External interference positioning method and device, electronic equipment and storage medium

Abstract

The invention provides an external interference positioning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the working parameter data of a plurality of cells subjected to external interference, and determining the interference types of the plurality of cells; clustering the plurality of cells according to the working parameter data and the interference types of the plurality of cells to obtain a plurality of interference clusters; determining a delineated area corresponding to each main cell of each interference cluster, dividing the delineated area into a plurality of grids, and determining a grid set associated with each main cell of each interference cluster from the plurality of grids; searching adjacent grids from the grid set associated with each main cell to obtain all grid pairs, and determining all non-positive sequence grid pairs according to the RSRP and the RSRQ of the service cell of each grid pair; and determining the position of the external interference source according to the change amplitude of the RSRP and the RSRQ of the service cell of each non-positive sequence grid pair. The interference source positioning accuracy is improved, and the method is suitable for complex and changeable application scenes.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to an external interference localization method, apparatus, electronic device, and storage medium. Background Technology

[0002] External interference is a key factor affecting network quality, easily causing problems such as decreased throughput, coverage contraction, handover failures, and network congestion. Accurately locating external interference is a critical issue that urgently needs to be addressed in network operation and maintenance. Currently, existing external interference location methods rely on historical interference data, considering only a single factor, making it difficult to adapt to complex and ever-changing application scenarios and affecting the accuracy of interference source location. Summary of the Invention

[0003] This invention provides an external interference localization method, apparatus, electronic device, and storage medium to address the shortcomings of existing external interference localization methods, which rely on historical interference data, consider only a single factor, are difficult to adapt to complex and ever-changing application scenarios, and affect the accuracy of interference source localization.

[0004] In a first aspect, the present invention provides an external interference localization method, comprising: Obtain the operating parameter data of multiple cells in the target wireless network that are subject to external interference, and determine the interference type of the multiple cells subject to external interference; Based on the engineering parameter data and interference type of the multiple cells affected by external interference, the multiple cells affected by external interference are clustered to obtain multiple interference clusters. Each interference cluster includes N main cells, where N is a natural number greater than or equal to 1. Determine the defined area corresponding to each main cell of each interference cluster, divide the defined area into multiple grids, and determine the grid set associated with each main cell of each interference cluster from the multiple grids; Search for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs. Based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cell of the multiple grid pairs, determine multiple non-order grid pairs from the multiple grid pairs. The location of the external interference source is determined based on the variation magnitude of the RSRP and RSRQ of the serving cell for each non-order grid pair.

[0005] In some embodiments, the step of searching for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs, and determining multiple non-order grid pairs from the multiple grid pairs based on the RSRP and RSRQ of the serving cells of the multiple grid pairs, includes: The first grid cell is determined from the grid set associated with each primary cell; From the set of grids associated with each primary cell, select the second grid that is closest to the first grid, wherein the serving cell RSRP of the second grid is greater than that of the first grid; Determine whether the RSRQ of the serving cell of the second grid is less than that of the serving cell of the first grid. If so, determine that the grid pair consisting of the first grid and the second grid is a non-order grid pair. Traverse all grids in the grid set associated with each primary cell and find all non-order grid pairs in the grid set associated with each primary cell.

[0006] In some embodiments, determining the delineated area corresponding to each primary cell of each interference cluster, dividing the delineated area into multiple grids, and determining the grid set associated with each primary cell of each interference cluster from the multiple grids includes: Taking each main cell of each interference cluster as the center and a preset threshold as the radius, the delineated area corresponding to each main cell of each interference cluster is determined; The defined area is divided into multiple grids; Obtain the location information of the multiple grids, as well as the radio parameters of the serving cells of the multiple grids; Based on the location information of the multiple grids, the multiple grids are filtered to obtain multiple grids within the defined area corresponding to each main cell; The radio parameters of the serving cells of multiple grids within the delineated area corresponding to each main cell are compared with the radio parameters of each main cell, and the set of grids associated with each main cell is determined from the multiple grids within the delineated area corresponding to each main cell.

[0007] In some embodiments, determining the location of the external interference source based on the variation magnitude of the RSRP and RSRQ of the serving cell for each non-order grid pair includes: Based on the improvement of the serving cell RSRP of each non-order grid pair and the degradation of the serving cell RSRQ of each non-order grid pair, the non-order grid pair with the greatest difference is determined from the plurality of non-order grid pairs. The location of the external interference source is determined based on the position information of the non-order grid pair with the greatest difference.

[0008] In some embodiments, the step of clustering the multiple cells affected by external interference based on their engineering parameter data and interference type to obtain multiple interference clusters includes: Based on the base stations and interference types corresponding to the multiple cells affected by external interference, the multiple cells affected by external interference are deduplicated to obtain multiple disturbed cells after deduplication. Based on the latitude, longitude, and operating frequency band of the deduplicated multiple disturbed cells, the deduplicated multiple disturbed cells are divided into multiple areas. Feature extraction is performed on the engineering parameter data and interference type of multiple disturbed cells in each area to obtain the feature data of multiple disturbed cells in each area; The feature data of multiple disturbed cells in each area are input into a deep neural network model to obtain the optimal K value of the predicted K-means clustering for each area output by the deep neural network model. Based on the optimal K value of the predicted K-means clustering for each region, multiple disturbed cells within each region are clustered to obtain multiple interference clusters and the Top N cells within each cluster.

[0009] In some embodiments, before acquiring the engineering parameter data of multiple cells in the target wireless network that are subject to external interference, the method further includes: Acquire the operating parameter data of multiple cells of the target wireless network, as well as the Operation and Maintenance Center (OMC) data of the target wireless network; Extract frequency domain data of multiple cells of the target wireless network from the OMC data; Based on the engineering parameter data and frequency domain data of multiple cells in the target wireless network, the multiple cells in the target wireless network are filtered to identify multiple cells in the target wireless network that are subject to external interference.

[0010] Secondly, the present invention also provides an external interference locating device, comprising: The first acquisition unit is used to acquire the operating parameter data of multiple cells in the target wireless network that are subject to external interference, and to determine the interference type of the multiple cells subject to external interference. The clustering unit is used to cluster the multiple cells affected by external interference according to their operating parameter data and interference type, to obtain multiple interference clusters. Each interference cluster includes N main cells, where N is a natural number greater than or equal to 1. The association unit is used to determine the delineated area corresponding to each main cell of each interference cluster, divide the delineated area into multiple grids, and determine the grid set associated with each cell of each interference cluster from the multiple grids. The determining unit is used to search for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs, and to determine multiple non-order grid pairs from the multiple grid pairs based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cell of the multiple grid pairs. The positioning unit is used to determine the location of external interference sources based on the variation amplitude of RSRP and RSRQ of the serving cell for each non-order grid pair.

[0011] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the external interference localization methods described above.

[0012] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the external interference localization method as described above.

[0013] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the external interference localization methods described above.

[0014] The external interference localization method, apparatus, electronic device, and storage medium provided by this invention utilize the power parameter data and interference type of multiple cells in a target wireless network subject to external interference to cluster the multiple cells subject to external interference, obtaining multiple interference clusters. A delineated area corresponding to each main cell of each interference cluster is determined. From multiple grids in the delineated area, a set of grids associated with each main cell of each interference cluster is determined. Adjacent grids are searched from the set of grids associated with each main cell to obtain multiple grid pairs. Based on the Reference Signal Received Power (RSRP) and Reference Signal Received Quality (RSRQ) of the serving cells of the multiple grid pairs, multiple non-order grid pairs are determined from the multiple grid pairs. The location of the external interference source is determined based on the variation amplitude of RSRP and RSRQ of the serving cells of each non-order grid pair. This improves the accuracy of interference source localization and is suitable for complex and ever-changing application scenarios. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the external interference localization method provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of determining the grid set associated with each primary cell of each interference cluster, as provided in an embodiment of the present invention. Figure 3 This is a flowchart illustrating the method for determining non-orthogonal grid pairs provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the external interference positioning device provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0018] Figure 1 This is a flowchart illustrating the external interference localization method provided in an embodiment of the present invention. Figure 1 As shown, an external interference localization method is provided, including the following steps: steps 110-150. This method's steps are merely one possible implementation of the present invention.

[0019] Step 110: Obtain the operating parameter data of multiple cells in the target wireless network that are subject to external interference, and determine the interference type of the multiple cells subject to external interference.

[0020] Optionally, the engineering parameter data may include at least the cell frequency band, frequency point, bandwidth, subcarrier spacing, longitude, latitude, and other information.

[0021] In some embodiments, before acquiring the power parameter data of multiple cells in the target wireless network that are subject to external interference, the method further includes: Acquire the operating parameter data of multiple cells of the target wireless network, as well as the Operation and Maintenance Center (OMC) data of the target wireless network; Extract frequency domain data of multiple cells of the target wireless network from OMC data; Based on the engineering parameter data and frequency domain data of multiple cells in the target wireless network, multiple cells in the target wireless network are screened to identify multiple cells in the target wireless network that are subject to external interference.

[0022] Optionally, frequency domain data of multiple cells per day (i.e., 24 hours) can be extracted from OMC data, and interference cell analysis can be performed based on existing threshold rules and algorithms.

[0023] Optionally, the frequency domain data includes information on the power of the interference.

[0024] Understandably, by utilizing the engineering parameter data and OMC data of multiple cells, multiple cells in the target wireless network that are subject to external interference can be identified, providing a data foundation for the accurate location of subsequent interference sources.

[0025] Step 120: Based on the engineering parameter data and interference type of the multiple cells affected by external interference, cluster the multiple cells affected by external interference to obtain multiple interference clusters. Each interference cluster includes N main cells, where N is a natural number greater than or equal to 1.

[0026] Optionally, the K-means algorithm can be used to cluster multiple cells affected by external interference along the geographical dimension, forming multiple interference clusters.

[0027] In some embodiments, based on the engineering parameter data and interference type of multiple cells subject to external interference, multiple interference clusters are obtained, including: Based on the base stations and interference types corresponding to the multiple cells affected by external interference, the multiple cells affected by external interference are deduplicated to obtain the multiple disturbed cells after deduplication. Based on the latitude, longitude, and operating frequency band of the multiple deduplicated disturbed cells, the multiple deduplicated disturbed cells are divided into multiple areas. Feature extraction is performed on the engineering parameter data and interference type of multiple disturbed cells in each area to obtain the feature data of multiple disturbed cells in each area; The feature data of multiple disturbed cells in each area are input into a deep neural network model to obtain the optimal K value of the predicted K-means clustering for each area output by the deep neural network model. Based on the optimal K value of the predicted K-means clustering for each area, multiple disturbed cells within each area are clustered to obtain multiple disturbance clusters and the Top N cells within each cluster.

[0028] Optionally, the deep neural network model can determine the number of clusters in each region, i.e., the number of K-means categories.

[0029] The deep neural network model is trained based on the sample feature data of multiple disturbed cells within the sample area, as well as the optimal K-value label for the predicted K-means clustering of the sample area.

[0030] Optionally, duplicate cells affected by the same type of interference from the same base station can be deduplicated.

[0031] Optionally, based on the average interference of each cell, the cell most affected by the same type of interference within the same base station can be identified and retained.

[0032] Optionally, a scatter plot is constructed based on the interference mean of multiple deduplicated disturbed cells. The scatter plot is then input into a pre-trained deep neural network model to obtain the optimal K value for K-means clustering corresponding to the scatter plot output by the deep neural network model. Based on the optimal K value, multiple deduplicated disturbed cells are clustered to obtain multiple interference clusters.

[0033] Optionally, the deep neural network model includes an input layer, a first convolutional layer, an activation layer, a pooling layer, a second convolutional layer, a fully connected layer, a Dropout layer, and an output layer.

[0034] Optionally, the input layer is used to receive the regularized scatter plot, where the value of each point is the mean of the interference, i.e., the image representation of the regularized scatter plot before clustering. The size of the input layer is 64x64x1.

[0035] Optionally, the first convolutional layer (Conv2D-32) includes 32 convolutional kernels of size 3x3, used to extract local features of the scatter plot, with each kernel responsible for extracting a specific feature from the image.

[0036] Optionally, the activation layer (ReLU) applies the ReLU function to set all negative values ​​to 0 and retain positive values; the pooling layer (MaxPooling-2x2) is used to select the maximum value of each 2x2 region.

[0037] Optionally, the second convolutional layer (Conv2D-64) includes 64 3x3 convolutional kernels for extracting higher-level features.

[0038] Optionally, a fully connected layer (Dense-128) is used to further process the flattened feature vector; a dropout layer (Dropout-0.5) is used to randomly drop 50% of the neurons for regularization to prevent the network from overfitting.

[0039] Optionally, the output layer (Dense-1) is used to predict the optimal K value for K-means clustering.

[0040] Optionally, the interference cluster includes N primary cells, i.e., TopN cells, where N is a natural number greater than or equal to 1.

[0041] Understandably, by utilizing deep neural networks to modify the local K-means algorithm, the number of K-means categories can be automatically and intelligently output for interference scenarios, thereby improving the automation level and scenario adaptability of the K-means algorithm and increasing the accuracy of interference clustering results.

[0042] Step 130: Determine the delineated area corresponding to each primary cell of each interference cluster, divide the delineated area into multiple grids, and determine the grid set associated with each primary cell of each interference cluster from the multiple grids.

[0043] Optionally, a circular area is delineated with each main cell of each interference cluster as the center and a preset threshold as the radius, thus obtaining the delineated area corresponding to each main cell of each interference cluster.

[0044] Optionally, the preset threshold can be 1000m.

[0045] Optionally, location information of multiple grids and radio parameters of the serving cells of multiple grids can be obtained.

[0046] Optionally, the location information of multiple grids, such as latitude and longitude, and the radio parameters of the serving cells of multiple grids, such as the physical cell ID (PCI) and the radio frequency channel number (E-UTRA Absolute Radio Frequency Channel Number, EARFCN) of the serving cells, are obtained to obtain the grid data corresponding to each grid.

[0047] Table 1 shows a sample of raster data provided in an embodiment of the present invention. As shown in Table 1, the raster data includes city, longitude, latitude, raster size, serving cell RSRP, serving cell RSRQ, serving cell RS_SINR, serving cell PCI, and serving cell EARFCN.

[0048] Table 1. Raster data examples provided in the embodiments of the present invention

[0049] Figure 2 This is a flowchart illustrating the process of determining the grid set associated with each primary cell of each interference cluster, as provided in an embodiment of the present invention. Figure 2 As shown, in some embodiments, a delineated area corresponding to each primary cell of each interference cluster is determined, the delineated area is divided into multiple grids, and a set of grids associated with each primary cell of each interference cluster is determined from the multiple grids, including: Centered on each main cell of each interference cluster, and with a preset threshold as the radius, the delineated area corresponding to each main cell of each interference cluster is determined. The defined area is divided into multiple grids; Obtain the location information of multiple grids, as well as the radio parameters of the serving cells of multiple grids; Based on the location information of multiple grids, multiple grids are filtered to obtain multiple grids within the designated area corresponding to each main cell. The radio parameters of the serving cells in the multiple grids within the delineated area corresponding to each main cell are compared with the radio parameters of each main cell, and the set of grids associated with each main cell is determined from the multiple grids within the delineated area corresponding to each main cell.

[0050] Optionally, determine whether the TopN cells of each interference cluster are empty. If yes, end the algorithm; otherwise, record any cell in the TopN cells as cell A, and draw a circle with a preset radius centered on cell A to obtain the delineated area of ​​cell A.

[0051] In this context, the TopN cells of each interference cluster refer to the N primary cells of each interference cluster.

[0052] Optionally, all grids in the defined area are obtained to form a grid set. It is then determined whether the grid set is empty. If so, cell A is deleted. The associated grids of the next cell in the TopN cells are calculated. If not, the grid data of any grid in the grid set is obtained. It is then determined whether the serving cell EARFCN and serving cell PCI of the grid data are consistent with the PCI and frequency information of cell A. If so, the grid is stored as an associated grid of cell A. If not, the grid is skipped and the judgment of the next grid is entered.

[0053] Optionally, after all the grids within the designated area of ​​cell A in the TopN cells have been determined, the process moves on to determining the next cell in the TopN.

[0054] Optionally, select any cell from the TopN and denote it as cell A. Obtain the frequency band, PCI information, and latitude and longitude from the engineering parameters of cell A. Draw a circle with a radius of 1000 meters from its center to obtain the delineated area.

[0055] Optionally, the maximum and minimum longitudes, as well as the maximum and minimum latitudes, within the delineated area can be calculated.

[0056] Step 140: Search for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs. Based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cells of the multiple grid pairs, determine multiple non-order grid pairs from the multiple grid pairs.

[0057] Figure 3 This is a flowchart illustrating the method for determining non-order raster pairs provided in an embodiment of the present invention. Figure 3As shown, in some embodiments, neighboring grids are searched from the grid set associated with each primary cell to obtain multiple grid pairs. Based on the Reference Signal Received Power (RSRP) and Reference Signal Received Quality (RSRQ) of the serving cells of the multiple grid pairs, multiple non-order grid pairs are determined from the multiple grid pairs, including: The first grid cell is determined from the grid set associated with each primary cell; From the set of grids associated with each primary cell, select the second grid that is closest to the first grid, and the serving cell RSRP of the second grid is greater than that of the serving cell RSRP of the first grid; Determine whether the RSRQ of the serving cell of the second grid is less than that of the serving cell of the first grid. If so, determine that the grid pair consisting of the first grid and the second grid is a non-order grid pair. Traverse all grids in the grid set associated with each primary cell and find all non-order grid pairs in the grid set associated with each primary cell.

[0058] Optionally, the distance between two rasters can be calculated based on the latitude and longitude information in the raster data.

[0059] Optionally, the grid A with the smallest serving cell RSRP is determined from the grid set associated with each primary cell. It is then determined whether grid A exists. If so, grid pair A and B are selected. Grid B is the grid closest to grid A in the grid set, and the serving cell RSRP of grid B is greater than that of grid A.

[0060] Optionally, determine if grid pair A and B exist. If they do, determine if grid pair A and B are in ascending order. If they are, remove grid A, record grid B as the new grid A, and re-filter grid pairs A and B. Repeat this process until all non-ascending grid pairs in the grid set have been searched. If not, record grid pair A and B, remove grid A from the grid set, and re-determine the grid A with the smallest RSRP of the serving cell from the grid set associated with each primary cell. Then, perform the next round of searching for non-ascending grid pairs until all non-ascending grid pairs in the grid set have been searched.

[0061] It should be noted that if the RSRP of the serving cell in the second grid is greater than the RSRP of the serving cell in the first grid, and the RSRQ of the serving cell in the second grid is greater than the RSRQ of the serving cell in the first grid, then the first grid and the second grid are a positive-order grid pair; if the RSRQ of the serving cell in the second grid is less than the RSRQ of the serving cell in the first grid, then the first grid and the second grid are a non-positive-order grid pair.

[0062] Step 150: Determine the location of the external interference source based on the variation amplitude of RSRP and RSRQ of the serving cell for each non-order grid pair.

[0063] In some embodiments, determining the location of an external interference source based on the variation magnitude of RSRP and RSRQ of the serving cell for each non-order grid pair includes: Based on the improvement of the serving cell RSRP of each non-order grid pair and the degradation of the serving cell RSRQ of each non-order grid pair, the non-order grid pair with the greatest difference is determined from multiple non-order grid pairs. The location of the external interference source is determined based on the location information of the non-orthogonal grid pairs with the greatest differences.

[0064] Understandably, determining the location of external interference sources based on the variation amplitude of RSRP and RSRQ of the serving cell for each non-order grid pair improves the efficiency and accuracy of interference source localization.

[0065] In this embodiment of the invention, by utilizing the engineering parameter data and interference type of multiple cells in the target wireless network that are subject to external interference, multiple interference clusters are obtained. A delineated area corresponding to each main cell of each interference cluster is determined. From multiple grids in the delineated area, a set of grids associated with each main cell of each interference cluster is determined. Adjacent grids are searched from the set of grids associated with each main cell to obtain multiple grid pairs. Based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cells of the multiple grid pairs, multiple non-order grid pairs are determined from the multiple grid pairs. Based on the variation amplitude of RSRP and RSRQ of the serving cells of each non-order grid pair, the location of the external interference source is determined, which improves the accuracy of interference source location and is suitable for complex and ever-changing application scenarios.

[0066] The external interference location device provided in the embodiments of the present invention is described below. The external interference location device described below and the external interference location method described above can be referred to in correspondence.

[0067] Figure 4 This is a schematic diagram of the external interference positioning device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the external interference locating device 400 includes: The first acquisition unit 410 is used to acquire the operating parameter data of multiple cells in the target wireless network that are subject to external interference, and to determine the interference type of the multiple cells subject to external interference. Clustering unit 420 is used to cluster multiple cells affected by external interference based on their operating parameter data and interference type, resulting in multiple interference clusters. Each interference cluster includes N main cells, where N is a natural number greater than or equal to 1. The association unit 430 is used to determine the delineated area corresponding to each main cell of each interference cluster, divide the delineated area into multiple grids, and determine the grid set associated with each main cell of each interference cluster from the multiple grids. The determining unit 440 is used to search for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs, and to determine multiple non-order grid pairs from the multiple grid pairs based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cells of the multiple grid pairs. The positioning unit 450 is used to determine the location of the external interference source based on the variation magnitude of RSRP and RSRQ of the serving cell for each non-order grid pair.

[0068] Optionally, adjacent grids are searched from the grid set associated with each primary cell to obtain multiple grid pairs. Based on the Reference Received Power (RSRP) and Reference Received Quality (RSRQ) of the serving cells of the multiple grid pairs, multiple non-order grid pairs are determined from the multiple grid pairs, including: The first grid cell is determined from the grid set associated with each primary cell; From the set of grids associated with each primary cell, select the second grid that is closest to the first grid, and the serving cell RSRP of the second grid is greater than that of the serving cell RSRP of the first grid; Determine whether the RSRQ of the serving cell of the second grid is less than that of the serving cell of the first grid. If so, determine that the grid pair consisting of the first grid and the second grid is a non-order grid pair. Traverse all grids in the grid set associated with each primary cell and find all non-order grid pairs in the grid set associated with each primary cell.

[0069] Optionally, a delineated area corresponding to each primary cell of each interference cluster is determined, the delineated area is divided into multiple grids, and a set of grids associated with each cell of each interference cluster is determined from the multiple grids, including: Centered on each main cell of each interference cluster, and with a preset threshold as the radius, the delineated area corresponding to each main cell of each interference cluster is determined. Divide the defined area into multiple grids; Obtain the location information of multiple grids, as well as the radio parameters of the serving cells of multiple grids; The delineated area of ​​each main cell in each interference cluster is determined. Based on the location information of multiple grids, multiple grids are filtered to obtain multiple grids within the delineated area corresponding to each main cell. The radio parameters of the serving cells in the multiple grids within the demarcation area corresponding to each main cell are compared with the radio parameters of each main cell, and the set of grids associated with each main cell is determined from the multiple grids within the demarcation area corresponding to each main cell.

[0070] Optionally, the location of the external interference source is determined based on the variation magnitude of RSRP and RSRQ of the serving cell for each non-order grid pair, including: Based on the improvement of the serving cell RSRP of each non-order grid pair and the degradation of the serving cell RSRQ of each non-order grid pair, the non-order grid pair with the greatest difference is determined from multiple non-order grid pairs. The location of the external interference source is determined based on the location information of the non-orthogonal grid pairs with the greatest differences.

[0071] Optionally, based on the engineering parameter data and interference type of the multiple cells affected by external interference, the multiple cells affected by external interference are clustered to obtain multiple interference clusters, including: Based on the base stations and interference types corresponding to the multiple cells affected by external interference, the multiple cells affected by external interference are deduplicated to obtain the multiple disturbed cells after deduplication. Based on the latitude, longitude, and operating frequency band of the multiple deduplicated disturbed cells, the multiple deduplicated disturbed cells are divided into multiple areas. Feature extraction is performed on the engineering parameter data and interference type of multiple disturbed cells in each area to obtain the feature data of multiple disturbed cells in each area; The feature data of multiple disturbed cells in each area are input into a deep neural network model to obtain the optimal K value of the predicted K-means clustering for each area output by the deep neural network model. Based on the optimal K value of the predicted K-means clustering for each area, multiple disturbed cells within each area are clustered to obtain multiple disturbance clusters and the Top N cells within each cluster.

[0072] Optionally, the external interference locator 400 further includes: The second acquisition unit is used to acquire the operating parameter data of multiple cells of the target wireless network, as well as the operation and maintenance center (OMC) data of the target wireless network. The extraction unit is used to extract frequency domain data of multiple cells of the target wireless network from the OMC data; The filtering unit is used to filter multiple cells of the target wireless network based on the engineering parameter data and frequency domain data of multiple cells of the target wireless network, and to identify multiple cells in the target wireless network that are subject to external interference.

[0073] It should be noted that the external interference positioning device provided in this embodiment of the invention can implement all the method steps implemented in the above-described external interference positioning method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0074] Figure 5 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 510, a communications interface 520, a memory 530, and a communications bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communications bus 540. The processor 510 can call logic instructions in the memory 530 to execute an external interference localization method. This method includes: acquiring power parameter data of multiple cells in a target wireless network that are subject to external interference, and determining the interference type of the multiple cells; clustering the multiple cells subject to external interference based on the power parameter data and interference type to obtain multiple interference clusters, each interference cluster including N main cells, where N is a natural number greater than or equal to 1; determining the delineated area corresponding to each main cell of each interference cluster, dividing the delineated area into multiple grids, and determining the grid set associated with each main cell of each interference cluster from the multiple grids; searching for adjacent grids from the grid set associated with each cell to obtain multiple grid pairs; determining multiple non-order grid pairs from the multiple grid pairs based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cells of the multiple grid pairs; and determining the location of the external interference source based on the variation amplitude of the RSRP and RSRQ of the serving cells of each non-order grid pair.

[0075] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] On the other hand, the present invention also provides a computer program product, which includes a computer program that 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 external interference localization method provided by the above methods. The method includes: acquiring the power parameter data of multiple cells in a target wireless network that are subject to external interference, and determining the interference type of the multiple cells subject to external interference; clustering the multiple cells subject to external interference according to the power parameter data and interference type to obtain multiple interference clusters, each interference cluster including N main cells, where N is a natural number greater than or equal to 1; determining the delineated area corresponding to each main cell of each interference cluster, dividing the delineated area into multiple grids, and determining the grid set associated with each main cell of each interference cluster from the multiple grids; searching for adjacent grids from the grid set associated with each cell to obtain multiple grid pairs, and determining the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cell of the multiple grid pairs. Multiple non-order grid pairs are identified from multiple grid pairs; the location of the external interference source is determined based on the variation amplitude of RSRP and RSRQ of the serving cell of each non-order grid pair.

[0077] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the external interference localization method provided by the above methods. The method includes: acquiring power parameter data of multiple cells in a target wireless network that are subject to external interference, and determining the interference type of the multiple cells subject to external interference; clustering the multiple cells subject to external interference based on the power parameter data and interference type to obtain multiple interference clusters, each interference cluster including N main cells, where N is a natural number greater than or equal to 1; determining a delineated area corresponding to each main cell of each interference cluster, dividing the delineated area into multiple grids, and determining a grid set associated with each main cell of each interference cluster from the multiple grids; searching for adjacent grids from the grid set associated with each cell to obtain multiple grid pairs; determining multiple non-order grid pairs from the multiple grid pairs based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cells of the multiple grid pairs; and determining the location of the external interference source based on the variation amplitude of the RSRP and RSRQ of the serving cells of each non-order grid pair.

[0078] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0079] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for locating external interference, characterized in that, include: Obtain the operating parameter data of multiple cells in the target wireless network that are subject to external interference, and determine the interference type of the multiple cells subject to external interference; Based on the engineering parameter data and interference type of the multiple cells affected by external interference, the multiple cells affected by external interference are clustered to obtain multiple interference clusters. Each interference cluster includes N main cells, where N is a natural number greater than or equal to 1. Determine the defined area corresponding to each main cell of each interference cluster, divide the defined area into multiple grids, and determine the grid set associated with each main cell of each interference cluster from the multiple grids; Search for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs. Based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cell of the multiple grid pairs, determine multiple non-order grid pairs from the multiple grid pairs. The location of the external interference source is determined based on the variation magnitude of the RSRP and RSRQ of the serving cell for each non-order grid pair.

2. The external interference localization method according to claim 1, characterized in that, The step of searching for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs, and determining multiple non-order grid pairs from the multiple grid pairs based on the RSRP and RSRQ of the serving cells of the multiple grid pairs, includes: The first grid cell is determined from the grid set associated with each primary cell; From the set of grids associated with each primary cell, select the second grid that is closest to the first grid, wherein the serving cell RSRP of the second grid is greater than that of the first grid; Determine whether the RSRQ of the serving cell of the second grid is less than that of the serving cell of the first grid. If so, determine that the grid pair consisting of the first grid and the second grid is a non-order grid pair. Traverse all grids in the grid set associated with each primary cell and find all non-order grid pairs in the grid set associated with each primary cell.

3. The external interference localization method according to claim 1, characterized in that, The step of determining the delineated area corresponding to each primary cell of each interference cluster, dividing the delineated area into multiple grids, and determining the grid set associated with each primary cell of each interference cluster from the multiple grids includes: Taking each main cell of each interference cluster as the center and a preset threshold as the radius, the delineated area corresponding to each main cell of each interference cluster is determined; The defined area is divided into multiple grids; Obtain the location information of the multiple grids, as well as the radio parameters of the serving cells of the multiple grids; Based on the location information of the multiple grids, the multiple grids are filtered to obtain multiple grids within the defined area corresponding to each main cell; The radio parameters of the serving cells of multiple grids within the delineated area corresponding to each main cell are compared with the radio parameters of each main cell, and the set of grids associated with each main cell is determined from the multiple grids within the delineated area corresponding to each main cell.

4. The external interference localization method according to claim 1, characterized in that, The step of determining the location of the external interference source based on the variation magnitude of the RSRP and RSRQ of the serving cell for each non-order grid pair includes: Based on the improvement of the serving cell RSRP of each non-order grid pair and the degradation of the serving cell RSRQ of each non-order grid pair, the non-order grid pair with the greatest difference is determined from the plurality of non-order grid pairs. The location of the external interference source is determined based on the position information of the non-order grid pair with the greatest difference.

5. The external interference localization method according to claim 1, characterized in that, The process involves clustering the multiple cells affected by external interference based on their operational parameters and interference types to obtain multiple interference clusters, including: Based on the base stations and interference types corresponding to the multiple cells affected by external interference, the multiple cells affected by external interference are deduplicated to obtain multiple disturbed cells after deduplication. Based on the latitude, longitude, and operating frequency band of the deduplicated multiple disturbed cells, the deduplicated multiple disturbed cells are divided into multiple areas. Feature extraction is performed on the engineering parameter data and interference type of multiple disturbed cells in each area to obtain the feature data of multiple disturbed cells in each area; The feature data of multiple disturbed cells in each area are input into a deep neural network model to obtain the optimal K value of the predicted K-means clustering for each area output by the deep neural network model. Based on the optimal K value of the predicted K-means clustering for each region, multiple disturbed cells within each region are clustered to obtain multiple interference clusters and the Top N cells within each cluster.

6. The external interference localization method according to any one of claims 2-5, characterized in that, Before acquiring the power parameter data of multiple cells in the target wireless network that are subject to external interference, the method further includes: Acquire the operating parameter data of multiple cells of the target wireless network, as well as the Operation and Maintenance Center (OMC) data of the target wireless network; Extract frequency domain data of multiple cells of the target wireless network from the OMC data; Based on the engineering parameter data and frequency domain data of multiple cells in the target wireless network, the multiple cells in the target wireless network are filtered to identify multiple cells in the target wireless network that are subject to external interference.

7. An external interference positioning device, characterized in that, include: The first acquisition unit is used to acquire the operating parameter data of multiple cells in the target wireless network that are subject to external interference, and to determine the interference type of the multiple cells subject to external interference. The clustering unit is used to cluster the multiple cells affected by external interference according to their operating parameter data and interference type, to obtain multiple interference clusters. Each interference cluster includes N main cells, where N is a natural number greater than or equal to 1. The association unit is used to determine the delineated area corresponding to each main cell of each interference cluster, divide the delineated area into multiple grids, and determine the grid set associated with each cell of each interference cluster from the multiple grids. The determining unit is used to search for adjacent grids from the grid set associated with each primary cell to obtain multiple grid pairs, and to determine multiple non-order grid pairs from the multiple grid pairs based on the reference signal received power (RSRP) and reference signal received quality (RSRQ) of the serving cells of the multiple grid pairs. The positioning unit is used to determine the location of external interference sources based on the variation amplitude of RSRP and RSRQ of the serving cell for each non-order grid pair.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the external interference localization method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the external interference localization method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the external interference localization method as described in any one of claims 1 to 6.

Images