Network quality assessment method, device, equipment and storage medium

By dividing the high-speed rail lines into high-speed rail grids and obtaining the target user terminal data, evaluating the quality of the high-speed rail network based on the signal transmission model, the problems of positioning deviation and inaccurate evaluation in the existing technology are solved, and the accurate evaluation and cost saving of the high-speed rail network are achieved .

CN114422949BActive Publication Date: 2024-11-29CHINA TELECOM CORP LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202111649900.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-29
Publication Date
2024-11-29
Estimated Expiration
2041-12-29

AI Technical Summary

Technical Problem

The prior art has problems such as positioning deviation, inaccurate evaluation, time-consuming and short time-consuming in high-speed rail network quality assessment, especially the inability to accurately reflect the network usage and coverage blind spots of user terminals in high-speed rail trains.

Method used

By dividing the high-speed rail line into multiple high-speed rail grids, each grid corresponds to a service cell, the measurement report data of the target user terminal is obtained, and the signal strength is determined based on the average reference signal reception power and signal transmission model, so as to achieve accurate high-speed rail network quality Evaluate.

Benefits of technology

It improves the accuracy and credibility of network quality assessment, saves costs, and realizes accurate virtual road testing of high-speed rail for 4G/5G, and promptly discovers sections of roads with poor network quality and blind coverage areas.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114422949B_ABST
    Figure CN114422949B_ABST
Patent Text Reader

Abstract

The present application provides a network quality assessment method, device, equipment and storage medium, the method comprising: dividing a high-speed rail line into multiple high-speed rail grids according to a preset division rule and determining at least one service cell corresponding to each high-speed rail grid; obtaining target MR data corresponding to multiple target user terminals in a target time period; for each service cell, determining a cell signal transmission model corresponding to the service cell according to a first average RSRP corresponding to the service cell in the target time period and a target signal transmission model matching the service cell; for each high-speed rail grid, determining a signal strength corresponding to the high-speed rail grid according to the target RSRP corresponding to the service cell of the high-speed rail grid. The present application can obtain real and comprehensive target MR data based on the identified real user terminal of the high-speed rail, and determine the cell signal transmission model using the target MR data and the target signal transmission model, so as to obtain a highly credible and targeted network quality assessment result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a network quality assessment method, device, equipment and storage medium. Background Art

[0002] With the rapid development of high-speed rail, people hope to enjoy stable and high-quality mobile business services while traveling by high-speed rail. Therefore, high-speed rail users have become a user group that all operators focus on.

[0003] In the context of current mobile communication networks, Assisted Global Positioning System (AGPS), fingerprint positioning, triangulation positioning and other methods are often used to render the position of user terminals based on Measurement Report (MR) data to perform virtual drive test evaluation of 4G networks. Among them, the AGPS method performs virtual drive test evaluation based on positioning information; the fingerprint positioning method uses the signal features containing positioning information in MR data (such as primary neighbor cells, signal strength, etc.) for machine learning, establishes a fingerprint library, and predicts the position of the user terminal corresponding to the MR data without AGPS based on the fingerprint library to perform virtual drive test evaluation; the triangulation positioning method performs virtual drive test evaluation based on calculation.

[0004] For the AGPS method and the fingerprint positioning method, due to the high-speed movement of high-speed trains, the AGPS positioning in the user terminal will produce a large deviation (the deviation is generally more than 300 meters), which is not conducive to accurate positioning. At present, MR data with AGPS positioning information only accounts for about 2%-3% of the total data, and the amount of data on narrow and long high-speed rail lines is even less, which cannot cover all high-speed rail lines, so it is impossible to accurately evaluate the high-speed rail network. At present, 5G user terminals do not support MR data reporting AGPS longitude and latitude, so the above two methods do not support 5G virtual road testing. For the triangulation positioning method, there is also the problem of insufficient calculation accuracy.

[0005] For the AGPS method, fingerprint positioning method and triangulation positioning method, the MR data output by the user terminal cannot distinguish whether it is generated by the user terminal in the high-speed train or the user terminal resident around the high-speed rail line. That is, the obtained MR data cannot reflect the actual network usage of the user terminal in the high-speed train.

[0006] In the prior art, high-speed rail network quality measurement can also be performed based on a remote control unit (RCU). Testers are required to carry an RCU instrument and take the high-speed rail for testing. This method requires measurement at regular intervals. The network quality assessment is time-consuming, labor-intensive, and expensive, and the assessment results are short in timeliness. At the same time, it is not conducive to timely discovery of sections with poor network quality and network coverage blind spots.

[0007] It can be seen that in the prior art, when evaluating the quality of the high-speed rail network based on MR data, there is a problem that the obtained MR data cannot reflect the actual network usage of user terminals in the high-speed rail train and the high-speed rail network evaluation is inaccurate; when evaluating the quality of the high-speed rail network based on RCU, there are problems that the network quality evaluation is time-consuming, labor-intensive, and expensive, the evaluation results are short in timeliness, and it is not conducive to timely discovering sections with poor network quality and network coverage blind spots. Summary of the invention

[0008] In view of the above problems, embodiments of the present application provide a network quality assessment method, apparatus, device and storage medium that overcome the above problems or at least partially solve the above problems.

[0009] In a first aspect, an embodiment of the present application provides a network quality assessment method, including:

[0010] Divide the high-speed rail line into a plurality of high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, each of the high-speed rail grids corresponding to a regional range;

[0011] Acquire target measurement report MR data corresponding to multiple target user terminals within a target period, wherein the target user terminals are high-speed rail user terminals;

[0012] For each of the serving cells, determining a cell signal transmission model corresponding to the serving cell according to a first average reference signal received power RSRP corresponding to the serving cell in the target time period and a target signal transmission model matched with the serving cell, wherein the first average RSRP is determined based on target MR data corresponding to the serving cell in the target time period;

[0013] For each of the high-speed rail grids, the signal strength corresponding to the high-speed rail grid is determined according to the target RSRP corresponding to at least one serving cell of the high-speed rail grid, and the target RSRP is determined based on the corresponding cell signal transmission model.

[0014] In a second aspect, an embodiment of the present application provides a network quality assessment device, including:

[0015] A division determination module, used to divide the high-speed rail line into a plurality of high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, each of the high-speed rail grids corresponding to an area range;

[0016] A first acquisition module is used to acquire target measurement report MR data corresponding to multiple target user terminals within a target period, wherein the target user terminals are high-speed rail user terminals;

[0017] A first determining module is used to determine, for each of the serving cells, a cell signal transmission model corresponding to the serving cell according to a first average reference signal received power RSRP corresponding to the serving cell in the target time period and a target signal transmission model matched with the serving cell, wherein the first average RSRP is determined based on target MR data corresponding to the serving cell in the target time period;

[0018] The second determination module is used to determine the signal strength corresponding to each high-speed rail grid according to the target RSRP corresponding to at least one service cell of the high-speed rail grid, and the target RSRP is determined based on the corresponding cell signal transmission model.

[0019] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the network quality assessment method described in the first aspect.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the network quality assessment method described in the first aspect are implemented.

[0021] The technical solution of the embodiment of the present application divides the high-speed rail line into multiple high-speed rail grids, determines at least one service cell corresponding to each high-speed rail grid, obtains target MR data corresponding to multiple target user terminals in a target time period, obtains the first average RSRP corresponding to each service cell in the target time period based on the target MR data, so as to determine the cell signal transmission model corresponding to the service cell, determines the target RSRP corresponding to the service cell based on the cell signal transmission model, and determines the signal strength of the high-speed rail grid according to the correspondence between the high-speed rail grid and the service cell. It can be achieved that real and comprehensive target MR data is obtained based on the identified real user terminal of the high-speed rail, the cell signal transmission model is determined by using the target MR data and the target signal transmission model, so as to determine the target RSRP corresponding to the service cell based on the cell signal transmission model, and the high-speed rail network signal quality is located in the high-speed rail grid according to the correspondence between the service cell and the high-speed rail grid, so as to obtain a network quality evaluation result with relatively high credibility and stronger pertinence.

[0022] And because the target signal transmission model can be corrected based on the target MR data to determine the cell signal transmission model, there is no need to determine the signal transmission model multiple times, saving network quality assessment costs as well as time and labor costs; and the present application can realize 4G / 5G universal high-speed rail precise virtual road testing, and is conducive to timely discovery of sections with poor network quality and network coverage blind spots. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram showing a network quality assessment method provided in an embodiment of the present application;

[0024] Figure 2 A specific schematic diagram showing the gear division corresponding to the antenna hanging height, antenna tilt angle, and antenna transmission power provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram showing a specific example of a high-speed rail grid and an associated service cell provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram showing a specific example of determining the signal strength corresponding to a high-speed rail grid provided in an embodiment of the present application;

[0027] Figure 5 The overall flow chart of the network quality assessment method provided by the embodiment of the present application is shown;

[0028] Figure 6 A schematic diagram showing a network quality assessment device provided in an embodiment of the present application;

[0029] Figure 7 A structural block diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present application. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0032] In the various embodiments of the present application, it should be understood that the size of the serial numbers of the following processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0033] This application embodiment provides a network quality assessment method, see Figure 1 As shown, including:

[0034] Step 101: divide the high-speed rail line into a plurality of high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, wherein each of the high-speed rail grids corresponds to an area range.

[0035] The network quality assessment method provided in the embodiment of the present application is applied to a data processing platform. First, the high-speed rail line is divided into a plurality of high-speed rail grids based on a preset division rule. The plurality of high-speed rail grids are arranged in sequence along the high-speed rail line. For each high-speed rail grid, it may correspond to a regional range. The regional ranges corresponding to two adjacent high-speed rail grids are geographically continuous, and the areas of the regional ranges corresponding to the high-speed rail grids are equal. For example, the high-speed rail line is divided into a plurality of high-speed rail grids along the line according to a range of 50 meters by 50 meters, a range of 50 meters by 100 meters, or a range of 50 meters by 150 meters. When dividing the high-speed rail grids, the division may be performed on the route map corresponding to the high-speed rail line.

[0036] After the high-speed rail line is divided into multiple high-speed rail grids based on the preset division rule, one or more service cells corresponding to the current high-speed rail grid can be determined for each high-speed rail grid, and the multiple service cells corresponding to the current high-speed rail grid can belong to the same or different base stations. The service cell in this embodiment is the service cell corresponding to the high-speed rail line.

[0037] Step 102: Obtain target measurement report MR data corresponding to multiple target user terminals within a target period, wherein the target user terminals are high-speed rail user terminals.

[0038] The target MR data corresponding to the high-speed rail user terminal on the high-speed rail line within the target time period is obtained. The high-speed rail user terminal is a real high-speed rail user terminal moving along the high-speed rail line. The duration corresponding to the target time period is pre-set, such as 3 hours, 5 hours or 8 hours, or it can be one day or two days.

[0039] When obtaining target MR data corresponding to multiple target user terminals within a target time period, it is first necessary to filter out the target user terminals from the user terminal set. The user terminal set may include surrounding resident user terminals along the high-speed rail line and real high-speed rail user terminals. The surrounding resident user terminals cannot reflect the network quality inside the high-speed rail train, so these user terminals need to be filtered out.

[0040] Step 103: For each of the service cells, determine the cell signal transmission model corresponding to the service cell according to the first average reference signal received power RSRP corresponding to the service cell in the target time period and the target signal transmission model matching the service cell, wherein the first average RSRP is determined based on the target MR data corresponding to the service cell in the target time period.

[0041] For each of the multiple service cells corresponding to the high-speed rail line, based on the target MR data corresponding to the service cell in the target time period (the target MR data here is the filtered data that meets the requirements, specifically the MR data associated with the high-speed rail line), the first average reference signal receiving power (RSRP) corresponding to the service cell in the target time period is obtained. The target signal transmission model matching the service cell is obtained, and based on the target signal transmission model, the target signal transmission model is corrected in combination with the first average RSRP corresponding to the service cell to determine the cell signal transmission model corresponding to the service cell.

[0042] The target signal transmission model is a model among a preset number of signal transmission models, and the preset number of signal transmission models are determined based on data collected when the RCU performs network signal measurement on the high-speed railway line.

[0043] Step 104: for each of the high-speed rail grids, determine the signal strength corresponding to the high-speed rail grid according to the target RSRP corresponding to at least one serving cell of the high-speed rail grid, wherein the target RSRP is determined based on the corresponding cell signal transmission model.

[0044] For each of the multiple high-speed rail grids on the high-speed rail line, since the high-speed rail grid corresponds to at least one service cell, the target RSRP corresponding to the service cell can be obtained based on the cell signal transmission model corresponding to the service cell. For the target RSRP corresponding to at least one service cell, a preset calculation rule is used to calculate to obtain the signal strength corresponding to the high-speed rail grid, and the high-speed rail network quality (network signal quality) is located in the high-speed rail grid, realizing 4G / 5G universal high-speed rail precise virtual road testing, and improving the accuracy of locating network quality problem points.

[0045] The above-mentioned implementation process of the present application divides the high-speed rail line into multiple high-speed rail grids, determines at least one service cell corresponding to each high-speed rail grid, obtains the target MR data corresponding to the target user terminal in the target time period, obtains the first average RSRP corresponding to each service cell in the target time period based on the target MR data, so as to determine the cell signal transmission model corresponding to the service cell, determines the target RSRP corresponding to the service cell based on the cell signal transmission model, and determines the signal strength of the high-speed rail grid according to the correspondence between the high-speed rail grid and the service cell. It can be achieved that based on the identified real user terminal of the high-speed rail, real and comprehensive target MR data is obtained, the cell signal transmission model is determined by using the target MR data and the target signal transmission model, so as to determine the target RSRP corresponding to the service cell based on the cell signal transmission model, and the high-speed rail network signal quality is located in the high-speed rail grid according to the correspondence between the service cell and the high-speed rail grid, so as to obtain a network quality evaluation result with relatively high credibility and stronger pertinence.

[0046] And because the target signal transmission model can be corrected based on the target MR data to determine the cell signal transmission model, there is no need to determine the signal transmission model multiple times, saving network quality assessment costs as well as time and labor costs; and the present application can realize 4G / 5G universal high-speed rail precise virtual road testing, and is conducive to timely discovery of sections with poor network quality and network coverage blind spots.

[0047] Wherein, step 101 determines at least one serving cell corresponding to each high-speed railway grid, including:

[0048] For each of the high-speed rail grids, determining the serving cells corresponding to at least one first sampling geographical location in the high-speed rail grid as the serving cells corresponding to the high-speed rail grid;

[0049] The first sampling geographical location is the geographical location corresponding to the remote control unit RCU when performing network signal sampling.

[0050] When determining the service cell corresponding to the high-speed rail grid, at least one first sampling geographical location within the high-speed rail grid can be determined for each high-speed rail grid, and the first sampling geographical location is the geographical location determined by the RCU based on high-precision positioning when sampling the network signal. During the entire process of the high-speed rail running along the corresponding high-speed rail line, the RCU can sample the network signal at a specific sampling frequency, and each sampling moment corresponds to a first sampling geographical location. The service cell corresponding to the high-speed rail grid is the service cell on the high-speed rail line.

[0051] When determining at least one first sampling geographical location corresponding to the high-speed rail grid, it can be judged based on whether the longitude and latitude of the first sampling geographical location is located within the high-speed rail grid. If the longitude and latitude of the first sampling geographical location are located within the high-speed rail grid, the service cell corresponding to the first sampling geographical location is determined as the service cell corresponding to the high-speed rail grid, and a corresponding relationship between the high-speed rail grid and the service cell is established. Since the first sampling geographical location is determined based on high-precision positioning, the accuracy of determining the service cell corresponding to the high-speed rail grid can be guaranteed.

[0052] In this embodiment, a high-speed rail grid information library can also be generated, which includes the high-speed rail grid ID, the high-speed rail line corresponding to the high-speed rail grid, the area where the high-speed rail grid is located, the longitude and latitude corresponding to the four corners of the high-speed rail grid, the longitude and latitude corresponding to the center of the high-speed rail grid, and the service cell corresponding to the high-speed rail grid. For each high-speed rail line, a high-speed rail grid information library can be corresponding.

[0053] It should be noted that the service cells that meet the distance and azimuth conditions around the high-speed rail grid can also be scanned for supplementary entry to achieve dynamic update of the high-speed rail grid information library. Among them, when scanning the service cell, the service cell scan can be performed according to the preset trigger conditions, such as scanning according to the preset scanning frequency. The service cell that meets the distance and azimuth conditions around the high-speed rail grid can be a cell where the distance between the center of the service cell and the center of the high-speed rail grid is less than the preset distance, and the angle between the antenna azimuth corresponding to the base station to which the service cell belongs and the vertical line corresponding to the high-speed rail line is less than a preset angle (such as 90 degrees).

[0054] In the above implementation process of the present application, after the high-speed rail line is divided into multiple high-speed rail grids, for each high-speed rail grid, at least one first sampling geographical location corresponding to the high-speed rail grid is obtained, and the service cell corresponding to the at least one first sampling geographical location is determined as the service cell corresponding to the high-speed rail grid, so that the service cell can be determined based on the longitude and latitude of the first sampling geographical location and the positional relationship of the high-speed rail grid.

[0055] Wherein, step 102 obtains target measurement report MR data corresponding to multiple target user terminals within a target period, including:

[0056] Based on the deep data packet inspection DPI signaling sent by the user terminal, determine the target user terminal that moves along the high-speed railway line during at least a part of the time interval of the target time period according to the DPI signaling, so as to obtain a plurality of the target user terminals;

[0057] Acquire target MR data corresponding to the plurality of target user terminals when they move along the high-speed railway line within the target time period.

[0058] When obtaining target MR data corresponding to multiple target user terminals within a target time period, multiple target user terminals can be first screened in a user terminal set, where the user terminal set includes all user terminals associated with the current high-speed rail line within the target time period, and specifically may include surrounding resident user terminals along the high-speed rail line and real high-speed rail user terminals (target user terminals).

[0059] When screening multiple target user terminals, based on the deep packet inspection (DPI) signaling sent by the user terminal to the base station, the target user terminal that moves along the high-speed rail line in at least part of the time interval of the target period is determined. For each target user terminal, the movement trajectory of the DPI signaling matches the high-speed rail line, that is, the DPI signaling moves along at least part of the line of the high-speed rail line. Wherein the data processing platform in this embodiment can monitor the DPI signaling sent by the user terminal to the base station. In the target period, at least one batch of high-speed rail real user terminals can be obtained, such as, the target period is one day, the high-speed rail line is from A to B, and there are 3 high-speed rails from A to B in one day, and the operating time periods are 9 to 11, 12:05, 14:05, and 16:30 to 18:30, respectively, then 3 batches of real high-speed rail user terminals can be obtained, and multiple target user terminals are determined based on the obtained 3 batches of real high-speed rail user terminals. For 4G networks, the target user terminal is determined based on the mobile trajectory of the DPI S1-mobility management entity (Mobility Management Entity, MME) signaling generated by the user terminal; for 5G networks, the target user terminal is determined based on the mobile trajectory of the DPI N1N2 signaling generated by the user.

[0060] Among them, when determining the target user terminal based on the trajectory of DPI signaling, user terminals whose DPI signaling has occupied the service cells corresponding to at least two different stations or occupied the service cells corresponding to the provincial border can be retained. For example, the DPI signaling corresponding to the high-speed rail line from 7:00 to 22:00 on a certain day is counted, and user terminals that have occupied the service cells corresponding to at least two different stations are screened out based on the DPI signaling, so as to screen out multiple target user terminals. Of course, determining the target user terminal based on the trajectory of DPI signaling is not limited to the above method.

[0061] After screening out multiple target user terminals, the MR data corresponding to the multiple target user terminals when they move along the high-speed rail line within the target time period can be obtained, and the MR data obtained at this time is the target MR data. When obtaining the target MR data corresponding to the multiple target user terminals, all the MR data corresponding to the multiple target user terminals within the target time period can be obtained, and then based on the occupation of the service cells corresponding to the high-speed rail line by the multiple target user terminals, the target MR data corresponding to the multiple target user terminals when they move along the high-speed rail line are screened out. When obtaining the target MR data corresponding to the multiple target user terminals, the target time interval (the interval for moving along the high-speed rail line) corresponding to the target user terminal within the target time period can also be determined, and the corresponding MR data within the target time interval is obtained to obtain the target MR data.

[0062] The above implementation process of the present application can accurately identify the real user terminals of the high-speed railway by moving along the high-speed railway line based on the behavioral characteristics of the signaling trajectory, and screen out the target MR data corresponding to the real user terminals of the high-speed railway when moving along the high-speed railway line. It can obtain real and comprehensive target MR data, so as to facilitate network quality assessment based on the real and comprehensive target MR data.

[0063] In an optional embodiment of the present application, after acquiring target MR data corresponding to the plurality of target user terminals in the target time period, the method further includes:

[0064] Generate an MR statistical database corresponding to the high-speed rail user terminal according to the acquired target MR data;

[0065] Among them, the MR statistical database includes at least part of the cell identifiers, first average RSRP, number of sampling points, geographic location information and base station parameters corresponding to multiple service cells associated with the high-speed rail line during the target time period, and the first average RSRP corresponding to the service cell during the target time period is determined based on the MR statistical database.

[0066] After obtaining the target MR data corresponding to multiple target user terminals in the target time period, an MR statistical database corresponding to the high-speed rail user terminal in the target time period can be generated based on the obtained target MR data. The content in the MR statistical database is dynamically updated according to the update of the time period, and the target MR data includes: user terminal identification (number corresponding to the user terminal), visited service cell, RSRP corresponding to the service cell, and may also include the longitude and latitude corresponding to the user terminal when reporting data. Since the target MR data is the MR data corresponding to the target user terminal when it moves along the high-speed rail line, the service cells in this embodiment are all service cells corresponding to the high-speed rail line.

[0067] The MR statistical database may include at least part of the following contents: cell identifiers corresponding to multiple service cells associated with the high-speed rail line during the target time period, the first average RSRP corresponding to the multiple service cells, the number of sampling points corresponding to the multiple service cells (the number of sampling points is the number of target MR data corresponding to the service cells), the geographical location information corresponding to the multiple service cells, and the base station parameters corresponding to the multiple service cells.

[0068] Since the target MR data may include the service cells accessed by the user terminal, and each service cell is distinguished by a cell identifier, the cell identifiers corresponding to the multiple service cells associated with the high-speed rail line during the target period can be determined, and the cell identifier can be a cell name or a cell number. For each service cell associated with the high-speed rail line during the target period, the geographical location information corresponding to the service cell is predetermined and can be stored in the MR statistical database.

[0069] It should be noted that the target MR data may include the latitude and longitude corresponding to the user terminal when reporting data (the latitude and longitude can be reported when the user terminal turns on the positioning function). The latitude and longitude reported here are the second sampling geographical location corresponding to the user terminal. When the train moves at high speed, the positioning of the user terminal is prone to deviation, so the second sampling geographical location is only used as a reference. For the service cell, the number of second sampling geographical locations corresponding to the service cell can be determined. Since some target MR data do not include latitude and longitude information, the number of sampling points corresponding to the service cell is greater than the number of second sampling geographical locations.

[0070] For each service cell, the base station parameters corresponding to the service cell can also be obtained, wherein the base station parameters include antenna hanging height, antenna tilt angle, and maximum transmission power supported by the antenna. Since the acquired target MR data includes the RSRP corresponding to the service cell accessed by the target user terminal (the service cell corresponding to the high-speed rail line), according to the target MR data corresponding to multiple target user terminals in the target time period, the first average RSRP corresponding to each service cell (the service cell corresponding to the high-speed rail line) in the target time period can also be determined, that is, for each service cell (the service cell corresponding to the high-speed rail line), the average can be calculated based on the multiple RSRPs corresponding to the corresponding target user terminal in the target time period when accessing the current service cell (the service cell corresponding to the high-speed rail line), and the first average RSRP is determined and stored in the MR statistical database. When obtaining the first average RSRP corresponding to the service cell (the service cell corresponding to the high-speed rail line) in the target time period, it can be directly obtained through the MR statistical database.

[0071] In the above implementation process of the present application, after obtaining the target MR data corresponding to multiple target user terminals within the target time period, an MR statistical database corresponding to the high-speed rail user terminal is generated based on the obtained target MR data, and information associated with the target user terminal can be stored for subsequent use.

[0072] In an optional embodiment of the present application, the method further includes:

[0073] Acquire drive test data obtained by a remote control unit RCU sampling a network signal on the high-speed railway line, wherein the drive test data at least includes a first sampling geographical location, a serving cell corresponding to the first sampling geographical location, and an RSRP corresponding to the first sampling geographical location;

[0074] According to base station parameters corresponding to the base station to which the serving cell belongs, the drive test data is divided into a preset number of categories to obtain a preset number of second data sets;

[0075] Performing machine learning on each of the second data sets to obtain a preset number of signal transmission models, where the signal transmission model is used to characterize a mapping relationship between the first distance and the RSRP;

[0076] Among them, the first distance is the distance between the first sampling geographical location and the center point of the target base station, the target base station is the base station to which the service cell corresponding to the first sampling geographical location belongs, and the target signal transmission model is one of a preset number of the signal transmission models.

[0077] During the entire process of the high-speed rail running along the corresponding high-speed rail line, the RCU can sample the network signal at a specific sampling frequency, and the data processing platform can obtain the road test data obtained by the RCU through network signal sampling. The road test data at least includes the first sampling geographical location, the service cell corresponding to the first sampling geographical location, and the RSRP corresponding to the first sampling geographical location. Since the RCU performs sampling during the operation of the high-speed rail, the service cell in this embodiment is the service cell corresponding to the high-speed rail line.

[0078] Since the road test data includes the service cell corresponding to the first sampling geographic location, the base station parameters corresponding to the service cell can be obtained. After obtaining the road test data, the drive test data can be divided into a preset number of categories according to the base station parameters to obtain a preset number of second data sets, each of which includes data of the corresponding category.

[0079] For each second data set, machine learning is performed based on the data corresponding to the second data set to determine a signal transmission model used to characterize the mapping relationship between the first distance and RSRP to obtain a preset number of signal transmission models, and the target signal transmission model is one of the preset number of signal transmission models.

[0080] Among them, the first distance is the distance between the first sampling geographical location and the center point of the target base station, and the target base station is the base station to which the service cell corresponding to the first sampling geographical location belongs. Since the road test data includes the first sampling geographical location, the service cell corresponding to the first sampling geographical location, and the RSRP corresponding to the first sampling geographical location, a mapping relationship between the distance and the RSRP can be formed.

[0081] Among them, the base station parameters include antenna hanging height, antenna tilt angle, and maximum transmit power supported by the antenna. When the drive test data is divided into a preset number of categories according to the base station parameters, the categories can be divided according to the above parameters. For each parameter, it can correspond to multiple gears. The gear here can be understood as a parameter range, and each gear can correspond to a type of data. For example, according to the antenna hanging height (3 gears), the antenna tilt angle (3 gears), and the maximum transmit power supported by the antenna (3 gears), the drive test data is divided into 3x3x3=27 combinations, and each combination corresponds to a type of combined data.

[0082] See also Figure 2 As shown, the antenna height below 30 meters corresponds to the first high hanging position, the antenna height between 30 meters and 40 meters corresponds to the second high hanging position, and the antenna height above 40 meters corresponds to the third high hanging position; the antenna tilt angle of 3 degrees and below corresponds to the first tilt angle position, the antenna tilt angle of 4 degrees to 6 degrees corresponds to the second tilt angle position, and the antenna tilt angle of 7 degrees and above corresponds to the third tilt angle position; the maximum transmission power supported by the antenna is 40w and below, which corresponds to the first power position, the maximum transmission power supported by the antenna is 60w, which corresponds to the second power position, and the maximum transmission power supported by the antenna is 80w, which corresponds to the third power position. According to the position combinations between the three parameters (each parameter corresponds to three positions) (each combination corresponds to three parameters), 27 classifications can be obtained. For example, one combination corresponds to an antenna height of less than 30 meters, an antenna tilt angle of less than or equal to 3 degrees, and a maximum transmit power supported by the antenna of 60w; one combination corresponds to an antenna height of between 30 meters and 40 meters, an antenna tilt angle of less than or equal to 3 degrees, and a maximum transmit power supported by the antenna of 80w; one combination corresponds to an antenna height of greater than 40 meters, an antenna tilt angle of greater than 3 degrees and less than or equal to 6 degrees, and a maximum transmit power supported by the antenna of 80w. Other situations are not listed here.

[0083] After obtaining a preset number of second data sets, performing machine learning on each second data set to obtain a preset number of signal transmission models includes the following steps:

[0084] For each of the second data sets, edge sampling geographical locations are filtered using a preset principle to perform data cleaning to obtain a second target data set;

[0085] For each of the second target data sets, performing high-order curve fitting on the second target data set using the least square method to determine a first curve;

[0086] For each of the first curves, overfitting correction is performed based on a ridge regression algorithm to determine the signal transmission model, where the signal transmission model is a second curve that characterizes a mapping relationship between the first distance and RSRP.

[0087] When performing machine learning on each second data set to generate a corresponding signal transmission model, data cleaning can be first performed on the second data set to obtain a second target data set. For the second target data set, least squares can be used to perform high-order curve fitting to determine the first curve, and then overfitting correction can be performed based on the ridge regression algorithm to obtain the signal transmission model.

[0088] The following is a detailed introduction to the process of data cleaning, determining the first curve, and correcting the first curve for the second data set.

[0089] The road test data (a second data set) with the same antenna high gear, antenna tilt gear, and maximum transmission power gear are divided into multiple intervals according to a specific distance interval (such as 200m). The points in each interval are statistically analyzed according to the normal distribution, and the edge data is cleaned according to the 2σ criterion (μ-2σ, the probability in μ+2σ is 0.9545). Among them, the second data set corresponds to multiple groups of data, each group of data corresponds to a geographical location and a parameter RSRP that characterizes the signal strength. The specific distance interval refers to the distance between the geographical location and the corresponding base station center, and the points in each interval correspond to the sampling points. By performing edge data cleaning, a part of the data can be filtered out, and the second target data set can be determined based on the retained data.

[0090] When the least square method is used to perform high-order curve fitting on the second target data set, for any set of data (x i ,y i )(i=1,2,3……,m) fits the function h(x)=w0+w1x+w2x 2 +…+w n x nWhere m refers to the number of data sampling points corresponding to the second target data set. For each data sampling point, it corresponds to a set of data (distance and RSRP). For each data sampling point, the function h(x) can be fitted, w0, w1, w2... and w n are all coefficients. The following formula is used to minimize the sum of squares of the residuals of the fitting, namely:

[0091]

[0092] The first curve can be fitted through the above process. It should be noted that the corresponding multiple sets of data in the above process can be aggregated and represented by matrix X and matrix Y, that is, based on the above fitting process, a function H=WX can be established, where W is the matrix representation of the coefficients, X is the matrix representation of x in multiple sets of data, and H represents a matrix determined based on multiple h(x). The formula for minimizing the residual sum of squares is expressed as:

[0093] min(Y-WX) 2

[0094] Based on the residual square sum formula, the partial derivative of W is calculated and made equal to 0 to obtain W (as shown below), and then the first curve can be fitted.

[0095] W=(X T X) -1 X T Y

[0096] After obtaining the first curve, it is necessary to correct the overfitting of the first curve based on the ridge regression algorithm to determine the second curve representing the mapping relationship between the first distance and RSRP. The second curve here is the signal transmission model, which can be understood as the curve representation of the signal transmission model. The process of overfitting correction is described below:

[0097] Add a regularization term to the residual sum of squares in the least squares method, that is

[0098] min[(Y-WX) 2 +(αIW) 2 ]

[0099] Among them, I is the identity matrix, and α is the hyperparameter of the signal transmission model, which is set manually.

[0100] Then W=(X T X+αI) -1 X T Y

[0101] When α is equal to 0, it degenerates into the least squares method. Aiming at the weakness that the road test data is prone to overfitting, by abandoning the unbiasedness of the least squares method, a regression prediction curve with a lower order smooth curve that is more in line with reality is obtained. That is, based on this formula, by selecting a suitable α value, a second curve that is a correction of the first curve can be obtained.

[0102] In the above implementation process of the present application, by acquiring road test data, the road test data is divided into a preset number of categories based on base station parameters, and machine learning is performed on the data of each category to determine a preset number of signal transmission models. A cell signal transmission model can be constructed based on the determined signal transmission model to lay a foundation for the subsequent targeted acquisition of network quality assessment results.

[0103] In an optional embodiment of the present application, for each of the serving cells, determining the cell signal transmission model corresponding to the serving cell according to the first average reference signal received power RSRP corresponding to the serving cell in the target time period and the target signal transmission model matched with the serving cell, includes:

[0104] For each of the serving cells, according to base station parameters corresponding to the base station to which the serving cell belongs, determining the target signal transmission model from a preset number of signal transmission models, each of the signal transmission models corresponding to a type of base station parameters;

[0105] Acquire a correction parameter according to a first average RSRP corresponding to the serving cell in the target time period and a second average RSRP corresponding to the target signal transmission model;

[0106] Determine a cell signal transmission model corresponding to the serving cell according to the correction parameter and the target signal transmission model;

[0107] The second average RSRP corresponding to the target signal transmission model is determined based on the road test data obtained by the remote control unit RCU through network signal sampling on the high-speed railway line.

[0108] When determining the cell signal transmission model corresponding to the service cell, the target signal transmission model that matches the service cell can be first screened out from a predetermined number of signal transmission models. When screening the target signal transmission model, the target signal transmission model can be screened out from a preset number of signal transmission models based on the base station parameters corresponding to the base station to which the service cell belongs. The base station parameters corresponding to the target signal transmission model belong to the same combination as the base station parameters corresponding to the current service cell. For example, the base station parameters corresponding to the current service cell have an antenna height greater than 40 meters, an antenna tilt angle of 5 degrees (belonging to the second tilt gear), and a maximum transmission power supported by the antenna of 80w. The corresponding signal transmission model with an antenna height greater than 40 meters, an antenna tilt angle belonging to the second tilt gear, and a maximum transmission power supported by the antenna of 80w is determined as the target signal transmission model.

[0109] After determining the target signal transmission model, a correction parameter is obtained according to a first average RSRP corresponding to the serving cell in the target time period and a second average RSRP corresponding to the target signal transmission model, wherein the second average RSRP corresponding to the target signal transmission model is determined based on the drive test data, and since the drive test data includes RSRPs corresponding to a plurality of first sampling geographic locations, the second average RSRP can be calculated. The correction parameter is determined based on the first average RSRP and the second average RSRP, specifically, the correction parameter is determined based on the difference between the first average RSRP and the second average RSRP.

[0110] Then, the cell signal transmission model corresponding to the serving cell is determined based on the correction parameters and the target signal transmission model. Since the target signal transmission model is used to characterize the mapping relationship between distance and RSRP, that is, the target signal transmission model can be understood as a function that characterizes the mapping relationship between distance and RSRP, RSRP is the dependent variable, and distance is the independent variable, the expression corresponding to the cell signal transmission model is determined by adding the correction parameters to the expression corresponding to the target signal transmission model. Correcting the target signal transmission model means performing an up and down displacement correction on the second curve corresponding to the target signal transmission model.

[0111] The above process is explained below through a specific example. The number of signal transmission models is 27, among which the base station parameters corresponding to signal transmission model 21 are: antenna hanging height is greater than 40 meters, the antenna tilt angle belongs to the second tilt angle position, and the maximum transmission power supported by the antenna is 80w. The base station parameters corresponding to the current service cell match the base station parameters corresponding to signal transmission model 21, and signal transmission model 21 is the target signal transmission model.

[0112] The function expression of the second curve corresponding to the signal transmission model 21 is y=-163.05x 4 +392.1x 3 -343.59x 2+105.71x-93.143. The first average RSRP corresponding to the current serving cell is -95dbm, and the second average RSRP corresponding to the signal transmission model 21 is -90dbm. The correction coefficient E is -5, and the function expression of the cell signal transmission model corresponding to the current serving cell is y=-163.05x 4 +392.1x 3 -343.59x 2 +105.71x-98.143.

[0113] In the above implementation process of the present application, a target signal transmission model matching the service cell is determined from a preset number of signal transmission models based on base station parameters, and a correction parameter is determined according to a first average RSRP corresponding to the service cell and a second average RSRP corresponding to the target signal transmission model. The target signal transmission model is corrected based on the correction parameter to obtain a cell signal transmission model corresponding to the service cell. A personalized signal transmission model corresponding to the service cell can be obtained to ensure that network quality assessment can be performed in a targeted manner.

[0114] In an optional embodiment of the present application, for each of the high-speed rail grids, determining the signal strength corresponding to the high-speed rail grid according to the target RSRP corresponding to at least one serving cell of the high-speed rail grid, includes:

[0115] For each of the high-speed rail grids, obtaining a target RSRP corresponding to at least one serving cell of the high-speed rail grid, wherein the target RSRP corresponding to the serving cell is determined based on a second distance and the corresponding cell signal transmission model, wherein the second distance is the distance between the center point of the high-speed rail grid and the center point of the base station to which the serving cell belongs;

[0116] Determine a cell weight corresponding to at least one service cell of the high-speed railway grid, wherein the cell weight is negatively correlated with the second distance;

[0117] The signal strength corresponding to the high-speed rail grid is determined according to the target RSRP and the cell weight respectively corresponding to at least one serving cell of the high-speed rail grid.

[0118] For each high-speed rail grid, when determining the signal strength corresponding to the high-speed rail grid according to the target RSRP corresponding to at least one service cell of the high-speed rail grid, it is necessary to obtain the cell weight corresponding to each service cell in at least one service cell, wherein the cell weight is negatively correlated with the second distance between the center point of the high-speed rail grid and the center point of the base station to which the service cell belongs, that is, the larger the second distance, the smaller the cell weight, and the sum of the cell weights corresponding to each service cell is equal to 1. For example, multiple cell weights are set according to the second distance, or multiple cell weights are calculated according to multiple second distances.

[0119] The target RSRP corresponding to the serving cell is determined based on the cell signal transmission model corresponding to the serving cell, specifically, the distance between the center point of the high-speed rail grid and the center point of the base station to which the serving cell belongs is determined, and the determined distance is input into the corresponding cell signal transmission model to determine the target RSRP. After determining the target RSRP corresponding to the serving cell and the cell weight corresponding to the serving cell, the signal strength corresponding to the high-speed rail grid is determined according to the target RSRP and cell weight corresponding to the serving cell.

[0120] When determining the signal strength corresponding to the high-speed rail grid based on the target RSRP and cell weight corresponding to the service cell, the product of the target RSRP and the cell weight can be calculated for each service cell respectively, and the obtained products are accumulated to obtain the signal strength corresponding to the high-speed rail grid, that is, the signal strength corresponding to the high-speed rail grid is the grid RSRP.

[0121] The above implementation process is introduced below through a specific example. Figure 3 As shown, for the high-speed rail grid 101, the corresponding three service cells (service cell A, service cell B and service cell C) are determined, wherein the distance between the center of the high-speed rail grid 101 and the center of the base station corresponding to the service cell A is 150 meters, the distance between the center of the high-speed rail grid 101 and the center of the base station corresponding to the service cell B is 90 meters, and the distance between the center of the high-speed rail grid 101 and the center of the base station corresponding to the service cell C is 350 meters, and the base station parameters of the service cell A, the service cell B and the service cell C all match the base station parameters of the signal transmission model 15.

[0122] Among them, see Figure 4 As shown, based on the signal transmission model 15, the cell signal transmission models corresponding to the serving cell A, the serving cell B and the serving cell C are determined respectively, and then based on the distance (150 meters) and the cell signal transmission model corresponding to the serving cell A, the target RSRP corresponding to the serving cell A is determined to be -92dbm, based on the distance (90 meters) and the cell signal transmission model corresponding to the serving cell B, the target RSRP corresponding to the serving cell B is determined to be -88dbm, and based on the distance (350 meters) and the cell signal transmission model corresponding to the serving cell C, the target RSRP corresponding to the serving cell C is determined to be -101dbm. Among them, the expressions of the cell weight Pa corresponding to the serving cell A, the cell weight Pb corresponding to the serving cell B, and the cell weight Pc corresponding to the serving cell C are as follows:

[0123]

[0124]

[0125]

[0126] Among them, Pa is equal to 32%, Pb is equal to 54%, and Pc is equal to 14%. Then, the signal strength corresponding to the high-speed rail grid 101 is 32%*(-92)+54%*(-88)+14%*(-101)=-91dbm.

[0127] In the above implementation process of the present application, by obtaining the target RSRP and cell weight corresponding to at least one service cell of the high-speed rail grid, the target RSRP of the service cell is associated with the cell weight, and the signal strength corresponding to the high-speed rail grid is calculated by a weighted average algorithm. The high-speed rail network quality can be located in the high-speed rail grid to obtain a network quality assessment result with relatively high credibility and stronger pertinence.

[0128] The overall process of the network quality assessment method provided in the embodiment of the present application is described below. Figure 5 As shown, the following steps are included:

[0129] Step 501: Divide the high-speed rail line into multiple high-speed rail grids according to a preset division rule.

[0130] Step 502: Establish an association relationship between the service cell corresponding to the first sampling geographical location within the high-speed rail grid and the high-speed rail grid to determine the service cell corresponding to the high-speed rail grid.

[0131] Step 503: Determine multiple target user terminals based on the DPI signaling movement trajectory of the user terminal.

[0132] Step 504: Acquire target MR data corresponding to multiple target user terminals within a target time period.

[0133] Step 505: Combine the target MR data corresponding to the multiple target user terminals in the target time period with a preset number of signal transmission models, modify the signal transmission model, and obtain the cell signal transmission model corresponding to the serving cell.

[0134] Step 506: For each high-speed rail grid, determine the target RSRP corresponding to the serving cell according to the cell signal transmission model, and determine the signal strength corresponding to the high-speed rail grid according to the target RSRP and the cell weight.

[0135] The above implementation process can accurately identify real high-speed rail passengers based on the behavioral characteristics of the signaling trajectory moving along the high-speed rail line, and then obtain the corresponding target MR data. In this way, real and comprehensive target MR data can be obtained to facilitate network quality assessment based on the real and comprehensive target MR data; by combining the signal transmission model with the target MR data of real high-speed rail passengers, the model is corrected based on the target MR data to achieve precise coverage of one cell and one model; by performing calculations based on at least one service cell corresponding to the high-speed rail grid, the high-speed rail network quality is located in the high-speed rail grid, and precise virtual road testing of high-speed rails that is common to 4 / 5G can be achieved, thereby improving the accuracy of locating quality problem points.

[0136] The network quality assessment method provided in the embodiment of the present application can perform line indicator statistics, service area line analysis, and poor quality section positioning based on rasterized high-speed rail data, thereby realizing real-time virtual road test monitoring of high-speed rail lines, and effectively supporting the implementation of special high-speed rail optimization work (such as supporting daily evaluation of high-speed rail coverage quality and daily dispatching of problem points); and based on this solution, the number of high-speed rail passengers on each line can be counted, and the peak arrival time and destination of people returning home during the Spring Festival and holidays in various cities can be evaluated, supporting the timely launch of key network guarantees and holiday communication package marketing.

[0137] The above is the overall implementation process of the network quality assessment method of the embodiment of the present application. The high-speed rail line is divided into multiple high-speed rail grids, at least one service cell corresponding to each high-speed rail grid is determined, and the target MR data corresponding to the target user terminal in the target time period is obtained. Based on the target MR data, the first average RSRP corresponding to each service cell in the target time period is obtained to determine the cell signal transmission model corresponding to the service cell, and the target RSRP corresponding to the service cell is determined based on the cell signal transmission model. The signal strength of the high-speed rail grid is determined according to the correspondence between the high-speed rail grid and the service cell. It can be achieved that based on the identified real user terminal of the high-speed rail, real and comprehensive target MR data is obtained, and the cell signal transmission model is determined using the target MR data and the target signal transmission model, so as to determine the target RSRP corresponding to the service cell based on the cell signal transmission model, and the high-speed rail network signal quality is located in the high-speed rail grid according to the correspondence between the service cell and the high-speed rail grid, so as to obtain a network quality assessment result with relatively high credibility and stronger pertinence.

[0138] And because the target signal transmission model can be corrected based on the target MR data to determine the cell signal transmission model, there is no need to determine the signal transmission model multiple times, saving network quality assessment costs as well as time and labor costs; and the present application can realize 4G / 5G universal high-speed rail precise virtual road testing, without relying on the AGPS longitude and latitude in the MR data, to realize the evaluation of the high-speed rail 5G network. At the same time, the present application is conducive to timely discovery of sections with poor network quality and network coverage blind spots to improve network quality.

[0139] The present application also provides a network quality assessment device. Figure 6 As shown, the device comprises:

[0140] A division determination module 601 is used to divide the high-speed rail line into a plurality of high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, each of the high-speed rail grids corresponding to an area range;

[0141] A first acquisition module 602 is used to acquire target measurement report MR data corresponding to multiple target user terminals within a target period, wherein the target user terminals are high-speed rail user terminals;

[0142] A first determining module 603 is configured to determine, for each of the serving cells, a cell signal transmission model corresponding to the serving cell according to a first average reference signal received power RSRP corresponding to the serving cell in the target time period and a target signal transmission model matched with the serving cell, wherein the first average RSRP is determined based on target MR data corresponding to the serving cell in the target time period;

[0143] The second determination module 604 is used to determine the signal strength corresponding to each high-speed rail grid according to the target RSRP corresponding to at least one serving cell of the high-speed rail grid, and the target RSRP is determined based on the corresponding cell signal transmission model.

[0144] Optionally, the division determination module is further used to:

[0145] For each of the high-speed rail grids, determining the serving cells corresponding to at least one first sampling geographical location in the high-speed rail grid as the serving cells corresponding to the high-speed rail grid;

[0146] The first sampling geographical location is the geographical location corresponding to the remote control unit RCU when performing network signal sampling.

[0147] Optionally, the first acquisition module includes:

[0148] Determine an acquisition submodule, configured to determine, based on a deep data packet inspection DPI signaling sent by a user terminal, the target user terminal that moves along the high-speed rail line during at least a portion of the time interval of the target time period by the DPI signaling, so as to acquire a plurality of the target user terminals;

[0149] The first acquisition submodule is used to acquire target MR data corresponding to a plurality of target user terminals when they move along the high-speed railway line within the target time period.

[0150] Optionally, the device further comprises:

[0151] A second acquisition module is used to acquire drive test data obtained by a remote control unit RCU through network signal sampling on the high-speed railway line, wherein the drive test data at least includes a first sampling geographical location, a serving cell corresponding to the first sampling geographical location, and an RSRP corresponding to the first sampling geographical location;

[0152] A division acquisition module, configured to divide the drive test data into a preset number of categories according to a base station parameter corresponding to the base station to which the serving cell belongs, so as to acquire a preset number of second data sets;

[0153] a processing module, configured to perform machine learning on each of the second data sets to obtain a preset number of signal transmission models, wherein the signal transmission model is used to characterize a mapping relationship between the first distance and the RSRP;

[0154] Among them, the first distance is the distance between the first sampling geographical location and the center point of the target base station, the target base station is the base station to which the service cell corresponding to the first sampling geographical location belongs, and the target signal transmission model is one of a preset number of the signal transmission models.

[0155] Optionally, the processing module includes:

[0156] A second acquisition submodule is used to filter the first edge sampling geographical location according to a preset principle for each of the second data sets to perform data cleaning and obtain a second target data set;

[0157] A first determination submodule is used to perform high-order curve fitting on each of the second target data sets using the least square method to determine a first curve;

[0158] The second determination submodule is used to perform overfitting correction based on a ridge regression algorithm for each of the first curves to determine the signal transmission model, where the signal transmission model is a second curve that characterizes a mapping relationship between the first distance and RSRP.

[0159] Optionally, the first determining module includes:

[0160] A third determination submodule is used to determine, for each of the serving cells, the target signal transmission model from a preset number of signal transmission models according to the base station parameters corresponding to the base station to which the serving cell belongs, each of the signal transmission models corresponding to a type of base station parameters;

[0161] A third acquisition submodule, configured to acquire a correction parameter according to a first average RSRP corresponding to the serving cell in the target time period and a second average RSRP corresponding to the target signal transmission model;

[0162] A fourth determination submodule, configured to determine a cell signal transmission model corresponding to the serving cell according to the correction parameter and the target signal transmission model;

[0163] The second average RSRP corresponding to the target signal transmission model is determined based on the road test data obtained by the remote control unit RCU through network signal sampling on the high-speed railway line.

[0164] Optionally, after acquiring target MR data corresponding to the plurality of target user terminals within the target time period, the apparatus further includes:

[0165] A generating module, used to generate an MR statistical database corresponding to the high-speed rail user terminal according to the acquired target MR data;

[0166] Among them, the MR statistical database includes at least part of the cell identifiers, first average RSRP, number of sampling points, geographic location information and base station parameters corresponding to multiple service cells associated with the high-speed rail line during the target time period, and the first average RSRP corresponding to the service cell during the target time period is determined based on the MR statistical database.

[0167] Optionally, the second determining module includes:

[0168] A fourth acquisition submodule is used to obtain, for each of the high-speed rail grids, a target RSRP corresponding to at least one serving cell of the high-speed rail grid, wherein the target RSRP corresponding to the serving cell is determined based on a second distance and the corresponding cell signal transmission model, wherein the second distance is the distance between the center point of the high-speed rail grid and the center point of the base station to which the serving cell belongs;

[0169] A fifth determination submodule, configured to determine a cell weight corresponding to at least one service cell of the high-speed railway grid, wherein the cell weight is negatively correlated with the second distance;

[0170] The sixth determination submodule is used to determine the signal strength corresponding to the high-speed rail grid according to the target RSRP and cell weight respectively corresponding to at least one serving cell of the high-speed rail grid.

[0171] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0172] On the other hand, an embodiment of the present application further provides an electronic device, including a memory, a processor, a bus, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the above-mentioned network quality assessment method when executing the program.

[0173] For example, Figure 7 A schematic diagram of the physical structure of an electronic device is shown.

[0174] like Figure 7 As shown, the electronic device may include: a processor (processor) 710, a communication interface (Communications Interface) 720, a memory (memory) 730 and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other through the communication bus 740. The processor 710 can call the logic instructions in the memory 730, and the processor 710 is used to perform the following steps: divide the high-speed rail line into multiple high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, and each of the high-speed rail grids corresponds to an area range; obtain target measurement report MR data corresponding to multiple target user terminals in a target period, and the target user terminal is a high-speed rail user terminal; for each of the service cells, according to the first average reference signal received power RSRP corresponding to the service cell in the target period and the target signal transmission model matched with the service cell, determine the cell signal transmission model corresponding to the service cell, and the first average RSRP is determined based on the target MR data corresponding to the service cell in the target period; for each of the high-speed rail grids, according to the target RSRP corresponding to at least one service cell of the high-speed rail grid, respectively, determine the signal strength corresponding to the high-speed rail grid, and the target RSRP is determined based on the corresponding cell signal transmission model. The processor 710 can also perform other steps in this solution, which will not be described one by one here.

[0175] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0176] On the other hand, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the network quality assessment method provided in the above embodiments are implemented.

[0177] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0178] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A network quality assessment method, characterized in that: include: Divide the high-speed rail line into a plurality of high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, each of the high-speed rail grids corresponding to a regional range; Acquire target measurement report MR data corresponding to multiple target user terminals within a target period, wherein the target user terminals are high-speed rail user terminals; For each of the serving cells, determining a cell signal transmission model corresponding to the serving cell by correcting the target signal transmission model according to a first average reference signal received power RSRP corresponding to the serving cell in the target time period and a target signal transmission model matched with the serving cell, wherein the first average RSRP is determined based on target MR data corresponding to the serving cell in the target time period; For each of the high-speed rail grids, determining the signal strength corresponding to the high-speed rail grid according to the target RSRP corresponding to at least one serving cell of the high-speed rail grid, wherein the target RSRP is determined based on the corresponding cell signal transmission model; The target signal transmission model is any one of a preset number of signal transmission models, and the preset number of signal transmission models are determined based on network measurement data collected by a remote control unit RCU on the high-speed railway line.

2. The network quality assessment method according to claim 1, characterized in that: The determining at least one serving cell corresponding to each of the high-speed railway grids includes: For each of the high-speed rail grids, determining the serving cells corresponding to at least one first sampling geographical location in the high-speed rail grid as the serving cells corresponding to the high-speed rail grid; The first sampling geographical location is the geographical location corresponding to the remote control unit RCU when performing network signal sampling.

3. The network quality assessment method according to claim 1, characterized in that: The obtaining of target measurement report MR data corresponding to multiple target user terminals within a target time period includes: Based on the deep data packet inspection DPI signaling sent by the user terminal, determine the target user terminal that moves along the high-speed railway line during at least a part of the time interval of the target time period according to the DPI signaling, so as to obtain a plurality of the target user terminals; Acquire target MR data corresponding to the plurality of target user terminals when they move along the high-speed railway line within the target time period.

4. The network quality assessment method according to claim 1, characterized in that: The method further comprises: Acquire drive test data obtained by a remote control unit RCU sampling a network signal on the high-speed railway line, wherein the drive test data at least includes a first sampling geographical location, a serving cell corresponding to the first sampling geographical location, and an RSRP corresponding to the first sampling geographical location; According to base station parameters corresponding to the base station to which the serving cell belongs, the drive test data is divided into a preset number of categories to obtain a preset number of second data sets; Performing machine learning on each of the second data sets to obtain a preset number of signal transmission models, where the signal transmission model is used to characterize a mapping relationship between the first distance and the RSRP; Among them, the first distance is the distance between the first sampling geographical location and the center point of the target base station, the target base station is the base station to which the service cell corresponding to the first sampling geographical location belongs, and the target signal transmission model is one of a preset number of the signal transmission models.

5. The network quality assessment method according to claim 4, characterized in that: The performing machine learning on each of the second data sets to obtain a preset number of signal transmission models includes: For each of the second data sets, a preset principle is used to filter the first edge sampling geographical location to perform data cleaning and obtain a second target data set; For each of the second target data sets, performing high-order curve fitting on the second target data set using the least square method to determine a first curve; For each of the first curves, overfitting correction is performed based on a ridge regression algorithm to determine the signal transmission model, where the signal transmission model is a second curve that characterizes a mapping relationship between the first distance and RSRP.

6. The network quality assessment method according to claim 1, characterized in that: The determining, for each of the serving cells, a cell signal transmission model corresponding to the serving cell according to a first average reference signal received power RSRP corresponding to the serving cell in the target time period and a target signal transmission model matched with the serving cell, includes: For each of the serving cells, according to base station parameters corresponding to the base station to which the serving cell belongs, determining the target signal transmission model from a preset number of signal transmission models, each of the signal transmission models corresponding to a type of base station parameters; Acquire a correction parameter according to a first average RSRP corresponding to the serving cell in the target time period and a second average RSRP corresponding to the target signal transmission model; Determine a cell signal transmission model corresponding to the serving cell according to the correction parameter and the target signal transmission model; The second average RSRP corresponding to the target signal transmission model is determined based on the road test data obtained by the remote control unit RCU through network signal sampling on the high-speed railway line.

7. The network quality assessment method according to claim 6, characterized in that: After acquiring target MR data corresponding to the plurality of target user terminals in the target time period, the method further includes: Generate an MR statistical database corresponding to the high-speed rail user terminal according to the acquired target MR data; Among them, the MR statistical database includes at least part of the cell identifiers, first average RSRP, number of sampling points, geographic location information and base station parameters corresponding to multiple service cells associated with the high-speed rail line during the target time period, and the first average RSRP corresponding to the service cell during the target time period is determined based on the MR statistical database.

8. The network quality assessment method according to claim 1, characterized in that: The determining, for each of the high-speed rail grids, a signal strength corresponding to the high-speed rail grid according to a target RSRP corresponding to at least one serving cell of the high-speed rail grid, comprises: For each of the high-speed rail grids, obtaining a target RSRP corresponding to at least one serving cell of the high-speed rail grid, wherein the target RSRP corresponding to the serving cell is determined based on a second distance and the corresponding cell signal transmission model, wherein the second distance is the distance between the center point of the high-speed rail grid and the center point of the base station to which the serving cell belongs; Determine a cell weight corresponding to at least one service cell of the high-speed railway grid, wherein the cell weight is negatively correlated with the second distance; The signal strength corresponding to the high-speed rail grid is determined according to the target RSRP and the cell weight respectively corresponding to at least one serving cell of the high-speed rail grid.

9. A network quality assessment device, characterized in that: include: A division determination module, used to divide the high-speed rail line into a plurality of high-speed rail grids according to a preset division rule, and determine at least one service cell corresponding to each of the high-speed rail grids, each of the high-speed rail grids corresponding to an area range; A first acquisition module is used to acquire target measurement report MR data corresponding to multiple target user terminals within a target period, wherein the target user terminals are high-speed rail user terminals; A first determination module is configured to determine, for each of the serving cells, a cell signal transmission model corresponding to the serving cell by correcting the target signal transmission model according to a first average reference signal received power RSRP corresponding to the serving cell in the target time period and a target signal transmission model matched with the serving cell, wherein the first average RSRP is determined based on target MR data corresponding to the serving cell in the target time period; A second determination module is used to determine, for each of the high-speed rail grids, a signal strength corresponding to the high-speed rail grid according to a target RSRP corresponding to at least one serving cell of the high-speed rail grid, wherein the target RSRP is determined based on the corresponding cell signal transmission model; Wherein, the first determining module includes: The target signal transmission model is any one of a preset number of signal transmission models, and the preset number of signal transmission models are determined based on network measurement data collected by a remote control unit RCU on the high-speed railway line.

10. An electronic device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the network quality assessment method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the network quality assessment method according to any one of claims 1 to 8 are implemented.

Citation Information

Patent Citations

  • Method and device for testing track network quality

    CN108207009A

  • Method and device for wireless network optimization in high-speed scene of high-speed railway

    CN109561446A