CN106792514B - User position analysis method based on signaling data - Google Patents
User position analysis method based on signaling data Download PDFInfo
- Publication number
- CN106792514B CN106792514B CN201611085317.5A CN201611085317A CN106792514B CN 106792514 B CN106792514 B CN 106792514B CN 201611085317 A CN201611085317 A CN 201611085317A CN 106792514 B CN106792514 B CN 106792514B
- Authority
- CN
- China
- Prior art keywords
- user
- cell
- cells
- resident
- 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.)
- Active
Links
Images
Classifications
-
- 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
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user occupation analysis method based on signaling data, which comprises the steps of clearing an interference cell by utilizing a weight algorithm according to cell residence information of a user in a set time period to obtain an important cell of the user, then carrying out spatial clustering based on geographical position information, and dividing an area densely appearing in the clustering into frequent residences; setting different weights for each cell in the permanent station according to the residence time to mine the resident cells of the users; after the resident cell of the user is obtained, a resident cell scoring model based on frequency and duration is established according to the resident time distribution of the user's permanent location, and the resident cell of the user is subjected to attribute division to obtain the information of the residence place and the working place of the user. The method can excavate the user frequent site information of the user including the working place and the residence place, thereby facilitating the operator to pertinently and purposefully develop marketing work and carry out fixed-point marketing or network test on the user, which is very beneficial to broadband services, mobile phone network access and the like.
Description
Technical Field
The invention relates to a user occupation analysis method based on signaling data.
Background
The LTE network records people's travel information, including the position of a user in a day, the residence time in a certain place and the like, and the data are generally regular, for example, for people working on normal working days, the high frequency occurs in the daytime and stays at the working place, the high frequency occurs at night and weekends and stays at the residence place, and even the daily travel track of the user can be drawn according to the daily high frequency occurrence cell.
For an operator, how to dig out the user frequent site information, even further dig out the working place, the residence place or the working place of the user, so that the operator can pertinently and purposefully develop marketing work, can perform fixed-point marketing or network test on the user, and is very beneficial to broadband services, mobile phone network access and the like.
Disclosure of Invention
The invention aims to provide a user occupation analysis method based on signaling data, which is realized according to clustering based on geographic spatial positions and a cell scoring model based on frequency and duration after realizing the longitude and latitude matching of a cell of a user by means of signaling data and base station information of a mobile operator, realizes the judgment of resident occupation and working place, and solves the problems of how to dig out the frequent occupation information of the user and even further dig out the working place, the occupation place or the occupation place of the user in the prior art.
The technical solution of the invention is as follows:
a user occupation analysis method based on signaling data comprises the following steps:
according to the cell residence information of a user in a set time period, after eliminating interference cells by using a weight algorithm to obtain important user cells, carrying out spatial clustering based on geographical position information on the obtained important user cells, and dividing densely-appearing areas in the clustering into permanent locations;
setting different weights for each cell in the permanent station according to the residence time to mine the resident cells of the users;
after the resident cell of the user is obtained, a resident cell scoring model based on frequency and duration is established according to the resident time distribution of the user's permanent location, and the resident cell of the user is subjected to attribute division to obtain the information of the residence place and the working place of the user.
And further, clearing the interference cells by using a weight algorithm, specifically, calculating and ranking the average residence time of the residence cells of the user in a set time period, cleaning and deleting the cells with the average residence time being lower than a certain threshold value, removing the interference cells, and dividing the important cells of the user.
Further, a representative clustering algorithm based on density, namely a DBSCAN algorithm, is adopted to perform spatial clustering based on geographical location information on the obtained user important cell, specifically:
all objects in a given dataset D are marked as "not visited", one object p not visited is randomly selected, marked as "visited", and the p-neighborhood is checked for at least MinPts objects, if not, object p is marked as a noise point; otherwise, a new cluster C is created for p, and all objects in the neighborhood of p are placed in the candidate set N;
iteratively adding objects in the candidate set N that do not belong to other clusters to the cluster C; in this process, the object P marked as "not visited" in the corresponding candidate set N*DBSCAN object P*Marked as "visited" and examining the object P*If the object P is a neighborhood of*Is at least one MinPts object, object P*All objects in the neighborhood are added into the candidate set N, the DBSCAN continues to add the objects to the cluster C until the cluster C cannot be expanded, namely until the candidate set N is empty, and the cluster C is generated and output at the moment;
the next cluster is continued to be found, DBSCAN randomly selects an object from the remaining objects that has not been accessed, and the clustering process continues until all objects in a given data set D have been accessed.
Further, different weights are set for each cell in the ordinary station according to the residence time to mine the user residence cell, specifically: setting the weight condition of the cell in the permanent residence where the user is located according to the residence time, adding the weight parameter, and then removing the cell with the weight smaller than the set threshold; and resetting the cell weight in the cells, and selecting the cell with the highest weight in a set number to obtain the user resident cell.
Further, a resident cell scoring model based on frequency and duration is established, and the residence area of the residents is judged, specifically:
extracting all data of 23: 00-6: 00 time period of the next day from the continuous historical data to obtain all resident cell information of the user during the period, and assuming that the frequency of the user appearing in the cell c is fc_homeTotal dwell time of dc_homeAnd performing the following 0-1 standardization processing on the total frequency of occurrence and the total residence time of each user in all cells:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
so as to obtain the values of 0-1 standardized residence time length and total frequency of all users, which are respectively
The residential cell importance score is then:
wherein wfAnd wdWeights respectively representing the frequency number and the residence time length;
the weights are set using a multiple ring ratio method: randomly arranging all evaluation factors, comparing all the factors according to the sequence to obtain a multiple relation among the importance degrees of all the factors, namely a ring ratio, uniformly converting the ring ratio into a reference value, and finally performing normalization processing to determine the final weight of the factor; according to the weight algorithm, all the cell scores are ranked, the cell with the highest score is selected and projected to a nearby map, and the user residence is excavated.
Further, a resident cell scoring model based on frequency and duration is established, and a working place is judged, specifically:
extracting all working day data in the historical data to obtain all resident cell information of the user in the period, and assuming that the frequency of the user appearing in the cell c is fc_workTotal dwell time of dc_workPerforming 0-1 standardization to obtain values f of residence time and total frequency of all cells of the user after 0-1 standardizationc_work、dc_workAnd performing the following 0-1 standardization processing on the total frequency of occurrence and the total residence time of each user in all cells:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
thereby obtainingThe values of all the user residence time and the total frequency after 0-1 standardization are respectively
The workplace cell importance score is:
wherein wfAnd wdWeights respectively representing the frequency number and the residence time length;
the weights are set using a multiple ring ratio method: firstly, randomly arranging all evaluation factors, then comparing all the factors according to the sequence to obtain a multiple relation among the importance degrees of all the factors, namely a ring ratio, uniformly converting the ring ratio into a reference value, and finally carrying out normalization processing to determine the final weight of the reference value; and ranking the scores of all the cells according to the weight algorithm, selecting the cell with the highest score, and projecting the cell onto a map, namely the work place of the user.
The invention has the beneficial effects that: according to the user occupation analysis method based on the signaling data, after interference cells are eliminated by a weighting algorithm according to residence information of a user in a certain period of time, spatial clustering is carried out based on geographical position information, and the residence importance of the residence cells is further marked according to time limitation, so that the frequent residence information of the user is obtained. Further, after the user common station information is obtained, the common station information is labeled and classified according to the residence time distribution of the user common station, and therefore the information of the residence and the working place of the user is obtained. The method can excavate the user frequent site information of the user including the working place and the residence place, thereby facilitating the operator to pertinently and purposefully develop marketing work and carry out fixed-point marketing or network test on the user, which is very beneficial to broadband services, mobile phone network access and the like.
Drawings
Fig. 1 is a schematic diagram of residence distribution over a period of time based on latitude and longitude information in the embodiment.
FIG. 2 is a schematic diagram illustrating density reachability and density connectivity among density-based clusters in an example embodiment.
FIG. 3 is a schematic diagram illustrating the clustering algorithm in the embodiment.
FIG. 4 is a diagram illustrating the effect of density-based geo-clustering for a user.
Fig. 5 is a schematic diagram of the distribution of the user stay cells in the embodiment.
Fig. 6 is a schematic diagram of the user cell stay distribution after removing the interference cell in the embodiment.
Fig. 7 is a schematic diagram of user resident cell distribution in the embodiment.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Examples
A user occupation area analysis method based on signaling data specifically comprises the following steps:
according to the cell residence information of a user in a set time period, after eliminating interference cells by using a weight algorithm to obtain important user cells, carrying out spatial clustering based on geographical position information on the obtained important user cells, and dividing densely-appearing areas in the clustering into permanent locations;
setting different weights for each cell in the permanent station according to the residence time to mine the resident cells of the users;
after the resident cell of the user is obtained, a resident cell scoring model based on frequency and duration is established according to the resident time distribution of the user's permanent location, and the resident cell of the user is subjected to attribute division to obtain the information of the residence place and the working place of the user.
The embodiment is that the cell residence information comprises operator signaling data and employee's reference table geographical position data, and is intended to form a wide table by recording cell records such as cell identifiers (ECGI)/ECI, residence time and the like through a user residence 2/3/4G cell, associating cell employee's parameters such as cell identifiers (ECGI)/ECI, longitude, latitude and the like, and identifying the user frequent residence including a user residence and a work place through algorithm modeling according to the wide table.
The data source of the embodiment is resident 2/3/4G data of an operator user and a work parameter table of a base station of a certain geographic cell in a set time period, and comprises matching information of longitude and latitude of the cell and the geographic position.
And matching the longitude and latitude information of the cell according to the ECI of the cell where the user resides and the work participation table. For a user, a residence distribution map over a period of time based on latitude and longitude information is drawn, as shown in fig. 1. As shown in fig. 1, the geographical locations of users appearing in a period of time are mostly concentrated, and in order to excavate frequent residences of users, it is first necessary to remove the interference information of users.
And cleaning the interference cells and dividing the important cells of the users. In order to eliminate the interference of most users passing through cells back and forth between the ordinary residential cells and the extraordinary residential situation of frequent switching change of some sales and marketing personnel cells, firstly, the resident cells of the users in a period of time are calculated and ranked, the cells with the average resident time lower than a certain threshold value are cleaned and deleted, the interference cells are removed, and the important cells of the users are divided.
And clustering the cells based on the spatial distance. Since the cell shift caused by the user's small-scale movement and external wind direction may cause the user's cell change, it is more meaningful to find the user's resident geographical location. In order to achieve this, the important cells obtained after screening may be clustered based on the density spatial distance according to the resident cell information of the user, and the result is generally within 3 classes.
Embodiments cluster the residence locations of users using the DBSCAN algorithm, and the following is a description of the DBSCAN algorithm:
first, density-based clustering algorithms, in short, algorithms based on a process that continuously expands according to the density of objects. The density of one object O can be judged by the number of objects close to O.
The concepts in the examples are as follows:
-neighborhood: the parameter >0 is a field radius value for each object specified by the user, in a space with the object O as the center and the radius as the radius.
MinPts is the domain density threshold: number of objects of-neighborhood of objects.
Core object: an object is a core object if the number of objects in the-neighborhood of object O contains at least MinPts objects.
The direct density can reach: if object p is within-neighborhood of core object q, object p is directly density reachable from core object q.
The density can reach: in DBSCAN, object P is density reachable from core object q if there is a chain of objects P1,P2,P3,...,PnSo that P is1＝q,Pn＝p,Pi+1Is PiReachable from direct density with respect to MinPts, i.e. Pi+1At PiWithin the neighborhood of (1), then P1To PnThe density can be reached.
Density connection: if there is an object q ∈ D, let the object P1And P2Are all reachable from q with respect to the MinPts density, then P is called1And P2Is concerned with linking to the MinPts density.
The density can be achieved and described in connection with the density as shown in fig. 2, with a radius, MinPts 3; it can be seen from fig. 2 that m, p, o.r are all core objects, since they all contain only 3 objects.
1. Object q is directly density reachable from m. Object m is directly density reachable from p.
2. Object q is indirectly density reachable from p because q is directly density reachable from m, which is directly density reachable from p.
3. r and s are achievable from o density and o is achievable from r density, all of which are density-connected.
DBSCAN clustering process, as in fig. 3: initially, all objects in a given dataset D are marked as "not accessed", DBSCAN randomly selects an object p that is not accessed, marks object p as "accessed", and checks if the-neighborhood of object p contains at least MinPts objects. If not, object p is marked as a noise point. Otherwise, a new cluster is created for object pC and all objects in the-neighborhood of object p are placed in candidate set N. DBSCAN iteratively adds objects in the candidate set N that do not belong to other clusters to cluster C. In this process, the object P marked as "not visited" in the corresponding candidate set N*DBSCAN marks it as "visited" and checks its-neighborhood if object P*Is at least one MinPts object, object P*All objects in the neighborhood are added to the candidate set N. DBSCAN continues to add objects to cluster C until cluster C cannot expand, i.e., until candidate set N is empty. At this time, the cluster C is generated and output.
To find the next cluster, DBSCAN randomly selects an object that has not been accessed from the remaining objects. The clustering process continues until all objects have been accessed. The clustering effect is as shown in fig. 4, and the densely appearing areas in the cluster are divided into permanent locations.
And mining the resident cell of the user. In order to identify the user resident cells at a higher level, the user resident cells are mined by setting different weights to the cells in the regular premises according to the residence time.
Mining the resident user cell according to different weight setting algorithms of each user cell, which specifically comprises the following steps: firstly, the cell weight situation in the regular residence where the user is located is marked, and a certain user is taken as an example, and a weight parameter is added, as shown in fig. 5. Further, in order to more clearly find the user's resident cell and the distance between resident cells, an attempt is made to remove the cells with particularly small weights on the basis of the above steps, resulting in the following fig. 6, where fig. 6 is a distribution diagram of the user's cell staying after the interference cells are removed. It can be seen that the two larger cells in fig. 6 should be the user's resident cells of interest for the embodiment. In order to further mine the above two cells, the cell weights are reset in the above cells, and a cell with a higher weight is selected to obtain a resident cell, as shown in fig. 7.
Then, the user residence/work place is excavated. In order to judge the residence and the working place of residents, the resident cells of users need to be subjected to attribute division, and a resident cell scoring model based on frequency and duration is established, wherein the scoring model is specifically as follows:
extract 23 of the continuous historical data for each day: 00-day 6: all data in the period of 00 hours, and obtaining all resident cell information of the user in the period of 00 hours, and assuming that the frequency of the user in the cell c is fc_homeTotal dwell time of dc_homeAnd performing 0-1normalization (0-1normalization) processing on the total occurrence frequency and the total residence time of each user in all cells as follows:
where max is the maximum value of the sample data and min is the minimum value of the sample data. So as to obtain the values of 0-1 standardized residence time length and total frequency of all users, which are respectively
The residential cell importance score is then:
wherein wfAnd wdThe weights of the frequency count and the dwell time duration are respectively represented.
The weights are set using a multiple ring ratio method: the multiple ring ratio method firstly randomly arranges each evaluation factor, then compares each factor according to the sequence to obtain the multiple relation between the importance degrees of each factor, also called ring ratio, then uniformly converts the ring ratio into a reference value, and finally performs normalization processing to determine the final weight. The method needs to have objective judgment basis for evaluation factors and needs to have objective and accurate historical data as support. Taking the above four factors as examples, the following table 1 is shown.
Table 1 example weight setting results of weights using multiple loop ratio method
| Evaluation factor | A | B | C | D | Total up to |
| Ring ratio | 0.3 | 2 | 0.55 | 1 | |
| Reference value | 0.33 | 1.1 | 0.55 | 1 | 2.98 |
| Final weight | 0.1107 | 0.3691 | 0.1846 | 0.3356 | 1 |
Wherein, second row in table 1, 0.3 indicates that a is 0.3 times more important than B; 2 means that B is 2 times more important than C, 0.55 means that C is 0.55 times more important than D; 1 represents D itself. The third row, which is a ratio normalization based on D, takes the value 0.55 x 1 to 0.55 since C is 0.55 times as important as D; b is 2 times C, so the value is 0.55 x 2 to 1.1; the following analogy is made. The final weight is calculated by taking the total number as a denominator and each reference value as a numerator.
The method for determining the weight by the multiple ring ratio method is practical, simple in calculation and high in objective scientificity due to the fact that accurate historical data are used as supports.
According to the weight algorithm, all the cell scores are ranked, the cell with the highest score is selected and projected to a nearby map, and the user residence is excavated.
Extracting all working day data in the historical data to obtain all resident cell information of the user in the period, and assuming that the frequency of the user appearing in the cell c is fc_workTotal dwell time of dc_workIn the same way, the values f after 0-1 standardization of the residence time and the total frequency of all the cells of the user are obtained by 0-1 standardization (0-1 standardization) processingc_work、dc_workAnd performing the following 0-1 standardization processing on the total frequency of occurrence and the total residence time of each user in all cells:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
so as to obtain the values of 0-1 standardized residence time length and total frequency of all users, which are respectively
The workplace cell importance score is:
and ranking the scores of all the cells according to the weight algorithm, selecting the cell with the highest score, and projecting the cell onto a map, namely the work place of the user.
Claims (2)
1. A method for analyzing a user's place of employment based on signaling data, comprising:
according to the cell residence information of a user in a set time period, after eliminating interference cells by using a weight algorithm to obtain important user cells, carrying out spatial clustering based on geographical position information on the obtained important user cells, and dividing densely-appearing areas in the clustering into permanent locations;
setting different weights for each cell in the permanent station according to the residence time to mine the resident cells of the users;
after the resident cell of the user is obtained, establishing a resident cell scoring model based on frequency and duration according to the resident time distribution of the user's permanent location, and performing attribute division on the resident cell of the user to obtain the information of the residence and the working place of the user;
clearing the interference cells by using a weight algorithm, specifically, calculating and ranking the average residence time of the residence cells of a user in a set time period, cleaning and deleting the cells with the average residence time being lower than a certain threshold value, removing the interference cells, and dividing important cells of the user;
setting different weights for each cell in the ordinary station according to the residence time to mine the user resident cells, specifically comprising the following steps: setting the weight condition of the cell in the permanent residence where the user is located according to the residence time, adding the weight parameter, and then removing the cell with the weight smaller than the set threshold; resetting the cell weight in the above cells, and selecting the cell with the highest weight in a set number to obtain a user resident cell;
performing spatial clustering based on geographical position information on the obtained important user cells by adopting a representative clustering algorithm based on density, namely a DBSCAN algorithm, specifically comprising the following steps:
all objects in a given dataset D are marked as "not visited", one object p not visited is randomly selected, marked as "visited", and the p-neighborhood is checked for at least MinPts objects, if not, object p is marked as a noise point; otherwise, a new cluster C is created for p, and all objects in the neighborhood of p are placed in the candidate set N;
iteratively adding objects in the candidate set N that do not belong to other clusters to the cluster C; in this process, the object P marked as "not visited" in the corresponding candidate set N*DBSCAN marks object P' as "visited" and examines object P*If the object P is a neighborhood of*Is at least one MinPts object, object P*All objects in the neighborhood are added into the candidate set N, the DBSCAN continues to add the objects to the cluster C until the cluster C cannot be expanded, namely until the candidate set N is empty, and the cluster C is generated and output at the moment;
continuing to find the next cluster, randomly selecting an object which is not accessed from the rest objects by the DBSCAN, and continuing the clustering process until all the objects in the given data set D are accessed;
establishing a resident community scoring model based on frequency and duration, and judging the residential area of a resident, specifically comprising the following steps:
extracting all data of 23: 00-6: 00 time period of the next day from the continuous historical data to obtain all resident cell information of the user during the period, and assuming that the frequency of the user appearing in the cell c is fc_homeTotal dwell time of dc_homeAnd performing the following 0-1 standardization processing on the total frequency of occurrence and the total residence time of each user in all cells:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
so as to obtain the values of 0-1 standardized residence time length and total frequency of all users, which are respectively
The residential cell importance score is then:
wherein wfAnd wdWeights respectively representing the frequency number and the residence time length;
the weights are set using a multiple ring ratio method: randomly arranging all evaluation factors, comparing all the factors according to the sequence to obtain a multiple relation among the importance degrees of all the factors, namely a ring ratio, uniformly converting the ring ratio into a reference value, and finally performing normalization processing to determine the final weight of the factor; according to the weight algorithm, all the cell scores are ranked, the cell with the highest score is selected and projected to a nearby map, and the user residence is excavated.
2. The method for analyzing occupational locations of a user based on signaling data as claimed in claim 1, wherein: establishing a resident cell scoring model based on frequency and duration, and judging a working place, wherein the method specifically comprises the following steps:
extracting all working day data in the historical data to obtain all resident cell information of the user in the period, and assuming that the frequency of the user appearing in the cell c is fc_workTotal dwell time of dc_workPerforming 0-1 standardization to obtain values f of residence time and total frequency of all cells of the user after 0-1 standardizationc_work、dc_workAnd performing the following 0-1 standardization processing on the total frequency of occurrence and the total residence time of each user in all cells:
wherein max is the maximum value of the sample data, and min is the minimum value of the sample data;
so as to obtain the values of 0-1 standardized residence time length and total frequency of all users, which are respectively
The workplace cell importance score is:
wherein wfAnd wdWeights respectively representing the frequency number and the residence time length;
the weights are set using a multiple ring ratio method: firstly, randomly arranging all evaluation factors, then comparing all the factors according to the sequence to obtain a multiple relation among the importance degrees of all the factors, namely a ring ratio, uniformly converting the ring ratio into a reference value, and finally carrying out normalization processing to determine the final weight of the reference value; and ranking the scores of all the cells according to the weight algorithm, selecting the cell with the highest score, and projecting the cell onto a map, namely the work place of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611085317.5A CN106792514B (en) | 2016-11-30 | 2016-11-30 | User position analysis method based on signaling data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611085317.5A CN106792514B (en) | 2016-11-30 | 2016-11-30 | User position analysis method based on signaling data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106792514A CN106792514A (en) | 2017-05-31 |
| CN106792514B true CN106792514B (en) | 2020-10-30 |
Family
ID=58914775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611085317.5A Active CN106792514B (en) | 2016-11-30 | 2016-11-30 | User position analysis method based on signaling data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106792514B (en) |
Families Citing this family (51)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107369037A (en) * | 2017-06-27 | 2017-11-21 | 中国联合网络通信集团有限公司 | User's portrait acquisition methods and device |
| CN107547633B (en) * | 2017-07-27 | 2021-09-03 | 腾讯科技（深圳）有限公司 | User constant standing point processing method and device and storage medium |
| CN107484134B (en) * | 2017-10-17 | 2020-05-15 | 南京市城市与交通规划设计研究院股份有限公司 | Resident position analysis method and device |
| CN108260205B (en) * | 2017-12-07 | 2020-10-23 | 西安汇龙科技股份有限公司 | User position positioning system and method |
| CN110020221B (en) * | 2017-12-11 | 2022-02-18 | 腾讯科技（深圳）有限公司 | Job distribution confirmation method, apparatus, server and computer readable storage medium |
| CN109963253B (en) * | 2017-12-25 | 2020-11-20 | 中国移动通信集团上海有限公司 | Method and device for identifying geographic position of user residence |
| CN108717676B (en) * | 2018-04-23 | 2021-07-06 | 深圳市数字城市工程研究中心 | Multi-data fusion-based job and live space evaluation method and system under different scales |
| CN108650632B (en) * | 2018-04-28 | 2020-05-26 | 广州市交通规划研究院 | Stagnation point judgment method based on occupational correspondence and time-space kernel clustering |
| CN110737848A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Mining processing method and device for user work unit and electronic equipment |
| CN110674208B (en) * | 2018-07-03 | 2022-12-02 | 百度在线网络技术（北京）有限公司 | Method and device for determining position information of user |
| CN108898445A (en) * | 2018-07-12 | 2018-11-27 | 智慧足迹数据科技有限公司 | The analysis method and device of customer consumption ability |
| CN109672715A (en) * | 2018-09-13 | 2019-04-23 | 深圳壹账通智能科技有限公司 | User's permanent residence judgment method, device, equipment and computer readable storage medium |
| 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 |
| CN109525637B (en) * | 2018-10-15 | 2020-04-10 | 北京创鑫旅程网络技术有限公司 | Method and device for determining permanent station |
| CN111126653B (en) * | 2018-11-01 | 2022-06-17 | 百度在线网络技术（北京）有限公司 | User position prediction method, device and storage medium |
| CN111127065B (en) * | 2018-11-01 | 2023-07-25 | 百度在线网络技术（北京）有限公司 | User job site acquisition method and device |
| CN111263311B (en) * | 2018-11-30 | 2021-07-30 | 中国移动通信集团湖南有限公司 | Resident physical cell identification method and device |
| 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 |
| CN109362041B (en) * | 2018-12-18 | 2021-06-04 | 成都方未科技有限公司 | Population space-time distribution analysis method based on big data |
| CN111417075B (en) * | 2018-12-18 | 2023-06-06 | 北京融信数联科技有限公司 | User workplace identification method based on mobile communication big data |
| CN109743693A (en) * | 2018-12-21 | 2019-05-10 | 中国联合网络通信集团有限公司 | Information recommendation method, device and storage medium |
| CN109840872A (en) * | 2019-01-08 | 2019-06-04 | 福建福诺移动通信技术有限公司 | A method of commuting model in city is calculated based on operator's signaling data |
| CN109982257B (en) * | 2019-02-27 | 2021-03-23 | 中国联合网络通信集团有限公司 | Method, device and system for determining mobile user home region |
| CN110213714B (en) * | 2019-05-10 | 2020-08-14 | 中国联合网络通信集团有限公司 | Terminal positioning method and device |
| CN110324787B (en) * | 2019-06-06 | 2020-10-02 | 东南大学 | Method for acquiring occupational sites of mobile phone signaling data |
| CN112218230B (en) * | 2019-06-24 | 2023-03-24 | 中兴通讯股份有限公司 | Method and device for acquiring user resident position and computer readable storage medium |
| 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 |
| CN110418287B (en) * | 2019-07-12 | 2021-06-01 | 重庆市交通规划研究院 | Population residence migration identification method based on mobile phone signaling |
| CN110351734B (en) * | 2019-08-12 | 2023-02-17 | 桔帧科技(江苏)有限公司 | Method for realizing prediction of cell position based on mobile terminal data |
| CN110659320B (en) * | 2019-09-02 | 2022-08-09 | 恩亿科(北京)数据科技有限公司 | Analysis method and analysis device for occupational distribution and readable 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 |
| CN111198972B (en) * | 2019-12-30 | 2023-05-09 | 中国联合网络通信集团有限公司 | User job place identification method, device, control equipment and storage medium |
| CN112561759B (en) * | 2020-01-02 | 2023-08-04 | 北京融信数联科技有限公司 | Graduate forward dynamic monitoring method based on mobile signaling big data |
| CN111080176A (en) * | 2020-01-08 | 2020-04-28 | 浙江省农业科学院 | Comprehensive evaluation method and system for quality and safety of agricultural products |
| CN111241225B (en) * | 2020-01-10 | 2023-08-08 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for judging change of resident area |
| CN111291092A (en) * | 2020-02-14 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Data processing method, device, server and storage medium |
| CN113286333B (en) * | 2020-02-19 | 2022-08-19 | 华为技术有限公司 | Network selection method and device |
| CN111641688B (en) * | 2020-05-20 | 2022-09-02 | 成都众树信息科技有限公司 | Member marketing system based on mobile signaling |
| CN111815361A (en) * | 2020-07-10 | 2020-10-23 | 北京思特奇信息技术股份有限公司 | Region boundary calculation method and device, electronic equipment and storage medium |
| CN112085268B (en) * | 2020-08-31 | 2024-03-05 | 北京百度网讯科技有限公司 | Method, device, equipment and readable storage medium for measuring and calculating resident trip information |
| CN112105052B (en) * | 2020-09-14 | 2021-05-14 | 智慧足迹数据科技有限公司 | Building type determination method, building type determination device, server and storage medium |
| CN113052425A (en) * | 2020-10-14 | 2021-06-29 | 中国联合网络通信集团有限公司 | Rework risk index determination method and device based on big data |
| CN114363825B (en) * | 2021-05-26 | 2023-08-29 | 科大国创云网科技有限公司 | Building attribute identification method and system based on MR (magnetic resonance) resident site |
| CN113347574B (en) * | 2021-06-03 | 2023-04-07 | 中国联合网络通信集团有限公司 | Method and device for determining ordinary station |
| CN113613174A (en) * | 2021-07-09 | 2021-11-05 | 中山大学 | Method, device and storage medium for identifying occupational sites based on mobile phone signaling data |
| CN113935881A (en) * | 2021-12-16 | 2022-01-14 | 北京融信数联科技有限公司 | Population structure analysis method and system based on big data and readable storage medium |
| 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 |
| CN114219379B (en) * | 2022-02-22 | 2022-05-24 | 北京融信数联科技有限公司 | Resource matching evaluation method and system suitable for community service circle |
| CN115550843B (en) * | 2022-04-19 | 2023-10-20 | 荣耀终端有限公司 | Positioning method and related equipment |
| CN116033354B (en) * | 2022-12-16 | 2023-07-21 | 中科世通亨奇(北京)科技有限公司 | Analysis method and system for user position attribute information |
| CN117014803A (en) * | 2023-07-06 | 2023-11-07 | 荣耀终端有限公司 | Positioning method, recommending method, readable medium and electronic device |
Citations (10)
| 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 |
| CN102607553A (en) * | 2012-03-06 | 2012-07-25 | 北京建筑工程学院 | Travel track data-based stroke identification method |
| CN102629297A (en) * | 2012-03-06 | 2012-08-08 | 北京建筑工程学院 | Traveler activity rule analysis method based on stroke recognition |
| CN104159189A (en) * | 2013-05-15 | 2014-11-19 | 同济大学 | Resident trip information obtaining method based on intelligent mobile phone |
| 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 |
| CN105513348A (en) * | 2015-11-27 | 2016-04-20 | 西南交通大学 | Mobile phone signaling trip chain-based OD matrix acquisition method |
| CN105657666A (en) * | 2016-03-31 | 2016-06-08 | 东南大学 | Commercial employee group residence recognition method based on mobile phone positioning data |
| CN105682025A (en) * | 2016-01-05 | 2016-06-15 | 重庆邮电大学 | User residing location identification method based on mobile signaling data |
| CN105847310A (en) * | 2015-01-13 | 2016-08-10 | 中国移动通信集团江苏有限公司 | Position determination method and apparatus |
| CN105989226A (en) * | 2015-02-12 | 2016-10-05 | 中兴通讯股份有限公司 | Method and apparatus for analyzing track of user |
-
2016
- 2016-11-30 CN CN201611085317.5A patent/CN106792514B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102607553A (en) * | 2012-03-06 | 2012-07-25 | 北京建筑工程学院 | Travel track data-based stroke identification method |
| CN102629297A (en) * | 2012-03-06 | 2012-08-08 | 北京建筑工程学院 | Traveler activity rule analysis method based on stroke recognition |
| 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 |
| CN104159189A (en) * | 2013-05-15 | 2014-11-19 | 同济大学 | Resident trip information obtaining method based on intelligent mobile phone |
| CN105847310A (en) * | 2015-01-13 | 2016-08-10 | 中国移动通信集团江苏有限公司 | Position determination method and apparatus |
| CN105989226A (en) * | 2015-02-12 | 2016-10-05 | 中兴通讯股份有限公司 | Method and apparatus for analyzing track of user |
| 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 |
| CN105513348A (en) * | 2015-11-27 | 2016-04-20 | 西南交通大学 | Mobile phone signaling trip chain-based OD matrix acquisition method |
| CN105682025A (en) * | 2016-01-05 | 2016-06-15 | 重庆邮电大学 | User residing location identification method based on mobile signaling data |
| CN105657666A (en) * | 2016-03-31 | 2016-06-08 | 东南大学 | Commercial employee group residence recognition method based on mobile phone positioning data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106792514A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106792514B (en) | User position analysis method based on signaling data | |
| CN107547633B (en) | User constant standing point processing method and device and storage medium | |
| CN108282860B (en) | Data processing method and device | |
| Vieira et al. | Characterizing dense urban areas from mobile phone-call data: Discovery and social dynamics | |
| EP3132592B1 (en) | Method and system for identifying significant locations through data obtainable from a telecommunication network | |
| US8577380B2 (en) | Method for an automatic identification of urban dense areas from cell phones records | |
| CN110856186B (en) | Method and system for constructing wireless network knowledge graph | |
| Logan et al. | Identifying and bounding ethnic neighborhoods | |
| CN106326923B (en) | A kind of position data clustering method of registering taking position into account and repeating with density peaks point | |
| CN110825883A (en) | Knowledge graph-based hybrid group discovery method | |
| CN108733774B (en) | Dynamic monitoring method for unemployed population based on big data | |
| CN112328728A (en) | Clustering method and device for mining traveler track, electronic device and storage medium | |
| Li et al. | A framework for spatial interaction analysis based on large-scale mobile phone data | |
| CN108647189B (en) | Method and device for identifying user crowd attributes | |
| CN110446161A (en) | User identity identification method, device, equipment and storage medium | |
| CN114595300A (en) | Active chain reconstruction method and system combining multi-source space-time data | |
| CN110990722B (en) | Fuzzy co-site analysis method and system based on big data mining | |
| CN110913408B (en) | Indoor weak coverage positioning analysis method and system based on MRO | |
| Shad et al. | Precise location acquisition of mobility data using cell-id | |
| Qiu et al. | Classifying urban fabrics into mobile call activity with supervised machine learning | |
| Xing et al. | Traffic zone division using mobile billing data | |
| Zhang et al. | Mobile traffic data decomposition for understanding human urban activities | |
| Kwon et al. | A novel location prediction scheme based on trajectory data | |
| CN109951848B (en) | Regional wireless cell determining method, device, equipment and medium | |
| CN106851669A (en) | A kind of wireless site Valuation Method and system |
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 |