CN111090642B - Method for cleaning signaling data of mobile phone - Google Patents
Method for cleaning signaling data of mobile phone Download PDFInfo
- Publication number
- CN111090642B CN111090642B CN201911217881.1A CN201911217881A CN111090642B CN 111090642 B CN111090642 B CN 111090642B CN 201911217881 A CN201911217881 A CN 201911217881A CN 111090642 B CN111090642 B CN 111090642B
- Authority
- CN
- China
- Prior art keywords
- signaling
- data
- travel
- signaling data
- travel chain
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention relates to the field of big data analysis, and aims to provide a method for cleaning signaling data of a mobile phone. Comprising the following steps: collecting various signaling events generated by a user mobile phone in a mobile phone communication network, and sequencing signaling time of the user according to a time stamp; cutting a user travel chain, and taking the cut travel chain as a minimum study unit; based on the position change rule of the travel chains, cleaning each travel chain to remove invalid data; and simplifying the acquired travel chain. According to the invention, invalid signaling data in the travel chain can be effectively cleared, the purpose of simplifying the travel chain is realized, and the subsequent data analysis is convenient. The time is considered, and meanwhile, the speed factor is considered, so that compared with the travel chain divided by the prior art, the divided travel chain of the user is more in line with the actual travel of the user, and the washing of signaling data is facilitated. The method has high degree of automation and strong applicability, and can be suitable for cleaning the signaling data of the mobile phone with a large sample size and a large range and various different characteristics.
Description
Technical Field
The invention belongs to the field of big data analysis, and particularly relates to a data cleaning technology based on a mobile communication signaling event.
Background
The mobile phone signaling data has large sample size, objective and comprehensive data, no obvious tendency in sampling, and strong time-space continuity, so that the whole process of traffic travel can be observed, and the traffic travel is incomparable with any other data source. However, the mobile phone signaling data has a lot of invalid and erroneous data due to the reasons of bouncing, drifting and the like of signals between base stations, so that the original data cannot truly reflect the travel track of the user. Therefore, it is critical to apply the mobile phone signaling data to quickly identify and remove the invalid data.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects in the prior art and providing a method for cleaning mobile phone signaling data. The method aims at cleaning all data of the disordered mobile phone signaling so as to acquire data which can be used for subsequent data analysis.
In order to solve the technical problems, the invention adopts the following solutions:
the method for cleaning the signaling data of the mobile phone comprises the following steps:
(1) Collecting various signaling events generated by a user mobile phone in a mobile phone communication network, and sequencing signaling time of the user according to a time stamp;
(2) Cutting a user travel chain, and taking the cut travel chain as a minimum study unit;
(3) Based on the position change rule of the travel chains, cleaning each travel chain to remove invalid data;
(4) And (3) simplifying the travel chain obtained in the step (3).
In the present invention, the step (2) specifically includes:
calculating a segmentation index S of the current signaling one by one from a 2 nd signaling of each travel chain, when the segmentation index is larger than 1, dividing the travel chain of the user into two travel chains by taking the current signaling as a division boundary, and re-executing the step (2) on the second travel chain after division until a new travel chain cannot be divided;
the segmentation index calculation formula is as follows:
wherein, p is the current trip chain signaling number, t is the interval time of the current signaling, v is the instantaneous speed of the current signaling,for the average speed of the current travel chain, +.>For the average interval time of the current travel chain, +.> a, b, c, d are fixed constants determined according to the elbow rule.
In the present invention, the step (3) specifically includes:
first, starting from the 2 nd signaling of each travel chain until the next to last signaling: recording the current signaling as the ith data, and deleting the ith data if j (j < i) exists, so that D (j, m)/T (j, m) > K;
then, starting again from the 2 nd signaling of each travel chain until the next to last signaling: the current signaling is noted as the ith data, if j (j < i), m (m > i) is present, such that D (j, m) < D 1 ,∑ q∈Q 1<L,∑ q∈Q T(q,i)<T 1 If the three conditions are met simultaneously, the ith data is marked as data to be deleted;
after all the data to be deleted of the whole travel chain are marked, deleting the marked data from the travel chain data;
finally, for the signaling data continuously at the same position, only the first signaling and the last signaling are reserved, so that the calculated amount is saved to a great extent;
wherein D (j, m) represents a distance between the jth signaling data and the mth signaling data, and T (j, m) represents a distance between the jth signaling data and the mth signaling dataIs a time interval of (1); the definition of the point set Q is as follows: for the signaling data with the subscript q in the travel chain, j < q < m, D (q, j) is more than or equal to D 1 On the basis of the two conditions, if T (q, q+1) > T is also satisfied 2 ,D(q,q+1)>D 2 Either 1 of the two conditions, Q is Q, K, L, D 1 ,T 1 ,D 2 ,T 2 Are six fixed constants determined according to the elbow law.
In the present invention, the step (4) specifically includes:
starting from the second signaling data of the trip chain until the third last signaling data: recording the current signaling data as the ith signaling data, and deleting the ith signaling data from the travel chain if any one of the following conditions is met:
(1) The distance from the position of the ith signaling data to the line segment formed by the positions of the (i-1) th and (i+1) th signaling data is less than s 1 The method comprises the steps of carrying out a first treatment on the surface of the Or alternatively, the first and second heat exchangers may be,
(2) The area of the triangle formed by the position of the ith signaling data and the position of the (i-1) th signaling data and the position of the (i+1) th signaling data is smaller than s 2 The method comprises the steps of carrying out a first treatment on the surface of the Or alternatively, the first and second heat exchangers may be,
(3) The included angle formed by the positions of the ith-1, ith and (i+1) th three signaling data and the included angle formed by the positions of the ith, the (i+1) th and the (i+2) th three signaling data are smaller than s 3 The method comprises the steps of carrying out a first treatment on the surface of the Or alternatively, the first and second heat exchangers may be,
(4) The line segment formed by the positions of the ith signaling data and the (i+1) th signaling data are intersected with the line segment formed by the positions of the (i+2) th signaling data; or alternatively, the first and second heat exchangers may be,
(5) Three line segments formed by the positions of the ith, the (i+1) th and the (i-1) th three signaling data, wherein the ratio of the sum of the lengths of any two line segments to the length of the third line segment is greater than s 4 And the third line segment is less than s 5 ;
The s is 1 、s 2 、s 3 、s 4 、s 5 Is a fixed constant determined according to the elbow rule.
The method can be suitable for the mobile phone signaling data with different characteristics by modifying the given fixed constant, and has great flexibility. The given manner of fixing the constant is determined according to the elbow law and can be adjusted by the person skilled in the art according to the actual needs.
Compared with the prior art, the method has the beneficial effects that:
1. the trip chain refers to a collection of a series of signaling data generated during the trip of the user. According to the invention, the purpose of simplifying the travel chain is achieved by designing the method capable of effectively clearing invalid signaling data in the travel chain, and subsequent data analysis is facilitated.
2. In the prior art, only time factors are considered basically when the travel chains are divided, and the method also considers speed factors when considering time, so that compared with the travel chains divided in the prior art, the divided user travel chains are more in line with actual travel of users, and are more beneficial to cleaning signaling data.
3. The existing data cleaning method has poor effect of eliminating ABAB type cyclic switching unique to mobile phone signaling. For example, the kalman filter algorithm requires tuning by a large number of parameters on the basis that the data set satisfies extremely severe conditions, so that most of the "ABAB" type cyclic switching data can be removed. The method can effectively remove almost all 'ABAB' -type circularly switched data in the data set (through the operation of the step 3), and greatly improves the accuracy of subsequent sequence comparison.
4. The invention can clean out a large amount of signaling data irrelevant to the actual travel track (through the operation of the step 4), instead of only cleaning out the signaling data which stays in place or the signaling data which is close in distance as in the prior art, so that a large amount of irrelevant data can be cleaned out on the premise of ensuring the travel characteristics of users, and the subsequent calculated amount is reduced.
5. The invention has high degree of automation and strong applicability, and can be suitable for cleaning the signaling data of the mobile phone with a large sample size and a large range and various different characteristics.
Drawings
Fig. 1 is an exemplary diagram of a travel chain division result of a certain user in the present embodiment.
Fig. 2 is an exemplary diagram of a result of cleaning travel chain data of a certain user in the present embodiment.
Detailed Description
The following describes the specific implementation of the present invention in detail with reference to the drawings and specific examples.
Step 1, collecting signaling data
The invention adopts the partial mobile phone signaling data which is provided by an operator and comprises 4 fields of user identification, time stamp, base station longitude and base station latitude as the data set used by the invention. The dataset had 41654036 rows and 337686 rows of chains. Wherein a part of the data is shown in table 1. In this embodiment, the unit of interval time is constant in seconds, the unit of interval distance is constant in kilometers, and the unit of interval speed is constant in kilometers per hour. Fig. 1 is a graph of the longitude of signaling data of user 1 over time, where the abscissa is time and the ordinate is the longitude of signaling, and it can be seen that 23 points 02 to 57 in the original trace of the user contain a large amount of abnormal data in time periods.
TABLE 1
User identification | Time stamp | Base station longitude | Latitude of base station |
User 1 | 20180919110759 | 120.26731 | 30.88472 |
User 2 | 20180919105619 | 120.26731 | 30.88472 |
User 3 | 20180919185212 | 120.26731 | 30.88472 |
User 4 | 20180919193046 | 120.26731 | 30.88472 |
User 5 | 20180919175801 | 120.26731 | 30.88472 |
User 6 | 20180919155420 | 120.26731 | 30.88472 |
User 7 | 20180919160746 | 120.26731 | 30.88472 |
Step 2, dividing a user travel chain
The above travel chain dividing method is adopted for each travel chain, and the value of the fixed parameter is selected by using an elbow rule. The calculated and determined parameter values are as follows: a=0.16, b=5, c=2400, d=0.62. The total number of the travel chains after division is 346247, and 8561 travel chains are added before division. Taking a travel chain of the user 1 as an example, the travel chain has 123 signaling data, the starting time is 18 points and 0 minutes, the ending time is 23 points and 57 minutes, the travel process of the user throughout the day is covered, and after the travel chain is divided, 2 sub travel chains are obtained. As shown in fig. 2, after the travel chain is divided, the long-time silence period from the point 21 to the point 14 of the user is identified as the dividing point of two sub travel chains, and the two sub travel chains have practical significance, so that the travel characteristics of the user can be conveniently studied.
Step 3, cleaning and simplifying signaling data
The data of each travel chain is cleaned and simplified by using the data cleaning method, and the values of the parameters are determined by using an elbow rule as follows: k=282, l=5, d 1 =1,T 1 =1200,D 2 =2,T 2 =30,s 1 =0.1,s 2 =0.01,s 3 =15,s 4 =3.5,s 5 =0.2. The simplified data set has 5845106 rows of data, which is reduced by 35808930 rows and the reduction amplitude reaches 86 percent. Taking the trip chain of the user 1 as an example, after the trip chain is processed, the trip chain only contains 59 signaling data, compared with the trip chain before the processing, 64 signaling is reduced, the reduction range reaches 52%, all the characteristics of the trip chain before the processing are still reserved, the change chart of the longitude along with time is shown in fig. 2, and it can be seen that the data processing algorithm can effectively delete the bouncing point and the extraction user residence point in the signaling data on the basis of reserving the characteristic attribute of the trip chain of the user: the wave-shaped bouncing data of 23 points 02 to 23 points 57 time intervals in the travel sub-chain of the actual travel track of the user are effectively removed, and only 2 pieces of data representing the stay characteristics of the user are reserved. The wave-shaped bouncing data (ABAB type circulation switching data) can be removed, so that the burden of subsequent calculation can be effectively reduced, and the user track can be visualized conveniently.
Claims (4)
1. The method for cleaning the signaling data of the mobile phone is characterized by comprising the following steps:
(1) Collecting various signaling events generated by a user mobile phone in a mobile phone communication network, and sequencing signaling time of the user according to a time stamp;
(2) Cutting a user travel chain, and taking the cut travel chain as a minimum study unit; the method specifically comprises the following steps:
calculating a segmentation index S of the current signaling one by one from a 2 nd signaling of each travel chain, when the segmentation index is larger than 1, dividing the travel chain of the user into two travel chains by taking the current signaling as a division boundary, and re-executing the step (2) on the second travel chain after division until a new travel chain cannot be divided;
the segmentation index calculation formula is as follows:
wherein, p is the current trip chain signaling number, t is the interval time of the current signaling, v is the instantaneous speed of the current signaling,for the average speed of the current travel chain, +.>For the average interval time of the current travel chain, +.> a, b, c, d are fixed constants determined according to the elbow law;
(3) Based on the position change rule of the travel chains, cleaning each travel chain to remove invalid data;
(4) And (3) simplifying the travel chain obtained in the step (3).
2. The method according to claim 1, wherein the step (3) specifically comprises:
first, starting from the 2 nd signaling of each travel chain until the next to last signaling: recording the current signaling as the ith data, and deleting the ith data if j exists and j < i so that D (j, m)/T (j, m) > K;
then, starting again from the 2 nd signaling of each travel chain until the next to last signaling: note the current signaling as the ith data, if j exists<i,m>i, and such that D (j, m) < D 1 ,∑ q∈Q 1<L,∑ q∈Q T(q,i)<T 1 If the three conditions are met simultaneously, the ith data is marked as data to be deleted;
after all the data to be deleted of the whole travel chain are marked, deleting the marked data from the travel chain data;
finally, for the signaling data continuously at the same position, only the first signaling and the last signaling are reserved, so that the calculated amount is saved to a great extent;
wherein D (j, m) represents a distance between the jth signaling data and the mth signaling data, and T (j, m) represents an interval time between the jth signaling data and the mth signaling data; the definition of the point set Q is as follows: for the signaling data with the subscript q in the travel chain, j < q < m, D (q, j) is more than or equal to D 1 On the basis of the two conditions, if T (q, q+1) > T is also satisfied 2 ,D(q,q+1)>D 2 Either 1 of the two conditions, Q is Q, K, L, D 1 ,T 1 ,D 2 T is six fixed constants determined according to the elbow law.
3. The method according to claim 1, wherein the step (4) specifically comprises:
starting from the second signaling data of the trip chain until the third last signaling data: recording the current signaling data as the ith signaling data, and deleting the ith signaling data from the travel chain if any one of the following conditions is met:
(1) From the position of the ith signaling data to the position of the (i-1) th and (i+1) th two signaling dataThe distance of the line segments is less than s 1 The method comprises the steps of carrying out a first treatment on the surface of the Or alternatively, the first and second heat exchangers may be,
(2) The area of the triangle formed by the position of the ith signaling data and the position of the (i-1) th signaling data and the position of the (i+1) th signaling data is smaller than s 2 The method comprises the steps of carrying out a first treatment on the surface of the Or alternatively, the first and second heat exchangers may be,
(3) The included angle formed by the positions of the ith-1, ith and (i+1) th three signaling data and the included angle formed by the positions of the ith, the (i+1) th and the (i+2) th three signaling data are smaller than s 3 The method comprises the steps of carrying out a first treatment on the surface of the Or alternatively, the first and second heat exchangers may be,
(4) The line segment formed by the positions of the ith signaling data and the (i+1) th signaling data are intersected with the line segment formed by the positions of the (i+2) th signaling data; or alternatively, the first and second heat exchangers may be,
(5) Three line segments formed by the positions of the ith, the (i+1) th and the (i-1) th three signaling data, wherein the ratio of the sum of the lengths of any two line segments to the length of the third line segment is greater than s 4 And the third line segment is less than s 5 ;
The s is 1 、s 2 、s 3 、s 4 、s 5 Is a fixed constant determined according to the elbow rule.
4. The method of claim 1 wherein the signaling event of step (1) includes at least 4 fields of mobile phone signaling data including user identification, time stamp, base station longitude and base station latitude.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911217881.1A CN111090642B (en) | 2019-12-02 | 2019-12-02 | Method for cleaning signaling data of mobile phone |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911217881.1A CN111090642B (en) | 2019-12-02 | 2019-12-02 | Method for cleaning signaling data of mobile phone |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111090642A CN111090642A (en) | 2020-05-01 |
CN111090642B true CN111090642B (en) | 2023-07-14 |
Family
ID=70393924
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911217881.1A Active CN111090642B (en) | 2019-12-02 | 2019-12-02 | Method for cleaning signaling data of mobile phone |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111090642B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114979995B (en) * | 2022-05-23 | 2023-04-14 | 智慧足迹数据科技有限公司 | Mobile phone signaling data simplifying method and device, electronic equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104244314A (en) * | 2014-07-30 | 2014-12-24 | 北京拓明科技有限公司 | Potential group client identification method based on Mc interface signaling |
CN105117789A (en) * | 2015-07-29 | 2015-12-02 | 西南交通大学 | Resident trip mode comprehensive judging method based on handset signaling data |
CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
CN105761190A (en) * | 2016-02-01 | 2016-07-13 | 东南大学 | Urban community vacancy rate dynamic monitoring method based on mobile phone location data |
CN106897420A (en) * | 2017-02-24 | 2017-06-27 | 东南大学 | A kind of resident Activity recognition method of user's trip based on mobile phone signaling data |
CN106953858A (en) * | 2017-03-17 | 2017-07-14 | 贵州省煤炭产品质量监督检验院 | A kind of clean energy resource information acquisition control system based on internet communication |
CN107133318A (en) * | 2017-05-03 | 2017-09-05 | 北京市交通信息中心 | A kind of population recognition methods based on mobile phone signaling data |
CN107305590A (en) * | 2017-06-14 | 2017-10-31 | 北京市交通信息中心 | A kind of urban transportation trip characteristicses based on mobile phone signaling data determine method |
CN108171974A (en) * | 2017-12-27 | 2018-06-15 | 东南大学 | A kind of traffic trip mode discrimination method based on cellular triangulation location data |
CN108955693A (en) * | 2018-08-02 | 2018-12-07 | 吉林大学 | A kind of method and system of road network |
CN109104694A (en) * | 2018-06-26 | 2018-12-28 | 重庆市交通规划研究院 | A kind of user stop place discovery method and system based on mobile phone signaling |
CN109902930A (en) * | 2019-01-28 | 2019-06-18 | 同济大学 | A kind of auxiliary facility planning auxiliary system based on real population index |
-
2019
- 2019-12-02 CN CN201911217881.1A patent/CN111090642B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104244314A (en) * | 2014-07-30 | 2014-12-24 | 北京拓明科技有限公司 | Potential group client identification method based on Mc interface signaling |
CN105117789A (en) * | 2015-07-29 | 2015-12-02 | 西南交通大学 | Resident trip mode comprehensive judging method based on handset signaling data |
CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
CN105761190A (en) * | 2016-02-01 | 2016-07-13 | 东南大学 | Urban community vacancy rate dynamic monitoring method based on mobile phone location data |
CN106897420A (en) * | 2017-02-24 | 2017-06-27 | 东南大学 | A kind of resident Activity recognition method of user's trip based on mobile phone signaling data |
CN106953858A (en) * | 2017-03-17 | 2017-07-14 | 贵州省煤炭产品质量监督检验院 | A kind of clean energy resource information acquisition control system based on internet communication |
CN107133318A (en) * | 2017-05-03 | 2017-09-05 | 北京市交通信息中心 | A kind of population recognition methods based on mobile phone signaling data |
CN107305590A (en) * | 2017-06-14 | 2017-10-31 | 北京市交通信息中心 | A kind of urban transportation trip characteristicses based on mobile phone signaling data determine method |
CN108171974A (en) * | 2017-12-27 | 2018-06-15 | 东南大学 | A kind of traffic trip mode discrimination method based on cellular triangulation location data |
CN109104694A (en) * | 2018-06-26 | 2018-12-28 | 重庆市交通规划研究院 | A kind of user stop place discovery method and system based on mobile phone signaling |
CN108955693A (en) * | 2018-08-02 | 2018-12-07 | 吉林大学 | A kind of method and system of road network |
CN109902930A (en) * | 2019-01-28 | 2019-06-18 | 同济大学 | A kind of auxiliary facility planning auxiliary system based on real population index |
Non-Patent Citations (2)
Title |
---|
"基于手机信令数据的区域住房价格与居民出行特性相关性研究";廖锟;《中国优秀硕士学位论文全文数据库(工程科技Ⅱ辑)》;C034-298 * |
"基于手机信令的数据分析引擎设计与实现";余锦斌;《中国优秀硕士学位论文全文数据库(信息科技辑)》(第2019第5期期);I138-1071 * |
Also Published As
Publication number | Publication date |
---|---|
CN111090642A (en) | 2020-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108955693B (en) | Road network matching method and system | |
CN108156037B (en) | Alarm correlation analysis method, device, equipment and medium | |
CN109104694B (en) | User stay position finding method and system based on mobile phone signaling | |
Chen et al. | Short-term load forecasting: Similar day-based wavelet neural networks | |
CN102087788B (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
CN108320501A (en) | Public bus network recognition methods based on user mobile phone signaling | |
CN110020178A (en) | Point of interest recognition methods, device, equipment and storage medium | |
CN109239554A (en) | A kind of denoising of power cable partial discharge signal and useful signal extracting method and system | |
CN111090642B (en) | Method for cleaning signaling data of mobile phone | |
US20130166352A1 (en) | Mobile categorization | |
CN110990443A (en) | Mobile phone signaling-based professional and living population characteristic estimation method | |
CN111294742B (en) | Method and system for identifying accompanying mobile phone number based on signaling CDR data | |
CN107979810A (en) | Indoor orientation method, server and system | |
CN107180223A (en) | Action identification method and system based on WIFI wireless signals | |
CN109121094B (en) | Pseudo code signaling data preprocessing and trip chain identification method | |
CN112988936A (en) | Travel track prediction method and device, computing equipment and storage medium | |
CN105608895A (en) | Local abnormity factor-based urban heavy-traffic road detection method | |
CN111510368A (en) | Family group identification method, device, equipment and computer readable storage medium | |
CN105307262A (en) | Positioning method and device for pseudo base station | |
CN110933601B (en) | Target area determination method, device, equipment and medium | |
CN104318795A (en) | Expressway site traffic state deviation degree acquiring method based on time-space analysis | |
CN108629980A (en) | A method of improving air quality by controlling the flow of traffic | |
CN108303622A (en) | Delay time estimation method and device | |
Waury et al. | Adaptive travel-time estimation: A case for custom predicate selection | |
CN109444660B (en) | Method for identifying faults and interferences of power transmission line |
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 |