Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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, but 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.
The current cell identification method can only identify and obtain the resident base station cell of the user, and when one base station comprises a plurality of physical cells, the physical cell where the user actually lives cannot be accurately positioned, which brings inconvenience to the stationing point marketing of operators. In view of the foregoing problems, an embodiment of the present invention provides a method for identifying a resident physical cell. Fig. 1 is a flowchart illustrating a resident physical cell identification method according to an embodiment of the present invention, as shown in fig. 1, the method includes:
and 110, acquiring the user resident base station based on the user signaling data.
Here, the user signaling data is signaling data of a user who needs to perform resident physical cell identification, and the signaling data may be from a smart phone or from a communication tool such as a smart watch. The user signaling data may be obtained by extracting signaling data of the mobile core network and the wireless side, for example, the user signaling data is obtained through an a (abis) interface and an S1-MME (Mobility Management Entity) interface. The user resident base station is a resident base station of a user acquired based on user signaling data, and here, there are various methods for acquiring the user resident base station based on the user signaling data, for example, the user resident base station is acquired by a spatial clustering method, and for example, the resident cell information of the user activity is counted based on a preset rule, so as to identify the user resident base station.
120, acquiring a preset number of adjacent base stations based on the user resident base station; the nearby base station is the base station closest to the user's resident base station based on the user signaling data acquisition.
Specifically, after the user resident base station is obtained, a preset number of base stations closest to each other are selected from each base station as neighboring base stations based on the distance between the user resident base station and each base station around the user resident base station appearing in user signaling data. Here, the preset number is a preset number of neighboring base stations, for example, the preset number is 3, and the first three base stations closest to the user resident base station are selected from each base station appearing in the user signaling data as the neighboring base stations.
130, selecting a resident physical cell from each physical cell based on the distance between each physical cell corresponding to the user resident base station and each adjacent base station and the all-day resident data of each adjacent base station; the all-day camping data of the adjacent base station is acquired based on the user signaling data.
Specifically, the all-day camping data of the neighboring base station is data acquired based on the user signaling and appearing in the neighboring base station all day by the user within a preset period. The physical cell corresponding to the user resident base station refers to a physical cell within the coverage range of the user resident base station cell, and whether any physical cell is the physical cell corresponding to the user resident base station or not can be judged by calculating the distance between the user resident base station and the central point of the physical cell and comparing the distance with the coverage radius of the user resident base station. There may be more than one physical cell corresponding to the user's resident base station.
And after the physical cell and the adjacent base station corresponding to the user resident base station are obtained, calculating the distance between each physical cell and the adjacent base station. And then, based on the distance between the physical cell and the adjacent base station and the all-day resident data of the adjacent base station, selecting one physical cell from all the physical cells corresponding to the user resident base station as a resident physical cell. For example, the distance between the physical cell and the neighboring base station and the all-day residence data of the neighboring base station are input into a pre-trained model, the resident physical cell output by the model is obtained, the score of each physical cell is calculated according to the distance between the physical cell and the neighboring base station and the all-day residence data of the neighboring base station, and the resident physical cell is selected according to the score.
According to the method provided by the embodiment of the invention, the resident physical cell is selected based on the distance between each physical cell corresponding to the user resident base station and each adjacent base station and the all-day resident data of each adjacent base station, so that the positioning accuracy of the residence of the user physical cell is effectively improved, the difficulty of mapping and identifying the user resident base station cell and the resident physical cell is reduced, and the marketing accuracy of customers is further improved.
Based on the above embodiment, step 110 specifically includes:
111, acquiring night resident data of each base station in a preset date based on user signaling data; the night stay data includes a night stay duration and/or a number of night stays.
Specifically, the night camping data is data acquired based on user signaling and presented to the base station at night by the user within a preset period. The night stay duration is duration that a user appears in the base station at night within a preset time, and the night stay is here the number of times that the user appears in the base station at night within the preset time. For example, the preset time period is every odd days in one month, the night is set to 00:00 to 06:00, and one day is divided into 24 time periods, so that the night residence time of any base station is the accumulated time length of residence of every odd days 00:00 to 06:00 users in the base station in one month, and the night residence time of any base station is the accumulated hours of residence of every odd days 00:00 to 06:00 users in the base station in one month.
The night stay duration and the night stay times of any base station are as follows:
in the formula, thiAnd tdiRespectively the night stay time length and the night stay times th of the ith base stationijkIs the residence time of the ith base station in the jth time period on the kth day, tdijkThe number of times of residence of the ith base station in the jth time period on the kth day, j is the night time period, and k is the preset period.
And 112, acquiring the night residence score of any base station based on the night residence data of the base station.
Here, the night stay score corresponding to the night stay data may be obtained through a preset table, and the night stay score may also be obtained by calculating based on the night stay data through a preset calculation rule, which is not specifically limited in the embodiment of the present invention.
And 113, selecting the base station with the highest night residence score from each base station as the user resident base station.
According to the method provided by the embodiment of the invention, the user resident base station is selected by acquiring the night resident score of each base station, and the positioning accuracy of the user resident base station is improved by utilizing the daily work and rest rules of a plurality of users.
Based on any of the above embodiments, step 112 specifically includes: normalizing the night residence time of each base station to obtain the night normalized time of each base station; normalizing the night residence times of each base station to obtain the night normalization times of each base station; and multiplying the night normalization duration of any base station by the night normalization times to obtain the night residence score of the base station.
Specifically, the night normalized time length of any base station is obtained according to the following formula:
in the formula (I), the compound is shown in the specification,
normalized time length at night for ith base station, th
iIs the night stay duration, max (th) of the ith base station
i) And min (th)
i) Respectively, the maximum value and the minimum value of the night dwell time of each base station.
The night normalization times of any base station are obtained according to the following formula:
in the formula (I), the compound is shown in the specification,
is the night normalization number of the ith base station, td
iNumber of nighttime dwells, max (td), for the ith base station
i) And min (td)
i) Respectively, the maximum value and the minimum value of the night dwell times of each base station.
Obtaining the night stay score s of any base station according to the following formulai:
Based on any of the above embodiments, step 130 further includes: acquiring all-day resident data of each adjacent base station in a preset date based on user signaling data; the all-day residence data comprises all-day residence time and/or all-day residence times.
Specifically, the all-day camping data is data acquired based on user signaling and appearing in the base station by the user all day within a preset period. The all-day residence time is the time length of the user appearing in the base station all day in the preset time, and the all-day residence is the times of the user appearing in the base station all day in the preset time. For example, the preset period is every odd-numbered day in one month, and one day is divided into 24 time periods, so that the all-day residence time length of any adjacent base station is the accumulated time length of each odd-numbered day user residing in the base station in one month, and the all-day residence times of any adjacent base station is the accumulated hours of each odd-numbered day user residing in the base station in one month.
The whole-day residence time and the whole-day residence times of any adjacent base station are as follows:
in the formula, thi' and tdi' the total resident time length and the total resident times, th of the ith adjacent base stationijk' is the residence time of the ith adjacent base station in the jth time period on the kth day, tdijk' is the residence time of the ith adjacent base station in the jth time period on the kth day, j is the whole day time period, and k is the preset time period.
Based on any of the above embodiments, step 130 specifically includes:
and 131, aiming at any physical cell, acquiring an influence factor of the physical cell based on the distance between the physical cell and each adjacent base station and the all-day resident data of each adjacent base station.
And 132, selecting the physical cell with the largest influence factor from each physical cell as a resident physical cell.
Here, the influence factor is used to characterize the possibility that a physical cell is a resident physical cell, and the larger the influence factor is, the higher the possibility that the corresponding physical cell is a resident physical cell is.
Further, step 131 specifically includes: normalizing the all-day residence time of each adjacent base station to obtain the all-day normalized time of each adjacent base station; normalizing the all-day residence times of each adjacent base station to obtain the all-day normalized times of each adjacent base station; normalizing the distance between each physical cell and each adjacent base station to obtain the normalized distance between each physical cell and each adjacent base station; and acquiring the influence factor of the physical cell based on the normalized distance between any physical cell and each adjacent base station, the all-day normalized time length and the all-day normalized times of each adjacent base station.
Specifically, the normalized time length of any adjacent base station in the whole day is obtained according to the following formula:
in the formula (I), the compound is shown in the specification,
normalized time length, th, of the ith neighbor base station
i' is the whole day residence time length, max (th) of the ith neighbor base station
i') and min (th)
i') are the maximum and minimum values, respectively, of the all-day dwell time period for each neighboring base station.
Obtaining the whole-day normalized times of any adjacent base station according to the following formula:
in the formula (I), the compound is shown in the specification,
is the total day normalized times, td, of the ith adjacent base station
i' is the number of whole day dwells, max (td), of the ith neighbor base station
i') and min (td)
i') are the maximum and minimum values, respectively, of the number of dwells per day for each neighboring base station.
The normalized distance between any physical cell and any nearby base station is obtained according to the following formula:
in the formula (I), the compound is shown in the specification,
is the normalized distance, len, between the mth physical cell and the nth neighboring base station
mnIs the normalized distance, max (len), between the mth physical cell and the nth neighboring base station
mn) And min (len)
mn) Respectively the maximum and minimum of the distance between each physical cell and each neighbouring base station.
After the all-day normalized time length and the all-day normalized times of each adjacent base station and the normalized distance between each physical cell and each adjacent cell are obtained, for any physical cell, the influence factor of the physical cell is obtained based on the normalized distance between the physical cell and each adjacent base station and the all-day normalized time length and the all-day normalized times of each adjacent base station.
Further, the impact factor of the physical cell is obtained by the following formula:
in the formula, aff
nFor the impact factor of the nth physical cell,
and
respectively the all-day normalized time length and the all-day normalized times of the mth adjacent base station,
is the normalized distance, w, between the nth physical cell and the mth neighboring base station
th、w
tdAnd w
lenRespectively, time length weight, frequency weight and distance weight, and l is the number of adjacent base stations.
Here, the time length weight, the order weight, and the distance weight in the above equation are set in advance. For example, the weights may be adjusted according to sample data obtained by sampling based on a logistic regression algorithm to obtain an approximation optimal for the influence factors, and further determine the final duration weight, the frequency weight, and the distance weight.
Based on any of the above embodiments, a resident physical cell identification method includes the following steps:
first, based on the user signaling data obtained by the interface a and the interface S1-MME, the time length th for the base station to appear in each time period (each day is divided into 24 time periods) is obtainedijkAnd number of times tdijkWherein i is the base station number, i is 1,2, …, n is the total number of base stations; j is a time period, j is 0,1,2, …, 23; k is a preset date for indicating a specific date.
Secondly, the night residence time th of the ith base station of the selected days in the previous month is countediAnd night stay number tdi. In order to reflect the generality, 5 days are selected in the upper, middle and lower ten days, 15 days are used as sampling points, and the night is set to be 00:00 to 06:00, then:
in the formula, thiAnd tdiRespectively the night stay time length and the night stay times th of the ith base stationijkIs the residence time of the ith base station in the jth time period on the kth day, tdijkThe number of times of residence of the ith base station in the jth time period on the kth day, j is the night time period, and k is the selected 15 dates.
Then, normalizing the night residence time and the night residence times of each base station to obtain the night normalized time and the night normalized times of each base station as follows:
in the formula (I), the compound is shown in the specification,
normalized time length at night for ith base station, th
iIs the night stay duration, max (th) of the ith base station
i) And min (th)
i) Respectively being the maximum value and the minimum value of the night residence time of each base station;
is the night normalization number of the ith base station, td
iNumber of nighttime dwells, max (td), for the ith base station
i) And min (td)
i) Respectively, the maximum value and the minimum value of the night dwell times of each base station.
Multiplying night normalization duration of any base station by night normalization times to obtain night residence time of the base stationScoring
And then, selecting the base station with the highest night residence score from each base station as the user resident base station.
Then, based on the user signaling data, a preset number of base stations closest to the user resident base station are selected as the adjacent base stations. Here, the preset number is 3. Counting the whole-day residence time th of each adjacent base station in the selected days of the previous monthi' and number of whole day dwells tdi'. Similarly, 5 days are selected in the upper, middle and lower ten days, and 15 days are taken as sampling points, then:
in the formula, thi' and tdi' the total resident time length and the total resident times, th of the ith adjacent base stationijk' is the residence time of the ith adjacent base station in the jth time period on the kth day, tdijk' is the residence time of the ith adjacent base station in the jth time period on the kth day, j is the whole day time period, and k is the preset time period.
In addition, a physical cell corresponding to the user resident base station is obtained through the crawler. Specifically, a mapping relation between a cell of the user permanent base station and a physical cell is established, a distance between the cell of the user permanent base station and a central point of the physical cell is calculated, and if the distance is less than a radius covered by the user permanent base station, the physical cell belongs to the cell of the user permanent base station.
Then, calculating the distance between the physical cell corresponding to each user resident base station and each adjacent base station, and normalizing the all-day residence time and the all-day residence times of each adjacent base station and the distance between each physical cell and each adjacent base station respectively to obtain the all-day normalized time and the all-day normalized times of each adjacent base station, and the normalized distance between each physical cell and each adjacent base station as follows:
in the formula (I), the compound is shown in the specification,
normalized time length, th, of the ith neighbor base station
i' is the whole day residence time length, max (th) of the ith neighbor base station
i') and min (th)
i') is the maximum value and the minimum value of the whole-day residence time of each adjacent base station respectively;
is the total day normalized times, td, of the ith adjacent base station
i' is the number of whole day dwells, max (td), of the ith neighbor base station
i') and min (td)
i') is the maximum value and the minimum value of the whole day residence times of each adjacent base station respectively;
is the normalized distance, len, between the mth physical cell and the nth neighboring base station
mnIs the normalized distance, max (len), between the mth physical cell and the nth neighboring base station
mn) And min (len)
mn) Respectively the maximum and minimum of the distance between each physical cell and each neighbouring base station.
Then, for any physical cell, based on the normalized distance between the physical cell and each neighboring base station, and the all-day normalized time length and the all-day normalized times of each neighboring base station, obtaining the impact factor of the physical cell by the following formula:
in the formula, aff
nFor the impact factor of the nth physical cell,
and
respectively the all-day normalized time length and the all-day normalized times of the mth adjacent base station,
is the normalized distance, w, between the nth physical cell and the mth neighboring base station
th、w
tdAnd w
lenRespectively, time length weight, frequency weight and distance weight, and l is the number of adjacent base stations.
And finally, selecting the physical cell with the largest influence factor from each physical cell as a resident physical cell.
According to the method provided by the embodiment of the invention, the resident physical cell is selected based on the distance between each physical cell corresponding to the user resident base station and each adjacent base station and the all-day resident data of each adjacent base station, so that the positioning accuracy of the residence of the user physical cell is effectively improved, the difficulty of mapping and identifying the user resident base station cell and the resident physical cell is reduced, and the marketing accuracy of customers is further improved.
Based on any of the above embodiments, fig. 2 is a schematic structural diagram of a resident physical cell identification apparatus according to an embodiment of the present invention, as shown in fig. 2, the resident physical cell identification apparatus includes a resident base station acquiring unit 210, an adjacent base station acquiring unit 220, and a physical cell identification unit 230;
the resident base station obtaining unit 210 is configured to obtain a user resident base station based on user signaling data;
the neighboring base station obtaining unit 220 is configured to obtain a preset number of neighboring base stations based on the user resident base station; the nearby base station is a base station which is obtained based on the user signaling data and is closest to the user resident base station;
the physical cell identification unit 230 is configured to select a resident physical cell from each physical cell corresponding to the user's resident base station based on a distance between each physical cell and each neighboring base station, and the all-day resident data of each neighboring base station; the all-day camping data of the adjacent base station is obtained based on the user signaling data.
According to the device provided by the embodiment of the invention, the resident physical cell is selected based on the distance between each physical cell corresponding to the user resident base station and each adjacent base station and the all-day resident data of each adjacent base station, so that the positioning accuracy of the residence place of the user physical cell is effectively improved, the difficulty of mapping and identifying the user resident base station cell and the resident physical cell is reduced, and the marketing accuracy of a client is further improved.
Based on any of the above embodiments, the resident base station acquiring unit 210 specifically includes a night data acquiring subunit, a night scoring subunit, and a night selecting subunit;
the night data acquisition subunit is used for acquiring night resident data of each base station in a preset date based on the user signaling data; the night stay data comprises night stay duration and/or night stay times;
the night evaluation unit is used for acquiring the night residence score of any base station based on the night residence data of any base station;
and the night selection subunit is used for selecting the base station with the highest night residence score from each base station as the user resident base station.
Based on any of the above embodiments, the night scoring unit is specifically configured to:
normalizing the night residence time of each base station to obtain the night normalized time of each base station;
normalizing the night residence times of each base station to obtain the night normalization times of each base station;
and multiplying the night normalization duration of any base station by the night normalization times to obtain the night residence score of any base station.
Based on any of the above embodiments, the resident physical cell identification apparatus further includes a neighboring base station data acquisition unit;
the adjacent base station data acquisition unit is used for acquiring all-day resident data of each adjacent base station in a preset date based on the user signaling data; the all-day residence data comprise all-day residence time and/or all-day residence times.
Based on any of the above embodiments, the physical cell identification unit 230 includes an influence factor subunit and a cell identification subunit;
the influence factor subunit is configured to, for any one of the physical cells, obtain an influence factor of the any one physical cell based on a distance between the any one physical cell and each of the neighboring base stations and the all-day camping data of each of the neighboring base stations;
and the cell identification subunit is configured to select the physical cell with the largest impact factor from each physical cell as the resident physical cell.
Based on any of the above embodiments, the impact factor subunit includes a normalization module and a calculation module;
the normalization module is used for normalizing the all-day residence time length of each adjacent base station to obtain the all-day normalized time length of each adjacent base station; normalizing the all-day residence times of each adjacent base station to obtain the all-day normalized times of each adjacent base station; normalizing the distance between each physical cell and each adjacent base station to obtain the normalized distance between each physical cell and each adjacent base station;
the calculation module is configured to obtain an impact factor of any physical cell based on the normalized distance between the physical cell and each neighboring base station, the all-day normalized time length of each neighboring base station, and the all-day normalized times.
Based on any of the embodiments above, the calculation module is specifically configured to: obtaining an impact factor of any one of the physical cells by:
in the formula, aff
nFor the impact factor of the nth physical cell,
and
respectively the all-day normalized time length and the all-day normalized times of the mth adjacent base station,
is the normalized distance, w, between the nth physical cell and the mth neighboring base station
th、w
tdAnd w
lenRespectively, time length weight, frequency weight and distance weight, and l is the number of adjacent base stations.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a communication bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the communication bus 304. The processor 301 may invoke a computer program stored on the memory 303 and executable on the processor 301 to perform the resident physical cell identification method provided by the above embodiments, for example, including: acquiring a user resident base station based on user signaling data; acquiring a preset number of adjacent base stations based on the user resident base station; the nearby base station is a base station which is obtained based on the user signaling data and is closest to the user resident base station; selecting a resident physical cell from each physical cell based on the distance between each physical cell corresponding to the user resident base station and each adjacent base station and the all-day resident data of each adjacent base station; the all-day camping data of the adjacent base station is obtained based on the user signaling data.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or make a contribution to the prior art, or may be implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method for identifying a resident physical cell provided in the foregoing embodiments when executed by a processor, for example, the method includes: acquiring a user resident base station based on user signaling data; acquiring a preset number of adjacent base stations based on the user resident base station; the nearby base station is a base station which is obtained based on the user signaling data and is closest to the user resident base station; selecting a resident physical cell from each physical cell based on the distance between each physical cell corresponding to the user resident base station and each adjacent base station and the all-day resident data of each adjacent base station; the all-day camping data of the adjacent base station is obtained based on the user signaling data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.