A method, device and electronic device for evaluating regional coverage

Abstract

The present invention provides a method, device and electronic device for evaluating regional coverage, which relates to the field of communication technology and solves the problem of how operators evaluate the coverage effectiveness of each cell in the network. The method comprises: obtaining evaluation data of the area to be evaluated; wherein the evaluation data at least includes site data, statistical data, network data and drive test data; determining the evaluation result of the area to be evaluated according to a pre-stored evaluation model and evaluation data; wherein the evaluation model includes the corresponding relationship between the evaluation data and the evaluation result.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method, device and electronic equipment for evaluating regional coverage. Background Art

[0002] With the construction, optimization and adjustment, antenna aging, changes in the surrounding environment of the base station or the influence of new base stations, the coverage effectiveness of the cell becomes worse, for example, the signal quality of the cell is poor, the actual coverage area of ​​the cell is much smaller than the preset coverage area, or the actual coverage area of ​​the cell is much larger than the preset coverage area. The cell with poor coverage effectiveness will affect the use of the network by the user equipment (UE).

[0003] Therefore, how operators evaluate the coverage effectiveness of each cell in the network has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a method, device and electronic equipment for evaluating regional coverage, which solves the problem of how operators evaluate the coverage effectiveness of each cell in a network.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] In a first aspect, an embodiment of the present invention provides an area coverage assessment method, comprising: obtaining assessment data of an area to be assessed; wherein the assessment data at least includes site data, statistical data, network data and road test data; determining an assessment result of the area to be assessed based on a pre-stored assessment model and assessment data; wherein the assessment model includes a corresponding relationship between the assessment data and the assessment result.

[0007] As can be seen from the above, the regional coverage evaluation method provided by the present invention pre-stores an evaluation model including the corresponding relationship between evaluation data and evaluation results, so that when the operation and maintenance personnel evaluate the area to be evaluated, after obtaining the evaluation data of the area to be evaluated, they can determine the evaluation result of the area to be evaluated according to the pre-stored evaluation model and evaluation data. This makes it convenient for the operation and maintenance personnel to evaluate the regional coverage of the area to be evaluated, thus solving the problem of how operators evaluate the coverage effectiveness of each cell in the network.

[0008] In an achievable manner, the site data at least includes: site type and site level; the statistical data at least includes key performance indicator KPI statistical information and measurement report MR statistical information, the KPI statistical information at least includes the average daytime cell availability, the average daytime target system reverse flow ratio, the average daytime single-cell air interface service flow, the daytime downlink physical resource block PRB average utilization rate, the nighttime cell average availability, the nighttime target system reverse flow ratio, the nighttime single-cell average air interface service flow and the nighttime downlink physical resource block PRB average utilization rate, the MR statistical information at least includes the first sampling point ratio of the reference signal received power RSRP of the sampling points of the daytime target cell greater than or equal to the preset threshold and the second sampling point ratio of the RSRP of the sampling points of the nighttime target cell greater than or equal to the preset threshold, the network data at least includes the total number of base stations, the total number of macro cells, and the total number of indoor cells contained in the area to be evaluated. The total number and the distance between at least one base station and the center point of the area to be evaluated, the drive test data at least includes the total number of the first grid corresponding to the area to be evaluated, the total number of the second grid with data transmission corresponding to the area to be evaluated, the first ratio of the total number of the second grid to the total number of the first grid, the total number of the third grid with data transmission corresponding to the area to be evaluated and the total number of the third grid, the total number of the fourth grid with no data transmission corresponding to the area to be evaluated, the third ratio of the total number of the fourth grid to the total number of the first grid, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, the total number of the fifth grid with RSRP collected by the sampling points in the grid corresponding to the area to be evaluated greater than or equal to the target threshold, the fourth ratio of the total number of the fifth grid to the total number of the first grid, and the fifth ratio of the total number of the fifth grid to the total number of the second grid.

[0009] In one achievable manner, before obtaining the evaluation data of the area to be evaluated, the area coverage evaluation method provided by an embodiment of the present invention also includes: obtaining training sample data and evaluation results of the training sample data; wherein the training sample data at least includes sample site data, sample statistical data, sample network data and sample road test data; inputting the training sample data into a gradient boosting decision tree GBDT model; based on the model evaluation indicator AUC, determining whether the predicted comparison result of the training sample data output by the GBDT model matches the evaluation result; when the predicted comparison result does not match the evaluation result, repeatedly and cyclically updating the training sample data until the score corresponding to the AUC is greater than the score threshold, determining that the GBDT model has converged to obtain an evaluation model.

[0010] In a second aspect, the present invention provides an area coverage assessment device, comprising: an acquisition unit and a processing unit.

[0011] An acquisition unit is used to acquire evaluation data of the area to be evaluated; wherein the evaluation data at least includes site data, statistical data, network data and road test data; a processing unit is used to determine the evaluation result of the area to be evaluated based on a pre-stored evaluation model and the evaluation data acquired by the acquisition unit; wherein the evaluation model includes a corresponding relationship between the evaluation data and the evaluation result.

[0012] In an achievable manner, the site data at least includes: site type and site level; the statistical data at least includes key performance indicator KPI statistical information and measurement report MR statistical information, the KPI statistical information at least includes the average daytime cell availability, the average daytime target system reverse flow ratio, the average daytime single-cell air interface service flow, the daytime downlink physical resource block PRB average utilization rate, the nighttime cell average availability, the nighttime target system reverse flow ratio, the nighttime single-cell average air interface service flow and the nighttime downlink physical resource block PRB average utilization rate, the MR statistical information at least includes the first sampling point ratio of the reference signal received power RSRP of the sampling points of the daytime target cell greater than or equal to the preset threshold and the second sampling point ratio of the RSRP of the sampling points of the nighttime target cell greater than or equal to the preset threshold, the network data at least includes the total number of base stations, the total number of macro cells, and the total number of indoor cells contained in the area to be evaluated. The total number and the distance between at least one base station and the center point of the area to be evaluated, the drive test data at least includes the total number of the first grid corresponding to the area to be evaluated, the total number of the second grid with data transmission corresponding to the area to be evaluated, the first ratio of the total number of the second grid to the total number of the first grid, the total number of the third grid with data transmission corresponding to the area to be evaluated and the total number of the third grid, the total number of the fourth grid with no data transmission corresponding to the area to be evaluated, the third ratio of the total number of the fourth grid to the total number of the first grid, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, the total number of the fifth grid with RSRP collected by the sampling points in the grid corresponding to the area to be evaluated greater than or equal to the target threshold, the fourth ratio of the total number of the fifth grid to the total number of the first grid, and the fifth ratio of the total number of the fifth grid to the total number of the second grid.

[0013] In one implementable manner, the acquisition unit is further used to acquire training sample data and evaluation results of the training sample data; wherein the training sample data at least includes sample site data, sample statistical data, sample network data and sample road test data; the processing unit is further used to input the training sample data acquired by the acquisition unit into a gradient boosting decision tree GBDT model; the processing unit is further used to determine whether the prediction comparison results of the training sample data output by the GBDT model match the evaluation results based on the model evaluation indicator AUC; the processing unit is further used to iteratively update the training sample data repeatedly and cyclically when the prediction comparison results do not match the evaluation results, until the score corresponding to the AUC is greater than the score threshold, to determine that the GBDT model has converged and obtain an evaluation model.

[0014] In a third aspect, the present invention provides an electronic device, comprising: a communication interface, a processor, a memory, and a bus; the memory is used to store computer-executable instructions, and the processor and the memory are connected via the bus. When the electronic device is running, the processor executes the computer-executable instructions stored in the memory, so that the electronic device executes the regional coverage evaluation method provided in the first aspect above.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a computer, the computer is enabled to execute the method for evaluating area coverage provided in the first aspect.

[0016] In a fifth aspect, the present invention provides a computer program product, which, when executed on a computer, enables the computer to execute the area coverage evaluation method as described in the design mode of the first aspect.

[0017] It should be noted that the above computer instructions may be stored in whole or in part on the first computer-readable storage medium, wherein the first computer-readable storage medium may be packaged together with the processor of the electronic device, or may be packaged separately from the processor of the electronic device, which is not limited in the present invention.

[0018] The description of the second, third, fourth and fifth aspects of the present invention can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, fourth and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0019] In the present invention, the names of the above electronic devices do not limit the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of the present invention, they fall within the scope of the claims of the present invention and their equivalent technologies.

[0020] These and other aspects of the present invention will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A communication system to which an area coverage assessment method is applied is provided for an embodiment of the present invention;

[0023] Figure 2 One of the flow charts of a method for evaluating regional coverage is provided for an embodiment of the present invention;

[0024] Figure 3 A second flow chart of a method for evaluating regional coverage is provided for an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of evaluation data of an evaluation method for regional coverage is provided for an embodiment of the present invention;

[0026] Figure 5 A GIS schematic diagram of a method for evaluating regional coverage is provided for an embodiment of the present invention;

[0027] Figure 6 One of the structural schematic diagrams of an electronic device is provided for an embodiment of the present invention;

[0028] Figure 7 A second structural schematic diagram of an electronic device is provided for an embodiment of the present invention;

[0029] Figure 8 A schematic diagram of the structure of a computer program product of a method for evaluating regional coverage provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The embodiments of the present invention are described below in conjunction with the accompanying drawings.

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order.

[0033] Figure 1 A communication system to which an area coverage evaluation method provided by an embodiment of the present invention is applied, such as Figure 1 As shown, the system architecture may include: a server 1 and an area to be evaluated 2.

[0034] The server 1 obtains the evaluation data of the area to be evaluated 2 , so that the server 1 can determine the evaluation result of the area to be evaluated 2 according to the pre-stored evaluation model and the evaluation data of the area to be evaluated 2 .

[0035] The electronic device in the embodiment of the present invention may be Figure 1 The server 1 shown in the figure may also be a part of the device in the server 1. For example, a chip system in the server 1. The chip system is used to support the server 1 to implement the functions involved in the first aspect and any possible implementation thereof. For example, the evaluation data of the area to be evaluated 2 is obtained, and the evaluation result of the area to be evaluated 2 is determined according to the pre-stored evaluation model and the evaluation data of the area to be evaluated 2. The chip system includes a chip and may also include other discrete devices or circuit structures.

[0036] Some of the terms used in this disclosure have their common and customary meanings in the industry. In addition, some of the terms will be explained when they appear in this specification. However, it is helpful to understand a few of the terms used specifically in this article.

[0037] 3G is the third generation of mobile communication technology (3rd-Generation).

[0038] GeoJSON is a format for encoding various geographic data structures and a geospatial information data exchange format based on JavaScript Object Notation (JSON).

[0039] XGBoost is an optimized distributed gradient boosting library designed to be efficient, flexible, and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides parallel tree boosting (also known as GBDT, GBM) that can solve many data science problems quickly and accurately. The same code runs on major distributed environments (Hadoop, SGE, MPI) and can solve problems beyond billions of examples.

[0040] In the prior art, since cells with poor coverage effectiveness will affect UE's use of the network, operators need a method that can evaluate the coverage effectiveness of each cell in the network. To this end, an embodiment of the present invention provides a method for evaluating regional coverage, which pre-stores an evaluation model including the corresponding relationship between evaluation data and evaluation results, so that when the operation and maintenance personnel evaluate the area to be evaluated, after obtaining the evaluation data of the area to be evaluated, they can determine the evaluation result of the area to be evaluated based on the pre-stored evaluation model and evaluation data, so that it is convenient for the operation and maintenance personnel to evaluate the regional coverage of the area to be evaluated, which can solve the problem of how operators evaluate the coverage effectiveness of each cell in the network. The specific implementation process is as follows:

[0041] The following combination Figure 1 The communication system shown takes the electronic device as server 1 as an example to introduce the area coverage evaluation method provided by the embodiment of the present invention.

[0042] like Figure 2 As shown, the regional coverage evaluation method includes the following steps S11 and S12:

[0043] S11, the server 1 obtains evaluation data of the area to be evaluated, wherein the evaluation data at least includes site data, statistical data, network data and drive test data.

[0044] S12: The server 1 determines the evaluation result of the to-be-evaluated area according to the pre-stored evaluation model and evaluation data, wherein the evaluation model includes the corresponding relationship between the evaluation data and the evaluation result.

[0045] As can be seen from the above, in the regional coverage evaluation method provided by the present invention, the server 1 pre-stores an evaluation model including the corresponding relationship between evaluation data and evaluation results, so that when the operation and maintenance personnel evaluate the area to be evaluated, they can obtain the evaluation data of the area to be evaluated through the server 1. Then, the server 1 can determine the evaluation result of the area to be evaluated based on the pre-stored evaluation model and evaluation data. This can facilitate the operation and maintenance personnel to evaluate the regional coverage of the area to be evaluated, so as to solve the problem of how operators evaluate the coverage effectiveness of each cell in the network.

[0046] In one achievable manner, the field point data at least includes: field point type and field point level.

[0047] The statistical data includes at least key performance indicator (KPI) statistical information and measurement report (MR) statistical information. The KPI statistical information includes at least the average daytime cell availability, the average daytime target system reverse flow ratio, the average daytime single-cell air interface service flow, the daytime downlink physical resource block (PRB) average utilization, the nighttime cell average availability, the nighttime target system reverse flow ratio, the nighttime single-cell average air interface service flow and the nighttime PRB average utilization. The MR statistical information includes at least the first sampling point ratio of the sampling points of the daytime target cell whose reference signal received power (RSRP) is greater than or equal to a preset threshold and the second sampling point ratio of the sampling points of the nighttime target cell whose RSRP is greater than or equal to the preset threshold. The network data at least includes the total number of base stations, the total number of macro cells, the total number of indoor cells and the distance of at least one base station from the center point of the area to be evaluated contained in the area to be evaluated. The drive test data at least includes the total number of first grids corresponding to the area to be evaluated, the total number of second grids with data transmission corresponding to the area to be evaluated, the first ratio of the total number of second grids to the total number of first grids, the total number of third grids with data transmission corresponding to the area to be evaluated and the total amount of data transmission is less than or equal to the transmission threshold, the second ratio of the total number of third grids to the total number of first grids, the total number of fourth grids with no data transmission corresponding to the area to be evaluated, the third ratio of the total number of fourth grids to the total number of first grids, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, the total number of fifth grids with RSRP collected by sampling points in the grid corresponding to the area to be evaluated greater than or equal to the target threshold, the fourth ratio of the total number of fifth grids to the total number of first grids and the fifth ratio of the total number of fifth grids to the total number of second grids.

[0048] Specifically, the average daytime cell availability is equal to A represents the total time duration of all cells in the area to be evaluated during the day, and B represents the total unavailable time duration of all cells in the area to be evaluated during the day.

[0049] Specifically, the daytime target system average backflow ratio is equal to the average value of the target system backflow ratios of all cells in the area to be evaluated during the daytime.

[0050] Specifically, the average air interface traffic flow of a single cell during the day is equal to the average air interface traffic flow of all cells in the area to be evaluated during the day.

[0051] Specifically, the average downlink PRB utilization rate during the day is equal to the average downlink PRB utilization rate of all cells in the area to be evaluated during the day.

[0052] Specifically, the average availability of a cell at night is equal to C represents the total time duration of all cells in the area to be evaluated at night, and D represents the total unavailable time duration of all cells in the area to be evaluated at night.

[0053] Specifically, the target system average backflow ratio at night is equal to the average value of the target system backflow ratios of all cells in the area to be evaluated at night.

[0054] Specifically, the average air interface service flow of a single cell at night is equal to the average air interface service flow of all cells in the area to be evaluated at night.

[0055] Specifically, the average utilization rate of downlink PRB at night is equal to the average value of downlink PRBs of all cells in the area to be evaluated at night.

[0056] Specifically, the proportion of the first sampling points whose RSRP is greater than or equal to the preset threshold among the sampling points of the target cell during the day is equal to the ratio of the total number of sampling points whose RSRP is greater than or equal to the preset threshold in the area to be evaluated during the day to the total number of sampling points in the area to be evaluated during the day.

[0057] Specifically, the proportion of second sampling points whose RSRP is greater than or equal to the preset threshold among the sampling points of the target cell at night is equal to the ratio of the total number of sampling points whose RSRP is greater than or equal to the preset threshold in the area to be evaluated at night to the total number of sampling points in the area to be evaluated at night.

[0058] In one achievable approach, combining Figure 2 ,like Figure 3 As shown, the regional coverage evaluation method provided in the embodiment of the present application also includes:

[0059] S13, the server 1 obtains training sample data and evaluation results of the training sample data, wherein the training sample data at least includes sample site data, sample statistical data, sample network data and sample drive test data.

[0060] In some examples, in order to obtain the evaluation model more accurately, the regional coverage evaluation method provided by the embodiment of the present invention uses the historical evaluation data of the existing cells as the training sample data, and uses the evaluation results corresponding to the historical evaluation data of the existing cells as the evaluation results of the training sample data. Therefore, when the training sample data is input into the evaluation model, it can be determined whether the evaluation results given by the corresponding evaluation model are the same as the evaluation results of the training sample data, so that the evaluation model can be continuously iterated to ensure the accuracy of the evaluation results given by the evaluation model.

[0061] Specifically, the first original data of the historical evaluation data of existing cells include: engineering parameter data, site information data, KPI data, MR data, Minimization of Drive-Test (MDT) data and complaint data. Among them, the engineering parameter data at least includes: base station type, site height, antenna direction angle, downtilt angle, base station location longitude and latitude. The site information data at least includes: site classification, site importance classification, site geographic boundary information. KPI data, specific information at least includes: the number of switching initiations to low priority standards, reverse flow ratio, uplink PRB utilization and downlink PRB utilization. Complaint data at least includes: complaint location and number of complaints related to coverage issues.

[0062] It should be noted that the longer the statistical duration of the site information is, the more it can reflect the actual situation of the area to be evaluated. For example: statistics of KPI data for the first preset duration, statistics of MR data for the second preset duration, statistics of MDT data for the third preset duration, and statistics of complaint data for the fourth preset duration. The first preset duration, the second preset duration, the third preset duration, and the fourth preset duration may be the same or different. Exemplarily, the first preset duration may be 30 days, the second preset duration may be 31 days, the third preset duration may be 28 days, and the fourth preset duration may be 29 days; or the first preset duration, the second preset duration, the third preset duration, and the fourth preset duration are all 30 days.

[0063] The second original data of the evaluation results of the historical evaluation data of the existing cells includes: the evaluation results given by the operation and maintenance personnel based on the historical evaluation data of the existing cells. Exemplarily, the evaluation results are divided into two categories, and the evaluation results after the division include reaching the standard and not reaching the standard. The evaluation results are divided into multiple categories, and the evaluation results after the division include excellent, good, medium and poor.

[0064] At this point, server 1 has obtained the first original data and the second original data. In order to better analyze, it is necessary to process the first original data and the second original data to obtain data that is easy to analyze. Specifically, the process of processing the first original data and the second original data is as follows:

[0065] 1. Determine at least one base station included in the area to be evaluated.

[0066] Based on the geographic boundary data of the area to be evaluated (the geographic boundary data is a collection of location information of polygons of the geographic boundary of the area to be evaluated. Exemplarily, the location information in the collection can be recorded in a geojson string) and the location information of the base stations, a list of base stations within the boundary of the area to be evaluated is determined and stored in the site information data.

[0067] Preferably, since base stations outside the boundary will also cover the area within the area to be evaluated, the boundary of the area to be evaluated can be expanded by x meters before the process of determining base stations within the area to be evaluated is performed.

[0068] 2. Calculate the location information corresponding to the center point of the area to be evaluated.

[0069] Preferably, the polygon centroid algorithm is used to calculate the location information of the center point of the area to be evaluated. Exemplarily, taking the Global Positioning System (GPS) as an example, the location information of the center point includes longitude and latitude.

[0070] 3. Determine the raster data contained in the area to be evaluated.

[0071] The MDT data is subjected to geographic rasterization processing. If a square grid is used, the grid size is m×m meters. If m is equal to 30, the server 1 performs geographic rasterization processing on the MDT data according to a 30m×30m square grid, so that the grid data contained in the area to be evaluated can be determined.

[0072] 4. Summarize KPI data and MR data to determine site data, statistical data, network data and drive test data.

[0073] First, the KPI data within the preset time length is statistically summarized and processed, and different statistical processing is performed for different types of data. For quantitative data, such as the number of cells, service flow, etc., the quantitative data of the same data are summed and counted. For corresponding percentage data, such as the average PRB utilization rate, etc., the average value of the cells in the regional range is used for processing. For example, the cell to be analyzed contains 2 cells, namely cell 1 and cell 2, the uplink service flow of cell 1 is 300M, and the uplink service flow of cell 2 is 200M. When the uplink service flow of the cell to be analyzed is counted, the uplink service flow of cell 1 and cell 2 needs to be summed, so that the uplink service flow of the cell to be analyzed can be determined to be 500M. For another example: the cell to be analyzed contains 2 cells, namely cell 1 and cell 2, the average PRB utilization of cell 1 is 80%, and the average PRB utilization of cell 2 is 90%. When the average PRB utilization of the cell to be analyzed is counted, the average PRB utilization of cell 1 and cell 2 needs to be averaged, so that the uplink service flow of the cell to be analyzed can be determined to be

[0074] Then, the first raw data after data processing and the second raw data are summarized to form feature items. Exemplarily, the area to be evaluated can be called a "site". If the site type of the area to be evaluated is a university, the target university is one of the specific sites, and the cells used to cover the target university are all cells belonging to the site. The historical evaluation data is classified into feature items using the site as a sample, that is, each row of the data set is a site, and each column is a different feature item of the site. Among them, the characteristic items can be the average availability of the cell during the day, the average backflow ratio of the target system during the day, the average air interface service flow of a single cell during the day, the average PRB utilization rate during the day, the average availability of the cell at night, the average backflow ratio of the target system at night, the average air interface service flow of a single cell at night, the average PRB utilization rate at night, the proportion of the first sampling points whose RSRP is greater than or equal to the preset threshold among the sampling points of the target cell during the day, the proportion of the second sampling points whose RSRP is greater than or equal to the preset threshold among the sampling points of the target cell at night, the total number of base stations contained in the area to be evaluated, the total number of macro cells, the total number of indoor cells, the distance of at least one base station from the center point of the area to be evaluated, the total number of first grids corresponding to the area to be evaluated (also called the total number of field grids in the area to be evaluated), and the number of data transmission points corresponding to the area to be evaluated. one or more of the total number of second grids (also called the total number of grids with data in the field point), the first ratio of the total number of second grids to the total number of first grids, the total number of third grids with data transmission corresponding to the area to be evaluated and the total amount of data transmission is less than or equal to the transmission threshold, the second ratio of the total number of third grids to the total number of first grids, the total number of fourth grids with no data transmission corresponding to the area to be evaluated, the third ratio of the total number of fourth grids to the total number of first grids, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, the total number of fifth grids with RSRP collected by sampling points in the grid corresponding to the area to be evaluated being greater than or equal to the target threshold, the fourth ratio of the total number of fifth grids to the total number of first grids, and the fifth ratio of the total number of fifth grids to the total number of second grids.

[0075] Specifically, the site data includes at least the site type, site level, site name and site identification code (Identity document, ID). Site type: defined by the operator according to the network operation and management requirements, such as colleges and universities, residential areas, high-speed rail stations, industrial parks, etc. Site levels are divided by the operator according to the requirements of construction and operation. For example, the operator divides the site level according to the investment amount of the area to be evaluated.

[0076] Specifically, the statistical data includes at least KPI statistical information and MR statistical information. The collection time of KPI statistical information and MR statistical information is daytime and nighttime, and the daytime period is t1-t2, and the nighttime period is t3-t4. Generally, taking the 24-hour system as an example, it is recommended that t1 is equal to 7, t2 is equal to 19, t3 is equal to 20, and t4 is equal to 1. In this way, the data collection time of KPI statistical information and MR statistical information during the day is from 7 am to 7 pm, and the data collection time of KPI statistical information and MR statistical information at night is from 8 pm to 1 am the next day.

[0077] For all cells under each site, KPI statistical information is summarized and counted according to the two time periods of day and night, so that the average daytime cell availability, the average backflow ratio of the target system during the day, the average air interface service flow of a single cell during the day, the average PRB utilization rate during the day, the average nighttime cell availability, the average backflow ratio of the target system at night, the average air interface service flow of a single cell at night, and the average PRB utilization rate at night can be determined. Exemplarily, the target system can be the 4th generation mobile communication technology (4G) or the 5th generation mobile communication technology (5G).

[0078] Then, q RSRP threshold values ​​(also called preset thresholds) {thr1, thr2, thr3, ..., thr q}. To avoid dimensionality explosion, q is generally an integer greater than 0 and less than or equal to 10. Specifically, the preset threshold is recommended to select some threshold values ​​with specific meanings such as typical service coverage requirements and planning goals. For example: -110dbm corresponds to the road test requirement threshold, -110dbm corresponds to the planning coverage threshold, -112dbm corresponds to the volte coverage threshold, etc.

[0079] For all cells under each site, the MR statistical information is summarized and counted according to the two time periods of daytime and nighttime, so as to obtain the first sampling point ratio of the reference signal received power RSRP in the sampling points of the target cell during the daytime is greater than or equal to the preset threshold and the second sampling point ratio of the RSRP in the sampling points of the target cell at night is greater than or equal to the preset threshold. It should be noted that when there are multiple preset thresholds, it is necessary to collect the first sampling point ratio and the second sampling point ratio corresponding to each preset threshold. For example, it includes 2 preset thresholds, namely thr1 and thr2. At this time, the server 1 needs to determine the first sampling point ratio of the reference signal received power RSRP in the sampling points of the target cell during the daytime is greater than or equal to thr1, determine the first sampling point ratio of the reference signal received power RSRP in the sampling points of the target cell during the daytime is greater than or equal to thr2, determine the second sampling point ratio of the RSRP in the sampling points of the target cell at night is greater than or equal to thr1, and determine the second sampling point ratio of the RSRP in the sampling points of the target cell at night is greater than or equal to thr2.

[0080] Specifically, based on the list of base stations within the boundary of the area to be evaluated, the total number of base stations contained in each site, the number of macro cells in each site, and the number of indoor cells in each site are summarized and counted, so as to obtain the total number of base stations, the total number of macro cells, and the total number of indoor cells contained in the area to be evaluated in the network data. Then, the distance of each base station in the base station list from the center point of the area to be evaluated is calculated. Exemplarily, in order to facilitate calculation, after calculating the distance between each base station in the area to be evaluated and the center point of the area to be evaluated, the distances of the nearest N cells are selected as the distances from at least one base station in the network data to the center point of the area to be evaluated. If N is 3, then after calculating the distance between each base station and the center point of the area to be evaluated, the server 1 sorts each distance in order from small to large, and sorts the first three distances with the smallest distance, such as distance 1, distance 2, and distance 3, where distance 1 is less than distance 2, and distance 2 is less than distance 3. Then, the server 1 determines distance 1, distance 2, and distance 3 as the distances from at least one base station in the network data to the center point of the area to be evaluated.

[0081] Specifically, through the grid data contained in the area to be evaluated, the total number of first grids corresponding to the area to be evaluated in the road test data, the total number of second grids with data transmission corresponding to the area to be evaluated, the first ratio of the total number of second grids to the total number of first grids, the total number of third grids with data transmission corresponding to the area to be evaluated and the total amount of data transmission is less than or equal to the transmission threshold (also called the number of low sampling point grids), the second ratio of the total number of third grids to the total number of first grids (also called the proportion of the number of low sampling point grids), the total number of fourth grids with no data transmission corresponding to the area to be evaluated (also called the number of empty low grids), and the third ratio of the total number of fourth grids to the total number of first grids (also called the proportion of the number of empty low grids) can be determined.

[0082] Specifically, by statistically analyzing the MDT data in the site, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, and the RSRP cumulative distribution function (CDF) curve in the site can be determined. By analyzing the RSRP CDF curve in the site, the total number of the fifth grid (also called the number of qualified grids) whose RSRP collected by the sampling points in the grid corresponding to the area to be evaluated is greater than or equal to the target threshold, the fourth ratio of the total number of the fifth grid to the total number of the first grid, and the fifth ratio of the total number of the fifth grid to the total number of the second grid can be determined. Exemplarily, the target threshold may be one or more of the q RSRP threshold values.

[0083] Preferably, the selection of segmentation points for the RSRP CDF curve distribution output does not need to be too fine to avoid dimensionality explosion.

[0084] Preferably, the fourth ratio and the fifth ratio mainly differ in the denominator. Since MDT data has no data or the data volume is very low in some sites (such as indoors, not supported by the terminal), this will affect the statistical results. Therefore, introducing two statistical features for the fourth ratio and the fifth ratio can add additional information to the data set and ensure the accuracy of the calculation.

[0085] S14. Server 1 inputs the training sample data into the gradient boosting decision tree GBDT model.

[0086] In some examples, when inputting training sample data into the gradient boosting decision tree GBDT model, it is necessary to encode the "feature item" feature. For example, label encoding is performed on both the field point type and the field point level. When the evaluation results are divided into two categories (such as meeting the standard and not meeting the standard), binary encoding is performed. When the evaluation results are divided into multiple categories (such as excellent, good, medium and poor), onehot encoding is performed. Then, the target variable y in the GBDT model is set to "evaluation result" and the "feature item" is used as the input data matrix X.

[0087] In other examples, the historical evaluation data of existing cells and the evaluation results of the historical evaluation data of existing cells need to be segmented to form a training data set trainset = (X_train, y_train) and a verification data set testset = (X_test, y_test). Then, the trainset data is used as training data to perform the fit training of the GBDT model to obtain the trained model clf. Among them, clf = GBDT (X_train, y_train, **param).fit, **param represents the adjustable parameters of the model.

[0088] In order to verify the accuracy of the GBDT model, it is necessary to perform model verification on the trained model clf. For example, perform model prediction (predict) on the testset data set and output the predicted result y′ of the target variable "evaluation result", y′=clf.predict(X_test).

[0089] S15. Server 1 determines whether the prediction comparison result of the training sample data output by the GBDT model matches the evaluation result based on the model evaluation indicator AUC.

[0090] In some examples, by calculating the scores of y_test and y′ in the trainset data, it is possible to determine whether the prediction comparison results of the training sample data output by the GBDT model match the evaluation results.

[0091] For example, the model evaluation index (Area Under Curve, AUC) is used to calculate the score of y_test and y′ in the trainset data, score = auc(y test , y′).

[0092] S16. When the prediction comparison result does not match the evaluation result, server 1 iteratively updates the training sample data repeatedly and cyclically until the score corresponding to the AUC is greater than the score threshold, and determines that the GBDT model converges to obtain the evaluation model.

[0093] In some examples, when the score is greater than the score threshold, the GBDT model is considered to have converged and the model is saved. Otherwise, by adjusting "**param", the training sample data is iteratively updated repeatedly until the score corresponding to the AUC is greater than the score threshold, the GBDT model is determined to have converged and the evaluation model is obtained.

[0094] In combination with the above example, the server 1 obtains the evaluation data of the area to be evaluated including the following steps:

[0095] The server 1 collects local network data through the Operation Support Systems (OSS), so as to determine the engineering parameter data, site information data, KPI data and MDT data.

[0096] For example, taking the example of server 1 collecting local network data including data of 15 local networks through OSS, some engineering parameter data are shown in Tables 1 to 3, and some site information data are shown in Table 4. Among them, since the local network data uses the comma-separated values ​​(CSV) file format to record data, the data can be displayed in a table.

[0097] Table 1

[0098]

[0099] Table 2

[0100]

[0101] Table 3

[0102]

[0103]

[0104] Table 4

[0105]

[0106] Specifically, the geographic boundary layer data of the area to be evaluated in the site information data is recorded in a separate csv file, and the geographic boundary is stored as data composed of a two-dimensional sampling point. Exemplarily, the geographic boundary information of some sites is shown in Table 5.

[0107] Table 5

[0108]

[0109]

[0110] For example, taking the example of server 1 collecting 31 days of 4G KPI data through OSS, server 1 parses the collected KPI data into structured data (two-dimensional table) and summarizes it into structured csv files by hour. Among them, the structured csv files of some 4G KPI data are as follows: Figure 4 shown.

[0111] Exemplarily, the example of server 1 preprocessing MDT data into 50x50 meter rasterized data is used for description, and some rasterized data are shown in Table 6 to Table 11.

[0112] Table 6

[0113]

[0114]

[0115] Table 7

[0116]

[0117] Table 8

[0118]

[0119]

[0120] Table 9

[0121]

[0122] Table 10

[0123]

[0124]

[0125] Table 11

[0126] Number of sampling points for the first operator RSRP ≥ -115 The first operator RSRP ≥ -120 sampling points 0 0 0 0

[0127] The server 1 collects MR data through the network management system. Usually, MR data is recorded in the format of Extensible Markup Language (XML).

[0128] Server 1 determines the evaluation results of the historical evaluation data of existing cells by collecting the test data of the drive test (DT) / call quality test (CQT) of the specific sites of the local network by the operation and maintenance personnel, the complaint handling and daily operation and maintenance experience, and the company's coverage requirements for different sites. Exemplarily, the evaluation results of the historical evaluation data of some existing cells are shown in Table 12.

[0129] Table 12

[0130]

[0131]

[0132] Specifically, in the embodiment provided by the present invention, the server 1 expands the boundary of the area to be evaluated by 300 meters and then calculates the list of base stations falling within the area to be evaluated. Then, the server 1 uses the polygon centroid algorithm to calculate the central longitude and latitude of the site. Exemplarily, a partial list of base stations is shown in Table 13.

[0133] Table 13

[0134]

[0135]

[0136] Server 1 performs geographic gridding processing on MDT data using a square grid. For example, the size of the square grid is 50 meters × 50 meters. For example, the gridded MDT data Geographic Information System (GIS) is as follows: Figure 5 shown.

[0137] Then, the server 1 determines the site data, statistical data, network data and drive test data according to the evaluation results of the engineering parameter data, site information data, KPI data, MR data, gridded MDT data and historical evaluation data of existing cells.

[0138] Exemplarily, the preset threshold value includes four RSRP threshold values, namely thr1 = -100dbm, thr2 = -105dbm, thr3 = -110dbm and thr4 = -112dbm.

[0139] Server 1 uses binary classification to classify the evaluation results of the historical evaluation data of the existing cells and determine each evaluation result. For example, the evaluation results include "meeting the standard" and "not meeting the standard". After the feature construction is completed, the evaluation data of the area to be evaluated is formed and stored as a csv file. For example, some evaluation data of the area to be evaluated are shown in Tables 14 to 22.

[0140] Table 14

[0141]

[0142]

[0143] Table 15

[0144]

[0145]

[0146] Table 16

[0147]

[0148]

[0149] Table 17

[0150]

[0151]

[0152] Table 18

[0153]

[0154]

[0155]

[0156]

[0157] Table 19

[0158]

[0159] Table 20

[0160]

[0161] Table 21

[0162]

[0163]

[0164]

[0165] Table 22

[0166]

[0167]

[0168] Then, server 1 uses xgboost, an open source project of GBDT algorithm, to perform model training. Exemplarily, the GBDT model training code written in Python, a computer programming language, is as follows:

[0169] 1) Encode the “category” feature: perform label encoding on the site type and site level; in this embodiment, the coverage rating is a binary classification, and binary encoding is performed, mapping “meeting the standard” or “qualified” to 1, and “meeting the standard” or “not meeting the standard” to 0.

[0170] 2) Set the target variable y = "evaluation result" and all feature items as the input data matrix X.

[0171] 3) The historical evaluation data of the existing communities and the evaluation results of the historical evaluation data of the existing communities are segmented to form a training data set and a verification data set.

[0172] 4) Use the XGB Classifer model provided by xgboost, set the general parameters of the model, and input the training data set into the XGB Classifer model for fit training.

[0173] 5) Model validation: Perform model prediction (predict) on the validation data set and output the predicted result y′ of the target variable "evaluation result". Calculate the score of y_test and y′ in the trainset data, and select AUC (Area Under Curve) as the model validation indicator.

[0174] 6) The auc scores of the XGB Classifer model on both the training dataset and the validation dataset exceed the score threshold, such as 0.95, indicating that the classification performance of the XGB Classifer model is good. The XGB Classifer model can be saved for field coverage evaluation of the evaluation data.

[0175] Exemplarily, the running code of the electronic device when running the XGB Classifer model is as follows:

[0176]

[0177]

[0178]

[0179]

[0180]

[0181]

[0182]

[0183]

[0184]

[0185]

[0186] 7) Finally, server 1 collects new network multi-source data and establishes a data set according to the above method. At this time, there is no need to manually provide relevant features of network coverage assessment experience. The network side data is used as the model input, and the model intelligently gives a prediction of the "assessment result", thereby completing the field-based coverage assessment quickly and at low cost.

[0187] The above mainly introduces the solution provided by the embodiment of the present invention from the perspective of the method. In order to achieve the above functions, it includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0188] The embodiment of the present invention can divide the electronic device into functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0189] like Figure 6 , which is a schematic diagram of the structure of an electronic device 10 provided in an embodiment of the present invention. The electronic device 10 is used to obtain evaluation data of a to-be-evaluated area; and determine the evaluation result of the to-be-evaluated area according to a pre-stored evaluation model and evaluation data. The electronic device 10 may include an acquisition unit 101 and a processing unit 102.

[0190] The acquisition unit 101 is used to acquire the evaluation data of the area to be evaluated. Figure 2 , the acquisition unit 101 can be used to execute S11. Figure 3 , the acquisition unit 101 can be used to execute S13.

[0191] The processing unit 102 is used to determine the evaluation result of the area to be evaluated according to the pre-stored evaluation model and evaluation data. Figure 2 , the processing unit 102 may be configured to execute S12. Figure 3 , the processing unit 102 can be used to execute S14, S15 and S16.

[0192] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and its role will not be repeated here.

[0193] Of course, the electronic device 10 provided in the embodiment of the present invention includes but is not limited to the above modules, for example, the electronic device 10 may also include a storage unit 103. The storage unit 103 may be used to store the program code of the writing electronic device 10, and may also be used to store data generated by the writing electronic device 10 during operation, such as data in a write request, etc.

[0194] Figure 7 A schematic diagram of the structure of an electronic device 10 provided in an embodiment of the present invention is shown in FIG. Figure 7 As shown, the electronic device 10 may include: at least one processor 51 , a memory 52 , a communication interface 53 and a communication bus 54 .

[0195] Combine the following Figure 7 A detailed introduction to the various components of electronic equipment:

[0196] The processor 51 is the control center of the electronic device 10, and may be a processor or a general term for multiple processing elements. For example, the processor 51 is a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more DSPs, or one or more field programmable gate arrays (FPGAs).

[0197] In a specific implementation, as an embodiment, the processor 51 may include one or more CPUs, such as Figure 7 Also, as an embodiment, the electronic device may include multiple processors, such as Figure 7 51 and 55 are shown in FIG. Each of these processors may be a single-core processor (Single-CPU) or a multi-core processor (Multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0198] The memory 52 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 52 may exist independently and be connected to the processor 51 via a communication bus 54. The memory 52 may also be integrated with the processor 51.

[0199] In a specific implementation, the memory 52 is used to store the data of the present invention and execute the software program of the present invention. The processor 51 can execute various functions of the air conditioner by running or executing the software program stored in the memory 52 and calling the data stored in the memory 52.

[0200] The communication interface 53 uses any transceiver or other device to communicate with other devices or communication networks, such as Radio Access Network (RAN), Wireless Local Area Networks (WLAN), terminals, cloud, etc. The communication interface 53 may include an acquisition unit to implement a receiving function.

[0201] The communication bus 54 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0202] As an example, combining Figure 6The function implemented by the acquisition unit 101 in the electronic device 10 is similar to Figure 7 The function of the communication interface 53 in the embodiment is the same as that of the processing unit 102. Figure 7 The functions of the processor 51 in the embodiment are the same as those of the storage unit 103. Figure 7 The function of the memory 52 in is the same.

[0203] Another embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a computer, the computer executes the method shown in the above method embodiment.

[0204] In some embodiments, the disclosed methods may be implemented as computer program instructions encoded in a machine-readable format on a computer-readable storage medium or on other non-transitory media or articles of manufacture.

[0205] Figure 8 The diagram schematically shows a conceptual partial view of a computer program product provided by an embodiment of the present invention, wherein the computer program product includes a computer program for executing a computer process on a computing device.

[0206] In one embodiment, the computer program product is provided using a signal bearing medium 410. The signal bearing medium 410 may include one or more program instructions, which when executed by one or more processors may provide the above-mentioned Figure 2 Thus, for example, reference to Figure 2 In the embodiment shown in , one or more features of S11 and S12 may be undertaken by one or more instructions associated with the signal bearing medium 410. In addition, Figure 8 The program instructions in also describe example instructions.

[0207] In some examples, signal bearing medium 410 may include computer readable medium 411, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM), or a random access memory (RAM), and the like.

[0208] In some implementations, signal bearing medium 410 may include computer recordable medium 412 such as, but not limited to, memory, read / write (R / W) CD, R / W DVD, and the like.

[0209] In some implementations, signal bearing medium 410 may include communication medium 413 such as, but not limited to, digital and / or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0210] The signal bearing medium 410 may be communicated by a wireless form of communication medium 413 (eg, a wireless communication medium complying with the IEEE 802.41 standard or other transmission protocols). The one or more program instructions may be, for example, computer executable instructions or logic implemented instructions.

[0211] In some examples, such as for Figure 2 The described writing data device may be configured to provide various operations, functions, or actions in response to one or more program instructions via computer-readable medium 411 , computer-recordable medium 412 , and / or communication medium 413 .

[0212] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0213] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0214] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0215] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0216] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0217] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating regional coverage, characterized in that: include: Acquire assessment data of the area to be assessed; wherein the assessment data at least includes site data, statistical data, network data and drive test data; Determine the evaluation result of the to-be-evaluated area according to the pre-stored evaluation model and the evaluation data; wherein the evaluation model includes the corresponding relationship between the evaluation data and the evaluation result; The site data at least includes: site type and site level; the statistical data at least includes key performance indicator KPI statistical information and measurement report MR statistical information, the KPI statistical information at least includes daytime average cell availability, daytime target standard average reverse flow ratio, daytime single cell average air interface service flow, daytime downlink physical resource block PRB average utilization, nighttime cell average availability, nighttime target standard average reverse flow ratio, nighttime single cell average air interface service flow and nighttime downlink physical resource block PRB average utilization, the MR statistical information at least includes the first sampling point ratio of the reference signal received power RSRP of the sampling points of the daytime target cell greater than or equal to the preset threshold and the second sampling point ratio of the RSRP of the sampling points of the nighttime target cell greater than or equal to the preset threshold, the network data at least includes the total number of base stations, the total number of macro cells, the total number of indoor cells and the distance of at least one base station from the sampling points to be evaluated. The distance between the center point of the area to be evaluated and the drive test data at least includes the total number of the first grid corresponding to the area to be evaluated, the total number of the second grid with data transmission corresponding to the area to be evaluated, the first ratio of the total number of the second grid to the total number of the first grid, the total number of the third grid with data transmission corresponding to the area to be evaluated and the total number of the third grid is less than or equal to the transmission threshold, the second ratio of the total number of the third grid to the total number of the first grid, the total number of the fourth grid without data transmission corresponding to the area to be evaluated, the third ratio of the total number of the fourth grid to the total number of the first grid, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, the total number of the fifth grid in which the RSRP collected by the sampling points in the grid corresponding to the area to be evaluated is greater than or equal to the target threshold, the fourth ratio of the total number of the fifth grid to the total number of the first grid, and the fifth ratio of the total number of the fifth grid to the total number of the second grid; Before obtaining the assessment data of the area to be assessed, the method further includes: Acquire training sample data and evaluation results of the training sample data; wherein the training sample data at least includes sample site data, sample statistical data, sample network data and sample drive test data; Input the training sample data into the gradient boosted decision tree (GBDT) model; Based on the model evaluation index AUC, determine whether the prediction comparison result of the training sample data output by the GBDT model matches the evaluation result; When the predicted comparison result does not match the evaluation result, the training sample data is iteratively updated repeatedly and cyclically until the score corresponding to the AUC is greater than the score threshold, and the GBDT model is determined to converge to obtain the evaluation model.

2. A device for evaluating regional coverage, characterized in that: include: An acquisition unit, used to acquire evaluation data of the area to be evaluated; wherein the evaluation data at least includes site data, statistical data, network data and drive test data; A processing unit, configured to determine an evaluation result of the to-be-evaluated area according to a pre-stored evaluation model and the evaluation data acquired by the acquisition unit; wherein the evaluation model includes a corresponding relationship between the evaluation data and the evaluation result; The site data at least includes: site type and site level; the statistical data at least includes key performance indicator KPI statistical information and measurement report MR statistical information, the KPI statistical information at least includes daytime average cell availability, daytime target standard average reverse flow ratio, daytime single cell average air interface service flow, daytime downlink physical resource block PRB average utilization, nighttime cell average availability, nighttime target standard average reverse flow ratio, nighttime single cell average air interface service flow and nighttime downlink physical resource block PRB average utilization, the MR statistical information at least includes the first sampling point ratio of the reference signal received power RSRP of the sampling points of the daytime target cell greater than or equal to the preset threshold and the second sampling point ratio of the RSRP of the sampling points of the nighttime target cell greater than or equal to the preset threshold, the network data at least includes the total number of base stations, the total number of macro cells, the total number of indoor cells and the distance of at least one base station from the sampling points to be evaluated. The distance between the center point of the area to be evaluated and the drive test data at least includes the total number of the first grid corresponding to the area to be evaluated, the total number of the second grid with data transmission corresponding to the area to be evaluated, the first ratio of the total number of the second grid to the total number of the first grid, the total number of the third grid with data transmission corresponding to the area to be evaluated and the total number of the third grid is less than or equal to the transmission threshold, the second ratio of the total number of the third grid to the total number of the first grid, the total number of the fourth grid without data transmission corresponding to the area to be evaluated, the third ratio of the total number of the fourth grid to the total number of the first grid, the total number of sampling points in the area to be evaluated, the average value of RSRP collected by all sampling points in the area to be evaluated, the total number of the fifth grid in which the RSRP collected by the sampling points in the grid corresponding to the area to be evaluated is greater than or equal to the target threshold, the fourth ratio of the total number of the fifth grid to the total number of the first grid, and the fifth ratio of the total number of the fifth grid to the total number of the second grid; The acquisition unit is further used to acquire training sample data and evaluation results of the training sample data; wherein the training sample data at least includes sample site data, sample statistical data, sample network data and sample drive test data; The processing unit is further used to input the training sample data acquired by the acquisition unit into a gradient boosting decision tree GBDT model; The processing unit is further used to determine whether the prediction comparison result of the training sample data output by the GBDT model matches the evaluation result based on the model evaluation index AUC; The processing unit is also used to iteratively update the training sample data repeatedly and cyclically when the predicted comparison result does not match the evaluation result, until the score corresponding to the AUC is greater than the score threshold, determine that the GBDT model converges, and obtain the evaluation model.

3. A computer-readable storage medium, characterized in that: The method comprises instructions which, when executed on a computer, cause the computer to execute the method for evaluating area coverage as claimed in claim 1.

4. An electronic device, characterized in that: include: Communication interface, processor, memory, bus; The memory is used to store computer-executable instructions, and the processor is connected to the memory via the bus; When the electronic device is running, the processor executes the computer-executable instructions stored in the memory, so that the electronic device performs the area coverage assessment method as described in claim 1 above.

Images