Uplink interference identification method and device, electronic equipment and storage medium

Abstract

The invention provides an uplink interference identification method and device, electronic equipment and a storage medium, and relates to the technical field of interference identification. The method comprises the following steps: constructing a first node feature of each node in an interference feature pattern based on network information of each user terminal; wherein the interference characteristic pattern takes each user terminal as a node; based on the position information and the uplink beam information of each user terminal, constructing an edge weight between the nodes; based on the first node feature and the edge weight, determining an interference influence degree between the nodes; and determining an uplink interference terminal based on the interference influence degrees among the nodes. According to the method and the device, the uplink interference terminal can be identified, so that accurate interference positioning can be provided for subsequent network interference optimization, the network interference phenomenon can be reduced, and the network quality can be improved.

Description

Technical Field

[0001] The present invention relates to the field of interference identification technology, and in particular to an uplink interference identification method, device, electronic equipment and storage medium. Background Art

[0002] At present, China Mobile's 5G network uses 2.6G co-frequency networking. For areas with dense sites and high traffic volume, uplink interference between macro-macro, macro-micro, and macro sites and indoor sites is inevitable. The existing methods for reducing 5G TDD (Time Division Duplexing) network interference include: SRS (Sounding Reference Signal) resource configuration optimization, uplink power control, cyclic prefix, etc. However, none of the above methods can identify uplink interference and cannot optimize network interference through precise positioning. Summary of the invention

[0003] The embodiments of the present invention provide an uplink interference identification method, device, electronic device and storage medium, which are used to solve the technical problem that interference positioning cannot be performed in existing interference solutions.

[0004] In a first aspect, an embodiment of the present invention provides an uplink interference identification method, comprising: constructing a first node feature of each node in an interference feature graph based on network information of each user terminal; wherein the interference feature graph takes each user terminal as a node; constructing edge weights between each node based on location information and uplink beam information of each user terminal; determining the interference impact degree between each node based on the first node feature and the edge weight; and determining the uplink interference terminal based on the interference impact degree between each node.

[0005] In some embodiments, the edge weights between the nodes are constructed based on the location information and uplink beam information of the user terminals, including: determining the spatial distance between the user terminals based on the location information of the user terminals; determining the beam influence between the user terminals based on the uplink beam information of the user terminals; and determining the edge weights between the nodes based on the spatial distance and the beam influence.

[0006] In some embodiments, determining the interference influence between the nodes based on the first node feature and the edge weight includes: fusing the first node feature with the edge weight to obtain the second node feature of the nodes; determining a similarity matrix based on the second node feature of the nodes; performing spectral clustering based on the similarity matrix to obtain multiple interference node sets; and determining the interference influence between the nodes in each of the interference node sets based on the edge weight.

[0007] As a possible implementation method, the first node feature is fused with the edge weight to obtain the second node feature of each node, including: based on a graph convolution operation, the first node feature and the edge weight are fused to obtain the second node feature of each node.

[0008] As a possible implementation method, determining the interference impact between each node in each interference node set based on the edge weight includes: obtaining the interference level value between each node in each interference node set; and determining the interference impact between each node in each interference node set based on the interference level value and the edge weight.

[0009] In some embodiments, determining the uplink interference terminal based on the interference impact between the nodes includes: determining a target interference node from the nodes based on the interference impact between the nodes and an interference impact threshold; and determining the uplink interference terminal based on the target interference node.

[0010] In the second aspect, an embodiment of the present invention provides an uplink interference identification device, comprising: a first construction module, used to construct a first node feature of each node in an interference feature map based on network information of each user terminal; wherein the interference feature map has each user terminal as a node; a second construction module, used to construct an edge weight between each node based on location information and uplink beam information of each user terminal; a first determination module, used to determine the interference impact degree between each node based on the first node feature and the edge weight; and a second determination module, used to determine the uplink interference terminal based on the interference impact degree between each node.

[0011] In a third aspect, an embodiment of the present invention provides a network device, including a memory, a transceiver, and a processor; the memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: based on the network information of each user terminal, construct a first node feature of each node in an interference feature map; wherein the interference feature map takes each user terminal as a node; based on the location information and uplink beam information of each user terminal, construct an edge weight between each node; based on the first node feature and the edge weight, determine the interference impact degree between each node; based on the interference impact degree between each node, determine the uplink interference terminal.

[0012] In a fourth aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory storing a computer program, wherein the processor implements the uplink interference identification method described in the first aspect when executing the program.

[0013] In a fifth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the uplink interference identification method described in the first aspect.

[0014] In a sixth aspect, an embodiment of the present invention provides a computer program product, including a computer program, and when the computer program is executed by a processor, the uplink interference identification method described in the first aspect is implemented.

[0015] The uplink interference identification method, device, electronic device and storage medium provided by the embodiments of the present invention construct the first node feature of each node in the interference feature graph based on the network information of each user terminal; wherein the interference feature graph takes each user terminal as a node; constructs the edge weight between each node based on the location information and uplink beam information of each user terminal; determines the interference influence degree between each node based on the first node feature and the edge weight; determines the uplink interference terminal based on the interference influence degree between each node. The present invention realizes the identification of uplink interference terminals by constructing an interference feature graph in combination with the network information, location information and uplink beam information of the user terminal, and determines the interference influence degree between each node based on the interference feature graph, thereby providing accurate interference positioning for subsequent network interference optimization, thereby reducing the interference phenomenon of 5G TDD network and improving network quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of an uplink interference identification method provided by an embodiment of the present invention; Figure 2 A second flow chart of an uplink interference identification method provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an uplink interference identification device provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a network device provided according to an embodiment of the present invention; Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In the related technologies, the solutions to reduce the interference phenomenon of 5G TDD networks include: SRS resource configuration optimization, uplink power control, cyclic prefix optimization and other methods, which can improve the network interference situation in some scenarios. However, none of the above methods combines the new features of 5G air interface to design interference avoidance solutions, and even sacrifice spectrum efficiency to reduce the network co-frequency interference in light load scenarios, which is not enough to apply to the increasingly complex 5G application scenarios in the future.

[0020] In order to solve the above problem, the present invention provides an uplink interference identification method, device, electronic device and storage medium.

[0021] Figure 1 FIG. 1 is a flow chart of an uplink interference identification method provided by an embodiment of the present invention. Figure 1 As shown, the method may include the following steps.

[0022] Step 101, based on the network information of each user terminal, construct the first node feature of each node in the interference feature graph; wherein the interference feature graph takes each user terminal as a node.

[0023] In some embodiments, each user terminal may be an uplink transmitting user terminal currently residing in a 5G network. The network information of each user terminal may be network basic data of each user terminal during the current service.

[0024] In some embodiments, the network information of each user terminal may include the SRS set configured by the user, SRS resources, information that can be used for uplink and downlink beam management, uplink adaptation, and uplink channel correlation measurement, and may also include throughput, number of users, beam space grid, measurement information of serving cells and neighboring cells, etc. The network information of each user terminal may be obtained through the network management data platform, or may be obtained through the base station data management platform.

[0025] As an example, the network information of each user terminal may include the data in Table 1 below.

[0026] Table 1 Network information of each user terminal

[0027] In some embodiments, each user terminal may be regarded as a node in the interference feature graph, and various data included in the network information of each user terminal may be concatenated and combined, and the node feature of the corresponding node may be obtained through encoding conversion.

[0028] Step 102: construct edge weights between nodes based on the location information and uplink beam information of each user terminal.

[0029] In some embodiments, the location information of each user terminal may be user longitude and latitude information. The uplink beam information of each user terminal may include SRS beam level information.

[0030] It can be understood that the location information and uplink beam speed information between user terminals can have a direct impact on the interference between user terminals, so the edge weights between two nodes can be determined based on the location information and uplink beam information between user terminals. In other words, the edge weights between two nodes in the interference feature graph can characterize the degree of association between nodes. If the edge weight is larger, it means that the association between the two nodes is closer, and the more likely there is interference. If the edge weight is smaller, it means that the association between the two nodes is not close, and the possibility of interference is smaller.

[0031] In some embodiments, based on the location information and uplink beam information of each user terminal, constructing edge weights between each node includes: determining the spatial distance between each user terminal based on the location information of each user terminal; determining the beam influence between each user terminal based on the uplink beam information of each user terminal; and determining the edge weights between each node based on the spatial distance and the beam influence. The location information of each user terminal may be user longitude and latitude information, and the uplink beam information may be an SRS beam level value.

[0032] As a possible implementation manner, based on the location information of each user terminal, determining the spatial distance between each user terminal can be implemented by the following formula (1).

[0033] (1); in, is the spatial distance between user terminal i and user terminal j; is the longitude of user terminal i; is the dimension of user terminal i; is the longitude of user terminal j; is the dimension of user terminal j; , represents the latitude difference between user terminal i and user terminal j; , represents the difference in latitude between user terminal i and user terminal j.

[0034] As a possible implementation method, the implementation method of determining the beam influence between each user terminal based on the uplink beam information of each user terminal includes: determining the level difference between each user terminal based on the SRS beam level value of each user terminal; determining the beam influence between each user terminal based on the level difference and the corresponding relationship between the preset level difference and the beam influence. As an example, the level difference n between user terminal i and user terminal j can be determined based on the difference in SRS beam level values ​​between user terminal i and user terminal j; based on the following Table 2, determine the SRS beam influence m (i, j) corresponding to the level difference n.

[0035] Table 2 Correspondence between level difference and wave velocity influence

[0036] As an example, based on the spatial distance and beam influence, the edge weights between nodes can be determined using the following formula (2).

[0037] (2); in, is the edge weight between node i and node j; is the spatial distance between user terminal i and user terminal j; is the beam influence between user terminal i and user terminal j.

[0038] Step 103: Determine the interference influence between the nodes based on the first node feature and the edge weight.

[0039] In some embodiments, the interference influence between the nodes can be determined by a graph neural network according to the first node feature and the variable weight, wherein the graph neural network can be trained based on the interference feature graph sample and the interference influence degree labels between the nodes.

[0040] In some embodiments, a symmetric similarity matrix between nodes can be determined based on the first node feature and the edge weight; graph clustering is performed based on the similarity matrix to divide each node in the interference feature graph into multiple interference node sets; and the interference influence between each node is determined based on the nodes included in each interference node set and the edge weights between each node.

[0041] The interference impact degree between nodes refers to the interference impact degree value of each node on other nodes. For example, the interference impact degree of node i on node j is Rji, and the interference impact degree of node j on node i is Rij.

[0042] Step 104: determine the uplink interference terminal based on the interference impact degree between each node.

[0043] In some embodiments, the interference impacts between the nodes may be ranked, and the user terminal corresponding to the interference node corresponding to the highest interference impact value may be determined as the uplink interference terminal. As an example, if the highest interference impact value is Rij, that is, node j has the highest interference impact on node i, then the user terminal interfering with node j is the uplink interference terminal.

[0044] In other embodiments, the target interference node can be determined from each node based on the interference impact degree between each node and the interference impact degree threshold; based on the target interference node, the uplink interference terminal is determined. As an example, the interference impact degree between each node can be compared with the interference impact degree threshold to determine the target interference impact degree greater than the interference impact degree threshold; the interference node corresponding to the target interference impact degree is determined as the target interference node; and the user terminal corresponding to the target interference node is determined as the uplink interference terminal. The number of target interference nodes can be one or more.

[0045] For example, if the interference impact Rij of node j on node i is greater than the interference impact threshold, node j is determined as a target interference node, and the user terminal corresponding to node j is determined as an uplink interference terminal.

[0046] In some embodiments, if it is determined that node j is an uplink interference terminal, the cell where the uplink interference terminal is located may be network optimized to accurately suppress network interference and improve network service quality.

[0047] According to the uplink interference identification method of the embodiment of the invention, based on the network information of each user terminal, the first node feature of each node in the interference feature map is constructed; wherein, the interference feature map takes each user terminal as a node; based on the location information and uplink beam information of each user terminal, the edge weight between each node is constructed; based on the first node feature and the edge weight, the interference influence between each node is determined; based on the interference influence between each node, the uplink interference terminal is determined. The present invention realizes the identification of uplink interference terminals by constructing an interference feature map in combination with the network information, location information and uplink beam information of the user terminal, and determining the interference influence between each node based on the interference feature map, so as to provide accurate interference positioning for subsequent network interference optimization, thereby reducing the interference phenomenon of 5G TDD network and improving network quality.

[0048] Figure 2 The second flowchart of the uplink interference identification method provided by the embodiment of the present invention is as follows. Figure 2 As shown, based on the above embodiments, Figure 1 The implementation process of step 103 in may include the following steps.

[0049] Step 201: The first node feature is fused with the edge weight to obtain the second node feature of each node.

[0050] In some embodiments, the first node feature and the corresponding edge weight may be concatenated to achieve a fusion process of the two and obtain the second node feature of each node.

[0051] In some embodiments, the first node features and edge weights may be fused through an attention graph neural network to obtain second node features of each node.

[0052] In some embodiments, the first node features and edge weights may be fused based on a graph convolution operation to obtain second node features of each node.

[0053] As an implementation method, the adjacency matrix Z can be determined based on the edge weights between each node, and the feature matrix Y={y1,y2,…yn} can be determined based on the first node feature of each node, where yi is the first node feature of node i and n is the total number of nodes; based on the adjacency matrix Z, the degree matrix D is constructed; and the standardized Laplace matrix is ​​constructed ; Assume the graph convolution order k, and perform graph convolution on the interference feature graph to fuse the edge weights between nodes with the first node features to obtain the second node feature matrix of each node .

[0054] Step 202: Determine a similarity matrix based on the second node feature of each node.

[0055] In some embodiments, the similarity matrix may be determined by the following formula (3).

[0056] (3); in, is a similarity matrix; is the second characteristic matrix.

[0057] Step 203: Perform spectral clustering processing based on the similarity matrix to obtain multiple interference node sets.

[0058] It can be understood that each node has node features related to the serving cell and the neighboring cell. The higher the similarity of node features between different nodes and the closer the spatial distance, the greater the possibility of interference between nodes. Therefore, the interference feature graph can be cut by spectral clustering to make the sum of edge weights between different subgraphs as low as possible after cutting, while the sum of edge weights within the subgraph is as high as possible. The subgraph obtained in this step is the interference node set.

[0059] In some embodiments, each node can be divided into s interference node sets, where s is a positive integer greater than 1. Calculate the eigenvector y corresponding to the first s largest eigenvalues ​​of the similarity matrix W, and form an n×s feature matrix F with the s eigenvectors; take each row in F as an s-dimensional vector sample, with a total of n samples, and perform clustering on the feature matrix F based on the K-means algorithm to obtain a matrix A. , is the i-th interference node set, each interference node set includes multiple nodes, and s interference node sets can be determined based on A.

[0060] The embodiment of the present invention combines graph convolution operations with spectral clustering operations to divide nodes with a high possibility of interference into the same interference node set, and makes the possibility of interference between nodes in different interference node sets as low as possible, so as to improve the accuracy of subsequent interference impact calculation, thereby improving the ability to identify uplink interference.

[0061] In some other embodiments, the embodiments of the present invention may be implemented based on a spectral clustering method of adaptive graph convolution, and the implementation process of step 201 to step 203 specifically includes the following steps.

[0062] Step S1, define the initial iteration number r=0, determine the adjacency matrix Z based on the edge weights between each node, determine the feature matrix Y={y1,y2,…yn} based on the first node feature of each node, yi is the first node feature of node i, n is the total number of nodes, construct the degree matrix D according to the adjacency matrix Z, and construct the standardized Laplace matrix ; Step S2, let r=r+1, set the graph convolution order k=r, perform k-order graph convolution on the interference feature graph, so as to fuse the edge weights between nodes and the first node features, and obtain the matrix composed of the second node features of each node ; Step S3, calculate the symmetric similarity matrix between nodes ; Step S4, perform spectral clustering on the similarity matrix W, that is, calculate the eigenvectors corresponding to the first s largest eigenvalues ​​of W, and form these s eigenvectors into an n×s feature matrix F. Each row in F is taken as an s-dimensional vector sample, and there are n samples in total. Use the input K-means algorithm to perform clustering and obtain the matrix ; Step S5, calculate the distance within the interference node set and the distance between the interference node set ,in It is defined as the mean of the average distances between samples in the set, for The i-th row vector of . The calculation formula is as follows (4).

[0063] (4); in, is the i-th node; is the jth node.

[0064] It is defined as the average value of the distance between the centroids of each interference set, and the calculation formula is as follows (5).

[0065] (5); in, is the centroid of the interference node set i, and its calculation formula is as follows (6).

[0066] (6); Step S6, return to step S2 and continue to execute until and ,or That is, the loop iteration termination condition is: the distance within the interference node set is no longer reduced compared with the previous iteration, and the distance between sets is no longer increased or the number of iterations is greater than s, and based on A obtained when the iteration is terminated, multiple interference node sets are determined.

[0067] In an embodiment of the present invention, the structural features and node features of the interference feature graph are fused through the spectral clustering algorithm of adaptive graph convolution, and each node is divided into different interference node sets, which can further improve the accuracy of the interference node set division, thereby further improving the accuracy of interference identification.

[0068] Step 204: Determine the interference influence between each node in each interference node set based on the edge weight.

[0069] The interference influence degree between each node in each interference node set refers to the interference influence degree of each node in the interference node set by each other node in the set. , then the interference node set The interference impact between each node includes right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact , right The interference impact .

[0070] In some embodiments, interference measurement information between various nodes may be obtained, and for each interference node set, the interference influence between the two nodes in the interference node set may be determined based on the edge weights between the two nodes and the corresponding interference measurement information. For example, the edge weight between node i and node j may be multiplied by the interference measurement information of node i to node j to obtain the interference influence of node i on node j.

[0071] In some embodiments, the interference measurement information may be an interference level value, or an interference power value, etc.

[0072] In some embodiments, based on edge weights, the implementation process of determining the interference impact between each node in each interference node set may include: obtaining the interference level value between each node in each interference node set; and determining the interference impact between each node in each interference node set based on the interference level value and edge weights.

[0073] For example, according to the interference level value and the edge weight, the implementation process of determining the interference influence degree between each node in each interference node set is as follows (7).

[0074] (7); in, is the edge weight between node i and node j; is the interference level value of node j to node i; To interfere with the background noise; is the interference impact of node j on node i.

[0075] According to the uplink interference identification method of the embodiment of the present invention, the first node feature and the edge weight are fused to obtain the second node feature of each node, a similarity matrix is ​​determined based on the second node feature of each node, and spectral clustering is performed based on the similarity matrix to obtain multiple interference node sets, and the interference influence between each node in each interference node set is determined based on the edge weight. The present invention divides each node into different interference node sets through feature fusion processing and spectral clustering processing, which can improve the accuracy of interference identification.

[0076] The following describes an uplink interference identification device provided by an embodiment of the present invention. The uplink interference identification device described below and the uplink interference identification method described above can be referred to each other.

[0077] Figure 3 Schematic diagram of the structure of the uplink interference identification device provided by the embodiment of the present invention. Figure 3 As shown, the device includes: a first construction module 310 , a second construction module 320 , a first determination module 330 and a second determination module 340 .

[0078] A first construction module 310 is used to construct a first node feature of each node in an interference feature graph based on network information of each user terminal; wherein the interference feature graph takes each user terminal as a node; A second construction module 320 is used to construct edge weights between nodes based on location information and uplink beam information of each user terminal; A first determination module 330, configured to determine the interference influence between the nodes based on the first node feature and the edge weight; The second determination module 340 is configured to determine an uplink interference terminal based on the interference impact degree between each node.

[0079] In some embodiments, the second construction module 320 is specifically used to: determine the spatial distance between each user terminal based on the location information of each user terminal; determine the beam influence between each user terminal based on the uplink beam information of each user terminal; and determine the edge weight between each node based on the spatial distance and the beam influence.

[0080] In some embodiments, the first determination module 330 is specifically used to: fuse the first node feature with the edge weight to obtain the second node feature of each node; determine the similarity matrix based on the second node feature of each node; perform spectral clustering based on the similarity matrix to obtain multiple interference node sets; and determine the interference influence between each node in each interference node set based on the edge weight.

[0081] As a possible implementation manner, the first determination module 330 is further used to: based on a graph convolution operation, fuse the first node features and the edge weights to obtain the second node features of each node.

[0082] As a possible implementation manner, the first determination module 330 is further used to: obtain the interference level value between each node in each interference node set; and determine the interference impact degree between each node in each interference node set according to the interference level value and the edge weight.

[0083] In some embodiments, the second determination module 340 is specifically used to: determine a target interference node from each node based on the interference impact degree and the interference impact degree threshold between each node; and determine an uplink interference terminal based on the target interference node.

[0084] It should be noted that the above explanations and descriptions in the embodiment of the uplink interference identification method are also applicable to the uplink interference identification device in the embodiment of the present invention, and will not be described in detail here.

[0085] The network device involved in the embodiment of the present invention may be a base station, which may include multiple cells providing services for user terminals. Depending on the specific application scenario, the base station may also be called an access point, or may be a device in the access network that communicates with a wireless terminal device through one or more sectors on the air interface, or other names.

[0086] Figure 4 A schematic diagram of the structure of a network device according to an embodiment of the present invention, referring to Figure 4 The embodiment of the present invention further provides a network device, which may include: a memory 410, a transceiver 420 and a processor 430.

[0087] The memory 410 is used to store computer programs; the transceiver 420 is used to send and receive data under the control of the processor 430; the processor 430 is used to read the computer program in the memory 410 and perform the following operations: based on the network information of each user terminal, construct the first node characteristics of each node in the interference characteristic graph; wherein the interference characteristic graph takes each user terminal as a node; based on the location information and uplink beam information of each user terminal, construct the edge weights between each node; based on the first node characteristics and the edge weights, determine the interference impact between each node; based on the interference impact between each node, determine the uplink interference terminal.

[0088] Among them, Figure 4 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 430 and various circuits of memory represented by memory 410 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 420 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 430 is responsible for managing the bus architecture and general processing, and the memory 410 may store data used by the processor 430 when performing operations.

[0089] Optionally, the processor 430 is also used to perform the following operations: determine the spatial distance between the user terminals based on the location information of the user terminals; determine the beam influence between the user terminals based on the uplink beam information of the user terminals; and determine the edge weight between the nodes based on the spatial distance and the beam influence.

[0090] Optionally, the processor 430 is further used to perform the following operations: fuse the first node feature with the edge weight to obtain the second node feature of each node; determine a similarity matrix based on the second node feature of each node; perform spectral clustering based on the similarity matrix to obtain multiple interference node sets; and determine the interference influence between each node in each of the interference node sets based on the edge weight.

[0091] Optionally, the processor 430 is further used to perform the following operations: based on a graph convolution operation, fusing the first node features and the edge weights to obtain second node features of each node.

[0092] Optionally, the processor 440 is further used to perform the following operations: obtain the interference level value between each node in each of the interference node sets; and determine the interference impact degree between each node in each of the interference node sets based on the interference level value and the edge weight.

[0093] Optionally, the processor 440 is further configured to perform the following operations: determine a target interference node from among the nodes based on the interference impact degree and an interference impact degree threshold between the nodes; and determine the uplink interference terminal based on the target interference node.

[0094] It should be noted here that the network device provided in the embodiment of the present invention can implement all the method steps implemented in the above method embodiment and can achieve the same technical effect. The parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0095] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call a computer program in the memory 530 to execute the steps of the uplink interference identification method.

[0096] For example, the method includes: constructing the first node feature of each node in the interference feature map based on the network information of each user terminal; wherein the interference feature map takes each user terminal as a node; constructing the edge weight between each node based on the location information and uplink beam information of each user terminal; determining the interference impact degree between each node based on the first node feature and the edge weight; and determining the uplink interference terminal based on the interference impact degree between each node.

[0097] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0098] On the other hand, an embodiment of the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the steps of the uplink interference identification method provided in the above embodiments.

[0099] The method includes: constructing the first node feature of each node in the interference feature map based on the network information of each user terminal; wherein the interference feature map takes each user terminal as a node; constructing the edge weight between each node based on the location information and uplink beam information of each user terminal; determining the interference influence degree between each node based on the first node feature and the edge weight; and determining the uplink interference terminal based on the interference influence degree between each node.

[0100] On the other hand, an embodiment of the present invention further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the steps of the uplink interference identification method provided in the above embodiments.

[0101] For example, the method includes: constructing the first node feature of each node in the interference feature map based on the network information of each user terminal; wherein the interference feature map takes each user terminal as a node; constructing the edge weight between each node based on the location information and uplink beam information of each user terminal; determining the interference impact degree between each node based on the first node feature and the edge weight; and determining the uplink interference terminal based on the interference impact degree between each node.

[0102] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0103] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying uplink interference, characterized in that: include: Based on the network information of each user terminal, construct a first node feature of each node in the interference feature graph; wherein the interference feature graph takes each user terminal as a node; Constructing edge weights between the nodes based on the location information and uplink beam information of the user terminals; Determining the interference influence between the nodes based on the first node characteristics and the edge weights; An uplink interference terminal is determined based on the interference impact degree between the nodes.

2. The method according to claim 1, characterized in that The constructing edge weights between the nodes based on the location information and uplink beam information of the respective user terminals includes: Determining the spatial distance between the user terminals based on the location information of the user terminals; Determining the beam influence between the user terminals based on the uplink beam information of the user terminals; Based on the spatial distance and the beam influence, edge weights between the nodes are determined.

3. The method according to claim 1, characterized in that The determining, based on the first node feature and the edge weight, the interference influence degree between the nodes includes: The first node feature is merged with the edge weight to obtain the second node feature of each node; Determining a similarity matrix based on the second node features of each node; Performing spectral clustering processing based on the similarity matrix to obtain multiple interference node sets; Based on the edge weights, the interference influence degree between each node in each interference node set is determined.

4. The method according to claim 3, characterized in that The fusing the first node feature with the edge weight to obtain the second node feature of each node includes: Based on a graph convolution operation, the first node features and the edge weights are fused to obtain second node features of each node.

5. The method according to claim 3, characterized in that: The determining, based on the edge weight, the interference influence degree between each node in each interference node set comprises: Obtaining interference level values ​​between nodes in each of the interference node sets; The interference influence degree between each node in each interference node set is determined according to the interference level value and the edge weight.

6. The method according to any one of claims 1 to 5, characterized in that The determining of the uplink interference terminal based on the interference impact degree between the nodes includes: Determining a target interference node from among the nodes based on the interference impact degree and the interference impact degree threshold between the nodes; Based on the target interference node, the uplink interference terminal is determined.

7. An uplink interference identification device, characterized in that: include: A first construction module is used to construct a first node feature of each node in an interference feature graph based on network information of each user terminal; wherein the interference feature graph takes each user terminal as a node; A second construction module is used to construct edge weights between the nodes based on the location information and uplink beam information of the user terminals; A first determination module, configured to determine the interference influence degree between the nodes based on the first node feature and the edge weight; The second determining module is used to determine the uplink interference terminal based on the interference impact degree between the nodes.

8. A network device, characterized in that: Includes memory, transceiver, and processor; A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations: Based on the network information of each user terminal, construct a first node feature of each node in the interference feature graph; wherein the interference feature graph takes each user terminal as a node; Constructing edge weights between the nodes based on the location information and uplink beam information of the user terminals; Determining the interference influence between the nodes based on the first node characteristics and the edge weights; An uplink interference terminal is determined based on the interference impact degree between the nodes.

9. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the uplink interference identification method according to any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the uplink interference identification method according to any one of claims 1 to 6 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the uplink interference identification method according to any one of claims 1 to 6 is implemented.

Images