Communication method and related apparatus

Abstract

A communication method and a related apparatus, which relate to the technical field of communications. The method can be applied to a computing node, and comprises: receiving priority indication information of a computing task to be processed, wherein the priority indication information indicates the processing priority of a computing node for the computing task, and the priority indication information is obtained on the basis of at least one of a task requirement of the computing task and subscription data of a terminal device; and on the basis of the priority indication information, scheduling the computing task to a first position of a first queue or a second queue of the computing node, or directly scheduling the computing task to a third queue, wherein the first queue is one of a plurality of different priority queues of the computing node, the second queue is a queue in the computing node that waits to access a coprocessor resource, and the third queue is a queue in a coprocessor in the computing node. The present application can ensure the quality of service for important users or computing tasks requiring a low latency.

Description

Communication method and related apparatus

[0001] The present application claims priority to the Chinese patent application No. 202411389142.1, filed on September 30, 2024, entitled "Communication method and related apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, and in particular to a communication method and related apparatus. BACKGROUND

[0003] With the development of technology, computing nodes located in a core network in a wireless network can provide computing services for terminals to complete various computing tasks, such as image rendering, target recognition, text-to-image, etc. The computing nodes can include a central processing unit (CPU) and various co-processors such as a graphics processing unit (GPU) and a neural network processing unit (NPU).

[0004] In some computing nodes, a co-processor such as a GPU must be connected to a CPU-based host through a high-speed serial computer expansion bus standard (per ipheral component interconnect express, PCIe) bus to operate. When the number of computing tasks received by the CPU is greater than the processing capability of the GPU, the computing tasks will be queued in a queue in the CPU, waiting for subsequent transmission to the GPU through the PCIe bus for parallel computing. Therefore, in the process of processing some computing tasks, a large amount of time delay is consumed in the queue waiting in the CPU, and the quality of service (QoS) of these computing tasks cannot be guaranteed. SUMMARY

[0005] Embodiments of the present application provide a communication method and related apparatus, which can guarantee the quality of service of important users or computing tasks requiring low latency.

[0006] In a first aspect, an embodiment of the present application provides a communication method applied to a computing node. It can be understood that the method can be executed by a communication device, which can be a computing node or a chip (system) or circuit for the computing node, and the present application does not limit the same. The method comprises: receiving priority indication information of a to-be-processed computing task, the priority indication information indicating a processing priority of the computing task by the computing node; the priority indication information is obtained based on at least one of task requirements of the computing task and subscription data of a terminal device; based on the priority indication information, the computing task is scheduled to a first position of a first queue or a second queue of the computing node, or the computing task is directly scheduled to a third queue, the first queue being one of a plurality of different priority queues of the computing node, the second queue being a queue waiting for access to a coprocessor resource in the computing node, and the third queue being a queue in a coprocessor in the computing node.

[0007] The computing node can be used to provide a computing service and execute a computing task, and can include at least one of the following types: an access network device, a core network device, or a MEC platform, etc. The computing node can include a central processing unit and a coprocessor, which can also be referred to as an acceleration card, etc. The processing priority of the computing node for various computing tasks can include multiple priorities, for example, can include three priorities of "high", "medium", and "low", and the present application does not limit the same.

[0008] In the present application, since the priority indication information is obtained based on at least one of the task requirements of the computing task and the subscription data of the terminal device, the priority indication information is related to the task requirements of the computing task and the importance of a corresponding user of the terminal device. Based on the priority indication information, the computing task is scheduled to a corresponding queue or a corresponding position in the CPU or the coprocessor, so that the time length of the computing task in the coprocessor queue matches the processing priority, thereby realizing the priority processing of the computing task requiring a low latency and / or an important user, meeting the requirements of the computing task of these users, and guaranteeing the service quality of these computing tasks.

[0009] In a possible implementation, the computing node is separately arranged from a user plane network element; and the receiving of the priority indication information of the to-be-processed computing task comprises:

[0010] receiving a first data packet from the user plane network element, the first data packet carrying marking information including the priority indication information, and the marking information being obtained based on a computing service quality (QoS) policy corresponding to the computing task.

[0011] The first data message can be a marked data message. The computing node can mark the data message based on a computing QoS policy corresponding to the computing task to obtain the first data message and then send the first data message to the computing node.

[0012] In the embodiment of the present application, in the scenario where the computing node and the user plane network element are separately arranged, the user plane network element obtains the marked data message (i.e., the first data message) based on a computing QoS policy corresponding to the computing task, and indicates the priority indication information of the computing task through the marking information, thereby indicating the processing priority of the computing task. The priority indication information can be conveniently sent to the computing node by using the first data message, which is simple and easy to implement.

[0013] In a possible implementation, the computing node and the user plane network element are arranged together; and the receiving of the priority indication information of the computing task includes:

[0014] receiving the computing QoS policy corresponding to the computing task from the control plane network element, the computing QoS policy including the priority indication information of the computing task and a computing delay requirement, the computing QoS policy being obtained based on at least one of a task requirement of the computing task and subscription data of the terminal device.

[0015] In this embodiment, in the scenario where the computing node and the user plane network element are arranged together, the user plane network element and the computing node receive the computing QoS policy corresponding to the computing task sent by the control plane network element, and the computing node can obtain the priority indication information of the computing task, without the need for the user plane node to send the first data message to the computing node, thereby reducing the transmission delay.

[0016] In a possible implementation, the scheduling of the computing task to the first position of the first queue or the second queue of the computing node or the direct scheduling of the computing task to the third queue based on the priority indication information includes:

[0017] In a case where the priority indication information indicates that the processing priority of the computing task is the highest priority among a plurality of processing priorities, the computing task is directly scheduled to the third queue.

[0018] In a case where the priority indication information indicates that the processing priority of the computing task is not the highest priority among the plurality of processing priorities, the computing task is scheduled to the first position of the first queue or the second queue based on the priority indication information, the first queue and the second queue being queues in a central processing unit (CPU) in the computing node.

[0019] The first queue is a queue in a central processing unit (CPU) in the computing node, and the first queue is a priority queue in a plurality of different priority queues. Specifically, the first queue is a priority queue corresponding to the priority indication information. For example, if the priority indication information indicates that the processing priority of the computing task is a high priority, the first queue can be a high priority queue in the plurality of different priority queues in the CPU. The second queue is a queue in the CPU in the computing node. At this time, the queues in the CPU in the computing node can not be prioritized. Alternatively, the queues in the CPU in the computing node waiting to access the coprocessor resource only include the second queue. The first position is a position in the second queue corresponding to the priority indication information. For example, if the priority indication information indicates that the processing priority of the computing task is a high priority, the first position is closer to a de-queue position.

[0020] In this embodiment, in the case where the computing node supports directly scheduling the computing task to the queue in the coprocessor, if the processing priority of the computing task to be processed is the highest priority, the computing task can be directly scheduled to the queue in the coprocessor, without queuing in the queue in the CPU, so as to ensure that the computing task with the highest priority can be processed preferentially, and the quality of service of the computing task is guaranteed. In the case where the priority indication information indicates that the processing priority of the computing task is not the highest priority, the computing task is scheduled to the corresponding priority queue in the CPU or to the corresponding position in the queue in the CPU based on the high and low of the processing priority of the computing task, so that the computing task waits for a period of time before entering the coprocessor, and the order of processing the computing task and the computing time delay are matched with the processing priority, so as to guarantee the quality of service of the computing task with a higher priority as much as possible.

[0021] In a possible implementation, the CPU in the computing node includes a plurality of priority queues, and the scheduling of the computing task to the first queue based on the priority indication information includes:

[0022] The computing task is scheduled to the first queue based on the priority indication information, and the higher the priority level of the processing priority of the computing task indicated by the priority indication information, the higher the priority level of the first queue.

[0023] In the embodiment, in the case that the CPU of the computing node comprises a plurality of priority queues, the computing task is scheduled to a certain priority queue (i.e., the first queue) corresponding to the priority indication information of the computing task in the CPU based on the priority indication information of the computing task, so as to ensure that the queuing waiting time of the computing task in the queue of the CPU matches the processing priority of the computing task, and the higher the processing priority of the computing task is, the shorter the waiting time is, thereby realizing the priority processing of the computing task of high task demand and / or important user, meeting the demand of the computing task, and guaranteeing the service quality of the computing task.

[0024] In a possible implementation, the queue waiting for accessing the coprocessor resource in the CPU of the computing node comprises one queue, and the scheduling of the computing task to the first position of the second queue based on the priority indication information comprises:

[0025] The scheduling of the computing task to the first position of the second queue based on the priority indication information, the higher the priority level of the processing priority of the computing task indicated by the priority indication information is, the closer the first position is to the de-queue position.

[0026] In the embodiment, the queue waiting for accessing the coprocessor resource in the CPU of the computing node comprises one queue, and the computing task is scheduled to a position corresponding to the processing priority in the queue based on the priority indication information without distinguishing the priority, so as to realize the scheduling of the computing task with higher processing priority to a position closer to the de-queue position, thereby reducing the queuing waiting time of the computing task in the queue of the CPU, ensuring that the computing task can be processed as soon as possible, and guaranteeing the service quality of the computing task with higher time delay requirement or higher user importance.

[0027] In a possible implementation, the task demand of the computing task comprises at least one of the following: end-to-end time delay demand, demand bandwidth, and computing resource type.

[0028] In a possible implementation, the subscription data of the terminal device comprises at least one of the following: user subscription type and service guarantee level.

[0029] In a second aspect, an embodiment of the present application provides a communication method, which can be executed by a communication device, the communication device can be a control plane network element, or a chip (system) or circuit for the control plane network element, and the method comprises:

[0030] generating a computing quality of service (QoS) policy corresponding to the computing task, the computing QoS policy comprising priority indication information of the computing task, the computing QoS policy being obtained based on at least one of task demand of the computing task and subscription data of a terminal device;

[0031] sending the computing QoS policy.

[0032] In a possible implementation, the task requirement of the computing task includes at least one of the following: an end-to-end latency requirement of the computing task, a required bandwidth, a computing resource type.

[0033] In a possible implementation, the subscription data of the terminal device includes at least one of the following: a user subscription type, a service assurance level.

[0034] In the embodiments of the present application, the control plane network element generates the computing QoS policy based on the subscription data of the terminal device and / or the task requirement of the computing task, and sends the computing QoS policy to the user plane network element. In the scenario where the computing node and the user plane network element are separately arranged, the user plane network element obtains the marked data packet (i.e., the first data packet) based on the computing QoS policy and sends the first data packet, and can conveniently pass the priority indication information included in the first data packet to the computing node. In the scenario where the computing node and the user plane network element are arranged together, the computing node can directly obtain the priority indication information. In this way, the processing priority of the computing task is determined by using the task requirement of the computing task and the importance of the user. The computing node subsequently processes the computing task according to the processing priority, i.e., selects to schedule the computing task to a coprocessor, to a certain priority queue of the CPU of the computing node corresponding to the priority indication information, or to a certain position of the second queue of the CPU of the computing node corresponding to the priority indication information, so that the computing task of a user with high importance and / or a computing task with high requirement can be processed preferentially, the requirement of these computing tasks is met, and the quality of service of these computing tasks is guaranteed.

[0035] In a third aspect, an embodiment of the present application provides a communication method, which can be executed by a communication apparatus. The communication apparatus can be a user plane network element, or a chip (system) or circuit for the user plane network element, which is not limited in the present application. The method includes:

[0036] receiving a computing quality of service (QoS) policy corresponding to a computing task from a control plane network element, the computing QoS policy including priority indication information of the computing task, the computing QoS policy being obtained based on at least one of a task requirement of the computing task and subscription data of a terminal device;

[0037] sending a first data packet, the marking information carried by the first data packet including the priority indication information of the computing task, the marking information being generated based on the computing QoS policy.

[0038] In the embodiments of the present application, in the scenario where the computing node and the user plane network element are separately arranged, the user plane network element obtains the marked data packet (i.e., the first data packet) based on the computing QoS policy from the control plane network element and sends, and the priority indication information included therein can be conveniently delivered to the computing node. In the scenario where the computing node and the user plane network element are arranged together, the computing node can directly obtain the computing QoS policy from the control plane network element and obtain the priority indication information. Since the computing QoS policy is obtained based on at least one of the task demand of the computing task and the subscription data of the terminal device, the processing priority of the computing task can be determined by using the task demand of the computing task and the importance of the user. The computing node subsequently processes the computing task according to the high and low of the processing priority, i.e., selects to schedule the computing task to the co-processor, or to a certain priority queue corresponding to the priority indication information in the CPU of the computing node, or to a certain position corresponding to the priority indication information in the second queue of the CPU of the computing node, so that the computing task of the high task demand and / or important user can be processed preferentially, the demand of these computing tasks is met, and the quality of service of these tasks is guaranteed.

[0039] In a fourth aspect, the embodiments of the present application provide a communication method, which can be executed by a communication device. The communication device can be a terminal device, or a chip (system) or circuit for the terminal device, which is not limited in the present application. The method comprises:

[0040] sending a computing task request, wherein the computing task request comprises a task demand of a computing task, and the task demand is used to generate a computing QoS policy corresponding to the computing task, and the computing QoS policy comprises priority indication information of the computing task.

[0041] In a fifth aspect, the embodiments of the present application provide a communication device, which comprises units for executing the method in the first aspect and any possible implementation manner.

[0042] In a possible design, the device comprises:

[0043] a communication unit, configured to receive priority indication information of a computing task to be processed, wherein the priority indication information indicates a processing priority of the computing node for the computing task, and the priority indication information is obtained based on at least one of a task demand of the computing task and subscription data of the computing node;

[0044] In a possible design, the device further comprises:

[0045] a processing unit, configured to schedule the computing task to a first position of a first queue or a second queue of the computing node, or directly to a third queue, based on the priority indication information, the first queue being one of a plurality of different priority queues of the computing node, the second queue being a queue of the computing node waiting for accessing a co-processor resource, and the third queue being a queue in a co-processor of the computing node.

[0046] The processing unit and the communication unit according to the fifth aspect and any possible implementation thereof perform the steps as described with respect to the first aspect and corresponding implementation.

[0047] The technical effects brought about by the fifth aspect and any possible implementation thereof can be referred to the introduction of the technical effects of the first aspect and corresponding implementation.

[0048] According to a sixth aspect, an embodiment of the present application provides a communication apparatus, which comprises units for performing the method according to the second aspect and any possible implementation thereof.

[0049] a communication unit, configured to send a computing quality of service, QoS, policy corresponding to the computing task, the computing QoS policy comprising priority indication information of the computing task, the computing QoS policy being obtained based on at least one of a task requirement of the computing task and subscription data of a terminal device;

[0050] In a possible design, the apparatus includes:

[0051] a processing unit, configured to generate the computing QoS policy.

[0052] The processing unit and the communication unit according to the sixth aspect and any possible implementation thereof perform the steps as described with respect to the second aspect and corresponding implementation.

[0053] The technical effects brought about by the sixth aspect and any possible implementation thereof can be referred to the introduction of the technical effects of the third aspect and corresponding implementation.

[0054] According to a seventh aspect, an embodiment of the present application provides a communication apparatus, which comprises units for performing the method according to the third aspect and any possible implementation thereof.

[0055] a communication unit, configured to receive a computing quality of service, QoS, policy corresponding to the computing task from a control plane network element, the computing QoS policy comprising priority indication information of the computing task, the computing QoS policy being obtained based on at least one of a task requirement of the computing task and subscription data of a terminal device;

[0056] The communication unit is further configured to send a first data packet, wherein the first data packet carries marking information including priority indication information of the computing task, and the marking information is generated based on the computing QoS policy.

[0057] In a possible design of the apparatus, the apparatus includes:

[0058] The processing unit is configured to generate the first data packet.

[0059] The processing unit and the communication unit described in relation to the seventh aspect and any possible implementation perform the steps as described in relation to the third aspect and corresponding implementation.

[0060] The processing unit and the communication unit described in relation to the seventh aspect and any possible implementation perform the steps as described in relation to the third aspect and corresponding implementation.

[0061] In an eighth aspect, an embodiment of the present application provides a communication apparatus, which includes units configured to perform the method described in relation to the fourth aspect and any possible implementation.

[0062] The communication unit is configured to send a computing task request, wherein the computing task request includes task requirements of a computing task, the task requirements are used to generate a computing QoS policy corresponding to the computing task, and the computing QoS policy includes priority indication information of the computing task.

[0063] In a possible design of the apparatus, the apparatus includes:

[0064] The processing unit is configured to generate the computing task request.

[0065] The processing unit and the communication unit described in relation to the eighth aspect and any possible implementation perform the steps as described in relation to the fourth aspect and corresponding implementation.

[0066] The processing unit and the communication unit described in relation to the eighth aspect and any possible implementation perform the steps as described in relation to the fourth aspect and corresponding implementation.

[0067] Optionally, in the communication apparatus described in any of the fifth aspect to the eighth aspect and any possible implementation,

[0068] In an implementation, the communication apparatus is a communication device. When the communication apparatus is a communication device, the communication unit can be a transceiver, or an input / output interface; and the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0069] In another implementation, the communication apparatus is a chip (system) or circuit for a communication device. When the communication apparatus is a chip (system) or circuit for a communication device, the communication unit can be a communication interface (input / output interface), interface circuit, output circuit, input circuit, pin or related circuit on the chip (system) or circuit; the processing unit can be at least one processor, processing circuit or logic circuit.

[0070] In a ninth aspect, an embodiment of the present application provides a communication apparatus, which comprises a processor. The processor is coupled with a memory and is configured to execute instructions in the memory to implement the method in any one of the first aspect to the fourth aspect and any possible implementation.

[0071] In a tenth aspect, an embodiment of the present application provides a communication apparatus, which comprises a logic circuit and a communication interface. The communication interface is configured to receive information or send information; the logic circuit is configured to receive information or send information through the communication interface, so that the communication apparatus implements the method in any one of the first aspect to the fourth aspect and any possible implementation.

[0072] In an eleventh aspect, an embodiment of the present application provides a computer readable storage medium, which is configured to store a computer program (also referred to as code or instructions); when the computer program is run on a computer, the method in any one of the first aspect to the fourth aspect and any possible implementation is implemented.

[0073] In a twelfth aspect, an embodiment of the present application provides a computer program product, which comprises a computer program (also referred to as code or instructions); when the computer program is run, the method in any one of the first aspect to the fourth aspect and any possible implementation is implemented.

[0074] In a thirteenth aspect, an embodiment of the present application provides a chip, which comprises a processor configured to execute instructions; when the processor executes the instructions, the chip implements the method in any one of the first aspect to the fourth aspect and any possible implementation. Optionally, the chip further comprises a communication interface configured to receive a signal or send a signal.

[0075] In a fourteenth aspect, an embodiment of the present application provides a communication system, which comprises at least one communication apparatus as described in any one of the fifth aspect to the eighth aspect, or the communication apparatus as described in the ninth aspect, or the communication apparatus as described in the tenth aspect, or the chip as described in the thirteenth aspect.

[0076] In a fifteenth aspect, an embodiment of the present application provides a communication system, the communication system comprising at least one of a computing node, a control plane network element, a user plane network element and a terminal device, the computing node being configured to perform the method of the first aspect and any possible implementation thereof, the control plane network element being configured to perform the method of the second aspect and any possible implementation thereof, the user plane network element being configured to perform the method of the third aspect and any possible implementation thereof, and the terminal device being configured to perform the method of the fourth aspect and any possible implementation thereof.

[0077] Further, in the process of performing the method of any of the first aspect to the fourth aspect and any possible implementation thereof, the process of sending information and / or receiving information and the like in the above method can be understood as the process of outputting information by the processor and / or the process of receiving input information by the processor. When outputting information, the processor can output the information to the transceiver (or the communication interface or the sending module) so as to be transmitted by the transceiver. After being output by the processor, the information can also need to be processed further before reaching the transceiver. Similarly, when the processor receives input information, the transceiver (or the communication interface or the sending module) receives the information and inputs it to the processor. Furthermore, after the transceiver receives the information, the information can need to be processed further before being input to the processor.

[0078] Based on the above principle, for example, the sending information mentioned in the foregoing method can be understood as the processor outputting information. For another example, the receiving information can be understood as the processor receiving input information.

[0079] Optionally, for the transmission, sending and receiving operations and the like involved by the processor, if no special description is made, or if it is not contrary to the actual role or inherent logic thereof in the related description, it can be more generally understood as the processor outputting and receiving, inputting and the like.

[0080] Optionally, in the process of performing the method of any of the first aspect to the fourth aspect and any possible implementation thereof, the processor can be a processor specially configured to perform the method, or can be a processor such as a general processor which performs the method by executing computer instructions in a memory. The memory can be a non-transitory memory such as a Read Only Memory (ROM), which can be integrated on the same chip as the processor, or can be respectively arranged on different chips. The type of the memory and the arrangement mode of the memory and the processor are not limited in the embodiments of the present application.

[0081] In a possible implementation, the at least one memory is located outside the apparatus.

[0082] In another possible implementation, the at least one memory is located inside the apparatus.

[0083] In yet another possible implementation, part of the at least one memory is located inside the apparatus, and another part of the at least one memory is located outside the apparatus.

[0084] In the present application, the processor and the memory can also be integrated into one device, that is, the processor and the memory can also be integrated together.

[0085] In the embodiments of the present application, the terminal device initiates a computing request of a computing task, a control plane network element generates a computing QoS policy based on subscription data of the terminal device and / or task requirements of the computing task, and sends the computing QoS policy to a user plane network element. In a scenario where a computing node and the user plane network element are separately arranged, the user plane network element obtains a marked data packet (i.e., a first data packet) based on the computing QoS policy and sends the marked data packet, and can conveniently pass priority indication information included in the marked data packet to the computing node. In a scenario where the computing node and the user plane network element are arranged together, the computing node can directly obtain the priority indication information. In this way, the processing priority of the computing task is determined by using the task requirements of the computing task and the importance of the user. The computing node processes the computing task according to the processing priority, that is, selects to schedule the computing task to a coprocessor, or to a certain priority queue of a CPU of the computing node corresponding to the priority indication information, or to a certain position of a second queue of the CPU of the computing node corresponding to the priority indication information, so that the computing task of a high task requirement and / or an important user can be processed preferentially, the requirements of these computing tasks are met, and the quality of service of these tasks is guaranteed. BRIEF DESCRIPTION OF DRAWINGS

[0086] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. Obviously, the drawings described below are only some of the embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0087] FIG. 1 is a schematic diagram of a 5G network architecture;

[0088] FIG. 2 is a flowchart of a communication method provided by the embodiments of the present application;

[0089] FIG. 3a is a process diagram of scheduling a computing task provided by the embodiments of the present application;

[0090] FIG. 3b is another process diagram for scheduling a computing task according to an embodiment of the present application;

[0091] FIG. 4a is yet another process diagram for scheduling a computing task according to an embodiment of the present application;

[0092] FIG. 4b is yet another process diagram for scheduling a computing task according to an embodiment of the present application;

[0093] FIG. 5 is another flow diagram of a communication method according to an embodiment of the present application;

[0094] FIG. 6 is yet another flow diagram of a communication method according to an embodiment of the present application;

[0095] FIG. 7 is a structure diagram of a communication apparatus according to an embodiment of the present application;

[0096] FIG. 8 is a structure diagram of a communication apparatus according to an embodiment of the present application;

[0097] FIG. 9 is a structure diagram of a chip according to an embodiment of the present application. DETAILED DESCRIPTION

[0098] In order to make the objects, technical solutions and advantages of the present application clearer, the embodiments of the present application will be described below with reference to the drawings.

[0099] The terms "first" and "second" and the like in the specification of the present application, claims, and drawings are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device, etc. that includes a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or device, etc.

[0100] In this document, "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood by those skilled in the art that the terms and / or descriptions used in various embodiments of the present application are consistent with each other, and can be mutually referred to, unless there is a special statement and a logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0101] It should be understood that in the present application, "at least one" refers to one or more, "multiple" refers to two or more, "at least two" refers to two or three and three or more, and "and / or" is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0102] It should be noted that in the present application, "indication" can include direct indication, indirect indication, display indication, and implicit indication. When describing that certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.

[0103] In the present application, the information indicated by the indication information is referred to as the to-be-indicated information. In the specific implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or the index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, the protocol stipulates), thereby reducing the indication overhead to a certain extent. The to-be-indicated information can be sent as a whole, or can be sent separately into multiple sub-information, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited by the present application. The sending period and / or sending time of these sub-information can be pre-defined, for example, pre-defined according to the protocol, or can be configured by the transmitting end device by sending configuration information to the receiving end device.

[0104] It should be noted that in the present application, "sending" can be understood as "output", and "receiving" can be understood as "input". "Sending information to A" means that A is the destination of the information transmission, and A is not limited to direct sending on the air interface. "Sending information to A" includes directly sending information to A, and also includes indirectly sending information to A through a transmitter. Therefore, "sending information to A" can also be understood as "outputting information to A". Similarly, "receiving information from A" means that the source of the information is A, which includes directly receiving information from A, and also includes indirectly receiving information from A through a receiver. Therefore, "receiving information from A" can also be understood as "inputting information from A".

[0105] The method provided by the present application can be applied to various communication systems, for example, can be an internet of things (IoT) system, a narrow band internet of things (NB-IoT) system, a long term evolution (LTE) system, and also can be a 5th-generation (5G) communication system, and a new communication system (such as 6G) that appears in future communication development. In addition, the method provided by the present application can also be applied to fixed network and wireless local area network (WLAN) systems, such as wireless fidelity (Wi-Fi) and the like.

[0106] The technical solutions provided in the application can also be applied to machine type communication (MTC), long term evolution-machine (LTE-M), device-to-device (D2D) network, machine to machine (M2M) network, internet of things (IoT) network, industrial internet, or other networks. The IoT network may, for example, include a vehicle internet. In the vehicle internet system, the communication modes are collectively referred to as vehicle-to-everything (V2X, X may represent any thing), for example, the V2X may include vehicle-to-vehicle (V2V) communication, vehicle-to-infrastructure (V2I) communication, vehicle-to-pedestrian (V2P) communication, or vehicle-to-network (V2N) communication, and the like.

[0107] For example, the network architecture related to the application will be described below by taking a 5G communication system as an example.

[0108] The 3rd generation partnership project (3GPP) standard group formulates a next-generation mobile communication network architecture, referred to as a 5G network architecture. FIG. 1 is a schematic diagram of a 5G network architecture, which includes a terminal device part, a network device part, and a data network (DN) part.

[0109] The terminal device part generally includes a user equipment (UE) and the like. In a wireless network, the UE is a device with wireless transceiving function, which can communicate with one or more core network (CN) network elements through an access network element in a radio access network (RAN).

[0110] The user equipment can also be referred to as an access terminal, terminal, user unit, user station, mobile station, mobile, remote station, remote terminal, mobile device, user terminal, user agent, user device, etc. The user equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water (such as ships, etc.); can also be deployed in the air (such as airplanes, balloons, and satellites, etc.). The user equipment can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a smart phone, a mobile phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), etc. Alternatively, the user equipment can also be a handheld device, a computing device, or other device with wireless communication function connected to a wireless modem, a vehicle-mounted device, a wearable device, a drone device, or a terminal in Internet of Things (also referred to as Internet of Things device), a terminal in Internet of Vehicles, a terminal in 5G network and future network, a relay user equipment, a mobile termination (MT), or a terminal in future evolved public land mobile network (PLMN), etc. Among them, the relay user equipment can be, for example, a 5G residential gateway (RG). For example, the user equipment can be a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The embodiments of the present application do not limit the type or category of terminal device, etc.

[0111] The network device part includes a network exposure function (NEF), a network repository function (NRF), a policy control function (PCF), a unified data management (UDM), an authentication server function (AUSF), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), an access network (AN), a network slice selection function (NSSF), and the like. Among the above network devices, the part except the access network part can be referred to as the core network part. Among them, the UDM can be used to manage the subscription data of the terminal device.

[0112] The core network part includes a user plane function and a control plane function. The user plane function is mainly responsible for forwarding data packets, quality of service (QoS) control, charging information statistics, and the like. The control plane function is mainly responsible for service process interaction, issuing data packet forwarding policies and QoS control policies to the user plane function, and the like. In this application, the control plane network element can be a control plane function network element, and the user plane network element can be a user plane function network element.

[0113] The data network DN, which can also be referred to as a packet data network (PDN), can be deployed outside the operator network, for example, a third-party network. For example, the operator network can access multiple DNs, and multiple services can be deployed on the DN, thereby providing data and / or voice services for the UE. The third party mentioned above can be a service provider other than the operator network and the UE, which can provide other data and / or voice services for the UE. The specific form of the third party can be determined according to the actual application scenario, which is not limited here.

[0114] An application function (AF) can or can not be affiliated with the operator network. Typically, however, the AF is affiliated with a third party and not the operator network, but has a contractual relationship with the operator network. The AF is a functional network element that provides various service functions, and can support functions for influencing data routing through applications, and access network exposure function (NEF), interacting with a policy framework for policy control, etc.

[0115] For example, network functions in the operator network are briefly introduced as follows.

[0116] The RAN is a subnetwork of the operator network, and is an implementation system between service nodes (or network functions) in the operator network and a UE. To access the operator network, the UE first accesses the RAN, and then connects to the service nodes in the operator network through the RAN, that is, the RAN exists between the UE and the core network part, and provides a communication connection therebetween. The RAN in the embodiments of the present application can refer to the access network itself, or can refer to an access network element, which are not distinguished here. The access network element is a device that provides wireless communication functions for the UE, and can also be referred to as an access network device or an AN device, etc. The access network element includes but is not limited to: a next generation base station or a next generation node B (gNB) in a 5G system, an evolved node B (eNB) in an LTE system, a radio network controller (RNC), a node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home node B (HNB), a building base band unit (BBU), a transmit receive point (TRP), a transmission point (TP), a pico, a mobile switching center, or a network device in a future network, etc. It can be understood that the specific type of the access network device is not limited in the present application. In systems using different wireless access technologies, the names of devices with access network device functions can be different.

[0117] Optionally, in some deployments of the access device, the access device can include a centralized unit (CU) and a distributed unit (DU), etc.

[0118] The above 5G network architecture supports multi-access edge computing (MEC), which is mainly achieved by introducing a service platform function on a mobile base station (such as the RAN part in the above 5G network architecture), so that service applications can be deployed at the edge of the mobile network.

[0119] The MEC platform can be deployed at the wireless access network side (which can be referred to as an access network side MEC platform), for example, the MEC platform can be deployed after a single base station node or after a convergence node of multiple base stations, and the present application does not limit this. The MEC platform can also be deployed at the core network side (which can be referred to as a core network side MEC platform). The specific deployment mode can refer to known technologies, and will not be described in detail here.

[0120] It should be noted that the above network elements or functional entities can be network elements in a hardware device, software functions running on a dedicated hardware, or virtualized functions instantiated on a platform (such as a cloud platform). Optionally, the above network elements or functional entities can be implemented by one device, or can be implemented by multiple devices together, or can be different functional modules in one device, and the embodiments of the present application do not limit this.

[0121] In order to more clearly describe the scheme of the present application, the following first explains several terms involved in the present application.

[0122] Computing task: in the present application, the computing task includes but is not limited to, for example: image rendering enhancement, Al inference, target detection, target recognition, target classification, behavior prediction, action decision in control system, etc. The present application includes but is not limited to this. The above computing task can be a computing task in a third-party application service such as VR, AR, cloud game, etc. In the present application, the computing task can also be referred to as task, etc.

[0123] Computing node: a node for providing computing services and executing computing tasks. For example, the computing node can include at least one of the following types: an access network device, a core network device, or an MEC platform, etc. Specifically, it can include a central processing unit (CPU) in the above devices, and can also include a coprocessor such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), a data processing unit (DPU), etc. The present application does not limit this.

[0124] Please refer to Fig. 2, which is a flowchart of a communication method provided by the embodiments of the present application. The communication method is applied to the technical field of communication. It can be understood that the communication method can be executed by a communication device, which can be a computing node, a control plane network element, a user plane network element, or a terminal device, or a chip (system) or circuit used in these devices, and the present application does not limit the same. The communication method includes but is not limited to the following steps:

[0125] S201: The computing node receives priority indication information of a to-be-processed computing task.

[0126] The priority indication information is used to indicate the processing priority of the computing task by the computing node. It can be understood that the processing priority of the computing task by the computing node can include multiple priorities, for example, the processing priority can include high priority, medium priority, and low priority. Alternatively, the processing priority can include first priority, second priority, etc. The present application does not limit the specific number and name of the processing priority. Correspondingly, the priority indication information of the to-be-processed computing task can indicate that the processing priority of the computing task is a certain priority among the multiple priorities. For example, when the priority indication information is represented by the number "1, 2, 3…", if the priority indication information is 1, it can indicate that the processing priority of the computing task by the computing node is high priority, if the priority indication information is 2, it can indicate that the processing priority of the computing task by the computing node is medium priority, and so on. For example, when the priority indication information is represented by the English word "high, middle, low…", if the priority indication information is middle, it can indicate that the processing priority of the computing task by the computing node is medium priority, if the priority indication information is low, it can indicate that the processing priority of the computing task by the computing node is low priority, and so on.

[0127] The priority indication information can be obtained based on at least one of the task requirement of the computing task and the subscription data of the terminal device. Here, the terminal device is the terminal device that initiates the request of the computing task. The task requirement of the computing task can include the computing requirement of executing the computing task, specifically, the computing task requirement can be a service level agreement (SLA) requirement.

[0128] In a possible embodiment, the task requirement of the computing task can include but is not limited to at least one of the following: end-to-end delay requirement, required bandwidth, and computing resource type of the computing task, etc.

[0129] It can be understood that when one or more parameters in the task requirement of the computing task require a high requirement, a suitable computing node may need to be selected, the computing task may need to be specially processed, and the like, so as to meet the task requirement of the computing task. For example, if the end-to-end delay requirement of the computing task is high, that is, the computing task is a low-delay task, scheduling the computing task to the CPU according to normal operation, queuing for a period of time, and then processing in the coprocessor may cause high delay, which cannot meet the task requirement, and the quality of service of the computing task cannot be guaranteed. Therefore, the steps in the embodiments of the present application can be performed to obtain the priority indication information of the computing task, and the computing task is specially processed based on the priority indication information, so as to guarantee the quality of service of the computing task.

[0130] In the embodiments of the present application, the priority indication information of the computing task can be obtained based on the task requirement of the computing task. The computing tasks with different requirements are distinguished by using the priority indication information, which is beneficial to subsequent processing of different computing tasks, so as to ensure that the computing tasks with high delay requirements (for example, low-delay tasks) are processed preferentially, the task requirements are met, and the quality of service of the computing tasks is guaranteed.

[0131] In a possible embodiment, the subscription data of the terminal device can include, but is not limited to, at least one of the following: a user subscription type, a service guarantee level, and the like.

[0132] The user subscription type can be divided into different types based on user level information, user package and service subscription information, and the like. For example, the user subscription type can include a VIP (very important person), a non-VIP, and the like. For another example, the user subscription type can include gold, silver, copper, and the like. The present application does not limit this. The service guarantee level can be divided into different levels based on the user service level and the importance of the user service. For example, the service guarantee level can include AAA level, AA level, A level, and ordinary level. The present application does not limit this either.

[0133] In the embodiments of the present application, the priority indication information of the computing task can be obtained based on the subscription data of the terminal device. In this way, the computing tasks initiated by users with different importance levels can be distinguished by using the priority indication information, which is beneficial to subsequent processing of different computing tasks, so as to ensure that the computing tasks of users with high importance levels (for example, VIP users) are processed preferentially, the user requirements are met, and the quality of service of the computing tasks initiated by the users is guaranteed.

[0134] In the present application, since the priority indication information can be obtained based on at least one of the task requirement of the computing task and the subscription data of the terminal device, the priority indication information is related to the task requirement of the computing task and the importance of the user corresponding to the terminal device. If the task requirement of the computing task is high, the priority indication information indicates that the processing priority of the computing task can be high. If the importance of the user corresponding to the terminal device is high, the priority indication information indicates that the processing priority of the computing task can also be high. When the computing task is executed based on the priority indication information subsequently, based on the high or low of the processing priority indicated by the priority indication information, the computing task is scheduled to the corresponding queue or corresponding position in the CPU or coprocessor, which can make the time length of the computing task entering the coprocessor queue match the processing priority, so as to realize the priority processing of the computing task requiring low latency and / or important user, meet the requirements of the computing task of these users, and guarantee the service quality of these computing tasks.

[0135] In the embodiments of the present application, the computing node can receive the priority indication information of the computing task in the following two implementation manners.

[0136] Implementation manner (1), in the case that the computing node is separated from the user plane network element, S201 can specifically include the following steps.

[0137] The user plane network element sends the first data packet, and the computing node receives the first data packet from the user plane network element.

[0138] The first data packet carries the marking information, which can include the priority indication information, and the marking information is generated based on the computing QoS policy corresponding to the computing task.

[0139] It can be understood that the first data packet received by the computing node can be a marked data packet, and the marking information carried by the marked data packet includes the priority indication information. The marking information can be generated based on the computing QoS policy corresponding to the computing task. In other words, the computing node can mark the data packet based on the computing QoS policy corresponding to the computing task, and send the first data packet to the computing node after obtaining the first data packet.

[0140] It can be understood that before the user plane network element sends the first data packet, the terminal device can send the computing task model and / or computing task data, and the user plane receives the task model and / or computing task data, and generates the first data packet based on them and the computing QoS policy corresponding to the computing task. When the computing task is processed subsequently, it can be understood as executing the computing task, that is, obtaining the result of the computing task based on the computing task model and / or computing task data.

[0141] In the embodiments of the present application, in the scenario where the computing node and the user plane network element are separately arranged, the user plane network element obtains the marked data packet (i.e., the first data packet) based on the computing QoS policy corresponding to the computing task, and indicates the priority indication information of the computing task through the marking information, thereby indicating the processing priority of the computing task. The priority indication information can be conveniently sent to the computing node by using the first data packet, which is simple and easy to implement.

[0142] The user plane network element sends the first data packet to the computing node, and the computing node obtains the priority indication information of the computing task after receiving the first data packet. The user plane network element sends the priority indication information to the computing node by using the first data packet, and the subsequent computing node can perform corresponding processing on the computing task according to the processing priority of the computing task, thereby ensuring that the computing task from an important user or requiring a high demand can be processed in priority, ensuring the processing efficiency of the computing task and the service quality of the task.

[0143] In the case where the computing node and the user plane network element are arranged together, the computing node and the user plane network element can be referred to as a forwarding computing node, and S201 can specifically include the following steps.

[0144] The control plane network element sends the computing QoS policy corresponding to the computing task, and the computing node receives the computing QoS policy corresponding to the computing task.

[0145] The computing QoS policy includes the priority indication information of the computing task and the computing delay requirement, and the computing QoS policy is obtained based on at least one of the task requirement of the computing task and the subscription data of the terminal device.

[0146] The computing node and the user plane network element are arranged together, which can include that the central processing unit (CPU) of the computing node and the user plane network element are combined.

[0147] It can be understood that since the computing node and the user plane network element are arranged together, the computing node receives the computing QoS policy, i.e., the user plane receives the computing QoS policy. The computing node can obtain the priority indication information of the computing task through the computing QoS policy. In this way, the user plane node does not need to send the first data packet to the computing node, which can reduce the transmission delay and improve the processing efficiency of the computing task.

[0148] In the embodiments of this application, in the scenario where the computing node and the user plane network element are arranged together, the user plane network element and the computing node receive the computing QoS policy corresponding to the computing task sent by the control plane network element, obtain the priority indication information of the computing task, and do not need the user plane node to send the first data packet to the computing node, so as to reduce the transmission delay. The subsequent computing node can process the computing task according to the priority of the computing task, so as to ensure that the computing task from an important user or with high demand can be processed first, ensure the processing efficiency of the computing task, and protect the service quality of the task.

[0149] It can be understood that before the computing node processes the computing task based on the priority indication information of the computing task, the terminal device can send the computing task model and / or the computing task data, and the computing node receives the task model and / or the computing task data, and subsequently obtains the result of the computing task based on the computing task model and / or the computing task data.

[0150] In the implementation manner (1) or the implementation manner (2), the computing QoS policy includes multiple parameters, and specifically can include but is not limited to the priority indication information of the computing task, a computing delay requirement, a computing resource type, and the like. The application does not make any limitation in this regard.

[0151] It can be understood that the computing QoS policy is obtained by the control plane network element based on at least one of the task requirement of the computing task and the subscription data of the terminal device. After the control plane network element generates the computing QoS policy, the control plane network element sends the computing QoS policy, and the user plane network element can receive the computing QoS policy.

[0152] In some embodiments, the control plane network element can also generate a communication QoS policy. The communication QoS policy can include one or more parameters, and specifically can include but is not limited to at least one of the following: a transmission bandwidth, a transmission delay requirement, a jitter, a computing resource type, a packet loss rate, a maximum rate, and the like. It should be noted that the computing QoS policy and the communication QoS policy in this application can also be represented by other performance indicators, and the application does not make any limitation on the specific content of the parameters included in these QoS policies. After the control plane network element generates the communication QoS policy, the control plane network element can send the communication QoS policy, and the user plane network element can receive the communication QoS policy. Based on the communication QoS policy, a suitable policy can be selected to protect the communication service quality of the computing task.

[0153] S202: The computing node schedules the computing task to a first position of a first queue or a second queue of the computing node, or directly schedules the computing task to a third queue, based on the priority indication information.

[0154] The first queue is one of a plurality of different priority queues in a central processing unit (CPU) of the computing node, and the second queue is a queue in the CPU of the computing node waiting for access to the coprocessor resource, and the third queue is a queue in the coprocessor of the computing node.

[0155] It can be understood that the first queue is a queue in a central processing unit (CPU) of the computing node, and the first queue is a priority queue in a plurality of different priority queues. Specifically, the first queue is a priority queue corresponding to the priority indication information. For example, if the priority indication information indicates that the processing priority of the computing task is a high priority, the first queue can be a high priority queue in the plurality of different priority queues in the CPU.

[0156] The second queue is a queue in the CPU of the computing node. At this time, the queue in the CPU of the computing node can not be prioritized. Or, the queue in the CPU of the computing node waiting for access to the coprocessor resource only includes the second queue. The first position is a position in the second queue corresponding to the priority indication information. For example, if the priority indication information indicates that the processing priority of the computing task is a high priority, the first position is closer to the de-queue position.

[0157] The coprocessor in the computing node can be a processor other than the CPU. The coprocessor can also be referred to as an acceleration card, etc. The coprocessor can include, but is not limited to, at least one of the following: GPU, NPU, DPU, TPU, etc.

[0158] In the embodiments of the present application, based on the priority indication information of the computing task, the computing task is scheduled to the first queue or the first position in the second queue or the third queue, that is, the computing task is directly scheduled to the coprocessor, or scheduled to a certain priority queue in the CPU of the computing node corresponding to the priority indication information, or scheduled to a certain position in the second queue of the CPU of the computing node corresponding to the priority indication information. The processing priority indicated by the priority indication information can be used to process the computing task in the corresponding order, so that the computing task with high task demand and / or important user can be processed preferentially, the demand of the computing task can be met, and the quality of service of the computing task can be guaranteed.

[0159] In actual scenarios, the computing node can schedule the computing task to the corresponding queue or queue position in the queue based on the priority indication information described above. How to schedule is specifically introduced below.

[0160] In a possible embodiment, in the case that the computing node supports scheduling the computing task directly to a queue in the coprocessor, the computing node schedules the computing task to the first position of the first queue or the second queue of the computing node, or directly schedules the computing task to the third queue based on the priority indication information, which can specifically include:

[0161] In the case that the priority indication information indicates that the processing priority of the computing task is the highest priority in the multiple processing priorities, the computing node directly schedules the computing task to the third queue.

[0162] In the case that the priority indication information indicates that the processing priority of the computing task is not the highest priority in the multiple processing priorities, the computing node schedules the computing task to the first position of the first queue or the second queue based on the priority indication information.

[0163] The first queue and the second queue are queues in a central processing unit (CPU) in the computing node. Further, the first queue and the second queue are both queues in the CPU waiting for access to the coprocessor resource, in other words, the computing task in the first queue or the second queue is waiting for access to the coprocessor resource.

[0164] In the embodiment, the highest priority in the multiple processing priorities can be a highest priority in a narrow sense, i.e., the only and highest priority in the multiple processing priorities, or can be a highest priority in a broad sense, i.e., at least two relatively high priorities in the multiple processing priorities, which is not limited in the application. For example, if the multiple processing priorities include priorities 1, 2 and 3, the highest priority can be the priority 1. For another example, if the multiple priorities include priorities A, B, C, D and E, the highest priority can include the relatively high priorities A and B.

[0165] It can be understood that, in this embodiment, if the processing priority of the computing task is the highest priority among the plurality of processing priorities, it means that the computing task has higher requirements or the corresponding user has higher importance, and the quality of service of the computing task needs to be guaranteed. At this time, the computing task is directly scheduled to the third queue in the coprocessor, and the computing task does not need to wait in the queue in the CPU for a period of time before entering the coprocessor, thereby reducing the queuing time, so that the computing task can be processed in priority, and the quality of service of the computing task is guaranteed. On the other hand, if the processing priority of the computing task is not the highest priority among the plurality of processing priorities, it means that the requirements of the computing task are relatively low or the importance of the corresponding user is not the highest, and at this time the computing task is scheduled to the queue in the CPU and waits for a period of time before entering the coprocessor, which can also meet the user's demand, thereby guaranteeing the quality of service of the computing task with the highest priority. The priority or the order of the queue position of the computing task entering the queue is related to the priority indication information, and the order of the computing task being processed can be further arranged according to the priority of the computing task, so as to guarantee the quality of service of the computing task with higher priority as much as possible.

[0166] For example, as shown in FIGS. 3a and 3b, the processing priorities of the computing task include priority #1, priority #2, and priority #3, and the processing priorities are sorted in descending order of priority level as priority #1, priority #2, and priority #3. In this scenario, the coprocessor includes a GPU and an NPU. The computing task enters the GPU queue in the CPU shown in FIGS. 3a and 3b, indicating that the computing task needs to be queued and wait to access the GPU resource. FIGS. 3a-4b all take the computing task to be processed as an example that needs to access the GPU resource. It can be understood that these examples do not constitute a limitation on the present application, and the related description of FIGS. 3a-4b will not be repeated below.

[0167] As shown in FIGS. 3a and 3b, when the priority indication information of the computing task indicates that the processing priority of the computing task is priority #1, which is the highest priority among the plurality of processing priorities, the computing node can directly schedule the computing task to the third queue (i.e., the GPU queue in FIGS. 3a and 3b). In this way, the computing task does not need to wait in the queue in the CPU, and can directly enter the GPU for processing, which is faster and can meet the latency requirements of the computing task, thereby guaranteeing the quality of service of the computing task.

[0168] When the priority indication information of the computing task indicates that the processing priority of the computing task is priority #2, which is not the highest priority among the multiple processing priorities, the computing task can be scheduled to the first queue (i.e., the medium priority queue in the CPU in FIG. 3a) as shown in FIG. 3a, or to the first position in the second queue (i.e., the position pointed by the small arrow in FIG. 3b) as shown in FIG. 3b. Similarly, when the priority indication information of the computing task indicates that the processing priority of the computing task is priority #3, the computing task can be scheduled to the first queue or the first position in the second queue, where the first queue refers to the low priority queue in the CPU in FIG. 3a, and the first position in the second queue corresponds to the position for priority #3. In this way, when the processing priority of the computing task is not the highest processing priority, the computing task can still be scheduled to the queue corresponding to the processing priority or to the appropriate position in the queue based on the level of the processing priority, so that the computing tasks are queued and then processed in the co-processor in order, and the computing tasks with higher processing priorities have shorter waiting time and faster processing speed, thereby guaranteeing the service quality of the computing tasks.

[0169] In the embodiments of the present application, when the priority indication information indicates that the processing priority of the computing task is the highest priority, the computing task is directly scheduled to the queue in the co-processor without queuing in the queue in the CPU, so as to ensure that the computing task with the highest priority is processed preferentially and the service quality of the computing task is guaranteed. When the priority indication information indicates that the processing priority of the computing task is not the highest priority, the computing task is scheduled to the queue corresponding to the processing priority in the CPU or to the corresponding position in the queue in the CPU based on the level of the processing priority, so that the computing task waits for a period of time and then enters the co-processor, and the order and computing delay of processing the computing task are matched with the processing priority, thereby guaranteeing the service quality of the computing task with higher priority as much as possible.

[0170] In a possible embodiment, when the CPU of the computing node includes multiple priority queues, the computing task is scheduled to the first queue based on the priority indication information, which can specifically include the following steps.

[0171] The computing task is scheduled to the first queue based on the priority indication information, where the priority indication information indicates that the higher the priority level of the processing priority of the computing task, the higher the priority level of the first queue.

[0172] It can be understood that the first queue is a queue corresponding to the priority indication information. For example, when the priority indication information indicates that the priority of the computing task is the highest priority, the first queue can be the highest priority queue in the plurality of priority queues. When the priority indication information indicates that the priority of the computing task is a low priority, the first queue can be a low priority queue in the plurality of priority queues.

[0173] For example, as shown in FIG. 4a, the processing priorities of the computing tasks include priority #1, priority #2, and priority #3, and the processing priorities are sorted in descending order of priority level as priority #1, priority #2, and priority #3. The computing task enters the GPU queue in the CPU shown in FIG. 4a, indicating that the computing task needs to be queued to wait for access to the GPU resource. The computing task enters the NPU queue in the CPU shown in FIG. 4a, indicating that the computing task needs to be queued to wait for access to the NPU resource. As shown in FIG. 4a, when the priority indication information of the computing task indicates that the processing priority of the computing task is priority #1, the computing node can schedule the computing task to the high-priority queue in the GPU. As shown in FIG. 3a and FIG. 4a, when the priority indication information of the computing task indicates that the processing priority of the computing task is priority #2, the computing node can schedule the computing task to the medium-priority queue in the GPU. When the priority indication information of the computing task indicates that the processing priority of the computing task is priority #3, the computing node can schedule the computing task to the low-priority queue in the GPU. In this way, the higher the processing priority level of the computing task, the shorter the queuing time of the computing task in the CPU, and the faster the computing task enters the GPU for processing, so that the processing delay of the computing task is smaller.

[0174] In the embodiment of the present application, in the case that the CPU of the computing node includes a plurality of priority queues, the computing task is scheduled to a certain priority queue (i.e., the first queue) in the CPU corresponding to the priority indication information of the computing task based on the priority indication information of the computing task, so as to ensure that the queuing waiting time of the computing task in the CPU matches the processing priority of the computing task, and the higher the processing priority of the computing task, the shorter the waiting time. Therefore, the computing task of high task demand and / or important user can be processed preferentially, the demand of the computing task is met, and the quality of service of the computing task is guaranteed.

[0175] In a possible embodiment, in the case that the queue waiting for access to the coprocessor resource in the CPU of the computing node includes one queue, the computing task is scheduled to the first position of the second queue based on the priority indication information, which can specifically include:

[0176] The computing task is scheduled to a first position in the second queue based on the priority indication information, wherein the higher the priority level of the processing priority of the computing task indicated by the priority indication information, the closer the first position to the de-queue position.

[0177] It can be understood that, since there is only one queue in the CPU waiting for accessing the coprocessor resource and no priority is distinguished, the computing task can be scheduled to a corresponding position, i.e., the first position, in the second queue based on the priority indication information. For example, if the priority indication information indicates that the processing priority of the computing task is a high priority, the first position can be position a1 in the second queue, and if the priority indication information indicates that the processing priority of the computing task is a medium priority, the first position can be position a2 in the second queue, and position a1 is closer to the de-queue position than position a2.

[0178] For example, as shown in FIG. 4b, the processing priorities of the computing tasks include priority #1, priority #2 and priority #3, and these processing priorities are sorted in descending order of priority level as priority #1, priority #2 and priority #3. As shown in FIG. 4b, when the priority indication information of the computing task indicates that the processing priority of the computing task is priority #1, the computing node can schedule the computing task to the position pointed by the small arrow in the GPU queue; as shown in FIG. 3b and FIG. 4b, when the priority indication information of the computing task indicates that the processing priority of the computing task is priority #2 or priority #3, the computing node can schedule the computing task to the position corresponding to the processing priority in the GPU queue. In this way, the computing task with a higher processing priority level can be scheduled to a position closer to the de-queue position in the queue in the CPU, and the computing task with a higher processing priority can wait for a shorter time in the queue in the CPU and enter the GPU processing faster, so that the processing delay of the computing task can be smaller, and the quality of service of the computing task with a higher processing priority can be ensured.

[0179] In the embodiments of the present application, the queue in the CPU of the computing node waiting for accessing the coprocessor resource includes one queue, and the computing task is scheduled to a position corresponding to the processing priority in the queue based on the priority indication information without distinguishing the priority, which can realize scheduling the computing task with a higher processing priority to a position closer to the de-queue position, so as to reduce the queuing waiting time of the computing task in the CPU, ensure that the computing task can be processed as soon as possible, and ensure the quality of service of the computing task with a higher delay requirement or a higher importance of corresponding user.

[0180] Please refer to FIG. 5, which is another flow diagram of the communication method provided by the embodiments of the present application. It can be understood that the steps in the embodiments of the present application can be regarded as reasonable variations or supplements of the embodiments in FIG. 2 described above; or it can be understood that the communication method in the embodiments of the present application can also be regarded as an embodiment that can be executed independently, and the present application does not limit this. In the communication method, the computing node is set separately from the user plane network element.

[0181] The communication method includes but is not limited to the following steps:

[0182] S501: The terminal device requests to create a computing session.

[0183] S502a: The control plane network element obtains the subscription data of the terminal device from the user subscription data management network element.

[0184] Here, the user subscription data management network element can be used to manage the subscription data of the user. In the 5G network, the user subscription data management network element can be UDM. For related description of the subscription data, please refer to the above.

[0185] S502b: The control plane network element creates a computing session.

[0186] It can be understood that steps S501 and S502b can refer to related technologies, and will not be described here.

[0187] S503: The terminal device initiates a computing request of a computing task, and correspondingly, the control plane network element receives the computing request.

[0188] Among them, the computing request carries the task requirement of the computing task, which can include but is not limited to the end-to-end delay requirement, the required bandwidth, the computing resource type, etc. of the computing task.

[0189] S504: The control plane network element generates the QoS policy corresponding to the computing task based on the subscription data and / or the computing request.

[0190] Among them, the QoS policy corresponding to the computing task can include a communication QoS policy and a computing QoS policy. The computing QoS policy includes the priority indication information of the computing task. For specific description, please refer to the above.

[0191] S505: The control plane network element selects the computing node that can meet the above QoS policy.

[0192] In some embodiments, this step can not necessarily be executed.

[0193] S506: The control plane network element issues the QoS policy corresponding to the computing task, and correspondingly, the user plane network element receives the QoS policy.

[0194] Specifically, the QoS policy corresponding to the computing task can include a communication QoS policy and a computing QoS policy.

[0195] S507: The user plane network element creates a computing task context and records the above QoS policy.

[0196] S508: The terminal device sends a computing task model and / or computing task data, and correspondingly, the user plane network element receives the computing task model and / or computing task data.

[0197] S509: The user plane network element sends a marked data packet, and correspondingly, the computing node receives the marked data packet.

[0198] The user plane network element obtains the marked data packet based on the received computing QoS policy and the computing task model and / or computing task data. The data packet is the first data packet, and the marking information carried in the first data packet includes priority indication information of the computing task. In this way, by marking the data packet and sending the marked data packet to the computing node, the priority indication information of the computing task can be sent to the computing node, which is simple and easy to implement.

[0199] After the computing node obtains the priority indication information of the computing task, there are two cases. Case one: If the computing node supports scheduling the computing task directly to a queue in the coprocessor, steps S510-S512 are performed. Case two: If the computing node does not support scheduling the computing task directly to a queue in the coprocessor, steps S513-S514 are performed.

[0200] S510: In a case where the priority indication information of the computing task indicates that the processing priority of the computing task is the highest priority, the computing node schedules the computing task directly to a queue in the coprocessor.

[0201] As shown in FIG. 5, the computing network element includes a CPU and a coprocessor, which can be any one of a GPU, a DPU, an NPU, etc. It can be understood that the computing network element can actually include multiple coprocessors, and FIG. 5 is only an example and does not limit the present application. When the computing node schedules the computing task, a logical part in the computing node can specifically issue an instruction. The computing task can be directly scheduled to a queue in the coprocessor, or the computing task can be scheduled to a queue in the CPU and then enter the coprocessor for processing after queuing. This is uniformly described here, and will not be described again below.

[0202] S511: In a case where the priority indication information of the computing task indicates that the processing priority of the computing task is not the highest priority, the computing node schedules the computing task to a first position in a first queue or a second queue in the CPU based on the priority indication information.

[0203] Specifically, in the case that the computing node CPU includes multiple priority queues, the computing node schedules the computing task to a first queue in the CPU based on the priority indication information; in the case that the computing node CPU includes one queue waiting for calling processor resources (referred to as a second queue), without distinguishing the priority of the queue, the computing node schedules the computing task to a first position in the second queue in the CPU based on the priority indication information. For specific description, refer to the foregoing description.

[0204] S512: The computing node schedules the computing task in the queue in the CPU to the coprocessor processing in sequence.

[0205] It can be understood that for a certain computing task, step S510 can be performed or steps S511-S512 can be performed based on the priority indication information of the computing task.

[0206] S513: The computing node schedules the computing task to a first queue in the CPU or a first position in the second queue based on the priority indication information of the computing task.

[0207] Specifically, in the case that the computing node CPU includes multiple priority queues, the computing node schedules the computing task to a first queue in the CPU based on the priority indication information; in the case that the computing node CPU includes one queue waiting for calling processor resources (referred to as a second queue), without distinguishing the priority of the queue, the computing node schedules the computing task to a first position in the second queue in the CPU based on the priority indication information. For specific description, refer to the foregoing description.

[0208] S514: The computing node schedules the computing task in the queue in the CPU to the coprocessor processing in sequence.

[0209] Through the embodiments of the present application, in the scenario that the computing node and the user plane network element are separately arranged, the terminal device initiates a computing request of a computing task, the control plane network element generates a computing QoS policy based on the subscription data of the terminal device and / or the task requirement of the computing task, and sends the computing QoS policy to the user plane network element. The user plane network element obtains the marked data packet (i.e., the first data packet) based on the computing QoS policy and sends the marked data packet, and can conveniently deliver the priority indication information included in the marked data packet to the computing node, so as to determine the processing priority of the computing task by using the task requirement of the computing task and the importance of the user. The computing node processes the computing task according to the high and low of the processing priority, i.e., selects to schedule the computing task to the coprocessor, or to a certain priority queue of the CPU of the computing node corresponding to the priority indication information, or to a certain position of the second queue of the CPU of the computing node corresponding to the priority indication information, so that the computing task of the high task requirement and / or the important user can be processed preferentially, the requirements of these computing tasks are met, and the quality of service of these computing tasks is guaranteed.

[0210] Referring to FIG. 6, FIG. 6 is another flowchart of a communication method provided by an embodiment of the present application. It can be understood that the steps in the embodiments of the present application can be regarded as reasonable variations or supplements of the embodiments in FIG. 2 described above; or it can be understood that the communication method in the embodiments of the present application can also be regarded as an independently executable embodiment, and the present application does not limit this. In the communication method, the computing node and the user plane network element are arranged together.

[0211] The communication method includes but is not limited to the following steps:

[0212] S601: The terminal device requests to create a computing session.

[0213] S602a: The control plane network element obtains the subscription data of the terminal device from the user subscription data management network element.

[0214] Here, the user subscription data management network element can be used to manage the subscription data of the user. In the 5G network, the user subscription data management network element can be a UDM. For related description of the subscription data, refer to the above.

[0215] S602b: The control plane network element creates a computing session.

[0216] It can be understood that steps S601 and S602b can refer to related technologies, and will not be described here.

[0217] S603: The terminal device initiates a computing request of a computing task, and correspondingly, the control plane network element receives the computing request.

[0218] The task requirement of the computing task can include, but is not limited to, an end-to-end delay requirement, a required bandwidth, a computing resource type, and the like of the computing task.

[0219] S604: The control plane network element generates a QoS policy corresponding to the computing task based on the subscription data and / or the computing request.

[0220] The QoS policy corresponding to the computing task can include a communication QoS policy and a computing QoS policy. The computing QoS policy includes priority indication information of the computing task. For specific descriptions, refer to the foregoing.

[0221] S605: The control plane network element selects a computing node that can meet the QoS policy.

[0222] In some embodiments, the step can not necessarily be performed.

[0223] S606: The control plane network element issues the QoS policy corresponding to the computing task, and correspondingly, the user plane network element receives the QoS policy.

[0224] Specifically, the QoS policy corresponding to the computing task can include a communication QoS policy and a computing QoS policy, and the computing QoS policy can include priority indication information of the computing task.

[0225] It can be understood that, since the user plane network element and the computing node are arranged together, the computing node can obtain the computing QoS policy corresponding to the computing task, and thus obtain the priority indication information of the computing task.

[0226] S607: The user plane network element creates a computing task context and records the QoS policy.

[0227] S608: The terminal device sends a computing task model and / or computing task data, and correspondingly, the user plane network element receives the computing task model and / or computing task data.

[0228] It can be understood that, since the user plane network element and the computing node are arranged together, the computing node can obtain the computing task model and / or computing task data, and compared with the embodiment shown in FIG. 5, the embodiment does not need the user plane network element to send a first data packet to the computing node, and can reduce the time delay.

[0229] After the computing node obtains the priority indication information of the computing task, there are two cases. Case one: if the computing node supports directly scheduling the computing task to a queue in the coprocessor, steps S609-S611 are performed; case two: if the computing node does not support directly scheduling the computing task to a queue in the coprocessor, steps S612-S613 are performed.

[0230] S609: In a case where the priority indication information of the computing task indicates that the processing priority of the computing task is the highest priority, the computing node directly schedules the computing task to a queue in the co-processor.

[0231] As shown in FIG. 6, the computing network element includes a CPU and a co-processor, which can be any one of a GPU, a DPU, an NPU, etc. It can be understood that the computing network element can actually include multiple co-processors, and FIG. 6 is only an example and does not limit the present application. When the computing node schedules the computing task, a specific instruction can be issued by a logical part in the computing node. The computing task can be directly scheduled to a queue in the co-processor, or the computing task can be scheduled to a queue in the CPU and then enter the co-processor for processing after queuing. This is uniformly described here, and will not be repeated below.

[0232] S610: In a case where the priority indication information of the computing task indicates that the processing priority of the computing task is not the highest priority, the computing node schedules the computing task to a first queue or a first position in a second queue in the CPU based on the priority indication information.

[0233] Specifically, in a case where the computing node CPU includes multiple priority queues, the computing node schedules the computing task to the first queue in the CPU based on the priority indication information; in a case where the computing node CPU includes one queue waiting for calling processor resources (referred to as the second queue) without distinguishing the queue priority, the computing node schedules the computing task to the first position in the second queue in the CPU based on the priority indication information. For specific description, reference can be made to the above.

[0234] S611: The computing node schedules the computing task in the queue in the CPU to the co-processor for processing in sequence.

[0235] It can be understood that for a certain computing task, step S609 or steps S610-S611 can be performed based on the priority indication information of the computing task.

[0236] S612: The computing node schedules the computing task to a first queue or a first position in a second queue in the CPU based on the priority indication information of the computing task.

[0237] Specifically, in a case where the computing node CPU includes multiple priority queues, the computing node schedules the computing task to the first queue in the CPU based on the priority indication information; in a case where the computing node CPU includes one queue waiting for calling processor resources (referred to as the second queue) without distinguishing the queue priority, the computing node schedules the computing task to the first position in the second queue in the CPU based on the priority indication information. For specific description, reference can be made to the above.

[0238] S613: The computing node schedules the computing task in the queue in the CPU to the coprocessor for processing in order.

[0239] Through the embodiments of the present application, in the scenario that the computing node and the user plane network element are arranged together, the terminal device initiates a computing request of a computing task, the control plane network element generates a computing QoS policy based on the subscription data of the terminal device and / or the task requirement of the computing task, and sends the computing QoS policy to the user plane network element. Then, the computing node also receives the computing QoS policy to obtain the priority indication information of the computing task, and does not need the user plane node to send a first data packet to the computing node, so that the transmission delay can be reduced, and the processing priority of the computing task is determined by using the task requirement of the computing task and the importance of the user. The computing node processes the computing task according to the high and low of the processing priority, that is, the computing task is selected to be directly scheduled to the coprocessor, or to be scheduled to a certain priority queue in the CPU of the computing node corresponding to the priority indication information, or to a certain position in the second queue of the CPU of the computing node corresponding to the priority indication information. The computing task of the high task requirement and / or the important user can be processed preferentially, the requirements of these computing tasks are met, and the quality of service of these computing tasks is guaranteed.

[0240] The above describes the method of the embodiments of the present application in detail, and the following provides an apparatus for implementing any one of the methods in the embodiments of the present application, for example, an apparatus including units (or means) for implementing each step performed by the device in any one of the above methods.

[0241] Please refer to FIG. 7, which is a structural schematic diagram of a communication apparatus provided by the embodiments of the present application.

[0242] As shown in FIG. 7, the communication apparatus 70 can include a communication unit 701 and a processing unit 702. The communication unit 701 and the processing unit 702 can be software, hardware, or a combination of software and hardware.

[0243] The communication unit 701 can implement the sending function and / or the receiving function, and the communication unit 701 can also be described as a transceiver unit. The communication unit 701 can also be a unit integrated with an acquisition unit and a sending unit, wherein the acquisition unit is used to implement the receiving function, and the sending unit is used to implement the sending function. Optionally, the communication unit 701 can be used to receive information sent by other apparatuses, and also can be used to send information to other apparatuses.

[0244] In a possible design, the communication apparatus 70 can correspond to a computing node in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6, and the communication apparatus 70 can be a computing node or a chip in the computing node. The communication apparatus 70 can include units for performing the operations performed by the computing node in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6, and each unit in the communication apparatus 70 is configured to implement the operation performed by the computing node in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6. The units are described as follows:

[0245] The communication unit 701 is configured to receive priority indication information of a computing task to be processed, the priority indication information indicating a processing priority of the computing task by the computing node; and the priority indication information is obtained based on at least one of task requirements of the computing task and subscription data of the computing node.

[0246] In a possible implementation, the apparatus further includes:

[0247] The processing unit 702 is configured to schedule the computing task to a first position of a first queue or a second queue of the computing node, or directly to a third queue, based on the priority indication information, the first queue being one of a plurality of different priority queues of the computing node, the second queue being a queue waiting for access to a coprocessor resource in the computing node, and the third queue being a queue in a coprocessor in the computing node.

[0248] The communication unit 701 and the processing unit 702 described in this design perform the steps as described in the implementation corresponding to the computing node in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6.

[0249] The technical effects brought by the implementation performed by the communication unit 701 and the processing unit 702 described in this design can be referred to the introduction of the technical effects of the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6.

[0250] In another possible design, the communication apparatus 70 can correspond to a control plane network element in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6, and the communication apparatus 70 can be a control plane network element or a chip in the control plane network element. The communication apparatus 70 can include units for performing the operations performed by the control plane network element in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6, and each unit in the communication apparatus 70 is configured to implement the operation performed by the control plane network element in the method embodiments of any of the above-described FIG. 2, FIG. 5, and FIG. 6. The units are described as follows:

[0251] The communication unit 701 is configured to send a computing service quality (QoS) policy corresponding to a computing task, the computing QoS policy comprising priority indication information of the computing task, the computing QoS policy being obtained based on at least one of task requirements of the computing task and subscription data of a terminal device.

[0252] In a possible implementation, the apparatus further includes:

[0253] The processing unit 702 is configured to generate the computing QoS policy.

[0254] The communication unit 701 and the processing unit 702 described in the present design perform steps that can refer to the implementation corresponding to the control plane network element in the method embodiment of any one of the above-described FIG. 2, FIG. 5 and FIG. 6.

[0255] The technical effects brought by the implementation performed by the communication unit 701 and the processing unit 702 described in the present design can refer to the introduction of the technical effects of the method embodiment of any one of the above-described FIG. 2, FIG. 5 and FIG. 6.

[0256] In yet another possible design, the communication apparatus 70 can correspond to the user plane network element in the method embodiment of any one of the above-described FIG. 2, FIG. 5 and FIG. 6, for example, the communication apparatus 70 can be a user plane network element or a chip in a user plane network element. The communication apparatus 70 can include units configured to perform the operations performed by the user plane network element in the method embodiment of any one of the above-described FIG. 2, FIG. 5 and FIG. 6, and each unit in the communication apparatus 70 is respectively configured to implement the operations performed by the user plane network element in the method embodiment of any one of the above-described FIG. 2, FIG. 5 and FIG. 6. The description of each unit is as follows:

[0257] The communication unit 701 is configured to receive a computing service quality (QoS) policy corresponding to a computing task from a control plane network element, the computing QoS policy comprising priority indication information of the computing task, the computing QoS policy being obtained based on at least one of task requirements of the computing task and subscription data of a terminal device.

[0258] The communication unit 701 is further configured to send a first data packet, the marking information carried by the first data packet comprising the priority indication information of the computing task, the marking information being generated based on the computing QoS policy.

[0259] In a possible implementation, the apparatus further includes:

[0260] The processing unit 702 is configured to generate the first data packet.

[0261] The steps performed by the communication unit 701 and the processing unit 702 described in the design can refer to the implementation corresponding to the user plane network element in the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6.

[0262] The technical effects brought by the implementation performed by the communication unit 701 and the processing unit 702 described in the design can refer to the introduction of the technical effects of the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6.

[0263] In another possible design, the communication apparatus 70 can correspond to the terminal device in the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6, for example, the communication apparatus 70 can be a terminal device or a chip in a terminal device. The communication apparatus 70 can include units for performing the operations performed by the terminal device in the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6, and each unit in the communication apparatus 70 is respectively for implementing the operations performed by the terminal device in the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6. The description of each unit is as follows:

[0264] The communication unit 701 is configured to send a computing task request, wherein the computing task request comprises task requirements of a computing task, and the task requirements are used to generate a computing QoS policy corresponding to the computing task, and the computing QoS policy comprises priority indication information of the computing task.

[0265] In a possible implementation, the apparatus further includes:

[0266] The processing unit 702 is configured to generate the computing task request.

[0267] The steps performed by the communication unit 701 and the processing unit 702 described in the design can refer to the implementation corresponding to the terminal device in the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6.

[0268] The technical effects brought by the implementation performed by the communication unit 701 and the processing unit 702 described in the design can refer to the introduction of the technical effects of the method embodiment corresponding to any of the above FIG. 2, FIG. 5 and FIG. 6.

[0269] According to the embodiments of the present application, each unit in the apparatus shown in FIG. 7 can be combined into one or several other units respectively or all, or some of the units can be further split into a plurality of units with smaller functions to constitute, which can achieve the same operation without affecting the implementation of the technical effects of the embodiments of the present application. The above units are divided based on logical functions. In actual application, the function of one unit can also be implemented by a plurality of units, or the functions of a plurality of units are implemented by one unit. In other embodiments of the present application, the electronic device can also include other units. In actual application, these functions can also be assisted by other units, and can be implemented by a plurality of units.

[0270] It should be noted that the implementation of each unit can also correspond to the description of the method embodiments of any of the above FIG. 2, FIG. 5 and FIG. 6.

[0271] In the communication apparatus 70 described in FIG. 7, the terminal device initiates a computing request of a computing task, the control plane network element generates a computing QoS policy based on the subscription data of the terminal device and / or the task requirement of the computing task, and sends it to the user plane network element. In the scenario where the computing node and the user plane network element are separately arranged, the user plane network element obtains the marked data packet (i.e. the first data packet) based on the computing QoS policy and sends it, and can conveniently pass the priority indication information included therein to the computing node. In the scenario where the computing node and the user plane network element are arranged together, the computing node can directly obtain the priority indication information. In this way, the processing priority of the computing task is determined by using the task requirement of the computing task and the importance of the user. The computing node processes the computing task according to the high and low of the processing priority, that is, selects to schedule the computing task to the coprocessor, or to a certain priority queue of the CPU of the computing node corresponding to the priority indication information, or to a certain position of the second queue of the CPU of the computing node corresponding to the priority indication information. The computing task of the high task requirement and / or the important user can be processed preferentially, the requirements of these computing tasks are met, and the quality of service of these tasks is guaranteed.

[0272] Please refer to FIG. 8, which is a structural schematic diagram of a communication apparatus provided by an embodiment of the present application.

[0273] It should be understood that the communication apparatus 80 shown in FIG. 8 is only an example. The communication apparatus of the embodiments of the present application can also include other components, or include components with similar functions to the components in FIG. 8, or not include all the components in FIG. 8.

[0274] The communication apparatus 80 includes a communication interface 801 and at least one processor 802.

[0275] The communication apparatus 80 can correspond to any of the computing node, the control plane network element, the user plane network element, or the terminal device. The communication interface 801 is configured to transceive signals, and the at least one processor 802 executes program instructions to cause the communication apparatus 80 to implement the corresponding procedures of the method performed by the corresponding device in the above method embodiments.

[0276] In a possible design, the communication apparatus 80 can correspond to the computing node in the method embodiments of any of the above FIG. 2, FIG. 5, and FIG. 6, and can be the computing node or a chip in the computing node. The communication apparatus 80 can include components configured to perform the operations performed by the computing node in the above method embodiments, and each component in the communication apparatus 80 is respectively configured to implement the operations performed by the computing node in the above method embodiments. Specifically, the communication apparatus 80 can include the following components:

[0277] receiving priority indication information of a to-be-processed computing task, the priority indication information indicating a processing priority of the computing task by the computing node; the priority indication information is obtained based on at least one of task requirement of the computing task and subscription data of a terminal device;

[0278] scheduling the computing task to a first position of a first queue or a second queue of the computing node, or directly scheduling the computing task to a third queue, based on the priority indication information, the first queue being one of multiple different priority queues of the computing node, the second queue being a queue waiting for accessing a coprocessor resource in the computing node, and the third queue being a queue in a coprocessor in the computing node.

[0279] In another possible design, the communication apparatus 80 can correspond to the control plane network element in the method embodiments of any of the above FIG. 2, FIG. 5, and FIG. 6, and can be the control plane network element or a chip in the control plane network element. The communication apparatus 80 can include components configured to perform the operations performed by the control plane network element in the above method embodiments, and each component in the communication apparatus 80 is respectively configured to implement the operations performed by the control plane network element in the above method embodiments. Specifically, the communication apparatus 80 can include the following components:

[0280] generating a computing quality of service (QoS) policy corresponding to a computing task, the computing QoS policy including priority indication information of the computing task, the computing QoS policy being obtained based on at least one of task requirement of the computing task and subscription data of a terminal device;

[0281] sending the computing QoS policy.

[0282] In yet another possible design, the communication device 80 can correspond to a user plane network element in the method embodiments of any of FIG. 2, FIG. 5, and FIG. 6, e.g., the communication device 80 can be a user plane network element or a chip in a user plane network element. The communication device 80 can include means for performing the operations of the user plane network element in the method embodiments described above, and the means in the communication device 80 are respectively configured to perform the operations of the user plane network element in the method embodiments described above. Specifically, the communication device 80 can include the following means:

[0283] receiving a computing quality of service (QoS) policy corresponding to the computing task from the control plane network element, the computing QoS policy including priority indication information of the computing task, the computing QoS policy being derived based on at least one of a task requirement of the computing task and subscription data of the terminal device;

[0284] sending a first data packet, the first data packet carrying marking information including the priority indication information of the computing task, the marking information being generated based on the computing QoS policy.

[0285] In yet another possible design, the communication device 80 can correspond to a terminal device in the method embodiments of any of FIG. 2, FIG. 5, and FIG. 6, e.g., the communication device 80 can be a terminal device or a chip in a terminal device. The communication device 80 can include means for performing the operations of the terminal device in the method embodiments described above, and the means in the communication device 80 are respectively configured to perform the operations of the terminal device in the method embodiments described above. Specifically, the communication device 80 can include the following means:

[0286] sending a computing task request, the computing task request including a task requirement of a computing task, the task requirement being used to generate a computing quality of service (QoS) policy corresponding to the computing task, the computing QoS policy including priority indication information of the computing task.

[0287] In the communication apparatus 80 described in FIG. 8, the terminal device initiates a computing request of a computing task, the control plane network element generates a computing QoS policy based on the subscription data of the terminal device and / or the task requirement of the computing task, and sends the computing QoS policy to the user plane network element. In the scenario where the computing node and the user plane network element are separately arranged, the user plane network element obtains the marked data packet (i.e., the first data packet) based on the computing QoS policy and sends the same, and the priority indication information included in the first data packet can be conveniently delivered to the computing node. In the scenario where the computing node and the user plane network element are arranged together, the computing node can directly obtain the priority indication information. In this way, the processing priority of the computing task is determined by using the task requirement of the computing task and the importance of the user. The computing node processes the computing task according to the processing priority, i.e., selects to schedule the computing task to the co-processor, or to a certain priority queue corresponding to the priority indication information in the CPU of the computing node, or to a certain position corresponding to the priority indication information in the second queue of the CPU of the computing node, so that the computing task of the high task requirement and / or the important user can be processed preferentially, the requirements of these computing tasks are met, and the quality of service of these tasks is guaranteed.

[0288] For the case that the communication apparatus can be a chip or a chip system, refer to the structural schematic diagram of the chip shown in FIG. 9.

[0289] As shown in FIG. 9, the chip 90 includes a processor 901 and an interface 902. The number of the processor 901 can be one or more, and the number of the interface 902 can be multiple. It should be noted that the functions of the processor 901 and the interface 902 can be realized by hardware design, software design, or a combination of software and hardware, which is not limited here.

[0290] Optionally, the chip 90 can further include a memory 903, which is used to store necessary program instructions and data.

[0291] In this application, the processor 901 can be used to call the implementation program of the communication method provided by one or more embodiments of the present application in the terminal device, the network device, or one or more devices or network elements, and execute the instructions contained in the program. The interface 902 can be used to output the execution result of the processor 901. In this application, the interface 902 can be specifically used to output various messages or information of the processor 901.

[0292] For the communication method provided by one or more embodiments of the present application, refer to any of the foregoing FIG. 2, FIG. 5, and FIG. 6 for various embodiments, which will not be repeated here.

[0293] The processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0294] The memory in the embodiments of the present application is used to provide storage space, and the storage space can store data such as an operating system and a computer program. The memory includes but is not limited to a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a compact disc read-only memory (CD-ROM).

[0295] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program runs on one or more processors, the method shown in any of FIG. 2, FIG. 5 and FIG. 6 can be implemented.

[0296] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a computer program product, and the computer program product includes a computer program. When the computer program runs on a processor, the method shown in any of FIG. 2, FIG. 5 and FIG. 6 can be implemented.

[0297] The embodiments of the present application further provide a system, and the system includes at least one communication device 70 or communication device 80 or chip 90 as described above, and is used to execute the steps executed by the corresponding device in any of the embodiments of FIG. 2, FIG. 5 and FIG. 6.

[0298] The embodiment of the present application further provides a system, which comprises at least one of a computing node, a control plane network element, a user plane network element and a terminal device, the computing node is used for executing the steps executed by the computing node in any one of the illustrated embodiments of FIG. 2, FIG. 5 and FIG. 6, the control plane network element is used for executing the steps executed by the control plane network element in any one of the illustrated embodiments of FIG. 2, FIG. 5 and FIG. 6, the user plane network element is used for executing the steps executed by the user plane network element in any one of the illustrated embodiments of FIG. 2, FIG. 5 and FIG. 6, and the terminal device is used for executing the steps executed by the terminal device in any one of the illustrated embodiments of FIG. 2, FIG. 5 and FIG. 6.

[0299] The embodiment of the present application further provides a processing device, comprising a processor and an interface; the processor is used for executing the method in any one of the method embodiments.

[0300] It should be understood that the processing device described above can be a chip. For example, the processing device can be a field programmable gate array (FPGA), a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can also be a system chip (SoC), a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), a micro controller unit (MCU), a programmable logic device (PLD) or other integrated chip. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software modules in the coding processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.

[0301] It is to be appreciated that the memory in the embodiments of this application can be volatile, nonvolatile, or a combination of both. By way of example, and without limitation, nonvolatile memory can include read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), a flash memory, or a combination of these. Volatile memory can include random-access memory (RAM), which acts as external cache. By way of example and without limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM). Proper selection of memory will depend on factors such as costs and technical specifications of the system or computer in which the memory is employed.

[0302] In the embodiments described above, all or some of the steps can be implemented by using software, hardware, firmware or any combination thereof. When implemented by using software, all or some of the steps can be implemented by using one or more computer programs. When implemented by using computer programs, the computer programs can be stored in one or more computer program products. The computer program products include one or more computer readable storage media (media) on which the computer programs are stored. The computer readable storage media can be tangible media, such as one or more types of disk including floppy disks, optical disks, CD-ROMs, DVDs, Blu-ray discs, hard disks, solid state drives (SSDs), or any other type of tangible media suitable for storing electronic data. The computer readable storage media can also be a computer readable storage medium that is integrated with a computer system (e.g., a solid state drive (SSD) integrated with a computer system), a computer readable storage medium that is separate from a computer system (e.g., a USB flash drive), or a computer readable storage medium that is used in combination with a computer system (e.g., a floppy disk used in combination with a computer system). The computer programs can be downloaded to the computer from one or more computer program products (e.g., from a website, using a computer network, such as the Internet) or can be uploaded to the computer from one or more computer program products (e.g., from a computer network, such as the Internet). The computer programs can be executed by one or more computer processors (e.g., one or more processors of a computer system).

[0303] The units in the various device embodiments and the electronic devices in the method embodiments fully correspond, and the corresponding steps are performed by the corresponding modules or units, for example, the communication unit (transceiver) performs the steps of receiving or sending in the method embodiments, and other steps except sending and receiving can be performed by the processing unit (processor). The functions of the specific units can refer to the corresponding method embodiments. The processor can be one or more.

[0304] It can be understood that the electronic device in the embodiments of the present application can perform some or all of the steps in the embodiments of the present application, and these steps or operations are only examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, each step can be performed in a different order from the order presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application are performed.

[0305] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0306] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0307] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0308] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0309] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0310] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk, and various media that can store program codes.

[0311] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A communication method characterized by comprising: The method comprises: receiving priority indication information of a to-be-processed computing task, the priority indication information indicating a processing priority of the computing task by a computing node; the priority indication information is obtained based on at least one of task requirements of the computing task and subscription data of a terminal device; scheduling the computing task to a first position of a first queue or a second queue of the computing node or directly scheduling the computing task to a third queue based on the priority indication information, the first queue being one of multiple different priority queues in the computing node, the second queue being a queue waiting for access to a coprocessor resource in the computing node, and the third queue being a queue in a coprocessor in the computing node.

2. The method of claim 1, wherein, The computing node is arranged separately from a user plane network element; and the receiving of the priority indication information of the to-be-processed computing task comprises: receiving a first data packet from the user plane network element, the first data packet carrying marking information including the priority indication information, the marking information being obtained based on a computing quality of service (QoS) policy corresponding to the computing task.

3. The method of claim 1, wherein, The computing node is arranged together with a user plane network element; The receiving of the priority indication information of the to-be-processed computing task comprises: receiving a computing QoS policy corresponding to the computing task from a control plane network element, the computing QoS policy including priority indication information and a computing time delay requirement of the computing task, the computing QoS policy being obtained based on at least one of task requirements of the computing task and subscription data of the terminal device.

4. The method according to any one of claims 1 to 3, characterized in that, The scheduling of the computing task to the first position of the first queue or the second queue of the computing node or the direct scheduling of the computing task to the third queue based on the priority indication information comprises: in a case where the priority indication information indicates that the processing priority of the computing task is a highest priority in multiple processing priorities, directly scheduling the computing task to the third queue; in a case where the priority indication information indicates that the processing priority of the computing task is not the highest priority in the multiple processing priorities, scheduling the computing task to the first position of the first queue or the second queue based on the priority indication information, the first queue and the second queue being queues in a central processing unit (CPU) in the computing node.

5. The method according to any one of claims 1 to 5, characterized in that, The CPU in the computing node includes multiple priority queues, and the scheduling of the computing task to the first queue based on the priority indication information comprises: scheduling the computing task to the first queue based on the priority indication information, the priority indication information indicating that the higher the priority level of the processing priority of the computing task is, the higher the priority level of the first queue is.

6. The method according to any one of claims 1 to 5, characterized in that, The queue waiting for access to the coprocessor resource in the CPU in the computing node includes one queue, and the scheduling of the computing task to the first position of the second queue based on the priority indication information comprises: The computing task is scheduled to a first position of the second queue based on the priority indication information, and the higher the priority level of the processing priority of the computing task indicated by the priority indication information, the closer the first position to a de-queue position.

7. The method according to any one of claims 1 to 6, characterized in that, The task requirement of the computing task comprises at least one of an end-to-end delay requirement, a required bandwidth, and a computing resource type of the computing task.

8. The method according to any one of claims 1 to 7, characterized in that, The subscription data of the terminal device comprises at least one of a user subscription type and a service assurance level.

9. A communication method characterized by comprising: The method comprises: generating a computing quality of service (QoS) policy corresponding to the computing task, wherein the computing QoS policy comprises priority indication information of the computing task, and the computing QoS policy is obtained based on at least one of a task requirement of the computing task and subscription data of a terminal device; sending the computing QoS policy.

10. The method of claim 9, wherein, The task requirement of the computing task comprises at least one of an end-to-end delay requirement, a required bandwidth, and a computing resource type of the computing task.

11. The method according to claim 9 or 10, characterized in that, The subscription data of the terminal device comprises at least one of a user subscription type and a service assurance level.

12. A communication method characterized by comprising: The method comprises: receiving, from a control plane network element, a computing quality of service (QoS) policy corresponding to a computing task, wherein the computing QoS policy comprises priority indication information of the computing task, and the computing QoS policy is obtained based on at least one of a task requirement of the computing task and subscription data of a terminal device; sending a first data packet, wherein the first data packet carries marking information comprising the priority indication information of the computing task, and the marking information is generated based on the computing QoS policy.

13. A method of communication, comprising: The method comprises: sending a computing task request, wherein the computing task request comprises a task requirement of a computing task, and the task requirement is used to generate a computing quality of service (QoS) policy corresponding to the computing task, wherein the computing QoS policy comprises priority indication information of the computing task.

14. A communications device, characterized by The apparatus comprises means for implementing the method of any one of claims 1 to 8, claims 9-11, claim 12, claim 13.

15. A communications device, characterized by The apparatus comprises a processor configured to cause the apparatus to implement the method of any one of claims 1 to 8, claims 9-11, claim 12, claim 13.

16. A communications device, characterized by The apparatus comprises a logic circuit and an interface, and the logic circuit and the interface are coupled; The interface is configured to input and / or output information, and the logic circuit is configured to cause the communication apparatus to implement the method of any one of claims 1 to 8, claims 9-11, claim 12, claim 13.

17. A computer-readable storage medium, characterized in that, The computer readable storage medium is configured to store a computer program, and the computer program is configured to be executed to implement the method of any one of claims 1 to 8, claims 9-11, claim 12, claim 13.

18. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is configured to be executed to implement the method of any one of claims 1 to 8, claims 9-11, claim 12, claim 13.

19. A communication system, characterized by The apparatus comprises at least one of: a computing node, a control plane network element, a user plane network element, and a terminal device. The computing node is configured to perform the method of any one of claims 1 to 8, the control plane network element is configured to perform the method of any one of claims 9 to 11, the user plane network element is configured to perform the method of claim 12, and the terminal device is configured to perform the method of claim 13.

Images