CN108876475B - City functional area identification method based on interest point acquisition, server and storage medium - Google Patents
City functional area identification method based on interest point acquisition, server and storage medium Download PDFInfo
- Publication number
- CN108876475B CN108876475B CN201810767026.7A CN201810767026A CN108876475B CN 108876475 B CN108876475 B CN 108876475B CN 201810767026 A CN201810767026 A CN 201810767026A CN 108876475 B CN108876475 B CN 108876475B
- Authority
- CN
- China
- Prior art keywords
- city
- poi
- bus
- interest
- characteristic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000006870 function Effects 0.000 claims abstract description 144
- 239000000203 mixture Substances 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 21
- 239000000126 substance Substances 0.000 claims description 3
- 238000011161 development Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 11
- 230000002093 peripheral effect Effects 0.000 description 10
- 238000011160 research Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 3
- 235000015655 Crocus sativus Nutrition 0.000 description 2
- 244000124209 Crocus sativus Species 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 235000013974 saffron Nutrition 0.000 description 2
- 239000004248 saffron Substances 0.000 description 2
- 238000013316 zoning Methods 0.000 description 2
- 239000004566 building material Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012771 household material Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
Images
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a city functional area identification method based on interest point acquisition, a server and a storage medium, wherein the city functional area identification method based on interest point acquisition comprises the steps of acquiring target city POI data based on a network electronic map and establishing POI indexes; dividing a target city into regions, counting POI indexes of each region, and calculating a corresponding POI total index value POI _ Classes; according to the POI indexes and the total POI index values of the areas, judging the city functions contained in the areas and the number of the city functions contained in the areas, and obtaining single function areas of the city and the areas with mixed functions; acquiring bus card swiping data of each region with mixed urban functions, and establishing and calculating passenger number characteristic indexes of a bus station according to the bus card swiping data; and clustering each region of urban function mixture according to the calculated passenger number characteristic index value.
Description
Technical Field
The invention relates to the technical field of geographic information, in particular to a city functional area identification method based on interest point collection, a server and a storage medium.
Background
The functional area division of the city is the basis of city management and city planning. In the early city functional area division research, data such as population economy general survey, land utilization maps, questionnaires and the like are mainly adopted, the space scale of the city functional pattern research is large under the constraint of the data, and villages, towns and streets or counties are mostly used as basic space units. In recent years, with the development of information and communication technology, a large amount of LBS (location Based service) big data (such as GPS (global positioning system), GSM (global system for mobile communications) and smart card charging system data) Based on individual behaviors emerge, and conditions are created for the detailed division of urban functional areas.
The bus card swiping data represents individual travel rules, and the key for researching city function partitions by adopting the bus card swiping data is how to mine the association between resident travel rules and city function characteristics. In the method for identifying the urban functional area in the prior art, the urban functional area is researched through correlation analysis of urban functions and resident individual trip time, a starting place, a destination, trip purposes and the like, a resident trip model is constructed by taking a riding individual as a research object, and the research is carried out through methods such as text mining and the like.
Disclosure of Invention
The invention mainly aims to provide a city function area identification method based on interest point acquisition, a server and a storage medium, and aims to provide a city function identification method which can identify city functions more accurately.
In order to achieve the above object, the present invention provides a city functional area identification method based on interest point collection, which includes:
acquiring POI (point of interest) data of a target city based on a network electronic map, and establishing POI indexes { IsContainResidce, IsContainJob and IsContainShopping } and a POI total index POI _ Classes; wherein, IsContainResidce is whether the house function is contained, IsContainJob is whether the employment function is contained, and IsContainShopping is whether the shopping service is contained;
dividing a target city into regions, counting and obtaining POI indexes of each region according to POIs contained in each region and the number of various POIs contained in each region, and calculating corresponding POI total index values POI _ Classes;
obtaining single function areas and function mixed areas of the city according to the POI indexes and the total POI index values of the areas;
acquiring bus card swiping data of each region with mixed urban functions, and establishing and calculating passenger number characteristic index values of a bus station according to the bus card swiping data;
and determining the urban function of the area according to the calculated passenger number characteristic index value.
Preferably, the acquiring of the bus card swiping data of the target land, and the establishing and calculating of the passenger number characteristic indexes of the bus station according to the bus card swiping data specifically include:
acquiring bus card swiping data of target land, and respectively counting bus card swiping data indexes
According to the data index of bus card swiping
Calculating a characteristic value of each bus stop, wherein the characteristic value of each bus stop comprises full-time absolute quantity characteristics
Full time wave characteristic
Full time skewness feature
Full time kurtosis feature
And full time trending features
Wherein the content of the first and second substances,
when k is 1, it represents weekday, and when k is 2, it represents weekend.
Preferably, the full time absolute quantity characteristic
The calculation formula of (2) is as follows:
Preferably, the full-time wave characteristic
The calculation formula of (2):
Preferably, the full time skewness feature
The calculation formula of (2):
Preferably, the full-time kurtosis feature
The calculation formula of (2):
Preferably, the full time trend feature
The calculation formula of (2):
wherein T is the total number of time periods of a day.
Preferably, the calculation formula of the POI total index POI _ Classes is as follows:
POI_Classes＝IsContainResidence×100+IsContainJob×10+IsContainShopping。
in order to achieve the above object, the present invention further provides a server, including: the system comprises a memory, a processor and a city functional area identification program which is stored on the memory and can run on the processor, wherein the city functional area identification program based on the point of interest acquisition realizes the steps of the city functional area identification method based on the point of interest acquisition when being executed by the processor.
In order to achieve the above object, the present invention further provides a storage medium, where the storage medium stores a functional area identification program for identifying a functional area of a city based on point of interest acquisition, and the functional area identification program for identifying a functional area of a city based on point of interest acquisition implements the steps of the functional area identification method for identifying a functional area of a city based on point of interest acquisition when executed by a processor.
According to the technical scheme provided by the invention, the data of getting off the bus is not needed, so that all bus card swiping data participate in calculation. In the research of excavating individual behavior patterns to carry out city function zoning, models need to be established by adopting individual getting-on/off time and places, so that only bus line data of card swiping on getting-on/off of a bus is adopted, but in fact, in each local bus system, the bus line ratio of card swiping on getting-on/off of the bus is large.
Further, the POI category contained in the area is used to reflect the function type of the area; the number of the POIs cannot reflect the strength of the functions of the POIs, and the number of the crowd served by the geographic entity represented by the POIs can reflect the strength of the functions of the POIs; and the travel purposes are different, and the travel time rule characteristics also have differences. According to the invention, the regional function is more accurately distinguished by comprehensively considering different travel purposes and the number of people served by the geographic entity represented by the POI.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an urban functional area identification method based on point of interest collection according to an embodiment of the present invention;
FIG. 2 is a cut map of the Beijing area facing the sun;
FIG. 3 is a schematic flow chart diagram illustrating one embodiment of a characteristic indicator of the number of passengers at a bus stop according to the present invention;
FIG. 4 is a graph illustrating the number of passengers getting on the bus at each time interval in three bus stations of the west door, the east door and the south of the space bridge;
FIG. 5 is a graph showing the number of passengers getting on the bus at each time period of three bus stations, namely a North House door station and a West Red House door station;
FIG. 6 is a graph schematically showing the number of passengers getting on the bus at each time period at three bus stations of Yanling intersection, Anhui bridge north and Ciyun temple;
fig. 7 is a curve diagram of the number of passengers getting on the bus at each time interval of two bus stops.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a city functional area identification method based on interest point acquisition, referring to fig. 1, the city functional area identification method comprises the following steps:
step S100, acquiring target land POI data based on a network electronic map, and establishing POI indexes { IsContainResidence, IsContainJob, IsContainShopping }, and a POI total index POI _ Classes; wherein, IsContainResidce is whether the house function is contained, IsContainJob is whether the employment function is contained, and IsContainShopping is whether the shopping service is contained;
step S200, dividing a target city into regions, counting and obtaining POI indexes of each region according to the number of POIs contained in each region and the number of various POIs contained in each region, and calculating the corresponding total index value of the POIs;
step S300, obtaining single function areas and all areas with mixed functions of the city according to the POI indexes and the total POI index values of all the areas;
s400, acquiring bus swiping card data of each region with mixed urban functions, and establishing and calculating a passenger number characteristic index of a bus station according to the bus swiping card data;
and S500, determining the urban function of the area according to the calculated passenger number characteristic index value.
The execution of each step is described in detail below.
Step S100 is executed firstly, target land POI data are obtained based on the network electronic map, and POI indexes and POI total indexes are established.
The POI data is Point of interest data (Point of interest), and the function attribute of the regional facility is described through the POI data. The POI data comprises information of houses, shops, schools, hotels and the like, and the information is organized by the network electronic map POI according to a unified three-level classification standard. According to the POI data, the POI indexes are extracted and obtained, and the POI indexes are divided into three categories by taking the POI data in the sunny region of Beijing as an example: IsContainResidce (whether a home function is included), IsContainJob (whether a employment function is included), and IsContainShoppinging (whether a shopping service is included). Details of POI indices and extraction methods are shown in table 1.
TABLE 1 POI indices and extraction description
The IsContainResidence, IsContainJob and IsContainShopping are normalized by counting the value of IsContainResidence, the value of IsContainJob and the value of IsContainShopping. And (4) carrying out preliminary identification on the city functional area by calculating a POI index and a POI total index POI _ Classes.
Preferably, the first and second liquid crystal materials are,
POI _ Classes ═ iscontainresponse × 100+ IsContainJob × 10+ iscontainshoping (formula 1).
Calculating the functions of the blocks through POI _ Classes, wherein the result of the POI _ Classes is 0, and the functions of living, employment and shopping are not contained in the area; 1. 10, 100 represent single function areas, respectively, which only include shopping, employment and living functions in the area; 11. reference numerals 101, 110, and 111 denote mixed function areas, which respectively denote a career shopping mixed area, a resident career mixed area, and a resident career shopping mixed area.
And step S200 is executed, the target city is divided into areas, POI indexes of each area are obtained through statistics according to the number of the POIs contained in each area and the number of the POIs contained in each area, and the corresponding total POI index value is calculated.
For dividing the target city into regions, a block can be selected as a basic space unit for forming the city, or other cities recognized by people and basic elements for forming city images can be adopted, or the basic social unit of city life can be adopted. The boundary of the block can be an urban road, a river, a green belt, a fence lamp element, or a boundary range which can obviously define a block. In this embodiment, an administrative division vector diagram of a target city is imported into ArcGIS software, longitude and latitude coordinates of bus stop points in the city are imported into the ArcGIS software, a voronoi diagram is generated according to the bus stop points, and then the voronoi diagram is cut by using an administrative division diagram of the target city, so that each obtained polygonal area is used as a divided area.
And statistically calculating the POI contained in each polygonal area and the number of POI contained in each category.
Then, step S300 is executed to obtain the number of the city single function areas, the areas with the mixed functions, and the polygon areas containing the city functions of each category according to the POI index and the POI total index value POI _ Classes of each area.
A POI _ Classes result of 0 indicates that the area does not contain residential, employment, and shopping functions; 1. 10, 100 represent single function zones, respectively, which represent zones that contain only shopping, employment, and residential functions, wherein the zone with a result of 0 may not be considered because it does not contain residential, employment, and shopping functions.
And when the calculated POI _ Classes results are 1, 10, and 100, the calculated POI _ Classes result is represented as a single functional area, and the calculation of the classification of the areas through the POI index is more complete, so that no further classification is needed.
And for the POI _ Classes results of 11, 101, 110, and 111, the mixed function area is represented, and the dominant function in the mixed function area cannot be clearly embodied by using the POI index calculation, so the present invention further classifies the POI _ Classes.
Taking fig. 2 as an example to illustrate the city function of each area, when the result of calculating POI _ Classes is 0, it indicates that the area does not include the functions of living, employment and shopping; 1. 10, 100 represent single function areas, respectively, which only include shopping, employment and living functions in the area; 11. reference numerals 101, 110, and 111 denote mixed function areas, which respectively denote a career shopping mixed area, a resident career mixed area, and a resident career shopping mixed area. In terms of quantity, the quantity of the living and employment shopping mixed areas in the figure 2 is the largest, and the total quantity is 424; secondly, 65 employment and shopping mixed areas are provided in total; again, a total of 40 residential shopping mix areas. Only a relatively large number of these three types of regions were studied. Areas that did not contain the functions of housing, employment and shopping, as well as single function areas, were not further classified in this study, and the 110 housing employment mix area and the 11 employment shopping mix area were fewer in number and were not further classified. Because the single functional regions obtained by statistics are accurately distinguished, further classification is not needed, and only a large number of mixed regions need to be further classified.
The next step is to further classify a higher number of these blend zones.
And executing step S400, acquiring bus swiping card data of each region with mixed urban functions, and establishing and calculating the passenger number characteristic indexes of the bus station according to the bus swiping card data.
The bus card swiping data can effectively reflect the riding rules of the passengers, the purpose and the rule of working day going out and double-holiday going out are different, the main purpose of working day going out is commuting on duty, and the starting point, time, line and other characteristics of going out are generally stable and are non-elastic going out; the double-holiday travel aims at shopping, leisure and entertainment generally, the travel frequency and the travel space-time distribution have certain randomness, and the double-holiday travel is elastic travel. Therefore, the bus card swiping data is divided into weekday data and weekend data when the bus card swiping data is considered.
The acquiring of the bus card swiping data of the target city, and establishing and calculating the passenger number characteristic index of the bus station according to the bus card swiping data, please refer to fig. 3, specifically including:
step S410, obtaining bus card swiping data of target land, and respectively counting bus card swiping data indexes
Wherein the content of the first and second substances,
the number of passengers getting on the bus in the t-th time period on the ith bus station working day/weekend;
when k is 1, the day is the working day, and when k is 2, the weekend is represented;
In the step S410, bus card swiping data of the target city is obtained, and bus card swiping data indexes are respectively counted
It may be that a time period is selected, such as statistics of ride data for 4 months per day 2014. The riding data rules of the working days are approximately the same, and the riding rules of the weekends are also approximately the same, so that statistics can be carried out by taking one week as one period. For example, data from 4/14/2014 (monday) to 4/20/2014 (sunday) may be selected as a research cycle, and the total number of passengers in each period from 4/14/2014 to 20/day may be counted. For example, if the number of passengers per day is mainly concentrated on 05:00:00-23:59:59, the study period may be determined to be 5-23 periods (19 periods in total), in the embodiment provided by the present invention, for convenience of description, a period is defined as one hour from an hour, and in other embodiments, the period may be defined in other manners, which is not limited herein.
Taking fig. 4 as an example, fig. 4 shows bus card swiping data of three bus stations of the xiqian (Xi Bian Men), the Dong Zhi (Dong Zhi Men), and the South Hangtian (South Hangtian Bridge) in beijing, and it can be seen that the total time series data of the number of passengers at the three bus stations has difference, and the number of passengers at the three bus stations at different time periods and the total number of passengers at all day have larger difference. The maturity of the construction of the surrounding areas of the three places, namely western Bimen, east-oriented door, and aerospace bridge south, can also be seen by combining the figure that the total number of passengers (bus card swiping data) also reflects the maturity of the construction of the surrounding areas of the station to a certain extent, and the large number of the total number of passengers indicates that the number of living or working people around the station is large or other services are provided. The difference between the total number of passengers in the weekdays and the total number of passengers in the weekends respectively reflects the perfection degree of different functions, for example, places with more passengers in the weekends tend to be more prone to shopping functions, and places with more passengers in the weekends tend to employment functions. Therefore, the present invention provides embodiments by considering weekdays and weekends separately.
In addition, the peripheral functions of the station also affect the distribution of the number of passengers (bus swiping card data) in the station, please refer to fig. 5, and the distribution of the number of passengers in the north courtyard station and the west courtyard station of the subway is shown in fig. 5. As can be seen from fig. 5, the passengers at the saffron station are mainly concentrated in a few time intervals, namely, the 7 th time interval and the 18 th time interval, and the two time intervals are the peak periods of working and working, which shows that the living function and employment function around the saffron station are very obvious and far exceed other functions in the area; the number of passengers at the station in the north of the subway is distributed uniformly all day, which shows that the living function and employment function in the peripheral area of the station are not obvious compared with other functions. .
Referring to fig. 6, fig. 6 shows the time series data of the number of passengers getting on the bus at each time interval of the working day of the yanling intersection, the north of anhui bridge and the temple of Ciyun. The number of people getting on the bus at the Yanling intersection station in the early peak is far larger than that in the late peak, the number of people getting on the bus at the north of Anhui bridge in the early peak and the late peak is basically equal, and the number of people getting on the bus at the Ciyun station in the early peak is far smaller than that in the late peak. The residential function of the peripheral area of the station at the Yanling intersection is far greater than the employment function, the residential function of the peripheral area of the station at the North Huiyi bridge is equivalent to the employment function, and the employment function of the peripheral area of the Ciyun station is far greater than the residential function. It can be seen that the difference performance of the number of people getting on the bus at the peak in the morning and at the evening reflects the difference of the functional proportion in the peripheral area of the bus station, and the trend characteristic of the peak in the morning and at the evening at the working day and the trend characteristic of the peak in the morning and at the evening at weekend respectively reflect the difference of the different functional proportion in the area, for example, the difference of the peak in the morning and at the evening at working day can reflect the difference of the ratio of the living function and the employment function in the area, and the difference of the peak in the morning and at the evening at weekend reflects the difference of the ratio of the living function and the functional proportion of leisure, entertainment, shopping and the like in the area.
That is, the trend of the bus card swiping data has a close relationship with weekends/working days, peripheral functions of stations, morning and evening peaks.
Step S420, according to the bus card swiping data index
Calculating a characteristic value of each bus stop, wherein the characteristic value of each bus stop comprises full-time absolute quantity characteristics
Full time wave characteristic
Full time skewness feature
Full time kurtosis feature
And full time trending features
Specifically, the characteristic value of each bus stop will be described in detail below.
(1) Full time absolute quantity feature
Full time absolute quantity feature
The characteristic is the full-time 'absolute quantity' of the time sequence data of the number of passengers getting on the bus on the working day and on the weekend of the ith bus stop.
The full time absolute quantity characteristic
The calculation formula of (2) is as follows:
When k is 1, it represents weekday, and when k is 2, it represents weekend.
Full time absolute quantity feature
The average value of the number of people getting on the bus (bus card swiping data) on the working day and on the weekend of the ith bus station is represented. The larger the absolute quantity at all times is, the more the total number of passengers is, the higher the maturity of the periphery of the station is; otherwise the lower the station periphery maturity.
(2) Full time wave characteristic
Full time wave characteristic
The characteristic of the full-time fluctuation of the time sequence data of the number of passengers getting on the bus on the ith bus station on the weekdays and weekends.
The full time fluctuation characteristic
The calculation formula of (2):
When k is 1, it represents weekday, and when k is 2, it represents weekend.
Full time wave characteristic
Representing the difference of the number of passengers getting on the bus at the ith bus station on workdays/weekends, wherein the larger the difference is, the more concentrated the number of passengers on one or more busesIn the time zone, the more single the function of the peripheral area of the station or the more prominent one of the functions.
(3) Full time skewness feature
Full time skewness feature
The feature is the full-time deviation of the time sequence data of the number of passengers getting on the bus in each time interval of the working day/weekend of the ith bus station.
The full time skewness characteristic
The calculation formula of (2):
When k is 1, it represents weekday, and when k is 2, it represents weekend.
Full time skewness feature
The deviation of the number of passengers getting on the bus in each time period of the working day/weekend of the ith bus station and the normal distribution is reflected, and whether the number of passengers getting on the bus in the ith bus station in the whole period T is symmetrical or not is measured, and the characteristics of full time skewness in quantity
Negative means that the vast majority of the values (including the median) are to the left of the mean, and vice versa means that the vast majority of the values (including the median) are to the right of the mean.
Therefore, the full-time skewness characteristic further refines the fluctuation trend of the time series data of the number of passengers at the station on the basis of the full-time fluctuation characteristic. The fluctuation feature can only reflect the difference, and the skewness feature can reflect the difference distribution feature or the reason for the difference.
(4) Full time kurtosis feature
Full time kurtosis feature
The characteristic of the full-time kurtosis of the time sequence data of the number of passengers getting on the bus in each time period of the working day/weekend of the ith bus station.
The full time kurtosis characteristic
The calculation formula of (2):
When k is 1, it represents weekday, and when k is 2, it represents weekend.
Full time kurtosis feature
The concentration degree of the number of the passengers getting on the bus in the working day/weekend day of the ith bus station or the sharp kurtosis degree of a distribution curve is represented, and if the kurtosis is more than 0, the distribution of the index value is more concentrated around the average value than normal distribution; if the kurtosis is less than 0, it means that the distribution of the index value is more dispersed than the normal distribution. The SCF and the KCF both reflect the distribution characteristics of sample data, and if the two samples are more consistent along with the development of time, the samples are more similar.
(5) Full time trend feature
Full time trend feature
The number of passengers getting on the bus for each time period of working day/weekend of the ith bus stationThe full time "trend" feature TF of the time series data.
When k is 1, it represents weekday, and when k is 2, it represents weekend.
The full time trend feature
The calculation formula of (2):
wherein T is the total number of time periods of a day.
Full time trend feature
The difference value between the maximum value of the number of the passengers getting on the bus in the 5 th to 9 th time period and the maximum value of the number of the passengers getting on the bus in the 16 th to 20 th time period in the working day/weekend day of the ith bus station is represented, the maximum value of the number of the passengers getting on the bus in the 16 th to 20 th time period is indicated by the negative TF, the maximum value of the number of the passengers getting on the bus in the 5 th to 9 th time period is indicated by the positive TF, the larger the absolute value of the TF is, the larger the difference between the two maximum values is, and the smaller the difference between the two maximum values is indicated by the closer TF to 0. And the 5 th to 9 th time periods are early peak time periods, the 16 th to 20 th time periods are late peak time periods, and the difference performance of the number of passengers in the working day and the weekend early and late peak time periods reflects the difference of the functions in the peripheral areas of the station.
Full time absolute quantity feature
Full time wave characteristic
Full time skewness feature
Full time kurtosis feature
And full time trend feature TF (Q)i k) In (c), AQF is used to reflect the variability in bus headcount; VF, SCF and KCF are used for reflecting the difference of the passenger number distribution, usually VF and SCF can reflect the distribution characteristics of data, but although the arithmetic mean, standard deviation and skewness coefficient of the two groups of data are the same, the high-rise degree at the top end of the distribution curves of the VF and SCF are different (please refer to figure 7), and the kurtosis of the passengers is an important index which can reflect the strength of certain urban function in the peripheral area of a station, so that the KCF is also selected as the difference for reflecting the passenger number distribution; the TF is used to reflect the variability of occupant trends.
The invention establishes 10 characteristic indexes when distinguishing the difference between areas containing the same city function type by adopting the time sequence characteristics of the bus station passenger flow. The ten characteristic indexes are AQF (full-time absolute quantity characteristic), VF (full-time fluctuation characteristic), SCF (full-time skewness characteristic), KCF (full-time kurtosis characteristic) and TF (full-time trend characteristic) of the working day and weekend of each bus station respectively. Compared with a method of directly adopting the number of passengers in each time period of working days and weekends of each bus station as a clustering index, the method improves the dimensionality of the clustering index; the 10 characteristic indexes are established, and the passenger flow time sequence change characteristic in each time interval is highlighted.
Characteristic value K (Q) of each bus stopi)，
And executing step S500, and determining the city function of the area according to the calculated passenger number characteristic index value.
Specifically, the step S500 further includes classifying the regions of the function mixture, and in the embodiment of the present invention, the mixture region is divided into six types, where the six types are developed more mature, developed immature, developed most mature, developed least mature, developed immature and developed less mature, and in other embodiments, the six types may be classified according to specific situations.
The classification criteria are detailed in the case of residential shopping mix, see table 2, and so on for other mixes.
TABLE 2 Living employment shopping mix zone Classification
| Category numbering | Description of the |
| 1 | Mature development, less difference of 3 functions, living > shopping > employment |
| 2 | Immature development, obvious difference of 3 functions, shopping > employment > living |
| 3 | The most mature development, 3 functions are basically equivalent |
| 4 | The development is the least mature, the 3 functions are obviously different, and the living > employment > |
| 5 | Immature development, less difference of 3 functions, living > shopping > |
| 6 | The development is less mature, 3 functions are basically small, shopping > employment > living > |
The invention does not need the data of getting off the bus, so all the bus card swiping data participate in the calculation. In the research of excavating individual behavior patterns to carry out city function zoning, models need to be established by adopting individual getting-on/off time and places, so that only bus line data of card swiping on getting-on/off of a bus is adopted, but in fact, in each local bus system, the bus line ratio of card swiping on getting-on/off of the bus is large.
The POI categories contained in the area are used for reflecting the function type of the area; the number of the POIs cannot reflect the strength of the functions of the POIs, and the number of the crowd served by the geographic entity represented by the POIs can reflect the strength of the functions of the POIs; and the travel purposes are different, and the travel time rule characteristics also have differences. According to the invention, the regional function is more accurately distinguished by comprehensively considering different travel purposes and the number of people served by the geographic entity represented by the POI.
Furthermore, the regional function type is judged through distribution of POI in different types; comparing the absolute value of the passenger flow volume to judge the maturity of the regional function development; and finally, judging the regional function proportion characteristics according to the change characteristics of the passenger flow in different time periods, and comprehensively considering the influence of various factors.
Due to the fact that the function types contained in the regions are different, the traveling purposes of people are different, the time law characteristics of traveling are different, and therefore the passenger flow time sequence characteristics of the bus stations in the regions with different function types are different. Therefore, the effect of identifying the strength of different function types according to the passenger flow of the bus station at different time intervals is better.
Example one
Referring to fig. 2, in the ArcGIS software, a bus stop is opened to generate a voronoi diagram, then a sunny region administrative division diagram is opened, the voronoi diagram is cut, only regions in the sunny region are reserved, and polygons in the voronoi diagram are used as research objects to perform subsequent city function classification.
And acquiring POI data of the target city based on the network electronic map, and establishing POI indexes { IsContainResidence, IsContainJob and IsContainShopping }, and POI total indexes.
And importing the POI into ArcGIS software according to the longitude and latitude coordinates of the POI, connecting the POI layer with the voronoi diagram by using a spatialjoin function, and calculating the POI index in the table 1. The total index is calculated by integrating 3 POI indexes according to the following formula:
POI_Classes＝IsContainResidence×100+IsContainJob×10+IsContainShoppin g
and then, counting the number of the urban functions contained in each polygonal area and the number of the polygonal areas containing the urban functions of each category according to the POI _ Classes. The statistical results are shown in the lower left corner of fig. 2. The number of the living and employment shopping mixed areas is the largest, and the total number is 424; secondly, 65 employment and shopping mixed areas are provided in total; again, a total of 40 residential shopping mix areas.
And further classifying the mixed residential employment shopping areas with larger quantity.
By using K (Q)i) The function clustering research is carried out on 10 indexes in the method by using a k-means clustering method. Due to K (Q)i) The orders of magnitude of the 10 indexes are greatly different, and the indexes are standardized by adopting a z-score standardization method before clustering. The k-means clustering method needs to set the category number before clustering, can set a relatively large category number, analyzes the similarity of indexes of all clustering centers and the number of blocks in all categories after clustering is finished, merges the clustering centers with large similarity, re-inputs the merged category number into a k-means algorithm for clustering again, and repeats the steps until the clustering categories and the differences of all clustering centers are relatively reasonable.
TABLE 3 characteristic index values of number of passengers in each category and number of passengers in each category
The category area is divided into 6 categories, and the passenger number characteristic index value and the number of each category are shown in a table 2. Wherein the AQF meterDisplay device
And AQF _ END represents
Other features are synonymous and so on.
As can be seen by combining the values of the indexes and the table 2, the AQF value of the 3 rd region is the largest, the number of passengers is the smallest in the 2 nd region, the development of the 3 rd region is the most mature, and the development of the 2 nd region is the least mature. In the 1 st, 3 rd and 6 th areas, the absolute value of TF is closest to 0, which shows that the number of passengers is basically equivalent in the morning and at night in the working day, and the living and employment functions in the areas are basically equivalent; the TF _ END absolute value is closest to 0, the number of passengers is basically equivalent in the morning and at the evening on weekends, and the living and shopping functions in the area are basically equivalent; the TF and TF _ END of the 1 st and 3 rd areas are greater than 0, which indicates that the living function is slightly greater than the employment and shopping functions; the category 6 zones TF and TF _ END are less than 0, indicating that the residential function is slightly less than the employment and shopping functions. The TF of the 4 th and 5 th areas is relatively large, which indicates that the living function is obviously stronger than the employment function, and the TF _ END is relatively large, which indicates that the living function is obviously stronger than the shopping function; the TF of the type 4 area is smaller than TF _ END, which shows that the employment function is stronger than the shopping function; the category 5 area TF is greater than TF _ END, indicating that the shopping function is stronger than the employment function. The TF and TF _ END values of the type 2 area are smaller than 0, and the absolute values are relatively large, so that the living function in the area is obviously weaker than the employment and shopping functions; the absolute value of TF is less than the absolute value of TF _ END, indicating that the employment function is weaker than the shopping function.
The POI category contained in the area is adopted to reflect the function type of the area, the POI only represents the existence of a geographic entity, and the strength of the function of the geographic entity cannot be reflected when the POI is used alone, for example, the POI representing the entity of a business office building can reflect the employment function of the POI, but the POI data does not describe the detailed floor information of the building and cannot reflect the information of the number of employment people in the building. The existence of a certain type of POI can reflect the functions existing in the area, but the method of reflecting the function strength by only adopting the number of the POI reduces the accuracy of the city function partition. In the technical scheme provided by the invention, the time sequence characteristics of the passenger flow of the bus station are adopted to distinguish the difference (the difference of the strength of various functions) between the areas containing the same city function type. The invention adopts the number of the crowd served by the geographical entity represented by the POI to reflect the strength of the function of the geographical entity, and then adopts the passenger flow of the bus station to reflect the number of the crowd served in the area.
The city function area classification is carried out completely by adopting the bus card swiping data, the function identification process of the clustering center is combined with the POI, the function with similar trip characteristics can not be distinguished, if the areas with the leisure functions such as scenic spots and parks and the like and the areas containing the household and building material markets are similar in trip rules, the two areas can not be separated, and the classification accuracy is reduced. According to the method, the POI data is firstly adopted to qualitatively judge the regional function, and then the bus card swiping data is adopted to analyze the strength of the regional function, so that the classification accuracy is improved.
The invention also proposes a server comprising: the system comprises a memory, a processor and a city functional area identification program which is stored on the memory and can run on the processor, wherein the city functional area identification program based on the point of interest acquisition realizes the steps of the city functional area identification method based on the point of interest acquisition when being executed by the processor.
The invention also provides a storage medium, wherein the storage medium stores an urban functional area identification program based on the point of interest collection, and the urban functional area identification program based on the point of interest collection realizes the steps of the urban functional area identification method based on the point of interest collection when being executed by a processor.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (3)
1. A city functional area identification method based on interest point collection is characterized by comprising the following steps:
obtaining target city interest point data based on a network electronic map, and establishing interest point indexes { IsContainResidce, IsContainJob and IsContainShoppeng }, and a total interest point index POI _ Classes; wherein, IsContainResidce is whether the house function is contained, IsContainJob is whether the employment function is contained, and IsContainShopping is whether the shopping service is contained;
dividing the target city into areas, counting and obtaining interest point indexes of each area according to the interest points contained in each area and the number of various interest points contained in each area, and calculating the corresponding total interest point index value POI _ Classes;
obtaining each region of a single function region and a function mixture of the city according to the interest point index and the total interest point index value of each region;
acquiring bus card swiping data of each region with mixed urban functions, and establishing and calculating passenger number characteristic index values of a bus station according to the bus card swiping data;
according to the calculated passenger number characteristic index value, clustering of all regions with urban function mixing is carried out, and according to the passenger number characteristic index value of the clustering center of each category of clustering results, the urban functions of all the regions are determined;
the method comprises the steps of obtaining bus card swiping data of a target city, establishing and calculating passenger number characteristic indexes of a bus station according to the bus card swiping data, and specifically comprises the following steps:
acquiring bus card swiping data of a target city, and respectively counting bus card swiping data indexes
According to the data index of bus card swiping
Calculating a characteristic value of each bus stop, wherein the characteristic value of each bus stop comprises full-time absolute quantity characteristics
Full time wave characteristic
Full time skewness feature
Full time kurtosis feature
And all ofTime trend feature TF (Q)i k)；
Wherein the content of the first and second substances,
when k is 1, the day is weekday, and when k is 2, the weekend is represented;
the full time absolute quantity characteristic
The calculation formula of (2) is as follows:
the full time fluctuation characteristic
The calculation formula of (2):
the full time skewness characteristic
The calculation formula of (2):
the full time kurtosis characteristic
The calculation formula of (2):
the full time trend feature
The calculation formula of (2):
wherein T is the total time period of one day;
the calculation formula of the total index of interest POI _ Classes is as follows:
POI_Classes＝IsContainResidence×100+IsContainJob×10+IsContainShopping。
2. a server, characterized in that the server comprises: memory, processor and city functional area identification program based on point of interest collection stored on the memory and executable on the processor, the city functional area identification program based on point of interest collection implementing the steps of the city functional area identification method based on point of interest collection according to claim 1 when executed by the processor.
3. A storage medium storing a city functional area identification program based on point of interest collection, wherein the city functional area identification program based on point of interest collection is executed by a processor to implement the steps of the city functional area identification method based on point of interest collection according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810767026.7A CN108876475B (en) | 2018-07-12 | 2018-07-12 | City functional area identification method based on interest point acquisition, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810767026.7A CN108876475B (en) | 2018-07-12 | 2018-07-12 | City functional area identification method based on interest point acquisition, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108876475A CN108876475A (en) | 2018-11-23 |
| CN108876475B true CN108876475B (en) | 2022-02-01 |
Family
ID=64301418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810767026.7A Active CN108876475B (en) | 2018-07-12 | 2018-07-12 | City functional area identification method based on interest point acquisition, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108876475B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334321B (en) * | 2019-06-24 | 2023-03-31 | 天津城建大学 | City rail transit station area function identification method based on interest point data |
| CN110442662B (en) * | 2019-07-08 | 2022-05-20 | 清华大学 | Method for determining user attribute information and information push method |
| CN112579614B (en) * | 2019-09-27 | 2024-06-11 | 阿波罗智能技术(北京)有限公司 | Method and device for collecting map data, electronic equipment and medium |
| CN110738244B (en) * | 2019-09-29 | 2022-06-21 | 中国科学院深圳先进技术研究院 | Subway station function and evolution identification method and system based on card swiping data and electronic equipment |
| CN110766589A (en) * | 2019-10-28 | 2020-02-07 | 电子科技大学 | Method for deducing city function based on communication data and interest point data |
| CN111651502B (en) * | 2020-06-01 | 2021-09-14 | 中南大学 | City functional area identification method based on multi-subspace model |
| CN112381301B (en) * | 2020-11-18 | 2022-06-14 | 华南理工大学 | City path image generation method combining questionnaire survey and street view picture |
| CN112487298B (en) * | 2020-12-17 | 2023-12-08 | 深圳市城市规划设计研究院股份有限公司 | Urban function identification method and device based on airport passenger flow source data |
| CN113806419B (en) * | 2021-08-26 | 2024-04-12 | 西北大学 | Urban area function recognition model and recognition method based on space-time big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503714A (en) * | 2016-10-11 | 2017-03-15 | 湖州师范学院 | A kind of method that urban function region is recognized based on interest point data |
| CN106991142A (en) * | 2017-03-22 | 2017-07-28 | 湖州师范学院 | A kind of method that urban function region is recognized based on wechat data and interest point data |
-
2018
- 2018-07-12 CN CN201810767026.7A patent/CN108876475B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503714A (en) * | 2016-10-11 | 2017-03-15 | 湖州师范学院 | A kind of method that urban function region is recognized based on interest point data |
| CN106991142A (en) * | 2017-03-22 | 2017-07-28 | 湖州师范学院 | A kind of method that urban function region is recognized based on wechat data and interest point data |
Non-Patent Citations (3)
| Title |
|---|
| "基于公交刷卡数据和兴趣点数据的城市街区功能类型识别研究";钟少颖;《城市典环境研究》;20160331(第3期);第67-85页 * |
| "基于城市公交刷卡数据和兴趣点的城市";于翔;《中国优秀硕士学位论文 工程科技II辑》;20150315(第03期);全文 * |
| "基于大数据的用户轨迹及语义分析";丁秋林;《中国优秀硕士学位论文数据库 信息科技辑》;20180315(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108876475A (en) | 2018-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876475B (en) | City functional area identification method based on interest point acquisition, server and storage medium | |
| CN109101559B (en) | Urban functional area identification method based on POI and bus card swiping data | |
| CN106096631B (en) | A kind of floating population's Classification and Identification analysis method based on mobile phone big data | |
| CN106503714B (en) | Method for identifying city functional area based on point of interest data | |
| Wang et al. | Analyzing urban traffic demand distribution and the correlation between traffic flow and the built environment based on detector data and POIs | |
| CN105677804A (en) | Determination of authority stations and building method and device of authority station database | |
| CN103065205A (en) | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system | |
| Tang et al. | A mixed path size logit-based taxi customer-search model considering spatio-temporal factors in route choice | |
| Li et al. | Explore the recreational service of large urban parks and its influential factors in city clusters–Experiments from 11 cities in the Beijing-Tianjin-Hebei region | |
| CN110399402B (en) | Rail transit station classification method based on big data | |
| CN112579718B (en) | Urban land function identification method and device and terminal equipment | |
| WO2023050955A1 (en) | Urban functional zone identification method based on function mixing degree and ensemble learning | |
| Yuan et al. | Recognition of functional areas based on call detail records and point of interest data | |
| Mou et al. | Urban function identification based on POI and taxi trajectory data | |
| Mao et al. | Customer attractiveness evaluation and classification of urban commercial centers by crowd intelligence | |
| Hu et al. | Construction of a refined population analysis unit based on urban forms and population aggregation patterns | |
| CN116227791B (en) | Visual analysis method for exploring dynamic division of urban functional areas based on semantic fusion model | |
| Bolaños-Martinez et al. | Clustering pipeline for vehicle behavior in smart villages | |
| Chung et al. | Investigating the effects of POI-based land use on traffic accidents in Suzhou Industrial Park, China | |
| CN112288472A (en) | Street planning demand identification method based on multi-source big data | |
| CN117056823A (en) | Method and system for identifying occupation type of shared bicycle commuter user | |
| Xu et al. | What travel scenarios are the opportunities of car sharing? | |
| Yu et al. | Exploring taxi demand distribution of comprehensive land-use patterns using online car-hailing data and points of interest in Chengdu, China | |
| Morton et al. | Competition in Multi-Airport Regions: Measuring airport catchments through spatial interaction models | |
| CN111833229B (en) | Subway dependency-based travel behavior space-time analysis method and device |
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 |