A method, device and medium for identifying permanent population based on mobile phone signaling

By setting a fixed number of days per month and a monthly threshold in mobile signaling data, and combining the least squares method and the CRITIC weighting method, the problem of strong subjectivity and weak generalization ability in threshold setting in existing methods is solved, achieving higher recognition accuracy and adaptability, and is applicable to land spatial planning and urban management.

CN118627027BActive Publication Date: 2024-11-08CHINESE ACAD OF SURVEYING & MAPPING
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202411110484.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-08
Estimated Expiration
2044-08-14

AI Technical Summary

Technical Problem

Existing methods for identifying permanent residents based on mobile signaling data suffer from high subjectivity in threshold setting and weak generalization ability, resulting in low accuracy. Furthermore, it is difficult to obtain long-term mobile signaling data when data fees are high.

Method used

By statistically analyzing the number of nighttime overnight stays of mobile signaling users by month, and combining this with GIS spatial overlay analysis, a threshold for the number of fixed-location days within a month and a monthly threshold are set. The optimal threshold is calculated using the least squares method and the CRITIC weighting method. Taking into account the characteristics of the resident population and the data itself, the resident population is identified.

Benefits of technology

It improves the accuracy of resident population identification, enhances the generalization ability of the method, and can adapt to mobile phone signaling data with different time spans and spatial ranges, providing more reliable data support for land spatial planning and urban management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118627027B_ABST
    Figure CN118627027B_ABST
Patent Text Reader

Abstract

The present application discloses a method, device and medium for identifying permanent population based on mobile phone signaling, which relates to the field of natural resources. The method comprises: firstly, the number of days each mobile phone signaling user stays in a fixed residence in a month is counted by month, and the permanent population candidate set under different combinations of the fixed day threshold and the monthly threshold in a month and the corresponding total number of people in the study area are calculated, thereby calculating the market user number difference set and the total number of people in the study area under different combinations of the fixed day threshold and the monthly threshold in a month, and then calculating the combination set under different combinations of the fixed day threshold and the monthly threshold in a month, and finally using the least squares method to determine the optimal setting value of the fixed day threshold and the monthly threshold in a month, and determining the mobile phone signaling users in the permanent population candidate set corresponding to the optimal setting value as the permanent population of the study area. The present application can improve the recognition accuracy of the permanent population and the generalization ability of the recognition method.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of natural resources, and in particular to a method, device and medium for identifying permanent residents based on mobile phone signaling. Background Art

[0002] Permanent population is a crucial basis for urban land supply, planning, and population control. Traditional resident population survey methods are based on censuses and rely primarily on regular sampling surveys. However, with the rapid development of the economy and society, the number and speed of population mobility have increased, and people's increased focus on privacy has led to a decrease in their cooperation with surveys. Traditional methods are no longer able to meet the current demand for refined, timely, and accurate population information. Mobile phone signaling data is highly correlated with the spatiotemporal distribution of human activities. It offers the advantages of high spatiotemporal accuracy, a wide user base, and strong passive acquisition capabilities, making it increasingly widely used in various fields.

[0003] The related work that has been carried out to identify permanent residents from mobile phone signaling data includes: (1) the Chinese patent document with publication number CN115099542A, “Cross-city commuting travel generation and distribution prediction method, electronic device and storage medium”, proposes “identifying permanent residents based on the number of days of stay; users who stay for more than 2 / 3 of the analysis data time are identified as permanent residents”; (2) the Chinese patent document with publication number CN110334564A, “A method and system for identifying permanent residents based on target tracking”, proposes “using a human body recognition system and sensor equipment in the corridor to identify people entering and leaving the community”. When the personnel are continuously collected and the frequency of entry and exit meets the preset conditions, they are preliminarily determined to be permanent residents"; (3) The Chinese patent document "A method and storage device for identifying permanent residents and floating populations with big data" with publication number CN112118548A proposes "calculating the daily population inflow data of a specific area based on the data to be analyzed, obtaining the length of time the inflow population stays in the specific area within a preset time period, and if the length of stay exceeds the preset length, determining the inflow population as newly added permanent residents; if the length of stay does not exceed the preset length, determining the inflow population as floating population"; (4) The Chinese patent document with publication number CN107358265A, “Method for Identifying Foreign Residents Based on Spectral Clustering”, proposes “processing the resident information of mobile phone users to form resident feature variables, using spectral clustering method to perform cluster analysis, building a model, forming resident feature variables, and then identifying resident and non-resident users”; (5) The Chinese patent document with publication number CN106709840A, “A Method for Estimating Urban Resident Population Based on Mobile Network Data”, proposes “selecting the mobile network data of any mobile operator in city A, and obtaining the cumulative number of mobile users under the set training time. Calculate the number of mobile phone users whose residence time is greater than or equal to half of the set training time, and then calculate the empirical function of the permanent population attenuation of mobile phone users; apply the empirical function of the permanent population attenuation of mobile phone users to another city B, estimate the number of permanent mobile phone users of any mobile operator in city B, and thus estimate the total permanent population of city B based on the market share of the mobile operator in city B. (6) The Chinese patent document “A Population Identification Method Based on Mobile Phone Signaling Data” with publication number CN107133318A proposes “to determine whether user A has a stay point within the time interval (0, 6)∪(21, 24) of a day, and calculate the situation in the kth month. If there are more than 16 days with a stay point in a month, and 6 months meet this condition, then it is a permanent population”; (7) The Chinese patent document “Population Identification Method and System Based on Mobile Phone Signaling Data” with publication number CN109992605A proposes “to set target time periods for off-season and peak season for a target area respectively;Target users whose stay time in the target area exceeds a first time threshold in two target time periods are selected based on the user's mobile phone signaling data; the number of days each target user stays in the target area is counted and the number of days of stay is detected; if the number of days the target user stays in the target area exceeds the first number threshold in both target time periods, the target user is determined to be a permanent resident of the target area.

[0004] In summary, existing methods for identifying permanent residents from mobile phone signaling data set fixed thresholds for duration of residence. These thresholds are often based on empirical data, disregarding the inherent characteristics of the mobile phone signaling data. This often leads to low accuracy in identifying permanent residents. Furthermore, the behavioral characteristics of permanent residents are not fully considered when selecting thresholds, resulting in low accuracy. Furthermore, mobile phone signaling data complies with important data provisions of the Data Security Law. Major telecommunications operators impose various access restrictions when providing data services, and the data content is processed and charges high fees. Therefore, natural resources departments at all levels may not be able to access large amounts of continuous mobile phone signaling data for analysis when conducting business applications. They need to identify permanent residents as accurately as possible using the available data content and incomplete data samples, which can then be used for relevant land and space planning and monitoring. This requires that permanent resident identification methods based on mobile phone signaling data have strong generalization capabilities and can be applied to mobile phone signaling data of varying time scales and spatial extents. To address these issues, it is necessary to be able to scientifically set thresholds that can accurately identify permanent residents using the available mobile phone signaling data. Summary of the Invention

[0005] The purpose of this application is to provide a method, device and medium for identifying permanent residents based on mobile phone signaling, which can improve the accuracy of identifying permanent residents and the generalization ability of the identification method.

[0006] To achieve the above objectives, this application provides the following solutions.

[0007] On the first aspect, the present application provides a method for identifying permanent residents based on mobile phone signaling, including: counting the number of days each mobile phone signaling user stays at a fixed residence in a month in a study area; calculating the permanent resident population alternative set under different combinations of the fixed residence threshold and the monthly threshold according to the number of days each mobile phone signaling user stays at a fixed residence in a month in the study area and the fixed residence threshold and the monthly threshold; calculating the market user number difference under different combinations of the fixed residence threshold and the monthly threshold according to the length of the permanent resident population alternative set under different combinations of the fixed residence threshold and the monthly threshold, as well as the number of mobile phone users in the study area and the market share of communication operators in the study area; calculating the market user number difference under different combinations of the fixed residence threshold and the monthly threshold according to the number of days each mobile phone signaling user stays at a fixed residence in a month in the study area; calculating the market user number difference under different combinations of the fixed residence threshold and the monthly threshold according to the number of days each mobile phone signaling user stays at a fixed residence in a month The total number of people in the study area under different combinations of the fixed day threshold within a month and the monthly threshold and the official permanent population in the study area are used to calculate the difference in the total number of people in the study area under different combinations of the fixed day threshold within a month and the monthly threshold; the weighted sum of the difference in the number of market users and the difference in the total number of people in the study area under different combinations of the fixed day threshold within a month and the monthly threshold is performed to obtain the combined collection under different combinations of the fixed day threshold within a month and the monthly threshold; based on the combined collection under different combinations of the fixed day threshold within a month and the monthly threshold, the least squares method is used to determine the optimal setting values ​​of the fixed day threshold within a month and the monthly threshold, and the mobile phone signaling users in the permanent population alternative set corresponding to the optimal setting value are determined as the permanent population of the study area.

[0008] Optionally, the number of overnight stays of each mobile phone signaling user in the study area at a fixed residence within the month is counted on a monthly basis, specifically including: screening out the mobile phone signaling users in the study area based on the residence information of the mobile phone signaling users and the geographical scope of the study area using a GIS spatial overlay analysis method; identifying the nighttime residence set of each mobile phone signaling user by month based on the nighttime residence information of the mobile phone signaling users in the study area; counting the number of overnight stays of the mobile phone signaling users in each residence in the nighttime residence set, and taking the residence with the most overnight stays as the fixed residence of the mobile phone signaling user in that month; and recording the number of overnight stays of each mobile phone signaling user in the fixed residence in the month.

[0009] Optionally, according to the number of overnight stays of each mobile phone signaling user in the study area at the fixed residence within a month, the fixed number of days threshold within a month and the monthly threshold, calculate the permanent population alternative set under different combinations of the fixed number of days threshold within a month and the monthly threshold and the total number of people in the corresponding study area, specifically including: setting the initial values ​​of the fixed number of days threshold within a month and the monthly threshold to 1, setting the maximum values ​​to 27 and the number of months covered by the given mobile phone signaling data, making the fixed number of days threshold within a month and the monthly threshold increase by a step of 1, and cyclically executing the following steps: screening out the permanent population alternative sets under different combinations of the fixed number of days threshold within a month and the monthly threshold to 1, and setting the initial values ​​of the fixed number of days threshold within a month and the monthly threshold to 27 and the number of months covered by the given mobile phone signaling data, and cyclically executing the following steps: screening out the permanent population alternative sets under different combinations of the fixed number of days threshold within a month and the monthly threshold to 1, and setting the maximum values ​​to 27 and the number of months covered by the given mobile phone signaling data, and setting the fixed number of days threshold within a month and the monthly threshold to 1, and cyclically executing the following steps: screening out the permanent population alternative sets under different combinations of the fixed number of days threshold within a month and the monthly threshold to 1, and setting the fixed number of days threshold within a month and the monthly threshold ...27 and the number of months covered by the given mobile phone signaling data, and setting the fixed number of days threshold within a month and The number of mobile phone signaling users that exceeds the fixed location day threshold set value in the current month is used to form a mobile phone signaling user set divided by month; based on the mobile phone signaling user set divided by month, the number of sets in which the mobile phone signaling users are located is counted; the mobile phone signaling users whose sets are larger than the fixed location day threshold set value in the current month are screened to form a permanent population candidate set corresponding to the fixed location day threshold value and the monthly threshold set value in the current month; the extrapolated weight coefficient of each mobile phone signaling user in the permanent population candidate set corresponding to the fixed location day threshold value and the monthly threshold set value in the current month is added to obtain the total number of people in the study area.

[0010] Optionally, based on the length of the permanent population alternative set under different combinations of the fixed number of days in a month threshold and the monthly threshold and the number of mobile phone users in the study area and the market share of the communication operator in the study area, the market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold is calculated, specifically including: multiplying the number of mobile phone users in the study area and the market share of the communication operator in the study area to obtain the number of market users of the communication operator in the study area; performing difference calculation between the number of market users of the communication operator in the study area and the length of the permanent population alternative set under different combinations of the fixed number of days in a month threshold and the monthly threshold and taking the absolute value to form a market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold; normalizing the market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold using the range method to obtain the market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold.

[0011] Optionally, based on the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold and the official number of permanent residents in the study area, the difference set of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold is calculated, specifically including: constructing the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold based on the discrete values ​​of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold; calculating the difference between the official number of permanent residents in the study area and the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold and taking the absolute value to form the difference set of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold; normalizing the difference set of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold using the range method to obtain the difference set of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold.

[0012] Optionally, a weighted sum is performed on the market user number difference aggregation under different combinations of the fixed day threshold within a month and the monthly threshold and the total number of people difference aggregation in the study area to obtain the combined aggregation under different combinations of the fixed day threshold within a month and the monthly threshold, specifically including: constructing an indicator matrix based on the market user number difference aggregation under different combinations of the fixed day threshold within a month and the monthly threshold and the total number of people difference aggregation in the study area; using the CRITIC weight method to determine the weight of each indicator in the indicator matrix as the weight of the corresponding set; a weighted sum is performed on the market user number difference aggregation under different combinations of the fixed day threshold within a month and the monthly threshold and the total number of people difference aggregation in the study area to obtain the combined aggregation under different combinations of the fixed day threshold within a month and the monthly threshold.

[0013] Optionally, based on the combination aggregation under different combinations of the fixed number of days in a month threshold and the monthly threshold, the optimal setting values ​​of the fixed number of days in a month threshold and the monthly threshold are determined using the least squares method, and the mobile phone signaling users in the permanent population alternative set corresponding to the optimal setting value are determined as the permanent population of the study area, specifically including: performing a square operation on the combination aggregation under different combinations of the fixed number of days in a month threshold and the monthly threshold using the least squares method, and obtaining the minimum value of the operation results; using the fixed number of days in a month threshold and the monthly threshold setting values ​​corresponding to the minimum value of the operation results as the optimal setting values ​​of the fixed number of days in a month threshold and the monthly threshold respectively; and finding the permanent population alternative set corresponding to the optimal setting value from the permanent population alternative set under different combinations of the fixed number of days in a month threshold and the monthly threshold as the permanent population of the study area.

[0014] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying permanent residents based on mobile phone signaling.

[0015] In a third aspect, the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for identifying permanent residents based on mobile phone signaling is implemented.

[0016] According to the specific embodiments provided by this application, this application discloses the following technical effects: This application provides a method, device and medium for identifying permanent residents based on mobile phone signaling, which comprehensively considers the fixed residence at night and monthly data, sets two identification parameters: the number of days in a month and the monthly threshold, which are more in line with the characteristics of the permanent population group and can effectively improve the accuracy of identifying permanent residents; the least squares method is used to obtain the most suitable threshold setting value based on the current mobile phone signaling data, which is more in line with the data itself. For mobile phone signaling data with different time spans and different spatial ranges, the most suitable threshold setting value can be found, and the generalization ability is strong. Therefore, this application solves the problems of the current method of identifying permanent residents based on mobile phone signaling data, such as the strong subjectivity of threshold setting, the weak generalization ability of the identification method, and the low accuracy of identifying permanent residents. In the current situation where mobile phone signaling data charges are high and departments at all levels may not be able to obtain mobile phone signaling data with a long span when carrying out business applications, this application can provide more reliable permanent population data support for fields such as land space planning, natural resource monitoring and supervision, and urban management based on the existing given data content and incomplete data samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a flowchart of the permanent resident population identification method based on mobile phone signaling provided in this application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] like Figure 1 As shown, in order to address the problems of highly subjective threshold setting, weak generalization ability of identification methods, and low accuracy in identifying permanent residents in existing methods of identifying permanent residents based on mobile phone signaling data, the permanent resident identification method based on mobile phone signaling provided in this application includes the following steps 1 to 6.

[0022] Step 1: Count the number of days each mobile phone signaling user in the study area stays at a fixed residence within a month.

[0023] This step specifically includes: using the Geographic Information System (GIS) spatial overlay analysis method to screen out mobile phone signaling users in the study area based on their residence information and the geographical scope of the study area; identifying the nighttime residence set of each mobile phone signaling user by month based on the nighttime residence information of the mobile phone signaling users in the study area; counting the number of nighttime residence days of the mobile phone signaling users in each residence in the nighttime residence set, and taking the residence with the most nighttime residence days as the fixed residence of the mobile phone signaling user in that month; and recording the number of nighttime residence days of each mobile phone signaling user in the study area in that month.

[0024] Step 2: Based on the number of days each mobile phone signaling user stays at a fixed residence within a month, as well as the fixed residence day threshold and monthly threshold within a month, calculate the alternative set of permanent residents under different combinations of the fixed residence day threshold and monthly threshold and the corresponding total number of people in the study area.

[0025] This step specifically includes: setting the initial values ​​of the monthly fixed-place days threshold and the monthly threshold to 1, setting the maximum values ​​to 27 and the number of months covered by the given mobile phone signaling data, respectively, making the monthly fixed-place days threshold and the monthly threshold increase in steps of 1, and cyclically executing the following steps: screening out mobile phone signaling users whose number of overnight stays at a fixed residence exceeds the set value of the fixed-place days threshold in the current month, forming a mobile phone signaling user set divided by month; based on the mobile phone signaling user set divided by month, counting the number of sets in which the mobile phone signaling users are located; screening out mobile phone signaling users whose number of sets in which the mobile phone signaling users are located exceeds the set value of the current monthly threshold, forming a permanent population candidate set corresponding to the fixed-place days threshold and the monthly threshold set in the current month; adding the extrapolated weight coefficient of each mobile phone signaling user in the permanent population candidate set corresponding to the fixed-place days threshold and the monthly threshold set in the current month to obtain the total number of people in the study area.

[0026] The extrapolated weight coefficient can be the weight coefficient corresponding to the most recent month for the mobile phone signaling user, or the average of the weight coefficients for several months in which the mobile phone signaling user meets the conditions. The calculation formula for taking the average is as follows.

[0027]

[0028] Where: w u is the extrapolated weight coefficient of mobile signaling user u, w um is the weight coefficient of the u-th mobile phone signaling user in the m-th month in the permanent population candidate set, m u is the number of months in which the mobile phone signaling user meets the conditions, and m is the sequence number of the months in which the mobile phone signaling user meets the conditions.

[0029] The total number of people in the study area is obtained by adding the extrapolated weight coefficients of each mobile phone signaling user in the permanent population alternative set corresponding to the fixed number of days threshold in the current month and the monthly threshold setting value. The specific calculation formula is as follows.

[0030]

[0031] Where p is the total population of the study area, and j is the length of the permanent population candidate set. The length of the permanent population candidate set represents the number of permanent residents in this set.

[0032] Step 3: Based on the length of the permanent population alternative set under different combinations of the number of fixed days in a month threshold and the monthly threshold, as well as the number of mobile phone users in the study area and the market share of communication operators in the study area, calculate the difference in the number of market users under different combinations of the number of fixed days in a month threshold and the monthly threshold.

[0033] This step specifically includes: multiplying the number of mobile phone users in the study area and the market share of the communication operator in the study area to obtain the number of market users of the communication operator in the study area; performing difference calculation between the number of market users of the communication operator in the study area and the length of the permanent population alternative set under different combinations of the fixed number of days in a month threshold and the monthly threshold, and taking the absolute value to eliminate the influence of positive and negative signs to form a market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold; normalizing the market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold using the range method to obtain the market user number difference set under different combinations of the fixed number of days in a month threshold and the monthly threshold.

[0034] Step 4: Based on the total population of the study area under different combinations of the number of fixed days in a month threshold and the monthly threshold and the official permanent population in the study area, calculate the difference in the total population of the study area under different combinations of the number of fixed days in a month threshold and the monthly threshold.

[0035] This step specifically includes: constructing a set of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold according to the discrete values ​​of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold; calculating the difference between the official number of permanent residents in the study area and the set of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold, and taking the absolute value to eliminate the influence of positive and negative signs to form a set of difference values ​​of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold; normalizing the set of difference values ​​of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold using the range method to obtain a set of difference values ​​of the total number of people in the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold.

[0036] Step 5: Perform weighted summation on the market user number difference aggregation under different combinations of fixed-day thresholds within a month and monthly thresholds and the total number of users in the study area, and obtain the combined aggregation under different combinations of fixed-day thresholds within a month and monthly thresholds.

[0037] This step specifically includes: constructing an indicator matrix based on the market user number difference aggregation under different combinations of fixed day thresholds within a month and monthly thresholds and the total number of people difference aggregation in the study area; using the CRITIC weight method to determine the weight of each indicator in the indicator matrix as the weight of the corresponding set; performing weighted summation on the market user number difference aggregation under different combinations of fixed day thresholds within a month and monthly thresholds and the total number of people difference aggregation in the study area to obtain the combination aggregation under different combinations of fixed day thresholds within a month and monthly thresholds.

[0038] Among them, the indicator matrix is ​​constructed based on the difference in the number of market users under different combinations of fixed day thresholds and monthly thresholds within a month and the difference in the total number of people in the research area. The specific construction formula is as follows.

[0039]

[0040] Where: I is the indicator matrix, A and B represent the market user number difference set under different combinations of fixed day thresholds within a month and monthly thresholds, and the total number of people difference set in the study area, respectively; a and b are the elements in the market user number difference set under different combinations of fixed day thresholds within a month and monthly thresholds, and the total number of people difference set in the study area, respectively; n is the number of combinations of fixed day thresholds within a month and monthly thresholds; i is the combination sequence number of fixed day thresholds within a month and monthly thresholds.

[0041] The weighted sum of the market user number difference aggregation under different combinations of the fixed number of days in a month threshold and the monthly threshold and the total number of people difference aggregation in the study area is obtained to obtain the combined aggregation under different combinations of the fixed number of days in a month threshold and the monthly threshold. The specific calculation formula is as follows.

[0042]

[0043]

[0044] Where: C is the combination of different combinations of fixed day thresholds and monthly thresholds within a month, w A 、w B They represent the weights of the market user number difference aggregation A under different combinations of fixed day thresholds within a month and monthly thresholds, and the total number of people difference aggregation B in the research area under different combinations of fixed day thresholds within a month and monthly thresholds.

[0045] Step 6: Based on the combination of different combinations of the fixed number of days in a month threshold and the monthly threshold, the least squares method is used to determine the optimal setting values ​​of the fixed number of days in a month threshold and the monthly threshold, and the mobile phone signaling users in the permanent population alternative set corresponding to the optimal setting value are determined as the permanent population of the study area.

[0046] This step specifically includes: performing a square operation on the combination sets under different combinations of the fixed number of days in a month threshold and the monthly threshold using the least squares method, and obtaining the minimum value of the operation results; using the fixed number of days in a month threshold and the monthly threshold setting values ​​corresponding to the minimum value of the operation results as the optimal setting values ​​of the fixed number of days in a month threshold and the monthly threshold respectively; from the permanent population alternative sets under different combinations of the fixed number of days in a month threshold and the monthly threshold, finding the permanent population alternative set corresponding to the optimal setting value as the permanent population of the study area.

[0047] The least squares method finds the optimal function match for a set of data by minimizing the sum of squared errors. In this application, the optimal settings for the fixed day-of-month threshold and the monthly threshold are found. The least squares method is used to square the combinations of different fixed day-of-month thresholds and monthly thresholds, and the minimum value of the result is obtained. The specific calculation formula is as follows.

[0048]

[0049]

[0050] Where: c min is the minimum value of the operation result, C 2 is the result of the square operation, and c is the element in the combination set C under different combinations of fixed day thresholds within a month and month thresholds.

[0051] The following provides a specific example based on mobile phone signaling data from a certain telecommunications operator L in a certain city X to verify the feasibility of the permanent resident population identification method based on mobile phone signaling data provided in this application. The above mobile phone signaling data covers the period from January to June 2022 and July 2023. The number of mobile phone signaling users monitored in each month is shown in Table 1.

[0052] The city's permanent population at the end of 2022 is approximately 12.9959 million (source: the 2022 Statistical Bulletin on National Economic and Social Development). The city's mobile phone user count in July 2023 is approximately 18,150,675 (source: the local Communications Administration Bureau). In June 2023, telecom operator L held a market share of approximately 17.54%. Therefore, we estimate that telecom operator L will have approximately 3.18 million users in City X in 2023 (18,150,675 x 17.54% = 3,183,628).

[0053] Table 1 Number of mobile phone signaling users

[0054] month Number of monitored mobile phone signaling users 202201 4942176 202202 5738161 202203 5294179 202204 4822274 202205 5266617 202206 5750023 202307 6678615

[0055] The CRITIC weighting method was used to calculate the weight of each indicator. This method scientifically calculates the weight of each indicator using data from the sample within the indicator, taking into account both indicator volatility and conflicts between indicators. This method stands out among many objective weighting methods. Based on mobile phone signaling data from operator L in City X, the weights for the market user difference pool and the full user difference pool, calculated using the CRITIC weighting method for different combinations of fixed-day thresholds within a month and monthly thresholds, are shown in Table 2. Table 3 shows some sample data for the indicator matrix constructed using the market user difference pool and the full user difference pool.

[0056] Table 2: Market user number difference aggregation and total user number difference aggregation table

[0057] Indicator Indicator volatility Conflicting indicators Information volume Weight (%) Market user number difference aggregation 0.268 0.005 0.001 49.419 Total number of people difference collection 0.275 0.005 0.001 50.581

[0058] Table 3. Example data of some indicator matrix

[0059] Market user number difference aggregation Total number of people difference collection 0.818034534 0.93429629 0.759439413 0.86286608 0.733077988 0.83237283 0.711860089 0.807986701 0.684561939 0.776789425 0.658185217 0.746313436 0.634531768 0.718722433 0.612386257 0.692839071 ... ... 0.59182387 0.668401318

[0060] According to a permanent resident population identification method based on mobile phone signaling data proposed in this application, a total of 3,180,905 permanent residents were identified from the city's mobile phone signaling data. Since the user of L communication operator has signaling records, the communication operator identifies the location where the user spends the most time at night as the permanent residence. This application screens out users whose permanent residence is within the scope of City X identified by the communication operator and compares them with the identified permanent residents. It is found that there are 2,899,017 identical users, with an identification accuracy rate of 91.1%. However, the identification method of this communication operator has an obvious drawback, namely that the user's residence time in the new permanent residence must exceed the residence time in the old permanent residence before the user's permanent residence information is updated. This means that the accuracy rate of the identification method provided by this application is at least 91.1%, and the other 8.9% of people identified may also be new permanent residents.

[0061] In summary, the embodiment of the present application provides a method for identifying permanent residents based on mobile phone signaling data. It comprehensively considers the fixed residence at night and monthly data, sets two identification parameters: the threshold value of the number of days in a month and the monthly threshold value, integrates the data such as the number of permanent residents in the study area, the number of mobile phone users in the study area, and the market share of communication operators in the study area, and uses the CRITIC weight method to calculate the relative weights of the number of permanent residents in the study area and the market share of communication operators. It also uses the least squares method to obtain the threshold setting value suitable for the current mobile phone signaling data itself, thereby effectively improving the recognition accuracy of the permanent residents. Moreover, this recognition method obtains the threshold value based on the mobile phone signaling data itself, which is more in line with the data itself. For mobile phone signaling data of different time spans, the most suitable threshold setting value can be found, and the generalization ability is strong. It helps to provide more reliable data support for fields such as national land space planning, natural resource monitoring and supervision, and urban management.

[0062] In an exemplary embodiment, the present application further provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0063] In an exemplary embodiment, the present application further provides a computer-readable storage medium storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0064] In an exemplary embodiment, the present application further provides a computer program product, including a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0065] In this application, all actions to obtain signals, information, or data are performed in compliance with the relevant data protection laws and policies of the country in which they are located and with the authorization of the corresponding device owner. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, storage, and display, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data must comply with relevant laws and regulations.

[0066] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0067] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0068] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0069] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for identifying permanent residents based on mobile phone signaling, characterized in that: include: Count the number of days each mobile signaling user stays at a fixed residence in the study area by month; According to the number of days each mobile phone signaling user stays at a fixed residence in a month, as well as the fixed day threshold and monthly threshold in the study area, the permanent population candidate set under different combinations of the fixed day threshold and monthly threshold and the corresponding total population of the study area are calculated; According to the length of the permanent population alternative set under different combinations of the fixed day threshold and the monthly threshold, as well as the number of mobile phone users in the study area and the market share of the communication operators in the study area, the difference in the number of market users under different combinations of the fixed day threshold and the monthly threshold is calculated; According to the total population of the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold and the official permanent population in the study area, the difference in the total population of the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold is calculated; Perform weighted summation on the market user number difference aggregation under different combinations of fixed day thresholds and monthly thresholds within a month and the total number of user difference aggregation in the study area to obtain the combined aggregation under different combinations of fixed day thresholds and monthly thresholds within a month; According to the combination of different combinations of the fixed day threshold and the monthly threshold, the optimal setting value of the fixed day threshold and the monthly threshold is determined by the least square method, and the mobile phone signaling users in the permanent population candidate set corresponding to the optimal setting value are determined as the permanent population of the study area; According to the length of the permanent population alternative set under different combinations of the fixed day threshold and the monthly threshold, as well as the number of mobile phone users in the study area and the market share of the communication operators in the study area, the market user number difference under different combinations of the fixed day threshold and the monthly threshold is calculated, including: Multiply the number of mobile phone users in the study area by the market share of the communication operator in the study area to obtain the number of market users of the communication operator in the study area; The difference between the number of market users of the communication operator in the study area and the length of the permanent population candidate set under different combinations of the fixed day threshold and the monthly threshold is calculated and the absolute value is taken to form the difference set of the number of market users under different combinations of the fixed day threshold and the monthly threshold; The difference set of the number of market users under different combinations of the fixed day threshold and the monthly threshold within a month is normalized using the range method to obtain the difference set of the number of market users under different combinations of the fixed day threshold and the monthly threshold within a month; According to the total population of the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold and the official permanent population in the study area, the difference in the total population of the study area under different combinations of the fixed number of days in a month threshold and the monthly threshold is calculated, including: According to the discrete values ​​of the total number of people in the study area under different combinations of fixed day-of-month thresholds and monthly thresholds, the total number of people in the study area under different combinations of fixed day-of-month thresholds and monthly thresholds are constructed; The official permanent population in the study area is calculated and the total population set of the study area under different combinations of fixed day thresholds and monthly thresholds is taken, and the absolute value is taken to form the total population difference set of the study area under different combinations of fixed day thresholds and monthly thresholds; The total number of people difference set of the study area under different combinations of fixed day thresholds and monthly thresholds within a month is normalized using the range method to obtain the total number of people difference set of the study area under different combinations of fixed day thresholds and monthly thresholds within a month; According to the combination of different combinations of the fixed day threshold and the monthly threshold, the optimal setting value of the fixed day threshold and the monthly threshold is determined by the least squares method, and the mobile phone signaling users in the permanent population candidate set corresponding to the optimal setting value are determined as the permanent population of the study area, including: The combination of different combinations of fixed day thresholds and month thresholds within a month is aggregated and squared using the least squares method, and the minimum value of the calculation result is obtained; The fixed day threshold value and the month threshold setting value corresponding to the minimum value of the operation result are respectively used as the optimal setting values ​​of the fixed day threshold value and the month threshold value; From the permanent population alternative sets under different combinations of fixed day thresholds within a month and month thresholds, find the permanent population alternative set corresponding to the optimal setting value as the permanent population of the study area.

2. The method for identifying permanent residents based on mobile phone signaling according to claim 1, characterized in that: The number of days each mobile signaling user stays at a fixed residence in the study area is counted by month, including: According to the residence information of mobile phone signaling users and the geographical scope of the research area, the mobile phone signaling users in the research area are screened out using GIS spatial overlay analysis method; Based on the nighttime residence information of mobile signaling users in the study area, the nighttime residence set of each mobile signaling user is identified by month; Count the number of nighttime residences of mobile phone signaling users at each residence, and take the residence with the most nighttime residences as the fixed residence of the mobile phone signaling user in that month; The number of days each mobile signaling user in the study area stayed at a fixed residence during the month was recorded.

3. The method for identifying permanent residents based on mobile phone signaling according to claim 1, characterized in that: According to the number of nights each mobile phone signaling user stays at a fixed residence in the study area within a month, as well as the fixed day threshold and monthly threshold within a month, the permanent population candidate set under different combinations of the fixed day threshold and monthly threshold within a month and the corresponding total population of the study area are calculated, including: The initial values ​​of the fixed day-of-month threshold and the month threshold are set to 1, and the maximum values ​​are set to 27 and the number of months covered by the given mobile phone signaling data, respectively. The fixed day-of-month threshold and the month threshold are incremented by 1, and the following steps are executed cyclically: Monthly screening out mobile phone signaling users whose number of days of staying at a fixed residence exceeds a set threshold value of the number of days at the fixed residence in the current month, to form a mobile phone signaling user set divided by month; Based on the mobile signaling user sets divided by month, count the number of sets that the mobile signaling users belong to; Filter the mobile phone signaling users whose sets contain more mobile phone signaling users than the threshold value set for the current month, and form a permanent population candidate set corresponding to the fixed day threshold value and the monthly threshold value set in the current month; The total number of people in the study area is obtained by adding the extrapolated weight coefficients of each mobile phone signaling user in the permanent population alternative set corresponding to the fixed day threshold and the monthly threshold setting value in the current month.

4. The method for identifying permanent residents based on mobile phone signaling according to claim 1, characterized in that: The market user number difference aggregation under different combinations of fixed day thresholds and monthly thresholds and the total number of user difference aggregation in the study area are weighted summed to obtain the combined aggregation under different combinations of fixed day thresholds and monthly thresholds, including: The indicator matrix is ​​constructed by aggregating the market user number differences under different combinations of fixed day thresholds and monthly thresholds and the total number of users in the research area; The CRITIC weight method is used to determine the weight of each indicator in the indicator matrix as the weight of the corresponding set; The difference in the number of market users under different combinations of fixed day thresholds and monthly thresholds and the difference in the number of total users in the study area are weighted summed to obtain the combined collection under different combinations of fixed day thresholds and monthly thresholds.

5. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for identifying permanent residents based on mobile phone signaling as described in any one of claims 1 to 4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying permanent residents based on mobile phone signaling described in any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • City permanent population evaluation method based on mobile network data

    CN106709840A

  • Population identifying method based on cellular signal data

    CN107133318A

  • Non-native permanent resident population identification method based on spectral clustering

    CN107358265A

  • Population identification method and system based on mobile phone signaling data

    CN109992605A

  • Permanent resident population identification method and system based on target tracking

    CN110334564A