A method and system for determining permanent population based on communication big data

Abstract

The application provides a method and system for determining permanent population based on communication big data, utilizes spatial index technology to efficiently organize and quickly search massive signaling location data, realizes second-level screening of candidate users in any polygonal area from hundred-million-level data, introduces base station antenna azimuth, covering angle and other working parameter data, accurately calculates base station covering space and carries out geometric relation analysis with a target area, utilizes threshold intelligent screening of "effective base stations", fundamentally corrects population misjudgment caused by base station directional covering and boundary effect, and significantly improves the accuracy of small-scale regional population screening. The whole scheme is constructed on a big data parallel computing framework, realizes quick response to ten-thousand-level regional query in a high-concurrency environment through data fragmentation, task dynamic splitting and parallel processing.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for determining permanent residents based on big data communication. Background Technology

[0002] With the rapid development and widespread adoption of mobile communication technology, especially 5G networks, the number of mobile phone users continues to expand, and base station construction is becoming increasingly dense. This enables telecom operators to acquire communication signaling data with wide coverage, strong continuity, and a massive user base. The user location information contained in this data provides an unprecedented data foundation for population spatiotemporal distribution analysis in various fields such as smart city management, public safety emergency response, regional planning, and business insights. Compared to internet location data, operator signaling data has significant advantages such as not requiring active user triggering, continuous collection around the clock, and relatively comprehensive population coverage, making it play an increasingly important role in macro-level situational awareness and decision support at the enterprise level.

[0003] However, applying communication big data efficiently and accurately to regional population determination still faces a series of severe technical challenges. First, regarding positioning accuracy, traditional cell-based positioning methods are limited by the density and distribution of base stations, typically only locating users within a few hundred meters or even a kilometer of the cell's coverage area. In scenarios requiring small-scale (e.g., street, community) population statistics, such as regional population insights, emergency command, and precise policy implementation, this coarse-grained positioning leads to significant biases in regional user screening results. It struggles to distinguish users located inside or outside the regional boundaries who are misidentified due to connections to neighboring base stations, severely impacting the accuracy and application value of the analysis results. Second, regarding computational timeliness and processing capacity, operator signaling data is massive, reaching tens or even hundreds of millions of units, and is updated frequently. Existing population analysis solutions mostly employ offline batch processing, using data from the previous day or historical data for statistics, which cannot meet the urgent needs of second- or minute-level responses in scenarios such as emergency management and real-time monitoring. Simultaneously, existing solutions lack effective support for high-concurrency queries, making it difficult to simultaneously handle massive, random, multi-regional population statistics requests, resulting in insufficient system scalability and practicality. In addition, existing technical solutions, when improving accuracy, mostly focus on expanding and correcting the sampled data through statistical models or using historical trajectories for dwell pattern analysis. They fail to fully explore and utilize the engineering parameters of the base station itself (such as antenna azimuth angle, beamwidth, etc.) to finely model the actual coverage space of the base station, resulting in limited ability to solve the problem of misjudgment of boundary users at the physical space level.

[0004] Therefore, the urgent technical problem to be solved in this field is: how to design a method for determining the regional resident population that can take into account high accuracy, high efficiency and high concurrency capabilities, so as to overcome the shortcomings of existing population analysis technology based on communication big data, such as rough positioning, slow response and inability to support real-time multi-region concurrent computing, so as to truly unleash the application potential of operator location big data and meet the urgent needs for real-time and accurate population situation awareness in scenarios such as smart cities and emergency management. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for determining permanent residents based on big data communication, so as to solve the problems existing in the prior art.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] This invention provides a method for determining permanent residents based on big data communication, comprising the following steps:

[0008] S1. Obtain the boundary information of the target area, the base station engineering parameters provided by the operator, and user signaling data;

[0009] S2. Preprocess user signaling data based on a multi-dimensional spatial indexing algorithm to encode user location information into spatial grid identifiers;

[0010] S3. Based on the boundary information of the target region and the multi-dimensional spatial indexing algorithm, calculate the minimum grid set covering the target region and its corresponding spatial filling curve range.

[0011] S4. Based on the range of the space filling curve interval, select a set of candidate users from the preprocessed user signaling data;

[0012] S5. Based on the antenna azimuth, coverage angle and location information in the base station engineering parameters, calculate the coverage space range of each base station, and based on whether the overlap area ratio between the coverage space range and the target area is greater than a preset threshold, filter out the effective base station set of the target area.

[0013] S6. Based on the base station connection information in the user signaling data, select users who are connected to base stations in the effective base station set from the candidate user set to obtain the resident population data of the target area.

[0014] Preferably, in step S2, the multidimensional spatial indexing algorithm is the S2 algorithm or the GeoHash algorithm; step S2 includes: encoding the latitude and longitude coordinates in the user signaling data into the corresponding S2 Cell ID or GeoHash encoding.

[0015] Preferably, in step S5, the base station engineering parameters include at least: antenna azimuth angle, coverage angle, and base station latitude and longitude coordinates; the coverage space of the base station is approximated as a triangular or sector-shaped area with the base station location as the vertex, the coverage distance as the radius, the antenna azimuth angle as the center, and the coverage angle as the subtended angle.

[0016] Preferably, step S5 specifically includes:

[0017] S51. Establish a coordinate system with the latitude and longitude coordinates of the base station as the origin;

[0018] S52. Calculate the azimuth angle range of the coverage space boundary based on the antenna azimuth angle and coverage angle;

[0019] S53. Calculate the coordinates of multiple vertices of the coverage space boundary based on the azimuth angle range and the preset coverage distance;

[0020] S54. Calculate the coverage area of ​​the base station and the intersection and overlap area between the coverage area and the target area based on the vertex coordinates.

[0021] S55. Calculate the ratio of the intersection overlap area to the coverage area. If the ratio is greater than or equal to the preset threshold, the base station is determined to be a valid base station.

[0022] Preferably, steps S4 and S5 are implemented using a distributed parallel computing framework, specifically including:

[0023] User signaling data is segmented according to administrative regions and user identifiers;

[0024] Determine the relevant data fragments based on the target region;

[0025] The computing task is dynamically divided into multiple sub-tasks, which are then distributed to multiple computing nodes to execute the spatial filtering and base station filtering steps in parallel.

[0026] Aggregate the results from each computing node.

[0027] Preferably, the parallel computing framework is Spark or Flink.

[0028] Preferably, in step S5, the preset threshold value ranges from greater than 0 to less than 1, which is used to control the strictness of base station screening.

[0029] This invention provides a system for determining permanent residents based on big data from communications, employing a method for determining permanent residents based on big data from communications. The system includes:

[0030] The data acquisition module is used to acquire boundary information of the target area, base station engineering parameters provided by the operator, and user signaling data;

[0031] The data preprocessing module is used to preprocess user signaling data based on a multidimensional spatial indexing algorithm, and encode user location information into spatial grid identifiers;

[0032] The spatial index calculation module is used to calculate the minimum grid set covering the target area and its corresponding spatial filling curve range based on the boundary information of the target area and the multidimensional spatial indexing algorithm.

[0033] The candidate user filtering module is used to filter out a set of candidate users from the preprocessed user signaling data based on the range of the space filling curve interval.

[0034] The effective base station filtering module is used to calculate the coverage area of ​​each base station according to the base station engineering parameters, and filter out the effective base station set of the target area based on whether the overlap area ratio between the coverage area and the target area is greater than a preset threshold.

[0035] The population determination module is used to filter out users who are connected to base stations in the effective base station set from the candidate user set based on the base station connection information in the user signaling data, so as to obtain the resident population data of the target area.

[0036] The present invention also provides an electronic device, including at least one processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the at least one processor, the device implements a method for determining the permanent population based on big data communication.

[0037] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method for determining permanent residents based on big data communication.

[0038] The present invention achieves the following beneficial technical effects compared to the prior art:

[0039] This invention provides a method and system for determining permanent residents based on big data communication. By innovatively integrating multi-dimensional spatial indexing algorithms, base station antenna engineering parameter screening, and a distributed parallel computing architecture, it effectively solves the core problems of low accuracy, slow speed, and weak concurrency in existing regional population statistics technologies. This invention utilizes spatial indexing technology to efficiently organize and rapidly retrieve massive signaling location data, achieving second-level filtering of candidate users within arbitrary polygonal regions from hundreds of millions of data points. Furthermore, by introducing engineering parameters such as base station antenna azimuth and coverage angle, it accurately calculates the base station coverage space and performs geometric relationship analysis with the target region. Using threshold-based intelligent filtering of "effective base stations," it fundamentally corrects population misjudgments caused by base station directional coverage and boundary effects, significantly improving the accuracy of small-scale regional population screening. In particular, the entire solution is built on a big data parallel computing framework, achieving rapid response to tens of thousands of regional queries under high concurrency environments through data sharding, dynamic task splitting, and parallel processing. This invention combines high positioning accuracy, low response latency, and strong concurrency support capabilities, providing real-time, reliable, and accurate data decision support in scenarios such as population monitoring, emergency command, and regional planning. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A flowchart of the method for determining permanent residents based on big data communication provided by the present invention;

[0042] Figure 2 The flowchart of the regional population screening algorithm in the method for determining the permanent population based on communication big data provided by the present invention;

[0043] Figure 3 This is a schematic diagram of user location data grouping and fragmentation in the method for determining permanent residents based on big data communication provided by the present invention.

[0044] Figure 4 A schematic diagram of the spatial range of base station antenna coverage in the method for determining the permanent population based on communication big data provided by the present invention;

[0045] Figure 5 The flowchart of the regional effective base station screening algorithm in the method for determining the permanent population based on communication big data provided by the present invention; Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] The purpose of this invention is to provide a method and system for determining the permanent population based on communication big data, aiming to solve the technical problems of insufficient positioning accuracy, low computational efficiency, and inability to support high-concurrency real-time queries when using communication big data to determine the regional population. The core concept of this solution lies in constructing a two-stage high-precision, high-efficiency screening model by integrating multi-dimensional spatial indexing technology with base station antenna engineering parameters, and relying on a big data parallel computing framework to achieve the system's horizontal scalability, thereby meeting the needs for real-time and accurate regional population statistics in scenarios such as emergency management and smart cities.

[0048] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0049] Example 1:

[0050] This embodiment provides a method for determining permanent residents based on big data communication data. Specifically, as follows: Figure 1 The overall flowchart of the present invention shown, and Figure 2 The detailed flowchart of the regional population screening algorithm shown is as follows. The implementation of this scheme is mainly divided into two parallel and eventually convergent computational main lines: one is the rapid screening of regional candidate users based on spatial index; the other is the refined screening of regional effective base stations based on base station antenna parameters.

[0051] First, data preparation and preprocessing are performed. The system needs to acquire three basic data sources: boundary information of the target area, user signaling data provided by the telecom operator, and base station engineering parameter data. The boundary of the target area consists of a set of ordered latitude and longitude vertices, which can be any polygon. User signaling data includes at least a timestamp, user anonymity identifier (such as IMSI), and the identifier of the connected base station cell. Base station engineering parameter data includes key information such as base station cell identifier, latitude and longitude coordinates, antenna azimuth angle, and antenna coverage angle (degRange). To improve subsequent computational efficiency, the massive signaling data needs to be preprocessed by using a multidimensional spatial indexing algorithm (such as the S2 algorithm) to encode the geographical location (latitude and longitude) corresponding to each signaling message into a discrete spatial grid identifier (s2CellId). This step transforms the continuous two-dimensional spatial query problem into an efficient range lookup problem for a one-dimensional encoded sequence. Figure 3As shown, the preprocessed data can also be grouped and fragmented according to administrative regions and user identifiers, laying the foundation for distributed parallel computing.

[0052] Phase 1: Rapid screening of candidate users based on spatial indexing

[0053] The goal of this stage is to quickly narrow down the query scope from massive amounts of data. The algorithm is described as follows:

[0054] Step 1: Perform S2 encoding on the latitude and longitude of the signaling location data, and then encode the object p. i ={OID i ,Lng i ,Lat i} convert to pi={OID i s2Cell Id}, where OID is the unique identifier of the object.

[0055] Step 2: Calculate the minimum mesh size for the target region Z. Region Z is defined by the vertex sequence. Using the S2 library functions, find the minimum number of specific-level meshes that can completely cover the polygon; assume we get m meshes. Take the maximum and minimum values ​​of these mesh codes to obtain the range of the one-dimensional space-filling curve for the region Z:

[0056] Zspace-filling-curve=[[ cellId 0,min ,cellId 0,max ],[ cellId 1,min , cellId 1,max ],……,[ cellId m-1,min , cellId m-1,max ]];

[0057] Step 3: Based on the S2 encoding of the object and the Zspace-filling-curve interval of the region, quickly obtain the set D of candidate target objects falling within the interval range through one-dimensional interval search. candidate All objects whose s2CellId is not within this range can be directly excluded, greatly improving the filtering speed.

[0058] Step 4: Traverse the candidate set D candidate For each element in the index, precisely determine whether its latitude and longitude coordinates fall entirely within the spatial range of region Z. If so, it is confirmed as a target object; otherwise, it is discarded. The final result is a precise set D of target objects located within the region. This step ensures the final accuracy of the spatial index's rapid filtering results.

[0059] Phase Two: Refined Screening of Effective Regional Base Stations Based on Base Station Antenna Parameters

[0060] This stage is crucial for improving the accuracy of regional population screening, with a focus on resolving boundary error issues caused by the directional coverage of base stations.

[0061] First, it is necessary to calculate the coverage area of ​​a single base station. For example... Figure 4 As shown, the coverage area of ​​a base station is determined by its engineering parameters. The parameters required for the calculation are defined in Table 1.

[0062] Table 1. Parameters for calculating the coverage area of ​​a base station cell.

[0063]

[0064] For a directional antenna, its coverage area can be approximated as a spherical sector. The steps to calculate the vertices of the coverage triangle are as follows:

[0065] Step 1: Establish a coordinate system with the base station's latitude and longitude as the vertices, with the X-axis pointing due east and the Y-axis pointing due north.

[0066] Step 2: Calculate the azimuth angles of the left and right boundaries of the sector based on the azimuth angle and the coverage angle degRange:

[0067] ;

[0068] ;

[0069] Step 3: Calculate the coordinates of the other two vertices of the triangle. Find the azimuth of the left boundary vertex. leftDegree Azimuth of the right boundary vertex rightDegree Substitute the latitude and longitude of the new coordinate point into the formula for calculating the new coordinates of the left and right boundary vertices respectively:

[0070] An approximate calculation formula (for a small range) can be used when the distance is short (e.g., within tens of kilometers) and high accuracy is not required. It is assumed that within a local area, the changes in longitude and latitude are linearly related to distance, and the influence of latitude on the length of longitude is considered. Here, cos(Lat) is used to correct for the effect of longitude lines shortening with increasing latitude.

[0071] Latitude of the new coordinate point:

[0072] Latitude = r cos( Degree ) 360 / (2 math.PI EARTH_RADIUS 1000)+ Lat ;

[0073] Longitude of the new coordinate point:

[0074] Longitude =r sin( Degree ) 360 / (2 math.PI EARTH_RADIUS 1000 cos( Lat ))+ Lng ;

[0075] Step 4: Calculate the base station coverage area (baseStationArea) based on the coordinates of the triangle vertices. Since the base station's operating parameters are stable, the results of this calculation can be preprocessed offline and cached.

[0076] Secondly, the effective base station selection algorithm for the region is executed, such as... Figure 5 As shown, a valid base station is defined as one whose coverage area overlaps with the target area, and the proportion of its own coverage area is greater than a preset threshold α (0 < α < 1). The selection process is as follows:

[0077] Steps 1 and 2: For the target region, calculate its center point (point) and the farthest distance (d) from the vertex to the center (if it is a circular region, use the center and radius instead).

[0078] Step 3: Using the spatial point filtering algorithm, with point as the center and d+R as the radius, find all base stations within the extended circular area to form the initial base station set stations.

[0079] Step 4: Traverse the stations and use the above method to calculate the coverage boundary (baseStationBoundary) and area (baseStationArea) of each base station.

[0080] Step 5: Traverse the stations and calculate the intersection area between the coverage area of ​​each base station and the target area.

[0081] Step 6: Calculate the ratio: ratio = intersectionArea / baseStationArea. If ratio >= α, retain the base station as a valid base station; otherwise, remove it. By controlling this threshold α, base stations with antennas facing away from the area within the region can be eliminated, while base stations with antennas facing the area outside the region can be included, thus accurately defining the set of base stations serving the target area.

[0082] Regional population determination and high concurrency realization

[0083] Ultimately, as Figure 1 and Figure 2 As shown, the results of the two stages are aggregated. The first stage obtains the set of candidate users within the region, and the second stage obtains the set of effective base stations serving the region. The final regional population consists of those users who are in the candidate user set and whose signaling records indicate they are connected to base stations in the effective base station set.

[0084] To achieve high concurrency and low latency, this solution heavily relies on big data parallel computing frameworks (such as Spark). The key to its implementation lies in data partitioning and task parallelism. For example... Figure 3 As shown, signaling data is stored in shards based on city and user IMSI hashes. When processing a query, the system determines the associated district / county based on the target area and loads the corresponding data shard. Simultaneously, the task parallelism is dynamically calculated based on the number of cells in the coverage area. Subsequently, the data shards and computational tasks are allocated to various computation threads. Multiple threads execute a large number of geometric calculations in spatial point filtering and base station filtering in parallel, and finally, the results from all threads are aggregated. This design enables the system to handle tens of thousands of population query requests from random areas simultaneously, with each request returning results within seconds.

[0085] Application Validation

[0086] This solution has been validated in practice on the provincial-level communications big data platform. See Tables 2 and 3 for details.

[0087] Table 2. Population Calculation Results by Administrative Region

[0088]

[0089] Table 3 Population Calculation Results for Custom Regions

[0090]

[0091] For different areas (from 0.57km) 2 to 111.63km 2 Population calculations are performed on both administrative and custom regions within a timeframe of less than one second, yielding reliable results. The effective base station screening algorithm accurately identifies truly relevant base stations around the target area (solid circle), demonstrating its effectiveness in improving the accuracy of boundary population screening. This core capability supports over one million concurrent calls per day on the platform, fully validating its practicality and robustness.

[0092] Example 2:

[0093] This invention also provides a system for determining permanent residents based on big data communication. This system includes corresponding modules for performing the steps of the above-described methods, such as a data acquisition module, a data preprocessing module, a spatial index calculation module, a candidate user screening module, an effective base station screening module, and a population determination module. The functional implementation of these modules is already covered in the foregoing method description and will not be repeated here.

[0094] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention, such as using other spatial indexes like GeoHash, or adjusting the determination strategy of the threshold α, should be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0095] It should be noted that the components mentioned in the above embodiments are all general standard parts or components known to those skilled in the art. Their structures and principles can be learned by those skilled in the art through technical manuals or conventional experimental methods.

[0096] This invention has illustrated its principles and implementation methods using specific examples. The descriptions of these embodiments are merely illustrative of the method and its core ideas; furthermore, those skilled in the art will recognize that modifications may be made to the specific implementation methods and application scope based on the principles of this invention. Therefore, the content of this specification should not be construed as limiting the invention.

Claims

1. A method for determining permanent residents based on big data communication, characterized in that, Includes the following steps: S1. Obtain the boundary information of the target area, the base station engineering parameters provided by the operator, and user signaling data; S2. Preprocess user signaling data based on a multi-dimensional spatial indexing algorithm to encode user location information into spatial grid identifiers; S3. Based on the boundary information of the target region and the multi-dimensional spatial indexing algorithm, calculate the minimum grid set covering the target region and its corresponding spatial filling curve range. S4. Based on the range of the space filling curve interval, select a set of candidate users from the preprocessed user signaling data; S5. Based on the antenna azimuth, coverage angle and location information in the base station engineering parameters, calculate the coverage space range of each base station, and based on whether the overlap area ratio between the coverage space range and the target area is greater than a preset threshold, filter out the effective base station set of the target area. The base station engineering parameters include at least: antenna azimuth angle, coverage angle, and base station latitude and longitude coordinates; the coverage space of the base station is approximated as a triangular or sector-shaped area with the base station location as the vertex, the coverage distance as the radius, the antenna azimuth angle as the center, and the coverage angle as the subtended angle for calculation; Specifically, it includes: S51. Establish a coordinate system with the latitude and longitude coordinates of the base station as the origin; S52. Calculate the azimuth angle range of the coverage space boundary based on the antenna azimuth angle and coverage angle; S53. Calculate the coordinates of multiple vertices of the coverage space boundary based on the azimuth angle range and the preset coverage distance; S54. Calculate the coverage area of ​​the base station and the intersection and overlap area between the coverage area and the target area based on the vertex coordinates. S55. Calculate the ratio of the intersection overlap area to the coverage area. If the ratio is greater than or equal to the preset threshold, the base station is determined to be a valid base station. S6. Based on the base station connection information in the user signaling data, select users who are connected to base stations in the effective base station set from the candidate user set to obtain the resident population data of the target area.

2. The method for determining permanent residents based on big data communication as described in claim 1, characterized in that, In step S2, the multidimensional spatial indexing algorithm is either the S2 algorithm or the GeoHash algorithm; step S2 includes: encoding the latitude and longitude coordinates in the user signaling data into the corresponding S2 Cell ID or GeoHash encoding.

3. The method for determining permanent residents based on big data communication according to claim 1, characterized in that, Steps S4 and S5 are implemented using a distributed parallel computing framework, specifically including: User signaling data is segmented according to administrative regions and user identifiers; Determine the relevant data fragments based on the target region; The computing task is dynamically divided into multiple sub-tasks, which are then distributed to multiple computing nodes to execute the spatial filtering and base station filtering steps in parallel. Aggregate the results from each computing node.

4. The method for determining permanent residents based on big data communication according to claim 3, characterized in that, The parallel computing framework is Spark or Flink.

5. The method for determining permanent residents based on big data communication according to claim 1, characterized in that, In step S5, the preset threshold value ranges from greater than 0 to less than 1, and is used to control the strictness of base station screening.

6. A system for determining permanent residents based on big data communication, characterized in that, The system employs the method for determining permanent residents based on big data communication as described in any one of claims 1-5, and includes: The data acquisition module is used to acquire boundary information of the target area, base station engineering parameters provided by the operator, and user signaling data; The data preprocessing module is used to preprocess user signaling data based on a multidimensional spatial indexing algorithm, and encode user location information into spatial grid identifiers; The spatial index calculation module is used to calculate the minimum grid set covering the target area and its corresponding spatial filling curve range based on the boundary information of the target area and the multi-dimensional spatial indexing algorithm. The candidate user filtering module is used to filter out a set of candidate users from the preprocessed user signaling data based on the range of the space filling curve interval. The effective base station filtering module is used to calculate the coverage area of ​​each base station according to the base station engineering parameters, and filter out the effective base station set of the target area based on whether the overlap area ratio between the coverage area and the target area is greater than a preset threshold. The base station engineering parameters include at least: antenna azimuth angle, coverage angle, and base station latitude and longitude coordinates; the coverage space of the base station is approximated as a triangular or sector-shaped area with the base station location as the vertex, the coverage distance as the radius, the antenna azimuth angle as the center, and the coverage angle as the subtended angle for calculation; Specifically, it includes: Establish a coordinate system with the latitude and longitude coordinates of the base station as the origin; Calculate the azimuth angle range of the coverage space boundary based on the antenna azimuth angle and coverage angle; Based on the azimuth angle range and the preset coverage distance, calculate the coordinates of multiple vertices of the coverage space boundary; The coverage area of ​​the base station and the overlapping area of ​​the coverage area with the target area are calculated based on the vertex coordinates. Calculate the ratio of the intersection overlap area to the coverage area. If the ratio is greater than or equal to the preset threshold, the base station is determined to be a valid base station. The population determination module is used to filter out users who are connected to base stations in the effective base station set from the candidate user set based on the base station connection information in the user signaling data, so as to obtain the resident population data of the target area.

7. An electronic device, characterized in that, The device includes at least one processor and a memory, the memory storing a computer program that, when executed by the at least one processor, causes the device to implement the method for determining permanent residents based on big data communication as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the method for determining permanent residents based on big data communication as described in any one of claims 1 to 5.

Images