Permanent resident population identification method and device, equipment, storage medium and product

Abstract

The invention discloses a permanent resident population identification method and device, equipment, a storage medium and a product. The method comprises the following steps: on the basis of position signaling data of user terminals in a set observation time period in a set area in a statistical period and a predetermined night residence of a user to which each user terminal belongs, determining a single-day staying accumulated duration of each user in a corresponding night residence every day in the statistical period; generating the number of permanent residents under an operator in a set area based on the accumulated duration of the single-day stay of each user and a set permanent resident population identification rule; wherein the night residence place of the user to which each user terminal belongs is generated based on a network topological graph formed by resident base station points of each user terminal in a set area in a set observation time period, and the set permanent resident population identification rule is generated based on inflection point detection of permanent resident population scale change trends under different rules. The method has the advantages of high speed processing, low identification cost, high result precision and the like.

Description

Technical Field

[0001] This application relates to the field of big data, and in particular to a method, device, equipment, storage medium, and product for identifying permanent residents. Background Technology

[0002] The resident population is a universally accepted population indicator for international population statistics and data publication, and it is also an important monitoring indicator for territorial spatial planning. Given the current large scale of the floating population and the prevalence of separation between residence and registered address, the resident population more accurately reflects the population size and current situation of a region, providing more effective information for the government to formulate relevant policies and services.

[0003] Traditional methods of identifying permanent residents rely on census data, which suffer from drawbacks such as low statistical efficiency, time-consuming and labor-intensive processes, long intervals, and high costs. With the development of mobile internet and information and communication technologies, and the widespread adoption of mobile devices, combining big data and artificial intelligence can effectively estimate population size, unaffected by the monitoring targets or timeframes, and effectively avoiding sampling survey errors.

[0004] In related technologies, the identification of permanent residents involves obtaining user location trajectory data through methods such as mobile positioning and internet access, and then identifying permanent residents based on this user location trajectory data. Specific methods for identifying permanent residents include the following:

[0005] Method 1: Based on experience and common sense, manually set a threshold for stay time and judgment conditions. When a user stays in the area for a longer time than the threshold, the user is judged to be a permanent resident.

[0006] Method 2: Construct feature variables and perform spectral clustering and k-means clustering analysis to distinguish population types by using residency features.

[0007] However, the artificially set residence time threshold and discrimination conditions in Method 1 are easily affected by external factors such as population mobility and changes in living habits, resulting in insufficient accuracy and stability of the resident population estimation results; the sample size in Method 2 is limited by the performance of traditional clustering algorithms, making it difficult to complete the discrimination of large sample resident populations, and the data calculation cost and model complexity are high. Summary of the Invention

[0008] In view of this, embodiments of this application provide a method, apparatus, device, storage medium, and product for identifying permanent residents, aiming to improve identification accuracy while saving on the cost of identifying permanent residents.

[0009] The technical solution of this application embodiment is implemented as follows:

[0010] In a first aspect, embodiments of this application provide a method for identifying permanent residents, including:

[0011] Based on the location signaling data of user terminals in a set area within a set observation period and the pre-determined nighttime residence of each user terminal, the cumulative daily stay of each user in the corresponding nighttime residence within the statistical period is determined.

[0012] Based on the cumulative daily stay duration of each user and the set resident population identification rules, the number of resident populations under the operator in the set area is generated;

[0013] The nighttime residence of each user terminal is generated based on the network topology map of the base stations where each user terminal resides within the set area during the set observation period. The set resident population identification rules are generated based on the inflection point detection of the resident population size change trend under different rules.

[0014] The method in the above scheme further includes:

[0015] Based on the location signaling data of each user terminal in the defined area during the defined observation period, the network topology map is constructed; wherein, the location signaling data includes: location information identifying the base station and time information identifying the entry and / or departure from the base station, and the network topology map includes: nodes representing each base station and edges representing the movement trajectories between base stations;

[0016] Based on the nodes and edges of the network topology graph, the iterative processing of the network topology graph yields the set of nighttime permanent locations of each user terminal.

[0017] Based on the set of nighttime locations for each user, the nighttime location with the longest cumulative stay is selected as the corresponding user's nighttime residence.

[0018] In the above scheme, the iterative processing of the network topology graph based on the nodes and edges of the network topology graph to obtain the set of nighttime persistent locations of each user terminal includes:

[0019] Based on nodes and edges, a module gain degree is constructed for the network topology graph, and the network topology graph is iterated based on the module gain degree until the module gain degree of the network topology graph is stable, thereby obtaining the set of nighttime permanent residence points of each user terminal; wherein, the module gain degree represents the gain after adjacent nodes are merged into the community, and the community represents the user's nighttime permanent residence point.

[0020] The method in the above scheme further includes:

[0021] The inflection point of the trend of permanent resident population size change in the defined area under different rules was detected based on the Kneedle algorithm.

[0022] The set resident population identification rules are generated based on the detected inflection point; wherein, the set resident population identification rules include: a daily stay duration threshold and a monthly residence days threshold.

[0023] In the above scheme, the detection of inflection points in the trend of resident population size change in the designated area under different rules based on the Kneedle algorithm includes:

[0024] An initial dataset is constructed based on the number of permanent residents in the designated areas under different rules.

[0025] The initial dataset is subjected to curve fitting and normalization to obtain a first smooth curve;

[0026] A line is constructed based on the start and end points of the first smooth curve, and a difference curve is constructed to represent the difference between the line and the points on the first smooth curve.

[0027] Based on the local maximum value of the difference curve, the inflection point is determined;

[0028] The generation of the set resident population identification rule based on the detection inflection point includes:

[0029] The daily stay duration threshold is determined based on the daily stay duration corresponding to the inflection point, and the monthly residence days threshold is determined based on the monthly residence days corresponding to the inflection point.

[0030] In the above scheme, determining the inflection point based on the local maximum value of the difference curve includes:

[0031] Based on the local maximum values ​​of the difference curve, a set of candidate inflection points is determined;

[0032] For the candidate inflection point set, the inflection point threshold corresponding to each local maximum value is determined based on the sensitivity parameter;

[0033] Based on the difference curve and the inflection point threshold, the detected inflection point is generated.

[0034] In the above scheme, generating the number of permanent residents under the operator in the set area based on the cumulative daily stay of each user and the set resident population identification rules includes:

[0035] Based on the user's cumulative daily stay duration and the daily stay duration threshold, the number of days the user resides in each month within the statistical period is determined;

[0036] Based on the number of days a user stays in each month within the statistical period and the threshold for the number of days a user stays in each month, the number of months a user stays in the statistical period is determined.

[0037] The number of users whose monthly stay reaches a set monthly threshold within a statistical period is used to generate the number of permanent residents under the operator in the set area.

[0038] The method in the above scheme further includes:

[0039] Obtain the user terminal penetration rate, operator user ratio, and dependency ratio of the population at a set age within the specified area;

[0040] Based on the user terminal penetration rate, the operator user ratio, and the dependency ratio of the set age population, the population sample of the permanent residents under the operators in the set area is expanded to obtain the total permanent resident population of the set area.

[0041] The method in the above scheme further includes:

[0042] The total number of permanent residents in the designated area is verified based on the census results.

[0043] If the difference between the total number of permanent residents in the designated area and the census result is less than a set difference threshold, then the total number of permanent residents in the designated area is output.

[0044] Secondly, embodiments of this application provide a resident identification device, including:

[0045] The first determining module is used to determine the cumulative daily stay of each user at the corresponding nighttime residence within the statistical period based on the location signaling data of user terminals in a set area within a set observation time period and the pre-determined nighttime residence of each user terminal.

[0046] The second determining module is used to generate the number of permanent residents under the operator in the set area based on the cumulative daily stay duration of each user and the set permanent resident identification rules.

[0047] The nighttime residence of each user terminal is generated based on the network topology map of the base stations where each user terminal resides within the set area during the set observation period. The set resident population identification rules are generated based on the inflection point detection of the resident population size change trend under different rules.

[0048] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor, wherein, when the processor is used to run the computer program, it executes the steps of the method described in the first aspect of embodiments of this application.

[0049] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect of embodiments of this application.

[0050] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in the first aspect of embodiments of this application.

[0051] The technical solution provided in this application, based on the location signaling data of user terminals in a set area within a statistical period and the pre-determined nighttime residences of the users to which each user terminal belongs, determines the cumulative daily stay of each user in the corresponding nighttime residence within the statistical period; based on the cumulative daily stay of each user and the set resident population identification rules, it generates the number of resident populations under the operator in the set area; wherein, the nighttime residences of the users to which each user terminal belongs are generated based on the network topology map composed of the base stations where each user terminal is stationed in the set area within the set observation period, and the set resident population identification rules are generated based on the inflection point detection of the trend of resident population size change under different rules. Since the user's nighttime residence location in this embodiment is generated based on the network topology map of the base stations where each user terminal stays within a set area during a set observation period, it can be combined with the location signaling data of the user terminal to achieve accurate monitoring of the user's daily stay duration at the nighttime residence location. Furthermore, the set resident population identification rules are generated based on the inflection point detection of the resident population size change trend under different rules, resulting in high stability and reliability of resident population identification. Thus, based on the cumulative daily stay duration of each user and the set resident population identification rules, the number of resident populations under the operator within the set area can be obtained, resulting in high identification accuracy. Moreover, the basic data comes from the wireless communication network, which has advantages such as fast processing speed, low identification cost, and high result accuracy compared to sampling statistics and other methods. Attached Figure Description

[0052] Figure 1 This is a flowchart illustrating the permanent resident identification method according to an embodiment of this application;

[0053] Figure 2 This is a flowchart illustrating the method for identifying permanent residents in an application embodiment of this application;

[0054] Figure 3 This is a schematic diagram of the network topology of user nighttime stay points in an application embodiment of this application;

[0055] Figure 4 This is a schematic diagram of the structure of the permanent resident identification device according to an embodiment of this application;

[0056] Figure 5This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0057] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0059] This application provides a method for identifying permanent residents, which can be applied independently to electronic devices with data processing capabilities, such as terminal devices and servers, or can be implemented by the cooperation of terminal devices and servers. Specifically, the terminal device can be a computer, smartphone, personal digital assistant (PDA), etc.; the server can be an application server or a web server. In actual deployment, the server can be a standalone server or a cluster server. Figure 1 As shown, the method includes:

[0060] Step 101: Based on the location signaling data of user terminals in a set area within a statistical period and the pre-determined nighttime residences of the users to which each user terminal belongs, determine the cumulative daily stay duration of each user in the corresponding nighttime residence within the statistical period; the nighttime residences of the users to which each user terminal belongs are generated based on the network topology map formed by the base stations where each user terminal resides in the set area within the set observation period.

[0061] Here, the defined area can be based on administrative divisions, such as counties, districts, and cities, which helps meet the needs of government departments for population management, urban planning, and public resource allocation. The statistical period is generally annual; however, those skilled in the art can adjust it according to requirements, and this application does not limit this. The user terminal is generally a mobile phone or other widely used electronic device with mobile communication capabilities. The observation period can be set reasonably according to requirements; for example, in one application example, the observation period is set to the time between 7 PM and 7 AM the following day.

[0062] For example, location signaling data includes: location information identifying the base station and time information identifying entry into and / or departure from the base station. It is understood that the location signaling data may also include a user identifier. In one application example, the location signaling data can be encrypted to improve information security. This location signaling data includes: a UID (User Unique Identifier), base station information, and the time of entry into and departure from the base station.

[0063] Step 102: Based on the cumulative daily stay duration of each user and the set resident population identification rules, generate the number of resident populations under the operator in the set area; the set resident population identification rules are generated based on the inflection point detection of the resident population size change trend under different rules.

[0064] It is understood that, since the user's nighttime residence location in this application embodiment is generated based on the network topology map of the base stations where each user terminal stays within a set area during a set observation period, the user's nighttime residence location can be accurately monitored by combining the location signaling data of the user terminal. Furthermore, the established resident population identification rules are generated based on the inflection point detection of the resident population size change trend under different rules, resulting in high stability and reliability of resident population identification. Thus, based on the cumulative daily residence time of each user and the established resident population identification rules, the number of resident populations under the operator within the set area can be obtained, resulting in high identification accuracy. Moreover, the basic data comes from the wireless communication network, which has advantages such as fast processing speed, low identification cost, and high result accuracy compared to methods such as sampling statistics.

[0065] Here, the aforementioned different rules can be understood as: thresholds for the duration of stay per day and / or the number of days of residence per month for identifying permanent residents, that is, different rules correspond to different thresholds for the duration of stay per day and / or the number of days of residence per month.

[0066] Exemplarily, the method further includes:

[0067] Based on the location signaling data of each user terminal in the defined area during the defined observation period, the network topology map is constructed; wherein, the location signaling data includes: location information identifying the base station and time information identifying the entry and / or departure from the base station, and the network topology map includes: nodes representing each base station and edges representing the movement trajectories between base stations;

[0068] Based on the nodes and edges of the network topology graph, the iterative processing of the network topology graph yields the set of nighttime permanent locations of each user terminal.

[0069] Based on the set of nighttime locations for each user, the nighttime location with the longest cumulative stay is selected as the corresponding user's nighttime residence.

[0070] For example, based on the nodes and edges of the network topology graph, iterative processing of the network topology graph is performed to obtain the set of nighttime persistent locations of users to which each user terminal belongs. This includes: constructing a module gain degree for the network topology graph based on the nodes and edges, and iterating the network topology graph based on the module gain degree until the module gain degree of the network topology graph is stable, thereby obtaining the set of nighttime persistent locations of users to which each user terminal belongs; wherein, the module gain degree represents the gain after adjacent nodes are merged into a community, and the community represents the user's nighttime persistent location;

[0071] It should be noted that in this embodiment of the application, the subgraph corresponding to the subset of closely connected nodes in the network topology graph is called a "community," which represents the user's nighttime residence. The process of iterating the network topology graph based on module gain is called "community discovery," thereby identifying each user's nighttime residence, obtaining a set of nighttime residences, and selecting the nighttime residence with the longest cumulative stay as the corresponding user's nighttime residence. Then, location signaling data for the observation period can be set to determine the stay duration of each base station falling into the nighttime residence, and the stay durations of each base station can be added together to obtain the user's daily cumulative stay duration at the nighttime residence, providing an accurate basis for judging the daily cumulative stay duration of each user's nighttime residence.

[0072] Exemplarily, the method further includes:

[0073] The inflection point of the trend of permanent resident population size change in the defined area under different rules was detected based on the Kneedle algorithm.

[0074] The set resident population identification rules are generated based on the detected inflection point; wherein, the set resident population identification rules include: a daily stay duration threshold and a monthly residence days threshold.

[0075] Here, the Kneedle algorithm is an inflection point detection algorithm. It considers the metric of the point where the difference between the continuous function formed by curves with different concavity and convexity is the largest and the straight line connecting the endpoints of the set is the largest. It fits the difference curve to identify local maxima and finally determines the knee point (i.e., the inflection point) by using an evaluation threshold. This application's embodiment introduces the Kneedle algorithm to detect the changing trend of the permanent population size in a set area. By detecting the inflection points corresponding to the monthly number of days of residence and the daily length of stay, it generates set rules for identifying permanent residents, which helps to improve the accuracy of permanent resident identification and overcomes the shortcomings of related technologies, such as the limited accuracy caused by manually setting the threshold for the length of stay or the limited sample size caused by k-means clustering analysis.

[0076] For example, the detection of inflection points in the trend of resident population size change in the designated area under different rules based on the Kneedle algorithm includes:

[0077] An initial dataset is constructed based on the number of permanent residents in the designated areas under different rules.

[0078] The initial dataset is subjected to curve fitting and normalization to obtain a first smooth curve;

[0079] A line is constructed based on the start and end points of the first smooth curve, and a difference curve is constructed to represent the difference between the line and the points on the first smooth curve.

[0080] The inflection point is determined based on the local maximum value of the difference curve.

[0081] The generation of the set resident population identification rule based on the detection inflection point includes:

[0082] The daily stay duration threshold is determined based on the daily stay duration corresponding to the inflection point, and the monthly residence days threshold is determined based on the monthly residence days corresponding to the inflection point.

[0083] It is understood that, in this embodiment of the application, by introducing the local maximum value of the difference curve to find the inflection point, the inflection point detection can be avoided from being too sensitive and causing the detection result to be unable to serve as an indicator of a significant change in the trend of permanent resident population size, thereby improving the reliability of the permanent resident population identification rules.

[0084] For example, determining the inflection point based on the local maximum value of the difference curve includes:

[0085] Based on the local maximum values ​​of the difference curve, a set of candidate inflection points is determined;

[0086] For the candidate inflection point set, the inflection point threshold corresponding to each local maximum value is determined based on the sensitivity parameter;

[0087] Based on the difference curve and the inflection point threshold, the detected inflection point is generated.

[0088] In one application example, generating resident identification rules based on the Kneedle algorithm may specifically include the following steps:

[0089] 1) By definition, the population that actually resides in a certain area for 6 months or more is considered the permanent resident population of that area. Therefore, the threshold for the residency month parameter is set to 6. The ranges for the residency days and residency duration parameters are set, and the number of permanent residents meeting different residency parameter conditions is calculated, forming the original dataset S. i ={(x i y i )};where, x i This represents a variable (i.e., a rule variable) based on the duration of stay per day and the number of days of residence per month, corresponding to the horizontal axis, y. iThe vertical axis represents the number of permanent residents corresponding to the rule variable.

[0090] 2): A smooth curve is obtained by fitting a smooth spline function to the original discrete dataset. Then, based on the principle that the shape trend of the original dataset remains unchanged, each data point of the smooth curve is normalized.

[0091] 3): Calculate the difference between points on the curve and points on the connecting straight line with the same x-coordinate, i.e., the set D of difference points. d = {(x, yx)}, and form a difference curve based on the set of difference points. The connecting straight line is the straight line obtained by connecting the start and end points of the smooth curve. Based on the difference between the points of the straight line and the smooth curve on the same horizontal coordinate, the set of difference points is obtained and the difference curve is generated.

[0092] 4) First, determine the concavity and convexity of the curve and its growth / decline trend. Then, by analyzing the changing trend of the difference curve, find the significant and gentle inflection points of the difference curve. Calculate all the local maxima of the difference curve to form a set of candidate inflection points in the original data curve.

[0093]

[0094] Where, x Imxi The x-coordinate of the point where the local maximum value is located in the difference curve; y Imxi D represents the ordinate value of the local maximum point in the difference curve; Imx This represents the set of local maxima in a difference curve; This represents the x-coordinate of the i-th point on the difference curve; This represents the ordinate value of the i-th point on the difference curve.

[0095] 5) In the candidate inflection point set, further compare the difference between each point to select the set of points with local maxima. For each local maxima, set a sensitivity parameter S to calculate a unique threshold. (i.e., the inflection point threshold), which is the difference between the local maximum value and the average difference between consecutive x values;

[0096]

[0097] Among them, y Imxi This represents the ordinate value of the local maximum point in the difference curve; This represents the x-coordinate of the i-th point after the original data has been normalized; S is the sensitivity parameter, which defaults to 1 and can be set according to actual conditions.

[0098] 6): If any difference in the difference curve Upon reaching the next local maximum value Previously dropped to the threshold The following, in the corresponding x I The kneele value is obtained at the value, and finally the knee points of the monthly number of days of residence and the daily stay of the permanent residents are obtained by traversing the points, thus generating the permanent resident identification rule.

[0099] For example, generating the number of permanent residents under the operator in the set area based on the cumulative daily stay of each user and the set resident population identification rules includes:

[0100] Based on the user's cumulative daily stay duration and the daily stay duration threshold, the number of days the user resides in each month within the statistical period is determined;

[0101] Based on the number of days a user stays in each month within the statistical period and the threshold for the number of days a user stays in each month, the number of months a user stays in the statistical period is determined.

[0102] The number of users whose monthly stay reaches a set monthly threshold within a statistical period is used to generate the number of permanent residents under the operator in the set area.

[0103] Understandably, when a user's cumulative daily stay exceeds a daily stay threshold, the number of days of residence is incremented by 1. If the cumulative number of days of residence in a month exceeds a monthly threshold, the user is considered a permanent resident for that month. If the number of months a user is a permanent resident within the statistical period reaches a monthly threshold, the user is considered a permanent resident. For example, if the statistical period is one year, the monthly threshold can be set to 6, and this monthly threshold can be set based on the criteria for determining permanent residents.

[0104] Exemplarily, the method further includes:

[0105] Obtain the user terminal penetration rate, operator user ratio, and dependency ratio of the population at a set age within the specified area;

[0106] Based on the user terminal penetration rate, the operator user ratio, and the dependency ratio of the set age population, the population sample of the permanent residents under the operators in the set area is expanded to obtain the total permanent resident population of the set area.

[0107] Here, user terminal penetration rate (e.g., mobile phone penetration rate), operator user ratio, and dependency ratio of a specified age group can be obtained based on data released by institutions such as the National Bureau of Statistics and the Ministry of Industry and Information Technology. The operator user ratio is the ratio of the number of users of a particular operator to the total number of terminal users in the specified area. The dependency ratio of the specified age group can be the ratio of the population outside the working age group to the population within the working age group. For example, this dependency ratio includes the dependency ratio of the elderly aged 65 and above and the dependency ratio of children aged 14 and below. A population expansion coefficient can be determined based on the user terminal penetration rate, the operator user ratio, and the dependency ratio of the specified age group. Based on this expansion coefficient, the permanent resident population under the operators in the specified area can be expanded to obtain the total permanent resident population of the specified area, thus achieving the statistical analysis of the total permanent resident population and saving statistical costs.

[0108] Exemplarily, the method further includes:

[0109] The total number of permanent residents in the designated area is verified based on the census results.

[0110] If the difference between the total number of permanent residents in the designated area and the census result is less than a set difference threshold, then the total number of permanent residents in the designated area is output.

[0111] Here, the total resident population of the designated area generated in this application embodiment can be verified based on the population census data released by the statistics bureau. If the difference between the total resident population and the population census result is greater than or equal to a set threshold, the result is deemed invalid; if the difference is less than the set threshold, the result is deemed valid, and the total resident population of the designated area is output. Thus, verification based on the population census results can further improve the accuracy of the total resident population generated in this application embodiment.

[0112] The present application will be further described in detail below with reference to application examples.

[0113] Figure 2 A flowchart illustrating the resident population identification method of this application embodiment is shown, as follows: Figure 2 As shown, the method includes:

[0114] Step 201: Construct a network topology map of the user's nighttime stay points based on location signaling data.

[0115] Here, we first set the effective nighttime residence observation time range for users. For example, taking 7 pm to 7 am the next day as an example, we obtain anonymous encrypted mobile phone user location data in the target area within the set observation time period. Each anonymous encrypted mobile location data includes: UID (user unique identifier), base station information, base station entry and exit time.

[0116] For example, based on the location signaling data of the user's terminal device, a network topology map of the user's nighttime stay points is constructed as follows: Figure 3 As shown, the network topology includes node st i Node connecting edge m i Nodes represent the user's location at night (i.e., the base station), and the edges connecting nodes indicate that the user switches between multiple locations at night, generating a movement trajectory.

[0117] Step 202: Identify users' nighttime residences based on community discovery using the network topology map.

[0118] Here, a subgraph corresponding to a subset of tightly connected nodes within a network topology graph is called a community, and the process of finding the community structure of a given network graph is called "community discovery." Each of a user's nighttime resident locations is considered an independent community in the network, and the number of users' nighttime resident locations represents the number of communities in the network topology graph.

[0119] For each node i, iterate through all its neighboring nodes, calculate the modularity gain before and after adding the node to the community of its neighbors, and select the neighboring node with the largest modularity gain to add to its community, as follows:

[0120]

[0121] Where Q is the modularity gain, m represents the total number of edges in the network topology graph, and i and j are any two nodes (staying points) in the network topology graph. A connection is indicated when there is a movement or switching between the staying points. ij k represents the connection weight of an edge in a node network (e.g., it can be 1). i δ(C) represents the sum of the weights of all edges connected to node i (the degree of the node); i C j ) is used to determine whether nodes i and j are in the same community. If δ(C) i C j =1, otherwise 0.

[0122] Repeat the previous step until the community affiliation of all nodes no longer changes. Fold the resulting preliminary community network graph, transforming each community into a supernode representing the user's nighttime residence. Here, folding means merging all nodes within the same community into a new node (also called a supernode), converting the weights of edges between nodes within the community into the weights of the cycles in the new node, and the weights of edges between communities into the weights of edges between the new nodes. Repeat this process until the community modularity of the entire network graph no longer changes, thus obtaining all the user's nighttime residences, which serve as the candidate set of residences. Calculate the cumulative dwell time at all the user's nighttime residences, and select the nighttime residence with the longest dwell time as the user's nighttime residence identification result.

[0123] Step 203: Resident parameter detection is performed based on the improved Kneedle algorithm for continuous function curvature.

[0124] Here, the process of Kneedle algorithm for detecting residency parameters can be found in the aforementioned process of "generating rules for identifying permanent residents based on Kneedle algorithm", which can obtain the knee points of the monthly number of days of residence and the daily stay duration of permanent residents.

[0125] Step 204: Generate the daily stay duration threshold and the monthly residence days threshold to obtain the resident population identification rules.

[0126] Here, based on the dwell parameters of the knee point, the daily dwell time threshold and the monthly dwell days threshold are obtained, and then the permanent resident identification rules are obtained.

[0127] Step 205: Generate the number of permanent residents under the operators in the set area, and perform population expansion and verification to obtain the total number of permanent residents.

[0128] Here, the location signaling data of user mobile phones in a defined area within a defined observation period and the nighttime residence obtained in step 202 can be used to calculate the cumulative daily stay time at the user's nighttime residence. Based on the resident population identification rules obtained in step 204, the number of resident populations under the operator in that defined area can be obtained. For example, suppose the knee point for the number of days of stay is found to be 15 days, and the stay time is 7 hours. When the cumulative daily stay time exceeds 7 hours, it is counted as 1 day of residence, and the monthly residence days are incremented by 1. When the monthly residence days exceed 15 days, the user is determined to be a resident in that month. If the number of months of a user's resident residence within the defined period reaches the monthly threshold, the user is determined to be a resident.

[0129] For example, population sampling and verification includes the following steps:

[0130] 1): The number of mobile phone users of the operator is calculated based on the valid SIM card data of location signaling. Based on the total number of mobile phone users, the regional operator mobile phone user ratio MUP_R is calculated. i ;

[0131] 2): Users are excluded based on the operator's card issuance age, and the number of permanent residents (CZL) aged 15-64 in the region meeting the residency requirements is calculated. i ; and based on the proportion of mobile phone users of regional operators MUP_R i The Ministry of Industry and Information Technology's mobile phone penetration rate MP i Expanding the sample of the resident population aged 15-64 under the operators in the region, we obtain the number of working-age people (PL) in the region aged 15-64. i The details are as follows:

[0132]

[0133] 3): Calculate the total permanent resident population of the region based on the dependency ratio of children and the elderly in the region;

[0134]

[0135] CZ` Ti =PL i +PFL i

[0136] in, The dependency ratio for the elderly population aged 65 and over The dependency ratio for children aged 14 and under, PFL i For the expanded sample of elderly and children in the region, CZ Ti This represents the estimated total permanent resident population of the region.

[0137] 4): Conditional verification is performed using census data. The estimated total permanent resident population sample data is compared with the census data to calculate the error rate. If the error is within the set range, the total permanent resident population can be obtained.

[0138] In order to implement the method of the present application embodiment, the present application embodiment also provides a permanent resident identification device, which corresponds to the above-mentioned permanent resident identification method, and the steps in the above-mentioned permanent resident identification method embodiment are also fully applicable to the present permanent resident identification device embodiment.

[0139] like Figure 4As shown, the resident population identification device includes: a first determining module 401 and a second determining module 402. The first determining module 401 is used to determine the cumulative daily stay duration of each user at their corresponding nighttime residence within the statistical period, based on location signaling data of user terminals in a set area during a set observation period and pre-determined nighttime residences of the users to which each user terminal belongs. The second determining module 402 is used to generate the number of permanent residents under the operator in the set area based on the cumulative daily stay duration of each user and set resident population identification rules. The nighttime residences of the users to which each user terminal belongs are generated based on the network topology map formed by the base stations where each user terminal resides within the set area during the set observation period, and the set resident population identification rules are generated based on the inflection point detection of the resident population size change trend under different rules.

[0140] For example, the resident identification device further includes: a nighttime residence determination module 403, used for:

[0141] Based on the location signaling data of each user terminal in the defined area during the defined observation period, the network topology map is constructed; wherein, the location signaling data includes: location information identifying the base station and time information identifying the entry and / or departure from the base station, and the network topology map includes: nodes representing each base station and edges representing the movement trajectories between base stations;

[0142] Based on the nodes and edges of the network topology graph, the network topology graph is iteratively processed to obtain the set of nighttime permanent residences of each user terminal; based on the set of nighttime permanent residences of each user, the nighttime permanent residence with the longest cumulative stay time is selected as the corresponding user's nighttime residence.

[0143] For example, based on the nodes and edges of the network topology graph, iterative processing of the network topology graph yields a set of nighttime persistent locations for each user terminal, including:

[0144] Based on nodes and edges, a module gain degree is constructed for the network topology graph, and the network topology graph is iterated based on the module gain degree until the module gain degree of the network topology graph is stable, thereby obtaining the set of nighttime permanent residence points of each user terminal; wherein, the module gain degree represents the gain after adjacent nodes are merged into the community, and the community represents the user's nighttime permanent residence point.

[0145] For example, the resident population identification device further includes: an identification rule determination module 404, used for:

[0146] The inflection point of the trend of permanent resident population size change in the defined area under different rules was detected based on the Kneedle algorithm.

[0147] The set resident population identification rules are generated based on the detected inflection point; wherein, the set resident population identification rules include: a daily stay duration threshold and a monthly residence days threshold.

[0148] For example, the rule determination module 404 detects inflection points in the trend of resident population size change in the designated area under different rules based on the Kneedle algorithm, including:

[0149] An initial dataset is constructed based on the number of permanent residents in the designated areas under different rules.

[0150] The initial dataset is subjected to curve fitting and normalization to obtain a first smooth curve;

[0151] A line is constructed based on the start and end points of the first smooth curve, and a difference curve is constructed to represent the difference between the line and the points on the first smooth curve.

[0152] The inflection point is determined based on the local maximum value of the difference curve.

[0153] The identification rule determination module 404 generates the set permanent resident identification rules based on the detected inflection points, including:

[0154] The daily stay duration threshold is determined based on the daily stay duration corresponding to the inflection point, and the monthly residence days threshold is determined based on the monthly residence days corresponding to the inflection point.

[0155] For example, determining the inflection point based on the local maximum value of the difference curve includes:

[0156] Based on the local maximum values ​​of the difference curve, a set of candidate inflection points is determined;

[0157] For the candidate inflection point set, the inflection point threshold corresponding to each local maximum value is determined based on the sensitivity parameter;

[0158] Based on the difference curve and the inflection point threshold, the detected inflection point is generated.

[0159] For example, the second determining module 402 is specifically used for:

[0160] Based on the user's cumulative daily stay duration and the daily stay duration threshold, the number of days the user resides in each month within the statistical period is determined;

[0161] Based on the number of days a user stays in each month within the statistical period and the threshold for the number of days a user stays in each month, the number of months a user stays in the statistical period is determined.

[0162] The number of users whose monthly stay reaches a set monthly threshold within a statistical period is used to generate the number of permanent residents under the operator in the set area.

[0163] For example, the resident population identification device further includes: a sample expansion and estimation module 405, used for:

[0164] Obtain the user terminal penetration rate, operator user ratio, and dependency ratio of the population at a set age within the specified area;

[0165] Based on the user terminal penetration rate, the operator user ratio, and the dependency ratio of the set age population, the population sample of the permanent residents under the operators in the set area is expanded to obtain the total permanent resident population of the set area.

[0166] For example, the resident population identification device further includes: a verification module 406, used for:

[0167] The total number of permanent residents in the designated area is verified based on the census results.

[0168] If the difference between the total number of permanent residents in the designated area and the census result is less than a set difference threshold, then the total number of permanent residents in the designated area is output.

[0169] In practical applications, the first determination module 401, the second determination module 402, the nighttime residence determination module 403, the identification rule determination module 404, the expansion calculation module 405, and the verification module 406 can be implemented by a processor in an electronic device. Of course, the processor needs to run a computer program in its memory to implement its functions.

[0170] It should be noted that the resident identification device provided in the above embodiments is only illustrated by the division of the above-described program modules when performing resident identification. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the resident identification device and the resident identification method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0171] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiments of this application, the embodiments of this application also provide an electronic device. Figure 5 The diagram shows only an exemplary structure of the electronic device, not the entire structure; implementation is possible as needed. Figure 5 The structure shown may be part or all of the structure.

[0172] like Figure 5As shown, the electronic device 500 provided in this application embodiment includes: at least one processor 501, a memory 502, a user interface 503, and at least one network interface 504. The various components in the electronic device 500 are coupled together via a bus system 505. It can be understood that the bus system 505 is used to implement communication between these components. In addition to a data bus, the bus system 505 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 5 The general designated all buses as Bus System 505.

[0173] The user interface 503 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.

[0174] The memory 502 in this embodiment is used to store various types of data to support the operation of the electronic device. Examples of such data include any computer program used to operate on the electronic device.

[0175] The resident identification method disclosed in this application can be applied to or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the resident identification method can be completed by the integrated logic circuitry in the hardware of the processor 501 or by instructions in software form. The processor 501 can be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 501 can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software modules can be located in a storage medium, specifically in memory 502. The processor 501 reads information from memory 502 and, in conjunction with its hardware, completes the steps of the resident identification method provided in the embodiments of this application.

[0176] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to perform the aforementioned method.

[0177] It is understood that memory 502 can be volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Sync Link Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this application are intended to include, but are not limited to, these and any other suitable types of memories.

[0178] In an exemplary embodiment, this application also provides a computer storage medium, specifically a computer-readable storage medium, such as a memory 502 storing a computer program, which can be executed by a processor 501 of an electronic device to complete the steps described in the method of this application embodiment. The computer-readable storage medium can be a ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM, etc.

[0179] In an exemplary embodiment, this application also provides a computer program product, including a computer program that can be executed by a processor 501 of an electronic device 500 to perform the steps described in the method of this application embodiment.

[0180] It should be noted that terms such as "first" and "second" are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0181] Furthermore, the technical solutions described in the embodiments of this application can be combined arbitrarily without conflict.

[0182] The above description is merely a specific embodiment of this application, but the scope of protection of this application 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 this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of identifying resident population, characterized by, The method comprises: determining the single-day stay cumulative duration of each user at the corresponding night-time residence in a statistical period based on the location signaling data of the user terminals in the set region in the set observation time period and the pre-determined night-time residence of the user to which each user terminal belongs; generating the number of permanent residents under the operator in the set region based on the single-day stay cumulative duration of each user and the set permanent resident identification rule; wherein the night-time residence of the user to which each user terminal belongs is generated based on the network topology map composed of the resident base station sites of each user terminal in the set region in the set observation time period, and the set permanent resident identification rule is generated based on the inflection point detection of the change trend of the permanent resident size under different rules.

2. The method of claim 1, wherein, The method further comprises: constructing the network topology map based on the location signaling data of each user terminal in the set observation time period in the set region; wherein the location signaling data comprises location information identifying the resident base station site and time information identifying the entry and / or exit of the resident base station site, and the network topology map comprises nodes representing each resident base station site and edges representing the moving track between the resident base station sites; iteratively processing the network topology map based on the nodes and edges of the network topology map to obtain the night-time residence point set of the user to which each user terminal belongs; and selecting the night-time residence point with the longest cumulative stay duration as the night-time residence of the corresponding user based on the night-time residence point set of each user.

3. The method of claim 2, wherein, The iterative processing of the network topology map based on the nodes and edges of the network topology map to obtain the night-time residence point set of the user to which each user terminal belongs comprises: constructing a module gain degree based on the nodes and edges of the network topology map, and iteratively processing the network topology map based on the module gain degree until the module gain degree of the network topology map is stable to obtain the night-time residence point set of the user to which each user terminal belongs; wherein the module gain degree represents the gain after adjacent nodes are incorporated into a community, and the community represents the night-time residence point of the user.

4. The method of claim 1, wherein, The method further comprises: detecting the inflection point of the change trend of the permanent resident size of the set region under different rules based on the Kneedle algorithm; generating the set permanent resident identification rule based on the detected inflection point; wherein the set permanent resident identification rule comprises a single-day stay duration threshold and a monthly residence day threshold.

5. The method of claim 4, wherein, The detection of the inflection point of the change trend of the permanent resident size of the set region under different rules based on the Kneedle algorithm comprises: constructing an initial data set based on the number of permanent residents of the set region under different rules; performing curve fitting and normalization processing on the initial data set to obtain a first smooth curve; constructing a connecting line based on the starting point and the ending point of the first smooth curve, and constructing a difference curve representing the difference between the connecting line and the points on the first smooth curve; determining the inflection point based on the local maximum value of the difference curve; The generation of the set permanent resident identification rule based on the detected inflection point comprises: determining the single-day stay duration threshold based on the single-day stay duration corresponding to the inflection point, and determining the monthly residence day threshold based on the monthly residence day corresponding to the inflection point.

6. The method of claim 5, wherein, The inflection point is determined based on the local maximum value of the difference value curve, comprising: A candidate inflection point set is determined based on each local maximum value of the difference value curve; An inflection point threshold corresponding to each local maximum value is determined based on the candidate inflection point set and a sensitivity parameter; A detected inflection point is generated based on the difference value curve and the inflection point threshold.

7. The method of claim 4, wherein, The resident population number under the operator in the set area is generated based on the single-day stay cumulative duration of each user and a set resident population identification rule, comprising: The residence days of each monthly period of a user in a statistical period are determined based on the single-day stay cumulative duration of the user and the single-day stay duration threshold; The stay monthly number of the user in the statistical period is determined based on the residence days of each monthly period of the user in the statistical period and the monthly residence day threshold; The resident population number under the operator in the set area is generated based on the number of users whose stay monthly number in the statistical period reaches a set monthly threshold.

8. The method of claim 1, wherein, The method further comprises: The user terminal popularization rate, the operator user proportion rate and the set age population dependency ratio of the users in the set area are acquired; The resident population number under the operator in the set area is population expanded based on the user terminal popularization rate, the operator user proportion rate and the set age population dependency ratio, to obtain the total resident population number of the set area.

9. The method of claim 1, wherein, The method further comprises: The total resident population number of the set area is verified based on a population census result; If it is determined that the difference between the total resident population number of the set area and the population census result is less than a set difference threshold, the total resident population number of the set area is output.

10. A resident population identification apparatus characterized by comprising: Comprise: The first determination module is configured to determine, based on the position signaling data of the user terminals in the set area in a set observation time period and the nighttime residence of each user to which a user terminal belongs in a statistical period, the single-day stay cumulative duration of each user in the corresponding nighttime residence every day in the statistical period; The second determination module is configured to generate the resident population number under the operator in the set area based on the single-day stay cumulative duration of each user and a set resident population identification rule; The nighttime residence of each user to which a user terminal belongs in the set area is generated based on a network topology map formed by the resident base stations of the user terminals in the set area in the set observation time period, and the set resident population identification rule is generated based on the inflection point detection of the resident population size variation trend under different rules.

11. An electronic device, comprising: Comprise: A processor and a memory for storing a computer program capable of running on the processor, wherein, The processor is configured to execute the computer program to perform the steps of the method of any one of claims 1 to 9.

12. A computer storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 9.

13. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 9.

Images