Regional edge number identification method and system

Abstract

The invention relates to the technical field of mobile communication security, and discloses an area edge number identification method and system, and the method comprises the steps: obtaining signaling data of a mobile terminal, and carrying out the preprocessing of the signaling data, and generating signaling track data; obtaining all base stations and position distribution thereof in the key area according to the signaling trajectory data; calculating the dynamic weight of each base station relative to the central point of the region based on all base stations in the key region; constructing a daily frequency spatial-temporal characteristic matrix based on the signaling trajectory data and the dynamic weight of the base station; constructing a monthly frequency spatial-temporal characteristic matrix based on the signaling trajectory data; and calculating a number edge index based on the daily frequency spatial-temporal characteristic matrix and the monthly frequency spatial-temporal characteristic matrix, and accurately identifying the edge number based on the number edge index. According to the invention, based on various features of user mobile phone signaling data in communication data, accurate identification of edge numbers in key areas is realized by combining user multi-dimensional feature analysis, a dynamic base station weight model and four-dimensional feature collaborative decision.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mobile communication security, and more particularly to a method and system for identifying edge numbers in a region. BACKGROUND

[0002] Currently, in the scenarios of emergency management and important facility protection, the demand for accurate identification of abnormal behaviors around specific regions is increasingly prominent. Traditional monitoring methods mainly rely on fixed-position cameras, access control systems or sensor networks, which have obvious limitations: on the one hand, they cannot effectively cover open or semi-open areas without access control management, making it difficult to detect abnormal loitering or repeated approaching behaviors around the region; on the other hand, they still rely on manual post-mortem investigation of a large number of images or card swiping records, lacking real-time warning capability; in addition, in areas such as parks, squares and open areas that lack special monitoring equipment, it is difficult to effectively obtain continuous personnel movement trajectories.

[0003] Communication big data provides a new solution to the above problems - signaling data generated by the interaction between mobile terminals and base stations can reflect the location and movement characteristics of personnel in real time. However, existing signaling data analysis schemes still have significant shortcomings: for example, the region personnel identification method based on stay duration is almost ineffective at night and other low-activity periods; in addition, the traditional GPS electronic fence technology has a large positioning error (usually more than 200 meters) in the edge area of base station signal coverage, and when personnel move in the boundary of the region, the trajectory may be interrupted and misjudged due to signal fluctuations or drift, making it difficult to effectively identify suspicious behaviors such as loitering or frequent approaching. Overall, existing methods are difficult to distinguish between terminal numbers whose actual positions are at the physical edge (such as near the fence or boundary) and those whose behavior patterns exhibit edge characteristics (such as short-time multiple visits), and lack a fusion discrimination mechanism for signal strength attenuation characteristics and spatio-temporal behavior patterns.

[0004] Therefore, how to accurately identify edge numbers (i.e. non-authorized or potentially high-risk personnel frequently approaching important regions) from massive signaling data has become a technical problem that needs to be solved in the field of emergency monitoring and regional security protection. SUMMARY

[0005] Therefore, the present application provides a method and system for identifying edge numbers in a region, which analyzes user mobile signaling trajectory data, analyzes the scope of key regions and the distribution of internal base stations, constructs spatio-temporal trajectory features, explores according to the features, calculates edge indicators, and effectively identifies suspicious numbers at the edge of the region.

[0006] To achieve the above purpose, the present application adopts the following technical solutions:

[0007] A method for identifying edge numbers in a region, comprising:

[0008] S1, acquiring signaling data of a mobile terminal, and generating signaling trajectory data after preprocessing;

[0009] S2, acquiring all base stations and their position distribution in a key area according to the signaling trajectory data;

[0010] S3, calculating a dynamic weight of each base station relative to the center point of the area based on all base stations in the key area;

[0011] S4, constructing a daily spatiotemporal feature matrix based on the signaling trajectory data and the dynamic weight of the base station;

[0012] S5, constructing a monthly spatiotemporal feature matrix based on the signaling trajectory data;

[0013] S6, calculating a number edge index based on the daily spatiotemporal feature matrix and the monthly spatiotemporal feature matrix, and accurately identifying an edge number based on the number edge index.

[0014] Preferably, S1 comprises:

[0015] Acquiring signaling data of a mobile terminal, and performing data cleaning on the signaling data to filter out data with abnormal trajectory state;

[0016] Sorting the terminal signaling trajectory data after data cleaning according to the time sequence of the trajectory of each number to obtain initial trajectory data;

[0017] Removing abnormal points and noise, aggregating data, and completing trajectories from the initial trajectory data to obtain the signaling trajectory data.

[0018] Preferably, S2 comprises:

[0019] According to the map dotting, acquiring the coverage range of the key area, selecting the center point of the area according to the coverage range, and extracting the latitude and longitude of the center point of the area;

[0020] Based on the signaling trajectory data, extracting signaling trajectory data in the past month, calculating the distance between the latitude and longitude of each trajectory and the latitude and longitude of the center point of the area, screening out trajectory points corresponding to the distance satisfying the preset condition, and counting the number and position distribution of base stations in the key area according to the screened trajectory points.

[0021] Preferably, the dynamic weight w i The calculation formula is:

[0022] w i = exp(k*(d max -d i ))

[0023] Wherein, d i is the distance from the base station i to the center point of the area, and dmax is the maximum value of all base stations in the area to the area center point, k is the attenuation coefficient.

[0024] Preferably, S4 comprises:

[0025] Based on the signaling trajectory data and the dynamic weight of the base station in the area cycle, the number of times each base station in the key area is connected by each number in a single day and the total number of times all base stations in the key area are connected in a single day are counted;

[0026] The base station connection density index CDI is constructed, and the calculation formula is:

[0027] CDI =∑ (con i *w i ) / con k

[0028] Wherein, con i is the number of times each number connects base station i in a day, w i is the dynamic weight parameter of base station i, and con k is the total number of times all base stations in the key area are connected by the number in a day.

[0029] The base station switching interval standard deviation SDS is calculated:

[0030]

[0031] Wherein, T j is the time interval of the jth base station switching of each number in the key area, and N is the total number of base station switching in the cycle; T avg is the average value of base station switching.

[0032] Preferably, S5 comprises:

[0033] Based on the signaling trajectory data in the area cycle, the number of days each number connects all base stations in the key area in a single month and the maximum value of the number of days each number continuously connects all base stations in the key area in a single month are counted.

[0034] The low-frequency visit duration LFD is calculated:

[0035] LFD = day totle / max (1, day con )

[0036] Wherein, day totle is the number of days the number appears in the key area in a month; day con is the maximum number of days the number continuously appears in the key area in a month.

[0037] The space-time density index SDI is calculated:

[0038] SDI = -∑(p t *lnp t )

[0039] wherein, p t is the proportion of the number of occurrences of the number in different hours t in a month to the total number of occurrences, t = 1, 2, 3, …, 24.

[0040] Preferably, the number edge index EI is calculated according to the following formula:

[0041] EI = a * CDI + β * SDS + γ * LFD - δ * SDI

[0042] wherein, a, β, γ and δ are adjustable weight coefficients obtained by data statistical analysis.

[0043] Preferably, the edge number is accurately identified based on the number edge index, including:

[0044] If EI > K, the corresponding number is identified as an edge number or a passing number;

[0045] If EI ≤ K, the corresponding number is identified as a non-edge number or a resident number, wherein K is a preset threshold.

[0046] A regional edge number identification system, comprising:

[0047] a signaling trajectory data acquisition module: configured to acquire signaling data of a mobile terminal, and generate signaling trajectory data after preprocessing;

[0048] a base station position analysis module: configured to acquire all base stations and their position distribution in a key area according to the signaling trajectory data;

[0049] a base station weight dynamic allocation module: configured to calculate a dynamic weight of each base station relative to a regional center point based on all base stations in the key area;

[0050] a daily frequency space-time feature construction module: configured to construct a daily frequency space-time feature matrix based on the signaling trajectory data and the base station dynamic weight;

[0051] a monthly frequency space-time feature construction module: configured to construct a monthly frequency space-time feature matrix based on the signaling trajectory data;

[0052] an edge system calculation and identification module: configured to calculate a number edge index based on the daily frequency space-time feature matrix and the monthly frequency space-time feature matrix, and accurately identify an edge number based on the number edge index.

[0053] Via the technical solutions, compared with the prior art, the application provides a regional edge number recognition method and system, which has the following effects:

[0054] 1. Based on the characteristics of user mobile signaling data in communication data, the application realizes accurate identification of edge numbers in key areas by combining user multi-dimensional feature analysis, dynamic base station weight model and four-dimensional feature collaborative decision-making. It solves the problem of sensing edge signals in secret key areas, and reduces the false alarm rate of high-frequency visitors (deliverymen or express deliverymen).

[0055] 2. The application is based on communication data, feature engineering and expert system rules, does not require expensive hardware materials, does not need to deploy camera, sensor network and other hardware facilities, directly uses operator signaling data to reduce implementation cost; edge computing supports dynamic parameter optimization (such as automatically increasing beta coefficient at night), adapts to different scenarios such as office area, nuclear power station and border inspection station, and can be widely applied to intelligent city management, technical reconnaissance and security and control business.

[0056] 3. The application has the advantages of high accuracy, real-time and wide applicability, can effectively improve the efficiency and precision of edge number recognition, and is helpful to the development and progress of intelligent city management, technical reconnaissance and security and control.

[0057] 4. The application combines communication big data with multi-dimensional feature strategy, uses advanced data analysis technology and algorithm to realize identification and tracking of edge numbers in key areas. BRIEF DESCRIPTION OF DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only embodiments of the application, and those skilled in the art can obtain other drawings according to the provided drawings without creative labor.

[0059] Figure 1 A flow chart of a regional edge number recognition method provided by the application.

[0060] Figure 2 A schematic diagram of base station weight distribution in a key area provided by the application.

[0061] Figure 3 An architecture diagram of multi-dimensional feature fusion calculation provided by the application.

[0062] Figure 4 A schematic diagram of a regional edge number recognition system provided by the application. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work are within the protection scope of the present application.

[0064] The embodiments of the present application disclose a regional edge number recognition method, as shown in the formula (1), comprising: Figure 1

[0065] S1, acquiring signaling data of a mobile terminal, and generating signaling trajectory data after preprocessing;

[0066] S2, acquiring all base stations in a key area and their position distribution according to the signaling trajectory data;

[0067] S3, calculating a dynamic weight of each base station relative to a center point of the area based on all base stations in the key area, so that the base station weight is dynamically allocated according to the base station position;

[0068] S4, constructing a daily frequency space-time feature matrix based on the signaling trajectory data and the dynamic weight of the base station;

[0069] S5, constructing a monthly frequency space-time feature matrix based on the signaling trajectory data;

[0070] S6, calculating a number edge index based on the daily frequency space-time feature matrix and the monthly frequency space-time feature matrix, and accurately recognizing an edge number based on the number edge index.

[0071] The specific implementation process of each step of the present application will be described in detail below.

[0072] In the present embodiment, S1 comprises:

[0073] The signaling data of the mobile terminal is acquired, and data cleaning is performed, and data with empty or zero key fields or abnormal trajectory state caused by base station data parsing errors or terminal device signal abnormalities is deleted to remove data noise;

[0074] The terminal signaling trajectory data after data cleaning is sorted in chronological order to obtain initial trajectory data;

[0075] The initial trajectory data is subjected to abnormal point noise removal, trajectory point aggregation of ping-pong switching data, and trajectory completion of data with few trajectory points or missing data fields in the initial trajectory data.

[0076] ​Preferably, the signaling trajectory data mainly includes trajectory location data, which contains different trajectory points. Each trajectory point is a sample data, containing information such as mobile phone number, time, latitude and longitude.

[0077] In this embodiment, based on signaling trajectory data, all base stations and their geographical distribution within a key area are identified. Specifically:

[0078] Use a map marker tool to plot the designated key area, and select a center point based on the coverage area. The center point can be defined according to the population density within the area, such as administrative buildings, important office areas, etc. Extract the latitude and longitude of the center point, and measure the distance d from the center point to the farthest boundary point. max .

[0079] Based on signaling trajectory data, the distance of each trajectory point from the latitude and longitude of the center point of the area is calculated, and points with a distance less than or equal to d are filtered out. max All signaling trajectories within the region are used for subsequent analysis.

[0080] Based on the selected signaling data, the number of base station IDs, the latitude and longitude location of each base station, and the distance from the center point of the area are counted.

[0081] In this embodiment, based on the base stations in the key area, the dynamic weight of each base station relative to the center point of the area is calculated, so that the base station weight is dynamically allocated according to the location of the base station.

[0082] like Figure 2 As shown, the specific rules for the dynamic allocation of base station weights are as follows:

[0083] Based on the principle that "the farther a base station is from the center point of the area, the lower its weight," a base station weight calculation rule is set. A dynamic attenuation coefficient k is introduced, with a value range of [0.05, 0.1]. In this embodiment, the default value of k is 0.08.

[0084] The specific calculation formula is as follows:

[0085] w i =exp(k*(d max -d i ))

[0086] Where, d i Let d be the distance from base station i to the center point of the region. max This represents the maximum distance from all base stations within the region to the region's center point, where k is the attenuation coefficient, and the value of k varies for different regions.

[0087] If the farthest boundary distance in the region from the region center point is 500m, the base station A position distance from the center point is 500m, and the base station B distance from the region center point is about 0m, according to the base station weight calculation formula, the base station A weight is obtained: w A = exp(0.08*(500-500)) = e 0 = 1, and the base station B weight is: w B = exp(0.08*(500-0)) = e -40 ≈ 0.

[0088] In this embodiment, a daily frequency space-time feature matrix is constructed, and the specific process is as follows:

[0089] Based on the signaling trajectory and the dynamic weight of the base station in the region cycle, the number of times that each number connects each base station in the region in a single day and the total number of times that all base stations in the region are connected in a single day are counted;

[0090] For the number of times that the user connects different base stations and the base station weight, a "base station connection density index CDI" is constructed to obtain the CDI score ratio of the base station in the connection region in a single day.

[0091] CDI = Σ(con i *w i ) / con k

[0092] Wherein, con i is the number of times that each number connects the base station i in a day, w i is the dynamic weight parameter of the base station i, and con k is the total number of times that all base stations in the key region are connected in a day.

[0093] The higher the base station connection density index CDI, the more the user tends to the edge of the region in the active position in the region; the lower the base station connection density index CDI, the more the user tends to the center point of the region in the active position in the region.

[0094] For example, a person connects A base station 0 times, connects B base station 2 times, and connects C base station 8 times in a day, then CDI = (0*1+2*0+8*0.8) / 10 = 0.64, wherein the base station weights of A, B and C are 1, 0 and 0.8 respectively, so from the feature, the user has a 64% probability of being active in the region edge.

[0095] Based on the signaling trajectory data in the region cycle, the time difference between adjacent trajectory points is calculated as the stay time; the average stay time of all trajectory points of each user appearing in the region in a single day is calculated; and the stay time standard deviation of each user in a single day in the region is calculated as a "base station switching interval standard deviation SDS" feature.

[0096]

[0097] wherein, T j is the time interval of the jth base station switching of each number in the focus area, N is the total number of base station switching in the period; T avg is the average value of base station switching.

[0098] The higher the base station switching interval standard deviation SDS, the greater the fluctuation of the user in the area, which is consistent with the behavior characteristics of the edge personnel lingering and short stay; the lower the base station switching interval standard deviation SDI, the smaller the fluctuation of the user in the area, which is more regular movement of the internal personnel of the area.

[0099] For example, the connection of the base station in the area and the stay time of a person in a day can be represented as: [A->B:120s, B->C:90s, C->B:110s], the average stay time is (120+90+110) / 3=106.67s, the variance is (120-106.67)^2+(90-106.67)^2+(110-106.67)^2=466.67, and the SDI standard deviation value is 15.28s, which indicates that the user switching interval fluctuation is moderate, and there is short stay in the area.

[0100] In this embodiment, a monthly frequency space-time feature matrix is constructed, and the specific process is as follows:

[0101] Based on the signaling trajectory in the period of the area, the number of days of connecting all base stations in the focus area in a month and the maximum number of days of continuously connecting all base stations in the focus area in a month are counted for each user, a "low-frequency continuous day number LFD" feature is constructed, and the ratio of the number of days of continuously connecting base stations in the area in a month is obtained.

[0102] LFD=day totle / max(1,day con )

[0103] wherein, day totle is the number of days that the number appears in the focus area in a month; day con is the maximum number of days that the number continuously appears in the focus area in a month;

[0104] The higher the low-frequency continuous day number LFD value, the more dispersed the access days of the user to the focus area, and the greater the probability of being an edge or passing personnel; the lower the low-frequency continuous day number LFD value, the smaller the probability of being an edge or passing personnel.

[0105] Low-frequency continuous days (LFD) can capture scattered visit patterns and identify individuals with high suspicion on the margins, but it may lead to misjudgments. For example, delivery drivers who briefly visit key areas every day have low LFD values ​​and are more likely to be local residents.

[0106] Therefore, in addition to this, a suppression feature related to the distribution of visit time, the "spatial-temporal density index (SDI)," is introduced to suppress LFD misjudgments caused by high-frequency regular visits.

[0107] SDI=-∑(p t *lnp t )

[0108] Where, p t Let SDI be the percentage of the number's occurrences in different hourly segments t within a month, relative to the total number of occurrences, where t = 1, 2, 3, ..., 24. SDI can also be expressed as:

[0109] SDI = -[p1*lnp1 + p2*lnp2 + ... + p 24 *lnp 24 ]

[0110] The Spatiotemporal Density Index (SDI) reflects the distribution of users' visits to key areas across different time periods. A higher SDI value indicates a more even distribution of visits, with a greater tendency towards people within the area; a lower SDI value indicates a more dispersed distribution of visits, with a greater tendency towards people on the periphery of the area.

[0111] For example, if a delivery driver delivers to a key area for 22 days in a month, with a maximum consecutive delivery period of 22 days, then according to the LFD calculation formula, LFD = 22 / max(1,22) = 1.0. This indicates that although the driver has frequent and continuous visits, they do not meet the marginal dispersion characteristic. If a worker within a certain area works 22 consecutive days, the LFD value is also 1.0. Therefore, they cannot be effectively separated, and the SDI feature is introduced.

[0112] If the delivery driver's delivery time in the past month is concentrated between 11:00-12:00 with a probability P1 of 0.45 and between 12:00-13:00 with a probability of 0.55, then according to the SI calculation formula, the SDI value is 0.69, indicating that his behavior pattern is highly concentrated (delivering food during lunchtime).

[0113] Therefore, by using LFD+SDI to make joint decisions, we can characterize users' marginal behaviors and improve the accuracy of edge recognition.

[0114] In this embodiment, as Figure 3 As shown, based on the daily and monthly frequency spatiotemporal feature matrices, the number edge index is calculated as follows:

[0115] By fusing the four-dimensional features of CDI, SDS, LFD and SDI, using the data with the label of the resident personnel in the region to debug the weight of feature fusion, and finally debugging the threshold value of EI, when the EI value is less than the specified threshold value, the resident personnel mobile phone number is screened out. Among them, the dynamic threshold value K is generally set as the mean value of the top 15% samples of the EI value in the historical data plus 2 times the standard deviation.

[0116] The number edge index EI calculation formula is:

[0117] EI = a * CDI + β * SDS + γ * LFD - δ * SDI

[0118] Among them, a, β, γ and δ are adjustable weight coefficients, which are obtained by data statistical analysis.

[0119] If EI > K, the corresponding number is judged as an edge number or a passing number;

[0120] If EI≤K, the corresponding number is judged as a non-edge number or a resident number, and its information is stored in the internal personnel database.

[0121] Using the resident personnel in a certain month to optimize the weight coefficients (such as a, β, γ and δ) of the edge number identification system, the specific process of setting the coefficients of the system is:

[0122] Obtain the list of resident personnel in the key area of a certain month and the mobile phone number, and extract the terminal signaling data of the month as fitting (or training) data;

[0123] Based on S2-S5, process the data of the month, and extract the daily and monthly space-time feature matrix of each number.

[0124] Based on S6, fit the number edge index from the space-time trajectory feature, and statistically analyze and adjust the weight coefficients a, β, γ and δ in the edge calculation system and the threshold value K of the final edge index EI, so that when the edge index EI≤K, the resident personnel mobile phone number in the month can be covered to the greatest extent, and then the weight value in the edge number calculation system for the region is fixed. Specifically, according to the above historical resident personnel in a certain month as a label, and calculating the CDI, SDS, LFD and SDI values of the month, by setting the grid parameters, enumerating the parameter values of a, β, γ, δ and K, the value range of each parameter is 0 to 1, comparing the mobile phone number that satisfies EI≤K with the resident personnel label, so that the a, β, γ, δ and K values with the highest coincidence degree are the final fixed parameter values.

[0125] In this embodiment, a regional edge number identification system is disclosed, as shown in Figure 4 , comprising:

[0126] Signaling trajectory data acquisition module: for acquiring signaling data of the mobile terminal, and generating signaling trajectory data after preprocessing;

[0127] Base station position analysis module: for acquiring all base stations and their position distribution in the key area according to the signaling trajectory data;

[0128] Base station weight dynamic allocation module: for calculating the dynamic weight of each base station relative to the center point of the area based on all base stations in the key area;

[0129] Daily frequency spatiotemporal feature construction module: for constructing a daily frequency spatiotemporal feature matrix based on the signaling trajectory data and the dynamic weight of the base station;

[0130] Monthly frequency spatiotemporal feature construction module: for constructing a monthly frequency spatiotemporal feature matrix based on the signaling trajectory data;

[0131] Edge system calculation and identification module: for calculating the number edge index based on the daily frequency spatiotemporal feature matrix and the monthly frequency spatiotemporal feature matrix, and accurately identifying the edge number based on the number edge index.

[0132] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can be referred to the method part.

[0133] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of regional number identification, characterized in that, The method comprises the following steps: S1, acquiring signaling data of a mobile terminal, and generating signaling trajectory data after preprocessing; S2, acquiring all base stations and their position distribution in a key area according to the signaling trajectory data; S3, calculating the dynamic weight of each base station relative to the center point of the area based on all base stations in the key area; S4, constructing a daily frequency space-time feature matrix based on the signaling trajectory data and the dynamic weight of the base station; S5, constructing a monthly frequency space-time feature matrix based on the signaling trajectory data; S6, calculating a number edge index based on the daily frequency space-time feature matrix and the monthly frequency space-time feature matrix, and accurately identifying edge numbers based on the number edge index.

2. The regional reach number identification method of claim 1, wherein, S1 comprises: Acquiring signaling data of a mobile terminal, and performing data cleaning on the signaling data to filter out data with abnormal trajectory state; Sorting the terminal signaling trajectory data after data cleaning in time sequence according to the trajectory of each number, to obtain initial trajectory data; Removing abnormal points and noise from the initial trajectory data, aggregating data, and completing the trajectory, to obtain the signaling trajectory data.

3. The regional number identification method according to claim 1, wherein S2 The method comprises the following steps: According to the map dotting, the coverage range of the key area is acquired, and the center point of the area is selected according to the coverage range, and the latitude and longitude of the center point of the area are extracted; Based on the signaling trajectory data, the signaling trajectory data of the past month is extracted, and the distance between the latitude and longitude of each trajectory and the latitude and longitude of the center point of the area is calculated, the trajectory points corresponding to the distance satisfying the preset condition are screened out, and the number and position distribution of the base stations in the key area are counted according to the screened trajectory points.

4. The regional reach number identification method of claim 1, wherein, Dynamic weights w i The calculation formula is: w i = exp(k*(d max -a i )) where d i is the distance from base station i to the center point of the region, d max is the maximum value of the distances from all base stations in the region to the center point of the region, and k is a decay coefficient.

5. The regional reach number identification method of claim 3, wherein, S4 comprises: Based on the signaling trajectory data and the dynamic weight of the base station in the area cycle, the number of times of connecting each base station in the key area and the total number of times of connecting all base stations in the key area in a single day are counted for each number. The base station connection density index CDI is constructed, and the calculation formula is: CDI = ∑(con i ) / con i ) / con k con i is the number of times the number connects the base station i in a day, w i is the dynamic weight parameter of the base station i, con k is the total number of times the number connects all the base stations in the key area in a day; The base station switching interval standard deviation SDS is calculated: wherein T j is the time interval of the jth base station handover for each number in the focus area, N is the total number of base station handovers in the period; T avg is the average value of base station handovers.

6. A regional number identification method according to claim 5, characterized in that S5 The method comprises the following steps: Based on the signaling trajectory data in the area cycle, the number of days of connecting all base stations in the key area in a single month and the maximum value of the number of days of continuously connecting all base stations in the key area in a single month are counted for each number. The low-frequency visit duration LFD is calculated: LFD = day totle / max(1, day con ) day totle is the number of days in which the number appears in the focus area in the past month; day con is the maximum number of consecutive days in which the number appears in the focus area in the past month; The space-time density index SDI is calculated: SDI = -∑(p t * lnp t ) where p t is the proportion of the total number of occurrences of the number in different hours t in a month, t = 1, 2, 3, …, 24.

7. A regional reach number identification method according to claim 6, characterized in that, The number edge index EI calculation formula is: EI = α * CDI + β * SDS + γ * LFD - δ * SDI Wherein, α, β, γ and δ are adjustable weight coefficients, which are obtained by data statistical analysis.

8. A regional reach number identification method according to claim 7, characterized in that, Based on the number edge index, the edge number is accurately identified, comprising: If EI > K, the corresponding number is judged as an edge number or a passing number; If EI ≤ K, the corresponding number is judged as a non-edge number or a resident number, wherein K is a preset threshold.

9. A regional reach number identification system, characterized by, The method comprises the following steps: A signaling trajectory data acquisition module is used to acquire signaling data of a mobile terminal, and generate signaling trajectory data after preprocessing; A base station position analysis module is used to acquire all base stations and their position distribution in a key area according to the signaling trajectory data; A base station weight dynamic distribution module is used to calculate the dynamic weight of each base station relative to the center point of the area based on all base stations in the key area; A daily frequency space-time feature construction module is configured to construct a daily frequency space-time feature matrix based on the signaling trajectory data and the base station dynamic weight; A monthly frequency space-time feature construction module is configured to construct a monthly frequency space-time feature matrix based on the signaling trajectory data; An edge system calculation and identification module is configured to calculate a number edge index based on the daily frequency space-time feature matrix and the monthly frequency space-time feature matrix, and accurately identify an edge number based on the number edge index.

Images