CN108171532A - A kind of user group distribution forecasting method and system - Google Patents
A kind of user group distribution forecasting method and system Download PDFInfo
- Publication number
- CN108171532A CN108171532A CN201711303977.0A CN201711303977A CN108171532A CN 108171532 A CN108171532 A CN 108171532A CN 201711303977 A CN201711303977 A CN 201711303977A CN 108171532 A CN108171532 A CN 108171532A
- Authority
- CN
- China
- Prior art keywords
- user
- user group
- region
- data
- accounting
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of user group distribution forecasting method and system.Method includes the following steps：(10) geographic area divides：Using existing geographical location information, geographic area division is carried out to city；(20) current dwell regions determine：It collects, record customer position information, and its coordinate position is updated according to setting renewal frequency, judges the current dwell regions of the user；(30) user group is predicted：The user for calculating each region different time is detained quantitative proportion, utilizes the flow tendency of user group between the quantity of user group in data with existing prediction following each some period of region and region；System includes user terminal (101), data collection module (201), geodata library module (202), data computation module (203), data-mining module (204) and database server (205).The user group distribution forecasting method and system of the present invention can effectively predict user group distribution, not be related to individual privacy.
Description
Technical field
The invention belongs to personnel positioning big data applied technical field, particularly a kind of effectively prediction user group is distributed, no
It is related to the user group distribution forecasting method and system of individual privacy.
Background technology
By means of GPS positioning technology, the user that can have GPS functional mobile phones to holding is accurately positioned.It is mobile fixed
Position provides various useful services, such as navigation feature for individual consumer, with reference to geographical database information, can be carried for user
For very useful help.
In order to from the mechanics of macroscopic perspective analysis crowd, all customer position informations are collected, are recorded and are divided
Analysis just necessitates.
However, in the existing method, the event trace being substantially for individual subscriber recorded, is analyzed and not
Carry out movement tendency to be predicted or predicted in the probability that certain region occurs for some user.It is examined from secure context
Consider, be related to the individual privacy of user, it is bad to conduct a research.There are also method, be for same type of personal behavior into
Row data analysis and excavation, so as to from macroscopic perspective, obtain statistical result.
It is however, existing there is not yet personnel's flow for some region (such as shopping centre, Office Area, park) carries out
Analysis and prediction, and it is not related to the open report of the method for individual privacy.
Invention content
The purpose of the present invention is to provide a kind of user group distribution forecasting methods, effectively predict user group distribution, are not related to
Individual privacy.
Another object of the present invention is to provide a kind of user group forecast of distribution system.
Realize the object of the invention technical solution be：
Kind user group distribution forecasting method, which is characterized in that include the following steps：
(10) geographic area divides：Using existing geographical location information, geographic area division is carried out to city, divides ground
It manages region and includes living area, workspace, shopping centre and main block；
(20) current dwell regions determine：It collects, record customer position information, and it is updated according to setting renewal frequency
Coordinate position with reference to the coordinate got and existing geographical location information, judges the current dwell regions of the user；
(30) user group is predicted：The user for calculating each region different time is detained quantitative proportion, utilizes data with existing
The quantity of user group in prediction following each some period of region, and between region user group flow tendency.
The technical solution for realizing another object of the present invention is：
A kind of user group forecast of distribution system, which is characterized in that including：
User terminal (101), the smart mobile phone for having GPS functions is held including user, for data collection module
(201) customer position information is sent；
Data collection module (201), for according to pre-set frequency, collecting customer mobile terminal periodically and uploading
Customer position information, customer position information is then sent to database server (205)；
Geodata library module (202), for prestoring the cartographic information in target cities region, and to the quotient in region
Industry square, resident living area, Office Area etc. carry out region division；
Data computation module (203), for combining the user information and geographical data bank in database server (205)
Cartographic information in module (202) calculates active user's quantity accounting in each region of current time, and will currently use
Amount amount accounting is sent to database server (205)；
Data-mining module (204) accounts for for reading number of users in each region from database server (205)
Than the record value changed over time, by means of data mining algorithm, to each zone user quantity accounting in some following period
It is predicted, and prediction number of users accounting is sent to database server (205)；
Database server (205), for storing customer position information, active user's quantity accounting, prediction number of users
Accounting.
Compared with prior art, the present invention its remarkable advantage is：
1st, effectively prediction user group distribution：The method of the present invention utilizes given data, to personnel's number in Future targets region
Amount ratio is made prediction, and the existing method analyzed user group behavior does not propose prediction algorithm；
2nd, it is not related to individual privacy：The method of the present invention does not study the mechanics of single user, but goal in research region
The flowing law of interior all personnel not may be useful for the worry of family privacy.
3rd, it is widely used：The present invention, which only proposes, makes personnel's flow in target area analysis prediction, but be based on receiving
The potential value that the data collected are analyzed is more than that, can also between main region (as After Hours, Ren Yuanyou
Workspace to shopping centre, the proportion of flow in living area) flow of personnel ratio makes prediction, and or to personnel in specified region
The high ebb of flow is analyzed and predicted.
The present invention is described in further detail with reference to the accompanying drawings and detailed description.
Description of the drawings
Fig. 1 is the main flow chart of user group distribution forecasting method of the present invention.
Fig. 2 is the structure diagram of user group forecast of distribution system of the present invention.
Fig. 3 is that main region divides schematic diagram.
Fig. 4 is that regional edge dividing value illustrates schematic diagram.
Fig. 5 is the schematic diagram that user group is flowed from commercial square to other regions.
Fig. 6 is the prediction schematic diagram of user group accounting in commercial square a-quadrant in embodiment.
Specific embodiment
As shown in Figure 1, user group distribution forecasting method of the present invention, includes the following steps：
(10) geographic area divides：Using existing geographical location information, geographic area division is carried out to city, divides ground
It manages region and includes living area, workspace, shopping centre and main block；
Main region divides as shown in Figure 3.The cartographic information of target area is prestored, and combines map datum and believes
Breath, its boundary value is divided, numbered and is determined to each component part in region.To commercial square, Technology Park, Ju Minsheng
Cell living etc. is respectively with A, B, C, D expressions.
Regional edge dividing value explanation is as shown in Figure 3.
Building area generally exists with approximate rectangular for main shape, as shown in figure 4, by taking commercial square A as an example, side
Dividing value x1, x2, y1, y2 can be obtained by the cartographic information deposited.For the user data information of any one upload
(x, y) meets 1≤x of condition xa≤1≤y of xa 2and ya≤ya 2, then the location of the user is in a-quadrant.
(20) current dwell regions determine：It collects, record customer position information, and it is updated according to setting renewal frequency
Coordinate position with reference to the coordinate got and existing geographical location information, judges the current dwell regions of the user；
(20) current dwell regions determine that step includes：
(21) user location is collected：The GPS data of user hand generator terminal is acquired to determine its more specific location information；
(22) user position update：Setting renewal frequency on demand carries out the GPS data of user such as per half an hour primary
Update；
(23) user's dwell regions judge：Compare the GPS location data of user and the main coverage area built in map,
Judge the band of position that user is belonged at current time.
(30) user group is predicted：The user for calculating each region different time is detained quantitative proportion, utilizes data with existing
The quantity of user group in prediction following each some period of region, and between region user group flow tendency.
(30) the user group prediction steps include：
(31) user is detained quantitative proportion and calculates：Assuming that user group sum immobilizes, each GPS data collection is completed
Afterwards, total number of users amount in each region is counted, it is calculated and accounts for the percentage of sum；
(32) user group quantitative forecast：Record daily with region simultaneously between section user group quantity, to the following region
User group quantity is predicted；
(33) user group flow tendency is predicted：The user group accounting in region of daily T1, T2 moment is recorded, with reference to single
Change in location situation of the user at T1, T2 moment, in following several days, (T2-T1) in the period user group in each main building
Flow tendency in region.
The schematic diagram that user group is flowed from commercial square to other regions is as shown in Figure 4.
As shown in Fig. 2, user group forecast of distribution system of the present invention, including：
User terminal (101), the smart mobile phone for having GPS functions is held including user, for data collection module
(201) customer position information is sent；
Data collection module (201), for according to pre-set frequency, collecting customer mobile terminal periodically and uploading
Customer position information, customer position information is then sent to database server (205)；
The customer position information includes user identifier, current time value, the warp of GPS positioning, latitude numerical value.It is described
For distinguishing the data information of different user individual, the smart mobile phone for having GPS functions is held including user for user identifier
IMEI.
Structure type as shown in table 1 below can be used in the data structure of customer position information.
The data structure table of 1 customer position information of table
| User identifier ID | Longitude x | Dimension values y | Time t |
The data of longitude x, dimension values y and time t can be obtained by GPS.
Geodata library module (202), for prestoring the cartographic information in target cities region, and to the quotient in region
Industry square, resident living area, Office Area etc. carry out region division；
Data computation module (203), for combining the user information and geographical data bank in database server (205)
Cartographic information in module (202) calculates active user's quantity accounting in each region of current time, and will currently use
Amount amount accounting is sent to database server (205)；
Data processing explanation is carried out with reference to table 2.
Location information based on user data determines the zone number belonging to each user current location；
The current time user in each region and the variation of last moment number of users are compared, provides flow of the people in a week
Flow tendency in phase；
The attributed region of the last moment user can be read from database server 205, all when initial
NULL；
There are calculating data above, the user that can easily count in each region is detained quantity, obtains it
The percentage of shared total number of persons；
2 data computation module function of table
| User identifier ID | Data information | Last moment attributed region | Current time attributed region | Flow tendency |
| 1 | (x1,y1,t1) | A | A | NULL |
| 2 | (x2,y2,t2) | A | B | A->B |
| 3 | (x3,y3,t3) | A | C | A->C |
| 4 | (x4,y4,t4) | A | D | A->D |
| 5 | (x5,y5,t5) | B | A | B->A |
In order to improve data calculating efficiency, the present invention in user group be distributed judgment method, can also be by means of k- most
The thought of classification is closed on, i.e., if the point around unknown sample belongs to a certain region substantially, then the unknown sample is current
Moment is also detained in this region.Here proximity selects Euclidean distance definition, any two point A=(x1, y1) and B=
(x2, y2) Euclidean distance is：
In Table II, it is known that the user current location that User ID is 1 is in A, when judging the position that User ID is 5,
5 and 1 distance is calculated, as long as the distance value in the range of threshold value 50m, then 5 attributed region number is consistent with 1 number.This
In threshold value be not fixed, size is changed based on the specific size of attributed region.
After the completion of calculating, by A, B, C, the number such as the percentage of D current time numbers of users and its user's flow tendency situation
It is preserved according to being back in database server 205.
Data-mining module (204) accounts for for reading number of users in each region from database server (205)
Than the record value changed over time, by means of data mining algorithm, to each zone user quantity accounting in some following period
It is predicted, and prediction number of users accounting is sent to database server (205)；
Database server (205), for storing customer position information, active user's quantity accounting, prediction number of users
Accounting.
For some individual region, according to the user group accounting data in its different time sections, calculated with reference to data mining
Method predicts the user group accounting in following a period of time most predicted value returns to database server 205 at last；
For in the same period between region, changing value being flowed according to existing user group, in following a period of time
User group flow tendency is predicted between region, and most predicted value returns to database server 205 at last.
Consider from business perspective, compare and concern flow of personnel trend and proportion in shopping centre, it is more after all
Personnel's accounting mean more profit potentials.Such as Fig. 5, it is shown that user group is flowed to the change in other regions by commercial square
Change situation.We are in daily 18 points to 20 periods of some commercial square, the mean value of user's accounting number being collected into carrys out table
Show same day shopping centre personnel's accounting value, then using day as horizontal axis, user's accounting is the longitudinal axis, to daily with period Nei Gai area
User's accounting in domain is recorded and is drawn time series chart, is analyzed and predicted, such as Fig. 6.
We, which select exponential smoothing to predict, is predicted to personnel's accounting in several days following.Prediction model is as follows：
Ft+1=α Yt+(1-α)F；
In formula
Ft+1Represent the predicted value in time series t+1 periods；
YtRepresent the actual value in time series t periods；
FtRepresent the predicted value in period time t, α represents smoothing constant (0 ＜ α ＜ 1)；
It can be proved that the Smoothing Prediction value in any period is actually the one of all real data in the past of time series
A weighted average.Such as one includes three period data Y1, Y2, Y3Time series, start to calculate：
F2=α Y1+(1-α)F1=α Y1+(1-α)Y1=Y1
F2=α Y2+(1-α)F2=α Y2+(1-α)Y1
By F3Expression formula substitute into F4Expression formula in, can obtain：
F4=α YB+(1-α)FB=α YB+(1-α)[αY2+(1-α)Y1]
=α YB+α(1-α)Y2+(1-α)2Y1
It can see F4It is the weighted average of three time serieses in front.
Here the selection of smoothing constant α should be selected according to actual conditions.We rewrite smoothing model as follows：
Ft+1=xYt+(1-α)Ft=α Yt+Ft-αFt=Ft+α(Yt-Ft)
So new predicted value is equal to past predicted value plus an adjusted value, this adjusted value is exactly nearest period
Predict error (Yt-Ft), i.e., by adjusting the predicted value in t periods and part prediction error, it is possible to obtain t+1 periods
Predicted value.If time series includes a large amount of random fluctuation, then it is intended that selecting smaller smoothing constant, in this way
Prediction error does not have too big fluctuation.
There are the distribution to user group and prediction data, it is meant that understand some very useful useful value informations, such as：
1) for businessman, it is known which distribution and flow tendency of the user group within each period be known that
A little regions there is a large amount of potential customers and those when be only harvest client's efficiency highest period；
2) for shared bicycle company hotter at present, it can grasp which region flow of the people variation is the largest,
It and then can be with the programs of Optimizing City district-share bicycle；
3) for individual subscriber, it is thus understood that the high ebb of target area, it is possible to rationally adjust the trip side of oneself
Case avoids congestion, effectively utilizes the time of oneself.
Claims (6)
1. a kind of user group distribution forecasting method, which is characterized in that include the following steps：
(10) geographic area divides：Using existing geographical location information, geographic area division is carried out to city, divides geographic area
Including living area, workspace, shopping centre and main block；
(20) current dwell regions determine：It collects, record customer position information, and its coordinate bit is updated according to setting renewal frequency
It puts, with reference to the coordinate got and existing geographical location information, judges the current dwell regions of the user；
(30) user group is predicted：The user for calculating each region different time is detained quantitative proportion, is predicted using data with existing
The quantity of user group in following each some period of region, and between region user group flow tendency.
2. user group distribution forecasting method according to claim 1, which is characterized in that (20) current dwell regions are true
Determine step to include：
(21) user location is collected：The GPS data of user hand generator terminal is acquired to determine its more specific location information；
(22) user position update：Setting renewal frequency on demand such as once updates the GPS data of user per half an hour；
(23) user's dwell regions judge：Compare the GPS location data of user and the main coverage area built in map, judge
The band of position that user is belonged at current time.
3. user group distribution forecasting method according to claim 1, which is characterized in that (30) the user group prediction steps
Including：
(31) user is detained quantitative proportion and calculates：Assuming that user group sum immobilizes, and after the completion of each GPS data collection, system
Total number of users amount in each region is counted, it is calculated and accounts for the percentage of sum；
(32) user group quantitative forecast：Record daily with region simultaneously between section user group quantity, to the user in the following region
Group's quantity is predicted；
(33) user group flow tendency is predicted：The user group accounting in region of daily T1, T2 moment is recorded, is existed with reference to single user
The change in location situation at T1, T2 moment, in following several days, (T2-T1) in the period user group in each main construction area
Flow tendency.
4. a kind of user group forecast of distribution system, which is characterized in that including：
User terminal (101), the smart mobile phone for having GPS functions is held including user, for being sent out to data collection module (201)
Send customer position information；
Data collection module (201), for according to pre-set frequency, collecting the use that customer mobile terminal uploads periodically
Then customer position information is sent to database server (205) by family location information；
Geodata library module (202), for prestoring the cartographic information in target cities region, and it is wide to the business in region
Field, resident living area, Office Area etc. carry out region division；
Data computation module (203), for combining the user information and geodata library module in database server (205)
(202) cartographic information in, calculates active user's quantity accounting in each region of current time, and by active user's quantity
Accounting is sent to database server (205)；
Data-mining module (204), for reading in each region number of users accounting from the database server (205) at any time
Between the record value that changes, by means of data mining algorithm, each zone user quantity accounting in some following period is carried out pre-
It surveys, and prediction number of users accounting is sent to database server (205)；
Database server (205), for storing customer position information, active user's quantity accounting, prediction number of users accounting.
5. user group forecast of distribution system according to claim 4, it is characterised in that：
The customer position information includes user identifier, current time value, the warp of GPS positioning, latitude numerical value.
6. user group forecast of distribution system according to claim 5, it is characterised in that：
For distinguishing the data information of different user individual, the intelligence for having GPS functions is held including user for the user identifier
The IMEI of energy mobile phone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711303977.0A CN108171532A (en) | 2017-12-11 | 2017-12-11 | A kind of user group distribution forecasting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711303977.0A CN108171532A (en) | 2017-12-11 | 2017-12-11 | A kind of user group distribution forecasting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108171532A true CN108171532A (en) | 2018-06-15 |
Family
ID=62525686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711303977.0A Withdrawn CN108171532A (en) | 2017-12-11 | 2017-12-11 | A kind of user group distribution forecasting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108171532A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448361A (en) * | 2018-09-18 | 2019-03-08 | 云南大学 | Resident's traffic trip volume forecasting system and its prediction technique |
| CN109978264A (en) * | 2019-03-27 | 2019-07-05 | 西安电子科技大学 | A kind of Urban Population Distribution prediction technique based on space time information |
| CN114446026A (en) * | 2020-10-30 | 2022-05-06 | 北京熵行科技有限公司 | Article forgetting reminding method, corresponding electronic equipment and device |
| CN114638524A (en) * | 2022-03-28 | 2022-06-17 | 哈尔滨商业大学 | Intelligent endowment integrated service center information statistical method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440278A (en) * | 2013-08-12 | 2013-12-11 | 曙光信息产业股份有限公司 | Data mining system and method |
| CN105634854A (en) * | 2014-11-07 | 2016-06-01 | 中兴通讯股份有限公司 | User attribute analyzing method and device |
| US20170328730A1 (en) * | 2010-03-04 | 2017-11-16 | A9.Com, Inc. | Dynamic map synchronization |
-
2017
- 2017-12-11 CN CN201711303977.0A patent/CN108171532A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170328730A1 (en) * | 2010-03-04 | 2017-11-16 | A9.Com, Inc. | Dynamic map synchronization |
| CN103440278A (en) * | 2013-08-12 | 2013-12-11 | 曙光信息产业股份有限公司 | Data mining system and method |
| CN105634854A (en) * | 2014-11-07 | 2016-06-01 | 中兴通讯股份有限公司 | User attribute analyzing method and device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448361A (en) * | 2018-09-18 | 2019-03-08 | 云南大学 | Resident's traffic trip volume forecasting system and its prediction technique |
| CN109448361B (en) * | 2018-09-18 | 2021-10-19 | 云南大学 | Resident traffic travel flow prediction system and prediction method thereof |
| CN109978264A (en) * | 2019-03-27 | 2019-07-05 | 西安电子科技大学 | A kind of Urban Population Distribution prediction technique based on space time information |
| CN114446026A (en) * | 2020-10-30 | 2022-05-06 | 北京熵行科技有限公司 | Article forgetting reminding method, corresponding electronic equipment and device |
| CN114446026B (en) * | 2020-10-30 | 2023-12-12 | 北京熵行科技有限公司 | Article forgetting reminding method, corresponding electronic equipment and device |
| CN114638524A (en) * | 2022-03-28 | 2022-06-17 | 哈尔滨商业大学 | Intelligent endowment integrated service center information statistical method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109978224B (en) | Method for analyzing and acquiring traffic trip rates of buildings with different properties | |
| CN108171532A (en) | A kind of user group distribution forecasting method and system | |
| CN111582948B (en) | Individual behavior analysis method based on mobile phone signaling data and POI (Point of interest) | |
| Bao et al. | Spatial analysis of bikeshare ridership with smart card and POI data using geographically weighted regression method | |
| CN106709606A (en) | Personalized scene prediction method and apparatus | |
| CN110414732A (en) | A kind of trip Future Trajectory Prediction method, apparatus, storage medium and electronic equipment | |
| CN104850734A (en) | Air quality index prediction method based on spatial and temporal distribution characteristics | |
| CN111554408B (en) | City internal dengue space-time prediction method, system and electronic equipment | |
| Zhou et al. | Understanding the modifiable areal unit problem and identifying appropriate spatial unit in jobs–housing balance and employment self-containment using big data | |
| CN112579922B (en) | Interest point recommendation method based on user track | |
| EP3014491B1 (en) | Displaying demographic data | |
| CN108733774A (en) | A kind of unemployment dynamic monitoring method based on big data | |
| US20140372172A1 (en) | Method and computer system to forecast economic time series of a region and computer program thereof | |
| US20150006255A1 (en) | Determining demographic data | |
| CN110110243A (en) | A kind of historical track destination prediction technique based on echo state network | |
| CN109195219A (en) | The method that server determines mobile terminal locations | |
| Cartlidge et al. | Spatio-temporal prediction of shopping behaviours using taxi trajectory data | |
| Zhong et al. | GIS-based travel demand modeling for estimating traffic on low-class roads | |
| CN114723480B (en) | Passenger flow prediction method and cargo scheduling system for rural travel | |
| CN109672986A (en) | A kind of space-time big data analysis system | |
| CN110377679B (en) | Public space activity measuring method and system based on track positioning data | |
| Cullinan | A spatial microsimulation approach to estimating the total number and economic value of site visits in travel cost modelling | |
| CN116437291A (en) | Cultural circle planning method and system based on mobile phone signaling | |
| Woo et al. | Optimal cooling shelter assignment during heat waves using real-time mobile-based floating population data | |
| CN112954624B (en) | Hybrid land use form estimation method based on mobile phone signaling big data |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180615 |
|
| WW01 | Invention patent application withdrawn after publication |