Network coverage performance evaluation method and device and electronic equipment

Abstract

The invention discloses a network coverage performance evaluation method and device and electronic equipment, and relates to the technical field of wireless, and the method comprises the steps: collecting network configuration information and network measurement data, constructing a network hierarchical networking structure diagram according to the network configuration information, the network hierarchical networking structure diagram is used for representing coverage ranges of different frequency bands in a network, and the coverage ranges of different frequency bands in the network are different; rasterizing the geographic electronic map to obtain a geographic grid set, associating the network measurement data with the geographic grid set, and evaluating the network coverage performance of the target area under different frequency bands according to the network hierarchical networking structure chart and the geographic grid set. By applying the technical scheme of the invention, the root of the network coverage problem actually perceived by the user can be accurately positioned.

Description

Technical Field

[0001] This application relates to the field of wireless technology, and in particular to a method, apparatus and electronic device for evaluating network coverage performance. Background Technology

[0002] Currently, 5G networks have been deployed on a large scale and coexist with 4G networks, forming a complex architecture of multi-band and multi-standard collaborative networking. Since some 5G terminals still need to fall back to the 4G network when initiating voice services, this further strengthens the deep integration of 4G and 5G networks. In terms of network coverage assessment, traditional methods mainly rely on cell-level performance statistics, field drive tests, and raster analysis based on Measurement Reports (MR), Minimization of Drive Tests (MDT), or Over The Top (OTT) data to monitor and optimize overall network performance.

[0003] However, existing methods have certain limitations. Cell-level metrics reflect average network performance and are insufficient to pinpoint instantaneous differences in individual user perception. Field testing is limited by fixed ranges and service scenarios, making it difficult to reproduce actual user scenarios. Grid-based analysis based on MR, MDT, or OTT, due to insufficient data representativeness and the averaging of signal strength within the grid, can easily mask localized weak coverage issues, leading to discrepancies between network metrics and actual user perception. This makes it impossible to accurately pinpoint the root cause of problems perceived by users, thus degrading the user experience. Summary of the Invention

[0004] In view of this, this application provides a network coverage performance evaluation method, apparatus and electronic device, which can accurately locate the root cause of network coverage problems actually perceived by users.

[0005] Firstly, this application provides a method for evaluating network coverage performance, including: Collect network configuration information and network measurement data; A hierarchical network structure diagram is constructed based on the network configuration information; the hierarchical network structure diagram is used to represent the coverage range of different frequency bands in the network; The geographic electronic map is rasterized to obtain a set of geographic raster cells; Associate the network measurement data with the geographic raster set; Based on the network hierarchical topology diagram and the geographic grid set, evaluate the network coverage performance of the target area in different frequency bands.

[0006] In some embodiments of this disclosure, associating the network measurement data with the geographic raster set includes: Iterate through the sampling points of the network measurement data; If the latitude and longitude of the sampling point are within the latitude and longitude range of the target geographic raster in the geographic raster set, the sampling point will be filled into the target geographic raster.

[0007] In some embodiments of this disclosure, evaluating the network coverage performance of a target area in different frequency bands based on the network hierarchical topology diagram and the geographic grid set includes: Based on the network hierarchical networking structure diagram, determine the weak coverage grids of the target area in the target frequency band from the set of geographic grids; Identify weak coverage areas; the weak coverage areas include at least two adjacent weak coverage grids; If the number of weak coverage grids in the target area is less than a first number, the number of sampling points in the weak coverage grids is greater than a second number, and the number of weak coverage grids in the weak coverage area is greater than a third number, then the network coverage performance of the target area in the target frequency band is determined to be insufficient.

[0008] In some embodiments of this disclosure, the step of extracting weak coverage gratings of the target area in the target frequency band from the geographic grating set includes: Iterate through the geographic rasters in the set of geographic rasters; Determine the signal strength and signal quality of the sampling points in the geographic grid; If the signal strength of all sampling points in the geographic raster is less than the signal strength threshold, and the signal quality of all sampling points in the geographic raster is less than the signal quality threshold, the geographic raster is determined to be a weak coverage raster.

[0009] In some embodiments of this disclosure, the method further includes: After optimizing and adjusting the network in the target area under the target frequency band, the network coverage performance of the target area under the target frequency band is evaluated again based on the network hierarchical networking structure diagram and the geographical grid set.

[0010] In some embodiments of this disclosure, the step of associating the network measurement data with the geographic raster set further includes, before: From the network measurement data, the measurement report data of the 5G network, the measurement report data of the 4G network, and the minimized drive test data of the 4G network are extracted; A fingerprint database is constructed based on the minimized drive test data of the 4G network; the fingerprint database includes the correlation between latitude and longitude and signal characteristics; Based on the fingerprint database and the measurement report data of the 4G network, determine the latitude and longitude information of the measurement report data of the 5G network; The latitude and longitude information is then backfilled into the measurement report data of the 5G network.

[0011] In some embodiments of this disclosure, after the step of associating the network measurement data with the geographic raster set, the method further includes: Based on the set of geographic grids, calculate and output the difference in network coverage indicators between the first network and the second network within the target area; the difference in network coverage indicators includes the difference in average signal strength, the difference in high-quality signal coverage rate, and the difference in the size of the high-quality signal coverage area.

[0012] In some embodiments of this disclosure, the method further includes: Based on the network hierarchical topology diagram, weak coverage grids for the target area in different frequency bands are determined in the set of geographic grids. Calculate and output network weak coverage indicators, which include single-band weak coverage rate and comprehensive band weak coverage rate; the single-band weak coverage rate is the ratio of the number of weak coverage grids to the total number of geographic grids in a single frequency band; the comprehensive band weak coverage rate is the sum of the products of the single-band weak coverage rate and the frequency band weighting factor in all frequency bands.

[0013] Secondly, this application provides a network coverage performance evaluation device, comprising: The data acquisition module is used to collect network configuration information and network measurement data; The processing module is used to construct a network hierarchical network structure diagram based on the network configuration information; perform rasterization processing on the geographic electronic map to obtain a geographic raster set; associate the network measurement data with the geographic raster set; the network hierarchical network structure diagram is used to represent the coverage range of different frequency bands in the network; The evaluation module is used to evaluate the network coverage performance of the target area in different frequency bands based on the network hierarchical topology diagram and the geographic grid set.

[0014] Thirdly, this application provides an electronic device including 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect.

[0015] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing the computer to perform the method described in the first aspect.

[0016] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0017] Based on the above technical solutions, this application provides a network coverage performance evaluation method, apparatus, and electronic device, relating to the field of wireless technology. The method includes: collecting network configuration information and network measurement data; constructing a network hierarchical network structure diagram based on the network configuration information, the network hierarchical network structure diagram being used to represent the coverage range of different frequency bands in the network; performing rasterization processing on a geographic electronic map to obtain a geographic raster set; associating the network measurement data with the geographic raster set; and evaluating the network coverage performance of a target area under different frequency bands based on the network hierarchical network structure diagram and the geographic raster set.

[0018] In the technical solution of this application, by constructing a hierarchical network structure diagram, network coverage performance can be analyzed independently by frequency band or frequency point, avoiding data confusion across multiple frequency bands and accurately identifying weak network coverage problems in specific frequency bands. By rasterizing the geographic electronic map and correlating it with network measurement data, the granularity of coverage assessment is refined from the cell level to the geographic raster level, more realistically reflecting the dimensions actually perceived by users. Through the correlation analysis of the hierarchical network structure diagram and the geographic raster, network coverage performance can be evaluated, and the root cause of network coverage problems actually perceived by users can be accurately located.

[0019] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic flowchart illustrating the network coverage assessment method provided in this embodiment of the disclosure; Figure 2 This is a network layering structure diagram of a 5G network provided in an embodiment of the present disclosure; Figure 3This is a network layered networking structure diagram of a 4G network provided in an embodiment of the present disclosure; Figure 4 A schematic diagram illustrating the process of backfilling 5G sampling point locations provided in this embodiment of the disclosure; Figure 5 A schematic diagram of a weak coverage area provided in an embodiment of this disclosure. Figure 1 ; Figure 6 A schematic diagram of a weak coverage area provided in an embodiment of this disclosure. Figure 2 ; Figure 7 A schematic diagram illustrating the formation of a weak coverage area by clustering multiple adjacent weak coverage grids according to an embodiment of this disclosure; Figure 8 This is a schematic diagram of the network coverage evaluation device provided in an embodiment of the present disclosure; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0023] The embodiments of this application will now be described in more detail with reference to the accompanying drawings. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0024] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0025] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0026] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0027] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure. In this disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular or a plural expression.

[0028] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0029] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0030] The prefixes such as "first" and "second" in the embodiments of this disclosure are only for distinguishing different descriptive objects and do not constitute restrictions on the position, order, priority, number or content of the descriptive objects. For the description of the descriptive objects, please refer to the description in the claims or the context of the embodiments. The use of prefixes should not constitute unnecessary restrictions.

[0031] In the embodiments disclosed herein, "multiple" refers to two or more.

[0032] In the embodiments disclosed herein, terms such as “import”, “input”, and “read in” can be used interchangeably.

[0033] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0034] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriberstation, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, and client can be used interchangeably.

[0035] Currently, 5G networks have achieved wide-area coverage, and 5G-A networks have been deployed in some hotspot areas. However, due to the large number of 4G terminals and the fact that some 5G terminals do not support Voice over New Radio (VoNR) technology, they still need to fall back to the 4G network through Evolved Packet System fallback (EPS fallback) when initiating voice services, resulting in a situation where 5G and 4G networks are co-networked.

[0036] In terms of frequency band planning, the 5G network is planned to use multiple frequency bands, including 700MHz for n28, 2.6GHz for n41, 3.5GHz for n78, and 4.9GHz for n79. Similarly, the 4G network is also planned to use multiple frequency bands, including 850MHz for n5, 900MHz for n8, 1800MHz for n3, 2.1GHz for n1, 1880MHz for n39, 2300MHz for n40, and 2.6GHz for n41.

[0037] Among them, n28, n1, n3, n5, and n8 adopt the Frequency Division Duplex (FDD) standard, while n39, n40, n41, n78, and n79 adopt the Time Division Duplex (TDD) standard, forming a network configuration with multiple standards and frequency bands coexisting.

[0038] In scenarios where 4G and 5G networks operate with multiple standards and frequency bands, operator satisfaction surveys indicate that the overall performance of current 4G and 5G networks has met standards. However, some users still report poor user experience, and network performance indicators do not fully match user perception. Regarding user complaints about weak network coverage in certain areas of the existing network, traditional network coverage assessment methods include the following categories: Cell-level network coverage performance analysis: Traditional methods for evaluating mobile communication network coverage performance use cell-level performance metrics. However, these metrics only reflect average performance and cannot accurately pinpoint user-perceived issues. Furthermore, cell-level performance statistics can overwhelm some user-perceived problems. In addition, current networks utilize multiple frequency bands, including 4G and 5G, meaning that even within the same area, cells may be using resources from different frequency bands. Therefore, cell-level performance metrics cannot accurately reflect the actual network coverage performance.

[0039] On-site testing with testing instruments: The on-site optimization team conducted on-site tests in the area where the user complaint occurred. However, the tests were limited to some public areas, only representing the network quality of a portion of the area, resulting in insufficient coverage. Furthermore, because the test items initiated by the testing instruments differed from the types of services used by the user, it was difficult to reproduce the specific scenario at the time of the user complaint, leading to a mismatch between the test results and the user's perception. For example, the test results for the complained area showed that the coverage rate reached 98.88%, the Reference Signal Received Power (RSRP) ≥ -110, the Signal to Interference plus Noise Ratio (SINR) ≥ -3, the average RSRP was -84.53 dBm, the average SINR was 14.52 dB, and the average download speed was 30.04 Mbps. The test results indicated that the network coverage performance in this area was good, with no obvious weak coverage areas.

[0040] Raster clustering sampling point analysis based on Measurement Report (MR) or Minimization of Drive Tests (MDT): This method uses a standard 50m×50m raster to process the data, filters MR sampling points carrying latitude and longitude information, and then filters the data again to remove rasteres with insufficient sampling points. The mean RSRP of each raster in the target area is obtained to evaluate the overall network coverage quality. However, because all sampling points are associated within a raster, but each raster represents the average of all sampling points, some sampling points with low RSRP values ​​may be covered by the mean RSRP of all sampling points. This makes it impossible to reconstruct the instantaneous network state at the time of user complaints, and it is difficult to accurately match the actual perceived problems of users. The results of the MR or MDT sampling point raster in the complaint area may indicate that there are no signal weaknesses.

[0041] Raster clustering sampling point analysis based on Over-The-Top (OTT) services: This method collects information such as Cell Identity (CID), frequency band, Physical Cell Identifier (PCI), and RSRP reported by one or more applications (APPs) during service operation. Then, it matches sampling points carrying latitude and longitude information with pre-set network grates, presenting the mean RSRP in the corresponding grates. However, the data relies on reports from specific APPs, resulting in limited user coverage and a relatively singular scenario. Grid averaging can mask localized weak coverage, failing to accurately recreate the instantaneous network state at the time of user complaints, leading to discrepancies with actual user experience. The presented results of OTT sampling point grates in the complaint area may indicate that there are no signal weaknesses.

[0042] Based on the above implementation methods, the aforementioned optimization analysis methods cannot accurately determine user perception, and network performance indicators do not completely match user perception. If traditional optimization analysis methods are used, the answer given to customers would be that there is no weak coverage issue in the area, even though the user's perception is real. This discrepancy between the assessment result and the actual experience directly leads to a decrease in user satisfaction. The core reason is that the network structure of 4G and 5G networks, with their multi-standard and multi-frequency band co-location, is becoming increasingly complex. Traditional network quality assessment methods struggle to accurately match real-world user scenarios and cannot objectively reflect actual user perception.

[0043] In related technologies, mobile network robustness situational awareness refers to the ability and related technical means to comprehensively, accurately, and stably perceive and judge the network's operational status and security situation in a mobile network environment, including the following aspects: Network optimization: Real-time monitoring of mobile network indicators such as signal strength and interference; data analysis to locate weak network coverage areas and performance bottlenecks, providing a basis for network planning and optimization.

[0044] Security Protection: Monitor security threats such as malicious attacks and data breaches in mobile networks, promptly detect and block unauthorized access, Distributed Denial of Service (DDoS) attacks, and other behaviors to protect user data and network security.

[0045] Service quality assurance: Identify user experience issues such as video buffering and voice call interruptions, and ensure the service quality of critical services by adjusting network resource allocation.

[0046] To address the aforementioned problems, embodiments of this application provide a network coverage assessment method, such as... Figure 1 The diagram shown is a flowchart of the network coverage assessment method provided in this application embodiment, including the following steps: S101: Collect network configuration information and network measurement data.

[0047] The network configuration information includes network information and base station information. Network information includes network identifier, network standard, frequency band, frequency point, physical cell identifier, bandwidth, power, etc. Base station information includes the base station's latitude and longitude, antenna azimuth angle, antenna downtilt angle, etc. Network measurement data includes MR data, MDT data, OTT data, etc.

[0048] S102: Construct a hierarchical network structure diagram based on network configuration information.

[0049] The network layered topology diagram is used to represent the coverage of different frequency bands in the network.

[0050] S103: Rasterize the geographic electronic map to obtain a set of geographic grids.

[0051] Among them, geographic electronic maps are digital maps marked with geographic coordinates (latitude and longitude), such as Geographic Information System (GIS) electronic maps.

[0052] S104: Associate network measurement data with a set of geographic rasters.

[0053] S105: Based on the network hierarchical topology diagram and geographic grid set, evaluate the network coverage performance of the target area in different frequency bands.

[0054] The target area refers to the geographical region where network coverage performance needs to be evaluated. For example, in a user complaint scenario, the area where the user complains can be defined as the target area. In a network planning scenario, a planned new urban area, an industrial park, or a university campus can be used as the target area. In a competitor analysis scenario, a contiguous area where the competitor's network performance is outstanding can be set as the target area.

[0055] The technical solution of this application provides a perception-based method for evaluating the robustness and coverage performance of mobile communication networks. This method is applicable to scenarios involving multi-band and multi-standard collaborative networking of 4G and 5G networks. It collects network configuration information and network measurement data, stratifies the data according to different frequency bands or frequency points of the network, and associates the network measurement data carrying latitude and longitude information with geographic rasters on a geographic electronic map. By constructing a perception-based network robustness and coverage performance evaluation system, the method determines the robustness and coverage performance of the mobile network, thereby enabling targeted network optimization and improving user experience.

[0056] The network coverage performance evaluation method provided in the embodiments of this application is described below with reference to the accompanying drawings.

[0057] In some embodiments, network configuration information is collected, a network hierarchical network structure diagram is constructed based on the network configuration information, and the network hierarchical network structure diagram is associated with a geographic electronic map to present the network hierarchical network structure diagram on the geographic electronic map. This can intuitively present to users the actual frequency band, network standard and corresponding coverage of each base station.

[0058] For example, in scenarios where 5G and 4G networks coexist, network configuration information such as network identifiers, network standards, frequency bands, bandwidth, power, base station latitude and longitude information, antenna azimuth angles, and antenna downtilt angles can be collected for both 4G and 5G networks. Among these, the network identifier is used to distinguish between 4G and 5G networks, and the network standards include Frequency Division Duplex (FDD) and Time Division Duplex (TDD).

[0059] For example, the network configuration information of a 5G network is shown in the table below:

[0060] The network configuration information for the 4G network is shown in the table below:

[0061] It should be noted that although current 4G and 5G networks plan and utilize multiple frequency bands to adapt to different coverage and capacity requirements, due to the influence of actual network deployment scenarios, a single base station will not deploy all frequency bands of 4G and 5G networks simultaneously. Therefore, subsequent data collection and coverage analysis need to be based on the frequency bands actually deployed by the base station. For example, suburban base stations are usually only configured with low-frequency 4G bands (such as n8) and low-frequency 5G bands (such as n28) to achieve wide-area coverage.

[0062] Based on the network configuration information of the 4G and 5G networks mentioned above, network layering structure diagrams are constructed respectively, as follows: Figure 2 , Figure 3 The diagrams shown are network layering diagrams for 5G and 4G networks provided in the embodiments of this application, respectively. They illustrate the differences in coverage between different frequency bands and different standards (TDD, FDD). Through the layered design where higher frequency bands have smaller coverage and lower frequency bands have larger coverage, the diagrams intuitively reflect the differentiated roles played by different frequency bands in the network, providing a visual basis for subsequent evaluation of network coverage performance by frequency band and precise optimization of the network.

[0063] It is understandable that linking the network hierarchical structure diagram with the geographic electronic map involves merging the network hierarchical structure diagram with the geographic electronic map according to the latitude and longitude information of the base stations. This maps the actual latitude and longitude of each base station to the same latitude and longitude coordinate point on the geographic electronic map. At the same time, the frequency band, network standard, and corresponding coverage area of ​​the base station are presented on the geographic electronic map in a differentiated form (such as color blocks of different colors corresponding to different frequency bands, frequency band labels, etc.). Ultimately, the actual frequency band, network standard, and corresponding coverage area of ​​each base station can be intuitively presented on the geographic electronic map.

[0064] In some embodiments, the network measurement data includes latitude and longitude information, and the sampling points in the network measurement data are associated with geographic rasters of a geographic electronic map according to the latitude and longitude information.

[0065] Network measurement data includes MR data, MDT data, and OTT data. OTT data refers to a type of data that automatically triggers seamless testing through the software development kit (SDK) embedded in mainstream APP software, collecting real-time user wireless network perception data. This type of data can not only collect core network signal parameters such as RSRP level and SINR value of the serving cell, but also supports the synchronous collection of network data from different operators in the same area, without the need for manual operation by the user, and the data coverage scenarios are highly consistent with the user's actual usage scenarios.

[0066] In scenarios where 5G and 4G networks coexist, 4G networks can output MR data and MDT data. Approximately 10-15% of the sampling points in 4G network MDT data carry latitude and longitude information. Due to limitations in chip technology and contractual mechanisms, 5G networks can output MR data but not MDT data.

[0067] To address this, MR data from 5G networks, MR data from 4G networks, and MDT data from 4G networks can be extracted from network measurement data. A fingerprint database can be constructed based on the 4G network MDT data, including the correlation between latitude / longitude and signal characteristics. By jointly analyzing the MR data from 4G and 5G networks, the signal characteristics in the 5G network MR data are matched with the fingerprint database to determine the latitude / longitude information of the 5G network MR data. This latitude / longitude information is then backfilled into the 5G network MR data.

[0068] In other words, to address the current lack of MDT (Measuring Report Optimized) data in 5G network systems, a technical solution can be implemented to enable 4G inter-frequency measurements using 5G network optimized measurement report (MRO) data. This involves combining MRO data from both 4G and 5G networks, and then using a fingerprint database from the 4G network to precisely locate the 5G network's MRO data. By organically integrating 5G network MRO data, 4G network MRO data, 4G network MDT data, base station location distribution, fingerprint database, and continuous multi-point data balance, accurate backfilling of 5G MRO sampling point locations can be achieved, assigning accurate latitude and longitude to the 5G MRO sampling points.

[0069] like Figure 4 The diagram illustrates the process of 5G sampling point location backfilling provided in this application embodiment. First, the cell identifiers of the primary serving cell and neighboring cells are extracted, such as the Evolved Universal Terrestrial Radio Access Network Cell Global Identifier (ECGI). Based on the base station type, signal characteristics, or other auxiliary information, it is determined whether the sampling point is indoors or outdoors, and the sampling environment, such as densely populated urban areas or ordinary urban areas.

[0070] To determine whether the primary serving cell is an urban base station, if the primary serving cell is an urban base station, a fingerprint database is established based on the MDT data of the 4G network, and joint positioning is performed by combining the MRO data of the 4G network and the 5G network.

[0071] The fingerprint database contains a large number of signal features from known geographical locations. By matching the signal features measured at the current 5G MRO sampling point with the fingerprint database, the known location with the most similar signal features is found, thereby estimating the location of the 5G MRO sampling point.

[0072] If the primary serving cell is not an urban base station, the trilateration method is used to calculate the location of the 5G MRO sampling point. Based on the distance estimates from the terminal to multiple (at least 3) known base stations, the terminal location is determined by geometric calculation of the intersection point, thereby determining the location of the 5G MRO sampling point.

[0073] Since the terminal is mobile, joint calculations and analyses can be performed using continuous sampling points. Abnormal data, such as erroneous positioning caused by signal jumps, can be identified and eliminated based on patterns such as trajectory consistency. Because the sampling point positions should change continuously, this logic can also be used to perform corrections using continuous location points.

[0074] Finally, the corrected location information is backfilled into the 5G MRO sampling points, giving them accurate latitude and longitude. The final output is the 5G MRO sampling points with geographical location, thus realizing the accurate presentation of 5G sampling points on the geographic electronic map and providing a data foundation for subsequent coverage analysis.

[0075] In this embodiment, since the 5G network cannot output MDT data with latitude and longitude, the MDT data of the 4G network is used as a reference. Combined with the MRO data of the 5G and 4G networks, the MRO data of the 5G network is given an accurate location through algorithm correction and fingerprint database matching, so that the 5G sampling point can also be accurately located on the geographic electronic map.

[0076] In some embodiments, the step of associating sampling points of network measurement data with a set of geographic rasters in a geographic electronic map can be performed by iterating through the sampling points of the network measurement data. If the latitude and longitude of a sampling point are within the latitude and longitude range of a target geographic raster in the set of geographic rasters, the sampling point is filled into the target geographic raster. That is, latitude and longitude information matching is performed; if the latitude and longitude of a sampling point are within the latitude and longitude range of a geographic raster, then the sampling point is filled into that geographic raster.

[0077] In some embodiments, after associating sampling points carrying latitude and longitude information with a set of geographic rasters of a geographic electronic map, the set of geographic rasters can be sorted out, all sampling points in each geographic raster can be summarized and analyzed, and the differences in network coverage indicators between the first network and the second network within the target area can be calculated and output.

[0078] The differences in network coverage indicators include differences in average signal strength, differences in the coverage rate of high-quality signals, and differences in the size of the area covered by high-quality signals.

[0079] For example, in a competitor analysis scenario, the first network is the mobile communication network built and operated by the operator itself, i.e., the "own network". The second network is the mobile communication network built and operated by other operators, i.e., the competitor.

[0080] Divide the GIS electronic map into 50×50 geographic grids. Associate sampling points carrying latitude and longitude information with the geographic grids of the GIS electronic map, and populate the geographic grids with sampling points within the latitude and longitude range of the geographic grids. Then, perform data processing on the geographic grids, summarize and analyze all sampling points in each geographic grid, and output the network coverage index differences in the following data format:

[0081] In the above formulas, signal strength is measured based on RSRP values. Sum(RSRP) represents the sum of the RSRP values ​​of all sampling points within a geographic raster. Sum(RSRP>-110) represents the number of sampling points in the target area with an RSRP value > -110 dBm. num1 represents the total number of sampling points in the geographic raster. num2 represents the total number of sampling points in the target area. Count(Local Raster RSRP>Competing Raster RSRP) represents the total number of rasters in the network whose average RSRP is greater than the average RSRP of competing rasters. Count(Competing Raster RSRP>Local Raster RSRP) represents the total number of rasters in the network whose average RSRP is greater than the average RSRP of competing rasters. Dbscan (Competitor Raster Better Than Local Raster) refers to using a density-based spatial clustering of applications with noise (Dbscan) algorithm to aggregate geographic rasters with a mean RSRP of competitor rasters greater than the mean RSRP of local rasters into contiguous areas, and then counting the number of such contiguous areas.

[0082] The network's average RSRP refers to the average RSRP of all sampling points within a specific geographic grid. The competitor's average RSRP refers to the average RSRP of all sampling points within a specific geographic grid. Both reflect differences in average signal strength. The network's good sampling point coverage rate refers to the percentage of sampling points in the target area with an RSRP > -110dBm. The competitor's good sampling point coverage rate refers to the percentage of sampling points in the target area with an RSRP > -110dBm. Both reflect differences in high-quality signal coverage. The number of grids with better RSRP than competitors refers to the number of grids in all geographic grids where the network's average RSRP is greater than the competitor's average RSRP. The number of grids with better RSRP than competitors refers to the number of grids in all geographic grids where the competitor's average RSRP is greater than the network's average RSRP. The number of clustered regions where the competitor's RSRP is better than that of the local grid refers to the number of contiguous regions formed by clustering geographical grids with a competitor's RSRP mean greater than that of the local grid using a clustering algorithm. All three can be used to reflect the differences in the scale of high-quality signal coverage areas.

[0083] In some embodiments, in order to facilitate the analysis of network coverage performance statistics for different frequency bands, the sampling point information in the geographic grid can be presented in layers according to different frequency bands. That is, based on the network layering structure diagram, the weak coverage grids of the target area under the target frequency band can be determined in the geographic grid set, so as to present the weak coverage grids under the target frequency band in the geographic electronic map. The target frequency band is one of all network frequency bands.

[0084] In some embodiments, the determination of a weak coverage grid can be made by traversing the geographic grids in the geographic grid set, determining the signal strength and signal quality of the sampling points in the geographic grid, and determining the geographic grid as a weak coverage grid if the signal strength of all sampling points in the geographic grid is less than the signal strength threshold and the signal quality of all sampling points in the geographic grid is less than the signal quality threshold.

[0085] For example, this application establishes a network robustness coverage performance evaluation system that can accurately reflect the user's real perception. First, it sets the criteria for judging weak coverage grids, and then achieves multi-dimensional measurement of network robustness through frequency band statistics and evaluation.

[0086] To accurately identify weak coverage grids, signal strength can be measured based on RSRP values ​​and signal quality can be measured based on SINR values. Referring to edge coverage scenarios of 4G and 5G networks, the criteria for determining weak coverage grids are set as follows, based on signal strength and signal quality:

[0087] ； ； in, Indicates the signal strength threshold. This represents the signal quality threshold. If either the RSRP value or SINR value of any sampling point (x, y) in a geographic raster is lower than the corresponding threshold, then the geographic raster is determined to be a weakly covered raster.

[0088] In some embodiments, in order to accurately evaluate network coverage performance, weak coverage grids of the target area in different frequency bands can be determined in the geographic grid set according to the network hierarchical topology diagram, and the network weak coverage index can be calculated and output, thereby providing a global decision basis for network optimization.

[0089] Among them, the network weak coverage index includes single-band weak coverage rate and comprehensive band weak coverage rate. The single-band weak coverage rate is the ratio of the number of weak coverage rasters to the total number of geographic rasters in a single frequency band. The comprehensive band weak coverage rate is the sum of the products of the single-band weak coverage rate and the frequency band weight factor in all frequency bands.

[0090] For example, to thoroughly evaluate the network coverage performance of different frequency bands, for a specific frequency band... The formula for calculating the weak coverage rate of a single frequency band is as follows: ; in, Indicates weak coverage in a single frequency band. Indicates frequency band The number of weak coverage graticles below, Indicates frequency band The total number of geographic grids.

[0091] To reflect the differentiated impact of different frequency bands on network robustness in multi-band networking, a frequency band weighting factor is introduced. The formula for calculating the weak coverage rate of the comprehensive frequency band is as follows: ; in, Indicates the overall weak coverage rate of frequency bands. The frequency band weighting factor can be configured according to the characteristics of the frequency band. For example, to emphasize the basic guarantee role of low frequency bands (such as 700MHz) in wide-area coverage, the frequency band weighting factor can be set to be inversely proportional to the frequency band.

[0092] In some embodiments, weak coverage grids under the target frequency band can be clustered to determine weak coverage areas, wherein a weak coverage area includes at least two adjacent weak coverage grids.

[0093] For example, based on the network layering structure diagram, the coverage performance statistics of different frequency bands are analyzed. Taking the frequency bands used by 4G networks as an example, weak coverage areas of each frequency band are clustered in a certain physical area, resulting in 167 weak coverage areas. The specific distribution of weak coverage areas for each frequency band is as follows: Band n41 (2600MHz), also known as the D band, includes 13 weak coverage areas; Band n39 (1880MHz), also known as the F band, includes 28 weak coverage areas; Frequency band n8 (900MHz) includes 122 weak coverage areas; Frequency band n3 (1800MHz) includes 3 weak coverage areas; Band n40 (2300MHz), also known as the E band, includes one weak coverage area.

[0094] Since some geographic rasters correspond to a small number of sampling points, in order to avoid large deviations in individual data due to signal instability and to ensure the accuracy of raster coverage, geographic rasters can be filtered. The sampling points in all geographic rasters can be counted, and weak coverage rasters with ≥20 sampling points and an RSRP mean <-110dBm can be clustered. Clustering rules can be set to set at least 2 adjacent weak coverage rasters to form an independent weak coverage area.

[0095] For example, regarding the clustering of weak coverage areas in the F band, there are a total of 28 weak coverage areas in the F band of the 4G network in a certain physical area, such as... Figure 5 The image shows a schematic diagram of one of the weakly covered areas on a GIS electronic map. This weakly covered area comprises eight weakly covered graticles, as shown in the table below:

[0096] The following table shows the 4G cells and sample points included in this weak coverage area:

[0097] For weak coverage areas in the FDD standard and 900MHz band, clustering was performed. In a certain physical area, there were 122 weak coverage areas in the 4G network using the FDD standard and 900MHz band. Figure 6 The image shows a schematic diagram of one of the weakly covered areas on a GIS electronic map. This weakly covered area comprises five weakly covered grids, as shown in the table below:

[0098] The following table shows the 4G cells and sample points included in this weak coverage area:

[0099] By employing the aforementioned frequency-band and gridded clustering analysis methods, weak coverage areas in different frequency bands can be accurately located, and their geographical distribution, signal quality, and associated cell information can be clearly presented. This overcomes the limitations of traditional cell-level statistics and provides a reliable data foundation for achieving precise network optimization. For other frequency bands of 4G networks and different frequency bands of 5G networks, the same hierarchical frequency-band analysis can be performed, and will not be listed here.

[0100] In some embodiments, the evaluation of network coverage performance of a target area under different frequency bands can be based on the weak coverage grid set and weak coverage area obtained in the above embodiments, and a multi-dimensional threshold judgment can be used to achieve an accurate evaluation of network coverage performance.

[0101] The number of weak coverage grids in the target area under the target frequency band, the number of sampling points in the weak coverage grids, and the number of weak coverage grids in the weak coverage area can be counted. If the number of weak coverage grids in the target area is less than the first number, the number of sampling points in the weak coverage grids is greater than the second number, and the number of weak coverage grids in the weak coverage area is greater than the third number, it is determined that the network coverage performance of the target area under the target frequency band is insufficient.

[0102] The first, second, and third quantities can be set based on actual needs.

[0103] For example, the first quantity T0 can be set to 10, or an extreme case can be considered where the first quantity T0 is set to 0, meaning that even a single weakly covered raster needs to be considered.

[0104] The number of sampling points in a weakly covered raster refers to the number of sampling points filled into that weakly covered raster. The data source can be MR data, MDT data, or OTT data, and the second number can be set to 20.

[0105] A weak coverage area refers to a region where weak coverage rasters cluster together. This means that after weak coverage rasters are displayed on a GIS electronic map, some weak coverage rasters may group together, forming a weak coverage area. The third quantity can be set to 2; that is, if there are more than two adjacent weak coverage rasters, it constitutes a problem of insufficient network coverage performance.

[0106] In a GIS electronic map, each geographic raster is identified according to its row and column coordinates. For any weak cover... Its adjacent weakly covered grid cells can be defined as: weakly covered Weak coverage Weak coverage Weak coverage .

[0107] By traversing all weakly covered rasters and checking whether they satisfy the adjacency condition, discrete weakly covered rasters are aggregated into continuous regions, i.e., weakly covered regions, such as... Figure 7 As shown, 10 adjacent weak coverage grids in the frame can form an independent weak coverage area.

[0108] Based on the above embodiments, targeted optimization and adjustments can be made to the target areas with insufficient network coverage and their corresponding target frequency bands. The optimization measures include at least one of the following: Antenna optimization involves adjusting antenna physical parameters such as antenna height and azimuth to reduce signal obstruction, such as avoiding obstruction from tall buildings.

[0109] Beam optimization dynamically adjusts the antenna beamwidth and tilt angle (electrically adjustable downtilt) to adapt to dynamic coverage requirements.

[0110] Power optimization involves increasing the base station's transmission power while meeting radiation safety standards, thereby expanding the coverage area of ​​a single station.

[0111] Network structure optimization enhances network coverage performance by adding relays, distributed systems, and new base stations.

[0112] After optimizing and adjusting the network in the target area under the target frequency band, the network coverage performance of the target area under the target frequency band can be re-evaluated based on the network hierarchical topology diagram and geographic grid set, thereby verifying the actual effectiveness of the optimization measures.

[0113] The above embodiments provide a perception-based method for evaluating the robustness and coverage performance of mobile communication networks. This method collects network configuration information such as frequency bands, bandwidth, power, and base station latitude and longitude to construct a hierarchical network structure diagram, which is then visualized on a GIS electronic map. Furthermore, it collects network MR data, MDT data, or OTT data, associating sampling points carrying latitude and longitude information with geographic rasters on the GIS electronic map. A perception-based network robustness and coverage performance evaluation system is constructed. According to different frequency bands or frequencies of 4G and 5G networks, the sampling point information in the geographic raster is presented hierarchically. Through multi-dimensional threshold judgments, accurate evaluation of network coverage performance is achieved. This allows for targeted optimization and adjustment of target areas with insufficient network coverage performance and their corresponding target frequency bands. After optimization and adjustment, the network robustness and coverage performance can be evaluated again using the network robustness and coverage perception evaluation system.

[0114] The technical solution of this application is applicable to scenarios involving multi-band and multi-standard collaborative networking of 4G and 5G networks. By analyzing network coverage performance through frequency bands or frequency points, it can accurately identify and determine weak coverage grids and their clustered weak coverage areas that meet preset threshold conditions. This can characterize user experience and achieve perception-based network robustness assessment. Furthermore, by establishing a perception-based network robustness assessment system, and through data processing of MR data, MDT data, and OTT data, it associates MDT sampling points and OTT sampling points carrying latitude and longitude information with GIS electronic maps. Addressing the lack of native positioning data in 5G networks, the 4G fingerprint database can be used to backfill the location of 5G network MR data, thereby accurately mapping it to GIS electronic maps and achieving an accurate assessment of real user experience.

[0115] According to embodiments of this disclosure, this disclosure also provides a network coverage performance evaluation apparatus. For example... Figure 8 The diagram shown is a structural schematic of a network coverage performance evaluation device provided in a disclosed embodiment. The device includes: The acquisition module 801 is used to collect network configuration information and network measurement data.

[0116] The processing module 802 is used to construct a hierarchical network structure diagram based on network configuration information, perform rasterization processing on the geographic electronic map to obtain a set of geographic grids, and associate the network measurement data with the set of geographic grids. The hierarchical network structure diagram is used to represent the coverage range of different frequency bands in the network.

[0117] Evaluation module 803 is used to evaluate the network coverage performance of a target area in different frequency bands based on the network hierarchical topology diagram and the set of geographic grids.

[0118] In some embodiments, the processing module 802 is used to traverse the sampling points of the network measurement data. If the latitude and longitude of the sampling point are within the latitude and longitude range of the target geographic raster in the geographic raster set, the sampling point is filled into the target geographic raster.

[0119] In some embodiments, the processing module 802 is configured to determine weak coverage grids of the target area in the target frequency band in the geographic grid set according to the network hierarchical topology diagram, and to determine the weak coverage area, wherein the weak coverage area includes at least two adjacent weak coverage grids.

[0120] If the number of weak coverage grids in the target area is less than the first number, the number of sampling points in the weak coverage grids is greater than the second number, and the number of weak coverage grids in the weak coverage area is greater than the third number, then the network coverage performance of the target area in the target frequency band is determined to be insufficient.

[0121] In some embodiments, the processing module 802 is used to traverse the geographic rasters in the geographic raster set, determine the signal strength and signal quality of the sampling points in the geographic raster, and determine the geographic raster as a weak coverage raster if the signal strength of all sampling points in the geographic raster is less than the signal strength threshold and the signal quality of all sampling points in the geographic raster is less than the signal quality threshold.

[0122] In some embodiments, the evaluation module 803 is used to evaluate the network coverage performance of the target area in the target frequency band again based on the network hierarchical topology diagram and the geographic grid set after optimizing and adjusting the network of the target area in the target frequency band.

[0123] In some embodiments, the processing module 802 is configured to extract MR data from the 5G network, MR data from the 4G network, and MDT data from the 4G network from the network measurement data; construct a fingerprint database based on the MDT data from the 4G network, the fingerprint database including the correlation between latitude and longitude and signal characteristics; determine the latitude and longitude information of the 5G network MR data based on the fingerprint database and the MR data from the 4G network; and backfill the latitude and longitude information into the MR data from the 5G network.

[0124] In some embodiments, the processing module 802 is configured to calculate and output the difference in network coverage indicators between the first network and the second network within a target area based on a set of geographic grids.

[0125] The differences in network coverage indicators include differences in average signal strength, differences in the coverage rate of high-quality signals, and differences in the size of the area covered by high-quality signals.

[0126] In some embodiments, the processing module 802 is used to determine the weak coverage grids of the target area in different frequency bands in the geographic grid set according to the network hierarchical topology diagram, and calculate and output the network weak coverage index.

[0127] Among them, network weak coverage indicators include single-band weak coverage rate and comprehensive band weak coverage rate. The single-band weak coverage rate is the ratio of the number of weak coverage rasters to the total number of geographic rasters in a single frequency band. The comprehensive band weak coverage rate is the sum of the products of the single-band weak coverage rate and the frequency band weighting factor across all frequency bands.

[0128] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0129] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0130] like Figure 9 As shown, the electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 902 or a computer program loaded from storage unit 908 into RAM (Random Access Memory) 903. The RAM 903 can also store various programs and data required for the operation of the electronic device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. An I / O (Input / Output) interface 905 is also connected to bus 904.

[0131] Multiple components in electronic device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of displays, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows electronic device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0132] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as network coverage performance evaluation methods. For example, in some embodiments, the network coverage performance evaluation method can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the aforementioned network coverage performance evaluation method by any other suitable means (e.g., by means of firmware).

[0133] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), System-on-Chips (SOCs), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0134] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0135] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Erasable Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0137] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0138] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0139] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0140] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0141] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for evaluating network coverage performance, characterized in that, include: Collect network configuration information and network measurement data; Construct a hierarchical network structure diagram based on the network configuration information; The network hierarchical topology diagram is used to represent the coverage of different frequency bands in the network; The geographic electronic map is rasterized to obtain a set of geographic raster cells; Associate the network measurement data with the geographic raster set; Based on the network hierarchical topology diagram and the geographic grid set, evaluate the network coverage performance of the target area in different frequency bands.

2. The method according to claim 1, characterized in that, The step of associating the network measurement data with the geographic raster set includes: Iterate through the sampling points of the network measurement data; If the latitude and longitude of the sampling point are within the latitude and longitude range of the target geographic raster in the geographic raster set, the sampling point will be filled into the target geographic raster.

3. The method according to claim 1 or 2, characterized in that, The step of evaluating the network coverage performance of the target area in different frequency bands based on the network hierarchical topology diagram and the geographic grid set includes: Based on the network hierarchical networking structure diagram, determine the weak coverage grids of the target area in the target frequency band from the set of geographic grids; Identify weak coverage areas; the weak coverage areas include at least two adjacent weak coverage grids; If the number of weak coverage grids in the target area is less than a first number, the number of sampling points in the weak coverage grids is greater than a second number, and the number of weak coverage grids in the weak coverage area is greater than a third number, then the network coverage performance of the target area in the target frequency band is determined to be insufficient.

4. The method according to claim 3, characterized in that, Extracting weak coverage gratings of the target area in the target frequency band from the geographic raster set includes: Iterate through the geographic rasters in the set of geographic rasters; Determine the signal strength and signal quality of the sampling points in the geographic grid; If the signal strength of all sampling points in the geographic raster is less than the signal strength threshold, and the signal quality of all sampling points in the geographic raster is less than the signal quality threshold, the geographic raster is determined to be a weak coverage raster.

5. The method according to claim 3, characterized in that, The method further includes: After optimizing and adjusting the network in the target area under the target frequency band, the network coverage performance of the target area under the target frequency band is evaluated again based on the network hierarchical networking structure diagram and the geographical grid set.

6. The method according to claim 1 or 2, characterized in that, Before the step of associating the network measurement data with the geographic raster set, the method further includes: From the network measurement data, the measurement report data of the 5G network, the measurement report data of the 4G network, and the minimized drive test data of the 4G network are extracted; A fingerprint database is constructed based on the minimized drive test data of the 4G network; the fingerprint database includes the correlation between latitude and longitude and signal characteristics; Based on the fingerprint database and the measurement report data of the 4G network, determine the latitude and longitude information of the measurement report data of the 5G network; The latitude and longitude information is then backfilled into the measurement report data of the 5G network.

7. The method according to claim 1 or 2, characterized in that, After the step of associating the network measurement data with the geographic raster set, the method further includes: Based on the set of geographic grids, calculate and output the difference in network coverage indicators between the first network and the second network within the target area; the difference in network coverage indicators includes the difference in average signal strength, the difference in high-quality signal coverage rate, and the difference in the size of the high-quality signal coverage area.

8. The method according to claim 1 or 2, characterized in that, The method further includes: Based on the network hierarchical topology diagram, weak coverage grids for the target area in different frequency bands are determined in the set of geographic grids. Calculate and output network weak coverage indicators, which include single-band weak coverage rate and comprehensive band weak coverage rate; the single-band weak coverage rate is the ratio of the number of weak coverage grids to the total number of geographic grids in a single frequency band; the comprehensive band weak coverage rate is the sum of the products of the single-band weak coverage rate and the frequency band weighting factor in all frequency bands.

9. A network coverage performance evaluation device, characterized in that, include: The data acquisition module is used to collect network configuration information and network measurement data; The processing module is used to construct a network hierarchical topology diagram based on the network configuration information; The geographic electronic map is rasterized to obtain a set of geographic grids; the network measurement data is associated with the set of geographic grids; the network hierarchical networking structure diagram is used to represent the coverage of different frequency bands in the network; The evaluation module is used to evaluate the network coverage performance of the target area in different frequency bands based on the network hierarchical topology diagram and the geographic grid set.

10. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

Images