CN112686483A - Early warning area identification method and device, computing equipment and computer storage medium - Google Patents
Early warning area identification method and device, computing equipment and computer storage medium Download PDFInfo
- Publication number
- CN112686483A CN112686483A CN201910989603.1A CN201910989603A CN112686483A CN 112686483 A CN112686483 A CN 112686483A CN 201910989603 A CN201910989603 A CN 201910989603A CN 112686483 A CN112686483 A CN 112686483A
- Authority
- CN
- China
- Prior art keywords
- cell
- early warning
- user number
- base station
- longitude
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000012417 linear regression Methods 0.000 claims abstract description 38
- 238000004891 communication Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 45
- 230000000694 effects Effects 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 28
- 230000003321 amplification Effects 0.000 claims description 11
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 11
- 230000009193 crawling Effects 0.000 claims description 8
- 238000003064 k means clustering Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 abstract description 9
- 230000008447 perception Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000012544 monitoring process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the invention relates to the technical field of big data, and discloses an early warning area identification method, an early warning area identification device, a computing device and a computer storage medium, wherein the method comprises the following steps: collecting the existing network data and historical data, comprising: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area. Through the mode, the embodiment of the invention can accurately find the early warning cell in advance, provides effective support for high-load cell analysis, improves the operation quality of the whole network and optimizes the use perception of a user on the communication network.
Description
Technical Field
The embodiment of the invention relates to the technical field of big data, in particular to an early warning area identification method, an early warning area identification device, computing equipment and a computer storage medium.
Background
At present, for identification of a sudden people flow gathering area, monitoring is mainly carried out by means of background indexes of the whole network, high-load cells in a time period are found, longitude and latitude information of a base station is relied on, an electronic map is manually combined, an early warning area is output, and optimization work is carried out.
The identification of the sudden people flow gathering area mainly comprises two aspects, namely early warning cell identification and active area identification. In the early warning cell identification in sudden major activities, the whole network index is monitored manually, then the whole network cell is deleted and selected manually according to a high-load rule, and the high-load cell is determined. When the sudden activity area is identified, the position of the base station is manually determined according to the longitude and latitude, the working parameters and the electronic map of the high-load cell, then the activity area is determined according to the site type (macro site and room division) and optimization experience, the whole process is manually processed, and the efficiency and the accuracy are difficult to guarantee.
Therefore, the identification of the early warning cell and the activity area at the present stage needs to be completed manually, time and labor are consumed, the timeliness and the activity area accuracy of the early warning cell are not high, and if activity information is omitted once, the use perception of a client on a communication network is seriously influenced, unnecessary network complaints and negative public sentiments are caused. Therefore, how to accurately and timely predict the burst activity and the region becomes a technical problem to be solved urgently.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention provide an early warning area identification method, apparatus, computing device and computer storage medium, which overcome or at least partially solve the above problems.
According to an aspect of an embodiment of the present invention, there is provided an early warning area identification method, including: collecting the existing network data and historical data, comprising: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area.
In an optional manner, the calculating a predicted value user number and a reference value user number according to the current network data and the number of connected users of the cell in the historical data includes: acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data; and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connected user number of the cell in the historical data.
In an optional manner, the obtaining the predicted number of users of the cell by using a long-term short-term memory network algorithm according to the number of connected users of the cell in the current network data and the historical data further includes: slicing the current network data and the historical data by adopting a long-short term memory network algorithm according to the granularity of one week for 15 minutes to establish a model, and modifying and optimizing the model according to the historical data; and predicting the predicted value user number of a plurality of time intervals in the future with the granularity of 15 minutes by applying the model according to the current network data and the number of the connected users of the cells in the historical data.
In an optional manner, the calculating, according to the number of connected users of the cell in the historical data, the reference number of users of the cell by using a K-MEANS s clustering algorithm and aponinaire's theorem includes:
according to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
connecting the 3 centroids to form a triangle; and calculating the number of the connected users corresponding to the intersection points of the three central lines of the triangle according to the Apollonian's theorem, and determining the number of the reference value users of the cell.
In an optional manner, the inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain the early warning cell includes: establishing a linear regression model according to the daily connection user number of the historical major activities and the connection user number during the activities; and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
In an optional mode, the applying the thiessen polygon to converge and identify a coverage area of the early warning cell according to the neighboring cell relationship and the latitude and longitude information, and outputting the early warning area includes: acquiring information of the early warning cell, wherein the information at least comprises longitude and latitude information and a neighboring cell relation; finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation; constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations; and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
In a selectable mode, the outputting the early warning region according to the neighboring cell relationship of the base station of the early warning cell and the coverage region of the base station includes: if the surrounding of the base station of any one early warning cell is determined to have no early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the surrounding base stations with the neighboring cell relation are gathered, and the early warning area is output according to the coverage area of the base station; and if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas.
According to another aspect of the embodiments of the present invention, there is provided an early warning area identification apparatus, including: the data acquisition unit is used for collecting the present network data and the historical data, and comprises: connecting the number of users, the adjacent area relationship and the longitude and latitude information; a calculating unit, configured to calculate a predicted value user number and a reference value user number of a cell according to the current network data and the number of connected users of the cell in the historical data; the early warning cell acquisition unit is used for inputting the predicted value user number and the reference value user number of the cell into a linear regression model to acquire an early warning cell; and the early warning area identification unit is used for applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information and outputting an early warning area.
According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the steps of the early warning area identification method.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes the processor to execute the steps of the above-mentioned warning area identification method.
The embodiment of the invention collects the current network data and the historical data, and comprises the following steps: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying the Thiessen polygon to assemble and identify the coverage area of the early warning cell according to the adjacent cell relation and the longitude and latitude information, outputting the early warning area, accurately finding the early warning cell in advance, providing effective support for high-load cell analysis, improving the operation quality of the whole network, and optimizing the use perception of a user on the communication network.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flow chart illustrating an early warning area identification method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating step S12 of the warning area identification method according to an embodiment of the present invention;
fig. 3 shows a model diagram for calculating the number of predicted values of users in the early warning area identification method provided in the embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a method for calculating a reference value user number according to the method for identifying an early warning area provided by the embodiment of the present invention;
fig. 5 is a schematic diagram illustrating a method for determining a coverage area of a base station according to an early warning area identification method provided in an embodiment of the present invention;
fig. 6 is a schematic structural diagram illustrating an early warning area recognition apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a schematic flow chart of an early warning area identification method provided by an embodiment of the present invention. As shown in fig. 1, the method for identifying an early warning area includes:
step S11: collecting the existing network data and historical data, comprising: the number of connected users, the relation of adjacent cells and the longitude and latitude information.
In the embodiment of the invention, the data acquisition of the current network can be completed by automatic docking of the background index monitoring platform of the whole network, and the main information of the acquired data comprises the following steps: time granularity, base station number (eNodeBID), cell number (CellId), the number of connected users, longitude (longitude), latitude (latitude), and neighbor relation. Historical data collection can be completed through automatic butt joint of whole-network background index monitoring, and the main data collection information comprises the following steps: time granularity, eNodeBID, CellId, the number of connected users, longitude, latitude, neighbor relation and other information.
And then cleaning historical important activity data from the collected current network data and historical data, wherein the cleaned current network data and historical data comprise: time granularity during historical daily and active periods, eNodeBID, CellId, and the number of connected users. And further, performing data cleaning on the cleaned current network data and the cleaned historical data in the same cell in different time periods, eliminating abnormal data, sorting and gathering daily and activity data in heavy activities, outputting a format for analysis and modeling application, and storing the format.
Step S12: and calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data.
In step S12, as shown in fig. 2, the method includes:
step S121: and acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data.
Specifically, the number of real-time continuous users with a granularity of 15 minutes in a cell in the current network data and the number of connected users with a granularity of 15 minutes in the same period of history in the cell in the historical data are obtained. Performing slice building on the current network data and the historical data in 15 minutes according to the granularity of one week by adopting a Long Short-Term Memory (LSTM) algorithm in machine learning, and performing correction optimization on the model according to the historical data; and then predicting the predicted value user number in a plurality of time intervals in the future with 15-minute granularity by applying the model according to the current network data and the number of the connected users of the cell in the historical data.
FIG. 3 is a schematic diagram of a model for calculating the number of predicted users, which is to perform time slice coding on the current network data and part of historical data according to the granularity of one week in 15 minutes and embed the current network data and part of the historical data into the input end of an LSTM algorithm model. And (2) performing data normalization on part of historical data, performing batch normalization (Batchnorm), outputting through a first linear layer, activating, combining with a time slice coding result to be used as an input layer x _ in of an LSTM algorithm model, and outputting through an output layer n _ out and a second linear layer Y _ out after LSTM algorithm operation.
And predicting the predicted number of users of the cell in a plurality of time periods in the future at the granularity of 15 minutes according to the historical data and the current network data combined model.
Step S122: and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connection user number of the cell in the historical data.
According to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
where the centroid, μ i, is the mean vector of the cluster, Ci, k, i 1, 2, 3,
and 3 centroids are obtained through calculation, and the 3 centroids are connected to form a triangle.
As shown in fig. 4, the number of connected users corresponding to the intersection of the three central lines of the triangle is calculated according to the apollonies theorem, and is determined as the number of reference value users of the cell.
Step S13: and inputting the predicted value user quantity and the reference value user quantity of the cell into a linear regression model to obtain an early warning cell.
Specifically, a linear regression model is established according to the daily connection user number of the historical major activities and the connection user number during the activities; and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
In the embodiment of the invention, the number of historical great-activity daily connection users and the number of the connection users during the activity are selected, and a linear regression model is established through the number of the historical great-activity daily connection users and the number of the connection users during the activity. In the linear regression model, the number of daily connected users is set to x, the number of movably connected users is set to y, and the established linear regression model is as follows:
y＝hθ(x)＝x·θT
the data correction calculation according to the number of connected users in a plurality of active periods is as follows:
wherein m is the number of samples, theta is a relation matrix, L is the difference between the calculated value of the number of the active connection users and the actual value, and i and j are positive integers.
According to
And (5) performing regression, wherein a is a coefficient, and finally determining the most accurate linear regression model.
In the embodiment of the invention, the data amplification conditions of multiple periods are predicted to be compared with a linear regression model, a correction value is set in each amplification, preferably to be plus or minus 3%, and the information to be input is shown in a table 1:
TABLE 1 information input into Linear regression model
And if the cell meeting the continuous amplification condition is the early warning cell through the comparison result. The continuous amplification condition is a condition in which the difference between the predicted value user number and the reference value user number continuously increases.
Step S14: and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area.
In step S14, acquiring information of the early warning cell, which at least includes longitude and latitude information and a neighboring cell relationship; finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation; constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations; and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
In the embodiment of the present invention, when the coverage areas of all base stations are obtained, as shown in fig. 5, triangles adjacent to a certain base station are sorted clockwise or counterclockwise by applying an algorithm in a thiessen polygon according to the latitude and longitude information of the base station, and the certain base station is set to be o. Finding out a triangle with the base station o as a vertex, and setting the triangle as a triangle A; taking another vertex of the triangle A except the base station o as the base station a, and finding out another vertex as the base station f; the next triangle must be bounded by of, which is triangle F; the other vertex of triangle F is base station e, and the next triangle is with oe as the side; and repeating the steps until the position returns to the oa side, and calculating and recording the circle center of the circumscribed circle of each triangle. And connecting the centers of the circumscribed circles of the adjacent triangles according to the adjacent triangles of each base station to obtain a polygon a 'b' c'd' e 'f', wherein the area defined by the polygon a 'b' c'd' e 'f' is the coverage area of the base station o.
In calculating the coverage area of a base station, a set of discrete points (x) is located on a planar area Bj,yj) I is 1, 2, 3, …, k is the number of discrete points. If the region B is divided into k mutually adjoining polygons by a set of straight line segments, it is necessary to satisfy:
(1) each polygon contains and contains only one discrete point.
(2) If any point (x) on the region B1,y1) Located at a position containing discrete points (x)j,yj) In the polygon of (a), the following inequality holds constantly at (i ≠ j):
(3) if point (x)1,y1) Located at a position containing discrete points (x)j,yj) On the common edge of two polygons, the following equation holds:
in the embodiment of the invention, when the early warning area is identified, after all base station coverage areas are determined, if no early warning cell is determined around the base station of any one early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the base stations around the early warning cell with the adjacent cell relation are gathered, and the early warning area is output according to the coverage area of the base station.
And if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas. Specifically, the final early warning base station is determined according to the rule of continuing the outward expansion. The base stations of the early warning cell and the base stations with the neighboring cell relation around the base station of the early warning cell are gathered until no early warning cell is around the base station of any early warning cell, and therefore the final early warning base station is determined. And then, crawling the boundary of the base station by applying a web crawler technology according to the early warning base station list and an algorithm in the Thiessen polygon, and outputting a final early warning area.
The embodiment of the invention utilizes a machine learning method to carry out intelligent early warning, can carry out intelligent monitoring and early warning on the cells in the whole province, and has wide early warning range; compared with the traditional method that the cells are manually circled according to the map, the embodiment of the invention can automatically find the early warning cells in advance and automatically converge, thereby realizing advanced prediction, and having high efficiency and low cost; the embodiment of the invention can be further popularized based on the major activity intelligent early warning method, correlates the change information such as user quantity and flow in the cell, can identify the high-value area, can provide effective support for high-load cell analysis, and improves the operation quality of the whole network.
The embodiment of the invention collects the current network data and the historical data, and comprises the following steps: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying the Thiessen polygon to assemble and identify the coverage area of the early warning cell according to the adjacent cell relation and the longitude and latitude information, outputting the early warning area, accurately finding the early warning cell in advance, providing effective support for high-load cell analysis, improving the operation quality of the whole network, and optimizing the use perception of a user on the communication network.
Fig. 6 shows a schematic structural diagram of an early warning area recognition apparatus according to an embodiment of the present invention. As shown in fig. 6, the early warning region identifying apparatus includes: a data acquisition unit 601, a calculation unit 602, an early warning cell acquisition unit 603, and an early warning area identification unit 604. Wherein:
the data acquisition unit 601 is used for collecting the present network data and the historical data, and includes: connecting the number of users, the adjacent area relationship and the longitude and latitude information; the calculating unit 602 is configured to calculate a predicted value user number and a reference value user number of a cell according to the current network data and the number of connected users of the cell in the historical data; the early warning cell obtaining unit 603 is configured to input the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; the early warning area identification unit 604 is configured to apply a thiessen polygon to perform aggregation and coverage area identification on the early warning cell according to the neighboring cell relationship and the longitude and latitude information, and output an early warning area.
In an alternative manner, the computing unit 602 is configured to: acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data; and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connected user number of the cell in the historical data.
In an optional manner, the computing unit 602 is further configured to: slicing the current network data and the historical data by adopting a long-short term memory network algorithm according to the granularity of one week for 15 minutes to establish a model, and modifying and optimizing the model according to the historical data; and predicting the predicted value user number of a plurality of time intervals in the future with the granularity of 15 minutes by applying the model according to the current network data and the number of the connected users of the cells in the historical data.
In an optional manner, the computing unit 602 is further configured to: according to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
connecting the 3 centroids to form a triangle; and calculating the number of the connected users corresponding to the intersection points of the three central lines of the triangle according to the Apollonian's theorem, and determining the number of the reference value users of the cell.
In an optional manner, the early warning cell obtaining unit 603 is configured to: establishing a linear regression model according to the daily connection user number of the historical major activities and the connection user number during the activities; and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
In an alternative manner, the early warning area identification unit 604 is configured to: acquiring information of the early warning cell, wherein the information at least comprises longitude and latitude information and a neighboring cell relation; finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation; constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations; and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
In an alternative manner, the early warning area identification unit 604 is configured to: if the surrounding of the base station of any one early warning cell is determined to have no early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the surrounding base stations with the neighboring cell relation are gathered, and the early warning area is output according to the coverage area of the base station; and if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas.
The embodiment of the invention collects the current network data and the historical data, and comprises the following steps: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying the Thiessen polygon to assemble and identify the coverage area of the early warning cell according to the adjacent cell relation and the longitude and latitude information, outputting the early warning area, accurately finding the early warning cell in advance, providing effective support for high-load cell analysis, improving the operation quality of the whole network, and optimizing the use perception of a user on the communication network.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the early warning area identification method in any method embodiment.
The executable instructions may be specifically configured to cause the processor to:
collecting the existing network data and historical data, comprising: connecting the number of users, the adjacent area relationship and the longitude and latitude information;
calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data;
inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell;
and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area.
In an alternative, the executable instructions cause the processor to:
acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data;
and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connected user number of the cell in the historical data.
In an alternative, the executable instructions cause the processor to:
slicing the current network data and the historical data by adopting a long-short term memory network algorithm according to the granularity of one week for 15 minutes to establish a model, and modifying and optimizing the model according to the historical data;
and predicting the predicted value user number of a plurality of time intervals in the future with the granularity of 15 minutes by applying the model according to the current network data and the number of the connected users of the cells in the historical data.
In an alternative, the executable instructions cause the processor to:
according to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
connecting the 3 centroids to form a triangle;
and calculating the number of the connected users corresponding to the intersection points of the three central lines of the triangle according to the Apollonian's theorem, and determining the number of the reference value users of the cell.
In an alternative, the executable instructions cause the processor to:
establishing a linear regression model according to the daily connection user number of the historical major activities and the connection user number during the activities;
and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
In an alternative, the executable instructions cause the processor to:
acquiring information of the early warning cell, wherein the information at least comprises longitude and latitude information and a neighboring cell relation;
finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation;
constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations;
and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
In an alternative, the executable instructions cause the processor to:
if the surrounding of the base station of any one early warning cell is determined to have no early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the surrounding base stations with the neighboring cell relation are gathered, and the early warning area is output according to the coverage area of the base station;
and if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas.
The embodiment of the invention collects the current network data and the historical data, and comprises the following steps: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying the Thiessen polygon to assemble and identify the coverage area of the early warning cell according to the adjacent cell relation and the longitude and latitude information, outputting the early warning area, accurately finding the early warning cell in advance, providing effective support for high-load cell analysis, improving the operation quality of the whole network, and optimizing the use perception of a user on the communication network.
An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method for identifying an early warning area in any of the above-mentioned method embodiments.
The executable instructions may be specifically configured to cause the processor to:
collecting the existing network data and historical data, comprising: connecting the number of users, the adjacent area relationship and the longitude and latitude information;
calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data;
inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell;
and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area.
In an alternative, the executable instructions cause the processor to:
acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data;
and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connected user number of the cell in the historical data.
In an alternative, the executable instructions cause the processor to:
slicing the current network data and the historical data by adopting a long-short term memory network algorithm according to the granularity of one week for 15 minutes to establish a model, and modifying and optimizing the model according to the historical data;
and predicting the predicted value user number of a plurality of time intervals in the future with the granularity of 15 minutes by applying the model according to the current network data and the number of the connected users of the cells in the historical data.
In an alternative, the executable instructions cause the processor to:
according to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
Connecting the 3 centroids to form a triangle;
and calculating the number of the connected users corresponding to the intersection points of the three central lines of the triangle according to the Apollonian's theorem, and determining the number of the reference value users of the cell.
In an alternative, the executable instructions cause the processor to:
establishing a linear regression model according to the daily connection user number of the historical major activities and the connection user number during the activities;
and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
In an alternative, the executable instructions cause the processor to:
acquiring information of the early warning cell, wherein the information at least comprises longitude and latitude information and a neighboring cell relation;
finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation;
constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations;
and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
In an alternative, the executable instructions cause the processor to:
if the surrounding of the base station of any one early warning cell is determined to have no early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the surrounding base stations with the neighboring cell relation are gathered, and the early warning area is output according to the coverage area of the base station;
and if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas.
The embodiment of the invention collects the current network data and the historical data, and comprises the following steps: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying the Thiessen polygon to assemble and identify the coverage area of the early warning cell according to the adjacent cell relation and the longitude and latitude information, outputting the early warning area, accurately finding the early warning cell in advance, providing effective support for high-load cell analysis, improving the operation quality of the whole network, and optimizing the use perception of a user on the communication network.
Fig. 7 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the device.
As shown in fig. 7, the computing device may include: a processor (processor)702, a Communications Interface 704, a memory 706, and a communication bus 708.
Wherein: the processor 702, communication interface 704, and memory 706 communicate with each other via a communication bus 708. A communication interface 704 for communicating with network elements of other devices, such as clients or other servers. The processor 702 is configured to execute the program 710, and may specifically execute relevant steps in the above-mentioned early warning area identification method embodiment.
In particular, the program 710 may include program code that includes computer operating instructions.
The processor 702 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present invention. The one or each processor included in the device may be the same type of processor, such as one or each CPU; or may be different types of processors such as one or each CPU and one or each ASIC.
The memory 706 stores a program 710. The memory 706 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 710 may specifically be used to cause the processor 702 to perform the following operations:
collecting the existing network data and historical data, comprising: connecting the number of users, the adjacent area relationship and the longitude and latitude information;
calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data;
inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell;
and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area.
In an alternative, the program 710 causes the processor to:
acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data;
and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connected user number of the cell in the historical data.
In an alternative, the program 710 causes the processor to:
slicing the current network data and the historical data by adopting a long-short term memory network algorithm according to the granularity of one week for 15 minutes to establish a model, and modifying and optimizing the model according to the historical data;
and predicting the predicted value user number of a plurality of time intervals in the future with the granularity of 15 minutes by applying the model according to the current network data and the number of the connected users of the cells in the historical data.
In an alternative, the program 710 causes the processor to:
according to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
connecting the 3 centroids to form a triangle;
and calculating the number of the connected users corresponding to the intersection points of the three central lines of the triangle according to the Apollonian's theorem, and determining the number of the reference value users of the cell.
In an alternative, the program 710 causes the processor to:
establishing a linear regression model according to the daily connection user number of the historical major activities and the connection user number during the activities;
and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
In an alternative, the program 710 causes the processor to:
acquiring information of the early warning cell, wherein the information at least comprises longitude and latitude information and a neighboring cell relation;
finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation;
constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations;
and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
In an alternative, the program 710 causes the processor to:
if the surrounding of the base station of any one early warning cell is determined to have no early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the surrounding base stations with the neighboring cell relation are gathered, and the early warning area is output according to the coverage area of the base station;
and if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas.
The embodiment of the invention collects the current network data and the historical data, and comprises the following steps: connecting the number of users, the adjacent area relationship and the longitude and latitude information; calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data; inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell; and applying the Thiessen polygon to assemble and identify the coverage area of the early warning cell according to the adjacent cell relation and the longitude and latitude information, outputting the early warning area, accurately finding the early warning cell in advance, providing effective support for high-load cell analysis, improving the operation quality of the whole network, and optimizing the use perception of a user on the communication network.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. An early warning area identification method is characterized by comprising the following steps:
collecting the existing network data and historical data, comprising: connecting the number of users, the adjacent area relationship and the longitude and latitude information;
calculating the predicted value user number and the reference value user number of the cell according to the current network data and the number of the connected users of the cell in the historical data;
inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell;
and applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information, and outputting an early warning area.
2. The method of claim 1, wherein the calculating a predicted number of users and a reference number of users based on the number of connected users of the cell in the current network data and the historical data comprises:
acquiring the predicted value user number of the cell by adopting a long-short term memory network algorithm according to the current network data and the number of the connected users of the cell in the historical data;
and calculating the reference value user number of the cell by adopting a K-MEANS clustering algorithm and an Apoloney Oerss theorem according to the connected user number of the cell in the historical data.
3. The method according to claim 2, wherein the obtaining the predicted number of users of the cell by using a long-short term memory network algorithm according to the number of connected users of the cell in the current network data and the historical data further comprises:
slicing the current network data and the historical data by adopting a long-short term memory network algorithm according to the granularity of one week for 15 minutes to establish a model, and modifying and optimizing the model according to the historical data;
and predicting the predicted value user number of a plurality of time intervals in the future with the granularity of 15 minutes by applying the model according to the current network data and the number of the connected users of the cells in the historical data.
4. The method of claim 2, wherein calculating the reference number of users for a cell using a K-MEANS s clustering algorithm and aporonous's theorem according to the number of connected users for a cell in the historical data comprises:
according to the historical data with 15-minute granularity, randomly selecting 3 points, setting the number of the connected users with each 15-minute granularity as clusters C1, C2 and C3, and converging the historical data into 3 regions E according to a K-Means algorithm:
connecting the 3 centroids to form a triangle;
and calculating the number of the connected users corresponding to the intersection points of the three central lines of the triangle according to the Apollonian's theorem, and determining the number of the reference value users of the cell.
5. The method of claim 1, wherein the inputting the predicted value user number and the reference value user number of the cell into a linear regression model to obtain an early warning cell comprises:
establishing a linear regression model according to the daily connection user number of the historical major activities and the connection user number during the activities;
and inputting the predicted value user number and the reference value user number into the linear regression model, and determining the cell meeting continuous amplification as the early warning cell.
6. The method of claim 1, wherein the applying the Thiessen polygon to perform convergence and coverage area identification on the early warning cell according to the neighboring cell relation and the longitude and latitude information, and outputting an early warning area comprises:
acquiring information of the early warning cell, wherein the information at least comprises longitude and latitude information and a neighboring cell relation;
finding out the base station of the early warning cell according to the longitude and latitude information, and converging the base station according to the longitude and latitude information of the base station and the adjacent cell relation;
constructing Delaunay triangulation networks of all base stations by applying an algorithm in a Thiessen polygon according to the longitude and latitude information of the base stations, and connecting the centers of circumscribed circles of adjacent triangles of each base station to obtain the coverage areas of all the base stations;
and outputting the early warning area according to the adjacent area relation of the early warning cell and the coverage area of the base station.
7. The method of claim 6, wherein outputting the early warning area according to the neighboring cell relation of the base station of the early warning cell and the coverage area of the base station comprises:
if the surrounding of the base station of any one early warning cell is determined to have no early warning cell according to the longitude and latitude of the base station, the base station of the early warning cell and the surrounding base stations with the neighboring cell relation are gathered, and the early warning area is output according to the coverage area of the base station;
and if the early warning cells are arranged around the base station of any one of the early warning cells according to the latitude and longitude of the base station, externally expanding the early warning cells to determine the early warning base stations, crawling the coverage areas of all the early warning base stations through a network crawler, and outputting the early warning areas.
8. An early warning area identification apparatus, the apparatus comprising:
the data acquisition unit is used for collecting the present network data and the historical data, and comprises: connecting the number of users, the adjacent area relationship and the longitude and latitude information;
a calculating unit, configured to calculate a predicted value user number and a reference value user number of a cell according to the current network data and the number of connected users of the cell in the historical data;
the early warning cell acquisition unit is used for inputting the predicted value user number and the reference value user number of the cell into a linear regression model to acquire an early warning cell;
and the early warning area identification unit is used for applying a Thiessen polygon to carry out convergence and coverage area identification on the early warning cell according to the adjacent cell relation and the longitude and latitude information and outputting an early warning area.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the steps of the warning area identification method according to any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the steps of the warning region identification method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910989603.1A CN112686483B (en) | 2019-10-17 | 2019-10-17 | Early warning area identification method, early warning area identification device, computing equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910989603.1A CN112686483B (en) | 2019-10-17 | 2019-10-17 | Early warning area identification method, early warning area identification device, computing equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686483A true CN112686483A (en) | 2021-04-20 |
| CN112686483B CN112686483B (en) | 2024-08-13 |
Family
ID=75444807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910989603.1A Active CN112686483B (en) | 2019-10-17 | 2019-10-17 | Early warning area identification method, early warning area identification device, computing equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686483B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304594A (en) * | 2023-05-11 | 2023-06-23 | 北京融信数联科技有限公司 | User area identification method, system and medium based on communication data |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101106789A (en) * | 2007-07-10 | 2008-01-16 | 中国移动通信集团江苏有限公司 | Self-adapted adjustment system and its method for GSM network intelligent cell |
| US20160034823A1 (en) * | 2014-07-31 | 2016-02-04 | Collision Communications, Inc. | Methods, Systems, And Computer Program Products For Optimizing A Predictive Model For Mobile Network Communications Based On Historical Context Information |
| CN105426978A (en) * | 2014-09-04 | 2016-03-23 | 中兴通讯股份有限公司 | Service concurrency prediction method and service concurrency prediction system |
| CN105741486A (en) * | 2016-03-18 | 2016-07-06 | 东南大学 | Urban public space stampede accident real-time early warning method based on mobile phone positioning data |
| JP2017204174A (en) * | 2016-05-12 | 2017-11-16 | 日本電信電話株式会社 | Destination prediction apparatus, destination prediction method, and destination prediction program |
| CN108038563A (en) * | 2017-11-28 | 2018-05-15 | 深圳市金立通信设备有限公司 | A kind of data predication method, server and computer-readable recording medium |
| CN108053080A (en) * | 2017-12-30 | 2018-05-18 | 中国移动通信集团江苏有限公司 | Zone user quantity statistics value Forecasting Methodology, device, equipment and medium |
| CN108601031A (en) * | 2018-03-29 | 2018-09-28 | 中国联合网络通信集团有限公司 | Mapping method and device are shared in a kind of communication cell and geographic area |
| CN108877151A (en) * | 2018-07-11 | 2018-11-23 | 中国医学科学院生物医学工程研究所 | Fatigue driving method for early warning, device, equipment and storage medium |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
| CN109816175A (en) * | 2019-02-19 | 2019-05-28 | 迪爱斯信息技术股份有限公司 | Region number prediction technique and system based on variable componenent and Structural risk minization |
| CN109905892A (en) * | 2017-12-11 | 2019-06-18 | 中国电信股份有限公司 | Method for positioning user and device |
| CN110175711A (en) * | 2019-05-17 | 2019-08-27 | 北京市天元网络技术股份有限公司 | One kind being based on joint LSTM base station cell method for predicting and device |
| US20200371491A1 (en) * | 2017-10-26 | 2020-11-26 | Gb Gas Holdings Limited | Determining Operating State from Complex Sensor Data |
-
2019
- 2019-10-17 CN CN201910989603.1A patent/CN112686483B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101106789A (en) * | 2007-07-10 | 2008-01-16 | 中国移动通信集团江苏有限公司 | Self-adapted adjustment system and its method for GSM network intelligent cell |
| US20160034823A1 (en) * | 2014-07-31 | 2016-02-04 | Collision Communications, Inc. | Methods, Systems, And Computer Program Products For Optimizing A Predictive Model For Mobile Network Communications Based On Historical Context Information |
| CN105426978A (en) * | 2014-09-04 | 2016-03-23 | 中兴通讯股份有限公司 | Service concurrency prediction method and service concurrency prediction system |
| CN105741486A (en) * | 2016-03-18 | 2016-07-06 | 东南大学 | Urban public space stampede accident real-time early warning method based on mobile phone positioning data |
| JP2017204174A (en) * | 2016-05-12 | 2017-11-16 | 日本電信電話株式会社 | Destination prediction apparatus, destination prediction method, and destination prediction program |
| US20200371491A1 (en) * | 2017-10-26 | 2020-11-26 | Gb Gas Holdings Limited | Determining Operating State from Complex Sensor Data |
| CN108038563A (en) * | 2017-11-28 | 2018-05-15 | 深圳市金立通信设备有限公司 | A kind of data predication method, server and computer-readable recording medium |
| CN109905892A (en) * | 2017-12-11 | 2019-06-18 | 中国电信股份有限公司 | Method for positioning user and device |
| CN108053080A (en) * | 2017-12-30 | 2018-05-18 | 中国移动通信集团江苏有限公司 | Zone user quantity statistics value Forecasting Methodology, device, equipment and medium |
| CN108601031A (en) * | 2018-03-29 | 2018-09-28 | 中国联合网络通信集团有限公司 | Mapping method and device are shared in a kind of communication cell and geographic area |
| CN108877151A (en) * | 2018-07-11 | 2018-11-23 | 中国医学科学院生物医学工程研究所 | Fatigue driving method for early warning, device, equipment and storage medium |
| CN109754113A (en) * | 2018-11-29 | 2019-05-14 | 南京邮电大学 | Load forecasting method based on dynamic time warping Yu length time memory |
| CN109816175A (en) * | 2019-02-19 | 2019-05-28 | 迪爱斯信息技术股份有限公司 | Region number prediction technique and system based on variable componenent and Structural risk minization |
| CN110175711A (en) * | 2019-05-17 | 2019-08-27 | 北京市天元网络技术股份有限公司 | One kind being based on joint LSTM base station cell method for predicting and device |
Non-Patent Citations (3)
| Title |
|---|
| LIJUAN ZHOU ET AL.: "Improved data mining algorithms based on an early warning system of college students", 《 JOURNAL OF SOFTWARE》, vol. 8, no. 9, 30 September 2013 (2013-09-30), pages 2352 - 2359 * |
| 郑亚平等: "基于AI的突发人流聚集区域识别与预警方法", 电信工程技术与标准化, no. 09, 11 September 2020 (2020-09-11), pages 82 - 86 * |
| 钟鼎;: "基于神经网络的4G用户感知预警模型构建和应用", 电信技术, no. 11, 25 November 2016 (2016-11-25), pages 76 - 78 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116304594A (en) * | 2023-05-11 | 2023-06-23 | 北京融信数联科技有限公司 | User area identification method, system and medium based on communication data |
| CN116304594B (en) * | 2023-05-11 | 2023-09-08 | 北京融信数联科技有限公司 | User area identification method, system and medium based on communication data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686483B (en) | 2024-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021012930A1 (en) | Voting node configuration method and system | |
| CN109176168B (en) | Tool sharpening tune machine device and method | |
| CN111294841B (en) | Method, device and storage medium for processing wireless network problem | |
| CN111475746B (en) | Point-of-interest mining method, device, computer equipment and storage medium | |
| CN111179108A (en) | Method and device for predicting power consumption | |
| CN103997515A (en) | Distributed cloud computing center selection method and application thereof | |
| CN112686483B (en) | Early warning area identification method, early warning area identification device, computing equipment and computer storage medium | |
| CN111144673A (en) | Method, device and equipment for evaluating structure of organization personnel and computer readable medium | |
| CN116521372A (en) | Management method of server cluster and related components | |
| Chandio et al. | Towards adaptable and tunable cloud-based map-matching strategy for GPS trajectories | |
| CN115511343A (en) | Method, device, equipment and storage medium for determining city core area | |
| CN112365103B (en) | Method, device, equipment and medium for predicting short-term load of building in operation stage | |
| CN111817898B (en) | Method and device for identifying dynamic network structure abnormality | |
| CN114554535A (en) | Method, device, equipment and storage medium for intelligently identifying common coverage cell pairs | |
| CN115271142A (en) | Channel site selection method and device, electronic equipment and readable storage medium | |
| CN112434430A (en) | Method and device for predicting cell capacity | |
| CN113076184A (en) | Power acquisition terminal task scheduling method based on fuzzy comprehensive evaluation | |
| CN113642834A (en) | Task importance evaluation method and system based on task attribute priority mapping | |
| CN113015153B (en) | Method and device for identifying attribution of serving cell | |
| CN115696348A (en) | 5G base station planning method and device | |
| CN108182494A (en) | load forecasting method, device, storage medium and processor | |
| CN116451168B (en) | Abnormal power information generation method, device, electronic equipment and readable medium | |
| CN117350549B (en) | Distribution network voltage risk identification method, device and equipment considering output correlation | |
| CN109494792B (en) | Method and device for determining light abandoning electric quantity of photovoltaic power station | |
| WO2022156743A1 (en) | Feature construction method and apparatus, model training method and apparatus, and device and medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |