CN113498094A - Grid coverage evaluation method, device and equipment - Google Patents
Grid coverage evaluation method, device and equipment Download PDFInfo
- Publication number
- CN113498094A CN113498094A CN202010266846.5A CN202010266846A CN113498094A CN 113498094 A CN113498094 A CN 113498094A CN 202010266846 A CN202010266846 A CN 202010266846A CN 113498094 A CN113498094 A CN 113498094A
- Authority
- CN
- China
- Prior art keywords
- grid
- cell
- sampling point
- coverage
- point number
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims description 26
- 238000005259 measurement Methods 0.000 claims abstract description 97
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000013210 evaluation model Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 35
- 238000005070 sampling Methods 0.000 claims description 240
- 238000012423 maintenance Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 description 13
- 238000012706 support-vector machine Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008439 repair process Effects 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Abstract
The embodiment of the invention discloses a method, a device and equipment for evaluating grid coverage, wherein the method comprises the following steps: when the target cell quits, determining the target cell as a first grid covered by the main cell or the adjacent cell; acquiring first measurement data corresponding to a first grid, and determining whether coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to the second grid and coverage state information corresponding to the second grid. The embodiment of the invention can evaluate the coverage condition of the grid under the condition of losing the coverage of the cell.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to a method, an apparatus, and a device for evaluating grid coverage.
Background
The coverage condition of the wireless network is evaluated, and the network planning quality, the current network operation condition, the problems in the network operation and the like can be judged, so that the overall operation condition of the wireless network is fully mastered, and a reference is provided for network construction and maintenance.
The existing coverage evaluation method generally evaluates the coverage of a cell to a grid when base station equipment is in a normal operation state, however, in the operation process of the base station equipment, equipment failure may occur to cause the cell to quit service, and under the condition, the method cannot evaluate the coverage of the grid.
Disclosure of Invention
The embodiment of the invention provides a grid coverage assessment method, a device and equipment, which are used for solving the problem that the coverage condition of a grid cannot be assessed under the condition that a cell quits service.
To solve the above technical problem, the embodiment of the present invention is implemented as follows:
in a first aspect, an embodiment of the present invention provides a grid coverage evaluation method, where the method includes: when a target cell quits service, determining a first grid covered by the target cell as a main cell or an adjacent cell; acquiring first measurement data corresponding to the first grid, wherein the first measurement data comprises at least one of the following items: a first total sampling point number of the first grid, a second total sampling point number when the target cell is used as a main cell, a third total sampling point number when the target cell is used as an adjacent cell, a first sampling point number in the first grid when the target cell is used as a main cell, a second sampling point number in the first grid when the target cell is used as an adjacent cell, a ratio of the first sampling point number in the first total sampling point number, a ratio of the first sampling point number in the second total sampling point number, a ratio of the second sampling point number in the first total sampling point number, a ratio of the second sampling point number in the third total sampling point number, and an average signal intensity of sampling points in the first grid when the target cell is used as a main cell or an adjacent cell; determining whether coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid.
In a second aspect, an embodiment of the present invention further provides a grid coverage evaluation apparatus, including: the grid determining module is used for determining a first grid covered by a target cell as a main cell or an adjacent cell when the target cell quits service; a measurement data obtaining module, configured to obtain first measurement data corresponding to the first grid, where the first measurement data includes at least one of: a first total sampling point number of the first grid, a second total sampling point number when the target cell is used as a main cell, a third total sampling point number when the target cell is used as an adjacent cell, a first sampling point number in the first grid when the target cell is used as a main cell, a second sampling point number in the first grid when the target cell is used as an adjacent cell, a ratio of the first sampling point number in the first total sampling point number, a ratio of the first sampling point number in the second total sampling point number, a ratio of the second sampling point number in the first total sampling point number, a ratio of the second sampling point number in the third total sampling point number, and an average signal intensity of sampling points in the first grid when the target cell is used as a main cell or an adjacent cell; the coverage evaluation module is used for determining whether the coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid.
In a third aspect, an embodiment of the present invention further provides an apparatus, including: a memory storing computer program instructions; a processor which, when executed by the processor, implements the grid coverage assessment method as described above in relation to the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to execute the grid coverage evaluation method according to the first aspect.
In the embodiment of the present invention, when a target cell is out of service, a first grid covered by the target cell as a main cell or an adjacent cell may be determined, first measurement data corresponding to the first grid is obtained, where the first measurement data includes an average signal intensity of sampling points and a plurality of statistical data of the sampling points, and then the first measurement data is input to a coverage evaluation model trained in advance, so as to determine whether coverage state information corresponding to the first grid is in a weak coverage state, where the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid. According to the method, when a cell quits due to failure, the coverage state corresponding to the grid is determined by using the collected measurement data and the pre-trained coverage evaluation model, so that the coverage condition of the grid under the condition that the cell coverage is lost can be evaluated.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram of a grid coverage assessment method in one embodiment of the invention.
Fig. 2 is a schematic structural diagram of a grid coverage evaluation apparatus according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a grid coverage evaluation device in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
FIG. 1 is a schematic flow chart diagram of a grid coverage assessment method in one embodiment of the invention. The method of fig. 1 may include:
s102, when the target cell quits service, the target cell is determined as a first grid covered by the main cell or the adjacent cell.
In order to evaluate the influence of the failure of the target cell on the grid covered by the target cell, the target cell may be determined as a first grid covered by the primary cell or the neighboring cell. Here, the grid means that a region is divided into a plurality of grids having the same size, each grid is referred to as a grid, and for example, a rectangle of 100 m × 100 m is divided as a grid. The first grid may be affected by the fallback of the target cell, and the coverage state of the first grid needs to be determined.
Specifically, the target cell may be determined as a primary cell or as a first grid covered by a neighboring cell through a correspondence between the grid and the covered cells. The corresponding relationship between the grid and the covered cells may be a grid scene and primary neighboring cell coverage relationship table, in which the grids covered by each cell as the primary cell or the neighboring cells are stored.
S104, acquiring first measurement data corresponding to the first grid.
The first measurement data is measurement data corresponding to the first grid in the user terminal historical measurement data collected in advance, and may include: the first total sampling point number of the first grid, the second total sampling point number of the target cell as the main cell, the third total sampling point number of the target cell as the adjacent cell, the first sampling point number of the target cell as the main cell in the first grid, the second sampling point number of the target cell as the adjacent cell in the first grid, the ratio of the first sampling point number in the first total sampling point number, the ratio of the first sampling point number in the second total sampling point number, the ratio of the second sampling point number in the first total sampling point number, the ratio of the second sampling point number in the third total sampling point number, the average signal intensity of the sampling point of the target cell as the main cell or the adjacent cell in the first grid, and the like. The first measurement data is historical measurement data periodically uploaded by user terminals in the first grid.
The first total sampling point number is the number of all sampling points in the first grid, the second total sampling point number is the number of the sampling points covered by the target cell as the main cell, the third total sampling point number is the number of the sampling points covered by the target cell as the adjacent cell, the first sampling point number is the number of the sampling points covered by the target cell as the main cell and positioned in the first grid, and the second sampling point number is the number of the sampling points covered by the target cell as the adjacent cell and positioned in the first grid.
Since the target cell is a neighbor cell, there is a first case: as a case where the neighboring cell covers a certain sampling point and plays a role of connection, there is also a second case: the neighboring cell covers a certain sampling point but does not perform a connection function. In the second case, although the target cell covers the sample point as a neighbor cell, the target cell is never used by the terminal at the sample point. Therefore, the third total number of sampling points may include two total numbers of sampling points, one of which counts only the number of sampling points of the first case, and the other of which counts the number of sampling points of the two cases; similarly, the second number of sampling points may include two numbers of sampling points, one of which counts only the number of the sampling points of the first case in the first grid, and the other of which counts the number of the sampling points of the two cases in the first grid.
And S106, determining whether the coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model.
The coverage evaluation model may be trained based on second measurement data corresponding to the second grid and coverage status information corresponding to the second grid. The coverage status information includes two kinds: a weak coverage state and a non-weak coverage state.
Second measurement data corresponding to the second grid, which is similar to the first measurement data, may be used as sample data for model training, and may include: the first total sampling point number of the second grid, the second total sampling point number of the sample cell as the main cell, the third total sampling point number of the sample cell as the adjacent cell, the first sampling point number of the sample cell as the main cell in the second grid, the second sampling point number of the sample cell as the adjacent cell in the second grid, the ratio of the first sampling point number in the first total sampling point number, the ratio of the first sampling point number in the second total sampling point number, the ratio of the second sampling point number in the first total sampling point number, the ratio of the second sampling point number in the third total sampling point number, the average signal intensity of the sampling point of the sample cell as the main cell or the adjacent cell in the second grid, and the like. The parameter definitions of the second measurement data are the same as or similar to the parameter definitions of the first measurement data, and are not repeated herein.
And training a coverage evaluation model by using the coverage state information corresponding to the second grid and the second measurement data as training data, wherein the trained coverage evaluation model can determine the coverage state information of the grid after the target cell quits the service according to the historical measurement data of the input grid.
The embodiment of the invention provides a grid coverage evaluation method, which can determine a first grid covered by a target cell as a main cell or an adjacent cell when the target cell is out of service, acquire first measurement data corresponding to the first grid, wherein the first measurement data comprises the average signal intensity of sampling points and various quantity statistical data of the sampling points, and input the first measurement data into a coverage evaluation model trained in advance so as to determine whether coverage state information corresponding to the first grid is in a weak coverage state or not, wherein the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid. According to the method, when a cell quits due to failure, the coverage state corresponding to the grid is determined by using the collected measurement data and the pre-trained coverage evaluation model, so that the coverage condition of the grid under the condition that the cell coverage is lost can be evaluated.
Next, a training process of the coverage evaluation model is described.
(1) And acquiring second measurement data corresponding to the second grid.
In particular, the second grid is covered by a plurality of first cells including at least one withdrawn cell and at least one unrelieved cell in the first cells. The second measurement data is historical measurement data periodically uploaded by the user terminal in the second grid.
(2) According to the second measurement data, determining coverage state information corresponding to the second grid;
in this embodiment, the coverage status information of the second grid is determined by a fallback impact evaluation algorithm.
Specifically, first, the number of third sampling points in the second grid when each first cell is used as a neighboring cell is determined; and the third sampling point number is the number of the sampling points which are covered by the first cell as the adjacent cell and are positioned in the second grid. Similarly to the definition of the second sampling point number, the total number of the sampling points of the first case and the second case in the second grid is counted as the third sampling point number in the present embodiment.
Secondly, calculating the proportion of the sum of the third sampling points corresponding to each un-quitted cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the un-quitted cells corresponding to the second grid; and calculating the proportion of the sum of the third sampling points corresponding to each deputy cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the deputy cells corresponding to the second grid.
Then, judging whether the sampling point proportion of the non-depowered cell is smaller than a first sampling point proportion threshold value or not and whether the sampling point proportion of the depowered cell is larger than a second sampling point proportion threshold value or not; if the sampling point occupation ratio of the non-deprecated cell is smaller than the first sampling point occupation ratio threshold value and the sampling point occupation ratio of the deprecated cell is larger than the second sampling point occupation ratio threshold value, determining that the coverage state information corresponding to the second grid is in a weak coverage state; and if the proportion of the sampling points of the un-served cell is less than or equal to the first sampling point proportion threshold or the proportion of the sampling points of the served cell is less than or equal to the second sampling point proportion threshold, determining that the coverage state information corresponding to the second grid is in a non-weak coverage state. The smaller the sampling point proportion of the un-uniform cell is, the larger the influence of the uniform cell on the second grid is; the larger the sampling point proportion of the deprecated cell is, the more the second grid is influenced by the deprecated cell. The first sampling point proportion threshold and the second sampling point proportion threshold can be flexibly determined according to whether the user terminal communication in the grid is influenced under the actual condition.
(3) And performing model training according to the second measurement data and the coverage state information corresponding to the second grid to obtain a coverage evaluation model. The coverage evaluation model may adopt a GBDT (gradient boosting decision tree) model or an SVM (support vector machine) model.
In the model training process, the training result may be not ideal, and the possible reason is that the training data has interference data to influence the model precision, and the training data needs to be cleaned. The step of acquiring the second measurement data corresponding to the second grid in the training process may include a data cleaning process, which is specifically as follows:
and if the coverage state information corresponding to the second grid is in a weak coverage state, judging whether a first cell covering the second grid as a main cell has a neighboring cell configuration error condition. The adjacent cell configuration error condition comprises: neighbor missing or handover covering.
And if the first cell has the wrong neighbor cell configuration, taking the first cell with the wrong neighbor cell configuration as second measurement data corresponding to the grid covered by the main cell or the neighbor cell, and removing the second measurement data corresponding to the second grid to obtain cleaned second measurement data.
In order to timely maintain the base station device corresponding to the first grid, the method may further include: and if the coverage state information corresponding to the first grid is determined to be in a weak coverage state, generating a maintenance instruction corresponding to the first grid, and sending the maintenance instruction to the target maintenance terminal. And the maintenance instruction comprises coverage state information corresponding to the first grid.
In order to allocate and maintain resources to a grid wafer region with a serious fault in a key manner to perform emergency repair work ahead of time, and avoid passively finding a problem through customer complaints after a user has a serious communication influence, which leads to a repair work lag, the method may further include: if the coverage state information corresponding to the first grid is determined to be a weak coverage state, determining fault area information corresponding to the first grid; and sending the fault area information to a target maintenance terminal. The fault area information can provide powerful data support for communication fault emergency repair work.
In the embodiment, based on the good data of the wireless network in Fujian province and combined with the wireless network good correlation theory, the influence of various elements on the grid coverage state is mainly considered, and a coverage evaluation model based on machine learning is constructed, so that the coverage condition of the grid is estimated when a cell quits due to a fault. When the cell fails to cause the quit of the service, the coverage evaluation model evaluates the influence of the quit of the service cell on the coverage of grids in real time according to the collected historical measurement data of the user terminal. Specifically, the out-of-service influence evaluation algorithm includes:
and taking the grid as a unit, wherein the sampling point proportion of the un-unsure cell is the sum of the third total sampling points of each un-unsure cell/the sum of the third total sampling points of each cell. And if the sampling point of the non-retreating cell accounts for less than 5%, confirming that the grid is influenced by retreating and presented to a GIS (Geographic Information System). And selecting the grids affected by the quit service in the GIS, and connecting the grids to all quit service cells corresponding to the grids.
And taking the grid as a unit, wherein the occupation ratio of the sampling points of the service quitting cell is the sum of the third total sampling points of the service quitting cell/the third total sampling points of each cell. If the sampling point proportion of the unsure cell is more than 10%, the unsure cell is confirmed to influence the grid.
The specific meanings of the parameters of the measurement data are described below. The measurement data mainly comprises grid main cell data and grid adjacent cell data.
Grid primary cell data, statistics of which primary cells of the coverage grid are, the occupancy of the coverage of these primary cells in the grid, and the average coverage level (i.e., average signal strength) of each primary cell in the grid.
The method specifically comprises the following steps:
the first total sampling point number of the grid is calculated by grouping grid ID (Identity document); a second total sampling point number of a certain Cell as a main Cell, and calculating the total sampling point number of the certain Cell as the main Cell in a CI (Cell Identity) grouping manner; when a certain cell is used as a main cell, the number of first sampling points in a first grid is the number of sampling points of the grid cell, and the total number of sampling points when the cell is used as the main cell is grouped and summarized by grid ID + CI; the sampling points of the main cell in the grid are in proportion, namely the number of first sampling points/the number of first total sampling points is 100; the ratio of the sampling points of the main cell falling into the grid is 100, namely the number of first sampling points/the number of second total sampling points; the average signal strength of the sampling points, such as the average level of the cell, is grouped and summarized by the grid ID + CI, and the average level of the sampling points is used as the main cell.
And counting the data of grid adjacent cells, wherein the superposition sampling condition of a certain cell serving as a main cell or an adjacent cell in a corresponding grid is counted, and whether the peripheral cells can be additionally covered in the corresponding grid or not can be evaluated after a certain station quits service.
The method specifically comprises the following steps:
taking a certain Cell as a third total sampling point number of the adjacent Cell, and calculating the total sampling point number of the certain Cell as the adjacent Cell in a CI (Cell Identity) grouping manner; when a certain cell is used as an adjacent cell, the number of second sampling points in the first grid is the number of sampling points of the grid cell, and the grid cell are grouped and collected by grid ID + CI to be used as the total number of sampling points of the adjacent cell; the sampling point ratio of adjacent cells in the grid is 100, namely the number of second sampling points/the number of first total sampling points of the grid; the adjacent cell falls into a grid sampling point ratio, namely the number of second sampling points/the number of third total sampling points is 100; the average signal strength of the sampling points, such as the average level of the cell, is grouped and summarized by the grid ID + CI, and the average level of the sampling points when the cell is taken as the adjacent cell.
It should be noted that the grid neighboring cell data may be sampling point data that a certain cell serves as a neighboring cell coverage grid and plays a role in connection, which is referred to as neighboring data for short, for example, a certain cell serves as a neighboring cell coverage grid and a certain sampling point in the grid is covered by the certain cell, and a terminal at the sampling point is connected by using the certain cell; the grid neighbor cell data may include, in addition to the aforementioned data, sampling point data that does not function as a neighbor cell coverage grid but is referred to as primary + neighbor data for short, for example, a certain cell covers this sampling point as a neighbor cell, but the neighbor cell is never used by a terminal at the sampling point, and such sampling points are also counted in the grid neighbor cell data.
Finally, the measurement data shown in table 1 were obtained.
TABLE 1
In the embodiment, wireless networks in main urban areas of cities and places in Fujian province are taken as research objects. And taking the grid of the coverage situation obtained by the periodic measurement of the common user terminal as training data. The label field of the training data is defined according to the measurement data reported by the user terminal, namely whether the coverage is weak or not. And evaluating the coverage condition of the grid by adopting a GBDT model and an SVM model, and when the GBDT model and the SVM model simultaneously evaluate the weak coverage of a certain grid, taking the grid as the grid to be optimized.
The GBDT model is one of integrated learning algorithms, takes a decision tree as a base classifier, and consists of a plurality of base classifiers. The GBDT model is formed by iteration of a forward distribution algorithm, and the core idea is that in each iteration process, the negative gradient of the current loss function is used for fitting the approximate value of the residual error, the approximate value of the residual error is used for fitting the decision tree of the current iteration, and the finally obtained model is the result obtained by superposition of each iteration of decision trees. The SVM model is a two-classification model, which is a linear classifier taking interval maximization as a learning strategy. The SVM can also handle non-linear classification problems thanks to the kernel function latitude-ascending technique. The SVM has the advantage of strong generalization capability, and the final decision function is determined by only a few support vectors, so the computation complexity is low.
Because the range of the SVM algorithm for processing data is limited, and the value range of some data fields is too large, the importance of the fields in the model can be improved, so that the accuracy of the model is influenced, and therefore, the measured data needs to be normalized before model training. For example, the maximum value (max) and the minimum value (min) are used as the normalization method, and the following is specific:
Xnorm＝(X-Xmin)/(Xmax-Xmin)
the results of the normalization are shown in table 2.
TABLE 2
Before model training, a data set can be divided into a training data set and a testing data set, the training data set is used for training a model, and a finally optimized model is obtained by adjusting various parameters; the test data set is used to test the performance of the model that has been trained. For example, using a multi-round cross validation method, the data set is randomly split into a training data set and a testing data set in each round, and cross validation is performed 50 times in total to obtain the results shown in table 3.
TABLE 3
| Model (model) | Rate of accuracy | F1 value | Precision ratio | Recall ratio of |
| GBDT | 96.10％ | 88.00％ | 95.65％ | 81.48％ |
| SVM | 92.86％ | 86.96％ | 95.24％ | 80.69％ |
In the embodiment, when the cell is out of service due to a fault, the coverage condition of the grid after removing the cell signal can be estimated by using the original collected historical measurement data, so that the important allocation and maintenance resources of the grid sheet region with a serious fault can be realized, the emergency repair work can be carried out in advance, and the strong data support is provided for the communication fault emergency repair work after the serious communication influence on a user is avoided.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Fig. 2 is a schematic structural diagram of a grid coverage evaluation apparatus according to an embodiment of the present invention, and referring to fig. 2, the grid coverage evaluation apparatus may include:
a grid determining module 202, configured to determine, when a target cell is out of service, that the target cell is a first grid covered by a primary cell or an adjacent cell;
a measurement data obtaining module 204, configured to obtain first measurement data corresponding to the first grid, where the first measurement data includes at least one of: a first total sampling point number of the first grid, a second total sampling point number when the target cell is used as a main cell, a third total sampling point number when the target cell is used as an adjacent cell, a first sampling point number in the first grid when the target cell is used as a main cell, a second sampling point number in the first grid when the target cell is used as an adjacent cell, a ratio of the first sampling point number in the first total sampling point number, a ratio of the first sampling point number in the second total sampling point number, a ratio of the second sampling point number in the first total sampling point number, a ratio of the second sampling point number in the third total sampling point number, and an average signal intensity of sampling points in the first grid when the target cell is used as a main cell or an adjacent cell;
a coverage evaluation module 206, configured to determine whether coverage state information corresponding to the first grid is a weak coverage state according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid.
The embodiment of the invention provides a grid coverage evaluation device, which can determine a first grid covered by a target cell as a main cell or an adjacent cell when the target cell is out of service, acquire first measurement data corresponding to the first grid, input the first measurement data into a coverage evaluation model trained in advance, and determine whether coverage state information corresponding to the first grid is in a weak coverage state or not, wherein the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid. According to the method, when a cell quits due to failure, the coverage state corresponding to the grid is determined by using the collected measurement data and the pre-trained coverage evaluation model, so that the coverage condition of the grid under the condition that the cell coverage is lost can be evaluated.
Optionally, as an embodiment, the apparatus further includes a training module, and the training module is configured to: acquiring second measurement data corresponding to the second grid; the second grid is covered by a plurality of first cells; the first cell comprises at least one withdrawn cell and at least one unrelieved cell; determining coverage state information corresponding to the second grid according to the second measurement data; and performing model training according to the second measurement data and the coverage state information corresponding to the second grid to obtain the coverage evaluation model.
Optionally, as an embodiment, the training module is specifically configured to: determining a number of third sampling points in the second grid when each first cell is used as a neighbor cell; calculating the proportion of the sum of the third sampling points corresponding to each un-unsure cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the un-unsure cells corresponding to the second grid; calculating the proportion of the sum of the third sampling points corresponding to each unsuccessfully served cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the unsuccessfully served cells corresponding to the second grid; judging whether the sampling point proportion of the non-depowered cell is smaller than a first sampling point proportion threshold value or not and whether the sampling point proportion of the depowered cell is larger than a second sampling point proportion threshold value or not; if so, determining that the coverage state information corresponding to the second grid is in a weak coverage state; and if not, determining that the coverage state information corresponding to the second grid is in a non-weak coverage state.
Optionally, as an embodiment, the training module is specifically configured to: if the coverage state information corresponding to the second grid is a weak coverage state, judging whether the first cell covering the second grid as a main cell has a neighboring cell configuration error condition or not; if so, the first cell with the adjacent cell configuration error condition is taken as the main cell or the second measurement data corresponding to the grid covered by the adjacent cell, and the second measurement data corresponding to the second grid is removed to obtain the cleaned second measurement data.
Optionally, as an embodiment, the apparatus further includes a maintenance instruction module, where the maintenance instruction module is configured to: if the coverage state information corresponding to the first grid is determined to be a weak coverage state, generating a maintenance instruction corresponding to the first grid; the maintenance instruction comprises coverage state information corresponding to the first grid; and sending the maintenance instruction to a target maintenance terminal.
Optionally, as an embodiment, the apparatus further includes a failure region module, where the failure region module is configured to: if the coverage state information corresponding to the first grid is determined to be a weak coverage state, determining fault area information corresponding to the first grid; and sending the fault area information to the target maintenance terminal.
Optionally, as an embodiment, the grid determining module 202 is specifically configured to: acquiring a corresponding relation between the grids and the covered cells; and determining the first grid covered by the target cell as a main cell or as an adjacent cell according to the corresponding relation.
The grid coverage evaluation device provided by the embodiment of the invention can realize each process in the embodiment of the grid coverage evaluation method, and is not described again to avoid repetition.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a grid coverage evaluation device applied in the embodiment of the present invention, which can implement details of the grid coverage evaluation method in the above embodiment and achieve the same effect. As shown in fig. 3, the grid coverage evaluation apparatus 300 includes: a processor 301, a transceiver 302, a memory 303, a user interface 304, and a bus interface, wherein:
in the embodiment of the present invention, the grid coverage evaluation apparatus 300 further includes: a computer program stored on the memory 303 and executable on the processor 301, the computer program when executed by the processor 301 performing the steps of:
when a target cell quits service, determining a first grid covered by the target cell as a main cell or an adjacent cell; acquiring first measurement data corresponding to the first grid, wherein the first measurement data comprises at least one of the following items: a first total sampling point number of the first grid, a second total sampling point number when the target cell is used as a main cell, a third total sampling point number when the target cell is used as an adjacent cell, a first sampling point number in the first grid when the target cell is used as a main cell, a second sampling point number in the first grid when the target cell is used as an adjacent cell, a ratio of the first sampling point number in the first total sampling point number, a ratio of the first sampling point number in the second total sampling point number, a ratio of the second sampling point number in the first total sampling point number, a ratio of the second sampling point number in the third total sampling point number, and an average signal intensity of sampling points in the first grid when the target cell is used as a main cell or an adjacent cell; determining whether coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid.
In FIG. 3, the bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 301, and various circuits, represented by memory 303, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 302 may be a number of elements including a transmitter and a receiver that provide a means for communicating with various other apparatus over a transmission medium. The user interface 304 may also be an interface capable of interfacing with a desired device for different user devices, including but not limited to a keypad, display, speaker, microphone, joystick, etc.
The processor 301 is responsible for managing the bus architecture and general processing, and the memory 303 may store data used by the processor 301 in performing operations.
Optionally, the computer program when executed by the processor 301 may further implement the following steps: acquiring second measurement data corresponding to the second grid; the second grid is covered by a plurality of first cells; the first cell comprises at least one withdrawn cell and at least one unrelieved cell; determining coverage state information corresponding to the second grid according to the second measurement data; and performing model training according to the second measurement data and the coverage state information corresponding to the second grid to obtain the coverage evaluation model.
Optionally, the computer program when executed by the processor 301 may further implement the following steps: determining a number of third sampling points in the second grid when each first cell is used as a neighbor cell; calculating the proportion of the sum of the third sampling points corresponding to each un-unsure cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the un-unsure cells corresponding to the second grid; calculating the proportion of the sum of the third sampling points corresponding to each unsuccessfully served cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the unsuccessfully served cells corresponding to the second grid; judging whether the sampling point proportion of the non-depowered cell is smaller than a first sampling point proportion threshold value or not and whether the sampling point proportion of the depowered cell is larger than a second sampling point proportion threshold value or not; if so, determining that the coverage state information corresponding to the second grid is in a weak coverage state; and if not, determining that the coverage state information corresponding to the second grid is in a non-weak coverage state.
Optionally, the computer program when executed by the processor 301 may further implement the following steps: if the coverage state information corresponding to the second grid is a weak coverage state, judging whether the first cell covering the second grid as a main cell has a neighboring cell configuration error condition or not; if so, the first cell with the adjacent cell configuration error condition is taken as the main cell or the second measurement data corresponding to the grid covered by the adjacent cell, and the second measurement data corresponding to the second grid is removed to obtain the cleaned second measurement data.
Optionally, the computer program when executed by the processor 301 may further implement the following steps: if the coverage state information corresponding to the first grid is determined to be a weak coverage state, generating a maintenance instruction corresponding to the first grid; the maintenance instruction comprises coverage state information corresponding to the first grid; and sending the maintenance instruction to a target maintenance terminal.
Optionally, the computer program when executed by the processor 301 may further implement the following steps: if the coverage state information corresponding to the first grid is determined to be a weak coverage state, determining fault area information corresponding to the first grid; and sending the fault area information to the target maintenance terminal.
Optionally, the computer program when executed by the processor 301 may further implement the following steps: acquiring a corresponding relation between the grids and the covered cells; and determining the first grid covered by the target cell as a main cell or as an adjacent cell according to the corresponding relation.
The embodiment of the invention provides grid coverage evaluation equipment, which can determine a first grid covered by a target cell as a main cell or an adjacent cell when the target cell is out of service, acquire first measurement data corresponding to the first grid, input the first measurement data into a pre-trained coverage evaluation model to determine whether coverage state information corresponding to the first grid is in a weak coverage state or not, and train the coverage evaluation model based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid. According to the method, when a cell quits due to failure, the coverage state corresponding to the grid is determined by using the collected measurement data and the pre-trained coverage evaluation model, so that the coverage condition of the grid under the condition that the cell coverage is lost can be evaluated.
Preferably, an embodiment of the present invention further provides a grid coverage evaluation device, which includes a processor 301, a memory 303, and a computer program that is stored in the memory 303 and is executable on the processor 301, and when the computer program is executed by the processor 301, the computer program implements each process of the grid coverage evaluation method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the embodiment of the grid coverage assessment method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
Embodiments of the present invention provide a computer-readable storage medium, which can evaluate a coverage condition of a grid in a case where coverage of the cell is lost.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A grid coverage assessment method, comprising:
when a target cell quits service, determining a first grid covered by the target cell as a main cell or an adjacent cell;
acquiring first measurement data corresponding to the first grid, wherein the first measurement data comprises at least one of the following items: a first total sampling point number of the first grid, a second total sampling point number when the target cell is used as a main cell, a third total sampling point number when the target cell is used as an adjacent cell, a first sampling point number in the first grid when the target cell is used as a main cell, a second sampling point number in the first grid when the target cell is used as an adjacent cell, a ratio of the first sampling point number in the first total sampling point number, a ratio of the first sampling point number in the second total sampling point number, a ratio of the second sampling point number in the first total sampling point number, a ratio of the second sampling point number in the third total sampling point number, and an average signal intensity of sampling points in the first grid when the target cell is used as a main cell or an adjacent cell;
determining whether coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid.
2. The method of claim 1, further comprising:
acquiring second measurement data corresponding to the second grid; the second grid is covered by a plurality of first cells; the first cell comprises at least one withdrawn cell and at least one unrelieved cell;
determining coverage state information corresponding to the second grid according to the second measurement data;
and performing model training according to the second measurement data and the coverage state information corresponding to the second grid to obtain the coverage evaluation model.
3. The method of claim 2, wherein the determining the coverage status information corresponding to the second grid comprises:
determining a number of third sampling points in the second grid when each first cell is used as a neighbor cell;
calculating the proportion of the sum of the third sampling points corresponding to each un-unsure cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the un-unsure cells corresponding to the second grid;
calculating the proportion of the sum of the third sampling points corresponding to each unsuccessfully served cell to the sum of the third sampling points corresponding to each first cell to obtain the proportion of the sampling points of the unsuccessfully served cells corresponding to the second grid;
judging whether the sampling point proportion of the non-depowered cell is smaller than a first sampling point proportion threshold value or not and whether the sampling point proportion of the depowered cell is larger than a second sampling point proportion threshold value or not;
if so, determining that the coverage state information corresponding to the second grid is in a weak coverage state; and if not, determining that the coverage state information corresponding to the second grid is in a non-weak coverage state.
4. The method of claim 3, wherein the obtaining second measurement data corresponding to the second grid comprises:
if the coverage state information corresponding to the second grid is a weak coverage state, judging whether the first cell covering the second grid as a main cell has a neighboring cell configuration error condition or not;
if so, the first cell with the adjacent cell configuration error condition is taken as the main cell or the second measurement data corresponding to the grid covered by the adjacent cell, and the second measurement data corresponding to the second grid is removed to obtain the cleaned second measurement data.
5. The method of claim 1, wherein after the determining whether the coverage status information corresponding to the first grid is a weak coverage status, the method further comprises:
if the coverage state information corresponding to the first grid is determined to be a weak coverage state, generating a maintenance instruction corresponding to the first grid; the maintenance instruction comprises coverage state information corresponding to the first grid;
and sending the maintenance instruction to a target maintenance terminal.
6. The method of claim 1, wherein after the determining whether the coverage status information corresponding to the first grid is a weak coverage status, the method further comprises:
if the coverage state information corresponding to the first grid is determined to be a weak coverage state, determining fault area information corresponding to the first grid;
and sending the fault area information to the target maintenance terminal.
7. The method of claim 1, wherein the determining the target cell as a first grid covered by a primary cell or a neighbor cell comprises:
acquiring a corresponding relation between the grids and the covered cells;
and determining the first grid covered by the target cell as a main cell or as an adjacent cell according to the corresponding relation.
8. A grid coverage assessment apparatus, comprising:
the grid determining module is used for determining a first grid covered by a target cell as a main cell or an adjacent cell when the target cell quits service;
a measurement data obtaining module, configured to obtain first measurement data corresponding to the first grid, where the first measurement data includes at least one of: a first total sampling point number of the first grid, a second total sampling point number when the target cell is used as a main cell, a third total sampling point number when the target cell is used as an adjacent cell, a first sampling point number in the first grid when the target cell is used as a main cell, a second sampling point number in the first grid when the target cell is used as an adjacent cell, a ratio of the first sampling point number in the first total sampling point number, a ratio of the first sampling point number in the second total sampling point number, a ratio of the second sampling point number in the first total sampling point number, a ratio of the second sampling point number in the third total sampling point number, and an average signal intensity of sampling points in the first grid when the target cell is used as a main cell or an adjacent cell;
the coverage evaluation module is used for determining whether the coverage state information corresponding to the first grid is in a weak coverage state or not according to the first measurement data and a pre-trained coverage evaluation model; the coverage evaluation model is obtained by training based on second measurement data corresponding to a second grid and coverage state information corresponding to the second grid.
9. A grid coverage assessment apparatus, comprising:
a memory storing computer program instructions;
a processor which, when executed by the processor, implements the grid coverage assessment method of any one of claims 1 to 7.
10. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform the grid coverage assessment method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010266846.5A CN113498094A (en) | 2020-04-07 | 2020-04-07 | Grid coverage evaluation method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010266846.5A CN113498094A (en) | 2020-04-07 | 2020-04-07 | Grid coverage evaluation method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113498094A true CN113498094A (en) | 2021-10-12 |
Family
ID=77995707
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010266846.5A Pending CN113498094A (en) | 2020-04-07 | 2020-04-07 | Grid coverage evaluation method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113498094A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130064226A1 (en) * | 2011-09-12 | 2013-03-14 | Esmael Dinan | Handover in Heterogeneous Wireless Networks |
| US20140153439A1 (en) * | 2012-12-04 | 2014-06-05 | Intucell Ltd. | Method for managing hetereogeneous cellular networks |
| CN107995630A (en) * | 2016-10-26 | 2018-05-04 | 中国移动通信集团广东有限公司 | A kind of the signal data computational methods and device of wireless network covering |
| CN109587721A (en) * | 2017-09-28 | 2019-04-05 | 中国移动通信集团浙江有限公司 | A kind of subzone network coverage evaluating method and device |
| CN109886533A (en) * | 2019-01-07 | 2019-06-14 | 中国联合网络通信集团有限公司 | A kind of analysis method and device of base station construction |
| CN109996186A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团陕西有限公司 | A kind of network coverage problem identification method and device, read/write memory medium |
-
2020
- 2020-04-07 CN CN202010266846.5A patent/CN113498094A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130064226A1 (en) * | 2011-09-12 | 2013-03-14 | Esmael Dinan | Handover in Heterogeneous Wireless Networks |
| US20140153439A1 (en) * | 2012-12-04 | 2014-06-05 | Intucell Ltd. | Method for managing hetereogeneous cellular networks |
| CN107995630A (en) * | 2016-10-26 | 2018-05-04 | 中国移动通信集团广东有限公司 | A kind of the signal data computational methods and device of wireless network covering |
| CN109587721A (en) * | 2017-09-28 | 2019-04-05 | 中国移动通信集团浙江有限公司 | A kind of subzone network coverage evaluating method and device |
| CN109996186A (en) * | 2017-12-29 | 2019-07-09 | 中国移动通信集团陕西有限公司 | A kind of network coverage problem identification method and device, read/write memory medium |
| CN109886533A (en) * | 2019-01-07 | 2019-06-14 | 中国联合网络通信集团有限公司 | A kind of analysis method and device of base station construction |
Non-Patent Citations (1)
| Title |
|---|
| 阳波: ""MR覆盖率提升策略研究"", 《电信技术》, pages 2 - 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106162714B (en) | A kind of calling information processing method and processing device | |
| CN111191918A (en) | Service route planning method and device for smart power grid communication network | |
| CN108934016B (en) | Method and device for dividing cell scene categories, computer equipment and storage medium | |
| CN107147514B (en) | Power communication network optimization resource configuration method and system | |
| CN107645393A (en) | Determine the method, apparatus and system of the black-box system input and output degree of association | |
| CN111246564A (en) | External interference positioning method and device based on MR data | |
| CN113379176B (en) | Method, device, equipment and readable storage medium for detecting abnormal data of telecommunication network | |
| Ma et al. | Networked system state estimation in smart grid over cognitive radio infrastructures | |
| CN107947968A (en) | The treating method and apparatus of network quality calling information | |
| CN102986146A (en) | Method and arrangement for reducing interference and enhancing coverage | |
| CN109842896A (en) | Grid value evaluation method and device | |
| CN115842342B (en) | Topology identification method and device for distributed power distribution network | |
| CN110063066A (en) | Toning cell detection | |
| CN113133069A (en) | Method and device for determining target cell, electronic equipment and storage medium | |
| CN113537697A (en) | Method and system for performance evaluation of supervisors in city management | |
| CN110428147B (en) | Virtual power plant communication risk assessment method, system and equipment | |
| CN114095856A (en) | Processing method and processing device for saving energy of base station | |
| CN109978241B (en) | Method and device for determining charging load of electric automobile | |
| CN113660687B (en) | Network difference cell processing method, device, equipment and storage medium | |
| CN113498094A (en) | Grid coverage evaluation method, device and equipment | |
| CN111953531A (en) | Network fault analysis method and device | |
| CN116915710A (en) | Traffic early warning method, device, equipment and readable storage medium | |
| CN110968075A (en) | Fault diagnosis method and system based on active learning self-organizing cellular network | |
| CN115860278A (en) | Motor assembly production management method and system based on data analysis | |
| CN112836843A (en) | Method and device for predicting base station out-of-service alarm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |