CN110958599A - One-machine multi-card user distinguishing method based on track similarity - Google Patents
One-machine multi-card user distinguishing method based on track similarity Download PDFInfo
- Publication number
- CN110958599A CN110958599A CN201811126908.1A CN201811126908A CN110958599A CN 110958599 A CN110958599 A CN 110958599A CN 201811126908 A CN201811126908 A CN 201811126908A CN 110958599 A CN110958599 A CN 110958599A
- Authority
- CN
- China
- Prior art keywords
- imsi
- base stations
- imsis
- machine multi
- residence
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/18—Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides a method for judging the number of one-machine multi-card users in regional population based on track similarity, which comprises the steps of randomly extracting a certain number of IMSIs from resident population of a residential area in a statistical region, and determining the moving track of each IMSI according to the number of base stations visited by each IMSI in statistical time period and the residence time of each base station in sampling data; comparing the moving tracks of one IMSI and other IMSIs one by one to screen out candidate one-machine multi-card users; and (3) detecting the candidate one-machine multi-card users by adopting super-geometric distribution, and performing multiple correction on the detection result to judge the one-machine multi-card users in the sampled data. The method is used for carrying out regional demographic statistics through the mobile big data, and correcting the demographic result by using the one-machine multi-card user in the judged statistical region, so that the accuracy of the demographic statistics can be improved.
Description
Technical Field
The invention relates to the technical field of mobile big data statistical analysis application, in particular to a method for distinguishing one machine with multiple cards based on signaling track similarity.
Background
The population is monitored and counted by adopting the mobile communication big data, so that the population scale can be effectively estimated, the population flow direction can be mastered, and the development trend of regional population can be early warned in time. The big data of mobile communication used in developing population monitoring and statistics work by using big data is collected and analyzed based on mobile communication terminal equipment, and the premise is that one mobile phone user corresponds to one mobile phone number. However, in reality, there are many phenomena of one phone with multiple cards, that is, one mobile phone user may carry multiple mobile phone numbers at the same time. The one-machine-multiple-card problem has seriously influenced the accuracy and reliability of data statistics, but no effective solution is available at present.
Disclosure of Invention
The invention aims to provide a method for distinguishing one machine with multiple cards based on track similarity aiming at the phenomenon of one machine with multiple cards in reality, which can effectively identify the condition that one user has multiple mobile numbers so as to improve the accuracy of monitoring and counting population based on mobile communication big data.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for judging the number of one-machine multi-card users in regional population based on track similarity is characterized by comprising the following steps:
(1) based on the mobile operator data, randomly extracting a certain number of IMSIs of residence places in the statistical area from resident population of a designated city as sampling data;
(2) determining the moving track of each IMSI according to the number of base stations visited by each IMSI in the sampling data in the statistical time period and the residence time of each base station; counting the total number of the base stations visited by all the sampled IMSIs and the IMSI visit number of each base station;
(3) data preprocessing: according to the moving track of each IMSI, deleting the IMSI which only visits one base station in one day in the sampling data; deleting the base stations with the IMSI access number exceeding a certain value in the total number of the base stations;
(4) comparing the moving track of each IMSI with the moving tracks of other IMSIs one by one to screen out candidate one-machine multi-card users; the screening method comprises the following steps:
a. the number of base stations which are commonly accessed by one IMSI and the other IMSI in one month exceeds a certain number;
b. the residence overlapping time length of one IMSI and the other IMSI in the commonly accessed base station per day is accumulated to exceed a certain value;
if the above conditions are met, the two IMSIs are used as a candidate IMSI pair;
(5) and judging whether each candidate IMSI pair belongs to a one-machine multi-card user or not based on the hyper-geometric distribution: taking the total number of base stations after data preprocessing as N, the number of base stations respectively visited by the two IMSIs as m and N, the number of base stations commonly visited by the two IMSIs as k, and under the assumption that the probabilities of the two IMSIs visiting each base station are independent and equal, calculating the probability P of the number of base stations commonly visited by the two IMSIs according to the following formula:
and when the calculated result is smaller than a preset judgment threshold value, judging that the candidate IMSI pair is a one-machine multi-card user.
Further, in the above method for determining the number of users with multiple cards in the area population based on the track similarity, in the step (5), the determination threshold is corrected by using a bonferroni correction method: dividing the decision threshold by the total number of sampled data to obtain a value as a correction threshold; and when the P value obtained through the super-geometric distribution calculation is smaller than the correction threshold value, judging that the IMSI pair is a one-machine multi-card user.
The method comprises the steps of converting track data into IMSI pair data, counting the time length of each IMSI pair from the same base station every day and the number of the IMSI pairs from the same base station every month, adopting a hyper-geometry inspection method to count the probability value of whether each IMSI pair belongs to the same user (one machine with multiple cards), and judging the IMSI pair reaching a set probability threshold value as a one machine with multiple cards user; furthermore, multiple tests can be adopted to further improve the judgment precision. The invention can effectively judge whether two IMSIs belong to one-phone multi-card users, and can optimize the traditional demographic method which assumes that one mobile phone user corresponds to one IMSI, thereby improving the accuracy of demographic counting through mobile big data.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a statistical chart of the range of activity of a subscriber based on the number of base stations visited by a sampled IMSI during a day.
Detailed Description
The data adopted by the invention comes from signaling data of a mobile operator, and comprises the following steps: subscriber's Mobile phone Number-IMSI (International Mobile Subscriber identity Number); position region identifier lac: for identifying different location areas; base station number ci: combined with a location area identity (lac) for identifying a cell covered in the network; the time the IMSI enters the base station, the time it leaves the base station. The data comes from the same mobile operator. It is not within the scope of the present invention that one machine with multiple cards belong to different operators. Through the data, the moving track of the IMSI can be drawn.
The basic idea of the invention is as follows: based on the mobile signaling data, judging the track similarity of the two IMSIs according to the number of base stations which are accessed by the two IMSIs together within a certain time and the overlapping duration of the residence time of the two IMSIs in the commonly accessed base stations, if the track similarity reaches a certain similarity, considering that the two IMSIs are possible to be one-machine multi-card users, then adopting super-geometric distribution to carry out inspection, and judging that the two IMSIs are one-machine multi-card users if the inspection result is smaller than a set threshold value.
In order to improve the accuracy of the judgment result, Bonferroni correction can be adopted to further screen the judgment result.
The invention is realized mainly based on the following theories:
1. and (4) super-geometric distribution.
Hyper-geometric distribution (hyper-geometric distribution) is a statistically discrete probability distribution that describes the number of times (not returned) that an item of a given type was successfully extracted by extracting n items from a finite number of items.
In the statistical hypothesis test analysis, sample data is assumed to come from the population of the zero hypothesis, the hypothesis test method calculates the rejection domain of the zero hypothesis according to the distribution of the detection statistics under the zero hypothesis, and when the sample statistics falls in the rejection domain, the sample rejects the zero hypothesis, that is, the zero hypothesis is not true. While the probability that a sample statistic from a null hypothesis falls into the rejection domain is called the significance level, which is customarily set at 5%.
The invention uses the hyper-geometric distribution theory to test the number of base stations which are accessed by two IMSIs together, wherein the zero hypothesis is that the two IMSIs to be analyzed are completely independent, and the phenomenon that the IMSIs access a certain base station simultaneously is generated randomly. Taking the number of base stations accessed by two IMSIs simultaneously as a statistic, the statistic can be considered to be obeyed to hyper-geometric distribution, and the number X of base stations accessed by the IMSIs together is tested based on the hyper-geometric distribution: taking the total number of base stations as N, the number of base stations respectively visited by the two IMSIs as m and N, and under the assumption that the probability of visiting each base station by the IMSI is independent and equal, the number of base stations visited by the two IMSIs together is k, and then the probability of visiting k base stations by the two IMSIs together is:
and comparing the P value obtained by the calculation result with a preset judgment threshold value, and judging whether the two IMSIs are the one-machine multi-card users. The decision threshold may take the level of significance customary for hypergeometric distributions, i.e. 5%. And if the calculation result is less than 5%, determining that the two IMSIs are the one-machine multi-card users.
2. Bonferroni correction.
Bonferroni correction is a more rigorous multi-test correction method, i.e. when n (n > -2) hypotheses are tested on the same data set, then the statistical significance level for each hypothesis should be 1/n of the significance level when only one hypothesis is tested.
The threshold value after bonferroni correction is greatly increased, so the determination result can be further screened by using the threshold value after bonferroni correction.
FIG. 1 is a flow chart of an implementation method of the present invention. The specific embodiment of the invention is as follows:
(1) based on the mobile operator data, a certain number of IMSIs of residences in the statistical area are randomly extracted as sample data from resident population in a designated city.
In the invention, each IMSI is compared with the rest IMSIs one by one, and for cities with large population, if all users are used as analysis objects, the calculation amount is overlarge, and the calculation time problem is considered, the method respectively counts all regions of the cities. The statistical area may be a city district, a street, a cell, or a designated parcel according to a specific requirement. A random sampling method is adopted to extract a certain amount of IMSIs in a statistical area as analysis objects, and sampling replaces the totality, so that the operation speed can be greatly improved. In a specific embodiment of the present invention, 3000 IMSIs are randomly selected as research objects in a certain cell of a city. Multiple samples may be considered to reduce error in a particular application.
The invention is mainly applied to the field of demographics. The resident population is generally used as a main statistical index in the urban demographics, so the statistical object of the invention is extracted from the resident population. The definition of city resident population according to the invention is determined according to the residence time of the mobile user in a designated city, and refers to the mobile user who resides in the city for more than 15 days and resides for more than 10 hours per day in one month.
The present invention requires collecting data of IMSI users within a certain time period, which is typically at least one month. In order to ensure the continuity of the data, users who live in statistical areas need to be collected. The residence of the mobile user is defined as follows: on the premise that the mobile user meets the urban resident population, the residence time of the mobile user is longest from 21 pm to 7 pm in the next day, and the area where the base station is located is defined as the residence of the mobile user on the day; and counting the residence days of the user in each area according to the month, wherein the area with the most residence days is the residence of the user in the month.
The residence time of the mobile user in the city and a certain base station can be matched through the track data of the mobile operator.
(2) Determining the moving track of each IMSI according to the number of base stations visited by each IMSI in a certain time period and the residence time of each base station in the sample data; and counting the total number of the base stations visited by all the sampled IMSIs and the number of IMSI visits of each base station per day. The above time period may be limited to one month.
(3) Data preprocessing: according to the moving track of each IMSI, deleting the IMSI which only visits one base station in one day in the sampling data; and deleting the base stations with the IMSI access number exceeding a certain value in the total number of the base stations.
Different IMSIs have different behavior laws. If the IMSI holder has a small range of activity, the number of base stations connected to the IMSI is small in one day, and if the IMSI holder has a large range of activity, the number of base stations visited by the IMSI is large in one day. Thus, the number of base stations visited by the IMSI during the day can be used as an index reflecting the range of activity of the holder.
Fig. 2 is a diagram illustrating a statistical chart of the range of activity of a subscriber based on the number of base stations visited by a sampled IMSI during a day, according to an embodiment of the present invention.
In fig. 2, the vertical axis represents the frequency of IMSI occurrences, and the horizontal axis represents the number of base stations visited by the IMSI. As can be seen from fig. 2, the number of base stations visited by part of the IMSIs every day is small, the trajectory data of the user with a small range of activity is less significant for distinguishing the problem of one machine with multiple cards, and the IMSI data that only visits one base station in one day is deleted in the data preprocessing process.
Fig. 2 shows that most base stations have a small number of IMSIs visited per day, but a few base stations have a large number of IMSIs visited per day. The most significant reason for this is that the selected data is from the same cell. Since the base stations are rich in a large amount of IMSI information, the accuracy of the IMSI pairs predicted as one-machine-two-card by the base stations is low, and the data is deleted in the data preprocessing process. The specific method is that the base stations with the largest IMSI access amount in the first 1 percent are deleted according to the sequence from the largest to the smallest IMSI access amount in all the base stations in one day.
(4) Comparing the moving track of each IMSI with the moving tracks of other IMSIs one by one to screen out candidate one-machine multi-card users; the candidate one-machine multi-card user satisfies the following conditions:
a. the number of base stations which are commonly accessed by one IMSI and the other IMSI in one month exceeds a certain number; the number is set to at least 5 in particular embodiments;
b. the residence overlapping time length of one IMSI and another IMSI in a commonly accessed base station every day exceeds a certain value; in particular, the overlap period may be set to at least 5 hours.
If the above conditions are satisfied, the two IMSIs are used as a candidate IMSI pair.
(5) And judging whether each candidate IMSI pair belongs to a one-machine multi-card user or not based on the hyper-geometric distribution: taking the total number of base stations after data preprocessing as N, the number of base stations respectively visited by the two IMSIs as m and N, the number of base stations commonly visited by the two IMSIs as k, and under the assumption that the probabilities of the two IMSIs visiting each base station are independent and equal, calculating the probability P that the number X of base stations commonly visited by the two IMSIs is more than or equal to k according to the following formula:
and presetting a judgment threshold, and judging the candidate IMSI pair to be a one-machine multi-card user when the calculated P value is smaller than the preset judgment threshold.
The decision threshold is typically set to 5% based on the usual threshold for a hypergeometric distribution. That is, when the calculated P value is less than 5%, the candidate IMSI pair is determined to be a one-machine-multi-card user.
In the specific implementation of the invention, in order to improve the accuracy of the judgment result, a bonferroni correction method can be adopted to correct the judgment threshold, the judgment threshold is divided by the total number of the sampled data, and the obtained value is used as the correction threshold.
When the sample data is 3000 and the determination threshold is 5%, the correction threshold is 0.05/3000. And when the P value obtained through the super-geometric distribution calculation is less than 0.05/3000, judging the IMSI pair to be a one-machine multi-card user.
Claims (7)
1. A one-machine multi-card user judgment method based on track similarity is characterized by comprising the following steps:
(1) based on the mobile operator data, randomly extracting a certain number of IMSIs of residence places in the statistical area from resident population of a designated city as sampling data;
(2) determining the moving track of each IMSI according to the number of base stations visited by each IMSI in the sampling data in the statistical time period and the residence time of each base station every day; counting the total number of the base stations visited by all the sampled IMSIs and the IMSI visit number of each base station;
(3) data preprocessing: according to the moving track of each IMSI, deleting the IMSI which only visits one base station in one day in the sampling data; deleting the base stations with the IMSI access number exceeding a certain value in the total number of the base stations;
(4) comparing the mobile track of each IMSI with the mobile tracks of other IMSIs one by one to screen out candidate one-machine multi-card users, wherein the screening method comprises the following steps:
a. the number of base stations which are commonly accessed by one IMSI and the other IMSI in one month exceeds a certain number;
b. the residence overlapping time length of one IMSI and the other IMSI in the commonly accessed base station per day is accumulated to exceed a certain value;
if the above conditions are met, the two IMSIs are used as a candidate IMSI pair;
(5) and judging whether each candidate IMSI pair belongs to a one-machine multi-card user or not based on the hyper-geometric distribution: taking the total number of base stations after data preprocessing as N, the number of base stations respectively visited by the two IMSIs as m and N, the number of base stations commonly visited by the two IMSIs as k, and under the assumption that the probabilities of the two IMSIs visiting each base station are independent and equal, calculating the probability P of the number of base stations commonly visited by the two IMSIs according to the following formula:
and when the calculated result is smaller than a preset judgment threshold value, judging that the candidate IMSI pair is a one-machine multi-card user.
2. The method for discriminating one-machine multi-card users based on trajectory similarity according to claim 1, wherein: the city resident population in the step (1) refers to mobile users who reside in the city for more than 15 days in one month and stay for more than 10 hours every day; the residence is defined as the residence of the mobile user in the day when the residence time of the mobile user is longest in a certain base station from 21 pm to 7 pm every day on the premise that the mobile user meets the urban resident population; counting the residence days of the user in each area according to the month, wherein the area with the most residence days is the residence place of the user in the month; the residence time of the mobile user in the base station is matched by the track data of the mobile operator.
3. The method for discriminating one-machine multi-card users based on trajectory similarity according to claim 1, wherein: the statistical time period in the step (2) is one month.
4. The method for discriminating one-machine multi-card users based on trajectory similarity according to claim 1, wherein: in the step (3), during data preprocessing, the first 1% of the base stations with the maximum IMSI access amount in each day in the total number of the base stations are deleted.
5. The method for discriminating one-machine multi-card users based on trajectory similarity according to claim 1, wherein: in the step (4), the two IMSIs are used as candidate one-machine multi-card users, and the following conditions should be specifically met:
a. the number of base stations which are commonly accessed by one IMSI and another IMSI in one month exceeds 5;
b. the residence overlap time of one IMSI with another IMSI at a commonly visited base station per day accumulates over 5 hours.
6. The method for discriminating one-machine multi-card users based on trajectory similarity according to claim 1, wherein: the determination threshold value in step (5) is 5%.
7. The one-machine multi-card user identification method based on track similarity as claimed in claim 1, wherein: in the step (5), the judgment threshold is further corrected by adopting a bonferroni correction method: dividing the decision threshold by the total number of sampled data to obtain a value as a correction threshold; and when the P value obtained through the super-geometric distribution calculation is smaller than the correction threshold value, judging that the IMSI pair is a one-machine multi-card user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811126908.1A CN110958599B (en) | 2018-09-26 | 2018-09-26 | One-machine multi-card user distinguishing method based on track similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811126908.1A CN110958599B (en) | 2018-09-26 | 2018-09-26 | One-machine multi-card user distinguishing method based on track similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110958599A true CN110958599A (en) | 2020-04-03 |
| CN110958599B CN110958599B (en) | 2022-05-24 |
Family
ID=69966220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811126908.1A Active CN110958599B (en) | 2018-09-26 | 2018-09-26 | One-machine multi-card user distinguishing method based on track similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110958599B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111970685A (en) * | 2020-10-23 | 2020-11-20 | 上海世脉信息科技有限公司 | One-person multi-card identification method in big data environment |
| CN113704373A (en) * | 2021-08-19 | 2021-11-26 | 国家计算机网络与信息安全管理中心 | User identification method and device based on movement track data and storage medium |
| CN116056067A (en) * | 2023-01-09 | 2023-05-02 | 中国联合网络通信集团有限公司 | Terminal identification method, device, server and storage medium |
| CN117150319A (en) * | 2023-10-30 | 2023-12-01 | 北京艾瑞数智科技有限公司 | Method and device for identifying multiple numbers of one person |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130122934A1 (en) * | 2011-11-11 | 2013-05-16 | International Business Machines Corporation | Data Pre-Fetching Based on User Demographics |
| CN103841550A (en) * | 2012-11-21 | 2014-06-04 | 中国移动通信集团吉林有限公司 | Method and device for identifying multi-card user |
| CN105589939A (en) * | 2015-12-15 | 2016-05-18 | 北京百度网讯科技有限公司 | Method and apparatus for identifying group motion track |
| CN106096631A (en) * | 2016-06-02 | 2016-11-09 | 上海世脉信息科技有限公司 | A kind of recurrent population's Classification and Identification based on the big data of mobile phone analyze method |
| EP3142393A1 (en) * | 2015-09-14 | 2017-03-15 | BASE Company | Method and system for obtaining demographic information |
| CN106778876A (en) * | 2016-12-21 | 2017-05-31 | 广州杰赛科技股份有限公司 | User classification method and system based on mobile subscriber track similitude |
| CN107409288A (en) * | 2015-03-16 | 2017-11-28 | 诺基亚技术有限公司 | Method and apparatus for finding social bond based on concealment track |
| CN108536851A (en) * | 2018-04-16 | 2018-09-14 | 武汉大学 | A kind of method for identifying ID based on motion track similarity-rough set |
-
2018
- 2018-09-26 CN CN201811126908.1A patent/CN110958599B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130122934A1 (en) * | 2011-11-11 | 2013-05-16 | International Business Machines Corporation | Data Pre-Fetching Based on User Demographics |
| CN103841550A (en) * | 2012-11-21 | 2014-06-04 | 中国移动通信集团吉林有限公司 | Method and device for identifying multi-card user |
| CN107409288A (en) * | 2015-03-16 | 2017-11-28 | 诺基亚技术有限公司 | Method and apparatus for finding social bond based on concealment track |
| EP3142393A1 (en) * | 2015-09-14 | 2017-03-15 | BASE Company | Method and system for obtaining demographic information |
| CN105589939A (en) * | 2015-12-15 | 2016-05-18 | 北京百度网讯科技有限公司 | Method and apparatus for identifying group motion track |
| CN106096631A (en) * | 2016-06-02 | 2016-11-09 | 上海世脉信息科技有限公司 | A kind of recurrent population's Classification and Identification based on the big data of mobile phone analyze method |
| CN106778876A (en) * | 2016-12-21 | 2017-05-31 | 广州杰赛科技股份有限公司 | User classification method and system based on mobile subscriber track similitude |
| CN108536851A (en) * | 2018-04-16 | 2018-09-14 | 武汉大学 | A kind of method for identifying ID based on motion track similarity-rough set |
Non-Patent Citations (2)
| Title |
|---|
| 孔扬鑫等: "基于手机轨迹数据的人口流动分析", 《计算机应用》 * |
| 贾若然等: "基于位置轨迹数据的用户相似性分析", 《计算机与数字工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111970685A (en) * | 2020-10-23 | 2020-11-20 | 上海世脉信息科技有限公司 | One-person multi-card identification method in big data environment |
| CN113704373A (en) * | 2021-08-19 | 2021-11-26 | 国家计算机网络与信息安全管理中心 | User identification method and device based on movement track data and storage medium |
| CN113704373B (en) * | 2021-08-19 | 2023-12-05 | 国家计算机网络与信息安全管理中心 | User identification method, device and storage medium based on movement track data |
| CN116056067A (en) * | 2023-01-09 | 2023-05-02 | 中国联合网络通信集团有限公司 | Terminal identification method, device, server and storage medium |
| CN116056067B (en) * | 2023-01-09 | 2024-04-19 | 中国联合网络通信集团有限公司 | Terminal identification method, device, server and storage medium |
| CN117150319A (en) * | 2023-10-30 | 2023-12-01 | 北京艾瑞数智科技有限公司 | Method and device for identifying multiple numbers of one person |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110958599B (en) | 2022-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110958599B (en) | One-machine multi-card user distinguishing method based on track similarity | |
| CN108156626B (en) | Rail transit wireless network quality evaluation method, device and medium | |
| CN110958600B (en) | Method for judging number of users with one machine and multiple cards in regional population based on track similarity | |
| CN109992605B (en) | Population identification method and system based on mobile phone signaling data | |
| CN113645182B (en) | Denial of service attack random forest detection method based on secondary feature screening | |
| CN104427549A (en) | Network problem analysis method and system | |
| CN111866847B (en) | Mobile communication network data analysis method, equipment and computer storage medium | |
| CN108513301A (en) | A kind of disabled user's recognition methods and device | |
| CN111459702B (en) | Indoor distribution system fault monitoring method and device based on MDT data | |
| CN109996272B (en) | Method, device, equipment and medium for detecting indoor leakage signal | |
| CN110933601B (en) | Target area determination method, device, equipment and medium | |
| CN108573265B (en) | People flow statistical method and statistical system | |
| CN109982373B (en) | LTE frequent fallback point analysis method and device, computing device and storage medium | |
| CN114828055A (en) | User service perception evaluation method, device, equipment, medium and program product | |
| CN110621027B (en) | Short-dwell user discovery and short-dwell reason analysis method | |
| CN115310735A (en) | Method, device, equipment and storage medium for identifying business district boundary | |
| CN109714771B (en) | Base station preprocessing method in base station analysis work based on signaling data | |
| CN115134909A (en) | Method, device and equipment for positioning communication interference source and storage medium | |
| CN114205820A (en) | Method, device and computer equipment for detecting suspicious user carrying pseudo base station | |
| CN115412854A (en) | Vehicle co-riding judgment method and device, electronic equipment and storage medium | |
| CN112073971A (en) | Pseudo base station trajectory tracking method and device based on ticket | |
| CN114095947B (en) | Network coverage evaluation method and device, electronic equipment and storage medium | |
| KR100687408B1 (en) | Method and apparatus for optimizing neighbor list automatically for handover management in synchronous w-cdma network | |
| CN113780407B (en) | Data detection method and device, electronic equipment and storage medium | |
| CN111294919B (en) | Pseudo base station positioning method and device, electronic equipment and storage medium |
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 |