Building coverage evaluation method and device based on user perception data

Abstract

The invention provides a building coverage evaluation method and device based on user perception data, and relates to the technical field of data processing, and the method comprises the steps: obtaining building standardized map data and user perception data in a to-be-planned region; associating each piece of user perception data with the corresponding building to which the user perception data belongs, and generating a building amp; a user perception data table; and calculating an RSRP coverage mean value and a weak coverage ratio of all user perception data in each building, and determining a problem building and a corresponding indoor distribution planning scheme based on the RSRP coverage mean value and the weak coverage ratio so as to execute the corresponding indoor distribution planning scheme on the problem building according to a priority sequence. Therefore, compared with the traditional manual CQT test, the network problem area can be more accurately positioned through analysis of the user perception data, and the working efficiency is remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a building coverage assessment method and device based on user perception data. Background Art

[0002] At present, the 4 / 5G network of operators has been quite large, and there is good 4 / 5G coverage in crowded areas, key areas, and traffic roads, and the construction of 4 / 5G macro stations in urban areas has reached saturation. Therefore, improving the deep coverage of buildings will become the key task of operators at this stage. Among them, indoor CQT (Channel Quality Testing) is a test method used to evaluate the quality and performance of wireless network signals, especially in indoor environments. The existing indoor 4 / 5G network coverage evaluation of buildings mainly relies on CQT test data.

[0003] Traditional CQT testing requires a lot of manpower and material resources. According to statistics, one tester can complete CQT testing of 4-5 buildings in one day. To carry out CQT testing, it is necessary to carry test terminals of different operators to conduct 4 / 5G network testing. Moreover, CQT testing is mainly aimed at public areas of buildings, which often cannot fully reflect the actual coverage of buildings. This method with high investment cost, low work efficiency and poor evaluation accuracy can no longer meet the requirements of high-quality development of the communications industry in the 5G era. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a building coverage assessment method and device based on user perception data. By analyzing the user perception data, the network problem area can be located more accurately and the work efficiency can be significantly improved.

[0005] In a first aspect, an embodiment of the present application provides a building coverage assessment method based on user perception data, the method comprising the following steps:

[0006] Obtaining standardized building map data and user perception data in the area to be planned; the standardized building map data includes boundary information of each building, and the user perception data includes latitude and longitude information and WiFi device MAC address;

[0007] First, the acquired user perception data is matched once based on the latitude and longitude information and the boundary information to determine the building to which each piece of user perception data belongs, and each piece of user perception data is associated with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the MAC address of the WiFi device, a secondary match is performed on the user perception data that is not in the building area to determine the building to which each piece of user perception data belongs, and the building & user perception data table is updated;

[0008] The RSRP coverage mean and weak coverage ratio of all user perception data in each building are calculated, and the problem buildings and corresponding indoor distribution planning schemes are determined based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning schemes on the problem buildings in order of priority.

[0009] In some embodiments, after obtaining the standardized map data of buildings in the area to be planned and the user perception data, the following steps are also included:

[0010] The data processing function is used to clean the obtained standardized building map data and user perception data in the area to be planned, including identifying and deleting missing values, duplicate values ​​and invalid values ​​in the data.

[0011] In some embodiments, performing secondary matching on the user perception data that is not in the building area based on the cluster analysis of the MAC address of the WiFi device to determine the building to which each piece of user perception data belongs includes the following steps:

[0012] The user perception data that is not in the building area is sorted according to the WiFi device MAC address, and a binary search algorithm is used to search for the user perception data under the same WiFi device MAC address;

[0013] Setting a clustering radius and a number of clusters of a clustering algorithm, and performing cluster analysis on each WiFi device MAC according to the clustering radius and the number of clusters to obtain a cluster center of each WiFi device MAC;

[0014] The shortest distance from the cluster center to the building boundary is calculated. If the shortest distance is within a set distance threshold, the corresponding building is used as the building to which the user perception data under the MAC of the corresponding WiFi device belongs.

[0015] In some embodiments, the determining of the problem building and the corresponding indoor distribution planning scheme based on the RSRP coverage mean and the weak coverage ratio includes the following steps:

[0016] Set RSRP coverage mean threshold and weak coverage ratio threshold;

[0017] If the RSRP coverage mean is less than the RSRP coverage mean threshold, or if the weak coverage ratio is greater than the weak coverage ratio threshold, the corresponding building is determined as a problem building;

[0018] Corresponding indoor distribution planning schemes are formulated for the problem buildings respectively, so that the RSRP coverage mean is greater than or equal to the RSRP coverage mean threshold, or the weak coverage ratio is less than or equal to the weak coverage ratio threshold.

[0019] In some embodiments, the entropy weight method is used to comprehensively score various indicators in the building, and the priority order of the problem buildings is obtained according to the scores; the indicators include non-numerical indicators and numerical indicators, the non-numerical indicators include building attributes and scenarios, and the numerical indicators include at least one of the building area, number of users, RSRP average, weak coverage ratio, number of sampling points, and number of demand operators.

[0020] In some embodiments, the method of using the entropy weight method to comprehensively score various indicators in the building and obtaining the priority order of the problem buildings according to the scores includes the following steps:

[0021] Assigning a value to the non-numerical indicator according to a preset assignment standard, and normalizing the numerical indicator and the non-numerical indicator after the assignment;

[0022] Calculate the weight of each problematic building under each indicator according to the normalized indicator value, and calculate the information entropy of each indicator according to the weight;

[0023] Calculating the weight of each indicator according to the information entropy, and calculating the comprehensive score of each building according to the weight;

[0024] The comprehensive scores are sorted from high to low, and the sorting is used as the priority order of the problem buildings.

[0025] In some embodiments, the number of required operators is obtained by integrating the problem buildings by category of network operators.

[0026] In a second aspect, an embodiment of the present application provides a building coverage assessment device based on user perception data, the device comprising:

[0027] An acquisition module, used to acquire standardized map data and user perception data of buildings in the area to be planned; the standardized map data of buildings includes boundary information of each building, and the user perception data includes latitude and longitude information and MAC address of WiFi devices;

[0028] The data processing module is used to first match the acquired user perception data based on the latitude and longitude information and the boundary information, determine the building to which each piece of user perception data belongs, and associate each piece of user perception data with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the MAC address of the WiFi device, perform a secondary match on the user perception data that is not in the building area, determine the building to which each piece of user perception data belongs, and update the building & user perception data table;

[0029] An evaluation module is used to calculate the RSRP coverage mean and weak coverage ratio of all user perception data in each building, and determine the problem buildings and corresponding indoor distribution planning schemes based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning schemes on the problem buildings in order of priority.

[0030] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the building coverage assessment method based on user perception data as described in any one of the first aspects are performed.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the building coverage assessment method based on user perception data described in any one of the first aspects above are executed.

[0032] The present application discloses a method and device for evaluating building coverage based on user perception data, which obtains standardized building map data and user perception data in a planned area; the standardized building map data includes boundary information of each building, and the user perception data includes latitude and longitude information and a MAC address of a WiFi device; firstly, the obtained user perception data is matched once based on the latitude and longitude information and the boundary information to determine the building to which each piece of user perception data belongs, and each piece of user perception data is associated with its corresponding building to generate a building & user perception data table; then, based on a cluster analysis of the MAC address of the WiFi device, a secondary match is performed on the user perception data that is not in the building area to determine the building to which each piece of user perception data belongs, and the building & user perception data table is updated; the RSRP coverage mean and weak coverage ratio of all user perception data in each building are calculated, and the problem building and the corresponding indoor distribution planning scheme are determined based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning scheme on the problem building in order of priority. Therefore, compared with traditional manual CQT testing, the analysis of user perception data can more accurately locate network problem areas and significantly improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1 A flowchart of a building coverage assessment method based on user perception data according to an embodiment of the present application is shown;

[0035] Figure 2 A schematic diagram of a boundary layer in building boundary information according to an embodiment of the present application is shown;

[0036] Figure 3 A flowchart is shown of performing secondary matching on user perception data that is not in a building area based on cluster analysis of the MAC address of the WiFi device according to an embodiment of the present application to determine the building to which each piece of user perception data belongs;

[0037] Figure 4 A flowchart of using the entropy weight method to comprehensively score various indicators in a building and obtain the priority order of problem buildings according to the scores is shown in an embodiment of the present application;

[0038] Figure 5 A schematic diagram of the structure of a building coverage assessment device based on user perception data according to an embodiment of the present application is shown;

[0039] Figure 6 A structural block diagram of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0041] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0042] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0043] In view of the technical problems raised by the background technology, the present application provides a building coverage assessment method and device based on user perception data. By analyzing the user perception data, the network problem area can be located more accurately and the work efficiency can be significantly improved.

[0044] See the instruction manual Figure 1 , a building coverage assessment method based on user perception data provided by an embodiment of the present application includes the following steps:

[0045] S1. Obtaining standardized building map data and user perception data in the area to be planned; the standardized building map data includes boundary information of each building, and the user perception data includes latitude and longitude information and a WiFi device MAC address;

[0046] S2. First, based on the latitude and longitude information and the boundary information, the acquired user perception data is matched once to determine the building to which each piece of user perception data belongs, and each piece of user perception data is associated with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the MAC address of the WiFi device, a second match is performed on the user perception data that is not in the building area to determine the building to which each piece of user perception data belongs, and the building & user perception data table is updated;

[0047] S3. Calculate the RSRP coverage mean and weak coverage ratio of all user perception data in each building, and determine the problem buildings and the corresponding indoor distribution planning scheme based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning scheme on the problem buildings in order of priority.

[0048] Specifically, in step S1, the standardized building map data includes not only the boundary information of each building but also the basic building information, and the basic building information includes the building number, building name, building attribute, building construction area, building height, floor, longitude, latitude, address and other information; the building boundary information adopts a layer in mapinfo format, with the longitude and latitude information of each vertex, and the boundary layer can be found in the appendix of the manual. Figure 2 .

[0049] The user perception data is the network perception information when the user uses the Internet APP application, including the operator number opt_id, the operator name opt_name, the dynamic network type dynamic_network_type, the cell identifier cell_id, the base station number enodeb, the physical cell identifier pci, the evolved absolute radio frequency channel number earfcn, the reference signal received power rsrp, the signal to interference plus noise ratio sinr, the device identifier did, the device brand brand, the WiFi name wifi_name, the MAC address of the WiFi device wifi_mac, the WiFi signal strength wifi_strength, the longitude longitude, the latitude latitude, the geographic location source geo_from and other information.

[0050] Furthermore, the acquired standardized building map data and the user-perceived data are also cleaned to identify and delete missing values, duplicate values, and invalid values ​​in the data, thereby ensuring the accuracy and consistency of the data and providing a reliable basis for subsequent analysis and clustering operations. In one embodiment, fields such as opt_name, dynamic_network_type, did, wifi_mac, longitude, latitude, rsrp, etc. in the user-perceived data are used as key fields for data cleaning; building number, building name, building scene, building area, floor, building height, etc. in the standardized building data are used as key fields for data cleaning, and the situation where there are missing values, duplicate values, and invalid values ​​in the above key fields is processed. Among them, data cleaning can use the df.dropna() function, which is a function in Pandas for deleting rows or columns containing missing values ​​(NaN or None), which can flexibly delete missing values ​​in the data according to different parameter settings.

[0051] In step S2, the user perception data is mainly matched with the standardized building data to classify the user perception data according to the building, provide support for building network evaluation and planning, and help optimize the network layout and improve the user experience.

[0052] Specifically, firstly, a match is made based on the longitude and latitude information in the user perception data and the building boundary information in the building standardized map data to determine whether each piece of user perception data is located in a certain building. In one embodiment, the shapely library of python is used for discrimination, and the polygonal area Qi of each building is created according to the building number and vertex coordinate information of the standardized building data; a point Gi is defined according to the longitude and latitude information of each piece of user perception data, and in shapely, the Gi point is represented by the point class; and the polygon.contains() function method is used to determine whether the point is within the polygonal area Qi. Then, each building is associated with the user perception data point information in its area to generate a building & user perception data table, which contains the building number, name, and the rsrp, enodeb, wifi_mac and other information of the user perception data point associated with it.

[0053] Since there is a certain error range in the longitude and latitude information, the perception data generated in some buildings may have longitude and latitude information falling around the building. Therefore, after a match is performed once through the above steps, a second match is required for the perception data of users who are not in the building area.

[0054] See the instruction manual Figure 3 , performing secondary matching on user perception data that is not in the building area based on cluster analysis of the MAC address of the WiFi device, and determining the building to which each piece of user perception data belongs, including the following steps:

[0055] S201, sorting the user perception data that is not in the building area according to the WiFi device MAC address, and using a binary search algorithm to search for user perception data under the same WiFi device MAC address,

[0056] S202, setting a clustering radius and a number of clusters of a clustering algorithm, and performing cluster analysis on each WiFi device MAC according to the clustering radius and the number of clusters to obtain a cluster center of each WiFi device MAC;

[0057] S203, calculating the shortest distance from the cluster center to the building boundary, and if the shortest distance is within a set distance threshold, taking the corresponding building as the building to which the user perception data under the MAC of the corresponding WiFi device belongs.

[0058] In step S201, the secondary matching between user perception data and buildings is mainly based on the wifi_mac field information of the WiFi device MAC address, because in actual scenarios, a specific wifi_mac is usually associated with a specific building or area. According to the wifi_mac information in the user perception data, the user perception data that is not in the building area is sorted in ascending order to optimize the execution efficiency and result accuracy of the post-order clustering analysis algorithm.

[0059] Since the amount of user perception data is huge, reaching tens of millions or more, the efficiency of relying on traditional loop analysis methods is too low. The binary search algorithm is usually used to find specific elements when processing large-scale data sets. Therefore, in this application, the query or screening operation of user perception data is accelerated by the binary search algorithm. In one embodiment, a binary search algorithm is combined with a recursive method to search for user perception data under the same wifi_mac by continuously halving the search range, and then find the user perception data under the same wifi_mac, and generate the data list required for clustering. The list is datasets = [dataset1, dataset2, ..., dataset m ], where m is the number of different wifi_mac, dataset i =[[lng1,lat1],[lng2,lat2],...,[lng n ,lat n ]](i∈[1,2,...,m]), where n is the number of users under the same wifi_mac.

[0060] In step S202, the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is used to perform cluster analysis on the user perception data. Among them, the cluster radius eps and the number of clusters minpts are two key parameters of the DBSCAN clustering algorithm. EPS is defined as the neighborhood radius of a point, and minpts is defined as the minimum number of points required to form a dense area. Due to different scenarios, the distribution characteristics of user perception data are different from actual needs. This application uses visualization tools (such as scatter plots) to observe the distribution of data, thereby selecting appropriate eps and minpts values, and using cross-validation methods to evaluate the clustering effects under different parameter combinations, and select the optimal parameter combination, which helps to improve the quality and reliability of the clustering results. For example, in the experimental data of this algorithm flow, eps is set to 30 meters and minpts is set to 100.

[0061] Then, according to the set eps and minpts parameters, cluster analysis is performed on the user perception data under each wifi_mac. After clustering, the information of the cluster center point of each wifi_mac is organized into a cluster center data table for subsequent analysis and reference. The cluster center data table contains information such as wifi_mac of user perception data and the longitude and latitude coordinates of the cluster center. Among them, obtaining the cluster center of each wifi_mac through a clustering algorithm should be a technical means well known in the art and will not be repeated here.

[0062] In step S203, the cluster center points of different wifi_macs are matched with the standardized building data to determine whether the cluster center of each wifi_mac is located in a certain building.

[0063] Among them, if the number of cluster centers is 1 and the cluster center is judged to be located in the building area, the corresponding building will be associated with the user perception data point information under wifi_mac, and the building & user perception data table will be updated; if the number of cluster centers is greater than 1 and it is judged that a cluster center is located in the building area, the corresponding building will be associated with the user perception data point information under wifi_mac, and the building & user perception data table will be updated; if it is judged that a cluster center is located outside the building area, the distance from the cluster center point to the boundary of the surrounding buildings under the same wifi_mac is calculated in turn. If the distance threshold Distance is met and the distance to the boundary of a certain building is the shortest, the corresponding building will be associated with the user perception data point information under the wifi_mac, and the building & user perception data table will be updated.

[0064] In step S3, there are two dimensions for judging the problem area of ​​the building 4 / 5G network, one is the mean RSRP coverage, and the other is the proportion of weak coverage. The mean RSRP coverage is to evaluate the RSRP coverage of the sampling points of the 4 / 5G networks of different operators in the building, which is the average RSRP value of all sampling points; the weak coverage proportion is to evaluate the proportion of sampling points of the 4 / 5G networks of different operators in the building with RSRP < a specific value to the total sampling points.

[0065] When the RSRP coverage mean is less than K1, it is defined as the RSRP mean difference problem area, where K1 is the RSRP coverage mean threshold. For example, set K1 to -105dBm. When the RSRP coverage mean of a certain operator's 4G or 5G network is less than -105dBm, it is defined as the coverage mean problem area. If a certain building X1-YD4G=-108.25dBm<K1(-105dBm), then the building is the operator A4G coverage mean difference problem area. When the weak coverage ratio is greater than K2, it is defined as the weak coverage ratio difference problem area, where K2 is the weak coverage ratio threshold. For example, set K2 to 30%. It should be noted that different network operators may have different settings for the RSRP coverage mean threshold K1 and the weak coverage ratio threshold K2.

[0066] Then, the buildings corresponding to the problem areas that meet the problem of the average RSRP value of the building 4 / 5G network are selected, and a planning scheme based on the RSRP average is output for the building; and the buildings corresponding to the problem areas that meet the problem of the weak coverage ratio of the building 4 / 5G network are selected, and a planning scheme based on the weak coverage ratio is output for the building.

[0067] In addition, in this application, problem buildings are processed in order of priority. Among them, the entropy weight method can be used to comprehensively score various indicators in the building, and the priority order of the problem buildings can be obtained according to the score; the indicators include non-numerical indicators and numerical indicators, the non-numerical indicators include building attributes and scenarios, and the numerical indicators include at least one of the building area, number of users, RSRP mean, weak coverage ratio, number of sampling points, and number of demand operators.

[0068] In one embodiment, see the attached specification Figure 4 The method of using the entropy weight method to comprehensively score each indicator in the building and obtain the priority order of the problem buildings according to the scores includes the following steps:

[0069] S301, assigning values ​​to the non-numerical indicators according to a preset assignment standard, and normalizing the numerical indicators and the assigned non-numerical indicators;

[0070] S302, calculating the weight of each problematic building under each indicator according to the normalized indicator value, and calculating the information entropy of each indicator according to the weight;

[0071] S303, calculating the weight of each indicator according to the information entropy, and calculating the comprehensive score of each building according to the weight;

[0072] S304: sort the comprehensive scores from high to low, and use the sorting as the priority order of the problem buildings.

[0073] In step S301, when assigning values ​​to building attributes, refer to Table 1, and when assigning values ​​to scenes, refer to Table 2.

[0074]

[0075]

[0076] Table 1

[0077] Scenario Assignment Key scenes 100 Dense urban area 87.5 General urban area 75 suburbs 62.5 county seat 50 Township 37.5 Rural 25 Remote areas 12.5

[0078] Table 2

[0079] Among them, the building area is obtained from the basic information of the building; the number of users includes the number of mobile network users and the number of fixed network users, the number of mobile network users is the total number of mobile network users of a certain network of a certain operator in the building, and the number of fixed network users is the total number of fixed network users of a certain network of a certain operator in the building; the RSRP mean value and the weak coverage ratio are as mentioned above; the number of sampling points is the number of all sampling points of a certain network of a certain operator in a certain building; the number of demand operators is obtained by integrating the problem buildings by the category of network operators, which can be seen in Table 3.

[0080]

[0081] Table 3

[0082] Among them, "there is demand" means that the RSRP average and / or the weak coverage ratio do not meet the requirements, and an indoor distribution planning scheme needs to be formulated for the building. Finally, the number of operator networks required for the building is output based on the six dimensions of the three operators A, B, and C operating 4 / 5G networks. The overall number of operator networks required is: 0, 1, 2, 3, 4, 5, 6, etc. The more the number required, the more serious the coverage problem of the building.

[0083] When normalizing the numerical index and the non-numerical index after the assignment, the following formula may be used:

[0084]

[0085] Among them, x ij is the value of the i-th building at the j-th index; x min(j) is the minimum value of the jth index; x max(j) is the maximum value of the jth indicator, and then all the eight-dimensional indicator values ​​of all buildings (building attributes, scenarios, building area, number of users, RSRP mean, weak coverage ratio, number of sampling points, and number of demand operators) are normalized to the [0,1] interval.

[0086] In step S302, the weight of each problematic building under each indicator is calculated according to the following formula:

[0087]

[0088] Among them, p ij is the weight of the i-th sample under the j-th indicator.

[0089] The information entropy of each indicator can be calculated according to the following formula:

[0090]

[0091] Among them, e j is the information entropy of the jth indicator, is a constant, the user standardized entropy value, n is the number of samples, when p ij = 0, define p ij ln(p ij )=0.

[0092] In step S303, the weight of each indicator is calculated according to the following formula:

[0093]

[0094] Among them, w j is the weight of the jth indicator, m is the number of indicators, and this application has 8 dimensional indicators.

[0095] The comprehensive score of each building can be calculated according to the following formula:

[0096]

[0097] Among them, S i is the comprehensive score of the i-th sample, r ij is the normalized value of the i-th sample under the j-th index.

[0098] In step S304, the obtained comprehensive scores are sorted in order from high to low, and the sorting is the priority order for executing the corresponding indoor distribution planning scheme for the problem building.

[0099] It can be seen that the building coverage assessment method based on user perception data provided in this application only needs to use user perception data and through corresponding data analysis, the 4 / 5G network assessment results and indoor distribution planning scheme of the building can be obtained. It has low manpower costs and is extremely efficient compared to traditional manual CQT testing. The data used is close to real user perception, and the positioning of network problem areas is more accurate.

[0100] Based on the same inventive concept, an embodiment of the present application also provides a building coverage assessment device based on user perception data. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned building coverage assessment method and device based on user perception data in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0101] As the instruction manual Figure 5 As shown, the present application also provides a building coverage assessment device based on user perception data, the device comprising:

[0102] The acquisition module 501 is used to acquire standardized map data and user perception data of buildings in the area to be planned; the standardized map data of buildings includes boundary information of each building, and the user perception data includes latitude and longitude information and MAC address of WiFi devices;

[0103] The data processing module 502 is used to first match the acquired user perception data based on the latitude and longitude information and the boundary information, determine the building to which each piece of user perception data belongs, and associate each piece of user perception data with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the MAC address of the WiFi device, perform a secondary match on the user perception data that is not in the building area, determine the building to which each piece of user perception data belongs, and update the building & user perception data table;

[0104] The evaluation module 503 is used to calculate the RSRP coverage mean and weak coverage ratio of all user perception data in each building, and determine the problem buildings and the corresponding indoor distribution planning scheme based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning scheme on the problem buildings in order of priority.

[0105] In some embodiments, after the acquisition module 501 acquires the standardized map data of buildings and user perception data in the area to be planned, it also includes: using a data processing function to clean the acquired standardized map data of buildings and user perception data in the area to be planned, including identifying and deleting missing values, duplicate values ​​and invalid values ​​in the data.

[0106] In some embodiments, the data processing module 502 performs secondary matching on user perception data that is not in the building area based on the cluster analysis of the WiFi device MAC address to determine the building to which each piece of user perception data belongs, including: sorting the user perception data that is not in the building area according to the WiFi device MAC address, and using a binary search algorithm to find user perception data under the same WiFi device MAC address, setting a clustering radius and a number of clusters of the clustering algorithm, and performing cluster analysis on each WiFi device MAC according to the clustering radius and the number of clusters to obtain a cluster center of each WiFi device MAC; calculating the shortest distance from the cluster center to the building boundary, and if the shortest distance is within a set distance threshold, taking the corresponding building as the building to which the user perception data under the corresponding WiFi device MAC belongs.

[0107] In some embodiments, the evaluation module 503 determines the problem building and the corresponding indoor distribution planning scheme based on the RSRP coverage mean and the weak coverage ratio, including: setting an RSRP coverage mean threshold and a weak coverage ratio threshold; if the RSRP coverage mean is less than the RSRP coverage mean threshold, or if the weak coverage ratio is less than the weak coverage ratio threshold, the corresponding building is determined as a problem building; and corresponding indoor distribution planning schemes are formulated for the problem buildings, so that the RSRP coverage mean is greater than or equal to the RSRP coverage mean threshold, or the weak coverage ratio is greater than or equal to the weak coverage ratio threshold.

[0108] In some embodiments, the evaluation module 503 uses the entropy weight method to comprehensively score various indicators in the building, and obtains the priority order of the problem buildings according to the scores; the indicators include non-numerical indicators and numerical indicators, the non-numerical indicators include building attributes and scenarios, and the numerical indicators include building area, number of users, RSRP average, weak coverage ratio, number of sampling points, and at least one of the number of demand operators; the number of demand operators is obtained by integrating the problem buildings through the category of network operators.

[0109] In some embodiments, the evaluation module 503 uses the entropy weight method to comprehensively score each indicator in the building, and obtains the priority order of the problem buildings according to the score, including: assigning values ​​to the non-numerical indicators according to a pre-set assignment standard, and normalizing the numerical indicators and the assigned non-numerical indicators; calculating the proportion of each problem building under each indicator according to the normalized indicator value, and calculating the information entropy of each indicator according to the proportion; calculating the weight of each indicator according to the information entropy, and calculating the comprehensive score of each building according to the weight; sorting the comprehensive scores in order from high to low, and using the sorting as the priority order of the problem buildings.

[0110] The present application provides a building coverage evaluation device based on user perception data, which obtains standardized building map data and user perception data in a planned area through an acquisition module; the standardized building map data includes boundary information of each building, and the user perception data includes latitude and longitude information and a WiFi device MAC address; the data processing module first matches the acquired user perception data based on the latitude and longitude information and the boundary information, determines the building to which each piece of user perception data belongs, and associates each piece of user perception data with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the WiFi device MAC address, a secondary match is performed on the user perception data that is not in the building area, determines the building to which each piece of user perception data belongs, and updates the building & user perception data table; the evaluation module calculates the RSRP coverage mean and weak coverage ratio of all user perception data in each building, and determines the problem building and the corresponding indoor distribution planning scheme based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning scheme on the problem building in priority order. Therefore, compared with traditional manual CQT testing, the analysis of user perception data can more accurately locate network problem areas and significantly improve work efficiency.

[0111] Based on the same concept of the present invention, the specification is attached Figure 6 As shown, the structure of an electronic device 600 provided in an embodiment of the present application includes: at least one processor 601, at least one network interface 604 or other user interface 603, a memory 605, and at least one communication bus 602. The communication bus 602 is used to realize the connection and communication between these components. The electronic device 600 optionally includes a user interface 603, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, a trackball (trackball), a touch pad or a touch screen, etc.).

[0112] The memory 605 may include a read-only memory and a random access memory, and provides instructions and data to the processor 601. A portion of the memory 605 may also include a non-volatile random access memory (NVRAM).

[0113] In some embodiments, the memory 605 stores the following elements, which may be protected modules or data structures, or a subset thereof, or an extended set thereof:

[0114] Operating system 6051, including various system programs for implementing various basic services and processing hardware-based tasks;

[0115] The application module 6052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0116] In an embodiment of the present application, by calling the program or instructions stored in the memory 605, the processor 601 is used to execute steps in a building coverage assessment method and device based on user perception data. By analyzing the user perception data, the network problem area can be located more accurately and work efficiency can be significantly improved.

[0117] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the building coverage assessment method based on user perception data are executed.

[0118] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned building coverage assessment method based on user perception data can be executed.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, 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 communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in the embodiments provided in the present application 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.

[0122] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0123] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A building coverage assessment method based on user perception data, characterized in that: The method comprises the following steps: Obtaining standardized building map data and user perception data in the area to be planned; the standardized building map data includes boundary information of each building, and the user perception data includes latitude and longitude information and WiFi device MAC address; First, the acquired user perception data is matched once based on the latitude and longitude information and the boundary information to determine the building to which each piece of user perception data belongs, and each piece of user perception data is associated with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the MAC address of the WiFi device, a secondary match is performed on the user perception data that is not in the building area to determine the building to which each piece of user perception data belongs, and the building & user perception data table is updated; The RSRP coverage mean and weak coverage ratio of all user perception data in each building are calculated, and the problem buildings and corresponding indoor distribution planning schemes are determined based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning schemes on the problem buildings in order of priority.

2. A building coverage assessment method based on user perception data according to claim 1, characterized in that: After obtaining the standardized map data of buildings in the area to be planned and the user perception data, the following steps are also included: The data processing function is used to clean the obtained standardized building map data and user perception data in the area to be planned, including identifying and deleting missing values, duplicate values ​​and invalid values ​​in the data.

3. A building coverage assessment method based on user perception data according to claim 2, characterized in that: The second matching of the user perception data not in the building area based on the cluster analysis of the MAC address of the WiFi device to determine the building to which each piece of user perception data belongs includes the following steps: The user perception data that is not in the building area is sorted according to the WiFi device MAC address, and a binary search algorithm is used to search for the user perception data under the same WiFi device MAC address; Setting a clustering radius and a number of clusters of a clustering algorithm, and performing cluster analysis on each WiFi device MAC according to the clustering radius and the number of clusters to obtain a cluster center of each WiFi device MAC; The shortest distance from the cluster center to the building boundary is calculated. If the shortest distance is within a set distance threshold, the corresponding building is used as the building to which the user perception data under the MAC of the corresponding WiFi device belongs.

4. The building coverage assessment method based on user perception data according to claim 3 is characterized in that: The method of determining the problem building and the corresponding indoor distribution planning scheme based on the RSRP coverage mean and the weak coverage ratio includes the following steps: Set RSRP coverage mean threshold and weak coverage ratio threshold; If the RSRP coverage mean is less than the RSRP coverage mean threshold, or if the weak coverage ratio is greater than the weak coverage ratio threshold, the corresponding building is determined as a problem building; Corresponding indoor distribution planning schemes are formulated for the problem buildings respectively, so that the RSRP coverage mean is greater than or equal to the RSRP coverage mean threshold, or the weak coverage ratio is less than or equal to the weak coverage ratio threshold.

5. A building coverage assessment method based on user perception data according to claim 4, characterized in that: in, The entropy weight method is used to comprehensively score various indicators in the building, and the priority order of the problem buildings is obtained according to the scores; the indicators include non-numerical indicators and numerical indicators, the non-numerical indicators include building attributes and scenarios, and the numerical indicators include at least one of the building area, number of users, RSRP mean, weak coverage ratio, number of sampling points, and number of required operator networks.

6. The building coverage assessment method based on user perception data according to claim 5, characterized in that: The method of using the entropy weight method to comprehensively score each indicator in the building and obtain the priority order of the problem buildings according to the scores includes the following steps: Assigning a value to the non-numerical indicator according to a preset assignment standard, and normalizing the numerical indicator and the non-numerical indicator after the assignment; Calculate the weight of each problematic building under each indicator according to the normalized indicator value, and calculate the information entropy of each indicator according to the weight; Calculating the weight of each indicator according to the information entropy, and calculating the comprehensive score of each building according to the weight; The comprehensive scores are sorted from high to low, and the sorting is used as the priority order of the problem buildings.

7. A building coverage assessment method based on user perception data according to claim 6, wherein: The number of required operators is obtained by integrating the problem buildings according to the categories of network operators.

8. A building coverage assessment device based on user perception data, characterized in that: The device comprises: An acquisition module, used to acquire standardized map data and user perception data of buildings in the area to be planned; the standardized map data of buildings includes boundary information of each building, and the user perception data includes latitude and longitude information and MAC address of WiFi devices; The data processing module is used to first match the acquired user perception data based on the latitude and longitude information and the boundary information, determine the building to which each piece of user perception data belongs, and associate each piece of user perception data with its corresponding building to generate a building & user perception data table; then, based on the cluster analysis of the MAC address of the WiFi device, perform a secondary match on the user perception data that is not in the building area, determine the building to which each piece of user perception data belongs, and update the building & user perception data table; An evaluation module is used to calculate the RSRP coverage mean and weak coverage ratio of all user perception data in each building, and determine the problem buildings and corresponding indoor distribution planning schemes based on the RSRP coverage mean and the weak coverage ratio, so as to execute the corresponding indoor distribution planning schemes on the problem buildings in order of priority.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the building coverage assessment method based on user perception data as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the building coverage assessment method based on user perception data as described in any one of claims 1 to 7 are executed.

Images