CN104217087B - A kind of permanent resident population's analysis method based on carrier network data - Google Patents
A kind of permanent resident population's analysis method based on carrier network data Download PDFInfo
- Publication number
- CN104217087B CN104217087B CN201310204412.2A CN201310204412A CN104217087B CN 104217087 B CN104217087 B CN 104217087B CN 201310204412 A CN201310204412 A CN 201310204412A CN 104217087 B CN104217087 B CN 104217087B
- Authority
- CN
- China
- Prior art keywords
- data
- population
- permanent resident
- network data
- resident population
- 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
Abstract
The present invention relates to a kind of permanent resident population's analysis method based on carrier network data, it applies the main thought of ant group algorithm on the basis of the carrier network data of collection, the network data of user crowd in certain area is counted, according to the position of its appearance, time index is classified, computing is carried out by the given obtained result of function transform pairs above-mentioned factor statistical analysis, as a judging basis of population classification, so as to be iterated amendment to the characteristic value (permanent resident population) of crowd, and return to new evaluation result.The present invention overcomes original statistical classification method Return Difference, convergence slowly, and for abnormal data quite sensitive, it be easy to cause and judges by accident and the shortcomings that failing to judge；Few with desired sample data, initial value requirement is inaccurate, the characteristics of being modified at any time according to data；Divide the permanent resident population in region and more really react present situation.
Description
Technical field
The invention belongs to data mining analysis technical field, and in particular to a kind of permanent people based on carrier network data
Mouth analysis method, it can accurately judge the population classification in a certain region, i.e., which is permanent resident population, is relevant departments
Grasp timely, accurate, effective data.
Background technology
Population situation is complicated in specific region at present, and movement of population is complicated, and national correlation department often only grasps static letter
Breath, these information often lag, and renewal is not in time, it is impossible to provides good technical support for relevant Decision.Traditional permanent people
Mouthful analysis method often uses fairly simple model, from intuitively concept, such as think permanent resident population be usually all
The data fixed locality are presented at night, and the mechanics on daytime is just more complicated, gives up this situation and is analyzed.With
Townie variation, the reaction present situation that this mechanics can not be exactly accurate.In addition, traditional statistical method will
The sample of acquisition is sufficiently large and enough, and Return Difference, convergence are slow, and for abnormal data quite sensitive, be easy to cause erroneous judgement,
Fail to judge.
Ant group algorithm is a kind of probability type algorithm for being used for finding path optimizing in figure.It is former that the algorithm is based on positive feedback
Reason, has the advantages that good strong robustness, convergence, concurrency and adaptivity, just be used to solving most of optimization problems or
Person can be converted into the problem of Optimization Solution.With ant group algorithm continue to develop and it is perfect, its application field has expanded at present
Multiple-objection optimization, data classification, data clusters, pattern-recognition, system modelling, flow layout, signal processing, image procossing, certainly
Plan support and emulation and System Identification etc..Ant group algorithm is highly suitable for user group's behavior spy with its plurality of advantages
The classification of sign.In addition, a large number of users data that operator grasps, can come as another data of real-time analysis population classification
Source.
The content of the invention
In view of this, it is an object of the invention to for deficiency of the prior art, using ant group algorithm, with reference to operator
Mass data, there is provided a kind of permanent resident population's analysis method based on carrier network data, calculates listener clustering.
To complete above-mentioned purpose, the technical solution adopted by the present invention is：On the basis of the carrier network data of collection
Using the main thought of ant group algorithm, the network data of the user crowd in certain area is counted, according to its appearance
Position, time index are classified, and are transported by the given obtained result of function transform pairs above-mentioned factor statistical analysis
Calculate, as a judging basis of population classification, so that amendment is iterated to the characteristic value (permanent resident population) of crowd, and
Return to new evaluation result.Specifically, the present invention provides a kind of permanent resident population analysis side based on carrier network data
Method, comprises the following steps：
Step A：The initial number in defined area is obtained at the Community Population information grasped from Census information, local police station
According to；
Step B：Historical data and real time data are obtained at operator, when the content of data includes collection number, collection
Between, collecting location；
Step C：Classified according to the position of user data appearance, time, and by given functional transformation, to operation
Quotient data and primary data carry out the matching analysis that iterates, so that initial data is divided into two major classes, one kind is can be preliminary
Definite, another kind of is the data of unusual fluctuation, i.e., new supplementary data caused by being lacked due to initial data；
Step D：Analyzed for functional transformation, introduce mechanics model, these models are dynamically added to knowledge knowledge network
In network, model includes：Peak period rule model, period at night rule model, festivals or holidays rule model and weather bar on and off duty
Part rule model；
Step E：According to the knowledge network enriched constantly, the data gathered in real time further according to operator, make amendment, pass through
The comentropy concept of ant group algorithm is further classified user.
The beneficial effects of the present invention are：1. overcome original statistical classification method Return Difference, convergence slowly, and for different
Regular data quite sensitive, the shortcomings that be easy to causeing erroneous judgement and fail to judge；2. few with desired sample data, initial value requires not smart
Really, the characteristics of being modified at any time according to data, while external factor can also be introduced well, such as census letter
The external data typings such as breath, corresponding weighted value can be dynamically adjusted to different factors.
Brief description of the drawings
The present invention is further described below in conjunction with the accompanying drawings.
Fig. 1 is the principle schematic of permanent resident population's analysis method of the invention based on carrier network data.
Embodiment
Illustrate as shown in Figure 1 for the principle of permanent resident population's analysis method provided by the invention based on carrier network data
Figure, its analysis method, comprises the following steps：
Step A：The initial number in defined area is obtained at the Community Population information grasped from Census information, local police station
According to；
Step B：Historical data and real time data are obtained at operator, when the content of data includes collection number, collection
Between, collecting location；Granularity when small (generally 2) of data acquisition, when data are more, judging basis are more accurate；
Step C：Classified according to the position of user data appearance, time, and by given functional transformation, to operation
Quotient data and primary data carry out the matching analysis that iterates, so that initial data is divided into two major classes, one kind is can be preliminary
Definite, another kind of is the data of unusual fluctuation, i.e., new supplementary data caused by being lacked due to initial data；
Step D：Analyzed for functional transformation, introduce mechanics model, these models are dynamically added to knowledge knowledge network
In network, model includes：Peak period rule model, period at night rule model, festivals or holidays rule model and weather bar on and off duty
Part rule model；
Peak period rule model on and off duty：In this period, operator's gathered data frequency increases, it is considered that up and down
Most of daylight hours outside class, permanent resident population are movable not in one's respective area.
Period at night rule model：Traditionally, it is that differentiation is fairly simple at night, because of the activity work and rest rule table of people
It is bright, all it is at night the time of having a rest, the data of collection can be very good to meet this feature.
Festivals or holidays rule model：This mechanics is the experience according to former years, and during festivals or holidays, permanent resident population is customary
Plan of travel.
Weather conditions rule model：The mechanics of people, such as big rainy day are also influenced when harsh weather occurs
People tend to unmovable in the street.
Step E：According to the knowledge network enriched constantly, the data gathered in real time further according to operator, make amendment, pass through
The comentropy concept of ant group algorithm is further classified user.
In above-mentioned steps, it according to external data is foundation that the initial value of functional transformation, which is, and the proportion that these factors take is
Constantly it is modified according to the data in later stage.The model of functional transformation be also dynamic adjustment, be by original external data not
It is disconnected to be rejected, a process of refinement.
The present invention considers the discriminating and analysis of bad data in data analysis process；Consider several frequently seen influence people
The factor of group's mechanics, such as work and rest on daytime, day off, festivals or holidays, extreme weather；Consider in time in certain time
Shortage of data, system can carry out auto-complete according to knowledge network automatically, and according to follow-up fructufy when corrects this and knows
Know network.It is shown experimentally that, the method makes permanent resident population's division in region more really react present situation, in real-time
On be also guaranteed.
Above embodiment is to illustrate the invention and not to limit the present invention, those skilled in the art couple
The equivalent variations of above-described embodiment progress, replace all within claims.
Claims (1)
- A kind of 1. permanent resident population's analysis method based on carrier network data, it is characterised in that：Comprise the following steps：Step A:Obtained at the Community Population information grasped from census data information and local police station initial in defined area Data；Step B:Obtain historical data and real time data at operator, the contents of data include collection number, acquisition time and Collecting location；Step C:The position and time occurred according to user data is classified, and by given functional transformation, to operator Data and primary data carry out the matching analysis that iterates, so that initial data is divided into two major classes, one kind is can be tentatively true Fixed, another kind of is the data of unusual fluctuation, i.e., new supplementary data caused by being lacked due to initial data；Wherein, the functional transformation Initial value using external data as foundation, and be constantly modified according to the data in later stage；Step D:Analyzed for functional transformation, introduce mechanics model, these models are dynamically added in knowledge network, Model includes：Peak period rule model, period at night rule model, festivals or holidays rule model and weather conditional plan on and off duty Model：Step E:According to the knowledge network enriched constantly, the data gathered in real time further according to operator, make amendment, pass through ant colony The comentropy concept of algorithm is further classified user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310204412.2A CN104217087B (en) | 2013-05-29 | 2013-05-29 | A kind of permanent resident population's analysis method based on carrier network data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310204412.2A CN104217087B (en) | 2013-05-29 | 2013-05-29 | A kind of permanent resident population's analysis method based on carrier network data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104217087A CN104217087A (en) | 2014-12-17 |
| CN104217087B true CN104217087B (en) | 2018-05-15 |
Family
ID=52098573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310204412.2A Active CN104217087B (en) | 2013-05-29 | 2013-05-29 | A kind of permanent resident population's analysis method based on carrier network data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104217087B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104361658B (en) * | 2014-09-30 | 2017-05-31 | 北京锐安科技有限公司 | The detection method and device of a kind of region Nei Ge places people information |
| CN106332052B (en) * | 2016-08-30 | 2019-12-31 | 上海新炬网络技术有限公司 | Micro-area public security early warning method based on mobile communication terminal |
| CN106709840B (en) * | 2016-12-06 | 2020-09-15 | 上海云砥信息科技有限公司 | Urban permanent population estimation method based on mobile network data |
| CN109784321A (en) * | 2019-03-28 | 2019-05-21 | 北京深醒科技有限公司 | A kind of real population statistical classification method and apparatus based on recognition of face |
| CN110807546A (en) * | 2019-10-22 | 2020-02-18 | 恒大智慧科技有限公司 | Community grid population change early warning method and system |
| CN110807547A (en) * | 2019-10-22 | 2020-02-18 | 恒大智慧科技有限公司 | Method and system for predicting family population structure |
| CN112000874A (en) * | 2020-06-29 | 2020-11-27 | 福建慧政通信息科技有限公司 | Digital twin city population management method and storage device |
| CN113938318B (en) * | 2021-12-01 | 2023-12-12 | 上海哔哩哔哩科技有限公司 | Method and device for determining live broadcast room brushing amount |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101394595A (en) * | 2008-08-22 | 2009-03-25 | 中兴通讯股份有限公司 | Permanent resident recognition method and system in mobile communication positioning type service |
| CN102592236A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertising crowd analysis system and analysis method |
| CN103106615A (en) * | 2013-01-28 | 2013-05-15 | 上海交通大学 | Excavated user behavior analysis method based on television watching log |
-
2013
- 2013-05-29 CN CN201310204412.2A patent/CN104217087B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101394595A (en) * | 2008-08-22 | 2009-03-25 | 中兴通讯股份有限公司 | Permanent resident recognition method and system in mobile communication positioning type service |
| CN102592236A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertising crowd analysis system and analysis method |
| CN103106615A (en) * | 2013-01-28 | 2013-05-15 | 上海交通大学 | Excavated user behavior analysis method based on television watching log |
Non-Patent Citations (2)
| Title |
|---|
| 基于移动通信数据处理的公安流动人口管理系统设计与研究;王大力;《中国优秀硕士学位论文全文数据库 信息科技辑》;20080315(第03期);摘要、第2.1.1节 * |
| 基于群体分类的自适应蚁群算法;英恒松等;《计算机工程与设计》;20070808;第28卷(第15期);第3668-3669、3689页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104217087A (en) | 2014-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104217087B (en) | A kind of permanent resident population's analysis method based on carrier network data | |
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| CN101465059B (en) | Early-warning system for inspecting and judging urban road traffic safety situation | |
| CN104156403B (en) | A kind of big data normal mode extracting method and system based on cluster | |
| CN108596386A (en) | A kind of prediction convict repeats the method and system of crime probability | |
| CN107656987B (en) | Subway station function mining method based on L DA model | |
| CN104331502B (en) | The recognition methods of courier's data in being marketed for courier periphery crowd | |
| CN101853291A (en) | Data flow based car fault diagnosis method | |
| CN106332052B (en) | Micro-area public security early warning method based on mobile communication terminal | |
| CN105467449B (en) | Deep layer Thin oil sandwich quantitatively characterizing method based on earthquake classification Sensitive Attributes fusion | |
| CN104680542A (en) | Online learning based detection method for change of remote-sensing image | |
| CN104036360A (en) | User data processing system and processing method based on magcard attendance behaviors | |
| CN105426441B (en) | A kind of automatic preprocess method of time series | |
| CN109684373A (en) | Emphasis party based on trip and call bill data analysis has found method | |
| CN107301604A (en) | Multi-model fusion estimation system | |
| CN106067079A (en) | A kind of system and method for gray haze based on BP neutral net prediction | |
| CN110458082A (en) | A kind of city management case classification recognition methods | |
| CN103177114A (en) | Cross-data-field shift learning sorting method based on differential manifolds | |
| CN105893352A (en) | Air quality early-warning and monitoring analysis system based on big data of social network | |
| CN107766500A (en) | The auditing method of fixed assets card | |
| CN115907822A (en) | Load characteristic index relevance mining method considering region and economic influence | |
| CN109166012A (en) | The method and apparatus of classification and information push for stroke predetermined class user | |
| CN112699955A (en) | User classification method, device, equipment and storage medium | |
| CN108053646A (en) | Traffic characteristic acquisition methods, Forecasting Methodology and system based on time-sensitive feature | |
| CN109389240A (en) | Trip mode discrimination method based on big data machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201104, Shanghai, Minhang District, No. 168, building No. 202, room 5 Patentee after: Shanghai Zaide Information Technology Co., Ltd Address before: 201104, Shanghai, Minhang District, No. 168, building No. 202, room 5 Patentee before: SHANGHAI ZAIDE INFORMATION SCIENCE & TECHNOLOGY CO., LTD. |
|
| CP01 | Change in the name or title of a patent holder |