A method for identifying a foreign site address based on 5G MRO measurement

Abstract

The present application discloses a method, device, equipment and storage medium for identifying an off-site address based on 5G MRO measurement, which relates to the field of communication technologies. The method includes: obtaining measurement data of multiple off-site neighboring cells; performing density clustering on the measurement data of each off-site neighboring cell to obtain multiple clustering groups; for each clustering group, grouping according to the serving cell identifier, neighboring cell frequency point and neighboring cell identifier of the measurement data of each off-site neighboring cell to obtain multiple first subgroups; for each first subgroup, grouping the horizontal arrival angle and time advance of the off-site cell corresponding to the first subgroup according to a preset granularity to obtain multiple second subgroups; calculating the characteristic indexes of each second subgroup according to the measurement data of each off-site neighboring cell; inputting the characteristic indexes in each first subgroup into a preset classifier model to obtain the output serving network cell identifier, and taking the position corresponding to the serving network cell identifier as the predicted position of the off-site cell. The present application can realize the prediction of the position of the off-site site.

Description

Technical Field

[0001] The present application relates to the field of communication technologies, and in particular, to a method, apparatus, device, and storage medium for identifying different-site addresses based on 5G MRO measurement. Background Art

[0002] Improving the sharing efficiency of 5G network tower resources and quickly and accurately verifying the pricing system of shared towers is crucial for reducing operation and maintenance costs. Therefore, in the context of industry competition, accurately identifying the locations of different-vendor sites and accordingly carrying out network optimization and planning work is particularly urgent and important.

[0003] Currently, the identification for such scenarios mainly relies on manual grid-by-grid investigation, by reporting the location information of different-network base stations in each grid or analyzing based on tower cost audit data. However, the method of manual investigation not only has low efficiency, but also has difficulty in guaranteeing accuracy, and it is impossible to effectively identify the sites unique to different networks based on tower costs.

[0004] In summary, how to identify the locations of different-site addresses has become an urgent problem to be solved in this field.

[0005] The above content is only used to assist in understanding the technical solution of the present application, and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main purpose of the present application is to provide a method, apparatus, device, and storage medium for identifying different-site addresses based on 5G MRO (Measurement Report Data) measurement, aiming to solve the technical problem of how to identify the locations of different-site addresses.

[0007] To achieve the above object, the present application proposes a method for identifying different-site addresses based on 5G MRO measurement, and the method includes:

[0008] Obtain multiple different-network neighbor cell measurement data;

[0009] Perform density clustering on each of the different-network neighbor cell measurement data according to the different-network parameters of each of the different-network neighbor cell measurement data to obtain multiple clustering groups;

[0010] For each clustering group, group each of the different-network neighbor cell measurement data according to the serving cell identifier, neighbor cell frequency point, and neighbor cell identifier of each of the different-network neighbor cell measurement data to obtain multiple first subgroups;

[0011] For each of the first subgroups, group the horizontal arrival angle and time advance of the different-network cell corresponding to the first subgroup according to a preset granularity to obtain multiple second subgroups;

[0012] Calculate the characteristic indicators of each of the second groups respectively according to the measured data of each of the off-net neighboring cells;

[0013] For each of the first groups, input the characteristic indicators in the first group into a preset classifier model to obtain the output serving cell identifier of the local network, and use the position corresponding to the serving cell identifier of the local network as the predicted position of the off-net cell.

[0014] In one embodiment, before the step of inputting the characteristic indicators in the first group into a preset classifier model, the method further includes:

[0015] Obtain a plurality of measured data of neighboring cells in the local network;

[0016] Group the measured data of each of the neighboring cells in the local network according to the serving cell identifier, neighboring cell frequency point, and neighboring cell identifier of each of the measured data of the neighboring cells in the local network to obtain a plurality of local network groups;

[0017] For each of the local network groups, slice the horizontal arrival angle and time advance of the area of the serving cell corresponding to the local network group according to a preset granularity to obtain each area slice;

[0018] Calculate the characteristic indicators of each of the area slices according to the measured data of each of the neighboring cells in the local network;

[0019] Statistically calculate the characteristic indicators of each of the area slices within a preset time according to a preset time granularity to obtain a plurality of slice feature sets;

[0020] Train a classifier with each of the serving cell identifiers as a unit, and use each of the slice feature sets corresponding to each of the serving cell identifiers as samples to train the preset classifier model to obtain a trained classifier model.

[0021] In one embodiment, the step of obtaining a plurality of measured data of off-net neighboring cells includes:

[0022] Collect measured data of off-net neighboring cells at a plurality of preset sampling points;

[0023] If there are abnormal sampling points with missing measured data of off-net neighboring cells among the sampling points, calculate the measured data of off-net neighboring cells of the abnormal sampling point according to the measured data of off-net neighboring cells of the sampling points adjacent to the abnormal sampling point to supplement each of the measured data of off-net neighboring cells.

[0024] In one embodiment, the step of grouping the horizontal arrival angle and time advance of the off-net cell corresponding to the first group according to a preset granularity includes:

[0025] Determine the grouping granularity of the horizontal arrival angle and time advance respectively according to the preset granularity;

[0026] Group the off-net cells corresponding to the first subgroup according to the described grouping granularity.

[0027] In one embodiment, the step of calculating the characteristic indicators of each of the second subgroups according to the off-net neighbor cell measurement data respectively includes:

[0028] Determine the second subgroup to which each of the off-net neighbor cell measurement data belongs according to the horizontal arrival angle and time advance in each of the off-net neighbor cell measurement data;

[0029] For each second subgroup, calculate the characteristic indicator of the second subgroup according to the off-net neighbor cell measurement data corresponding to the second subgroup.

[0030] In one embodiment, after the step of taking the position corresponding to the home network cell identifier as the predicted position of the off-net cell, the method further includes:

[0031] For each clustering group, determine the predicted positions corresponding to the first subgroups in the clustering group;

[0032] Perform weighted averaging on the predicted positions to obtain the final predicted position.

[0033] In one embodiment, the step of grouping the home network neighbor cell measurement data according to the serving cell identifier, neighbor cell frequency point, and neighbor cell identifier of each of the home network neighbor cell measurement data includes:

[0034] Group the home network neighbor cell measurement data according to the serving cell identifier of each of the home network neighbor cell measurement data to obtain a plurality of first home network subgroups;

[0035] For each first home network subgroup, group the home network neighbor cell measurement data according to the neighbor cell frequency point and neighbor cell identifier of each of the home network neighbor cell measurement data.

[0036] In addition, to achieve the above object, the present application further provides an electronic device, the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program is configured to implement the steps of the off-net site identification method based on 5G MRO measurement as described above.

[0037] In addition, to achieve the above object, the present application further provides a storage medium, the storage medium is a computer-readable storage medium, a computer program is stored on the storage medium, and when the computer program is executed by a processor, it implements the steps of the off-net site identification method based on 5G MRO measurement as described above.

[0038] In addition, to achieve the above object, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the above-mentioned off-site address identification method based on 5G MRO measurement.

[0039] The present application provides an off-site address identification method based on 5G MRO measurement. First, the present application collects measurement data of multiple off-site neighboring cells, then clusters the measurement data of each off-site neighboring cell according to off-site parameters, and clusters the data that may belong to the same cell into a clustering group. Then, for each clustering group, the measurement data of the off-site neighboring cell is grouped again according to the serving cell identifier, neighboring cell frequency point, and neighboring cell identifier to obtain multiple first subgroups. Then, for each off-site cell corresponding to each first subgroup, it is divided into multiple second subgroups according to the horizontal arrival angle and time advance. The characteristic indicators of each second subgroup can be calculated based on the measurement data of each off-site neighboring cell. Finally, by inputting the characteristic indicators into a preset classifier model, the serving cell identifier corresponding to the off-site cell can be obtained, and the position corresponding to the serving cell identifier can be used as the predicted position of the off-site cell.

[0040] In summary, the present application uses 5G off-site neighboring cell measurement data, subdivides the measurement data of off-site neighboring cells, uses a serving cell classifier model of the serving network to group neighboring cells in the same location, then obtains the characteristic indicators of each subgroup, and identifies the serving cell similar to the off-site cell through the classifier model. According to the position of the serving cell, the position of the off-site cell can be predicted, and the prediction of the off-site site position can be realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0042] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic flowchart provided for Embodiment 1 of the off-site address identification method based on 5G MRO measurement of the present application;

[0044] Figure 2 It is the overall implementation flowchart involved in the embodiment of the off-site address identification method based on 5G MRO measurement of the present application;

[0045] Figure 3 It is the schematic flowchart of the positioning process involved in the embodiment of the off-site address identification method based on 5G MRO measurement of the present application;

[0046] Figure 4 This is a schematic diagram of the area slice involved in the embodiment of the method for identifying different network site addresses based on 5G MRO measurement in this application;

[0047] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the method for identifying different network site addresses based on 5G MRO measurement in the embodiment of this application.

[0048] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments with reference to the accompanying drawings. Detailed implementation manners

[0049] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not used to limit this application.

[0050] In order to better understand the technical solutions of this application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0051] The main solution of the embodiment of this application is: obtaining measurement data of multiple different network neighboring cells; performing density clustering on each of the measurement data of the different network neighboring cells according to the different network parameters of each of the measurement data of the different network neighboring cells to obtain multiple clustering groups; for each clustering group, grouping each of the measurement data of the different network neighboring cells according to the serving cell identifier, neighboring cell frequency point and neighboring cell identifier of each of the measurement data of the different network neighboring cells to obtain multiple first subgroups; for each of the first subgroups, grouping the horizontal arrival angle and time advance of the different network cells corresponding to the first subgroup according to a preset granularity to obtain multiple second subgroups; calculating the characteristic indexes of each of the second subgroups according to each of the measurement data of the different network neighboring cells; for each of the first subgroups, inputting each of the characteristic indexes in the first subgroup into a preset classifier model to obtain the output serving network cell identifier, and taking the position corresponding to the serving network cell identifier as the predicted position of the different network cell.

[0052] In this embodiment, for the convenience of description, the following will be described with an electronic device as the execution subject.

[0053] Improving the sharing efficiency of 5G network tower resources and quickly and accurately verifying the pricing system of shared towers is crucial for reducing operation and maintenance costs. Therefore, in the context of industry competition, accurately identifying the locations of different manufacturer sites and accordingly carrying out network optimization and planning work is particularly urgent and important.

[0054] Currently, the identification of such scenarios mainly relies on manual grid-based inspections. By reporting the location information of off-net base stations within each grid or analyzing data based on tower cost audits. However, the method of manual inspection not only has low efficiency but also has difficulty in ensuring accuracy, and it is impossible to effectively identify off-net unique sites based on tower costs.

[0055] In summary, how to identify the location of off-net sites has become an urgent problem in this field.

[0056] To address the above problems, the present application provides a method for identifying off-net site addresses based on 5G MRO measurements. The present application first collects measurement data of multiple off-net neighboring cells, then clusters the measurement data of each off-net neighboring cell according to off-net parameters, clustering the data that may belong to the same cell into a clustering group. Then, for each clustering group, the measurement data of off-net neighboring cells is grouped again according to the serving cell identifier, neighboring cell frequency point, and neighboring cell identifier, obtaining multiple first subgroups. Then, for each off-net cell corresponding to each first subgroup, it is divided into multiple second subgroups according to the horizontal arrival angle and time advance. The characteristic indicators of each second subgroup can be calculated based on the measurement data of each off-net neighboring cell. Finally, by inputting the characteristic indicators into a preset classifier model, the serving cell identifier corresponding to the off-net cell can be obtained, and the location corresponding to the serving cell identifier can be used as the predicted location of the off-net cell.

[0057] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of implementing the above functions. Hereinafter, an electronic device will be used as an example to illustrate this embodiment and the following embodiments.

[0058] Based on this, the embodiments of the present application provide a method for identifying off-net site addresses based on 5G MRO measurements, referring to Figure 1 , Figure 1 is a schematic flowchart of the first embodiment of the method for identifying off-net site addresses based on 5G MRO measurements of the present application.

[0059] In this embodiment, the method for identifying off-net site addresses based on 5G MRO measurements includes steps S10 to S50:

[0060] Step S10, obtain measurement data of multiple off-net neighboring cells;

[0061] In this embodiment, the device collects measurement data of off-net neighboring cells at multiple sampling points, and these data contain various parameters of different off-net cells.

[0062] Further, in a feasible implementation manner, the above step S10 may further include steps S11 to S12:

[0063] Step S11, collect inter-network neighbor cell measurement data at multiple preset sampling points;

[0064] In this embodiment, the device collects inter-network neighbor cell measurement data at multiple preset sampling points.

[0065] Step S12, if there are abnormal sampling points with missing inter-network neighbor cell measurement data among the sampling points, calculate the inter-network neighbor cell measurement data of the abnormal sampling points according to the inter-network neighbor cell measurement data of the sampling points adjacent to the abnormal sampling points, so as to complete the inter-network neighbor cell measurement data.

[0066] In this embodiment, during the collection process, the inter-network neighbor cell measurement data of some sampling points may be missing due to various reasons (such as equipment failure, signal interference, etc.). At this time, the device will calculate and complete the data of the abnormal sampling points according to the data of other sampling points adjacent to the abnormal sampling points through interpolation, fitting or other mathematical methods.

[0067] The data completion step ensures the integrity and continuity of the data, and avoids analysis errors caused by data missing. By using the data of adjacent sampling points to complete the missing data, the authenticity and accuracy of the data can be maintained to the greatest extent.

[0068] Step S20, perform density clustering on the inter-network neighbor cell measurement data according to the inter-network parameters of the inter-network neighbor cell measurement data to obtain multiple clustering groups;

[0069] In this embodiment, the device uses the density clustering algorithm to process the inter-network neighbor cell measurement data, and divides the data into multiple clustering groups according to the similarity of the inter-network parameters (such as signal strength, frequency, etc.).

[0070] Specifically, obtain the inter-network neighbor cell measurement data of 5GMR sampling points, perform location density clustering according to the main serving cell NCI (NR Cell Identifier, 5G network cell identifier), longitude, latitude, neighbor cell frequency point, and neighbor cell PCI (Physical Cell Identifier), and obtain multiple ncNci and MR.NRNcArfcn (NRAbsolute Radio Frequency Channel Number, 5G absolute radio frequency channel number) clustering groups. Among them, the longitude and latitude can be the site longitude and latitude of the serving cell of this network, or the MDT (Minimization Drive Test) longitude and latitude in the MR. The measurement results of the same frequency and the same PCI clustered together can be considered as the same inter-network 5G cell.

[0071] Step S30: For each clustering group, group the heterogeneous network neighbor cell measurement data according to the serving cell identifier, neighbor cell frequency point, and neighbor cell identifier of each piece of the heterogeneous network neighbor cell measurement data, to obtain a plurality of first subgroups.

[0072] In this embodiment, within each clustering group, the device further subdivides the measurement data according to parameters such as the serving cell identifier, neighbor cell frequency point, and neighbor cell identifier, to form a plurality of first subgroups.

[0073] Specifically, for each clustering group, perform a grouping according to the serving cell NCI, neighbor cell frequency point, and neighbor cell PCI once.

[0074] Step S40: For each of the first subgroups, group the horizontal arrival angle and time advance of the heterogeneous network cells corresponding to the first subgroup according to a preset granularity, to obtain a plurality of second subgroups.

[0075] In this embodiment, within each first subgroup, the device further groups the data according to parameters such as the horizontal arrival angle and time advance according to a preset granularity (such as an angle range, a time interval, etc.), to form a plurality of second subgroups.

[0076] Further, in a feasible implementation manner, the above step S40 includes steps S41 to S42:

[0077] Step S41: Determine the grouping granularities of the horizontal arrival angle and time advance respectively according to the preset granularity.

[0078] In this embodiment, before grouping, the device first presets the grouping granularities of the horizontal arrival angle (such as an angle range, an angle interval, etc.) and time advance (such as a time interval, a time unit, etc.) according to actual requirements and analysis objectives. These granularities determine the division accuracy and detail degree of the data during subsequent grouping.

[0079] Step S42: Group the heterogeneous network cells corresponding to the first subgroup according to the grouping granularities.

[0080] In this embodiment, after determining the grouping granularities, the device groups the heterogeneous network cells within the first subgroup according to these granularities.

[0081] Step S50: Calculate the characteristic indicators of each of the second subgroups according to each piece of the heterogeneous network neighbor cell measurement data.

[0082] In this embodiment, the device calculates the characteristic indicators according to the heterogeneous network neighbor cell measurement data within each second subgroup.

[0083] Further, in a feasible implementation manner, the above step S50 may further include steps S51 to S52:

[0084] Step S51: Determine the second group to which each piece of the off-network neighbor cell measurement data belongs according to the horizontal angle of arrival and timing advance in each piece of the off-network neighbor cell measurement data;

[0085] In this embodiment, after determining the grouping granularity and completing the grouping operation, the device will, according to the horizontal angle of arrival and timing advance in each piece of the off-network neighbor cell measurement data, assign it to the corresponding second group.

[0086] Step S52: For each second group, calculate the characteristic index of the second group according to the off-network neighbor cell measurement data corresponding to the second group.

[0087] In this embodiment, after determining the belonging group of each piece of the off-network neighbor cell measurement data, the device will calculate the characteristic index for each second group according to the off-network neighbor cell measurement data corresponding to it.

[0088] Specifically, for the data of one grouping, the values of the serving cell MR.hAOA (Azimuth of Arrival, horizontal angle of arrival) and MR.NRScTadv (Timing Advance, the time advance between the sampling point and the serving cell) are grouped and statistically analyzed in a secondary manner according to a certain granularity. For example, MR.hAOA can be evenly divided into 18 parts according to a size of 10 degrees, and the MR.NRScTadv value is grouped according to a step size of 2. Then, calculate the characteristic indexes of each secondary grouping, including: scNci, ncNci, MR.NRNcArfcn, MR.NRNcPci, MR.hAOA segment identifier, MR.NRScTadv segment identifier, number of sampling points, average value of MR.NRScSSRSRP (Reference Signal Receiving Power), average value of MR.NRNcSSRSRP, co-correlation coefficient of MR.NRScSSRSRP and MR.NRNcSSRSRP, overlapping coverage (MR.NRNcSSRSRP - MR.NRScSSRSRP >= -6dB) coefficient, standard deviation of the field strength difference (MR.NRNcSSRSRP - MR.NRScSSRSRP).

[0089] Step S60: For each of the first groups, input the characteristic indexes in the first group into a preset classifier model to obtain the output serving cell identifier, and use the position corresponding to the serving cell identifier as the predicted position of the off-network cell.

[0090] In this embodiment, the device inputs the characteristic indexes in each first group into a pre-trained classifier model, and the model outputs the corresponding serving cell identifier according to the characteristic indexes. The device searches for the corresponding position according to the serving cell identifier as the predicted position of the off-network cell.

[0091] In the overall solution, please refer to Figure 2 , Figure 2 which is the overall implementation flowchart involved in the embodiment of the method for identifying different network site addresses based on 5G MRO measurement in this application. As Figure 2 shown, when locating different network neighboring cells, first calculate the slice wide table indicators of the 5G neighboring cells of the local network, then build a classification model for the 5G neighboring cells of the local network to obtain a 5G neighboring cell classifier model, then perform DBSCAN clustering on the 5G different network neighboring cells, then calculate the slice wide table indicators of the 5G different network neighboring cells, and then classify the different network 5G neighboring cells through the 5G neighboring cell classifier model, and finally output the location of the different network neighboring cells.

[0092] Specifically, please refer to Figure 3 , Figure 3 which is the schematic diagram of the location process involved in the embodiment of the method for identifying different network site addresses based on 5G MRO measurement in this application. As Figure 3 shown, load a set of data with the same scNci, ncEarfcn (E-UTRA Absolute Radio Frequency Channel Number, 4G absolute radio frequency channel number), and ncPci into the scNci classifier model, use the model to classify the data, and obtain a classification result. If the classification result is valid, it is determined that the classification result is the ECI of the local network cell that is closest to the characteristics of the current different network cell, and the location where the ECI of the local network cell is located can be used as the predicted location of the different network cell. If the classification result is invalid, the model needs to be retrained or more data needs to be obtained.

[0093] Further, after the above step S60, the method may further include steps S70 to S80:

[0094] Step S70, for each clustering group, determine the predicted location corresponding to each of the first subgroups in the clustering group;

[0095] In this embodiment, for each clustering group, it is necessary to determine the predicted location corresponding to each of the first subgroups (these first subgroups are initially grouped according to the measurement data of different network neighboring cells).

[0096] Step S80, perform weighted averaging on each of the predicted locations to obtain a final predicted location.

[0097] In this embodiment, after determining the predicted locations of the first subgroups in each clustering group, we use the method of weighted averaging to calculate the final predicted location. The weights for weighted averaging can be determined according to the data quality, reliability, quantity, or other relevant factors of each first subgroup within the clustering group. In this way, we can comprehensively consider the information of all first subgroups within the clustering group to obtain a more accurate and reliable final predicted location.

[0098] Specifically, the predicted positions of multiple scNcis in the clustering group for off-net neighboring cells are weighted and averaged to obtain the positions corresponding to MR.NRNcArfcn and MR.NRNcPci. First, determine the weight assignment method for weighted averaging. The weights can be determined according to the reliability, accuracy, or other relevant factors of each scNci. Based on the results of multiple predictions, the off-net positions with higher accuracy can be given greater weights. Then, multiply the predicted position of each scNci by its corresponding weight. Next, sum up all the weighted predicted positions. Finally, divide the sum by the sum of all weights to obtain the weighted average position, that is, the positions corresponding to MR.NRNcArfcn and MR.NRNcPci. Through this method of weighted averaging, the prediction results of multiple scNcis can be integrated, improving the accuracy and reliability of the position, and providing more accurate data support for subsequent network analysis and optimization.

[0099] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar content as in the above-mentioned embodiment one can be referred to the above introduction and will not be repeated hereinafter. On this basis, before the above step S60, the method further includes steps A10 to A60:

[0100] Step A10, obtain multiple in-network neighboring cell measurement data;

[0101] In this embodiment, the device collects multiple in-network neighboring cell measurement data.

[0102] Step A20, group each of the in-network neighboring cell measurement data according to the serving cell identifier, neighboring cell frequency point, and neighboring cell identifier of each of the in-network neighboring cell measurement data to obtain multiple in-network groups;

[0103] In this embodiment, the device groups the in-network neighboring cell measurement data according to parameters such as the serving cell identifier, neighboring cell frequency point, and neighboring cell identifier to form multiple in-network groups. The data within each in-network group has high similarity and relevance.

[0104] Specifically, obtain the in-network neighboring cell measurement data of 5G MR sampling points, and perform a first grouping according to the serving cell NCI, MR.NRNcArfcn, and MR.NRNcPci.

[0105] Group according to the NCI of the serving cell (PC). All MR data of each cell will be classified into its corresponding NCI group.

[0106] Within each NCI group, further secondary grouping is performed according to the frequency of neighboring cells (MR.NRNcArfcn) and the physical cell identifier (MR.NRNcPci) to obtain multiple local network groups. In this way, the MR data of each cell will be subdivided into more specific groups according to the different characteristics of its neighboring cells.

[0107] Step A30, for each of the local network groups, slice the horizontal arrival angle and time advance of the area of the serving cell corresponding to the local network group according to a preset granularity to obtain each area slice;

[0108] In this embodiment, within each local network group, the device slices the area of the serving cell according to parameters such as the horizontal arrival angle and time advance according to a preset granularity (such as angle range, time interval, etc.) to form multiple area slices.

[0109] Step A40, calculate the characteristic indicators of each area slice according to each of the local network neighboring cell measurement data;

[0110] In this embodiment, the device calculates the characteristic indicators according to the local network neighboring cell measurement data within each area slice.

[0111] Specifically, for the data of the first grouping, slice the MR.hAOA and MR.NRScTadv values according to a certain granularity, and then calculate the characteristic indicators of each slice, including: scNci, ncNci, MR.NRNcArfcn, MR.NRNcPci, MR.hAOA segmentation identifier, MR.NRScTadv segmentation identifier, number of sampling points, mean value of MR.NRScSSRSRP, mean value of MR.NRNcSSRSRP, covariance coefficient of MR.NRScSSRSRP and MR.NRNcSSRSRP, overlapping coverage (MR.NRNcSSRSRP - MR.NRScSSRSRP >= -6dB) coefficient, standard deviation of field strength difference (MR.NRNcSSRSRP - MR.NRScSSRSRP), etc. For example, please refer to Figure 4 , Figure 4 is a schematic diagram of the area slice involved in the embodiment of the method for identifying a foreign site based on 5G MRO measurement in this application. As Figure 4 shown, haoa can be divided into 6 equal parts with a size of 30 degrees, and the TA value is grouped according to a step size of 1. The coverage area of the serving cell can be divided into multiple slices, where the shaded area is the TA range [1, 2) and the AOA segmentation identifier range [4, 5).

[0112] Step A50, respectively count the characteristic indicators of each area slice within a preset time according to a preset time granularity to obtain multiple slice feature sets;

[0113] In this embodiment, the device statistically calculates the characteristic indicators of each regional slice within a preset time according to a preset time granularity (such as hours, days, etc.), and forms a plurality of slice feature sets. Each slice feature set contains the statistical information of the characteristic indicators of the regional slice within a period of time.

[0114] Step A60: Train a classifier with each of the master serving cell identifiers as a unit, and use each of the slice feature sets corresponding to each of the master serving cell identifiers as samples to train a preset classifier model to obtain a trained classifier model.

[0115] In this embodiment, the device uses each master serving cell identifier as a unit, takes the corresponding slice feature set as a sample, and trains a preset classifier model. The trained classifier model can predict the corresponding home network cell identifier according to the input characteristic indicators.

[0116] Specifically, the index statistics of the regional slices are performed according to a certain time granularity (such as 1 hour), and the data for N (>=7) consecutive days are continuously statistically calculated to construct a slice feature set, which includes fields: time, scNci, ncNci, MR.NRNcArfcn, MR.NRNcPci, MR.hAOA segmentation identifier, MR.NRScTadv segmentation identifier, number of sampling points, mean value of MR.NRScSSRSRP, mean value of MR.NRNcSSRSRP, covariance coefficient of MR.NRScSSRSRP and MR.NRNcSSRSRP, overlapping coverage (MR.NRNcSSRSRP - MR.NRScSSRSRP >= -6dB) coefficient, standard deviation of field strength difference (MR.NRNcSSRSRP - MR.NRScSSRSRP). Train a classifier with the master serving cell scNci as a unit, obtain the secondary grouping data with the same scNci, and train a classifier model for ncEci.

[0117] It should be noted that the above examples are only for understanding this application and do not constitute a limitation to the method for identifying off - site addresses based on 5G MRO measurement in this application. Based on this technical concept, more forms of simple transformations are within the protection scope of this application.

[0118] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor can execute the method for identifying off - site addresses based on 5G MRO measurement in the first embodiment above.

[0119] Next, refer to Figure 5, which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description: tablet computers), PMPs (Portable Media Player), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The illustrated electronic device is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0120] As Figure 5 shown, the electronic device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems may be implemented or had.

[0121] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0122] The electronic device provided by the present application adopts the method for identifying a foreign site address based on 5G MRO measurement in the above embodiments, and can solve the technical problem of how to identify the location of a foreign site. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as those of the method for identifying a foreign site address based on 5G MRO measurement provided in the above embodiments, and other technical features in the electronic device are the same as those disclosed in the method of the previous embodiment, which will not be elaborated herein.

[0123] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0124] As described above, only the specific implementation manners of the present application are provided, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0125] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the method for identifying a foreign site address based on 5G MRO measurement in the above embodiments.

[0126] The computer-readable storage medium provided by the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium can be transmitted by any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0127] The above computer-readable storage medium may be included in an electronic device; or it may exist separately without being assembled into the electronic device.

[0128] The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by an electronic device, the electronic device is caused to: obtain a plurality of off-network neighbor cell measurement data; perform density clustering on each of the off-network neighbor cell measurement data according to the off-network parameters of each of the off-network neighbor cell measurement data to obtain a plurality of clustering groups; for each clustering group, group each of the off-network neighbor cell measurement data according to the serving cell identifier, neighbor cell frequency point, and neighbor cell identifier of each of the off-network neighbor cell measurement data to obtain a plurality of first subgroups; for each of the first subgroups, group the horizontal arrival angle and time advance of the off-network cell corresponding to the first subgroup according to a preset granularity to obtain a plurality of second subgroups; calculate the characteristic indicators of each of the second subgroups according to each of the off-network neighbor cell measurement data; for each of the first subgroups, input the characteristic indicators in the first subgroup into a preset classifier model to obtain the output serving network cell identifier, and use the position corresponding to the serving network cell identifier as the predicted position of the off-network cell.

[0129] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN: Local Area Network) or a wide area network (WAN: Wide Area Network), or it can be connected to an external computer (for example, by connecting through an Internet service provider using the Internet).

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0131] The modules involved in the embodiments described in this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0132] The readable storage medium provided in this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned method for identifying an off-site address based on 5G MRO measurements, and can solve the technical problem of how to identify the location of an off-site site. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the method for identifying an off-site address based on 5G MRO measurements provided in the above embodiments, and will not be elaborated here.

[0133] The present application also provides a computer program product, including a computer program, which when executed by a processor implements the steps of the above-mentioned method for identifying a foreign site address based on 5G MRO measurement.

[0134] The computer program product provided by the present application can solve the technical problem of how to identify the location of a foreign site. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the method for identifying a foreign site address based on 5G MRO measurement provided in the above embodiments, and will not be elaborated here.

[0135] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A method for identifying foreign website URLs based on 5GMRO measurement, characterized in that: The method comprises: Obtain multiple neighboring cell measurement data from different networks; Density clustering is performed on each of the heterogeneous network neighboring area measurement data according to the heterogeneous network parameters of each of the heterogeneous network neighboring area measurement data to obtain a plurality of cluster groups; For each cluster group, grouping each of the heterogeneous network neighboring cell measurement data according to the primary service cell identifier, the neighboring cell frequency point and the neighboring cell identifier of each heterogeneous network neighboring cell measurement data to obtain a plurality of first subgroups; For each of the first groups, the horizontal arrival angles and time advances of the foreign network cells corresponding to the first group are grouped according to a preset granularity to obtain a plurality of second groups; Calculate the characteristic index of each of the second groups respectively according to the measurement data of each of the neighboring cells of the different networks; For each of the first groups, each of the characteristic indicators in the first group is input into a preset classifier model to obtain an output local cell identifier, and a position corresponding to the local cell identifier is used as the predicted position of the foreign cell, wherein the classifier model is obtained by training a sample using a primary service cell identifier in the local neighboring area measurement data as a unit and a slice feature set corresponding to each primary service cell identifier in the local neighboring area measurement data; Among them, the slice feature set is: the horizontal arrival angle and time advance of the area of ​​the main service cell corresponding to the group of this network of the neighboring area measurement data of this network are regionally sliced ​​according to a preset granularity to obtain each regional slice, and the characteristic indicators of each regional slice within a preset time are respectively counted according to the preset time granularity.

2. The method for identifying foreign website addresses based on 5GMRO measurement according to claim 1, characterized in that: Before the step of inputting each of the feature indicators in the first group into a preset classifier model, the method further includes: Obtain multiple neighboring area measurement data of the network; Grouping each of the local network neighboring cell measurement data according to the primary service cell identifier, neighboring cell frequency point and neighboring cell identifier of each of the local network neighboring cell measurement data to obtain a plurality of local network groups; For each of the local network groups, the horizontal arrival angle and the time advance of the area of ​​the primary service cell corresponding to the local network group are regionally sliced ​​according to a preset granularity to obtain regional slices; Calculate the characteristic index of each of the regional slices according to the measurement data of the neighboring areas of each network; According to a preset time granularity, the characteristic index of each of the regional slices within a preset time is counted to obtain a plurality of slice feature sets; The classifier is trained with each of the primary serving cell identifiers as a unit, and each of the slice feature sets corresponding to each of the primary serving cell identifiers is used as a sample, and a preset classifier model is trained to obtain a trained classifier model.

3. The method for identifying foreign website addresses based on 5GMRO measurement according to claim 1, characterized in that: The step of obtaining multiple heterogeneous network neighboring area measurement data comprises: Collecting measurement data of neighboring cells of different networks at multiple preset sampling points; If there is an abnormal sampling point among the sampling points where the measurement data of the neighboring areas of different networks is missing, the measurement data of the neighboring areas of different networks of the sampling points adjacent to the abnormal sampling point are calculated to complete the measurement data of the neighboring areas of different networks.

4. The method for identifying foreign website addresses based on 5GMRO measurement according to claim 1, characterized in that: The step of grouping the horizontal arrival angles and time advances of the foreign network cells corresponding to the first group according to a preset granularity includes: Determine the grouping granularity of the horizontal arrival angle and the timing advance amount respectively according to a preset granularity; The foreign network cells corresponding to the first group are grouped according to the grouping granularity.

5. The method for identifying foreign website addresses based on 5GMRO measurement according to claim 1, characterized in that: The step of respectively calculating the characteristic index of each of the second subgroups according to the measurement data of each of the neighboring cells of the different networks comprises: Determine the second group to which each of the heterogeneous network neighboring cell measurement data belongs according to the horizontal arrival angle and the time advance in each of the heterogeneous network neighboring cell measurement data; For each second group, a characteristic index of the second group is calculated according to the measurement data of the neighboring area of ​​the different network corresponding to the second group.

6. The method for identifying foreign website addresses measured by 5GMRO as claimed in claim 1, characterized in that: After the step of using the position corresponding to the own network cell identifier as the predicted position of the foreign network cell, the method further includes: For each cluster group, determining the predicted position corresponding to each of the first subgroups in the cluster group; The weighted average of the predicted positions is performed to obtain the final predicted position.

7. The method for identifying foreign website addresses based on 5GMRO measurement according to claim 2, characterized in that: The step of grouping each of the local network neighboring cell measurement data according to the primary serving cell identifier, neighboring cell frequency point and neighboring cell identifier of each of the local network neighboring cell measurement data comprises: Grouping each of the local network neighboring area measurement data according to the primary serving cell identifier of each of the local network neighboring area measurement data to obtain a plurality of first local network groups; For each first local network group, each local network neighboring cell measurement data is grouped according to the neighboring cell frequency point and the neighboring cell identifier of each local network neighboring cell measurement data.

Images