CN107133318B - Population identification method based on mobile phone signaling data - Google Patents
Population identification method based on mobile phone signaling data Download PDFInfo
- Publication number
- CN107133318B CN107133318B CN201710305183.1A CN201710305183A CN107133318B CN 107133318 B CN107133318 B CN 107133318B CN 201710305183 A CN201710305183 A CN 201710305183A CN 107133318 B CN107133318 B CN 107133318B
- Authority
- CN
- China
- Prior art keywords
- population
- point
- user
- data
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
Abstract
The invention discloses a population identification method based on mobile phone signaling data, which belongs to the field of traffic planning data analysis and comprises the following steps: (1) preprocessing the mobile phone signaling data, quickly extracting available fields, and forming a storage format with a user ID as a key field; (2) sequencing the moving position of each user according to time, and denoising according to a speed and angle abnormity judgment method; (3) forming an aggregation point by using a DBSCAN clustering algorithm, and identifying all stay points and stay start-stop time of each user every day; (4) the stay points are classified on a monthly basis to identify a regular population, employment population, and short-term outliers. The method makes full use of the mobile phone signaling data, and through the steps, the regular population, the employment population and the short-term foreign population are quickly and accurately calculated, so that data support is provided for urban population monitoring and traffic planning.
Description
Technical Field
The invention belongs to the field of traffic planning data analysis, and particularly relates to a population identification method based on mobile phone signaling data.
Background
The data of the standing population, the employment population and the short-term external population are important parameters reflecting the travel demand, and are scientific bases for traffic planning, city construction and city management. Currently, with the acceleration of urban construction speed and the continuous improvement of functions, people put higher demands on urban traffic planning, construction and management. The traditional method for acquiring data of the permanent population, the employment population and the short-term external population mainly depends on manual investigation modes such as an entrance investigation mode, a roadside inquiry mode, a form investigation mode, a vehicle license plate investigation mode, a monthly ticket investigation mode and the like, the mode has the problems of low sampling rate, long period, high manpower and financial cost, difficulty in realizing expected effect due to the problems of low sampling rate, high data quality and the like, and the population sampling investigation method is based on population census data and utilizes population change sampling investigation data to calculate. Based on the number of the permanent population in census, population change sampling survey is carried out every year to obtain the development speed of the permanent population or the proportion of the permanent population to the household population, and then the number of the permanent population in the report period is calculated.
The mobile phone signaling data refers to mobile location data generated by mobile phone users during making calls, sending short messages, changing locations and periodically updating, and along with the popularization of mobile phones and the development of wireless positioning technologies in recent years, the mobile phone signaling data is continuously improved and increased, so that a method for identifying the resident population, the employment population and the short-term foreign population by using mobile phone positioning becomes possible. Almost people all have a mobile phone at present, and each communication company has massive user resources and relevant basic data, so that more comprehensive and accurate data can be obtained undoubtedly compared with the traditional investigation mode, and a good data basis is provided for identifying deeper resident population, employment population and short-term external population.
DBSCAN is a relatively representative density-based clustering algorithm. Unlike the partitioning and hierarchical clustering method, which defines clusters as the largest set of density-connected points, it is possible to partition areas with sufficiently high density into clusters and find clusters of arbitrary shape in noisy spatial databases. The processing of the step can not only further eliminate the influence of jitter data on the calculation, but also aggregate the stop points to prepare for the human mouth type analysis.
At present, no relevant literature reports exist.
Disclosure of Invention
In view of this, the technical solution of the present invention is to: the population identification method based on the mobile phone signaling data overcomes the defects of the prior art, is fast and accurate, is mainly used for identifying the permanent population, the employment population and the short-term foreign population, and provides real-time and accurate data support for urban population monitoring and traffic planning.
The technical solution of the invention is as follows: the method mainly aims at identifying the constant population, employment population and short-term foreign population, (1) preprocessing the mobile phone signaling data, rapidly extracting available fields and forming a storage format with user ID as a key field; (2) sequencing the moving position data of each user according to time, and denoising according to a speed and angle abnormity judgment method; (3) forming an aggregation point by using a DBSCAN clustering algorithm, and identifying all stay points and stay start-stop time of each user every day; (4) the stay points are classified on a monthly basis to identify a regular population, employment population, and short-term outliers.
The method is realized by the following steps:
(1) preprocessing the mobile phone signaling data, extracting available fields, forming a storage format with a user ID (identity), namely a user Unique Identifier (UID), as a key field, and forming mobile position data of a user;
(2) sorting the mobile position data of each user according to time, and denoising according to a speed abnormality judgment method and an angle abnormality judgment method to obtain denoised mobile position data;
(3) performing cluster analysis by using a DBSCAN clustering algorithm according to the mobile position data subjected to denoising in the step (2) to form an aggregation point, and identifying all stay points and stay start-stop time of each user every day; the method for identifying the stop point and the stop start-stop time comprises the steps of sequencing all moving position data of the same user all day according to time stamps, dividing the aggregation points with continuous time in the same cluster number into the stop points, and taking the earliest time and the latest time of the stop points as the start-stop time of the stop points;
(4) the stay points and the stay start-stop times are classified in a month period, and a permanent population, a employment population and a short-term foreign population are identified.
The data preprocessing is as follows: the method for uniformly and separately storing the mobile phone signaling data according to the file size comprises the following steps: storing the two bits of the hash value of the UID into 256 different files according to the user ID; and then carrying out multi-thread processing, eliminating data which do not meet requirements, including field missing, longitude and latitude not in the calculation area and abnormal timestamp in the processing process, and forming a storage format which takes the UID as a key field as follows:
the ith file data format (i, UID, timestamp, longitude, latitude, cell, event)
Wherein i is the 121-128 bit hash value of the UID after hash encryption.
In the step (2), the speed abnormality determination method is as follows: reading a coordinate point A, B, C in the mobile phone signaling data generated by the same user according to the time sequence, and respectively calculating the moving speed v from the middle point B to the front and rear two points A, CABAnd vBCAnd if the speed from the middle point B to the front point and the rear point is greater than 120km/h, judging that the position point B is the speed abnormal point of the user.
In the step (2), the angle abnormality determination method is as follows: by reading 4 continuous position points A, B, C, D of the same user, calculating included angles formed by the front position point and the rear position point, and respectively calculating an included angle formed by the A, B, C position point and the B, C, D position pointABCAndBCDand if the two included angles are both smaller than pi/4, judging that the position point C is an abnormal point generated by the user in the traveling process.
In the step (3), the process of forming the aggregation points by clustering analysis by using the DBSCAN clustering algorithm comprises the following steps: setting a critical area with radius s (set as 300 meters in the invention), wherein s is determined by rounding the median of the distance difference between adjacent base stations, starting from the first position point in a user group, calculating the distances D between all the position points and the first position point, if all the distances are less than the critical area (300 meters), or the number of the position points with the distance less than the critical area (300 meters) is more than the minimum contained number of points 2, judging as an aggregation point, marking the cluster number of the aggregation point, and if any one distance is more than the critical area (300 meters), bringing the next position point to repeat the process.
In the step (3), after the stay points and the stay time are identified, data are merged according to the user ID to form the following storage mode:
with the non-stop point marked 0.
In the step (4), the process of identifying the standing population is as follows: judging whether a user A has a stopping point in a time interval of (0,6) U (21,24) (which means 0:00-6:00 and 21:00-24:00) in a day, and calculating the condition of the kth month:
if N is presentkAnd the number is more than or equal to 16, wherein k is 1, …,6, the user A is identified as a permanent population.
In the step (4), the process of identifying the employment population is as follows: if there is a stop point in the (8,18) time interval of the first day of the kth month, and the stop point start-stop time difference is greater than 4 hours, then βiAdd 1, repeat the above calculation for the k month data:
if J iskAnd the user A is identified as the employment population, wherein k is 1, …, 6.
In the step (4), the process of identifying the short-term foreign population is as follows: setting a counter N for a user A to be initialized to 0, and if the A has a position point in one day, accumulating 1 by the N; the above calculation process is repeated for one month of data, and if the counter N <7 for user a, user a is identified as a short term alien population.
Compared with the prior art, the invention has the advantages that:
(1) the method makes full use of the mobile phone signaling data, and through the steps, the constant population, employment population and short-term foreign population are quickly and accurately calculated, so that data support is provided for urban population monitoring and traffic planning;
(2) the basic data of the invention is from the wireless communication network, and the method has the advantages of fast processing speed and high result precision compared with the methods such as sampling statistics and the like.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram illustrating a speed anomaly determination principle according to the present invention;
FIG. 3 is a schematic view illustrating the principle of determining an angle abnormality according to the present invention;
FIG. 4 is a schematic diagram of DBSCAN clustering in the present invention;
FIG. 5 is a schematic diagram of the classification of the stop points according to the present invention.
Detailed Description
In order to make the technical solutions, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings.
The population identification method provided by the embodiment of the invention can be used for quickly extracting useful fields in the mobile phone signaling data in the preprocessing stage to form a data storage format taking the user ID (user unique identification) as a keyword, thereby facilitating the following data cleaning and the cluster analysis of the stop points.
As shown in fig. 1, a flow chart of a method for identifying a permanent population, a employment population and a short-term foreign population based on mobile phone signaling data according to an embodiment of the present invention includes:
Because the mobile phone signaling data volume of each day is large (about 7 hundred million records and 70G data per day), and the difference of file storage size is large, in order to improve the processing efficiency, the original mobile phone signaling data of one day is uniformly and separately stored according to the file size, and the method used by the user is as follows: storing the two latter bits of the hash value of the User ID (UID) into 256 different files; then, data which do not meet the requirements (fields are missing, longitude and latitude are not in the calculation area, and the time stamp is abnormal) are removed in the multithread processing process, and the following storage mode is formed:
the ith file data format (i, UID, timestamp, longitude, latitude, cell, event)
Wherein i is the hash value (i.e., 00 to FF) of 121 to 128 bits after hash encryption of UID.
And 102, sequencing the moving position data of each user according to time, and cleaning the data. Including speed exception cleaning and angle exception cleaning.
Because the mobile phone has the problem of drift in the positioning process, data cleaning is carried out before processing, and the influence of jitter and drift on the data is removed. Firstly, the mobile position data of each user is sorted according to time, and then the following steps are carried out:
step 1021, speed abnormity cleaning.
1. Firstly, reading continuous 3 position points, then calculating the distance d and the time difference t between two adjacent position points, as shown in fig. 2, A, B, C three position points are coordinate points in the mobile phone signaling data generated by the same user according to the time sequence, and respectively calculating the moving speed v from the middle point B to the front and rear two points A, CABAnd vBCWherein v isAB＝dAB/tAB，vBC＝dBC/tBC。
v＝min{vAB,vBC}
2. If v is more than 120 (namely, the speed from the middle point to the front and back points is more than 120km/h, and speed abnormality continuously occurs), the position point B is judged to be the speed abnormality point of the user, and the position point is deleted.
And step 1022, angle abnormity cleaning.
1. Reading 4 continuous position points of the same user, calculating included angles formed by the front position point and the rear position point, as shown in fig. 3, A, B, C, D the four position points are coordinate points in the mobile phone signaling data generated by the same user according to the time sequence, and calculating included angle formed by A, B, C and B, C, D the three position points respectivelyABCAndBCD。
α＝max{∠ABC,∠BCD}
2. if alpha is less than pi/4 (namely the angle a and the angle b are both larger than 135 degrees), the position point C is judged to be an abnormal point generated by the user in the process of traveling, and C is deleted through an angle abnormality judgment method.
And repeating the two steps to delete the speed and angle abnormal points of all users so as to remove the influence of jitter and drift on data.
And step 103, identifying all stop points and start-stop time of the user by using DBSCAN clustering.
Firstly, carrying out cluster analysis on the cleaned data set based on a DBSCAN clustering algorithm, and then judging a stop point according to a clustering result. Obtaining a series of position points of the same user every day through data cleaning, wherein each position point comprises three parameters: UTC time t, longitude lon, latitude lat. Three parameters are input to the DBSCAN algorithm: location point, minimum contained point number MinPts, search field radius Eps. The specific process of identifying the stop point comprises the following steps:
and step 1031, clustering the DBSCAN to form an aggregation point.
Taking the first location point as an example, a point with a distance of less than 300 meters between the first location point and the other location points is found, and then the number of location points contained in the aggregation point is judged to be less than the minimum number of contained points 2, so that the type of the first location point is output as an external point. And sequentially circulating, and when finding that the number of the position points contained in the aggregation point by a certain position point is greater than the minimum contained point MinPts, outputting the point type of the position point as a central point and identifying the position point as the aggregation point.
1. A critical area with a radius of s (300 m in this algorithm) is set, and s is determined by rounding the median of the distance differences between adjacent base stations. Starting from the first location point in a user group, the distances D of all location points from the first location point are calculated.
2. If all the distances are less than 300 meters, or the number of the points with the distances less than 300 meters is greater than the minimum contained number of 2, the cluster is judged to be the gathering point, and the cluster number of the gathering point is marked. If any one distance is greater than 300 meters, the next location point is taken in and the calculation process is repeated.
As shown in FIG. 4, A1、A2、A3、A4、A5Form aOne cluster, marked with cluster number A; b is1、B2Forming a cluster marked with cluster number B.
Step 1032, dwell point and start-stop time identification.
And sequencing all moving position data of the same user all day according to the time stamps, dividing the aggregation points with continuous time in the same cluster number into stop points, and taking the earliest time and the latest time of the points as the starting and stopping time of the stop points. As shown in FIG. 5, { A1、A2、A3Is a dwell point for cluster A, with a start time tA1End time tA3Its dwell time is tA3-tA1；B1、B2Is a stop point of cluster B, whose start time is tB1End time tB2. Its residence time is tB2-tB1。
After the stop point and the stop time are identified, data are merged according to the user ID to form the following storage mode:
with the non-stop point marked 0.
In a natural day of one month, all places where a user appears and the time for the places to stay are counted at 0 hour-6 hour and 21 hour-24 hour each day, and then the place with the largest number of appearing days and the longest stay time (if the stay time is the same, the place with the largest clustering points is selected) is used as the living place of the mobile phone user.
In a working day of one month, counting all places where a user appears and the stay time of the places when each working day is 8 hours to 18 hours, if the stay time of all the places is not less than 4 hours, selecting a place with the longest stay time (if the stay time is the same, the clustering points are the most) in the working day as the employment place of the working day, and then counting the place with the most days of appearance and the longest stay time (if the stay time is the same, the clustering points are the most) in the working day of one month as the employment place of the user.
Step 1041, identifying a standing population.
First, the standing population is defined as: people who live for six consecutive months in the local area for no less than 16 days, namely people who live for six consecutive months in the local area for no less than 16 days. The specific calculation process is as follows: judging whether a user A has a stopping point in a time interval of (0,6) U (21,24) in a day, and calculating the condition of the kth month:
if N is presentkAnd the number is more than or equal to 16, wherein k is 1, …,6, the user A is identified as a permanent population.
1042, identifying employment population.
The employment population is defined as that in six consecutive months, the employment days in the local area range are more than or equal to 60 percent (12 days) of the working days of the month, namely, in one month, the days of the employment data in the local area are not less than 60 percent of the working days of the month. The specific calculation process is as follows: if there is a stop point in the (8,18) time interval of the first day of the kth month, and the stop point start-stop time difference is greater than 4 hours, then βiThe 1 is accumulated. The above calculation procedure was repeated for the data of the k month:
if J iskAnd the user A is identified as the employment population, wherein k is 1, …, 6.
Step 1042, identifying short term outliers.
Short term exotic populations are defined as people in a month with days less than 7 present in the local area. The specific calculation process is as follows: a counter N is set for the user A, initialized to 0, and if the A has a position point in the day, N is added to 1. The above calculation process is repeated for one month of data, and if the counter N <7 for user a, user a is identified as a short term alien population.
The above examples are provided only for the purpose of describing the present invention, and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims. Various equivalent substitutions and modifications can be made without departing from the spirit and principles of the invention, and are intended to be within the scope of the invention.
Claims (1)
1. A population identification method based on mobile phone signaling data is characterized in that: the method mainly aims at identifying the constant population, employment population and short-term foreign population, and is realized by the following steps:
(1) preprocessing the mobile phone signaling data, extracting available fields, forming a storage format with a user ID (identity), namely a user Unique Identifier (UID), as a key field, and forming mobile position data of a user;
(2) sorting the mobile position data of each user according to time, and denoising according to a speed abnormality judgment method and an angle abnormality judgment method to obtain denoised mobile position data;
(3) performing cluster analysis by using a DBSCAN clustering algorithm according to the mobile position data subjected to denoising in the step (2) to form an aggregation point, and identifying all stay points and stay start-stop time of each user every day; the method for identifying the stop point and the stop start-stop time comprises the steps of sequencing all moving position data of the same user all day according to time stamps, dividing the aggregation points with continuous time in the same cluster number into the stop points, and taking the earliest time and the latest time of the stop points as the start-stop time of the stop points;
(4) classifying the stay points and the stay start-stop time in a month period, and identifying a regular population, a employment population and a short-term foreign population;
in the step (2), the speed abnormality determination method is as follows: reading a coordinate point A, B, C in the mobile phone signaling data generated by the same user according to the time sequence, and respectively calculating the moving speed v from the middle point B to the front and rear two points A, CABAnd vBCIf the speed from the middle point B to the front point and the rear point is greater than 120km/h, the position point B is judged to be a speed abnormal point of the user;
in the step (2), the angle abnormality determination method is as follows: by reading 4 continuous position points A, B, C, D of the same user, calculating included angles formed by the front position point and the rear position point, and respectively calculating an included angle formed by the A, B, C position point and the B, C, D position pointABCAndBCDif both the two included angles are smaller than pi/4, judging that the position point C is an abnormal point generated by the user in the process of traveling;
the mobile phone signaling data preprocessing comprises the following steps: the method for uniformly and separately storing the mobile phone signaling data according to the file size comprises the following steps: storing the two bits of the hash value of the UID into 256 different files according to the user ID; and then carrying out multi-thread processing, eliminating data which do not meet requirements, including field missing, longitude and latitude not in the calculation area and abnormal timestamp in the processing process, and forming a storage format which takes the UID as a key field as follows:
the ith file data format (i, UID, timestamp, longitude, latitude, cell, event)
Wherein i is a 121-128 bit hash value of the UID after hash encryption;
in the step (3), the process of forming the aggregation points by clustering analysis by using the DBSCAN clustering algorithm comprises the following steps: setting a critical area with radius s, wherein s is determined by the median value of the distance difference between adjacent base stations, calculating the distances D between all the position points and the first position point from the first position point in a user group, if all the distances are less than the critical area, or the number of the position points less than the critical area is more than the minimum contained number 2, judging as an aggregation point, marking the cluster number of the aggregation point, and if any one distance is more than the critical area, bringing the next position point to repeat the process;
in the step (3), after the stay points and the stay time are identified, data are merged according to the user ID to form the following storage mode:
wherein the non-stop point is marked 0;
in the step (4), the process of identifying the standing population is as follows: judging whether a user A has a stopping point in a time interval of (0,6) U (21,24) in a day, and calculating the condition of the kth month:
if N is presentkThe number of the users is more than or equal to 16, wherein k is 1, …,6, the users A are identified as the permanent population;
in the step (4), the process of identifying the employment population is as follows: if there is a stop point in the (8,18) time interval of the first day of the kth month, and the stop point start-stop time difference is greater than 4 hours, then βiAdd 1, repeat the above calculation for the k month data:
if J iskThe user A is identified as a employment population if the k is 1, …, 6;
in the step (4), the process of identifying the short-term foreign population is as follows: setting a counter N for a user A to be initialized to 0, and if the A has a position point in one day, accumulating 1 by the N; the above calculation process is repeated for one month of data, and if the counter N <7 for user a, user a is identified as a short term alien population.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305183.1A CN107133318B (en) | 2017-05-03 | 2017-05-03 | Population identification method based on mobile phone signaling data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710305183.1A CN107133318B (en) | 2017-05-03 | 2017-05-03 | Population identification method based on mobile phone signaling data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107133318A CN107133318A (en) | 2017-09-05 |
| CN107133318B true CN107133318B (en) | 2021-06-15 |
Family
ID=59716146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710305183.1A Active CN107133318B (en) | 2017-05-03 | 2017-05-03 | Population identification method based on mobile phone signaling data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107133318B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108733774B (en) * | 2018-04-27 | 2022-04-05 | 上海世脉信息科技有限公司 | Dynamic monitoring method for unemployed population based on big data |
| CN109040989A (en) * | 2018-07-19 | 2018-12-18 | 中山大学 | A kind of mobile phone signaling data cleaning method |
| CN110958571A (en) * | 2018-09-26 | 2020-04-03 | 北京融信数联科技有限公司 | Population subdivision method based on mobile signaling data under condition of difference compensation |
| CN109583640A (en) * | 2018-11-23 | 2019-04-05 | 东南大学 | A kind of Urban Traffic passenger flow attribute recognition approach based on multi-source location data |
| CN111222661B (en) * | 2018-11-25 | 2023-06-09 | 星际空间（天津）科技发展有限公司 | Urban planning implementation effect analysis and evaluation method |
| CN109711438A (en) * | 2018-12-10 | 2019-05-03 | 中国联合网络通信集团有限公司 | Bus traffic route acquisition methods, device and equipment |
| CN109495848B (en) * | 2018-12-18 | 2021-06-04 | 成都方未科技有限公司 | User space positioning method |
| CN109918459A (en) * | 2019-01-28 | 2019-06-21 | 同济大学 | A kind of city mid-scale view real population statistical method based on mobile phone signaling |
| CN109992605B (en) * | 2019-03-14 | 2022-09-16 | 上海同济城市规划设计研究院有限公司 | Population identification method and system based on mobile phone signaling data |
| CN110245981B (en) * | 2019-05-31 | 2021-10-01 | 南京瑞栖智能交通技术产业研究院有限公司 | Crowd type identification method based on mobile phone signaling data |
| CN110351664B (en) * | 2019-07-12 | 2021-07-20 | 重庆市交通规划研究院 | User activity space identification method based on mobile phone signaling |
| CN110837528A (en) * | 2019-11-15 | 2020-02-25 | 智慧足迹数据科技有限公司 | Demographic method, device and server |
| CN110868689B (en) * | 2019-11-25 | 2020-12-08 | 智慧足迹数据科技有限公司 | Standing population determining method and device and electronic equipment |
| CN111090642B (en) * | 2019-12-02 | 2023-07-14 | 杭州诚智天扬科技有限公司 | Method for cleaning signaling data of mobile phone |
| CN111078816B (en) * | 2019-12-16 | 2023-08-25 | 秒针信息技术有限公司 | Position-based analysis method, device, terminal and storage medium |
| CN111083636B (en) * | 2019-12-27 | 2021-11-30 | 中国联合网络通信集团有限公司 | Motion state information processing method and device |
| CN111797181B (en) * | 2020-05-26 | 2023-09-05 | 北京城市象限科技有限公司 | Positioning method, device, control equipment and storage medium for user location |
| CN112001829B (en) * | 2020-08-14 | 2024-03-12 | 青岛市城市规划设计研究院 | Population distribution judging method based on mobile phone signaling data |
| CN113641913B (en) * | 2021-08-20 | 2022-04-12 | 数睿科技(珠海横琴)有限公司 | Data processing method and device and electronic equipment |
| CN114501419B (en) * | 2021-12-30 | 2023-05-12 | 中国联合网络通信集团有限公司 | Signaling data processing method, apparatus and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102595323A (en) * | 2012-03-20 | 2012-07-18 | 北京交通发展研究中心 | Method for obtaining resident travel characteristic parameter based on mobile phone positioning data |
| CN105740904A (en) * | 2016-01-29 | 2016-07-06 | 东南大学 | Travel and activity mode identification method based on DBSCAN clustering algorithm |
| CN106570184A (en) * | 2016-11-11 | 2017-04-19 | 同济大学 | Method of extracting recreation-dwelling connection data set from mobile-phone signaling data |
-
2017
- 2017-05-03 CN CN201710305183.1A patent/CN107133318B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102595323A (en) * | 2012-03-20 | 2012-07-18 | 北京交通发展研究中心 | Method for obtaining resident travel characteristic parameter based on mobile phone positioning data |
| CN105740904A (en) * | 2016-01-29 | 2016-07-06 | 东南大学 | Travel and activity mode identification method based on DBSCAN clustering algorithm |
| CN106570184A (en) * | 2016-11-11 | 2017-04-19 | 同济大学 | Method of extracting recreation-dwelling connection data set from mobile-phone signaling data |
Non-Patent Citations (1)
| Title |
|---|
| 基于手机信令数据的流动人口出行特征分析方法研究;马景春;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》;20170315(第03期);第27-64页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107133318A (en) | 2017-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133318B (en) | Population identification method based on mobile phone signaling data | |
| CN107305590B (en) | Urban traffic trip characteristic determination method based on mobile phone signaling data | |
| Wang et al. | A simple baseline for travel time estimation using large-scale trip data | |
| CN106912015B (en) | Personnel trip chain identification method based on mobile network data | |
| CN107610469B (en) | Day-dimension area traffic index prediction method considering multi-factor influence | |
| WO2020238631A1 (en) | Population type recognition method based on mobile phone signaling data | |
| Zheng et al. | Detecting collective anomalies from multiple spatio-temporal datasets across different domains | |
| CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
| CN106651027B (en) | Internet regular bus route optimization method based on social network | |
| CN107958031B (en) | Resident travel OD distribution extraction method based on fusion data | |
| CN107040894A (en) | A kind of resident trip OD acquisition methods based on mobile phone signaling data | |
| CN104902438B (en) | A kind of statistical method and its system based on mobile communication terminal analysis passenger flow characteristic information | |
| CN105307121B (en) | A kind of information processing method and device | |
| CN110334111A (en) | A kind of multidimensional trajectory analysis method and device | |
| CN108629000A (en) | A kind of the group behavior feature extracting method and system of mobile phone track data cluster | |
| Demissie et al. | Understanding human mobility patterns in a developing country using mobile phone data | |
| CN109684373A (en) | Emphasis party based on trip and call bill data analysis has found method | |
| Kujala et al. | Estimation and monitoring of city-to-city travel times using call detail records | |
| CN108733774A (en) | A kind of unemployment dynamic monitoring method based on big data | |
| CN112738729A (en) | Method and system for distinguishing visiting hometown visitor by mobile phone signaling data | |
| CN114647684A (en) | Traffic prediction method and device based on stacking algorithm and related equipment | |
| CN112699955A (en) | User classification method, device, equipment and storage medium | |
| CN112101132A (en) | Traffic condition prediction method based on graph embedding model and metric learning | |
| CN117056823A (en) | Method and system for identifying occupation type of shared bicycle commuter user | |
| CN113516850B (en) | Pipeline traffic flow data acquisition method based on space syntactic analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |