Network quality evaluation method and device, electronic equipment and storage medium

Abstract

The invention discloses a network quality evaluation method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a grid unit set of a target detection area, acquiring detection data of the target detection area, and determining detected grid units and an undetected grid unit set in the grid unit set based on the detection data; obtaining network management data of the target detection area, and determining grid network attribute data of each detected grid unit in the detected grid unit set based on the detection data and the network management data; for the undetected grid units, determining a grid unit cluster corresponding to the undetected grid units, and determining grid network attribute data of the undetected grid units based on detection data corresponding to at least one detected grid unit in the grid unit cluster; and determining a network quality evaluation result of the corresponding grid unit based on the grid network attribute data of each grid unit. According to the scheme, the accuracy of the network evaluation result of each grid unit of the target detection area is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of network detection, and particularly to a network quality assessment method, apparatus, electronic device, and storage medium. Background Art

[0002] With the wide application of low-altitude flying devices such as unmanned aerial vehicles, it has become particularly important to ensure the network communication quality of these devices during flight. Traditional network quality assessment methods for low-altitude flying areas mainly rely on ground measurements and cannot comprehensively reflect the actual network conditions in the low-altitude flying environment. In addition, there are significant differences in network data collection between low-altitude scenarios and road surfaces. At the same time, network data collection and assessment in the low-altitude area are difficult, especially at different altitude layers, where the network quality may vary significantly. Traditional network quality assessment methods cannot meet the comprehensive network quality assessment requirements for low-altitude areas, and the test efficiency is low. Summary of the Invention

[0003] The present invention provides a network quality assessment method, apparatus, electronic device, and storage medium to improve the accuracy and efficiency of the network quality assessment results for each grid unit in the target detection area of the low-altitude area.

[0004] According to one aspect of the present invention, there is provided a network quality assessment method, including:

[0005] Determine a set of grid units in the target detection area, obtain detection data of the target detection area, and based on the detection data, determine the detected grid units and the set of undetected grid units in the set of grid units, where the set of grid units is obtained by performing three-dimensional grid division processing on the target detection area based on preset three-dimensional grid size data;

[0006] Obtain network management data of the target detection area, and based on the detection data and the network management data, determine the grid network attribute data of each detected grid unit in the set of detected grid units;

[0007] For the undetected grid units, determine the grid unit clusters corresponding to the undetected grid units, and based on the detection data respectively corresponding to at least one detected grid unit in the grid unit clusters, determine the grid network attribute data of the undetected grid units;

[0008] For any grid unit in the set of grid units, determine the network quality assessment result of the grid unit based on the grid network attribute data of the grid unit.

[0009] Optionally, the detection data includes detection point location data of multiple detection points; determining the set of detected grid cells and the set of undetected grid cells in the grid cell set based on the detection data includes: matching the detection point location data of each detection point with the grid location data of each grid cell in the grid cell set to determine the matching results of each grid cell in the grid cell set; forming a set of detected grid cells based on the grid cells with successful matching results, and forming a set of undetected grid cells based on the grid cells with failed matching results.

[0010] Optionally, the detection data includes the network cell identifier and network cell signal detection data of each detection point; determining the grid network attribute data of each detected grid cell in the set of detected grid cells based on the detection data and network management data includes: for each detected grid cell, determining the first network feature data of the detected grid cell based on the network cell signal detection data of each detection point in the detected grid cell, where the first network feature data includes signal reception power data, signal-to-noise ratio data, bit error rate data, and dominant ratio data; matching the network cell identifiers of each detection point in the detected grid cell in the network management data to obtain second network metric data that meets the preset grouping conditions, and determining the second network feature data of the detected grid cell based on the second network metric data, where the preset grouping conditions include one or more of time grouping conditions and service grouping conditions; determining the grid network attribute data of the detected grid cell based on the first network feature data and the second network feature data.

[0011] Optionally, determining the grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster includes: calibrating a pre-constructed signal propagation model based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster to obtain a target signal propagation model; determining the signal strength feature vector corresponding to the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster, network management data, and the target signal propagation model; calling a pre-trained network signal metric prediction model, and determining the grid network attribute data of the undetected grid cells through the pre-trained network signal metric prediction model and the signal strength feature vector corresponding to the undetected grid cells.

[0012] Optionally, determining the signal strength feature vector corresponding to the undetected grid cell based on the detection data, network management data, and target signal propagation model respectively corresponding to at least one detected grid cell in the grid cell cluster includes: determining the network cell identifiers of at least one candidate network cell corresponding to the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell, and determining the basic feature information respectively corresponding to each candidate network cell based on the network cell identifiers of at least one candidate network cell and the network management data, where the basic feature information includes the distance information between the network cell and the undetected grid cell, signal frequency information, network cell height information, and the height information of the undetected grid cell; determining the signal strength feature data corresponding to each candidate network cell based on the basic feature information respectively corresponding to each candidate network cell and the target signal propagation model; and constructing the signal strength feature vector corresponding to the undetected grid cell based on the network cell identifiers and the signal strength feature data corresponding to each candidate network cell.

[0013] Optionally, the detection data of the target detection area is detected by a target detection device, and the target detection device is configured on a flying device. The flying device carries the target detection device to perform a test task in the target detection area to obtain the detection data of the target detection area; for any grid cell in the grid cell set, determining the network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell includes: determining a network evaluation coefficient and a flight coefficient, where the flight coefficient is determined by the flight speed of the flying device located in the area corresponding to the grid cell during the test task; and performing weighted processing on the grid network attribute data of the grid cell based on the network evaluation coefficient and the flight coefficient to obtain the network quality evaluation result of the grid cell.

[0014] Optionally, the method further includes: during the process of the target detection device performing the test task, receiving the device operation data transmitted by the target detection device; in the case of identifying abnormal event data in the device operation data, generating a control instruction based on the abnormal event data, and sending the control instruction to the target detection device for controlling the target detection device to perform an abnormal handling operation, where the control instruction includes any one of a test task restart instruction and a flight termination instruction for the flying device.

[0015] According to another aspect of the present invention, there is provided a network quality evaluation device, including:

[0016] A grid cell classification module, configured to determine the grid cell set of the target detection area, obtain the detection data of the target detection area, and determine the detected grid cells and the undetected grid cell set in the grid cell set based on the detection data, where the grid cell set is obtained by performing three-dimensional grid division processing on the target detection area based on preset three-dimensional grid size data.

[0017] The first grid network attribute data determination module is configured to obtain network management data of a target detection area, and determine grid network attribute data of each detected grid unit in the detected grid unit set based on the detection data and the network management data;

[0018] The second grid network attribute data determination module is configured to, for undetected grid units, determine grid unit clusters corresponding to the undetected grid units, and determine grid network attribute data of the undetected grid units based on the detection data respectively corresponding to at least one detected grid unit in the grid unit clusters;

[0019] The network quality assessment result determination module is configured to, for any grid unit in the grid unit set, determine the network quality assessment result of the grid unit based on the grid network attribute data of the grid unit.

[0020] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0021] At least one processor; and

[0022] A memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the network quality assessment method according to any embodiment of the present invention.

[0024] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the network quality assessment method according to any embodiment of the present invention when executed.

[0025] In the technical solution of the embodiment of the present invention, by determining a set of grid cells in a target detection area, obtaining detection data of the target detection area, and determining detected grid cells and undetected grid cell sets in the set of grid cells based on the detection data, where the set of grid cells is obtained by performing three-dimensional grid division processing on the target detection area based on preset three-dimensional grid size data; obtaining network management data of the target detection area, and determining grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data; for undetected grid cells, determining grid cell clusters corresponding to the undetected grid cells, and determining grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell clusters; for any grid cell in the set of grid cells, determining a network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell. This solution determines the grid network attribute data of each detected grid cell in the target detection area according to multi-dimensional network detection data, and then determines the grid network attribute data of the undetected grid cells in the target detection area according to the detection data corresponding to the detected grid cells, so as to determine the network quality evaluation result of the grid cells according to the grid network attributes corresponding to each grid cell, solves the problem that the network quality of each position in the target detection area cannot be evaluated, and improves the accuracy of the network quality evaluation of each position in the target detection area.

[0026] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0028] Figure 1 is a flowchart of a network quality evaluation method provided in Embodiment 1 of the present invention;

[0029] Figure 2 is a flowchart of a network quality evaluation method provided in Embodiment 2 of the present invention;

[0030] Figure 3 is a flowchart of a network quality evaluation method provided in Embodiment 3 of the present invention;

[0031] Figure 4It is a schematic structural diagram of a network quality assessment device provided in Embodiment 4 of the present invention;

[0032] Figure 5 It is a schematic structural diagram of an electronic device for implementing the network quality assessment method of the embodiments of the present invention. Detailed implementation manners

[0033] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1 It is a flowchart of a network quality assessment method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of network quality assessment. This method can be executed by a network quality assessment device, which can be implemented in the form of hardware and / or software, and the network quality assessment device can be configured in electronic devices such as computers and servers. As Figure 1 shown, this method includes:

[0037] S110. Determine the grid cell set of the target detection area, obtain the detection data of the target detection area, and determine the detected grid cells and the undetected grid cell set in the grid cell set based on the detection data.

[0038] Among them, the set of grid cells is obtained by performing three-dimensional grid division processing on the target detection area based on preset three-dimensional grid size data. The preset three-dimensional grid size specifically refers to the sizes corresponding to the length, width, and height of the three-dimensional grid cells set according to the spatial division accuracy. Exemplarily, the preset three-dimensional grid size can be (length: 50 meters) * (width: 50 meters) * (height: 50 meters). A corresponding three-dimensional grid model is constructed according to the preset three-dimensional grid size for grid division of the target detection area, and corresponding grid identification information is set for each three-dimensional grid cell. The grid identification information can be specifically set according to the position in a coordinate system with the length / width / height of a grid cell as the unit distance. The set of three-dimensional grid cells of the target detection area is formed by the grid identification information corresponding to each three-dimensional grid cell. The information in the set of three-dimensional grid cells can also be modified according to actual needs, which is not limited here. A corresponding three-dimensional grid model can be set according to the preset three-dimensional grid size data, and the target detection area is grid-divided according to the three-dimensional grid model. Specifically, grid division can start from any vertex of the target detection area, and corresponding identification information is set for each three-dimensional grid cell in turn. The identification information can be set according to the three-dimensional position data of the grid cell in the target detection area. The set formed by each three-dimensional grid cell and the corresponding three-dimensional position information obtained after the three-dimensional grid division processing is determined as the set of grid cells of the target detection area. The target detection area can be pre-processed by three-dimensional grid division, and the obtained set of grid cells can be stored in a preset storage space so that it can be retrieved according to the target detection area later, which can be reused without re-performing three-dimensional grid division processing, avoiding excessive time consumption. The detection data can be specifically understood as the data collected at each detection point during the process of performing a test task in the target detection area. The detection data includes but is not limited to detection point position data, network cell identification of the detection point, and network cell signal detection data. It should be noted that one base station can correspond to one network cell, that is, the network cell can be specifically understood as a coverage area centered on the base station. Each network cell is set with a corresponding unique network cell identification (cell_id). If network information is detected at the detection point, then the network cell identification corresponding to the detected network information is determined as the network cell identification of the detection point. The network cell signal detection data specifically refers to the data representing the signal strength of the network cell, including but not limited to signal reception power data and signal-to-noise ratio data.

[0039] Specifically, match in a preset storage space according to the target detection area to obtain a set of grid cells that match the target detection area. If the match fails, call the three-dimensional grid division processing method to perform grid division processing on the target detection area to obtain the corresponding set of grid cells. Each grid cell in the set of grid cells is a three-dimensional grid cell. The detection data of the target detection area transmitted back by the target detection device can be obtained in real time. Match the detection data with the information of each grid cell in the set of grid cells to obtain a matching result, and determine the detected grid cells and the undetected grid cell set in the set of grid cells according to the matching result.

[0040] Optionally, the detection data includes the detection point position data of multiple detection points; determining the detected grid cell set and the undetected grid cell set in the set of grid cells based on the detection data includes: matching the detection point position data of each detection point with the grid position data of each grid cell in the set of grid cells to determine the matching results of each grid cell in the set of grid cells; forming a detected grid cell set based on the multiple grid cells with successful matching results, and forming an undetected grid cell set based on the multiple grid cells with failed matching results.

[0041] It should be noted that each grid cell in the set of grid cells has corresponding spatial position coordinate data. The target detection area is usually a relatively broad three-dimensional space area. The detection device is carried by a flying device to perform corresponding test tasks in the target detection area to obtain corresponding detection data. However, during such a flight test process, the flying device cannot traverse all the grid cells in the target detection area. Therefore, there will be detected grid cells and undetected grid cells in the target detection area. The detected grid cells and undetected grid cells in the target detection area can be determined by matching the position information of each grid cell with the detection point position data of each detection point in the detection data. Traverse the grid position data of each grid cell in the set of grid cells corresponding to the target detection area, match the detection point position data of each detection point with the grid position data to determine the matching results of each grid cell. For any grid cell, if at least one detection point is successfully matched, it is determined that the grid cell is successfully matched, and then the grid cell can be determined as a detected grid cell, that is, the detected grid cell includes at least one detection point; if the match fails, it indicates that there is no detection point in the grid cell, and then the grid cell is determined as an undetected grid cell. The set formed by the multiple grid cells with successful matching can be determined as the detected grid cell set, and the set formed by the multiple grid cells with failed matching can be determined as the undetected grid cell set.

[0042] In this embodiment, by performing a three-dimensional rasterization process on the target detection area, a set of grid cells in the target detection area is determined. The set of grid cells are all three-dimensional grid cells, and the detected grid cells and undetected grid cells in the set of grid cells can be determined according to the detection data, which is used to subsequently determine the network quality evaluation results corresponding to each grid cell, so that the network quality evaluation results of each spatial position in the target detection area can be better evaluated.

[0043] S120. Obtain the network management data of the target detection area, and determine the grid network attribute data of each detected grid cell in the set of detected grid cells based on the detection data and the network management data.

[0044] Among them, the network management data specifically represents the data for monitoring, controlling, and recording the performance and usage of the operator's network resources. In this embodiment, the network management data includes the usage information corresponding to multiple network cells. The usage information corresponding to each network cell includes, but is not limited to, the network cell identifier, location information, signal parameter index information, and height information. Among them, the location information specifically refers to the installation location of the base station corresponding to the network cell; the signal parameter index information refers to the signal characteristics corresponding to the network cell, including, but not limited to, the signal frequency information and the received signal strength indication information; the height information specifically refers to the height data of the base station corresponding to the network cell.

[0045] Specifically, the network management data of the target detection area can be obtained from the network management platform, and the detected grid cell data can be obtained by performing a convergence marking process on the network management data and the detection data. For each detected grid cell, the detection data corresponding to the detected grid cell can be extracted from the detection data of the target detection area, and then matched in the network management data according to the detection data of the detected grid cell to obtain a matching result. In this embodiment, the network data corresponding to each network cell identifier is obtained by matching according to the network cell identifier in the detection data of the detected grid cell, and the index calculation is performed according to the obtained network data and the corresponding detection data, and the obtained index calculation result is determined as the grid network attribute data of the detected grid cell.

[0046] In this embodiment, by processing the multi-dimensional network data, the grid network attribute data of each detected grid cell is obtained, which is used to subsequently determine the network quality evaluation result of the grid cell, and helps to improve the accuracy of the grid network quality evaluation.

[0047] S130. For the undetected grid cells, determine the grid cell clusters corresponding to the undetected grid cells, and determine the grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell clusters.

[0048] Among them, the grid cell cluster can be specifically understood as a set formed by at least one detected grid cell that is closest to the undetected grid cell. It can be achieved by taking any undetected grid cell as the center point and selecting a grid cluster where |x - x 0 | ≤ m, |y - y 0 | ≤ m, |z - z 0 | ≤ m, where (x, y, z) represents the position data of the undetected grid cell, and the position data here characterizes the position of the three-dimensional grid cell in the coordinate system with the cell size of the grid cell as the unit distance. (x 0 , y 0 , z 0 ) represents the position data of the grid cell in the neighborhood of the undetected grid cell, m represents the neighborhood range, and the selection method of m is to increment starting from 1 cell. In the case of m = 1, that is, searching within the neighborhood of one cell. If there is at least one detected grid cell, then the corresponding detected grid cell can be determined as the grid cell cluster of the undetected grid cell. If there is no detected grid cell, then m is set to 2 and the search continues until the grid cell cluster of the undetected grid cell is obtained. It can be understood that any grid cell cluster includes at least one detected grid cell. It should be noted that the larger the value of m, the more detected grid cells there are in the grid cell cluster, and the higher the accuracy of the grid network attribute data of the corresponding undetected grid cell. Therefore, the value of m can be set according to the accuracy requirement of the grid network attribute data of the undetected grid cell. In this embodiment, the grid network attribute data includes but is not limited to signal reception power data, signal-to-noise ratio data, and received signal strength indication information.

[0049] Specifically, for the undetected grid cell, taking the undetected grid cell as the target grid cell, querying the detected grid cells from the spatial neighborhood of the target grid cell. Among them, the detected grid cell (x 0 , y 0 , z 0 ) that is queried satisfies |x - x 0 | ≤ m, |y - y 0 | ≤ m, |z - z 0 | ≤ m, and m can be incremented according to the query result. When obtaining the grid cell cluster corresponding to the undetected grid cell, obtaining the detection data corresponding to each detected grid cell in the grid cell cluster, and calling the pre-constructed grid network attribute data prediction model to process the detection data corresponding to each detected grid cell to obtain the grid network attribute data of the undetected grid cell. Among them, the pre-constructed grid network attribute data prediction model can be specifically understood as a machine learning model constructed based on the propagation model.

[0050] In this embodiment, the detection data of each detected grid cell in the grid cell cluster corresponding to the undetected grid cell is used to predict the grid network attribute data of the undetected grid cell, so as to obtain the grid network attribute data of the undetected grid cell, avoiding using data with low relevance to the network characteristics corresponding to the undetected grid cell for prediction, improving the accuracy of the grid network attribute data of the undetected grid cell, and helping to improve the accuracy of grid network quality assessment.

[0051] S140. For any grid cell in the grid cell set, determine the network quality assessment result of the grid cell based on the grid network attribute data of the grid cell.

[0052] It should be noted that the grid network attribute data includes multiple attributes. Due to different requirements of different services for low-altitude communication, the target values corresponding to different attributes are different. The corresponding weight data can be set according to the deviation interval of each attribute value relative to the target value. The weight data corresponding to the attribute value interval can be determined in advance according to the mapping relationship between the deviation interval corresponding to each attribute and the weight data, and the attribute value interval and the corresponding weight data are stored. In the case of network quality assessment, the weight data corresponding to each attribute can be determined by matching according to the grid network attribute data.

[0053] Specifically, for any grid cell in the grid cell set, call the mapping relationship between the attribute value interval and the weight data corresponding to each attribute pre-constructed, match each attribute data in the grid network attribute data of the grid cell with the mapping relationship, so as to determine the weight data corresponding to each attribute, and then perform weighted processing on the numerical values of each attribute according to the weight data to obtain the weighted processing result, and determine the weighted processing result as the network quality assessment result of the grid cell.

[0054] Based on the above embodiment, the detection data of the target detection area is detected by a target detection device. The target detection device is configured on a flight device, and the flight device carries the target detection device to execute a test task in the target detection area to obtain the detection data of the target detection area; for any grid cell in the grid cell set, determining the network quality assessment result of the grid cell based on the grid network attribute data of the grid cell includes: determining a network evaluation coefficient and a flight coefficient, where the flight coefficient is determined based on the flight speed of the flight device in the area corresponding to the grid cell during the execution of the test task; performing weighted processing on the grid network attribute data of the grid cell based on the network evaluation coefficient and the flight coefficient to obtain the network quality assessment result of the grid cell.

[0055] It should be noted that the detection data of the target detection area is detected by the target detection device. In order to collect the detection data of each spatial area in the target detection area, the target detection device can be configured on the flying device, and the flying device is controlled to carry the target detection device to execute a test task in the target detection area. During the execution of the test task, the network signal parameters of each detection point are detected by the target detection device, and the flying device collects the flight data of each detection point. Among them, the flight data includes but is not limited to detection point position data, flight speed data, and flight altitude data. The target detection device can receive the flight data transmitted by the flying device and determine the detection data of the target detection area from the collected network parameters of each detection point and the received flight data. The target detection device can transmit the determined detection data to the test platform in real time. The network evaluation coefficient specifically represents the weight data of each attribute in the grid network attribute data.

[0056] It can be understood that during the execution of the test task, the flight speed of the flying device will affect the network signal parameters detected by the target detection device to a certain extent, thereby affecting the weight of the attributes in the grid network attribute data. The corresponding flight coefficient can be set according to the flight speed to adjust the weight data corresponding to the network attribute data.

[0057] Specifically, the corresponding network evaluation coefficient can be matched from the preset storage space according to the current test task. The flight coefficient is determined according to the flight speed of the flying device in the area corresponding to the grid unit during the execution of the test task; the grid network attribute data of the grid unit is weighted by the network evaluation coefficient and the flight coefficient to obtain the network quality evaluation result of the grid unit.

[0058] In a specific embodiment, considering the influence of the flight speed of the flying device on the network evaluation result, the weight data used to determine the network quality evaluation result includes the network evaluation coefficient and the flight coefficient; the grid network attribute data includes T 1 ,T 2 ,T 3 ,T 4 ,T 5 ,T 6 and other 6 items of attribute data, where T 3 ,T 5 is affected by the flight speed, and the corresponding flight coefficients are set as K 3 ,K 5 . And the corresponding index weight coefficients C 1 ,C 2 ,C 3 ,C 4 ,C 5 ,C 6 are added to the corresponding indicators. It is agreed that C 1 +C2 +C 3 +C 4 +C 5 +C 6 = 1. Among them, K n is the influence coefficient on the network evaluation result at different flight speeds, that is, the flight coefficient. The grid network quality evaluation expression is: S = T 1 ·C 1 +T 2 ·C 2 +T 3 ·C 3 ·K 3 +T 4 ·C 4 +T 5 ·C 5 ·K 5 +T 6 ·C 6 .

[0059] In this embodiment, considering the influencing factors of different dimensions, the network evaluation coefficient and the flight coefficient are determined, which are used to perform weighted processing on the grid network attribute data of the grid cell, and the network quality evaluation result of the grid cell is obtained, improving the accuracy of the network quality evaluation result of the grid cell.

[0060] Optionally, the method further includes: during the process of the target detection device executing the test task, receiving the device operation data transmitted by the target detection device; in the case of identifying abnormal event data in the device operation data, generating a control instruction based on the abnormal event data, and sending the control instruction to the target detection device for controlling the target detection device to perform an abnormal processing operation, where the control instruction includes any one of a test task restart instruction and a termination flight device flight instruction.

[0061] Among them, the abnormal event data specifically refers to the abnormal problems generated by the target detection device during the detection process, including but not limited to communication test attach failure information, FTP connection failure information, and test data log generation failure information.

[0062] In this embodiment, the transmission module used to obtain the detection data and the device operation data is different from the transmission module of other service operation data, and the detection data and the device operation data can be obtained in real time, and the network quality evaluation and abnormal problem detection are respectively performed according to the obtained detection data and the device operation data, realizing real-time interaction with the target detection device, thereby improving the efficiency and real-time performance of the network quality evaluation, and detecting and solving abnormal problems in a timely manner to ensure that the collected detection data and device operation data are accurate data.

[0063] Specifically, during the process of the target detection device executing a test task, the target detection device can generate corresponding log information packets based on the collected detection data and device operation data according to a set time. For example, the method, apparatus, electronic device, and storage medium for network quality evaluation - invention can generate a log information packet every 5 seconds to upload the detection data and device operation data to the target test platform, and can also receive control instructions issued by the target test platform. The target test platform analyzes the received device operation data to determine whether there is abnormal event data in the analysis result. Specifically, it can identify whether there is identification information corresponding to an abnormal event in the analysis result. If there is abnormal event identification information, the corresponding abnormal event data can be determined according to the abnormal event identification information. In the case of obtaining the abnormal event data, a corresponding control instruction can be generated according to the abnormal event data, and the control instruction can be sent to the corresponding target detection device to control the target detection device to perform an abnormal handling operation. Among them, the control instruction includes any one of a test task restart instruction and a flight termination instruction for the flight device. If the control instruction is a test task restart instruction, the target detection device is controlled to restart the test task according to the test task restart instruction. If the test task is successfully started within the preset number of restart attempts, the test task continues to be executed. If the test task fails to be successfully started within the preset number of restart attempts, a flight termination instruction for the flight device can be sent. When the target detection device receives the flight termination instruction for the flight device, it controls the bound flight device to stop flying, avoiding obtaining incorrect detection data and improving the accuracy of the detection data. If the control instruction is a flight termination instruction for the flight device, the flight device bound to the target detection device can be controlled to stop flying. After the abnormal event is successfully resolved, the target detection device and the corresponding flight device are controlled to perform data collection again.

[0064] Optionally, before determining the network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell, data update processing is performed on the grid network attribute data of the grid cell. The specific data update processing method includes: for any grid cell, obtaining the historical grid network attribute data corresponding to the grid cell; in the case of obtaining the historical grid network attribute data corresponding to the grid cell, obtaining preset weight data, and performing weighted processing on the grid network attribute data and the historical grid network attribute data of the grid cell based on the preset weight data to obtain a weighted processing result; updating the grid network attribute data of the grid cell based on the weighted processing result. In addition, for the update of network management data, it does not depend on detection data, and is updated according to the latest network cell occupancy situation and the latest statistical data over a period of time in the past to obtain the latest network management data.

[0065] The technical solution of this embodiment determines a grid cell set of a target detection area, obtains detection data of the target detection area, and determines detected grid cells and undetected grid cell sets in the grid cell set based on the detection data, where the grid cell set is obtained by performing three-dimensional grid division processing on the target detection area based on preset three-dimensional grid size data; obtains network management data of the target detection area, and determines grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data; for undetected grid cells, determines grid cell clusters corresponding to the undetected grid cells, and determines grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell clusters; for any grid cell in the grid cell set, determines a network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell. This solution determines grid network attribute data of each detected grid cell in the target detection area according to multi-dimensional network detection data, and further determines grid network attribute data of undetected grid cells in the target detection area according to the detection data corresponding to the detected grid cells, so as to determine the network quality evaluation result of the grid cell according to the grid network attributes corresponding to each grid cell, solves the problem that the network quality of each position in the target detection area cannot be evaluated, and improves the accuracy of network quality evaluation of each spatial area in the target detection area.

[0066] Embodiment 2

[0067] Figure 2 It is a flowchart of a network quality evaluation method provided by the second embodiment of the present invention. The method of this embodiment is a further optimization of the method of the above embodiment. Optionally, for each detected grid cell, determine first network feature data of the detected grid cell based on network cell signal detection data of each detection point in the detected grid cell; match the network cell identifiers of each detection point in the detected grid cell in the network management data to obtain second network index data that meets preset grouping conditions, and determine second network feature data of the detected grid cell based on the second network index data; determine grid network attribute data of the detected grid cell based on the first network feature data and the second network feature data. As Figure 2 shown, the method includes:

[0068] S210. Determine a grid cell set of the target detection area, obtain detection data of the target detection area, and determine detected grid cells and undetected grid cell sets in the grid cell set based on the detection data.

[0069] S220. Obtain network management data of the target detection area, where the detection data includes network cell identifiers and network cell signal detection data of each detection point.

[0070] S230. For each detected grid cell, determine the first network feature data of the detected grid cell based on the network cell signal detection data of each detection point in the detected grid cell.

[0071] Among them, the network cell signal detection data represents the data characterizing the signal strength detected at the detection point, including but not limited to signal reception power detection data, signal-to-noise ratio detection data, and bit error rate detection data. The first network feature data includes signal reception power data, signal-to-noise ratio data, bit error rate data, and dominant ratio data. The signal reception power data refers to the key parameter representing the wireless signal strength in the LTE network. The smaller the parameter value, the higher the signal strength. The signal-to-noise ratio data represents an important parameter for measuring signal quality, indicating the ratio of the power of the useful signal to the power of the background noise, usually expressed in decibels (dB). The bit error rate data is specifically used to measure the number of bit errors occurring during transmission, indicating the reliability of data transmission. The dominant ratio data specifically represents the ratio of the number of detection points corresponding to the network cell continuously used without handover in the grid cell to the number of all detection points in the grid, and is used to measure the stability of the network signal in the grid cell.

[0072] Specifically, for each detected grid cell, obtain the network cell signal detection data of each detection point in the detected grid cell, calculate the average value of the signal reception power detection data, the average value of the signal-to-noise ratio detection data, and the average value of the bit error rate detection data, determine the average value of the signal reception power detection data as the signal reception power data, determine the average value of the signal-to-noise ratio detection data as the signal-to-noise ratio data, and determine the average value of the bit error rate detection data as the bit error rate data. The calculation formulas for each feature data in the first network feature data of the detected grid cell (x, y, z) are as follows:

[0073] (x, y, z, RSPR) = AVG(RSPR values of each detection point in the detected grid cell);

[0074] (x, y, z, SINR) = AVG(SINR values of each detection point in the detected grid cell);

[0075] (x, y, z, BER) = AVG(BER values of each detection point in the detected grid cell);

[0076] (x, y, z, dominant ratio) = the number of detection points corresponding to the continuously used network cells that have not switched in the grid cell / the number of all detection points in the grid; where PSRP is the signal reception power data, SINR is the signal-to-noise ratio data, and BER is the bit error rate data; the obtained (x, y, z, RSPR), (x, y, z, SINR), (x, y, z, BER), and (x, y, z, dominant ratio) are aggregated into the first network feature data of the grid cell, and the first network feature data of the grid cell (x, y, z) can be expressed as: (x, y, z, RSPR, SINR, BER, dominant ratio).

[0077] In a specific embodiment, the first network feature data further includes uplink speed data and transmission delay data. Specifically, the uplink speed average value is determined according to the uplink speed detection data of each detection point in the detected grid cell, and the uplink speed average value is determined as the uplink speed data; the transmission delay average value is determined according to the transmission delay data of each detection point in the detected grid cell, and the transmission delay average value is determined as the transmission delay data. The obtained uplink speed data and transmission delay data are added to the first network feature data of the corresponding network grid cell to enrich the feature data in the first network feature data. This helps to improve the accuracy of the network evaluation result.

[0078] S240. Match based on the network cell identifiers of each detection point in the detected grid cell in the network management data to obtain the second network metric data that meets the preset grouping conditions, and determine the second network feature data of the detected grid cell based on the second network metric data.

[0079] Among them, considering that the network attribute data of the grid cell has the characteristic of hourly change, that is, it will change with different types of services and time. Therefore, data matching is performed from the network management data through preset grouping conditions to determine the corresponding second network metric data. The preset grouping conditions include but are not limited to time grouping conditions and service grouping conditions. The time grouping conditions include but are not limited to grouping by working days and grouping by holidays. The second network feature data can be specifically understood as the feature data extracted from the network management data, including but not limited to the received signal strength indication data RSSI.

[0080] Specifically, match according to the network cell identifiers of each detection point in the detected grid cell in the network management data, perform data grouping queries according to preset grouping conditions, obtain the signal strength indication data RSSI that meets the preset grouping conditions, that is, obtain the second network metric data that meets the preset grouping conditions, calculate the average value corresponding to the second network metric data, and determine the average value as the second network feature data of the detected grid cell. It should be noted that the second network metric data can be adjusted according to actual network evaluation requirements, and correspondingly, the second network feature data is also adjusted accordingly. Preferably, there are multiple network cells in the detected grid cell. There is no need to process the network management data of all network cells. The top three network cells with the largest number of corresponding detection points can be selected through the number of detection points corresponding to each network cell, perform grouped queries in the network management data according to the corresponding network cell identifiers, obtain the corresponding second network metric data, calculate the average value of the metrics in the second network metric data, and obtain the second network feature data. Exemplarily, the calculation expression of the second network feature data is: (x, y, z, [RSSI, h, grouping g]) = avg(RSSI statistically counted by the TOP3 occupied network cells in the grid cell at time h in grouping g), where grouping g is any one of the grouping conditions of weekdays, weekends, and special holidays. The average value is calculated based on the network metric data obtained by time grouping to obtain the corresponding feature data, which can reflect the network changes at different times and help improve the accuracy of grid network evaluation.

[0081] S250. Determine the grid network attribute data of the detected grid cell based on the first network feature data and the second network feature data.

[0082] Specifically, perform aggregation processing on the obtained first network feature data and second network feature data to obtain the corresponding grid network attribute data of the detected grid cell. For example, the grid network attribute data (x, y, z, RSPR, SINR, BER, dominant ratio, RSSI) of the detected grid cell is aggregated from the first network feature data which can be expressed as (x, y, z, RSPR, SINR, BER, dominant ratio) and the second network feature data (x, y, z, [RSSI, h, grouping g]).

[0083] S260. For undetected grid cells, determine the grid cell cluster corresponding to the undetected grid cells, and determine the grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster.

[0084] S270. For any grid cell in the grid cell set, determine the network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell.

[0085] In the technical solution of this embodiment, by determining the grid cell set of the target detection area, obtaining the detection data of the target detection area, and determining the detected grid cells and the undetected grid cell set in the grid cell set based on the detection data; obtaining the network management data of the target detection area, where the detection data includes the network cell identifier and the network cell signal detection data of each detection point; for each detected grid cell, determining the first network feature data of the detected grid cell based on the network cell signal detection data of each detection point in the detected grid cell; performing matching in the network management data based on the network cell identifiers of each detection point in the detected grid cell to obtain the second network index data that meets the preset grouping condition, and determining the second network feature data of the detected grid cell based on the second network index data; determining the grid network attribute data of the detected grid cell based on the first network feature data and the second network feature data; for the undetected grid cell, determining the grid cell cluster corresponding to the undetected grid cell, and determining the grid network attribute data of the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster; for any grid cell in the grid cell set, determining the network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell. This solution determines the grid network attribute data of each detected grid cell in the target detection area according to multi-dimensional network detection data, and then determines the grid network attribute data of the undetected grid cells in the target detection area according to the detection data corresponding to the detected grid cells, so as to determine the network quality evaluation result of the grid cells according to the grid network attributes corresponding to each grid cell, solving the problem that the network quality of each position in the target detection area cannot be evaluated, and improving the accuracy of the network quality evaluation of each position in the target detection area.

[0086] Embodiment III

[0087] Figure 3 It is a flowchart of a network quality evaluation method provided by Embodiment III of the present invention. The method of this embodiment is a further optimization of the method of the above embodiment. Optionally, calibrating a pre-constructed signal propagation model based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster to obtain a target signal propagation model; determining the signal strength feature vector corresponding to the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster, the network management data, and the target signal propagation model; calling a pre-trained network signal index prediction model, and determining the grid network attribute data of the undetected grid cell through the pre-trained network signal index prediction model and the signal strength feature vector corresponding to the undetected grid cell. As Figure 3 shown, the method includes:

[0088] S310. Determine the set of grid cells in the target detection area, obtain the detection data of the target detection area, and determine the detected grid cells and the set of undetected grid cells in the set of grid cells based on the detection data.

[0089] S320. Obtain the network management data of the target detection area, and determine the grid network attribute data of each detected grid cell in the set of detected grid cells based on the detection data and the network management data.

[0090] S330. For the undetected grid cells, determine the grid cell clusters corresponding to the undetected grid cells.

[0091] S340. Calibrate the pre-constructed signal propagation model based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster to obtain the target signal propagation model.

[0092] Among them, the pre-constructed signal propagation model includes but is not limited to the spatial electromagnetic wave propagation model and the line-of-sight propagation model. Among them, the representation form of the spatial electromagnetic wave propagation model can be:

[0093] PL = a1*log(d) + a2*log(f) + a3*log(ht) + a4*log(hr) + a5

[0094] Among them, PL is the path loss. Calibrate the above propagation model according to the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster, obtain the detection data of each detection point of at least one detected grid cell in the grid cell cluster, determine the spatial distance d between the position of the detection point and the base station of the corresponding network cell, the test frequency f detected at this detection point, the height data ht of the base station of the network cell corresponding to this detection point, and the height data hr of this detection point. a 1 , a 2 , a 3 , a 4 , a 5 is an adjustable parameter in the propagation model. Therefore, the corresponding parameter values of d, f, ht, and hr can be determined according to the detection data of each detection point of the detected grid cell. Combining the propagation model, the predicted PL value of each detection point can be calculated, and the corresponding predicted RSPR value can be predicted according to the predicted path loss. After obtaining the predicted RSPR value of each detection point, calibrate the pre-constructed signal propagation model according to the actual RSPR value and the predicted RSPR value of each detection point to obtain the target signal propagation model. Specifically, the mean square error between the predicted value and the true value can be calculated, and the model with the lowest mean square error can be selected as the target signal propagation model.

[0095] It should be noted that if the detection data in the grid cluster corresponding to the undetected grid cell cannot meet the purpose of propagation model calibration, and the m value corresponding to the grid cluster has not reached the maximum value, then let m = m + 1, and determine the grid cluster of the undetected grid cell again to increase the detected grid cells in the grid cell cluster. Calibrate the propagation model based on the detection data of the detected grid cells in the newly obtained grid cell cluster to obtain a target signal propagation model that meets the calibration purpose. If a target signal propagation model that meets the calibration purpose still cannot be obtained when the m value reaches the maximum, then this undetected grid cell is marked as unpredictable.

[0096] In this embodiment, the pre-constructed signal propagation model can be constructed based on the line-of-sight propagation model. The expression of the line-of-sight propagation model is: PL = 32.45 + 20log(f) + 20log(d) + c, where c is the compensation coefficient with an initial value of 0. It can also be constructed based on the line-of-sight + non-line-of-sight two-ray model. The expression of the line-of-sight + non-line-of-sight two-ray model is: PL = 20log(8pi) + 20log(ht) + 20log(hr) + 40log(f) + c, where c is the compensation coefficient with an initial value of 0. Both of the above two models can be calibrated according to the aforementioned calibration method, which will not be elaborated here. Preferably, multiple propagation models can be selected for calibration processing, and the model with the lowest mean square error can be selected as the target signal propagation model.

[0097] S350. Determine the signal strength feature vector corresponding to the undetected grid cell based on the detection data, network management data, and target signal propagation model corresponding to at least one detected grid cell in the grid cell cluster.

[0098] Specifically, extract the basic feature information of each detection point from the detection data and network management data corresponding to at least one detected grid cell in the grid cell cluster. The basic feature information includes but is not limited to the distance information between the network cell and the undetected grid cell, signal frequency information, network cell height information, and height information of the undetected grid cell. Calculate the signal strength data corresponding to each network cell through the target signal propagation model based on the basic feature information, and form the signal strength feature vector corresponding to the undetected grid cell based on the network cell identifier and the corresponding signal strength data in each network grid cell. Exemplarily, the signal strength feature vector corresponding to the undetected grid cell can be expressed as: [(RSRP-1, pci-1), (RSRP-2, pci-2), (RSRP-3, pci-3), ……, (RSRP-n, pci-n)], where RSRP-n represents the signal strength data of the nth network cell, and pci-n represents the network cell identifier of the network cell.

[0099] Optionally, determining a signal strength feature vector corresponding to an undetected grid cell based on detection data, network management data, and a target signal propagation model respectively corresponding to at least one detected grid cell in a grid cell cluster includes: determining network cell identifiers of at least one candidate network cell corresponding to the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell; determining basic feature information respectively corresponding to each candidate network cell based on the network cell identifiers of at least one candidate network cell and the network management data, where the basic feature information includes distance information between the network cell and the undetected grid cell, signal frequency information, network cell height information, and height information of the undetected grid cell; determining signal strength feature data corresponding to each candidate network cell based on the basic feature information respectively corresponding to each candidate network cell and the target signal propagation model; and constructing a signal strength feature vector corresponding to the undetected grid cell based on the network cell identifiers and the signal strength feature data corresponding to each candidate network cell.

[0100] Specifically, network cell data is extracted according to the detection data respectively corresponding to at least one detected grid cell in the grid cluster to obtain network cell identifiers of at least one candidate network cell corresponding to the undetected grid cell, and then matching is performed in the network management data based on the network cell identifiers of at least one candidate network cell to obtain corresponding basic information, and basic feature information respectively corresponding to each candidate network cell is determined according to the basic information, where the basic feature information includes distance information between the network cell and the undetected grid cell, signal frequency information, network cell height information, and height information of the undetected grid cell, where the height data of the network cell refers to the height data of the corresponding base station, and the height information of the undetected grid cell can be determined based on the position information of the undetected grid cell; substituting the basic feature information respectively corresponding to each candidate network cell into the target signal propagation model to calculate signal strength feature data corresponding to each candidate network cell, that is, RSSI data corresponding to each candidate network cell; and constructing a signal strength feature vector corresponding to the undetected grid cell based on the network cell identifiers and the signal strength feature data corresponding to each candidate network cell, such as [(RSRP-1, pci-1), (RSRP-2, pci-2), (RSRP-3, pci-3),..., (RSRP-n, pci-n)].

[0101] S360. Invoke a pre-trained network signal metric prediction model, and determine grid network attribute data of an undetected grid through the pre-trained network signal metric prediction model and the signal strength feature vector corresponding to the undetected grid cell.

[0102] Among them, the network signal index prediction model is a machine learning model that performs machine learning on the network cell coverage information [RSRP-1, RSRP-2, RSRP-3, ……, RSRP-n] corresponding to the detected grid cells in the target detection area and corresponding indicators such as SINR and BER to obtain a trained network signal index prediction model. After the RSRP corresponding to the network cell of the undetected grid cell can be determined through the target signal propagation model, the corresponding signal strength feature vector can be obtained, such as [(RSRP-1, pci-1), (RSRP-2, pci-2), (RSRP-3, pci-3), ……, (RSRP-n, pci-n)]. The signal strength feature vector can be predicted by the network signal index prediction model to obtain the grid network attribute data corresponding to the undetected grid cell. It should be noted that machine learning can be performed synchronously according to the network cell coverage information [RSRP-1, RSRP-2, RSRP-3, ……, RSRP-n] corresponding to the detected grid cells in the target detection area and corresponding indicators such as SINR and BER to obtain a model that can simultaneously output the grid network attribute data of the undetected grid. It can also be that the prediction model is separately trained according to each of the network cell coverage information [RSRP-1, RSRP-2, RSRP-3, ……, RSRP-n] corresponding to the detected grid cells in the target detection area and the corresponding SINR and BER, so as to obtain an index prediction model corresponding to each index, which is not limited here.

[0103] Specifically, the signal strength feature vector corresponding to the undetected grid cell is used as an input parameter and input into the pre-trained network signal index prediction model. The pre-trained network signal index prediction model performs prediction processing, and the pre-trained network signal index prediction model outputs the grid network attribute data of the undetected grid.

[0104] S370. For any grid cell in the grid cell set, determine the network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell.

[0105] The technical solution of this embodiment determines a grid cell set of a target detection area, obtains detection data of the target detection area, and determines detected grid cells and undetected grid cell sets in the grid cell set based on the detection data; obtains network management data of the target detection area, and determines grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data; for undetected grid cells, determines grid cell clusters corresponding to the undetected grid cells; calibrates a pre-constructed signal propagation model based on detection data respectively corresponding to at least one detected grid cell in the grid cell cluster to obtain a target signal propagation model; determines a signal strength feature vector corresponding to an undetected grid cell based on detection data, network management data, and the target signal propagation model respectively corresponding to at least one detected grid cell in the grid cell cluster; calls a pre-trained network signal index prediction model, and determines grid network attribute data of the undetected grid cell through the pre-trained network signal index prediction model and the signal strength feature vector corresponding to the undetected grid cell; for any grid cell in the grid cell set, determines a network quality evaluation result of the grid cell based on the grid network attribute data of the grid cell. This solution determines grid network attribute data of each detected grid cell in the target detection area according to multi-dimensional network detection data, and then determines grid network attribute data of undetected grid cells in the target detection area according to the detection data corresponding to the detected grid cells, so as to determine the network quality evaluation result of the grid cell according to the grid network attribute corresponding to each grid cell, solves the problem that the network quality of each position in the target detection area cannot be evaluated, and improves the accuracy of the network quality evaluation of each position in the target detection area.

[0106] Embodiment 4

[0107] Figure 4 is a schematic structural diagram of a network quality evaluation device provided in Embodiment 4 of the present invention. As Figure 4 shown, the device includes:

[0108] A grid cell classification module 410, configured to determine a grid cell set of a target detection area, obtain detection data of the target detection area, and determine detected grid cells and undetected grid cell sets in the grid cell set based on the detection data, where the grid cell set is obtained by performing three-dimensional grid division processing on the target detection area based on preset three-dimensional grid size data;

[0109] A first grid network attribute data determination module 420, configured to obtain network management data of the target detection area, and determine grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data;

[0110] The second grid network attribute data determination module 430 determines, for undetected grid cells, the grid cell clusters corresponding to the undetected grid cells, and determines the grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell clusters;

[0111] The network quality assessment result determination module 440 is configured to determine, for any grid cell in the grid cell set, the network quality assessment result of the grid cell based on the grid network attribute data of the grid cell.

[0112] The technical solution of this embodiment determines the grid cell set of the target detection area through the grid cell classification module, obtains the detection data of the target detection area, determines the detected grid cells and the undetected grid cell set in the grid cell set based on the detection data, wherein the grid cell set is obtained by performing three-dimensional grid division processing on the target detection area based on the preset three-dimensional grid size data; the first grid network attribute data determination module obtains the network management data of the target detection area, and determines the grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data; the second grid network attribute data determination module determines, for undetected grid cells, the grid cell clusters corresponding to the undetected grid cells, and determines the grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell clusters; the network quality assessment result determination module determines, for any grid cell in the grid cell set, the network quality assessment result of the grid cell based on the grid network attribute data of the grid cell. This solution determines the grid network attribute data of each detected grid cell in the target detection area according to multi-dimensional network detection data, and then determines the grid network attribute data of the undetected grid cells in the target detection area according to the detection data corresponding to the detected grid cells, so as to determine the network quality assessment result of the grid cells according to the grid network attributes corresponding to each grid cell, solves the problem that the network quality of each position in the target detection area cannot be evaluated, and improves the accuracy of the network quality assessment of each position in the target detection area.

[0113] On the basis of the above embodiment, optionally, the detection data includes the detection point position data of multiple detection points; the grid cell classification module 410 is specifically configured to match the detection point position data of each detection point with the grid position data of each grid cell in the grid cell set to determine the matching result of each grid cell in the grid cell set; form the detected grid cell set based on multiple grid cells with a successful matching result, and form the undetected grid cell set based on multiple grid cells with a failed matching result.

[0114] Optionally, the detection data includes the network cell identifier and network cell signal detection data of each detection point; the first grid network attribute data determination module 420 is specifically configured to, for each detected grid unit, determine the first network feature data of the detected grid unit based on the network cell signal detection data of each detection point in the detected grid unit, where the first network feature data includes signal reception power data, signal-to-noise ratio data, bit error rate data, and dominant ratio data; match the network cell identifiers of each detection point in the detected grid unit in the network management data to obtain second network metric data that meets the preset grouping conditions, and determine the second network feature data of the detected grid unit based on the second network metric data, where the preset grouping conditions include one or more of a time grouping condition and a service grouping condition; determine the grid network attribute data of the detected grid unit based on the first network feature data and the second network feature data.

[0115] Optionally, the second grid network attribute data determination module 430 includes a target signal propagation model determination unit, a signal strength feature vector determination unit, and a grid network attribute data determination unit. The target signal propagation model determination unit is configured to calibrate a pre-constructed signal propagation model based on the detection data respectively corresponding to at least one detected grid unit in the grid unit cluster to obtain a target signal propagation model; the signal strength feature vector determination unit is configured to determine the signal strength feature vector corresponding to the undetected grid unit based on the detection data respectively corresponding to at least one detected grid unit in the grid unit cluster, the network management data, and the target signal propagation model; the grid network attribute data determination unit is configured to call a pre-trained network signal metric prediction model and determine the grid network attribute data of the undetected grid unit through the pre-trained network signal metric prediction model and the signal strength feature vector corresponding to the undetected grid unit.

[0116] Optionally, the signal strength feature vector determination unit is specifically configured to determine the network cell identifiers of at least one candidate network cell corresponding to the undetected grid unit based on the detection data respectively corresponding to at least one detected grid unit, determine the basic feature information corresponding to each candidate network cell based on the network cell identifiers of at least one candidate network cell and the network management data, where the basic feature information includes the distance information between the network cell and the undetected grid unit, signal frequency information, network cell height information, and the height information of the undetected grid unit; determine the signal strength feature data corresponding to each candidate network cell based on the basic feature information corresponding to each candidate network cell and the target signal propagation model; construct the signal strength feature vector corresponding to the undetected grid unit based on the network cell identifiers and the signal strength feature data corresponding to each candidate network cell.

[0117] Optionally, the detection data of the target detection area is detected by a target detection device, which is configured on a flight device. The flight device carries the target detection device to perform a test task in the target detection area to obtain the detection data of the target detection area. The network quality evaluation result determination module 440 is specifically configured to determine a network evaluation coefficient and a flight coefficient, where the flight coefficient is determined based on the flight speed of the flight device in the area corresponding to the grid cell during the execution of the test task; perform weighted processing on the grid network attribute data of the grid cell based on the network evaluation coefficient and the flight coefficient to obtain the network quality evaluation result of the grid cell.

[0118] Optionally, the device is further configured to receive the device operation data transmitted by the target detection device during the execution of the test task by the target detection device; in the case of identifying abnormal event data in the device operation data, generate a control instruction based on the abnormal event data, and send the control instruction to the target detection device for controlling the target detection device to perform an abnormal handling operation, where the control instruction includes any one of a test task restart instruction and a flight termination instruction for the flight device.

[0119] The network quality evaluation device provided by the embodiments of the present invention can execute the network quality evaluation method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0120] Embodiment Five

[0121] Figure 5 FIG. 13 is a schematic structural diagram of an electronic device provided in Embodiment Five of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0122] As Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0123] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0124] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the network quality assessment method.

[0125] In some embodiments, the network quality assessment method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the network quality assessment method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the network quality assessment method by any other appropriate means (e.g., by means of firmware).

[0126] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] The computer programs for implementing the network quality assessment method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general purpose computer, a special purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0128] Embodiment Six

[0129] Embodiment Six of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a network quality assessment method, the method including:

[0130] Determining a set of grid cells in a target detection area, obtaining detection data of the target detection area, and determining detected grid cells and undetected grid cell sets in the set of grid cells based on the detection data, where the set of grid cells is obtained by performing three-dimensional grid partitioning processing on the target detection area based on preset three-dimensional grid size data;

[0131] Obtaining network management data of the target detection area, and determining grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data;

[0132] For undetected grid cells, determining grid cell clusters corresponding to the undetected grid cells, and determining grid network attribute data of the undetected grid cells based on the detection data respectively corresponding to at least one detected grid cell in the grid cell clusters;

[0133] For any grid cell in the set of grid cells, determine the network quality assessment result of the grid cell based on the grid network attribute data of the grid cell.

[0134] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0135] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, speech input, or tactile input).

[0136] The systems and techniques described herein can be implemented in a computing system including a backend component (e.g., as a data server), or a computing system including a middleware component (e.g., an application server), or a computing system including a frontend component (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0137] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0138] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0139] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. 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 principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A network quality assessment method, characterized in that: include: Determine a grid unit set of a target detection area, obtain detection data of the target detection area, and determine a detected grid unit set and an undetected grid unit set in the grid unit set based on the detection data, wherein the grid unit set is obtained by performing a three-dimensional grid division process on the target detection area based on preset three-dimensional grid size data; Acquire network management data of the target detection area, and determine grid network attribute data of each detected grid cell in the set of detected grid cells based on the detection data and the network management data; For the undetected grid cell, determine a grid cell cluster corresponding to the undetected grid cell, and determine grid network attribute data of the undetected grid cell based on detection data respectively corresponding to at least one detected grid cell in the grid cell cluster; For any grid cell in the grid cell set, a network quality assessment result of the grid cell is determined based on the grid network attribute data of the grid cell.

2. The method according to claim 1, characterized in that The detection data includes detection point position data of a plurality of detection points; The determining, based on the detection data, a detected grid cell set and an undetected grid cell set in the grid cell set comprises: Matching the detection point position data of each detection point with the grid position data of each grid cell in the grid cell set to determine the matching result of each grid cell in the grid cell set; The detected grid cell set is formed based on a plurality of grid cells whose matching results are successful, and the undetected grid cell set is formed based on a plurality of grid cells whose matching results are failed.

3. The method according to claim 1, characterized in that in, The detection data includes the network cell identification and network cell signal detection data of each detection point; The determining of grid network attribute data of each detected grid cell in the set of detected grid cells based on the detection data and the network management data comprises: For each of the detected grid cells, determining first network characteristic data of the detected grid cell based on the network cell signal detection data of each of the detection points in the detected grid cell, wherein the first network characteristic data includes signal receiving power data, signal-to-noise ratio data, bit error rate data and dominant ratio data; Based on the network cell identifier of each detection point in the detected grid unit, the network management data is matched to obtain second network indicator data that meets the preset grouping condition, and the second network characteristic data of the detected grid unit is determined based on the second network indicator data, wherein the preset grouping condition includes one or more of a time grouping condition and a service grouping condition; The grid network attribute data of the detected grid cells is determined based on the first network feature data and the second network feature data.

4. The method according to claim 1, characterized in that: The determining of the grid network attribute data of the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster comprises: Calibrate the pre-built signal propagation model based on the detection data corresponding to at least one detected grid cell in the grid cell cluster to obtain a target signal propagation model; Determine the signal strength feature vector corresponding to the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster, the network management data and the target signal propagation model; A pre-trained network signal index prediction model is called, and grid network attribute data of the undetected grid is determined through the pre-trained network signal index prediction model and the signal strength feature vector corresponding to the undetected grid unit.

5. The method according to claim 4, characterized in that The determining the signal strength feature vector corresponding to the undetected grid cell based on the detection data respectively corresponding to at least one detected grid cell in the grid cell cluster, the network management data and the target signal propagation model comprises: Determine the network cell identifier of at least one candidate network cell corresponding to the undetected grid cell based on the detection data corresponding to the at least one detected grid cell, and determine the basic feature information corresponding to each of the candidate network cells based on the network cell identifier of the at least one candidate network cell and the network management data, wherein the basic feature information includes distance information between the network cell and the undetected grid cell, signal frequency information, network cell height information, and height information of the undetected grid cell; Determine the signal strength characteristic data corresponding to each of the candidate network cells based on the basic characteristic information corresponding to each of the candidate network cells and the target signal propagation model; A signal strength feature vector corresponding to the undetected grid unit is constructed based on the network cell identifier and signal strength feature data corresponding to each of the candidate network cells.

6. The method according to claim 1, characterized in that The detection data of the target detection area is obtained by detection of a target detection device, which is configured on a flight device. The flight device carries the target detection device to perform a test task within the target detection area to obtain the detection data of the target detection area; The step of determining, for any grid cell in the grid cell set, a network quality assessment result of the grid cell based on grid network attribute data of the grid cell comprises: Determining a network evaluation coefficient and a flight coefficient, wherein the flight coefficient is determined based on a flight speed of the flight device in a region corresponding to the grid unit during execution of the test task; The grid network attribute data of the grid unit is weighted based on the network evaluation coefficient and the flight coefficient to obtain a network quality evaluation result of the grid unit.

7. The method according to claim 6, characterized in that The method further comprises: In the process of the target detection device executing the test task, receiving device operation data transmitted by the target detection device; When abnormal event data is identified in the device operation data, a control instruction is generated based on the abnormal event data and sent to the target detection device to control the target detection device to perform an abnormal handling operation, wherein the control instruction includes any one of a test task restart instruction and a flight termination instruction for the flight equipment.

8. A network quality assessment device, characterized in that: include: A grid cell classification module is used to determine a grid cell set of a target detection area, obtain detection data of the target detection area, and determine a detected grid cell set and an undetected grid cell set in the grid cell set based on the detection data, wherein the grid cell set is obtained by performing a three-dimensional grid division process on the target detection area based on preset three-dimensional grid size data; A first grid network attribute data determination module is used to obtain network management data of the target detection area, and determine grid network attribute data of each detected grid cell in the detected grid cell set based on the detection data and the network management data; A second grid network attribute data determination module is used to determine, for the undetected grid cell, a grid cell cluster corresponding to the undetected grid cell, and determine the grid network attribute data of the undetected grid cell based on detection data respectively corresponding to at least one detected grid cell in the grid cell cluster; The network quality assessment result determination module is used to determine the network quality assessment result of any grid cell in the grid cell set based on the grid network attribute data of the grid cell.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the network quality assessment method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the network quality assessment method according to any one of claims 1 to 7 when executed.

Images