Path determination method and device

Abstract

The embodiment of the invention provides a path determination method and device, relates to the technical field of computers, and can effectively reduce the time delay of a data packet in the transmission process, improve the data transmission efficiency and meet the application requirements of the industrial internet. The method comprises the following steps: receiving a data packet from terminal equipment, then determining at least one target transmission path and the transmission delay of each target transmission path based on the information of the data packet, and finally sending the data packet according to the target transmission path with the minimum transmission delay.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a path determination method and device. Background Art

[0002] In the industrial Internet architecture, the user plane function (UPF) network element, as an important component of the fifth generation mobile communication technology (5G) core network, is mainly responsible for forwarding user data and network data. Its performance determines the real-time and reliability of data transmission.

[0003] At present, UPF network elements mainly judge the network overhead of network nodes based on traditional routing tables, and select the path with the lowest latency to route and forward data packets based on the network overhead. However, the complexity of the actual network environment makes the network overhead determined by multiple factors such as link bandwidth, delay, packet loss rate, and jitter, and the traditional routing table cannot fully and accurately reflect the complexity of the actual network environment. Therefore, the path with the lowest latency determined based on the traditional routing table may be biased, resulting in higher latency during data transmission, which in turn cannot meet the application requirements of the Industrial Internet. Summary of the invention

[0004] The present application provides a path determination method and device, which can determine a path with the lowest latency for data packet transmission based on the information of the data packet, thereby reducing the latency of the data packet during transmission and meeting the application requirements of the industrial Internet.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a path determination method, the method comprising:

[0007] Receive data packets from terminal devices.

[0008] Based on the information of the data packet, at least one target transmission path and a transmission delay of each target transmission path are determined.

[0009] Send data packets along the target transmission path with the minimum transmission delay.

[0010] Based on the above technical solution, the present application provides a path determination method. After the UPF network element receives a data packet from a terminal device, it can determine at least one target transmission path that matches the information of the data packet based on the information of the data packet, and then select the target transmission path with the smallest transmission delay to transmit the data packet. In this way, the delay of the data packet during transmission can be effectively reduced, the data transmission efficiency can be improved, and the application requirements of the industrial Internet can be met.

[0011] Optionally, the UPF network element stores the correspondence between the data packet size and the transmission path, as well as the transmission delay of each transmission path. The information of the data packet includes the data packet size of the data packet. On this basis, based on the information of the data packet, determining at least one target transmission path and the transmission delay of each target transmission path may include: taking at least one transmission path corresponding to the data packet size of the data packet as the target transmission path, and obtaining the transmission delay of each target transmission path.

[0012] Optionally, the UPF network element stores the time when each network node is in an idle state. The information of the data packet includes the time when the UPF network element receives the data packet. On this basis, based on the information of the data packet, at least one target transmission path and the transmission delay of each target transmission path are determined, which may also include: determining at least one network node whose idle time coincides with the time when the UPF network element receives the data packet as the target network node, and then determining at least one target transmission path and the transmission delay of each target transmission path based on the target network node.

[0013] Optionally, a path determination model is deployed in the UPF network element, and the above method may also include: inputting the information of the first data sample into the path determination model, obtaining the model processing result, and then storing the model processing result, as well as the first data sample and the information of the first data sample.

[0014] The information of the first data sample includes at least the data packet size of the first data sample, the time when the UPF network element sends the first data sample to the target node, and the time when the UPF network element receives the response message sent by the target node. The target node can be an identification node or a network node. The response message is used to characterize that the target node receives the first data sample sent by the UPF network element. The model processing result includes at least multiple transmission paths and the transmission delay of each transmission path.

[0015] Optionally, the above-mentioned inputting the information of the first data sample into the path determination model to obtain the model processing result may include: determining a first weight corresponding to the information of the first data sample, and then inputting the information of the first data sample and the first weight corresponding to the information of the first data sample into the path determination model to obtain the model processing result.

[0016] The first weight is used to characterize the importance of the information of the first data sample to the transmission delay.

[0017] Optionally, the above-mentioned determination of the first weight corresponding to the information of the first data sample may include: obtaining the priority parameter of the first data sample based on the data packet header of the first data sample, and then determining the first weight corresponding to the information of the first data sample based on the initial weight corresponding to the information of the first data sample and the priority parameter of the first data sample.

[0018] Among them, the initial weight corresponding to the information of the first data sample is set by the UPF network element.

[0019] Optionally, the first data sample may be any one of a data packet generated by the UPF network element or a historical data packet received by the UPF network element from the terminal device.

[0020] In a second aspect, the present application provides a path determination device, comprising:

[0021] The transceiver unit is used to receive data packets from the terminal device.

[0022] The processing unit is used to determine at least one target transmission path and a transmission delay of each target transmission path based on information of the data packet.

[0023] The transceiver unit is also used to send data packets along a target transmission path with the minimum transmission delay.

[0024] Optionally, the processing unit is further configured to use at least one transmission path corresponding to the data packet size of the data packet as a target transmission path, and obtain a transmission delay of each target transmission path.

[0025] Optionally, the processing unit is also used to determine at least one network node whose idle time coincides with the time when the UPF network element receives the data packet as a target network node, and based on the target network node, determine at least one target transmission path and the transmission delay of each target transmission path.

[0026] Optionally, the processing unit is further used to input information of the first data sample into the path determination model to obtain a model processing result.

[0027] Optionally, the processing unit is further used to determine a first weight corresponding to the information of the first data sample, and input the information of the first data sample and the first weight corresponding to the information of the first data sample into the path determination model to obtain a model processing result.

[0028] Optionally, the processing unit is also used to obtain a priority parameter of the first data sample based on the data packet header of the first data sample, and determine a first weight corresponding to the information of the first data sample based on an initial weight corresponding to the information of the first data sample and the priority parameter of the first data sample.

[0029] In a third aspect, the present application provides a path determination device, the device comprising: a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement a path determination method as described in any one of the first aspect and any possible implementation of the first aspect.

[0030] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal, the terminal executes a path determination method as described in any one of the first aspect and any possible implementation manner of the first aspect.

[0031] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes a path determination method as described in the first aspect and any possible implementation of the first aspect.

[0032] It can be understood that the beneficial effects that can be achieved by the second to fifth aspects provided above can refer to the beneficial effects of any possible design method of the path determination method described in any one of the first aspect and any possible implementation method of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 An architecture diagram of a path determination system provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of a flow chart of a path determination method provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of a flow chart of another path determination method provided in an embodiment of the present application;

[0036] Figure 4 An interactive flow chart of a path determination method provided in an embodiment of the present application;

[0037] Figure 5 A schematic diagram of the structure of a path determination device provided in an embodiment of the present application;

[0038] Figure 6 A schematic diagram of the structure of another path determination device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] A path determination method and device provided in an embodiment of the present application are described in detail below with reference to the accompanying drawings.

[0040] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0041] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0042] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0043] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0044] The following is an explanation of some terms in the embodiments of the present disclosure to facilitate understanding by those skilled in the art:

[0045] (1) UPF network element is an important part of the 5G core network system architecture. It is mainly responsible for packet routing and forwarding, user plane policy rule implementation, traffic usage reporting, and user plane quality of service (QoS) processing.

[0046] As a product of the deep integration of new-generation information technology and manufacturing, the Industrial Internet is gradually becoming a key force in promoting high-quality industrial development. As an important part of the Industrial Internet system, the Industrial Internet identification resolution system has accelerated its development under the impetus of new infrastructure, providing strong support for the digital transformation of the industrial field.

[0047] The identification resolution system enables accurate data positioning and efficient interoperability by giving each physical entity and digital object a unique "identity card", which not only promotes the high-quality development of industry, but also forms new productivity. Driven by the industrial Internet identification resolution system, enterprises can achieve data interconnection and interoperability, thereby significantly improving the resilience and security level of the industrial chain and supply chain.

[0048] By achieving the transformation from "building" to "using", the identification resolution system has driven the chain development of suppliers, enriched the industrial chain ecology, and further promoted the high-quality development of the industry. At the same time, the identification resolution system is regarded as an important engine for promoting data interoperability and information sharing between upstream and downstream of the industrial chain. It enables enterprises to use data resources more efficiently and improve production efficiency and market competitiveness.

[0049] However, although the industrial Internet identification resolution system has achieved remarkable results in promoting industrial digital transformation, the development of the industrial Internet still faces many challenges, especially the problem of network latency. With the continuous deepening and expansion of industrial Internet applications, higher requirements are placed on network latency. In the industrial Internet architecture, the UPF network element, as an important component of the 5G core network, is responsible for forwarding user data and network data. Its performance determines the real-time and reliability of data transmission.

[0050] At present, UPF network elements mainly judge the network overhead of network nodes based on traditional routing tables, and select the path with the lowest latency to route and forward data packets based on the network overhead. However, the complexity of the actual network environment makes the network overhead determined by multiple factors such as link bandwidth, delay, packet loss rate, and jitter, and the traditional routing table cannot fully and accurately reflect the complexity of the actual network environment. Therefore, the path with the lowest latency determined based on the traditional routing table may be biased, resulting in higher latency during data transmission, which in turn cannot meet the application requirements of the Industrial Internet.

[0051] In order to solve the above technical problems, the embodiment of the present application provides a path determination method. After the UPF network element receives a data packet from a terminal device, it can determine at least one target transmission path and the transmission delay of each target transmission path based on the information of the data packet, and then select the target transmission path with the smallest transmission delay to transmit the data packet. In this way, the delay of the data packet during transmission can be effectively reduced, the data transmission efficiency can be improved, and the application requirements of the industrial Internet can be met.

[0052] Figure 1 An architecture diagram of a path determination system provided in an embodiment of the present application, such as Figure 1 As shown, the system framework includes: terminal equipment 101, base station 102, UPF network element 103, network node 104, and identification node 105.

[0053] The terminal device 101 may be a device that provides voice and / or data connectivity to a user, a device with a wireless connection function, or other devices connected to a wireless modem. The terminal device may be at least one of a desktop computer, a laptop, a wireless terminal, and a laptop portable computer. In one embodiment, the terminal device 101 has a communication function and can access a wired network or a wireless network.

[0054] Base station 102 can be a global system for mobile communication (GSM), a base station (base transceiverstation, BTS) in code division multiple access (CDMA), a base station in wideband code division multiple access (WCDMA), a base station in the Internet of things (IoT) or narrowband internet of things (NB IoT), a base station in the future 5G mobile communication network or the future evolved public land mobile network (PLMN).

[0055] The network node 104 may be a gateway device that connects different networks and provides network communication and data transmission services for different networks. The network node 104 may include but is not limited to: a router, a switch, and a virtual private network (VPN) device.

[0056] The embodiment of the present application does not limit the number of network nodes 104 in the path determination system, and may include: Figure 1 More or fewer network nodes 104 may be included.

[0057] The identification node 105 can be a high-performance server that provides various services online, an independent physical server, a server cluster composed of multiple physical servers, or at least one of cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data or artificial intelligence platforms. The embodiments of the present application do not limit this. Of course, the server can also include other functions to provide more comprehensive and diversified services.

[0058] In an embodiment of the present application, the terminal device 101 can send a data packet to the base station 102. After the base station 102 receives the data packet sent by the terminal device 101, it can send the data packet to the UPF network element 103. Accordingly, after the UPF network element 103 receives the data packet sent by the base station 102, it can determine at least one target transmission path and the transmission delay of each target transmission path based on the information of the data packet. Afterwards, the UPF network element 103 can send a data packet to the network node 104 according to the target transmission path with the minimum transmission delay. Accordingly, after the network node 104 receives the data packet sent by the UPF network element 103, it can send a data packet to the identification node 105.

[0059] It should be noted that each target transmission path can be composed of at least one network node 104 and an identification node 105, the network node 104 is an intermediate node in the transmission path, and the identification node 105 is a destination node, which is not specifically limited in the embodiment of the present application.

[0060] Optionally, the UPF network element 103 stores the correspondence between the data packet size and the transmission path, as well as the transmission delay of each transmission path. After receiving the data packet from the terminal device, the UPF network element 103 can determine the data packet size of the data packet based on the information of the data packet. Afterwards, the UPF network element 103 uses at least one transmission path corresponding to the data size of the data packet as the target transmission path, and obtains the transmission delay of each target transmission path.

[0061] Optionally, the UPF network element 103 also stores the time each network node is in an idle state, the correspondence between the data packet size and the transmission path, and the transmission delay of each transmission path. After the UPF network element 103 receives the data packet from the terminal device, it can first determine the time when the UPF network element 103 receives the data packet. Afterwards, the UPF network element 103 can determine at least one network node whose idle time coincides with the time when the UPF network element 103 receives the data packet as a target network node, and then determine at least one target transmission path and the transmission delay of each target transmission path based on the target network node.

[0062] Optionally, a path determination model is deployed in the UPF network element 103. The UPF network element 103 may input the information of the first data sample into the path determination model, and the path determination model may process the information of the first data sample. Afterwards, the UPF network element 103 may obtain the model processing result output by the path determination model, and store the model processing result, the first data sample and the information of the first data sample.

[0063] The first data sample may be a data packet generated by the UPF network element 103 or a historical data packet received by the UPF network element 103 from the terminal device.

[0064] Optionally, the UPF network element 103 may also obtain a priority parameter of the first data sample based on the data packet header of the first data sample, and determine a first weight corresponding to the information of the first data sample based on an initial weight corresponding to the information of the first data sample and the priority parameter of the first data sample. Afterwards, the UPF network element 103 may input the information of the first data sample and the first weight corresponding to the information of the first data sample into the path determination model to obtain a model processing result.

[0065] Optionally, the UPF network element 103 may include a sending unit, a storage unit, a computing unit, and a routing unit.

[0066] A sending unit is configured to send a first data sample to the network node 104 or the identification node 105 .

[0067] The storage unit is used to store the first data sample and the information of the first data sample. The storage unit can send the information of the first data sample to the calculation unit so that the calculation unit processes the information of the first data sample.

[0068] The computing unit includes a path determination model. The path determination model can process the information of the first data sample and output a model processing result. The computing unit can send the model processing result output by the path determination model to the routing unit so that the routing unit can store the model processing result.

[0069] The routing unit includes a routing information table for storing the model processing results of the path determination model in the above-mentioned calculation unit.

[0070] Figure 2 A schematic diagram of a flow chart of a path determination method provided in an embodiment of the present application, the method comprises Figure 1 The UPF network element 103 shown executes, as shown Figure 2 As shown, the method includes:

[0071] S201, receiving a data packet from a terminal device.

[0072] Specifically, the terminal device can send a data packet to the base station. After receiving the data packet sent by the terminal device, the base station can send the data packet to the UPF network element.

[0073] S202, determining at least one target transmission path and a transmission delay of each target transmission path based on the information of the data packet.

[0074] The embodiment of the present application does not limit the information of the data packet. For example, the information of the data packet may include but is not limited to the data packet size, the time when the UPF network element receives the data packet, the source address of the data packet and the destination address of the data packet.

[0075] Specifically, the UPF network element stores multiple transmission paths and the transmission delay of each transmission path. After receiving a data packet from a terminal device, the UPF network element can determine at least one target transmission path that matches the information of the data packet from multiple transmission paths based on the information of the data packet, as well as the transmission delay of each target transmission path.

[0076] The following will introduce in detail, through Example 1 and Example 2, how the above-mentioned UPF network element determines at least one target transmission path based on the information of the data packet, and the transmission delay of each target transmission path.

[0077] Embodiment 1

[0078] In an optional implementation, the UPF network element may store the correspondence between the data packet size and the transmission delay, as well as the transmission delay of each transmission path. After receiving the data packet from the terminal device, the UPF network element may use at least one transmission path corresponding to the data packet size of the data packet as the target transmission path, and obtain the transmission delay of each target transmission path.

[0079] Specifically, after receiving a data packet from a terminal device, the UPF network element can obtain the data packet size of the data packet based on the information of the data packet. Afterwards, based on the correspondence between the data packet size and the transmission path, the UPF network element can take the transmission path whose data packet size in the correspondence is greater than or equal to the data packet size of the data packet as the target transmission path, and obtain the transmission delay of each target transmission path.

[0080] For example, it is assumed that three sets of correspondences are stored in the UPF network element. Among them, the data packet size corresponding to the transmission path R1 in the correspondence relationship 1 is 10 megabytes (MB), and the transmission delay of the transmission path R1 is 5 milliseconds (ms). The data packet size corresponding to the transmission path R2 in the correspondence relationship 2 is 15MB, and the transmission delay of the transmission path R2 is 10ms. The data packet size corresponding to the transmission path R3 in the correspondence relationship 3 is 5MB, and the transmission delay is 8ms.

[0081] After receiving the data packet from the terminal device, the UPF network element can determine that the data packet size is 10MB based on the information of the data packet. Then, the UPF network element can determine the transmission path R1 and the transmission path R2 as the target transmission paths based on the above three groups of corresponding relationships, and obtain the transmission delay of each target transmission path.

[0082] Embodiment 2

[0083] In an optional implementation, the UPF network element may also store the corresponding relationship between the idle time of each network node, the data packet size and the transmission delay, and the transmission delay of each transmission path. After the UPF network element receives a data packet from a terminal device, it may determine at least one network node whose idle time coincides with the time when the UPF network element receives the data packet as a target network node, and then determine at least one target transmission path and the transmission delay of each target transmission path based on the target network node.

[0084] In some embodiments, the time when the network node is in an idle state can be a certain time period, and the time when the UPF network element receives the data packet can be a certain moment. The time when the UPF network element receives the data packet coincides with the time when the network node is in an idle state, which means that the time when the UPF network element receives the data packet is within the time period when the network node is in an idle state.

[0085] Specifically, after the UPF network element receives a data packet from a terminal device, it can first determine the time when the UPF network element receives the data packet. Afterwards, the UPF network element can determine, based on the time when the data packet is received, the network node whose idle time coincides with the time when the UPF network element receives the data packet as the target network node. Then, based on the target network node, the UPF network element can determine at least one target transmission path passing through the target network node, as well as the transmission delay of each target transmission path.

[0086] Exemplarily, the UPF network element stores the time when network node A, network node B, and network node C are in idle state. Among them, network node A is in idle state from 9:00 to 9:30, network node B is in idle state from 9:15 to 9:45, and network node C is in idle state from 10:00 to 10:30. At the same time, the UPF network element also stores 3 sets of corresponding relationships. In the corresponding relationship 1, the data packet size corresponding to the transmission path R1 is 10MB, the transmission path R1 passes through the network node A, and the transmission delay is 5ms. In the corresponding relationship 2, the data packet size corresponding to the transmission path R2 is 15MB, the transmission path R2 passes through the network node A and the network node B, and the transmission delay is 10ms. In the corresponding relationship 3, the data packet size corresponding to the transmission path R3 is 5MB, the transmission path R3 passes through the network node C, and the transmission delay is 8ms.

[0087] Assuming that the UPF network element receives a data packet from the terminal device at 9:20, the UPF network element can determine network node A and network node B as target network nodes. Afterwards, the UPF network element can determine transmission path R1 and transmission path R2 as target transmission paths based on network node A and network node B, and determine the transmission delay of each target transmission path.

[0088] The embodiments of the present application do not specifically limit the method by which the UPF network element determines at least one target transmission path and the transmission delay of each target transmission path. For example, the UPF network element may determine at least one target transmission path and the transmission delay of each target transmission path according to the method of Embodiment 1 or Embodiment 2. The UPF network element may also determine at least one target transmission path and the transmission delay of each target transmission path based on the data packet size of the data packet, the time when the UPF receives the data packet, and the time when the network node is in an idle state on the basis of Embodiment 1 and Embodiment 2.

[0089] S203, sending the data packet along the target transmission path with the minimum transmission delay.

[0090] Specifically, the UPF network element determines at least one target transmission path based on the information of the data packet, and after the transmission delay of each target transmission path, it can determine a target transmission path with the minimum transmission delay, and then send the data packet according to the target transmission path with the minimum transmission delay.

[0091] Exemplarily, assuming that the UPF network element determines two target transmission paths, where the transmission delay of the target transmission path R1 is 5ms and the transmission delay of the target transmission path R3 is 8ms, the UPF network element can send data packets according to the target transmission path R1.

[0092] Through the above technical solution, after the UPF network element receives a data packet from a terminal device, it can determine at least one transmission path corresponding to the data packet size of the data packet as the target transmission path based on the data packet size of the data packet, the time when the UPF network element receives the data packet, and / or the time when the network node is in an idle state, and / or determine the network node whose idle time coincides with the time when the UPF network element receives the data packet as the target network node, and based on the target network node, determine at least one target transmission path passing through the target network node. Finally, the UPF network element can select a target transmission path with the minimum transmission delay to transmit the data packet. Through the above method, the transmission delay of the data packet during the transmission process can be effectively reduced, and the efficient transmission of the data packet in the network can be guaranteed, thereby meeting the application needs of the industrial Internet.

[0093] In an optional implementation, a path determination model may be deployed in the UPF network element. Figure 2 Before S201-S203 shown in the figure, the UPF network element can input the information of the first data sample into the path determination model to obtain multiple transmission paths and the transmission delay of each transmission path, and store each transmission path and the transmission delay of each transmission path accordingly. Figure 3 As shown, before executing the above S201-S203, the following steps may also be implemented:

[0094] S301, input information of the first data sample into a path determination model to obtain a model processing result.

[0095] The model processing result may include multiple transmission paths and the transmission delay of each transmission path.

[0096] In an embodiment of the present application, the first data sample may be a historical data packet received by the UPF network element from a terminal device, or may be a data packet generated by the UPF network element, without specific limitation.

[0097] The information of the first data sample may include but is not limited to: the data packet size of the first data sample, the time when the UPF network element sends the first data sample to the network node or identification node (hereinafter referred to as the network node or identification node is collectively referred to as the target node), the time when the UPF network element receives the response message sent by the target node, the source address and destination address of the first data sample, and the address of each network node.

[0098] Among them, the response message sent by the target node is used to represent that the target node receives the first data sample sent by the UPF network element.

[0099] Specifically, the UPF network element may input the information of the first data sample into the path determination model, and the path determination model may process the information of the first data sample. Afterwards, the UPF network element may obtain the model processing result output by the path determination model, and determine multiple transmission paths and the transmission delay of each transmission path based on the model processing result.

[0100] In some embodiments, after the UPF network element obtains the information of the first data sample, it can also determine the first weight corresponding to the information of the first data sample, and then input the information of the first data sample and the first weight corresponding to the information of the first data sample into the path determination model to obtain the model processing result.

[0101] The first weight is used to characterize the importance of the information of the first data sample to the transmission delay.

[0102] For example, assuming that the first weight corresponding to the data packet size of the first data sample is 0.5, and the weight corresponding to the time when the UPF network element sends the first data sample is 0.8, it indicates that the data packet size of the first data sample is more important to the transmission delay than the sending time of the first data sample.

[0103] In some embodiments, the data packet header of the first data sample may include a priority parameter of the first data sample. On this basis, the first weight corresponding to the information of the first data sample may be obtained by the following steps: the UPF network element may obtain the priority parameter of the first data sample from the data packet header of the first data sample. Afterwards, the UPF network element may determine the first weight corresponding to the information of the first data sample based on the initial weight corresponding to the information of the first data sample and the priority parameter of the first data sample.

[0104] Among them, the initial weight corresponding to the information of the first data sample is set by the UPF network element. The method for setting the initial weight in the embodiment of the present application is not specifically limited. For example, the preset weight corresponding to the information of the first data sample may be stored in the UPF network element. The UPF network element may determine the preset weight corresponding to the information of the first data sample as the initial weight corresponding to the information of the first data sample. Alternatively, the UPF network element may set the corresponding initial weight for the information of the first data sample based on a built-in algorithm.

[0105] Exemplarily, it is assumed that the UPF network element stores information of the first data sample a, including the data packet size of the first data sample a, the time when the UPF network element sends the first data sample a to the target node, the time when the UPF network element receives the response message sent by the target node, the time difference between the time when the UPF network element sends the first data sample a to the target node and the time when the UPF network element receives the response message sent by the target node, and the source address and destination address of the first data sample a. On this basis, the UPF network element can set the preset weight corresponding to the stored information of the first data sample to the initial weight corresponding to the information of the first data sample a. Table 1 shows the information of the first data sample a, and the initial weight corresponding to the information of the first data sample a.

[0106] Table 1 Information of the first data sample and the initial weight corresponding to the information

[0107]

[0108] On the basis of the above, the UPF network element can obtain the priority parameter of the first data sample a by reading the data packet header of the first data sample a. Assuming that the priority parameter of the first data sample a is p, the UPF network element can determine the first weight W′ corresponding to the information of the first data sample a according to the following formula 1.

[0109] W′=W*(1-p) (Formula 1)

[0110] Wherein, W is the initial weight corresponding to the information of the first data sample a, and p is the priority parameter of the first data sample a.

[0111] After determining the first weight W′ corresponding to the information of the first data sample a, the UPF network element can input the information of the first data sample a and the first weight W′ corresponding to each information into the path determination model to obtain the model processing result.

[0112] The embodiment of the present application does not specifically limit the type of the path determination model. For example, the path determination model can be a convolutional neural network (CNN) model, a deep neural network (DNN) model, a support vector machine (SVM) model, etc.

[0113] Assuming that the path determination model is a CNN model, the calculation formula of the CNN model can refer to the following formula 2.

[0114] V = conv2(X, W ′ ) (Formula 2)

[0115] Where V is the model processing result, X is the specific data value of each information of the first data sample a, and W ′ is the first weight corresponding to each information of the first data sample a.

[0116] S302, store the model processing result, the first data sample and the information of the first data sample.

[0117] Specifically, after the UPF network element obtains the model processing result of the path determination model on the first data sample, it can store the model processing result (i.e., multiple transmission paths, and the transmission delay of each transmission path), and store the first data sample and information of the first data sample.

[0118] In some embodiments, the UPF network element may include a storage unit and a routing unit. The UPF network element may store the first data sample and information about the first data sample in the storage unit, and store the model processing result in a routing information table of the routing unit, so that the UPF network element may determine the target transmission path according to the routing information table.

[0119] The following will combine the above-mentioned various implementation methods to introduce the path determination method provided by the present application in detail. Figure 4 An interactive flow chart of a path determination method provided in an embodiment of the present application, such as Figure 4 As shown, the method includes:

[0120] S401, the UPF network element obtains the priority parameter of the first data sample based on the data packet header of the first data sample.

[0121] S402, the UPF network element determines a first weight corresponding to the information of the first data sample based on the priority parameter of the first data sample and the initial weight corresponding to the information of the first data sample.

[0122] S403, the UPF network element inputs the information of the first data sample and the first weight corresponding to the information of the first data sample into the path determination model to obtain a model processing result.

[0123] S404, the UPF network element stores the model processing result, the first data sample and the information of the first data sample.

[0124] S405, the terminal device sends a data packet to the base station.

[0125] S406, the base station sends a data packet to the UPF network element.

[0126] S407, the UPF network element determines at least one target transmission path and the transmission delay of each target transmission path based on the information of the data packet.

[0127] S408, the UPF network element sends a data packet to the network node according to the target transmission path with the minimum transmission delay.

[0128] S409, the network node sends a data packet to the identification node.

[0129] Figure 5 A schematic diagram of a path determination device provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the device comprises:

[0130] The transceiver unit 501 is used to receive data packets from a terminal device.

[0131] The processing unit 502 is used to determine at least one target transmission path and a transmission delay of each target transmission path based on the information of the data packet.

[0132] The transceiver unit 501 is further configured to send data packets along a target transmission path with the minimum transmission delay.

[0133] Optionally, the processing unit 502 is further configured to use at least one transmission path corresponding to the data packet size of the data packet as a target transmission path, and obtain a transmission delay of each target transmission path.

[0134] Optionally, the processing unit 502 is also used to determine at least one network node whose idle time coincides with the time when the UPF network element receives the data packet as a target network node, and based on the target network node, determine at least one target transmission path and the transmission delay of each target transmission path.

[0135] Optionally, the processing unit 502 is further configured to input information of the first data sample into a path determination model to obtain a model processing result.

[0136] Optionally, the processing unit 502 is further used to determine a first weight corresponding to the information of the first data sample, and input the information of the first data sample and the first weight corresponding to the information of the first data sample into the path determination model to obtain a model processing result.

[0137] Optionally, the processing unit 502 is also used to obtain a priority parameter of the first data sample based on the data packet header of the first data sample, and determine a first weight corresponding to the information of the first data sample based on an initial weight corresponding to the information of the first data sample and the priority parameter of the first data sample.

[0138] Figure 6 Another possible structural diagram of the path determination device involved in the above embodiment is shown. The path determination device includes: a processor 601 and a communication interface 602. The processor 601 is used to control and manage the actions of the path determination device, and the communication interface 602 is used to support the communication between the path determination device and other network entities. The path determination device may also include a memory 603 and a bus 604, and the memory 603 is used to store program codes and data of the path determination device.

[0139] Among them, the memory 603 can be a memory in a path determination device, etc., and the memory can include a volatile memory, such as a random access memory; the memory can also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk or a solid-state drive; the memory can also include a combination of the above types of memory.

[0140] The processor 601 may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The processor may be a processor that implements or executes various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0141] The bus 604 may be an extended industry standard architecture (EISA) bus, etc. The bus 604 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0142] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0143] An embodiment of the present application provides a computer program product including instructions. When the computer program product is run on a computer, the computer is enabled to execute the path determination method in the above method embodiment.

[0144] An embodiment of the present application also provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the path determination method in the method flow shown in the above method embodiment.

[0145] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read mnly memory (EPROM), a register, a hard disk, 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, or any other form of computer-readable storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). In the embodiments of the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0146] An embodiment of the present invention provides a computer program product including instructions, which, when executed on a computer, enables the computer to execute the path determination method described in the embodiment of the present application.

[0147] Since the path determination device, computer-readable storage medium, and computer program product in the embodiments of the present invention can be applied to the above method, the technical effects that can be obtained can also refer to the above method embodiments, and the embodiments of the present invention will not be repeated here.

[0148] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0151] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A path determination method, characterized in that: Applied to a user plane function UPF network element, the method comprises: Receive data packets from terminal devices; Based on the information of the data packet, determine at least one target transmission path and a transmission delay of each of the target transmission paths; The data packet is sent according to the target transmission path with the smallest transmission delay.

2. The method according to claim 1, characterized in that The UPF network element stores the correspondence between the data packet size and the transmission path, as well as the transmission delay of each transmission path; the information of the data packet includes the data packet size of the data packet; The determining, based on the information of the data packet, at least one target transmission path and a transmission delay of each of the target transmission paths comprises: Using at least one of the transmission paths corresponding to the data packet size of the data packet as the target transmission path; Obtaining the transmission delay of each target transmission path.

3. The method according to claim 1, characterized in that The UPF network element stores the time when each network node is in an idle state; the information of the data packet includes the time when the UPF network element receives the data packet; The determining, based on the information of the data packet, at least one target transmission path and a transmission delay of each of the target transmission paths comprises: Determine at least one network node whose idle time coincides with the time when the UPF network element receives the data packet as a target network node; Based on the target network node, at least one target transmission path and a transmission delay of each of the target transmission paths are determined.

4. The method according to any one of claims 1 to 3, characterized in that A path determination model is deployed in the UPF network element, and the method further includes: Input the information of the first data sample into the path determination model to obtain a model processing result; the information of the first data sample at least includes the data packet size of the first data sample, the time when the UPF network element sends the first data sample to the target node, and the time when the UPF network element receives the response message sent by the target node; the target node is an identification node or a network node; the response message is used to indicate that the target node has received the first data sample sent by the UPF network element; the model processing result at least includes multiple transmission paths and the transmission delay of each transmission path; The model processing result, as well as the first data sample and information of the first data sample are stored.

5. The method according to claim 4, characterized in that The step of inputting information of the first data sample into the path determination model to obtain a model processing result includes: Determine a first weight corresponding to the information of the first data sample; the first weight is used to characterize the importance of the information of the first data sample to the transmission delay; The information of the first data sample and the first weight corresponding to the information of the first data sample are input into the path determination model to obtain the model processing result.

6. The method according to claim 5, characterized in that The determining a first weight corresponding to the information of the first data sample includes: Based on the data packet header of the first data sample, obtaining a priority parameter of the first data sample; Based on the initial weight corresponding to the information of the first data sample and the priority parameter of the first data sample, the first weight corresponding to the information of the first data sample is determined; the initial weight corresponding to the information of the first data sample is set by the UPF network element.

7. The method according to claim 4, characterized in that The first data sample is any of the following: The data packet generated by the UPF network element; The UPF network element receives historical data packets from the terminal device.

8. A path determination device, characterized in that: The device comprises: A transceiver unit, used for receiving data packets from a terminal device; A processing unit, configured to determine at least one target transmission path and a transmission delay of each of the target transmission paths based on information of the data packet; The transceiver unit is further used to send the data packet according to the target transmission path with the smallest transmission delay.

9. A path determination device, characterized in that: include: A processor and a communication interface; the communication interface is coupled to the processor, and the processor is used to run a computer program or instruction to implement the path determination method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions. When a computer executes the instructions, the computer executes the path determination method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed on a computer, the computer is caused to execute the path determination method according to any one of claims 1 to 7.

Images