Computing and network service processing method and related device

Abstract

The present disclosure relates to the technical field of communications. Provided are a computing and network service processing method and a related device. The method comprises: on the basis of a computing and network service request, determining a computing and network service data volume, a computing and network service priority, a terminal-side computing delay range and a local round-trip delay; interacting with another network element to determine a computing power QoS, so as to determine a PCC rule; and finally deciding a computing and network QoS policy and a PFCP rule. By means of interaction, a computing and network QoS indicator required by a computing and network service is pre-allocated, resources required by a network and computing power are allocated, and collaborative scheduling is performed on computing power resources and network resources, so as to achieve the objective of computing and network integration.

Description

Method and related device for processing network service

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority to Chinese Patent Application No. 202411322442.8, filed on September 20, 2024, entitled "Method and related device for processing network service", the entire contents of which are incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the field of communication technology, and particularly relates to a method and related device for processing network service. BACKGROUND

[0004] The Quality of Service (QoS) mechanism defined in the network architecture of the 3rd Generation Partnership Project (3GPP) is only considering network QoS indicators such as network delay, bandwidth, packet loss rate, etc.

[0005] In the related art, the QoS indicators do not consider the computing power QoS indicators for emerging services with computing requirements, so the end-to-end service experience of the mobile computing power network cannot be effectively guaranteed.

[0006] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] The present disclosure provides a method and related device for processing network service, which at least partially overcomes the problem that the end-to-end service experience of the mobile computing power network cannot be effectively guaranteed in the related art.

[0008] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0009] In a first aspect, the embodiments in the present disclosure provide a method for processing network service, the method comprising:

[0010] receiving a network service request;

[0011] determining a network service data volume, a network service priority, an end-side computing delay range, and a local round-trip delay according to the network service request;

[0012] sending the network service data volume, the network service priority, the end-side computing delay range, the local round-trip delay, and the network service request.

[0013] In a second aspect, the embodiments in the present disclosure provide a method for processing computing network service, the method comprising:

[0014] receiving computing network service data volume, computing network service priority, end-side computing delay range, local round-trip delay, and computing network service request;

[0015] deciding computing power QoS (Quality of Service) of the computing network service request according to the computing network service data volume, the computing network service priority, and current available computing power resource;

[0016] determining computing network strategy and PCC (Policy and Charging Control) rule of the computing network service request according to the computing network service data volume, the end-side computing delay range, the local round-trip delay, and the computing power QoS;

[0017] sending the computing network PCC rule.

[0018] In a third aspect, the embodiments in the present disclosure provide a method for processing computing network service, the method comprising:

[0019] receiving computing network PCC rule; the computing network PCC rule at least comprises computing power QoS, end-side computing delay range, uplink and downlink GBR (Guaranteed Bit Rate), uplink and downlink MBR (Maximum Bit Rate), and first uplink and downlink PDB (Packet Delay Budget);

[0020] deciding computing network QoS (Quality of Service) strategy according to the computing network PCC rule; the computing network QoS strategy at least comprises uplink and downlink GFBR (Guaranteed Flow Bit Rate), uplink and downlink MFBR (Maximum Flow Bit Rate), second uplink and downlink PDB (Packet Delay Budget) and CDB (Computing Delay Budget), and matched computing power QoS;

[0021] generating computing network PFCP (Packet Forwarding Control Protocol) rule according to the computing network QoS strategy; the computing network PFCP rule is used to indicate processing mode of processing data of the computing network service;

[0022] sending the computing network PFCP rule and computing network service response.

[0023] In a fourth aspect, the embodiments in the present disclosure provide a method for processing computing network service, the method comprising:

[0024] sending computing network service request;

[0025] receiving computing network service response.

[0026] In a fifth aspect, the embodiments in the present disclosure provide an application function network element, comprising:

[0027] a memory configured to store a computer program;

[0028] a transceiver configured to transceive information under control of the processor;

[0029] The processor is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to receive the computing network service request; determining the computing network service data volume, the computing network service priority, the end-side computing delay range and the local round-trip delay according to the computing network service request; and controlling the transceiver to send the computing network service data volume, the computing network service priority, the end-side computing delay range, the local round-trip delay and the computing network service request.

[0030] In a sixth aspect, the embodiments in the present disclosure provide a computing network policy control and computing network management device, comprising:

[0031] The memory is configured to store the computer program.

[0032] The transceiver is configured to transceive information under the control of the processor.

[0033] The processor is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to receive the computing network service data volume, the computing network service priority, the end-side computing delay range, the local round-trip delay and the computing network service request; determining the computing network PCC rule of the computing network service request according to the computing network service data volume, the end-side computing delay range, the local round-trip delay and the computing power QoS; and controlling the transceiver to send the computing network PCC rule.

[0034] In a seventh aspect, the embodiments in the present disclosure provide a session management function network element, comprising:

[0035] The memory is configured to store the computer program.

[0036] The transceiver is configured to transceive information under the control of the processor.

[0037] The processor is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to receive the computing network PCC rule; the computing network PCC rule at least includes: the computing power QoS, the end-side computing delay range, the uplink and downlink GBR, the uplink and downlink MBR, the first uplink and downlink PDB; determining the computing network QoS policy and the computing network PFCP rule according to the computing network PCC rule; the computing network QoS policy at least includes: the uplink and downlink GFBR, the uplink and downlink MFBR, the second uplink and downlink PDB and CDB, and the matched computing power QoS; the computing network PFCP rule is configured to indicate the processing mode of processing the data of the computing network service; and controlling the transceiver to send the computing network PFCP rule and the computing network service response.

[0038] In an eighth aspect, the embodiments in the present disclosure provide a user equipment, comprising:

[0039] The memory is configured to store the computer program.

[0040] a transceiver configured to transceive information under control of the processor;

[0041] a processor configured to read a computer program in the memory and perform the following steps: control the transceiver to send a network service request; and control the transceiver to receive a network service response.

[0042] In a ninth aspect, an electronic device is provided, comprising: a processor; and a memory configured to store executable instructions of the processor; wherein the processor is configured to perform the method of the first aspect via execution of the executable instructions.

[0043] In a tenth aspect, a computer-readable storage medium is provided, having a computer program stored thereon, the computer program being executed by a processor to implement the method of the first aspect.

[0044] In an eleventh aspect, according to another aspect of the present disclosure, a computer program product or computer program is also provided, the computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method of any one of the above aspects.

[0045] The method comprises the following steps: receiving a calculation network service request; determining a calculation network service data volume, a calculation network service priority, an end-side calculation delay range and a local round-trip delay according to the calculation network service request; sending the calculation network service data volume, the calculation network service priority, the end-side calculation delay range, the local round-trip delay and the calculation network service request; deciding a calculation power QoS (Quality of Service) of the calculation network service request according to the calculation network service data volume, the calculation network service priority and a current available calculation power resource; determining a calculation network strategy and a PCC (Policy and Charging Control) rule of the calculation network service request according to the calculation network service data volume, the end-side calculation delay range, the local round-trip delay and the calculation power QoS; sending the calculation network PCC rule, wherein the calculation network PCC rule at least comprises the calculation power QoS, the end-side calculation delay range, an uplink / downlink GBR (Guaranteed Bit Rate), an uplink / downlink MBR (Maximum Bit Rate), a first uplink / downlink PDB (Packet Delay Budget) and a calculation delay budget CDB; deciding a calculation network QoS strategy according to the calculation network PCC rule, wherein the calculation network QoS strategy at least comprises an uplink / downlink GFBR (Guaranteed Flow Bit Rate), an uplink / downlink MFBR (Maximum Flow Bit Rate), a second uplink / downlink PDB and the matched calculation power QoS; generating a calculation network PFCP (Packet Forwarding Control Protocol) rule according to the calculation network QoS strategy, wherein the calculation network PFCP rule is used for indicating a processing mode of processing data of the calculation network service; and sending the calculation network PFCP rule and a calculation network service response. The calculation network QoS indicators required by the calculation network service are pre-allocated, the resources required on the network and the calculation power are allocated, the original network QoS is converted into the calculation network QoS, the goal of the calculation network integration is achieved, the calculation power resources and the network resources are collaboratively scheduled, and finally the end-to-end performance requirement of the service is met, thereby providing the end-edge-cloud collaborative strategy and the service performance guarantee for the calculation network service.

[0046] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0047] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained according to these drawings without creative labor for those skilled in the art.

[0048] FIG. 1 shows one of the flowcharts of the calculation network service processing method in the embodiments of the present disclosure;

[0049] FIG. 2 shows the second flowchart of the calculation network service processing method in the embodiments of the present disclosure;

[0050] FIG. 3 shows the third flowchart of the calculation network service processing method in the embodiments of the present disclosure;

[0051] Figure 4 shows a fourth flow chart of a method for processing network service in an embodiment of the present disclosure;

[0052] Figure 5 shows a fifth flow chart of a method for processing network service in an embodiment of the present disclosure;

[0053] Figure 6 shows a flow chart of a method for determining network service quality policy in an embodiment of the present disclosure;

[0054] Figure 7 shows a sixth flow chart of a method for processing network service in an embodiment of the present disclosure;

[0055] Figure 8 shows an interaction diagram of a method for processing network service in an embodiment of the present disclosure;

[0056] Figure 9 shows a structural diagram of an application function network element in an embodiment of the present disclosure;

[0057] Figure 10 shows a structural diagram of a network policy control and network management device in an embodiment of the present disclosure;

[0058] Figure 11 shows a structural diagram of a session management function network element in an embodiment of the present disclosure;

[0059] Figure 12 shows a structural diagram of a user equipment in an embodiment of the present disclosure;

[0060] Figure 13 shows a structural diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0061] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations can be implemented in any

[0062] Moreover, the drawings are not necessarily to scale. Like reference numerals can be used to denote like parts throughout the specification. Some of the blocks in the drawings can be functional blocks that can employ software, hardware, firmware, or a combination thereof for operation. Some of the blocks in the drawings can be implemented as software modules or code on a machine-readable medium.

[0063] It should be noted that the acquisition, storage, use, processing and the like of data in the technical solutions of the present disclosure comply with relevant regulations. The personal identity data, operation data, behavior data and other types of data of individuals, customers and crowds and the like obtained in the embodiments of the present disclosure have obtained consent.

[0064] The terms appearing in the present disclosure are explained as follows:

[0065] User Equipment (UE): various types of terminal devices with wireless communication functions and supporting user access to network services.

[0066] Radio Access Network (RAN): provides wireless access control, data transmission and the like for user equipment in a specific area, and supports wireless sensing, obtaining sensing measurement data for a specific area or target.

[0067] Application Function (AF): interacts with the 5G core network and provides network services and capabilities for third-party applications.

[0068] Data Network (DN): a network entity for communication between user equipment and external data networks.

[0069] Session Management Function (SMF): mainly responsible for the creation, modification, maintenance and release of sessions, including managing session connections between user equipment and data networks, and selecting appropriate user plane functions to forward data packets.

[0070] User Plane Function (UPF): responsible for routing and forwarding functions of user plane data packets.

[0071] Computing and Network Management Function (CNMF): responsible for the management of computing power and network coordination.

[0072] Policy Control Function (PCF): provides all mobility, UE access selection and Protocol Data Unit (PDU) session-related policies under its responsibility.

[0073] Access and Mobility Management Function (AMF): responsible for tasks such as registration, connection, separation and mobility management of UE.

[0074] N6(N6 Interface) latency: N6 interface is the interface between PDU Session Anchor UPF (PSA UPF) and DN, and N6 latency refers to the transmission latency on the N6 interface.

[0075] The present example embodiment will be described in detail below in conjunction with the accompanying drawings and examples.

[0076] First, FIG. 1 shows one of the flowcharts of the method for processing network calculation service in the embodiments of the present disclosure, as shown in FIG. 1, the method provided in the embodiments of the present disclosure can be applied to AF network element, and the method includes the following steps:

[0077] S102: receiving a network calculation service request.

[0078] S104: determining the network calculation service data volume, the network calculation service priority, the end-side calculation latency range, and the local round-trip latency according to the network calculation service request.

[0079] S106: sending the network calculation service data volume, the network calculation service priority, the end-side calculation latency range, the local round-trip latency, and the network calculation service request.

[0080] In one possible embodiment, the network calculation service can include various types of services, such as training large models, computing services, immersive communication, artificial intelligence and communication integration, and other application scenarios.

[0081] In one possible embodiment, the network calculation service request at least includes: a user equipment identifier, a network calculation service identifier, and a network calculation service requirement.

[0082] In one possible embodiment, the network calculation service request further includes: a PDU session identifier.

[0083] In one possible embodiment, the network calculation service data volume includes: a required data volume for calculation and a required data volume for uplink and downlink transmission.

[0084] The manner of determining the network calculation service data volume can include: determining the network calculation service data volume according to the network calculation service requirement and the network calculation service identifier in the network calculation service request.

[0085] In one possible embodiment, the network calculation service requirement at least includes: inference accuracy, security requirement, and power consumption requirement.

[0086] The manner of determining the network calculation service data volume can include: determining the required data volume for calculation and the required data volume for uplink and downlink transmission according to the inference accuracy, the security requirement, the power consumption requirement, and the network calculation service identifier.

[0087] In a possible embodiment, the AF network element determines the total data volume involved in the algorithm network service according to the received algorithm network service demand and algorithm network service identifier, and determines the first data volume and the second data volume in the total data volume according to the inference accuracy, the security requirement, the power consumption requirement and other parameters.

[0088] The first data volume can be understood as how much data needs to be processed and calculated by the user equipment, i.e., the end side, and the second data volume can be understood as how much data can be obtained from the user equipment side.

[0089] The security requirement determines the lower limit of the UE local calculation data volume, and the power consumption requirement and the calculation capability determine the upper limit of the UE local calculation data volume and the calculation time delay.

[0090] In a possible embodiment, when the security requirement is greater than a preset security threshold, the algorithm network service demand further includes the calculation capability.

[0091] The manner of determining the algorithm network service data volume can include determining the required data volume for calculation and the required data volume for uplink and downlink transmission according to the inference accuracy, the security requirement, the power consumption requirement, the calculation capability and the algorithm network service identifier.

[0092] In a possible embodiment, the AF network element can pre-allocate the network resources and the computing power resources required by the algorithm network service according to the algorithm network service request, i.e., the user equipment has not sent the actual data content involved in the algorithm network service to the network element, but only sent the algorithm network service request, the AF network element can determine how much network resources and computing power resources are required by this algorithm network service request, the network element side then performs actual resource allocation, feeds back to the user equipment side, and establishes an algorithm network service session channel, and then the user equipment side transmits the algorithm network service data for processing by the network side.

[0093] In a possible embodiment, the manner of determining the end side calculation time delay range can include determining the range of the user equipment local calculation data volume according to the algorithm network service demand and the algorithm network service identifier, and determining the end side calculation time delay range according to the range of the user equipment local calculation data volume and the algorithm network service demand.

[0094] In a possible embodiment, the local round-trip time in the present disclosure can be understood as the total two-way time delay of the algorithm network service between the UE and the UPF of the terminal N6 interface, including the two-way transmission time delay between the UE and the UPF of the terminal N6 interface and the calculation time delay of each algorithm network node.

[0095] The overall round-trip time in the present disclosure is the RTT (Round-Trip Time) delay, which can be the total two-way time delay from the start of the UE sending the algorithm network service to the reception of the algorithm network result, including the two-way transmission time delay and the calculation time delay of each algorithm network node.

[0096] In a possible embodiment, the AF network element determines the local round-trip delay without involving the cloud computing network node in the whole process of processing the computing network service.

[0097] The manner of determining the local round-trip delay can include: determining the local round-trip delay of the computing network service request according to the computing network service identifier and the computing network service requirement; and when the cloud computing network node does not participate in the process of the computing network service, the local round-trip delay is equal to the overall round-trip delay RTT of the computing network service request.

[0098] In a possible embodiment, the manner of determining the priority of the computing network service can include: determining the priority of the computing network service according to at least one of the UE identifier, the computing network service identifier, and the computing network service requirement.

[0099] For example, the UE identifier and the computing network service identifier are directly associated with a specific priority, and one computing network service can be decomposed into one or more tasks, and the tasks can also be associated with specific priorities, respectively. For another example, the lower the RTT delay requirement or the higher the inference accuracy requirement in the computing network service requirement, the higher the priority.

[0100] After the AF network element determines the data volume of the computing network service, the priority of the computing network service, the end-side computing delay range, and the local round-trip delay, the AF network element sends the data to a subsequent network element. The subsequent network element can be a computing network policy control and computing network management device. The computing network policy control and computing network management device can be a CNMF network element and a PCF network element, or a PCF network element. The CNMF network element can belong to a core network and exist in the form of an independent network element or a functional module. The CNMF network element and the PCF can be combined into one, that is, the PCF network element has both the computing network management function and the computing network policy control function.

[0101] The CNMF network element can also be an external system that does not belong to the core network but can interact with the core network, which is not limited in the present solution. The CNMF network element is a device with a computing network management function, which is referred to as CNMF in the present disclosure, but is not limited to this name.

[0102] In a possible implementation, when the computing network policy control and computing network management device is a PCF network element. FIG. 2 shows a flowchart of another method for processing a computing network service according to an embodiment of the present disclosure. As shown in FIG. 2, the method provided in the embodiment of the present disclosure includes the following steps when applied to the PCF network element:

[0103] S202: receiving the data volume of the computing network service, the priority of the computing network service, the end-side computing delay range, the local round-trip delay, and the computing network service request.

[0104] S204: determining the computing power QoS quality of service of the computing network service request according to the data volume of the computing network service, the priority of the computing network service, and the currently available computing power resource.

[0105] In a possible embodiment, the computing power QoS at least includes: at least one computing power QoS sequence number, a computing power resource type corresponding to each computing power QoS sequence number, a computing power resource size, and a first total computing time delay.

[0106] S206: According to the computing network service data volume, the end-side computing time delay range, the local round-trip time delay, and the computing power QoS, determine the computing network strategy and the charging control rule of the computing network service request.

[0107] In a possible embodiment, the computing network strategy and the charging control (Policy and Charging Control, PCC) at least includes: the computing power QoS, the end-side computing time delay range, the uplink and downlink guaranteed bit rate (Guaranteed Bit Rate, GBR), the uplink and downlink maximum bit rate (Maximum Bit Rate, MBR), and the first uplink and downlink packet delay budget (Packet Delay Budget, PDB).

[0108] S208: Send the computing network PCC rule.

[0109] In a possible embodiment, the manner of deciding the computing power QoS of the computing network service request can include: deciding the computing power QoS of the computing network service request according to the required data volume for computing, the computing network service priority, and the currently available computing power resource.

[0110] In a possible embodiment, the manner of determining the computing network PCC rule of the computing network service request can include: determining the transmission time delay of the uplink and downlink transmission according to the required data volume for the uplink and downlink transmission; and determining the computing network PCC rule of the computing network service request according to the transmission time delay, the end-side computing time delay range, the local round-trip time delay, and the first total computing time delay in the computing power QoS.

[0111] The list of the computing power QoS is illustrated by taking Table 1 as an example, as shown in Table 1:

[0112] Table 1

[0113] As shown in Table 1, each computing power QoS sequence number corresponds to an allocation manner, and the allocation manner specifically includes: a computing power resource type, a computing power resource size corresponding to each computing power resource type, and a first total computing time delay.

[0114] The one computing power QoS sequence number can correspond to at least one computing power resource type. The computing power resource type can at least include one of the following: CPU, GPU, and DPU.

[0115] In a possible embodiment, the information of the currently available computing power resources includes the locations (UE / RAN / UPF / cloud) and corresponding sizes of various types of computing power resources.

[0116] In a possible embodiment, the first total computing time delay includes a first total computing time delay upper limit and a first total computing time delay lower limit; the first total computing time delay upper limit is determined according to the algorithm network service priority; and the first total computing time delay lower limit is determined according to the currently available computing power resources.

[0117] In a possible embodiment, the size of the computing power resource corresponding to each computing power QoS sequence number is between a computing power resource upper limit and a computing power resource lower limit; the computing power resource upper limit is determined according to the currently available computing power resources; and the computing power resource lower limit is determined according to the algorithm network service priority.

[0118] Exemplarily, when the PCF makes a decision, the currently available computing power resources determine the computing power resource upper limit and the total computing time delay lower limit, and the algorithm network service priority determines the computing power resource lower limit and the total computing time delay upper limit.

[0119] Taking the content in Table 1 as an example, if the currently available computing power resources are 10, the currently available computing power resources are allocated to the algorithm network service, and 10 is used up, it is assumed that the first total computing time delay that can be obtained is 3 ms. For example, the first total computing time delay upper limit determined according to the algorithm network service priority is 10 ms. The computing power resource lower limit determined according to the algorithm network service priority is 2.

[0120] Based on this, when determining the computing power QoS list, max{M1+N1, L2+M2+N2, …, Xn}≤10, 2≤min{M1+N1, L2+M2+N2, …, Xn} should be followed. And the first total computing time delay D1 / D2 / … / Dn corresponding to the row where M1+N1, L2+M2+N2, …, Xn are located should be greater than or equal to 3 ms and less than or equal to 10 ms.

[0121] In a possible embodiment, the GBR, MBR, and PDB in the algorithm network PCC rule in the present disclosure are determined according to the network QoS and the computing power QoS, which is different from the manner in the related art.

[0122] In a possible embodiment, the PCF network element also interacts with the SMF network element in the process of processing the algorithm network service, and can specifically include: receiving an algorithm network node creation request sent by a current session management function SMF network element; determining whether to insert an algorithm network node for the algorithm network service according to the algorithm network node creation request; if yes, sending an algorithm network node creation response, the algorithm network node creation response at least including: inserted algorithm network node information and matched target computing power QoS.

[0123] In a possible implementation, if the inserted computing node is a user plane function (UPF) managed by another SMF, the computing node creation response further includes an identifier of the other SMF.

[0124] In a possible implementation, if the inserted computing node is a cloud computing node, the computing node creation response further includes a second total computing delay and an N6 transmission delay of the cloud computing node.

[0125] In another possible implementation, when the computing policy control and computing management device includes a CNMF network element and a PCF network element, FIG. 3 and FIG. 4 respectively show a flowchart three and four of a method for processing a computing service according to an embodiment of the present disclosure.

[0126] FIG. 3 shows a flowchart three of a method for processing a computing service according to an embodiment of the present disclosure. As shown in FIG. 3, the method provided in the embodiment of the present disclosure includes the following steps when applied to a CNMF network element:

[0127] S302: receiving a computing service data volume, a computing service priority, an end-side computing delay range, a local round-trip delay, and a computing service request.

[0128] S304: determining a computing power QoS (quality of service) for the computing service request according to the computing service data volume, the computing service priority, and a currently available computing power resource.

[0129] S306: sending the computing service data volume, the end-side computing delay range, the local round-trip delay, the computing service request, and the computing power QoS.

[0130] In a possible implementation, the CNMF network element can send a running mode of the computing service to an application function (AF) network element.

[0131] FIG. 4 shows a flowchart four of a method for processing a computing service according to an embodiment of the present disclosure. As shown in FIG. 4, the method provided in the embodiment of the present disclosure includes the following steps when applied to a PCF network element:

[0132] S402: receiving a computing service data volume, an end-side computing delay range, a local round-trip delay, a computing service request, and a computing power QoS.

[0133] S404: determining a computing PCC (policy control and computation) rule for the computing service request according to the computing service data volume, the end-side computing delay range, the local round-trip delay, and the computing power QoS.

[0134] S406: sending the computing PCC rule.

[0135] The specific process of processing the computing service is described in the above embodiments, which will not be repeated here.

[0136] FIG. 5 shows a flowchart of a fifth method for processing network calculation service according to an embodiment of the present disclosure. As shown in FIG. 5, the method provided in the embodiment of the present disclosure can be applied to an SMF network element, and includes the following steps:

[0137] S502: receiving a network calculation PCC rule, the network calculation PCC rule at least including: a computing power QoS, an end-side computing delay range, an uplink and downlink GBR, an uplink and downlink MBR, and a first uplink and downlink PDB.

[0138] S504: determining a network calculation QoS policy according to the network calculation PCC rule.

[0139] The network calculation QoS includes the computing power QoS and a network QoS.

[0140] The network calculation QoS policy at least includes: an uplink and downlink GFBR, an uplink and downlink MFBR, a second uplink and downlink PDB, a computing delay budget (CDB), and a matched computing power QoS.

[0141] S506: generating a network calculation PFCP rule according to the network calculation QoS policy.

[0142] The network calculation PFCP rule is used to indicate a processing manner of processing data of the network calculation service.

[0143] S508: sending the network calculation PFCP rule and a network calculation service response.

[0144] In a possible embodiment, a manner of determining the uplink and downlink GFBR in the network calculation QoS policy can include: determining the uplink and downlink GFBR according to the uplink and downlink GBR.

[0145] In a possible embodiment, a manner of determining the uplink and downlink MFBR in the network calculation QoS policy can include: determining the uplink and downlink MFBR according to the uplink and downlink MBR.

[0146] In a possible embodiment, a manner of determining the second uplink and downlink PDB in the network calculation QoS policy can include: determining the second uplink and downlink PDB according to the first uplink and downlink PDB.

[0147] In a possible embodiment, the PDB includes an access network packet delay budget (AN-PDB) and a core network packet delay budget (CN-PDB).

[0148] In a possible embodiment, the CDB at least includes a device-side computing delay budget (DS-CDB) and an edge-side computing delay budget (ES-CDB). The DS-CDB is within the range of end-side computing latency.

[0149] The device-side DS-CDB and the edge-side ES-CDB respectively define the upper limit of the computing latency of the algorithm network service at the end side and the edge side, and need to be respectively sent to the UE, the RAN, and / or the UPF.

[0150] In a possible embodiment, the algorithm network service response includes a QoS profile, and the QoS profile includes the algorithm network QoS policy. The QoS profile is sent to the RAN, and the sending manner can include: sending the QoS profile to the RAN via an access and mobility management function (AMF) network element.

[0151] In a possible embodiment, the algorithm network service response includes QoS rules and / or QoS parameters, and the QoS rules and / or QoS parameters include the algorithm network QoS policy. The QoS rules and / or QoS parameters are sent to the UE, and the sending manner can include: sending the QoS rules and / or QoS parameters to the user equipment via the AMF network element and the RAN.

[0152] In a possible embodiment, according to the algorithm network PCC rule, the decision of the algorithm network QoS policy can include the following manner, which is described in the following three cases.

[0153] Case 1:

[0154] In a possible embodiment, it is determined whether the first computing resource of the radio access network (RAN) and the UPF serving the user equipment meets the requirement of the computing power QoS, and if the first computing resource meets the requirement, a matched first computing power QoS is determined. According to the first computing power QoS, the DS-CDB and the ES-CDB are determined.

[0155] Case 2:

[0156] In a possible embodiment, if the first computing resource does not meet the requirement, it is determined whether a second computing resource of another UPF in the management range meets the requirement of the computing QoS; if the second computing resource meets the requirement, a matched second computing QoS is determined; and the DS-CDB and the ES-CDB are determined according to the second computing QoS.

[0157] Case 3:

[0158] In a possible embodiment, if the second computing resource does not meet the requirement, a new algorithm network node creation request is initiated; a new algorithm network node creation response is received, the new algorithm network node creation response at least including inserted algorithm network node information and matched target computing QoS; and the DS-CDB and the ES-CDB are determined according to the target computing QoS.

[0159] Case 3 is divided into two embodiments for illustration.

[0160] Embodiment 1:

[0161] When the algorithm network node information includes a UPF in the management range of another SMF, the new algorithm network node creation response further includes an identifier of the other SMF.

[0162] When the algorithm network node information includes a UPF in the management range of another SMF, the current SMF interacts with the other SMF according to a PFCP rule, such as routing information required when routing algorithm network data between UPFs, and algorithm service identifiers.

[0163] Embodiment 2:

[0164] When the new algorithm network node creation response includes a cloud algorithm network node, the new algorithm network node creation response further includes a second total computing delay and an N6 transmission delay of the cloud algorithm network node.

[0165] When the new algorithm network node creation response includes a cloud algorithm network node, the algorithm QoS policy can include determining the DS-CDB and the ES-CDB according to the target computing QoS and the second total computing delay of the cloud algorithm network node, and adjusting the first PDB to obtain the second PDB according to the N6 transmission delay of the cloud algorithm network node.

[0166] FIG. 6 shows a flowchart of a decision algorithm QoS policy in an embodiment of the present disclosure, as shown in FIG. 6, including the following steps:

[0167] S602: It is determined whether the first computing resource of the radio access network (RAN) and the UPF serving the user equipment meets the requirement of the computing QoS; if yes, S604 is performed; if no, S608 is performed.

[0168] S604: A matched first computing QoS is determined.

[0169] S606: Determine the DS-CDB and ES-CDB according to the first computing power QoS.

[0170] S608: Determine whether the second computing power resource of other UPF in the management range meets the requirement of the computing power QoS; if yes, perform S610; if not, perform S614.

[0171] S610: Determine the matched second computing power QoS.

[0172] S612: Determine the DS-CDB and ES-CDB according to the second computing power QoS.

[0173] S614: Initiate a new algorithm network node request.

[0174] S616: Receive a new algorithm network node response, which at least includes inserted algorithm network node information and matched target computing power QoS.

[0175] S618: Determine the DS-CDB and ES-CDB according to the target computing power QoS.

[0176] In a possible embodiment, based on the above cases 1-3, the sending algorithm network PFCP rule can include the following three cases.

[0177] Case 1:

[0178] In a possible embodiment, the algorithm network PFCP rule is sent to the UPF serving the user equipment through the N4 session modification request.

[0179] Case 2:

[0180] In a possible embodiment, the algorithm network PFCP rule is sent to the UPF serving the user equipment through the N4 session modification request; and the algorithm network PFCP rule is sent to other UPF in the SMF management range through the N4 session establishment request.

[0181] Case 3:

[0182] In a possible embodiment, the algorithm network PFCP rule is sent to the UPF serving the user equipment through the N4 session modification request; the algorithm network PFCP rule is sent to other UPF in the SMF management range through the N4 session establishment request; and the algorithm network PFCP rule is sent to other SMF through the algorithm network policy association request, so that the other SMF sends the algorithm network PFCP rule to the UPF in the management range of the other SMF.

[0183] FIG. 7 shows a flowchart of a sixth algorithm network service processing method in an embodiment of the present disclosure, as shown in FIG. 7, applied to a user equipment, including the following steps:

[0184] S702: sending an algorithm network service request.

[0185] S704: receiving an algorithm network service response.

[0186] In a possible embodiment, the algorithm network service request at least includes: a user equipment identifier, an algorithm network service identifier, and an algorithm network service requirement.

[0187] In a possible embodiment, the algorithm network service request can further include: a PDU session identifier.

[0188] In a possible embodiment, the algorithm network service requirement at least includes: inference accuracy, security requirement, and power consumption requirement.

[0189] In a possible embodiment, when the security requirement is greater than a preset security threshold, the algorithm network service requirement further includes: computing capability.

[0190] In a possible embodiment, the algorithm network service response includes: QoS rule and / or QoS parameter. The QoS rule and / or QoS parameter includes an algorithm network QoS policy.

[0191] The manner of receiving the algorithm network service response can include: receiving the QoS rule and / or QoS parameter via the AMF network element and the RAN.

[0192] Through the algorithm network service processing method in the present disclosure, through the interaction process among the user equipment, the AF network element, the algorithm network policy control and management device, the SMF network element, and the UPF network element, the algorithm network QoS can be pre-allocated, and the pre-allocation condition can be sent to the user equipment, so that the user equipment transmits data according to the algorithm network QoS in actual data transmission, and the network element side processes the algorithm network service, thereby realizing the conversion of the algorithm network service performance requirement to the algorithm network QoS index, achieving the algorithm network integration target, and performing collaborative scheduling on the computing power resource and the network resource, so as to finally meet the end-to-end performance requirement of the service, and provide the end-edge-cloud collaborative strategy and service performance guarantee for the algorithm network service.

[0193] The present disclosure is applicable to the computing power network deeply integrated with the computing power and the network, performs fusion decision control on the algorithm network QoS, realizes integrated scheduling of the algorithm network resource, and the method in the present disclosure can provide the allocation condition of the algorithm network QoS of the algorithm network service request of at least one side of the end, the edge, and the cloud, and better complete the algorithm network service.

[0194] FIG. 8 shows an interaction schematic diagram of an algorithm network service processing method in an embodiment of the present disclosure, which is applied to the UE, the AF, the CNMF, the PCF, the SMF, and the UPF network element, and shows the interaction process among the above network elements. It should be noted that the RAN and the AMF are also involved in the interaction process, but are not shown in FIG. 8.

[0195] As shown in FIG. 8, the following steps are included:

[0196] S802: The UE sends a network-computing service request to an AF network element.

[0197] S804: The AF network element determines a network-computing service data volume, a network-computing service priority, an end-side computing delay range, and a local round-trip delay according to the network-computing service request.

[0198] S806: The AF network element sends the network-computing service data volume, the network-computing service priority, the end-side computing delay range, the local round-trip delay, and the network-computing service request to a CNMF network element.

[0199] S808: The CNMF network element decides a computing power QoS service quality of the network-computing service request according to the network-computing service data volume, the network-computing service priority, and a current available computing power resource.

[0200] S810: The CNMF network element sends the network-computing service data volume, the end-side computing delay range, the local round-trip delay, the network-computing service request, and the computing power QoS to a PCF network element.

[0201] S812: The PCF network element determines a PCC rule of the network-computing service request according to the network-computing service data volume, the end-side computing delay range, the local round-trip delay, and the computing power QoS.

[0202] S814: The PCF network element sends the network-computing PCC rule to an SMF network element.

[0203] S816: The SMF network element decides a network-computing QoS policy according to the network-computing PCC rule, the network-computing QoS policy at least including: an uplink and downlink guaranteed flow bit rate GFBR, an uplink and downlink maximum flow bit rate MFBR, a second uplink and downlink data packet delay budget PDB, and a computing delay budget CDB, and a matched computing power QoS.

[0204] S818: The SMF network element generates a network-computing data packet forwarding control protocol PFCP rule according to the network-computing QoS policy, the network-computing PFCP rule being used to indicate a processing manner of processing data of the network-computing service.

[0205] S820: The SMF network element sends the network-computing PFCP rule to a UPF network element, and sends a network-computing service response to the UE.

[0206] Based on the same inventive concept, the disclosure also provides corresponding devices. Since the embodiments of the devices solve problems by similar principles to the above-mentioned method embodiments, the implementation of the device embodiments can be referred to the implementation of the above-mentioned method embodiments, and the repeated parts will not be described here.

[0207] Figure 9 shows a structural schematic diagram of an application function network element in an embodiment of the present disclosure. As shown in Figure 9, the application function network element 90 includes a memory 901, a transceiver 902, and a processor 903.

[0208] The memory 901 is configured to store a computer program; the transceiver 902 is configured to transceive information under the control of the processor; and the processor 903 is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to receive a network calculation service request; determining a network calculation service data volume, a network calculation service priority, an end-side calculation delay range, and a local round-trip delay according to the network calculation service request; and controlling the transceiver to send the network calculation service data volume, the network calculation service priority, the end-side calculation delay range, the local round-trip delay, and the network calculation service request.

[0209] Figure 10 shows a structural schematic diagram of a network calculation policy control and network calculation management device in an embodiment of the present disclosure. As shown in Figure 10, the network calculation policy control and network calculation management device 100 includes a memory 1001, a transceiver 1002, and a processor 1003.

[0210] The memory 1001 is configured to store a computer program; the transceiver 1002 is configured to transceive information under the control of the processor; and the processor 1003 is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to receive a network calculation service data volume, a network calculation service priority, an end-side calculation delay range, a local round-trip delay, and a network calculation service request; determining a computing power QoS (Quality of Service) for the network calculation service request according to the network calculation service data volume, the network calculation service priority, and a currently available computing power resource; determining a network calculation PCC (Policy Control and Charging) rule for the network calculation service request according to the network calculation service data volume, the end-side calculation delay range, the local round-trip delay, and the computing power QoS; and controlling the transceiver to send the network calculation PCC rule.

[0211] The network calculation policy control and network calculation management device can be a PCF (Policy Control Function) network element, or include a PCF network element and a CNMF (Cloud Network Management Function) network element, and specific contents are not described herein.

[0212] Figure 11 shows a structural schematic diagram of a session management function network element in an embodiment of the present disclosure. As shown in Figure 11, the session management function network element 110 includes a memory 1101, a transceiver 1102, and a processor 1103.

[0213] The memory 1101 is configured to store a computer program; the transceiver 1102 is configured to transceive information under the control of the processor; the processor 1103 is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to receive the algorithm network PCC rule; the algorithm network PCC rule at least includes: computing power QoS, end-side computing delay range, uplink and downlink GBR, uplink and downlink MBR, first uplink and downlink PDB; according to the algorithm network PCC rule, the algorithm network QoS policy and the algorithm network PFCP rule are decided; the algorithm network QoS policy at least includes: uplink and downlink GFBR, uplink and downlink MFBR, second uplink and downlink PDB and CDB, and the matched computing power QoS; the algorithm network PFCP rule is configured to indicate the processing mode of processing the data of the algorithm network service; and the transceiver is controlled to send the algorithm network PFCP rule and the algorithm network service response.

[0214] FIG. 12 shows a structural schematic diagram of a user equipment in an embodiment of the present disclosure. As shown in FIG. 12, the user equipment 120 includes a memory 1201, a transceiver 1202, and a processor 1203.

[0215] The memory 1201 is configured to store a computer program; the transceiver 1202 is configured to transceive information under the control of the processor; the processor 1203 is configured to read the computer program in the memory and perform the following steps: controlling the transceiver to send the algorithm network service request; and controlling the transceiver to receive the algorithm network service response.

[0216] Those skilled in the art can understand that each aspect of the present disclosure can be implemented as a system, a method or a program product. Therefore, each aspect of the present disclosure can be embodied as a complete hardware embodiment, a complete software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "system" herein.

[0217] In one possible embodiment, the algorithm network processing method in the present disclosure is executed in the core network, and can also be executed by an electronic device. The electronic device 1300 according to this embodiment of the present disclosure is described below with reference to FIG. 13. The electronic device 1300 shown in FIG. 13 is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0218] As shown in FIG. 13, the electronic device 1300 is in the form of a general computing device. The components of the electronic device 1300 can include, but are not limited to, the above-mentioned at least one processing unit 1310, the above-mentioned at least one storage unit 1320, and a bus 1330 connecting different system components, including the storage unit 1320 and the processing unit 1310.

[0219] The storage unit stores program codes which can be executed by the processing unit 1310, so that the processing unit 1310 performs the steps described in the above "Exemplary Methods" section according to various exemplary embodiments of the present disclosure. For example, the processing unit 1310 can perform the steps of any of the above method embodiments.

[0220] The storage unit 1320 can include a readable medium in the form of volatile storage such as a random access memory (RAM) 13201 and / or cache memory 13202, and also can include a non-volatile storage such as read-only memory (ROM) 13203.

[0221] The storage unit 1320 also can include program / utility 13204 having a set of programs / modules 13205, including an operating system, one or more application programs, other programs, and programmatic data, each or some combination thereof, which can include implementation of a network environment.

[0222] The bus 1330 can represent one or more of several types of bus structures, including a storage bus or bus controller, a peripheral bus, a graphics bus, a processor or local bus using any of a variety of bus architectures.

[0223] The electronic device 1300 also can communicate with one or more external devices 1340 such as a keyboard or pointing device, using one or more communication ports 1352. Communication can occur over the I / O interface 1350. Still yet, one or more of the electronic devices 1300 also can communicate audio

[0224] Those skilled in the art can easily understand from the above description of the embodiments that the example embodiments described herein can be implemented by software or by software in combination with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a U disk, a mobile hard disk, etc.) or a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to perform the methods according to the embodiments of the present disclosure.

[0225] In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer program product or a computer program including computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the methods in the above embodiments.

[0226] In the example embodiments of the present disclosure, a computer readable storage medium is also provided, which can be a readable signal medium or a readable storage medium. A program product capable of implementing the above methods of the present disclosure is stored thereon. In some possible embodiments, various aspects of the present disclosure can also be implemented in the form of a program product, which includes program codes for causing the terminal device to perform the steps according to various example embodiments of the present disclosure described in the above "example method" section of the specification when the program product is run on the terminal device.

[0227] More specific examples of the computer readable storage medium in the present disclosure can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0228] In the present disclosure, the computer readable storage medium can include a data signal propagating in a baseband or as a carrier wave in a propagated data signal, in which a readable program code is borne. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable signal medium can also be any readable medium other than the readable storage medium, which can send, propagate or transmit programs for use by or in connection with an instruction execution system, apparatus or device.

[0229] Optionally, program code embodied on a computer readable storage medium can be transmitted by way of electromagnetic signals, such as using radio frequency (RF) signals, infrared signals, etc., and / or the like. Computer readable storage medium then comprises a non-transitory computer readable medium.

[0230] In particular embodiments, the program code implementing the methods of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider (ISP).

[0231] It should be noted that, although several modules or units of devices for action execution are mentioned in the foregoing detailed description, such a division is not mandatory. Indeed, features and functionalities of two or more modules or units described above can be embodied in one module or unit according to embodiments of the present disclosure. Conversely, features and functionalities of one module or unit described above can be further divided into multiple modules or units embodied.

[0232] Moreover, although the various steps of the methods of the present disclosure are described in a particular order in the figures, this is not required or implied, nor is it necessary to perform all of the steps shown in order to achieve the desired result. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, one step can be broken into multiple steps, etc.

[0233] From the above description of the embodiments of the present disclosure, those skilled in the art will easily understand that the example embodiments described herein can be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or a network, and includes a number of instructions to make a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the methods according to the embodiments of the present disclosure.

[0234] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the disclosure be construed as including any patents, patent applications, publications, publications, or other disclosure of complementary subject matter that is within the scope of the disclosure. It is intended that the specification and examples be considered exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A method of processing a network service, wherein, The method comprises: receiving an algorithm network service request; determining algorithm network service data volume, algorithm network service priority, end-side computing delay range and local round-trip delay according to the algorithm network service request; sending the algorithm network service data volume, algorithm network service priority, end-side computing delay range, local round-trip delay and algorithm network service request.

2. The method of claim 1, wherein, The algorithm network service request at least includes: user equipment identification, algorithm network service identification and algorithm network service demand.

3. The method of claim 2, wherein, According to the algorithm network service request, the algorithm network service data volume is determined, comprising: According to the algorithm network service demand and algorithm network service identification in the algorithm network service request, the algorithm network service data volume is determined; the algorithm network service data volume includes: required data volume for computing and required data volume for uplink and downlink transmission.

4. The method of claim 3, wherein, The algorithm network service demand at least includes: inference accuracy, safety requirement and power consumption requirement; According to the algorithm network service demand and algorithm network service identification in the algorithm network service request, the algorithm network service data volume is determined, comprising: According to the inference accuracy, safety requirement, power consumption requirement and algorithm network service identification, the required data volume for computing and the required data volume for uplink and downlink transmission are determined.

5. The method of claim 3, wherein, When the safety requirement is greater than a preset safety threshold, the algorithm network service demand further includes: computing capability; According to the algorithm network service demand and algorithm network service identification in the algorithm network service request, the algorithm network service data volume is determined, comprising: According to the inference accuracy, safety requirement, power consumption requirement, computing capability and algorithm network service identification, the required data volume for computing and the required data volume for uplink and downlink transmission are determined.

6. The method of claim 2, wherein, According to the algorithm network service request, the end-side computing delay range is determined, comprising: According to the algorithm network service demand and algorithm network service identification, the range of user equipment local computing data volume is determined; According to the range of user equipment local computing data volume and algorithm network service demand, the end-side computing delay range is determined.

7. The method of claim 2, wherein, According to the algorithm network service request, the local round-trip delay is determined, comprising: According to the algorithm network service identification and algorithm network service demand, the local round-trip delay of the algorithm network service request is determined; when a cloud algorithm network node does not participate in the algorithm network service processing process, the local round-trip delay is equal to the overall round-trip delay RTT of the algorithm network service request.

8. The method of claim 2, wherein, According to the algorithm network service request, the algorithm network service priority is determined, comprising: According to at least one of the UE identification, algorithm network service identification and algorithm network service demand, the algorithm network service priority is determined.

9. A method of processing transactions in a network, wherein, The method comprises: receiving algorithm network service data volume, algorithm network service priority, end-side computing delay range, local round-trip delay and algorithm network service request; deciding the computing power QoS service quality of the algorithm network service request according to the algorithm network service data volume, the algorithm network service priority and current available computing power resource; determining the algorithm network strategy and charging control PCC rule of the algorithm network service request according to the algorithm network service data volume, end-side computing delay range, local round-trip delay and the computing power QoS; sending the algorithm network PCC rule.

10. The method of claim 9, wherein, The computing power QoS at least includes: at least one computing power QoS sequence number, computing power resource type corresponding to each computing power QoS sequence number, computing power resource size and first total computing delay.

11. The method of claim 10, wherein, The first total computing time delay includes a first total computing time delay upper limit and a first total computing time delay lower limit; The first total computing time delay upper limit is determined according to the algorithm network service priority; The first total computing time delay lower limit is determined according to the current available computing power resource.

12. The method of claim 10, wherein, The computing power resource size corresponding to each computing power QoS serial number is between a computing power resource upper limit and a computing power resource lower limit; The computing power resource upper limit is determined according to the current available computing power resource; The computing power resource lower limit is determined according to the algorithm network service priority.

13. The method of claim 10, wherein, The algorithm network service data volume at least includes a required data volume for uplink and downlink transmission; The algorithm network PCC rule of the algorithm network service request is determined according to the algorithm network service data volume, the end-side computing time delay range, the local round-trip time delay and the computing power QoS, including: The transmission time delay of the uplink and downlink transmission is determined according to the required data volume for uplink and downlink transmission; The algorithm network PCC rule of the algorithm network service request is determined according to the transmission time delay, the end-side computing time delay range, the local round-trip time delay and the first total computing time delay in the computing power QoS.

14. The method of claim 9, wherein, The algorithm network service data volume at least includes a required data volume for computing; The computing power QoS quality of service of the algorithm network service request is decided according to the algorithm network service data volume, the algorithm network service priority and the current available computing power resource, including: The computing power QoS of the algorithm network service request is decided according to the required data volume for computing, the algorithm network service priority and the current available computing power resource.

15. The method of claim 9, wherein, The algorithm network PCC rule at least includes the computing power QoS, the end-side computing time delay range, the uplink and downlink guaranteed bit rate GBR, the uplink and downlink maximum bit rate MBR and the first uplink and downlink data packet delay budget PDB.

16. The method of claim 9, wherein, The method further includes: Receiving an algorithm network node new establishment request sent by a current session management function SMF network element; Judging whether to insert an algorithm network node for the algorithm network service according to the algorithm network node new establishment request; If yes, sending an algorithm network node new establishment response, the algorithm network node new establishment response at least including inserted algorithm network node information and matched target computing power QoS.

17. The method of claim 16, wherein, If the inserted algorithm network node is a user plane function UPF within a management range of another SMF, the algorithm network node new establishment response further includes an identifier of the other SMF; If the inserted algorithm network node is a cloud algorithm network node, the algorithm network node new establishment response further includes a second total computing time delay of the cloud algorithm network node and an N6 transmission time delay.

18. The method of claim 9, wherein, The method further includes: Sending a running mode of the algorithm network service to an application function AF.

19. A method of processing transactions in a network, wherein, The method includes: Receiving an algorithm network PCC rule, the algorithm network PCC rule at least including the computing power QoS, the end-side computing time delay range, the uplink and downlink GBR, the uplink and downlink MBR and the first uplink and downlink PDB; Deciding an algorithm network QoS policy according to the algorithm network PCC rule, the algorithm network QoS policy at least including an uplink and downlink guaranteed flow bit rate GFBR, an uplink and downlink maximum flow bit rate MFBR, a second uplink and downlink data packet delay budget PDB and a computing delay budget CDB and the matched computing power QoS; According to the computing network QoS policy, a computing network packet forwarding control protocol (PFCP) rule is generated, and the computing network PFCP rule is used to indicate a processing manner of processing data of the computing network service; The computing network PFCP rule and a computing network service response are sent.

20. The method of claim 19, wherein, The computing network QoS policy is determined according to the computing network PCC rule, and the determining comprises: An uplink GFBR is determined according to the uplink GBR; An uplink MFBR is determined according to the uplink MBR; A second uplink PDB is determined according to the first uplink PDB.

21. The method of claim 19, wherein, The CDB comprises a device side DS-CDB and an edge side ES-CDB, and the DS-CDB is within the end side computing delay range.

22. The method of claim 21, wherein, The computing network QoS policy is determined according to the computing network PCC rule, and the determining comprises: It is judged whether first computing power resources of a radio access network (RAN) and a UPF serving a user equipment meet requirements of the computing power QoS; If the first computing power resources meet the requirements, a matched first computing power QoS is determined; DS-CDB and ES-CDB are determined according to the first computing power QoS.

23. The method of claim 22, wherein, The computing network PFCP rule is sent, and the sending comprises: The computing network PFCP rule is sent to the UPF serving the user equipment through an N4 session modification request.

24. The method of claim 22, wherein, The method further comprises: If the first computing power resources do not meet the requirements, it is judged whether second computing power resources of other UPFs within a management range meet the requirements of the computing power QoS; If the second computing power resources meet the requirements, a matched second computing power QoS is determined; DS-CDB and ES-CDB are determined according to the second computing power QoS.

25. The method of claim 24, wherein, The computing network PFCP rule is sent, and the sending comprises: The computing network PFCP rule is sent to the UPF serving the user equipment through an N4 session modification request; The computing network PFCP rule is sent to other UPFs within a management range of the SMF through an N4 session establishment request.

26. The method of claim 24, wherein, The method further comprises: If the second computing power resources do not meet the requirements, a computing network node new establishment request is initiated; A computing network node new establishment response is received, and the computing network node new establishment response at least comprises inserted computing network node information and a matched target computing power QoS; DS-CDB and ES-CDB are determined according to the target computing power QoS.

27. The method of claim 26, wherein, When the computing network node information comprises UPFs within a management range of other SMFs, the computing network node new establishment response further comprises an identifier of the other SMFs. The method further comprises: The PFCP rule is interacted with the other SMFs.

28. The method of claim 27, wherein, The computing network PFCP rule is sent, and the sending comprises: The computing network PFCP rule is sent to the UPF serving the user equipment through an N4 session modification request; The computing network PFCP rule is sent to other UPFs within a management range of the SMF through an N4 session establishment request; The computing network PFCP rule is sent to the other SMFs through a computing network policy association request, so that the other SMFs send the computing network PFCP rule to UPFs within a management range of the other SMFs.

29. The method of claim 26, wherein, When the cloud computing network node is included in the computing network node new creation response, the computing network node new creation response further includes: a second total computing time delay and an N6 transmission time delay of the cloud computing network node; and the method further includes: According to the target computing power QoS and the second total computing time delay of the cloud computing network node, determining a DS-CDB and an ES-CDB; According to the N6 transmission time delay of the cloud computing network node, adjusting the first PDB to obtain a second PDB.

30. The method of claim 19, wherein, The computing network service response includes a QoS configuration file; and the method further includes: Sending the QoS configuration file to the RAN via an access and mobility management function (AMF) network element; and the QoS configuration file includes a computing network QoS policy.

31. The method of claim 19, wherein, The computing network service response includes a QoS rule and / or a QoS parameter; and the method further includes: Sending the QoS rule and / or the QoS parameter to a user equipment via an AMF network element and a RAN; and the QoS rule and / or the QoS parameter includes a computing network QoS policy.

32. A method of processing transactions in a network, wherein The method includes: Sending a computing network service request; Receiving a computing network service response.

33. The method of claim 32, wherein, The computing network service request at least includes a user equipment identifier, a computing network service identifier, and a computing network service demand.

34. The method of claim 33, wherein, The computing network service demand at least includes an inference accuracy, a security requirement, and a power consumption requirement.

35. The method of claim 34, wherein, When the security requirement is greater than a preset security threshold, the computing network service demand further includes a computing power.

36. The method of claim 32, wherein, The computing network service response includes a QoS rule and / or a QoS parameter; and the receiving of the computing network service response includes: Receiving the QoS rule and / or the QoS parameter via an AMF network element and a RAN; and the QoS rule and / or the QoS parameter includes a computing network QoS policy.

37. An application function network element, wherein, Including: A memory configured to store a computer program; A transceiver configured to transceive information under control of a processor; The processor is configured to read the computer program in the memory, and perform the following steps: control the transceiver to receive a computing network service request; according to the computing network service request, determine a computing network service data volume, a computing network service priority, an end-side computing time delay range, and a local round-trip time delay; control the transceiver to send the computing network service data volume, the computing network service priority, the end-side computing time delay range, the local round-trip time delay, and the computing network service request.

38. A policy control and network management device, wherein, Including: A memory configured to store a computer program; A transceiver configured to transceive information under control of a processor; The processor is configured to read the computer program in the memory, and perform the following steps: control the transceiver to receive a computing network service data volume, a computing network service priority, an end-side computing time delay range, a local round-trip time delay, and a computing network service request; according to the computing network service data volume, the computing network service priority, and a current available computing power resource, determine a computing power QoS quality of service of the computing network service request; According to the computing network service data volume, the end-side computing time delay range, the local round-trip time delay, and the computing power QoS, determine a computing network PCC rule of the computing network service request; and control the transceiver to send the computing network PCC rule.

39. The policy control and network management apparatus of claim 38, wherein, The computing network policy control and computing network management device is a policy control function (PCF) network element; and the PCF network element includes: The memory is configured to store a computer program. The transceiver is configured to transceive information under control of the processor. The processor is configured to read the computer program in the memory and perform the following steps: control the transceiver to receive a computing network service data volume, a computing network service priority, an end-side computing delay range, a local round-trip delay, and a computing network service request; determine a computing power QoS (Quality of Service) of the computing network service request according to the computing network service data volume, the computing network service priority, and a current available computing power resource; determine a computing network PCC (Policy Control and Charging) rule of the computing network service request according to the computing network service data volume, the end-side computing delay range, the local round-trip delay, and the computing power QoS; and control the transceiver to send the computing network PCC rule.

40. The policy control and network management apparatus of claim 38, wherein, The computing network policy control and computing network management device comprises a computing network management function (CNMF) network element and a PCF (Policy Control Function) network element. The CNMF network element comprises: The memory is configured to store a computer program. The transceiver is configured to transceive information under control of the processor. The processor is configured to read the computer program in the memory and perform the following steps: control the transceiver to receive a computing network service data volume, a computing network service priority, an end-side computing delay range, a local round-trip delay, and a computing network service request; determine a computing power QoS (Quality of Service) of the computing network service request according to the computing network service data volume, the computing network service priority, and a current available computing power resource; control the transceiver to send the computing network service data volume, the end-side computing delay range, the local round-trip delay, the computing network service request, and the computing power QoS. The PCF network element comprises: The memory is configured to store a computer program. The transceiver is configured to transceive information under control of the processor. The processor is configured to read the computer program in the memory and perform the following steps: control the transceiver to receive a computing network service data volume, an end-side computing delay range, a local round-trip delay, a computing network service request, and a computing power QoS; determine a computing network PCC (Policy Control and Charging) rule of the computing network service request according to the computing network service data volume, the end-side computing delay range, the local round-trip delay, and the computing power QoS; and control the transceiver to send the computing network PCC rule.

41. The network policy control and management device of claim 40, wherein, The CNMF network element is a system belonging to a core network, or is an external system not belonging to the core network and interacting with the core network.

42. A session management function network element, wherein, Comprise: The memory is configured to store a computer program. The transceiver is configured to transceive information under control of the processor. The processor is configured to read a computer program in the memory and perform the following steps: controlling the transceiver to receive a network PCC rule; the network PCC rule at least includes: computing power QoS, end-side computing delay range, uplink and downlink GBR, uplink and downlink MBR, first uplink and downlink PDB; according to the network PCC rule, deciding a network QoS policy and a network PFCP rule; the network QoS policy at least includes: uplink and downlink GFBR, uplink and downlink MFBR, second uplink and downlink PDB and CDB, and matched computing power QoS; the network PFCP rule is configured to indicate a processing mode of processing data of the network service; controlling the transceiver to send the network PFCP rule and a network service response.

43. A user equipment, wherein, Comprise: a memory configured to store a computer program; a transceiver configured to transceive information under the control of the processor; the processor is configured to read a computer program in the memory and perform the following steps: controlling the transceiver to send a network service request; controlling the transceiver to receive a network service response.

44. An electronic device, comprising: Comprise: a processor; and a memory configured to store executable instructions of the processor; wherein the processor is configured to perform the method of any one of claims 1-36 via execution of the executable instructions.

45. A computer readable storage medium having stored thereon a computer program, wherein, The computer program is executed by the processor to realize the method of any one of claims 1-36.

46. A computer program product, comprising: Computer program or instructions, wherein the computer program or instructions are executed by the processor to realize the method of any one of claims 1-36.

Images