degrees Celsius and a health status of healthy and without abnormalities (e.g., a health status code of 1).

[0215] For example, the state information of the aforementioned sensing node can be represented as S i =[1,0,0,0,0,0.83,0.67,0.16,0.05,0.10,0.25, 0.43,0.52, 0.785,0.24,0.285,0,0.25,0.25,0.33,0.05,0.95,0.98,0.54,1].

[0216] Table 1

[0217] In one example, different normalization methods are used for different information items. After obtaining the parameter values ​​corresponding to each information item, the parameter values ​​are normalized using the normalization methods shown in Table 1. The vector of the state information of the sensing node is obtained from the normalized parameter values. In Table 1, the encoding includes one-hot encoding. For example, when the node type is a visible light camera, the encoding obtained is [1,0,0,0,0]. Preset altitude 1 is used to represent the lowest altitude; for example, preset altitude 1 is -500 meters. Preset altitude 2 is used to represent the highest altitude; for example, preset altitude 2 is 5000 meters. Preset bandwidth is used to represent the maximum bandwidth; for example, preset bandwidth is 1000 Mbps. Preset communication distance is used to represent the maximum communication distance; for example, preset communication distance is 20000 meters. Preset CPU is used to represent the maximum CPU; for example, preset CPU is 5000 GOPS. Preset GPU is used to represent the maximum GPU; for example, preset GPU is 50000 GFLOPS. For example, the preset maximum capacity is 500 Wh. For example, the maximum battery life is 1000 minutes. The preset maximum frame rate is 120 FPS. The preset maximum detection distance is 20000 meters. The preset maximum error 1 is 10 meters. The preset maximum error 2 is 5 degrees.

[0218] It should be noted that the above description is an example of the encoding method or preset value, and this application does not impose any limitations on it.

[0219] It should be understood that the parameter values ​​in Table 1 refer to the parameter values ​​corresponding to the information items. For example, when the information item is longitude, (parameter value + 180) / 360 in the normalization method means (parameter value corresponding to longitude + 180) / 360. When the information item is latitude, (parameter value + 90) / 180 in the normalization method means (parameter value corresponding to latitude + 90) / 180.

[0220] S302. The access network device updates the status of the sensing nodes based on the status information of the sensing nodes.

[0221] Optionally, after receiving the status information of the sensing node, the access network device updates the status of the sensing node based on the status information of the sensing node.

[0222] S303. The regional server sends a sensing task request to the access network device.

[0223] The perception task request carries information about the perception task.

[0224] In one implementation, the access network device receives a sensing task request from a regional server, the sensing task request including information about the sensing task.

[0225] Optionally, the perception task request includes a heterogeneous perception task request, whereby heterogeneous perception tasks are used to represent perception tasks that are coordinated by different types of perception nodes.

[0226] It should be understood that there can be a one-to-one correspondence between a regional server and an access network device; or one regional server can correspond to multiple access network devices; this application does not impose any limitations on this.

[0227] In one implementation, the area server detects a user action and, in response, sends a sensing task request to the access network device. The user action is used to request a sensing task.

[0228] Optionally, in response to a heterogeneous sensing task triggered by a user, the regional server sends a heterogeneous sensing task request to the access network device corresponding to the regional server.

[0229] In one implementation, the information for the sensing task includes one or more of the following: task type, task space, sensing requirements, resource requirements, and urgency.

[0230] The task type is used to indicate the category of the perception task. For example, task categories include at least one of the following: intrusion detection and security monitoring, traffic management, environmental and meteorological monitoring, industrial and logistics automation, smart parking, and immersive experience and health monitoring.

[0231] Task space is used to represent the geographical location or spatial extent of performing a perception task. For example, task space includes at least one of the following: longitude, latitude, and altitude of the center location of the target or target area.

[0232] The perception requirements of a task are used to represent the parameter requirements needed for the perception task. For example, the perception requirements of a task include at least one of the following: spatial positioning accuracy, information sampling frequency, imaging type, and uploaded data format.

[0233] Resource requirements for a perception task are used to represent the hardware requirements for performing the perception task. For example, resource requirements for a perception task include at least one of the following: maximum allowable latency, minimum uplink bandwidth, minimum downlink bandwidth, minimum CPU computing power requirement, minimum GPU computing power requirement, and memory requirements.

[0234] Urgency is used to indicate the priority of a perception task.

[0235] Table 2

[0236] In one example, as shown in Table 2, the initial urgency value for the sensing task of intrusion detection and security monitoring is 0.85; the initial urgency value for the sensing task of traffic management is 0.65; the urgency value for the sensing task of environmental and meteorological monitoring is 0.50; the initial urgency value for the sensing task of industrial and logistics automation is 0.35; and the initial urgency value for the sensing task of intelligent parking is 0.20.

[0237] It should be noted that the urgency level is directly proportional to the initial value of the urgency level; the higher the initial value of the urgency level, the higher the urgency level.

[0238] Optionally, the information for the perception task is represented in vector form; for example, T j ={REQ_TYPE, Position, REQ_SENSING, REQ_DEVICE, Urgency}; where REQ_TYPE represents the task type; Position represents the task space; REQ_SENSING represents the task's perceived requirements; REQ_DEVICE represents the task's resource requirements; and Urgency represents the perceived urgency of the task.

[0239] 304. The access network device writes the information of the sensing task into the corresponding buffer pool.

[0240] Optionally, the access network device classifies the sensing task based on the information of the sensing task and / or the status information of the sensing node; based on the classification of the sensing task, it determines the target network device for scheduling the sensing task. The classification of sensing tasks includes single-area sensing tasks and cross-area sensing tasks. When the sensing task is classified as a single-area sensing task, the target network device is the access network device. When the sensing task is classified as a cross-area sensing task, the target network device is the core network device.

[0241] In one example, the access network device determines the classification of a sensing task based on information about the sensing task; this information includes the sensing area of ​​the sensing task. The sensing task is classified as a single-area sensing task or a cross-area sensing task. A single-area sensing task indicates that the sensing area corresponding to the sensing task is located within the service area of ​​the access network device. A cross-area sensing task indicates that the sensing area corresponding to the sensing task includes areas located outside the service area of ​​the access network device.

[0242] In another example, the access network device categorizes sensing tasks based on the information of the sensing task and the status information of the sensing nodes. The sensing task information includes the sensing area and the task type; the sensing node status information includes the node type. Sensing tasks are categorized as either single-area sensing tasks or cross-area sensing tasks. A single-area sensing task indicates that the sensing area corresponding to the task is located within the service area of ​​the access network device, and the node type of the sensing nodes within the service area matches the task type. A cross-area sensing task satisfies at least one of the following: the sensing area corresponding to the task includes areas located outside the service area of ​​the access network device; or, the node type of the sensing nodes within the service area of ​​the access network device does not match the task type.

[0243] In one example, the access network device uses a neural network model to determine the classification of sensing tasks.

[0244] For example, such as Figure 5 As shown, the state information of the sensing nodes (e.g., including sensing nodes S1 to Sn) and the information of the sensing tasks (e.g., including sensing tasks T1 to Tn) are input into neural network model 1. Neural network model 1 outputs the classification labels for each sensing task (e.g., the classification label for sensing task T1 to the classification label for sensing task Tn). Taking sensing node S1 as an example, the state information of sensing node S1 includes: the node type of sensing node S1, the spatial location of sensing node S1, the communication capability of sensing node S1, the computing power of sensing node S1, the energy status of sensing node S1, the sensing capability of sensing node S1, and the dynamic state of sensing node S1. Taking sensing task T1 as an example, the information of sensing task T1 includes: the task type of sensing task T1, the sensing task (sensing area), the sensing requirements of sensing task T1, and the urgency of sensing task T1.

[0245] For example, based on the state information of each sensing node, neural network model 1 detects whether a single sensing node in the current serving cell meets all the indicator requirements indicated by the sensing task information. If a single sensing node exists that meets all the indicator requirements indicated by the sensing task information, neural network model 1 classifies the sensing task as a single-area sensing task. If no single sensing node meets all the indicator requirements indicated by the sensing task information, it detects whether multiple sensing nodes within the same serving cell collaboratively meet all the indicator requirements indicated by the sensing task information. If multiple sensing nodes within the same serving cell collaboratively meet all the indicator requirements indicated by the sensing task information, neural network model 1 classifies the sensing task as a single-area sensing task. If no multiple sensing nodes within the same cell collaboratively meet all the indicator requirements indicated by the sensing task information, it detects whether multiple sensing nodes in at least two serving cells collaboratively meet all the indicator requirements indicated by the sensing task information. If multiple sensing nodes in at least two serving cells collaboratively meet all the indicator requirements indicated by the sensing task information, neural network model 1 classifies the sensing task as a cross-area sensing task.

[0246] In one implementation, the access network device includes two buffer areas (e.g., two buffer pools); one buffer pool stores information for cross-region sensing tasks; the other buffer pool stores information for single-region sensing tasks. When the sensing task is a cross-region sensing task, the information of that sensing task is written to the cross-region sensing task buffer pool; when the sensing task is a single-region sensing task, the information of that sensing task is written to the single-region sensing task buffer pool.

[0247] It should be understood that each access network device involved in this application is configured with two independent buffer pools: an intra-area sensing task buffer pool and a cross-area sensing task buffer pool. The intra-area sensing task buffer pool stores information about sensing tasks performed by sensing nodes within the coverage area of ​​the access network device. The cross-area sensing task buffer pool stores information about sensing tasks performed collaboratively by sensing nodes within the coverage area and sensing nodes outside the coverage area; or, information about sensing tasks performed by sensing nodes outside the coverage area.

[0248] In the embodiments of this application, the sensing tasks include intra-regional sensing tasks and / or cross-regional sensing tasks; wherein, intra-regional sensing tasks and cross-regional sensing tasks can be executed simultaneously; or, single-regional sensing tasks can be executed first, followed by cross-regional sensing tasks; or, cross-regional sensing tasks can be executed first, followed by single-regional sensing tasks. This depends on which sensing task in the sensing task buffer pool meets the triggering condition first. The resource allocation for intra-regional sensing tasks and cross-regional sensing tasks is described in detail below.

[0249] The processing steps for single-area perception tasks are S305 to S307; S305 to S307 are described in detail below.

[0250] S305. Access network equipment schedules and processes single-area sensing tasks.

[0251] In one implementation, when a sensing task in a single-area sensing task buffer pool meets a first triggering condition, the access network device schedules and processes the sensing tasks in the single-area sensing task buffer pool.

[0252] The first triggering condition includes at least one of the following: a first condition, a second condition, and a third condition. The fact that a sensing task in a single-area sensing task buffer pool meets the triggering condition can be understood as the sensing task in the single-area sensing task buffer pool meeting at least one of the first, second, and third conditions. The first condition indicates that the number of sensing tasks in a waiting state is greater than or equal to a first preset threshold. The second condition indicates that the waiting time of a sensing task is greater than or equal to a preset time threshold. The third condition indicates that the urgency of a sensing task is greater than or equal to a preset urgency threshold.

[0253] In one example, the first preset threshold is 20; the preset duration threshold is 500 seconds; and the preset urgency threshold is 0.7.

[0254] It should be understood that the above description is an example of the values ​​corresponding to the first preset threshold, the preset duration threshold, and the preset urgency threshold; this application does not limit the specific values ​​of the above parameters.

[0255] Optionally, the access network device allocates resources for single-area sensing tasks based on a neural network model (e.g., a first neural network model).

[0256] In one example, such as Figure 6 As shown, the state information of the sensing nodes (e.g., including sensing nodes S1 to Sn) and the information of the sensing tasks (e.g., including sensing tasks T1 to Tn) are input into neural network model 2 (e.g., the first neural network model). Neural network model 2 outputs resource allocation results (e.g., the sensing nodes executing the sensing tasks). Taking sensing node S1 as an example, the state information of sensing node S1 includes: the node type of sensing node S1, the spatial location of sensing node S1, the communication capability of sensing node S1, the computing power of sensing node S1, the energy status of sensing node S1, the sensing capability of sensing node S1, and the dynamic state of sensing node S1. Taking sensing task T1 as an example, the information of sensing task T1 includes: the task type of sensing task T1, the task space (sensing area) of sensing task T1, the sensing requirements of sensing task T1, and the urgency of sensing task T1.

[0257] The following example uses neural network model 2 as the trained deep reinforcement learning agent.

[0258] In one example, the access network device acquires information about the sensing tasks in a single-area sensing buffer pool; based on the sensing task information and the state information of sensing nodes in the serving cell of the access network device, it generates a Markov decision process (MDP) state representation for the sensing task; the state representation is input into a trained deep reinforcement learning agent, and the agent's action decision unit outputs initial resource allocation information; the agent's auxiliary load balancing unit optimizes the initial allocation information to obtain the resource allocation information for the sensing task.

[0259] For example, suppose there are 3 sensing nodes in the serving cell of the access network device (Node 1: high-performance telephoto node, MIPS=3000, bandwidth 200Mbps, idle state; Node 2: medium-performance wide-angle node, MIPS=1500, bandwidth 100Mbps, half load; Node 3: low-performance environment sampling node, MIPS=800, bandwidth 50Mbps, low load). There is a sensing task to be scheduled in the single-area sensing buffer pool: to take 4K high-definition close-up shots of a certain area in the cell. The task space is the coordinates of the area. The sensing requirements are telephoto adaptation and resolution of 3840×2160. The resource requirements are computing power ≥2000MIPS, bandwidth ≥150Mbps, and urgency 0.9. After the access network device obtains the information of the sensing task and the status information of the three nodes, it generates an MDP state representation {S1, S2}, where S1 = {Task type: high-definition close-up shooting, sensing requirements: telephoto adaptation, resolution 3840×2160, computing power requirement: ≥2000MIPS, bandwidth requirement: bandwidth ≥150Mbps, urgency: 0.9}; S2 = {Node 1: Node type = high-performance telephoto node, MIPS = 3000, bandwidth = 200Mbps, dynamic state = idle state; Node 2: Node type = medium-performance wide-angle node, MIPS = 1500, bandwidth = 100Mbps, dynamic state = half load; Node 3: Node type = low-performance environment sampling node, MIPS = 800, bandwidth = 50Mbps, dynamic state = low load}, and inputs the MDP state representation into the trained deep reinforcement learning agent. The agent's action decision unit calculates the Q value of each action using the ε-greedy strategy (ε=0.1 in the later stage of training, i.e., the operation is utilized with a 90% probability and the exploration operation is performed with a 10% probability). Node 1 has the highest Q value because it perfectly matches the task requirements and is idle. The initial resource allocation information is output to allocate the 4K high-definition close-up task to node 1, with a bandwidth of 200Mbps and a computing power of 3000MIPS. Subsequently, the method based on the tiered load balancing factor was used for optimization: First, the sensing nodes in the serving cell were divided into three performance tiers according to the MIPS computing power; among them, R0 is the high-performance tier (only containing node 1), R1 is the medium-performance tier (only containing node 2), and R2 is the low-performance tier (only containing node 3); then, the total number of tasks currently allocated to each tier was counted to form a tiered task list M; among them, M[0]=1 indicates that node 1 of the R0 tier has been allocated 1 sensing task, M[1]=1 indicates that node 2 of the R1 tier has been allocated 1 sensing task, and M[2]=1 indicates that node 3 of the R2 tier has been allocated 1 sensing task.Calculate the ratio of the number of sensing tasks between the highest performance ladder and the second highest performance ladder, i.e., M[0] / M[1]=1. If this ratio is within the preset ladder balance factor range (e.g., 0.8~1.2), it means that the load of each ladder is in a balanced state. That is, it is determined that the load is balanced and there is no need to adjust the initial allocation information. The final resource allocation information is obtained for scheduling node 1 to execute the sensing task.

[0260] Optionally, the construction and training process of the above-mentioned trained deep reinforcement learning agent includes the following steps: First, the deep Q network (DQN) is optimized and upgraded based on the double Q learning algorithm and dueling network structures to obtain the D3QN model (dueling double deep Q network) containing four sets of fully connected layers. In this model, the first and second sets of fully connected layers are connected and jointly process the input state. The second set of fully connected layers connects the third and fourth sets of fully connected layers respectively. The third set of fully connected layers is used to calculate the value function, and the fourth set of fully connected layers is used to calculate the advantage function. The sum of the calculation results of the two sets is the corresponding Q value.

[0261] Secondly, the resource allocation problem of a single-area perception task is modeled as a Markov Decision Process (MDP) quadruple, which includes a state space, an action space, a reward function, and a next state. The state space encompasses the characteristics of the perception task and the state characteristics of the perception nodes; the action space is limited to the node allocation actions within the current serving cell; and the reward function is constructed based on performance evaluation metrics such as task processing efficiency, resource utilization, and node load balancing. Based on the aforementioned D3QN model and MDP quadruple, an initial deep reinforcement learning agent is constructed, comprising four core units: an action decision unit, a reward calculation unit, a parameter update unit, and an auxiliary load balancing unit.

[0262] Next, sample pre-training data for training the single-region perception task is acquired. This sample pre-training data can be generated through public datasets, historical scheduling data collection, or scenario simulation. During training, complete samples of "state-action-reward-next state" are stored in the experience replay pool. The ε-greedy policy is used to balance the agent's exploration and utilization of the state space. In the early stage of training, actions are randomly selected with a high probability to explore more states. In the later stage, the random probability is gradually reduced, and the optimal action with the largest Q value is selected first. At the same time, the parameter update unit randomly samples from the experience replay pool and iteratively updates the D3QN model parameters through backpropagation until the model converges. Finally, a trained agent with efficient task scheduling and load balancing optimization capabilities is obtained.

[0263] Q-learning is a classic reinforcement learning algorithm that directly optimizes an iteratively computeable Q-function. Deep Q-network (DQN) is a deep learning-based Q-learning algorithm that combines value function approximation with neural network techniques, employing a target network and experiential replay for training. D3QN (dueling double deep Q network) is a deep reinforcement learning DQN model that uses double Q-learning and dueling network structures to optimize DQN, resulting in a more stable policy.

[0264] Optionally, the above is for illustrative purposes only; this application may use existing scheduling models for arbitrary sensing tasks to allocate resources for single-area sensing tasks; this application does not impose any limitations on this.

[0265] Optionally, if at least one sensing task in the single-area sensing task buffer pool meets the first triggering condition, resource allocation is determined for all sensing tasks in the single-area sensing task buffer pool based on the current computing power of the access network device; or, resource allocation is performed for the sensing task that meets the first triggering condition and all sensing tasks previously written into the single-area sensing task buffer pool.

[0266] In one example, the information for sensing tasks 1, 2, 3, and 4 is written to the single-area sensing task buffer pool in chronological order; that is, the information for sensing task 1 is the earliest information written to the single-area sensing task buffer pool. If sensing task 3 meets the triggering condition, and the current computing power of the access network device is greater than or equal to the preset computing power, the access network device allocates resources to all sensing tasks from 1 to 4. If the current computing power of the access network device is less than the preset computing power, the access network device allocates resources to sensing tasks 1, 2, and 3.

[0267] S306. The access network device sends the resource allocation results of the single-area sensing task to the sensing node.

[0268] Optionally, the access network device generates the resource allocation result of the first sensing task, which is executed by the target sensing node; the access network device sends the resource allocation result of the first sensing task to the target sensing node.

[0269] S307. The sensing node performs a single-area sensing task.

[0270] Optionally, the sensing node is a sensing node group, that is, the sensing node includes multiple sensing nodes. When the target sensing node in the sensing node group receives the resource allocation information for the sensing task within the area sent by the access network device, the target sensing node executes the sensing task within the area.

[0271] The processing procedure for cross-regional perception tasks includes steps S308 to S315; steps S308 to S315 are described in detail below.

[0272] S308. When the first triggering condition is met, the access network device reports the cross-regional sensing task information to the core network device.

[0273] Optionally, the implementation method of the first triggering condition is described in the relevant description of S305, and will not be repeated here.

[0274] Optionally, the information of the perception task includes: an initial value of the urgency of the perception task; after the information of the perception task is written into the second buffer pool, the target value of the urgency of the perception task in the waiting state will be updated.

[0275] In one example, the target value for the urgency of the perception task is obtained using the following formula: U(t) = U0 + ΔT(t) + ΔE; Where U0 represents the initial value of the urgency of the perception task; ΔT(t) represents the first adjustment of the urgency. The first adjustment of the urgency is positively correlated with the waiting time of the perception task in the corresponding buffer region; ΔT(t) = α ×(1 e -βt ); α Used to represent the maximum increment of time urgency; β The growth rate coefficient is used; t represents the waiting time. ΔE represents the second adjustment factor for urgency. The second adjustment factor for urgency is related to the execution environment of the perception task.

[0276] In one example, when t=0, ΔT(t)=0. This can be understood as the initial adjustment of urgency being 0 when the information of the perception task is written into the buffer pool.

[0277] Optionally, the growth rate coefficient ( β The growth rate coefficient is a pre-configured parameter that is positively correlated with the time sensitivity of the sensing task. For example, the higher the time sensitivity of the sensing task, the smaller the growth rate coefficient should be.

[0278] In one example, for a sensing task of intrusion detection and security monitoring, the growth rate coefficient is set to [0.8, 1.2] because this task type is highly sensitive to time. For a sensing task of traffic management, the growth rate coefficient is set to [0.4, 0.6] because this task type is moderately sensitive to time. For a sensing task of environmental and meteorological monitoring, the growth rate coefficient is set to [0.1, 0.2] because this task type is less sensitive to time.

[0279] Table 3

[0280] In one example, the urgency of a sensing task waiting in the write buffer is associated with the environment of the serving cell of the access network device; that is, the urgency of a sensing task waiting in the write buffer is updated as the environmental conditions of the serving cell of the access network device change. As shown in Table 3, when a change in the environmental conditions of the serving cell is detected, including the detection of an intruding vehicle, the second adjustment amount of the urgency is 0.15. When a change in the environmental conditions of the serving cell is detected, including deteriorating weather conditions such as heavy rain, the second adjustment amount of the urgency is 0.10; when a change in the environmental conditions of the serving cell is detected, including a specific time period such as nighttime, the second adjustment amount of the urgency is 0.03.

[0281] It should be understood that the above are examples illustrating the second adjustment amount for the urgency corresponding to different task types; this application does not impose any limitations on this.

[0282] In the embodiments of this application, the urgency of the sensing task in the buffer pool is related to the waiting time and / or the regional environment. The urgency of the sensing task can be dynamically updated by the waiting time and the regional environment. Compared with a fixed urgency, the embodiments of this application can ensure the timeliness of the execution of urgent sensing tasks by dynamically updating the urgency.

[0283] In one example, the access network device first determines whether the sensing task in the buffer pool meets the second condition, then determines whether it meets the third condition, and finally determines whether it meets the first condition.

[0284] In another example, the access network device first determines whether the sensing task in the buffer pool meets the first condition, then determines whether it meets the second condition, and then determines whether it meets the third condition.

[0285] In one example, such as Figure 7 As shown, the access network device first determines whether the sensing task in the buffer pool (e.g., the first buffer area) meets the third condition, then determines whether the second condition is met, and then determines whether the first condition is met.

[0286] In this embodiment, the timely execution of urgent sensing tasks is ensured by adjusting the judgment order of various conditions. Specifically, the access network device first determines whether the sensing tasks in the buffer pool meet the third condition (i.e., whether there is an urgent sensing task). If an urgent sensing task is detected, the execution process of that sensing task is directly triggered without executing subsequent judgment steps regarding the first condition (number of tasks) and the second condition (waiting time), thereby minimizing the scheduling delay of urgent tasks and ensuring timely execution.

[0287] The following is combined Figure 7 The process of the buffer pool in the access network device meeting the triggering conditions is described in detail. Optionally, if the single-area sensing task buffer pool in the access network device meets the triggering conditions, the access network device is triggered to execute S305; if the cross-area sensing task buffer pool in the access network device meets the triggering conditions, the access network device is triggered to execute S308.

[0288] S401. Write the information of the perception task into the corresponding buffer pool.

[0289] Optionally, after determining the classification of the sensing task, the access network device writes the information of the sensing task into the buffer pool corresponding to the classification of the sensing task.

[0290] In one example, the access network device includes a single-area sensing task buffer pool and a cross-area sensing task buffer pool. When the sensing task is a single-area sensing task, the access network device writes the sensing task information of the single-area sensing task into the single-area sensing task buffer pool. When the sensing task is a cross-area sensing task, the access network device writes the sensing task information of the cross-area sensing task into the cross-area sensing task buffer pool.

[0291] S402. Update the urgency of perceived tasks in the buffer pool.

[0292] Optionally, the information of the perception task includes urgency, which can be understood as the initial value of urgency; after the information of the perception task is written into the buffer pool, the urgency of the perception task is updated to the initial value of urgency, i.e., U(t)=U0.

[0293] S403. Determine if the third condition is met. If the third condition is met, proceed to S408. If the third condition is not met, proceed to S404.

[0294] Optionally, it can be determined whether the urgency of the update meets the third condition. This can be understood as determining whether the urgency of each sensing task in the buffer pool is greater than or equal to a preset urgency threshold.

[0295] In one implementation, when the information of the sensing task is written to the buffer pool, the updated urgency is the initial value of the urgency carried in the information of the sensing task.

[0296] In another implementation, when the information of the sensing task is a waiting sensing task in the buffer pool, the target value of the urgency of the updated sensing task is obtained according to the following formula: U(t) = U0 + ΔT(t) + ΔE; Where U0 represents the initial value of the urgency corresponding to the perception task; ΔT(t) represents the first adjustment amount of the urgency; and ΔE represents the second adjustment amount of the urgency.

[0297] Optionally, the implementation of each of the above parameters can be referred to the relevant description in S308, and will not be repeated here.

[0298] S404. Update the waiting time of perception tasks in the buffer pool.

[0299] In one implementation, a timer is started when the information of the sensing task is written to the buffer pool. This timer is used to record the waiting time of the sensing task when it is written to the buffer pool.

[0300] It should be noted that a timer is set for each sensing task written to the buffer pool; that is, each sensing task in the buffer pool corresponds to a waiting time.

[0301] Optionally, at the moment of writing the information of the sensing task, the waiting time of the sensing task is an initial value; the initial value of the waiting time is 0.

[0302] S405. Determine if the second condition is met. If the second condition is met, proceed to S408; otherwise, proceed to S406.

[0303] Optionally, it can be determined whether the waiting time for the update corresponding to each sensing task is greater than or equal to a preset time threshold. If the waiting time for the updated sensing task is greater than or equal to the preset time threshold, it indicates that the waiting time for the update meets the second condition. If the waiting time for the update is less than the preset time threshold, it indicates that the waiting time for the update does not meet the second condition.

[0304] Optionally, the preset duration thresholds can be different for different types of perception tasks. That is, the preset duration thresholds are obtained based on the task type of the perception task.

[0305] In one implementation, when the information of the sensing task is written to the buffer pool, the update waiting time is the initial value of the waiting time.

[0306] In another implementation, when the information of the sensing task is a sensing task waiting in the buffer pool, the updated waiting time is the duration of the timer corresponding to the sensing task.

[0307] S406. Update the number of perception tasks in the buffer pool.

[0308] Optionally, when writing information for one sensing task to the buffer pool, the number of sensing tasks is incremented by 1 to obtain the updated number of sensing tasks. Similarly, when writing information for N sensing tasks to the buffer pool, the number of sensing tasks is incremented by N to obtain the updated number of sensing tasks; N is an integer greater than 1.

[0309] S407. Determine if the first condition is met. If the first condition is met, proceed to S408. If the first condition is not met, proceed to S401.

[0310] Optionally, it is determined whether the number of updated sensing tasks is greater than or equal to a preset threshold of 1. If the number of updated sensing tasks is greater than or equal to the preset threshold of 1, it indicates that the number of updated sensing tasks meets the first condition. If the number of updated sensing tasks is less than the preset threshold of 1, it indicates that the number of updated sensing tasks does not meet the first condition.

[0311] Optionally, the preset quantity threshold 1 is related to the computing power of the access network device. For example, the preset quantity threshold 1 is positively correlated with the computing power of the access network device; the stronger the computing power of the access network device, the larger the preset quantity threshold 1.

[0312] S408. Schedule and process single-area sensing tasks, and / or report information on cross-area sensing tasks.

[0313] In one implementation, the access network device schedules and processes the single-area sensing task if at least one of the first, second, or third conditions is met in the single-area sensing task buffer pool.

[0314] Optionally, the implementation method of the access network device for scheduling and processing single-area sensing tasks is described in the relevant description of S305, and will not be repeated here.

[0315] In another implementation, if the cross-regional sensing task buffer pool meets at least one of the first, second, or third conditions, the access network device reports the cross-regional sensing task information in the cross-regional buffer pool to the core network device.

[0316] Optionally, if a sensing task in the cross-regional sensing task buffer pool meets the third condition, the access network device reports the information of the sensing task in the cross-regional sensing task buffer pool to the core network device. After receiving the sensing task information, the core network device writes the sensing task information into the cross-regional sensing task buffer pool in the core network device and immediately triggers resource allocation for the cross-regional sensing tasks in the cross-regional sensing task buffer pool.

[0317] In one implementation, the core network device allocates resources to cross-regional sensing tasks in the cross-regional sensing task buffer pool, which can be understood as allocating resources to all cross-regional sensing tasks in the buffer pool. Optionally, the implementation method of the core network device allocating resources to cross-regional sensing tasks is described in the following S312.

[0318] S409. Set the number of sensing tasks in the buffer pool to the initial value.

[0319] In one implementation, when the access network device reports information about cross-regional sensing tasks in the cross-regional sensing task buffer pool to the core network device, the number of sensing tasks in the cross-regional sensing task buffer pool is set to an initial value.

[0320] In another implementation, when the access network device allocates resources to the single-area sensing tasks in the single-area sensing task buffer pool, the number of sensing tasks in the single-area sensing task buffer pool is set to the initial value.

[0321] Optionally, the number of perception tasks is initially set to 0.

[0322] In the embodiments of this application, the access network device first determines whether the sensing tasks in the buffer pool meet the third condition (i.e., whether there is an urgent sensing task). If an urgent sensing task is detected, the execution process of the sensing task is directly triggered without executing subsequent judgment steps regarding the first condition (number of tasks) and the second condition (waiting time), thereby minimizing the scheduling delay of urgent tasks and ensuring timely execution.

[0323] S309. Access network equipment reports the status information of sensing nodes to core network equipment.

[0324] Optionally, if the access network device reports the status information of the sensing node to the core network device, the access network device will also report the status information of the sensing node to the core network device. In other words, if the access network device does not report the status information of the sensing node to the core network device, the access network device will not report the status information of the sensing node.

[0325] In the embodiments of this application, when the access network device reports information about a cross-regional sensing task to the core network device, the access network device also reports the status information of the sensing nodes to the core network device. Since the core network device is used to coordinate cross-regional sensing tasks, if the sensing nodes report their status information to both the access network device and the core network device, it is possible that the core network device receives the status information of each sensing node even when there is no cross-regional sensing task, resulting in a waste of resources for the core network device.

[0326] S310. The core network equipment updates the status of the sensing nodes based on the status information of the sensing nodes.

[0327] Optionally, the status information of the sensing node includes at least one of the following: node type, spatial location, communication capabilities, computing resources, energy status, sensing capabilities, and dynamic status. The core network equipment updates the status of the sensing node based on this status information.

[0328] In one example, if the state information of a sensing node includes its spatial location, the core network device updates the spatial location of the sensing node based on that location. If the state information of a sensing node includes its energy status, the core network device updates at least one of the sensing node's current battery level, battery capacity, estimated range, and charging status. If the state information of a sensing node includes its computing resources, the core network device updates the sensing node's current CPU computing power or current GPU computing power.

[0329] S311. The core network equipment writes the information of the cross-regional sensing task into the cross-regional sensing task buffer pool.

[0330] It should be noted that, in the embodiments of this application, the access network device is configured with a cross-regional sensing task buffer pool and a regional sensing task buffer pool. The core network device is configured with a cross-regional sensing task buffer pool. The core network device writes the information of the cross-regional sensing task into the cross-regional sensing task buffer pool in the core network device.

[0331] In one implementation, if the reporting condition in S308 is either the first condition or the second condition, the information of the cross-regional sensing task is written into the cross-regional sensing task buffer pool; and it is further determined whether the cross-regional sensing task buffer pool of the core network device meets the triggering condition.

[0332] In one implementation, when the reporting condition in S308 is the third condition, the information of the cross-regional sensing task is written into the cross-regional sensing task buffer pool; at this time, since the third condition is met, the core network equipment is triggered to schedule the sensing tasks in the cross-regional sensing task buffer pool.

[0333] S312. Core network equipment schedules and processes cross-regional sensing tasks.

[0334] Optionally, the core network equipment is configured with a cross-regional sensing task buffer pool. When the cross-regional sensing task buffer pool meets a second triggering condition, the core network equipment performs resource allocation for the cross-regional sensing tasks. The second triggering condition includes a fourth condition, a second condition, and a third condition. If the cross-regional sensing task buffer pool in the core network equipment meets at least one of the fourth, second, and third conditions, it is determined that the second triggering condition is met, and the core network equipment triggers resource allocation for the cross-regional sensing tasks. The fourth condition is that the number of sensing tasks in the buffer pool that are waiting is greater than or equal to a preset threshold value of 2. The second condition is that at least one sensing task in the buffer pool has a waiting time greater than or equal to a preset time. The third condition is that the urgency of the sensing tasks in the buffer pool is greater than or equal to a preset urgency value.

[0335] In one example, the core network device first determines whether the sensing task in the buffer pool meets the second condition, then determines whether it meets the third condition, and then determines whether it meets the fourth condition.

[0336] In another example, the core network device first determines whether the sensing task in the buffer pool meets the fourth condition, then determines whether it meets the second condition, and then determines whether it meets the third condition.

[0337] In one example, such as Figure 8 As shown, the core network equipment first determines whether the sensing tasks in the buffer pool meet the third condition, then determines whether the second condition is met, and finally determines whether the fourth condition is met.

[0338] In this embodiment, the timely execution of urgent sensing tasks is ensured by adjusting the judgment order of various conditions. Specifically, the core network device prioritizes judging whether the sensing tasks in the buffer pool meet the third condition (i.e., whether there is an urgent sensing task). If an urgent sensing task is detected, the execution process of that sensing task is directly triggered without executing subsequent judgment steps regarding the first condition (number of tasks) and the second condition (waiting time), thereby minimizing the scheduling latency of urgent tasks and ensuring timely execution.

[0339] The following is combined Figure 8 The process of triggering core network devices to allocate resources for cross-regional sensing tasks is described in detail.

[0340] S501. Write the information of the sensing task into the cross-regional sensing task buffer pool.

[0341] Optionally, the core network device receives the sensing task information reported by the access network device, which is the information of a cross-regional sensing task; and writes the information of the cross-regional sensing task into the cross-regional sensing task buffer pool.

[0342] S502. Determine if the third condition is met. If the third condition is met, execute S508; if the third condition is not met, execute S503.

[0343] Alternatively, see the implementation details of S502. Figure 4 The relevant descriptions of S403 will not be repeated here.

[0344] S503. Update the waiting time for sensing tasks in the cross-region buffer pool.

[0345] S504. Determine if the second condition is met. If the second condition is met, proceed to S508; if the second condition is not met, proceed to S505.

[0346] Alternatively, see the implementation details of S504. Figure 7 The relevant descriptions of S405 will not be repeated here.

[0347] S505. Update the number of perception tasks in the cross-region buffer pool.

[0348] Alternatively, see the implementation details of S505. Figure 7 The relevant descriptions of S406 will not be repeated here.

[0349] S506. Determine if the fourth condition is met. If the fourth condition is met, proceed to S508; otherwise, proceed to S507.

[0350] Optionally, the fourth condition indicates that the number of sensing tasks in a waiting state is greater than or equal to a second preset threshold. If the number of updated sensing tasks is greater than or equal to the second preset threshold, it indicates that the number of updated sensing tasks satisfies the fourth condition. If the number of updated sensing tasks is less than the second preset threshold, it indicates that the number of updated sensing tasks does not satisfy the fourth condition.

[0351] In one implementation, the second preset threshold and Figure 7 The first preset threshold in S407 shown is equal. That is, the fourth condition is the same as the first condition.

[0352] In another implementation, the second preset threshold is greater than Figure 7 The first preset threshold in S407 is shown. That is, the fourth condition is different from the first condition.

[0353] In one example, the second preset threshold is 100.

[0354] Optionally, the second preset threshold is related to the computing power of the core network equipment. For example, the second preset threshold is positively correlated with the computing power of the core network equipment; the stronger the computing power of the core network equipment, the larger the second preset threshold.

[0355] In the embodiments of this application, different preset thresholds can be configured for the buffer pool in the access device and the buffer pool in the core network device. These preset thresholds are used to measure whether a large amount of sensing task information has been written into the buffer pool. Since the computing power of the core network device is typically stronger than that of the access network device—meaning the core network device can schedule a greater number of sensing tasks at once than the access network device can schedule a greater number of sensing tasks at once—the second preset threshold for the buffer pool in the core network device is greater than the first preset threshold for the buffer pool in the access network device. Configuring different preset thresholds based on the computing power of the core network device and the access network device ensures full utilization of their computing power.

[0356] S507. Update the urgency of sensing tasks in the cross-regional buffer pool.

[0357] Optionally, if the fourth condition is not met, update the urgency of cross-regional sensing tasks in the buffer pool.

[0358] In one implementation, when the information of the sensing task is written to the buffer pool, the updated urgency is the initial value of the urgency carried in the information of the sensing task.

[0359] In another implementation, when the sensing task is a waiting sensing task in a buffer pool, the target value for the urgency of the updated sensing task is obtained according to the following formula: U(t) = U0 + ΔT(t) + ΔE; Where U0 represents the initial value of the urgency of the perception task; ΔT(t) represents the first adjustment amount of the urgency; and ΔE represents the second adjustment amount of the urgency.

[0360] Optionally, the implementation of each of the above parameters can be referred to the relevant description in S308, and will not be repeated here.

[0361] S508. Schedule and process sensing tasks in the cross-regional buffer pool.

[0362] S509. Set the number of sensing tasks in the cross-regional buffer pool to the initial value.

[0363] Alternatively, see the implementation details of S509. Figure 7 The relevant descriptions of S409 will not be repeated here.

[0364] Optionally, the core network equipment schedules and processes cross-regional sensing tasks using a neural network model. This implementation is described in the aforementioned S305 and will not be repeated here.

[0365] S313. The core network equipment sends the resource allocation results of the cross-regional sensing task to the access network equipment.

[0366] In one implementation, the access network device receives the resource allocation results of the sensing task from the core network device.

[0367] Optionally, the sensing nodes performing cross-regional sensing task 1 are sensing node N1 and sensing node N5. The access network device corresponding to the area where sensing node N1 is located is access network device 1; the access network device corresponding to the area where sensing node N5 is located is access network device 2. The core network device sends the resource allocation information of sensing task 1 to access network device 1 and access network device 2. The resource allocation information includes the identification information of the sensing nodes performing the sensing task.

[0368] S314. The access network device sends the resource allocation results of the cross-regional sensing task to the sensing node.

[0369] In one implementation, the access network device sends the resource allocation results for the cross-regional sensing task to the sensing node indicated in the resource allocation results.

[0370] In another implementation, the access network device sends the resource allocation results to all sensing nodes within the area.

[0371] S315. The sensing node performs cross-regional sensing tasks.

[0372] Optionally, at least two sensing nodes indicated by the resource allocation results may collaboratively perform cross-regional sensing tasks.

[0373] Implementation Method Two In another implementation, the access network device is configured with a buffer area (e.g., a single-area sensing task buffer pool). After the access network device determines the classification of the sensing task, if the sensing task is a single-area sensing task, the sensing task information is written to the buffer pool. If the sensing task is a cross-area sensing task, the access network device reports the cross-area sensing task information to the core network device. After receiving the cross-area sensing task information, the core network device writes the cross-area sensing task information into the buffer area configured in the core network device (e.g., the cross-area sensing task buffer pool). When the buffer area of ​​the core network device meets the second triggering condition, the core network device allocates resources for the cross-area sensing task. The following section combines... Figure 9 This implementation method is described.

[0374] Figure 9This is a schematic diagram of a processing method for a perception task provided in an embodiment of this application.

[0375] It should be understood that the subject executing this processing method can be an access network device, a core network device, a sensing node, or a regional server, or it can be a chip applied to an access network device, a core network device, a sensing node, or a regional server. This application does not limit this. Figure 9 The processing method shown includes S601 to S615, which are described in detail below.

[0376] S601. The sensing node reports its status information to the access network equipment.

[0377] S602. The access network device updates the status of the sensing nodes based on the status information of the sensing nodes.

[0378] S603. The regional server sends a sensing task request to the access network device.

[0379] S604. The access network device writes the information of the single-area sensing task into the single-area sensing task buffer pool.

[0380] Optionally, the access network device writes the information of the single-area sensing task into the single-area sensing task buffer pool.

[0381] Optionally, the processing steps for a single-area perception task are S605 to S607; S605 to S607 are described in detail below.

[0382] S605. Access network equipment schedules and processes single-area sensing tasks.

[0383] S606. The access network device sends the resource allocation results of the single-area sensing task to the sensing node.

[0384] S607. The sensing node performs a single-area sensing task.

[0385] Optionally, the processing procedure for cross-regional perception tasks includes S608 to S615; S608 to S615 are described in detail below.

[0386] S608. Access network devices report cross-regional sensing task information to core network devices.

[0387] It should be understood that the difference between S608 and S308 lies in the fact that, in S308, the access network device reports cross-regional sensing task information to the core network device when the cross-regional sensing task buffer pool of the access network device meets the first triggering condition. However, in S608, since the access device is only configured with a single-regional sensing task buffer pool, it reports the cross-regional sensing task information to the core network device only when it detects a cross-regional sensing task.

[0388] S609. Access network devices report the status information of sensing nodes to core network devices.

[0389] S610. The core network equipment updates the status of the sensing nodes based on the status information of the sensing nodes.

[0390] S611. The core network equipment writes the information of the sensing task into the cross-regional sensing task buffer pool.

[0391] S612. Core network equipment schedules and processes cross-regional sensing tasks.

[0392] S613. The core network equipment sends the resource allocation results of the cross-regional sensing task to the access network equipment.

[0393] S614. The access network device sends the resource allocation results of the cross-regional sensing task to the sensing node.

[0394] S615. Sensing nodes perform cross-regional sensing tasks.

[0395] Optionally, the implementation methods of S601 to S615 above are as follows: Figure 4 The relevant descriptions will not be repeated here.

[0396] It should be understood that the above examples are provided to help those skilled in the art understand the embodiments of this application, and are not intended to limit the embodiments of this application to the specific values ​​or scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the above examples, and such modifications or changes also fall within the scope of the embodiments of this application.

[0397] The above text combined Figures 1 to 9 The processing method for perception tasks provided in the embodiments of this application is described in detail below; the following will be combined with Figure 10 and Figure 11 The embodiments of the apparatus provided in this application are described in detail below. It should be understood that the apparatus in the embodiments of this application can execute the various methods of the foregoing embodiments of this application, that is, the specific working processes of the various products below can be referred to the corresponding processes in the foregoing method embodiments.

[0398] In the embodiments described above, the access network device may execute some or all of the steps in each embodiment; the core network device may execute some or all of the steps in each embodiment. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the steps may be executed in different orders as presented in the embodiments, and it is not necessary to execute all the operations in the embodiments of this application. Moreover, the sequence number of each step does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0399] Figure 10 This is a schematic block diagram of a processing apparatus for a perception task provided in an embodiment of this application. Figure 10 As shown, the processing device 700 may include a communication module 710 and a processing module 720. The communication module 710 can implement corresponding communication functions, which can be internal communication functions of the processing device 700 or communication functions between the processing device 700 and other devices. Optionally, the communication module 710 may also be referred to as a communication interface or a transceiver unit. The processing module 720 can implement corresponding processing functions.

[0400] Optionally, the processing device 700 may further include a storage unit, which can be used to store instructions and / or data; the processing module 720 can read the instructions and / or data in the storage unit so that the processing device 700 can implement the aforementioned method embodiments.

[0401] In one possible design, the processing device 700 may correspond to the access network device in the above method embodiments, or to a component (e.g., circuitry, chip, or chip system) configured in the access network device. The processing device 700 is used to execute the steps or processes performed by the access network device in any of the above method embodiments.

[0402] Optionally, the communication module 710 is used to receive a sensing task request, which includes information about the sensing task; when the target network device is an access network device, the sensing task information is written into the first buffer area of ​​the access network device, and the target network device is used to represent the network device that schedules the sensing task; the processing module 720 is used to perform scheduling processing on the sensing tasks in the first buffer area when the sensing tasks in the first buffer area meet a first triggering condition, and obtain the scheduling result of the sensing tasks in the first buffer area; wherein, the first triggering condition is obtained based on a first parameter, which includes at least one of the following: the number of sensing tasks in the first buffer area, the waiting time, and the urgency.

[0403] In another possible design, the processing device 700 may correspond to the core network device in the above method embodiments, or a component (e.g., circuit, chip, or chip system) configured in the core network device. The processing device 700 can be used to perform the steps or processes performed by the core network device in any of the above method embodiments.

[0404] Optionally, the communication module 710 is used to receive sensing task information from the access network device when the target network device is a core network device, and the target network device is used to represent the network device scheduling the sensing task; the processing module 720 is used to write the sensing task information into the third buffer area of ​​the core network device; when the sensing task in the third buffer area meets the second triggering condition, the sensing task in the third buffer area is scheduled to obtain the scheduling result of the sensing task in the third buffer area, wherein the second triggering condition is obtained based on the second parameter, and the second parameter includes at least one of the following: the number of sensing tasks in the third buffer area, the waiting time, and the urgency.

[0405] It should be understood that the above are merely examples, and detailed steps or processes can be found in the description of the foregoing embodiments.

[0406] Figure 11 This is another schematic block diagram of the processing apparatus provided in the embodiments of this application. The processing apparatus 800 can be an access network device or a core network device; the processing apparatus 800 can be a chip, chip system, or processor, etc., in the access network device or core network device that implements the above-described methods. The processing apparatus 800 can be used to implement the processing method for the perception task described in the above method embodiments, and specific details can be found in the descriptions of the above method embodiments.

[0407] like Figure 11 As shown, the processing device 800 may include one or more processors 810, which may also be referred to as processing units or processing modules, and can implement certain control functions. The processor 810 may be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, while the central processing unit can be used to control the processing device 800 (e.g., access network equipment or core network equipment), execute software programs, and process data from the software programs.

[0408] In an alternative design, the processor 810 may also store instructions and / or data, which can be executed by the processor 810 to cause the processing device 800 to perform the processing method for the perception task described in the above method embodiments.

[0409] In another alternative design, the processing device 800 may include a communication interface 820 for implementing receiving and transmitting functions. For example, the communication interface 820 may be a transceiver circuit, interface, interface circuit, or transceiver. The transceiver circuit, interface, interface circuit, or transceiver for implementing receiving and transmitting functions may be separate or integrated. The aforementioned transceiver circuit, interface, interface circuit, or transceiver may be used for reading and writing code / data, or it may be used for transmitting or relaying signals.

[0410] Optionally, the processing device 800 may include one or more memories 830, which may store instructions that can be executed on the processor 810 to cause the processing device 800 to perform the methods described in the above method embodiments. Optionally, the memories 830 may also store data.

[0411] Optionally, instructions and / or data may also be stored in the processor 810. The processor 810 and memory 830 may be configured separately or integrated together.

[0412] It should be understood that, in one possible design, the steps in the method embodiments provided in this application can be implemented by integrated logic circuits in the processor's hardware or by instructions in software form. The steps of the methods disclosed in the embodiments of this application can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, detailed descriptions are not provided here.

[0413] In one implementation, the processing device 800 may correspond to the access network device in the above method embodiments, and may be used to execute various steps and / or processes performed by the access network device in the above method embodiments. The processor 810 may be used to execute instructions stored in the memory 830, and when the processor 810 executes the instructions stored in the memory, the processor 810 is used to execute various steps and / or processes of the above method embodiments corresponding to the access network device.

[0414] In another implementation, the processing device 800 may correspond to the core network device in the above method embodiments, and may be used to execute the various steps and / or processes executed by the core network device in the above method embodiments. The processor 810 may be used to execute instructions stored in the memory 830, and when the processor 810 executes the instructions stored in the memory, the processor 810 is used to execute the various steps and / or processes of the processing method embodiments corresponding to the core network device described above.

[0415] It should be understood that the aforementioned processing device can be one or more chips. For example, the processing device can be a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0416] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0417] According to the processing method for perception tasks provided in the embodiments of this application, this application also provides a chip system, which includes one or more processors for calling and executing instructions stored in the memory, thereby causing the methods described in the embodiments of this application to be executed. The chip system may be composed of chips or may include chips and other discrete devices.

[0418] The chip system may include input circuits or interfaces for transmitting information or data, and output circuits or interfaces for receiving information or data.

[0419] Optionally, based on the processing method for sensing tasks provided in the embodiments of this application, this application also provides a communication system, which includes the aforementioned access network device and core network device.

[0420] Optionally, according to the processing method for sensing tasks provided in the embodiments of this application, this application also provides a computer program product, which includes: computer program code, which, when run on a computer, causes the computer to execute the various steps or processes executed by the access network device or core network device in any of the foregoing method embodiments.

[0421] Optionally, according to the processing method for sensing tasks provided in the embodiments of this application, this application also provides a computer-readable storage medium storing program code. When the program code is run on a computer, it causes the computer to execute the various steps or processes executed by the access network device or core network device in any of the foregoing method embodiments.

[0422] The computer-readable storage medium may be the aforementioned volatile memory or non-volatile memory, or it may include both volatile memory and non-volatile memory.

[0423] In the embodiments of this application, the terms and English abbreviations are exemplary examples given for ease of description and should not be construed as limiting the application in any way. This application does not preclude the possibility of defining other terms that can achieve the same or similar functions in existing or future agreements.

[0424] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated.

[0425] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0426] It should be understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0427] In summary, the above are merely preferred embodiments of the technical solutions of this application and are not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for processing a perception task, characterized in that, Applied to access network equipment, the processing method includes: Receive a sensing task request, wherein the sensing task request includes information about the sensing task; When the target network device is the access network device, the information of the sensing task is written into the first buffer area of ​​the access network device, and the target network device is used to represent the network device that schedules the sensing task. If the sensing task in the first buffer area meets the first triggering condition, the sensing task in the first buffer area is scheduled and processed to obtain the scheduling result of the sensing task in the first buffer area. The first triggering condition is obtained based on the first parameter, which includes at least one of the following: the number of sensing tasks in the first buffer area, the waiting time, and the urgency.

2. The processing method according to claim 1, characterized in that, The processing method further includes: Receive status information from sensing nodes; The target network device is obtained based on the state information of the sensing node and / or the information of the sensing task.

3. The processing method according to claim 2, characterized in that, The information of the sensing task includes the task type and the sensing area of ​​the sensing task, and the status information of the sensing node includes the node type of the sensing node. The process of obtaining the target network device based on the state information of the sensing node and / or the information of the sensing task includes: If the sensing area of ​​the sensing task is located within the first area and the task type matches the node type, then the target network device is identified as the access network device. If the sensing area of ​​the sensing task includes an area outside the first area, or if the task type does not match the node type, the target network device is determined to be a core network device. The first region is the service area of ​​the access network device.

4. The processing method according to claim 1, characterized in that, The processing method further includes: If the target network device is a core network device, the information of the sensing task is sent to the core network device.

5. The processing method according to claim 4, characterized in that, The processing method further includes: When the target network device is the core network device, the information of the sensing task is written into the second buffer area of ​​the access network device; Sending the sensing task information to the core network device includes: If the sensing task in the second buffer area meets the first triggering condition, the sensing task information of the second buffer area is sent to the core network device.

6. The processing method according to any one of claims 1 to 5, characterized in that, The first triggering condition includes at least one of the following: a first condition, a second condition, and a third condition; Wherein, the first condition is used to indicate that the number of perception tasks in a waiting state is greater than or equal to a first preset threshold. The second condition is used to indicate that the waiting time for the perception task is greater than or equal to a preset time threshold; The third condition is used to indicate that the urgency of the perception task is greater than or equal to a preset urgency threshold.

7. The processing method according to claim 6, characterized in that, When the first triggering condition includes the first condition, the second condition, and the third condition, the priority of the third condition is higher than the priority of the second condition, and the priority of the second condition is higher than the priority of the first condition.

8. The processing method according to any one of claims 1 to 5, characterized in that, The processing method further includes: Based on the waiting time of the sensing task in the corresponding buffer area, a first adjustment amount is obtained, and the first adjustment amount is positively correlated with the waiting time of the sensing task in the corresponding buffer area; Based on the execution environment of the perception task, a second adjustment amount is obtained; Based on the first adjustment amount and / or the second adjustment amount, a target value for the urgency of the perception task in the corresponding buffer area is obtained. The target value for urgency is positively correlated with the urgency of the perception task. The corresponding buffer area is either the first buffer area or the second buffer area.

9. The processing method according to claim 8, characterized in that, The step of obtaining a target value for the urgency of the perception task based on the first adjustment amount and / or the second adjustment amount includes: Based on the initial value of the urgency of the perception task, the first adjustment amount, and / or the second adjustment amount, the target value of the urgency of the perception task is obtained. The initial value of the urgency of the perception task is obtained based on the task type of the perception task.

10. The processing method according to any one of claims 1 to 5, characterized in that, The process of scheduling the sensing tasks in the first buffer area to obtain the scheduling results of the sensing tasks in the first buffer area includes: The first neural network model is used to perform the scheduling process on the perception tasks in the first buffer area to obtain the resource allocation results of the perception tasks in the first buffer area.

11. A method for processing a perception task, characterized in that, Applied to core network equipment, the processing method includes: When the target network device is the core network device, information about the sensing task is received from the access network device, wherein the target network device is used to represent the network device that schedules the sensing task. The information of the sensing task is written into the third buffer area of ​​the core network device. If the sensing task in the third buffer area meets the second triggering condition, the sensing task in the third buffer area is scheduled to obtain the scheduling result of the sensing task in the third buffer area. The second triggering condition is obtained based on the second parameter, which includes at least one of the following: the number of sensing tasks in the third buffer area, the waiting time, and the urgency.

12. The processing method according to claim 11, characterized in that, The target network device is obtained by the access network device based on the status information of the sensing node and / or the information of the sensing task.

13. The processing method according to claim 12, characterized in that, The information of the sensing task includes the task type and the sensing area of ​​the sensing task, and the status information of the sensing node includes the node type of the sensing node. If the sensing area of ​​the sensing task is located within the first area and the task type matches the node type, then the target network device is the access network device. In the case where the sensing area of ​​the sensing task includes an area outside the first area, or in the case where the task type does not match the node type, the target network device is the core network device; The first region is the service area of ​​the access network device.

14. The processing method according to claim 11, characterized in that, The second triggering condition includes at least one of the following: the fourth condition, the second condition, and the third condition; The fourth condition indicates that the number of sensing tasks in a waiting state is greater than or equal to the second preset threshold. The second condition is used to indicate that the waiting time for the perception task is greater than or equal to a preset time threshold; The third condition is used to indicate that the urgency of the perception task is greater than or equal to a preset urgency threshold.

15. The processing method according to claim 14, characterized in that, When the second triggering condition includes the fourth condition, the second condition, and the third condition, the third condition has a higher priority than the second condition, and the second condition has a higher priority than the fourth condition.

16. The processing method according to any one of claims 11 to 15, characterized in that, The processing method further includes: Based on the duration of the perception task writing to the third buffer area, a first adjustment amount is obtained, and the first adjustment amount is positively correlated with the duration of the perception task writing to the third buffer area. Based on the execution environment of the perception task, a second adjustment amount is obtained; Based on the first adjustment amount and / or the second adjustment amount, a target value for the urgency of the perception task in the third buffer region is obtained, wherein the target value for urgency is positively correlated with the urgency of the perception task.

17. The processing method according to claim 16, characterized in that, The step of obtaining a target value for the urgency of the perception task based on the first adjustment amount and / or the second adjustment amount includes: Based on the initial value of the urgency of the perception task, the first adjustment amount, and / or the second adjustment amount, the target value of the urgency of the perception task in the third buffer area is obtained. The initial value of the urgency of the perception task is obtained based on the task type of the perception task.

18. The processing method according to any one of claims 11 to 15, characterized in that, The receiving of information from the sensing task of the access network device includes: When the sensing task in the second buffer area of ​​the access network device meets the first triggering condition, information from the sensing task of the access network device is received. The first triggering condition is obtained based on the first parameter, which includes at least one of the following: the number of sensing tasks in the first buffer area, the waiting time, and the urgency.

19. The processing method according to claim 18, characterized in that, The first triggering condition includes at least one of the following: a first condition, a second condition, and a third condition; Wherein, the first condition is used to indicate that the number of perception tasks in a waiting state is greater than or equal to a first preset threshold. The second condition is used to indicate that the waiting time for the perception task is greater than or equal to a preset time threshold; The third condition is used to indicate that the urgency of the perception task is greater than or equal to a preset urgency threshold.

20. The processing method according to claim 19, characterized in that, When the first triggering condition includes the first condition, the second condition, and the third condition, the priority of the third condition is higher than the priority of the second condition, and the priority of the second condition is higher than the priority of the first condition.

21. The processing method according to claim 11, characterized in that, The processing method further includes: Receive status information from the sensing nodes of the access network device.

22. The processing method according to any one of claims 11 to 15, characterized in that, The process of scheduling the sensing tasks in the third buffer region to obtain the scheduling results of the sensing tasks in the third buffer region includes: The second neural network model is used to perform the scheduling process on the perception tasks in the third buffer area to obtain the resource allocation results of the perception tasks in the third buffer area.

23. An access network device, characterized in that, The device includes at least one processor coupled to a memory for storing programs or instructions, the processor executing the programs or instructions to cause the access network device to perform the processing method as described in any one of claims 1 to 10.

24. A core network device, characterized in that, It includes at least one processor coupled to a memory for storing programs or instructions, the processor executing the programs or instructions to cause the core network device to perform the processing method as described in any one of claims 11 to 22.

25. A communication system, characterized in that, include: Access network equipment and core network equipment; The access network device is used to perform the processing method as described in any one of claims 1 to 10; The core network equipment is used to perform the processing method as described in any one of claims 11 to 22.

26. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by an electronic device, causes the electronic device to perform the processing method as claimed in any one of claims 1 to 10, or any one of claims 11 to 22.

27. A chip system, characterized in that, The chip system includes one or more processors, which are configured to retrieve and execute instructions stored in memory to perform the processing method as described in any one of claims 1 to 10, or any one of claims 11 to 22.

Images