CN104679942B - Construction land bearing efficiency measuring method based on data mining - Google Patents
Construction land bearing efficiency measuring method based on data mining Download PDFInfo
- Publication number
- CN104679942B CN104679942B CN201510047806.0A CN201510047806A CN104679942B CN 104679942 B CN104679942 B CN 104679942B CN 201510047806 A CN201510047806 A CN 201510047806A CN 104679942 B CN104679942 B CN 104679942B
- Authority
- CN
- China
- Prior art keywords
- data
- construction land
- activity
- bearing
- calculating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a construction land bearing efficiency measuring method based on data mining, which comprises the following steps: s1, data mining, wherein network open data are used as main data sources, traditional data such as census and the like are used as supplements, and spatial characteristics of bearing efficiency of the construction land are explored; s2, analyzing data, and analyzing addresses in the online shopping data and the enterprise data; s3, performing data space matching, and after data collection is completed, performing coordinate conversion on the address resolution data obtained by the method, converting the address resolution data into position data which can be used by a GIS platform, and performing association matching with the construction land; and S4, realizing the location difference measurement of the bearing efficiency of the construction land through comprehensive measurement based on the multivariate characteristics of the data. The invention adopts a data mining mode to obtain related network open data, reflects the social activities of micro individuals of enterprises or residents through space address matching, and solves the problem of measuring the bearing efficiency of construction land.
Description
Technical Field
The invention relates to the research field of bearing efficiency of construction land, in particular to a construction land bearing efficiency measuring method based on data mining.
Background
In the related research of the bearing efficiency of construction land, recent foreign scholars use an ordered response model to research the relationship between the land development strength and land owners (Nazneen Ferdous,2013), and are also involved in the diversified development of living activities (Yin, el al, 2011). In China, researchers have long proposed the necessity of intensive land use (Guxiang et al, 2006), and Zeng Yong et al (2004) have also studied matching land use with population size. Many scholars study the land utilization efficiency from an economic perspective, including establishing a theoretical model of the full-element land utilization efficiency (dawn waves, 2013), performing model study by using a DEA method (Yuan et al, 2009), and building Shi Yishao (2013) and comprehensively evaluating the land utilization in Guangzhou university city by using an entropy method, and exploring by using an analytic hierarchy process on the basis of the entropy method (Shang Tiancheng et al, 2009). However, the comprehensive land bearing capacity measure was not addressed by scholars until recently (zhu chi, 2013). Meanwhile, the characteristics and influence of the evolution of domestic construction land are under study (plum, 2013). However, existing research is mostly based on regional economic level and is not easy to discuss on spatial level, such economic-oriented research mode has the disadvantages that abstract regional scope level is over emphasized, efficiency evaluation cannot be performed on a specific land block due to data updating delay, and accuracy and timeliness of analysis results are affected to some extent.
The progress of information technology accelerates the space-time exchange of knowledge, technology, talents, funds and the like, the flow space becomes a main carrier of regional, urban and residential activities (Castells,1996), early learners propose that cities are high aggregates of crowd activities, the behaviors of people in cities occupy more dominant factors for urban research (i.gordon, 2008), and regional construction land production efficiency analysis dominated by statistical yearbook data just ignores the behavior characteristics of social individuals, which is one of the defects of the existing research.
In recent years, the emergence of big data has solved the problem of data shortage that has existed for a long time in the past to some extent, making quantitative analysis that is partially impossible feasible (Delyser, Sui, 2013). The method has great breakthrough in measuring urban activities, the economic, cultural, traffic, entertainment and other aspects of cities are closely combined with the informationized digital space (Wangshitong and so on 2014), and the data research on crowd activities and space distribution becomes possible through social tools such as microblogs and the like. At present, the research on the travel and traffic of residents is relatively more by applying big data, and data are mostly acquired from various ways such as telecom operators, social network sites, taxis, public transportation smart cards and the like for research (Becker, 2011; Kang, 2012; Mark, 2011; Naaman, 2012; Ying, Zhang, True and Prime, 2012; Batty, 2013). The emergence of related research results provides highly effective technical guidance for the development of urban and rural planning disciplines in a new period. Due to the real-time property of internet data updating, the geographic position of a user can be accurately positioned, and the range of people activity data research can be reduced to a specific block, so that the big data analysis of land bearing efficiency is more effective, and the problem that general statistical data cannot judge the specific land utilization efficiency is avoided.
In reality, the field of domestic planning is always clumsy on the measure of the bearing efficiency of the construction land and mostly depends on modes such as economic statistics yearbook data, and the like, and although the research mode of the large aperture can judge the quality of the urban construction environment under the macro scale, the research mode is limited by the limitation of the spatial scale and cannot judge the spatial characteristics of the land bearing efficiency more carefully. On the other hand, the bearing efficiency of the construction land cannot be separated from the activities of individual societies, and the bearing efficiency measure based on the statistical yearbook data can be used for calculating the overall urban development degree, but the structural measure easily ignores the spatial activity of the individual and even forms obvious fracture with the daily behaviors of citizens.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art and provide a construction land bearing efficiency measuring method based on data mining.
In order to achieve the purpose, the invention adopts the following technical scheme:
a construction land bearing efficiency measuring method based on data mining comprises the following steps:
s1, data mining, wherein network data are used as main data sources, traditional data such as census and the like are used as supplements, and spatial characteristics of bearing efficiency of the construction land are explored through mining and spatial positioning of various activity data; the network data comprises living activity data, employment activity data, recreation activity data, social network sites and online shopping consumption data;
s2, analyzing data, analyzing addresses in the online shopping data and the enterprise data, and converting text information of the addresses into longitude and latitude coordinates through the service function of a Geocoding API under a Web API page in a Baidu LBS open platform;
s3, space matching, after data collection is completed, coordinate conversion is carried out on the address analysis data obtained by the method, the address analysis data are converted into position data which can be used by a GIS platform, and correlation matching is carried out on the position data and the construction land;
s4, on the basis of data mining, analysis and spatial dimension reduction, based on the multivariate characteristics of data, realizing the location difference measurement of the bearing efficiency of the construction land through the comprehensive measurement, specifically including the spatial measurement of single-element data and the spatial superposition of the comprehensive data, specifically comprising the following steps:
s4.1, measuring the distribution density of each activity of living, enterprises and rest by the spatial measurement of single-element data, carrying out address analysis by utilizing multidimensional data of an open platform and an enterprise and public address list, acquiring the location distribution of each activity, and reflecting the single-element bearing strength of the whole city level by combining the density distribution conditions of construction land and population;
and S4.2, spatially superposing the comprehensive data, after performing spatial rasterization on various index values in each index element, determining index weight by integrating an entropy value method and an analytic hierarchy process, and performing subjective and objective comprehensive weighting calculation on the bearing strength of a single element, so as to form comprehensive evaluation on the bearing efficiency of the construction land and perform spatial discrimination on high-value and low-value areas.
Preferably, in step S1, the social network data includes data of the green microblog, and for the data acquisition of the green microblog, the text information and the geographic coordinate information of the released microblog are mainly acquired through a microblog interface and a geographic information interface in the microblog API service, specifically:
s1.1, filling in webpage application information according to related requirements, and acquiring an App Key and an App Secret;
s1.2, logging in an open platform of the Sina microblog, entering a data capture interface, setting parameters in a parameter setting area, clicking a calling interface, and displaying a result returned by the request;
s1.3, entering a '2/place/spare _ time' sub-interface in a geographic information interface, compiling a request URL according to request parameters, determining a captured central point, a search radius and start and stop time of search, and obtaining search contents in batches by Python files, wherein the search contents comprise: the method comprises the following specific steps of issuing time information, geographical coordinate information, issuing text content, user id, distance from a central point, gender and user location information of the microblog, and obtaining search content in batches through Python files:
s1.3.1, instantiating an APIClient class object, sending an Auth authentication request to a user, logging in by the client by using a stored user account password, and simulating to agree with authorization;
s1.3.2, obtaining URL after the user agrees to authorization:
YOUR _ REGISTERED _ DIRECT _ URI/? Monitoring the HTTP process, and intercepting the CODE value in a callback webpage;
s1.3.3, submitting code to API server, calling API by using obtained OAuth2.0Access Token;
s1.3.4, obtaining JSON format data containing the check-in number of POI points, microblogs with geographic positions, user information and other information by calling the interfaces of place/POIs/users, place/POIs/tips, place/POI _ time and the like;
s1.3.5, the data in the Json format is analyzed and stored locally.
Preferably, the network data further includes picture data, the capturing of the picture data is performed through a panoramio website, a URL for sending the http request is written according to a parameter requirement of a Web API service function under a Geocoding API page in a panoramio open platform, and data returned by the http request is sent and received in batch by means of locoySpider software.
Preferably, in step S2, the specific method of data analysis is:
s2.1, obtaining an API interface key;
s2.2, compiling a URL (uniform resource locator) for sending the http request by using the acquired key according to the parameter requirement;
and S2.3, sending and receiving data returned by the http request in batch by means of LocoySpider software, thereby completing address resolution of the text information.
Preferably, in step S4.1, in terms of single element measure of bearing efficiency of the construction site, starting from intensity distribution of three major basic activities, the number of the atomization data of living activities and recreational activities in the grid is summarized, enterprise activities are summarized by turnover, and activity intensity r of the kth element in the space unit i is calculatedikAnd carrying out normalization processing on the absolute intensity data of each activity, namely:
wherein SiArea of construction site for ith grid space cell, NiThe sum of the number of k activities of the ith grid; and displaying the spatial distribution in three dimensions by using Arcscene software.
Preferably, in step S4.2, in terms of comprehensive measure, the four types of subelement activity data are spatially superimposed on the population data, and a hierarchy Analysis (AHP) and an entropy weight method are integrated to perform weighted calculation on the five types of indexes, so as to form a comprehensive evaluation of the bearing efficiency of the construction land, where the comprehensive evaluation model of the construction land efficiency is:
composite weight alpha for each type of element activitykBy comprehensive empowerment method, note pk、qkRespectively represents k
The item elements are weighted by an analytic hierarchy process AHP weighting method and an entropy weighting method,
αk＝c1 *pk+c2 *qk (3)。
preferably, in S4.2, the weight p of each element is determined according to an analytic hierarchy process AHPkThe method specifically comprises the following steps:
s4.2.1, establishing a hierarchical structure model, and constructing a judgment matrix A;
s4.2.2, determining importance ranking of each element activity through pairwise ranking; for the judgment matrix A, the condition that AW is equal to lambda is calculatedmaxW, wherein λmaxIs the maximum characteristic root of A, W is the root corresponding to λmaxNormalized feature vector of (1), component W of WkThe weight values corresponding to the element list ordering are solved by applying a square root method to the normalized eigenvector and the eigenvalue; the method specifically comprises the following steps:
firstly, the n-th square root of the product of each row scale of the judgment matrix is calculated
MkJudging the value of each row element in the matrix;
normalizing the square root vector to obtain the kth component of the characteristic vector W
Finally calculating the maximum characteristic root of the judgment matrix
(AW)kIs the kth component of the vector AW;
s4.2.3, checking consistency, and determining the sequence of each element activity;
checking the consistency of the judgment matrix, and calculating the consistency index:
CI＝(λmax-k)/(k-1) (9)
comparing CI with the average random consistency index RI, recording as CR, and judging that the matrix has satisfactory consistency when CR is CI/RI < 0.10;
s4.2.4, determining the weight p of each element activity of the analytic hierarchy processk；
In the formula pkAs an index layer weight, ajThe weights of the elements of the criterion layer relative to the target layer,
presenting the weight of each factor relative to the criterion layer for the index;
overall rank consistency formula:
when CR is less than 0.10, the total ordering is considered to have satisfactory consistency, namely the weight of each element is obtained.
Preferably, q is calculated according to the entropy weight methodkDetermining objective weights of various activities, wherein the specific method comprises the following steps:
s4.2.5, calculating the constant population density of each unit by taking the town street as a unit;
s4.2.6, determining the weight coefficient according to the entropy method, if any
Wherein r ismax、rminRespectively representing the maximum value of the k-term elements in all grid cellsA minimum value;
s4.2.7 calculating entropy of each element evaluation index, defining
In the formula: i is 1,2, …, m; k is 1,2,3,4,5
Defining the entropy value of each element evaluation index according to the concept of entropy as follows:
due to fikWhen equal to 0, lnfikMeaningless, will fikAnd correcting, namely:
s4.2.8, calculating the entropy weight of each element by using the corrected measure indexes:
the above formula satisfies
Preferably, in step S4, the comprehensive measure of the bearing efficiency is specifically:
s5.1, calculating the comprehensive bearing efficiency of each grid unit;
s5.2, displaying the spatial distribution in a three-dimensional manner through Arcscene software, thereby obtaining the comprehensive evaluation of the bearing efficiency of the construction land;
s5.3, calculating low-value scores, searching space units with lower bearing efficiency through a difference method according to the finally determined comprehensive scores, normalizing the data, and calculating the low-value scores of the space units
S5.4, calculating the average value mu, calculating the arithmetic average value of the bearing efficiency of the construction land in all the grid units, wherein the number of effective grid units is m,
s5.5, calculating a standard deviation, and calculating the standard deviation of the bearing efficiency of the construction land for all the grid units according to the low values and the average values obtained by the calculation in the last two steps;
s5.6, distinguishing low-value areas, and finding bearing efficiency depression by the multiple of deviation of the average difference value of each unit from the standard deviation
S5.7, calculating the number N of each town street gridstThe number N of grid units contained in each town street is calculated by taking the town street as a unit and using GIS software to select large area as attributiont；
S5.8, judging the efficiency depression by taking the town streets as a unit, and calculating the average value of the number of bearing depression units of each town street construction depression deviating from the multiple of the standard deviation of the whole city;
therefore, whether the construction land of each town street belongs to the depression area with bearing efficiency is judged.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the existing construction land evaluation technology takes large spatial units such as cities, counties and districts as measurement objects, and is difficult to judge the land use efficiency of specific land parcels. The invention tries to acquire related network data by adopting a data mining mode, and solves the evaluation problem of the bearing efficiency of the construction land at the microscopic level by adopting a space matching correlation mode based on the social activities of individuals such as enterprises or residents.
2. The prior art depends on statistical data of national economy, and related judgment results depend on the existing statistical data. The invention utilizes network open data, enterprise directory data can be obtained by the business bureau, and the process of address resolution also utilizes the prior network open platform, thereby effectively overcoming the defect that the measured data is difficult to collect in the prior analysis technology.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2(a) -2 (d) are schematic diagrams of activity bearing efficiency represented by online shopping data, enterprise turnover, microblog data and picture data tables, respectively;
FIG. 3 is a schematic view illustrating comprehensive evaluation of bearing efficiency of the construction site in the present embodiment;
fig. 4 is a region schematic of low bearing efficiency value of the construction land for Dongguan in this embodiment.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the present invention is not limited thereto.
Examples
As shown in fig. 1, the method for measuring bearing efficiency of construction land based on data mining in the present embodiment includes the following steps:
(1) and data mining, wherein the method takes network data as a main data source and takes traditional data such as census and the like as supplement. The living activity data is derived from online shopping consumption data, address resolution is carried out through goods receiving information, and the living space position is obtained; employment activity data is from the 2014 enterprise and public institution directory; the rest activity data is derived from an open social network Sing-wave microblog platform (http:// open.weibo.com), and picture data of a pandoamio website (http:// www.panoramio.com) flagged by Google company is used as supplement to acquire geospatial information of microblogs issued by users and uploaded pictures. And exploring the space characteristics of the bearing efficiency of the construction land through the excavation and space positioning of each item of activity data. The social network site and online shopping consumption data acquisition time is 6-7 months in 2014, the picture data is all information contained in 2014 in 2006, the employment data source is an Yimei database, relevant geographic spatial coordinate information is spatially positioned by adopting a Baidu open platform, and the relevant geographic spatial coordinate information is introduced into a GIS system after coordinate correction.
(1-1) for data acquisition of the Sing microblog, text information and geographical coordinate information of a microblog released by the Sing microblog are mainly acquired through a microblog interface and a geographical information interface in a microblog API service, and the specific steps are as follows:
(1-1-1) filling in webpage application information according to related requirements, and acquiring an App Key and an App Secret; it should be noted that, although the two data are not directly involved in the subsequent steps, they are necessary steps for data capture.
(1-1-2) logging in an open platform of the Xinlang microblog, entering a data capture interface, inputting parameters in a frame of a parameter setting area, and clicking a calling interface to see a returned result in a green frame on the right side. The request parameter specification is shown in table 1.
TABLE 1 API test interface parameter description
(1-1-3) entering a '2/place/near _ time' sub-interface in the geographic information interface, compiling a request URL according to related request parameters, determining a captured central point, a search radius and start-stop time of search, and obtaining related contents in batches by using Python files compiled by authors. Available content includes: issuing time information, geographical coordinate information, issuing text content, user id, distance from a central point, gender, user location and the like of the microblog; the specific steps for obtaining the search content in batch through the Python file are as follows:
(1-1-3-1) instantiating an APIClient class object, sending an Auth authentication request to a user, logging in by using a stored user account password by a client, and simulating approval authorization;
(1-1-3-2) obtaining the URL after the user agrees to authorization:
YOUR _ REGISTERED _ DIRECT _ URI/? Monitoring the HTTP process, and intercepting the CODE value in a callback webpage;
(1-1-3-3) submitting the code to the API server, and calling the API by using the obtained OAuth2.0Access Token;
(1-1-3-4) obtaining JSON format data containing the check-in number of the POI points, microblogs with geographic positions, user information and the like by calling the interfaces of place/POIs/users, place/POIs/tips, place/POI _ time and the like;
and (1-1-3-5) analyzing the data in the Json format and storing the data in a local place.
(1-2) capturing picture data is mainly performed through a panoramio website (http:// www.panoramio.com), a URL (uniform resource locator) for sending an http request is compiled through a Web API service function under a Geocoding API page in a panoramio open platform according to parameter requirements, and data returned by the http request is sent and received in batches through LocoySpider software.
(2) And data analysis, namely performing address analysis on addresses in the online shopping data and the enterprise data. And converting the text information of the address into longitude and latitude coordinates through the service function of the Geocoding API under the Web API page in the Baidu LBS open platform. The method comprises the following specific steps:
(2.1) acquiring an API interface key;
(2.2) compiling a URL (uniform resource locator) for sending the http request by using the acquired key according to the parameter requirement of the key; as shown in table 2;
TABLE 2
Geocode specific request parameters:
and (2.3) sending and receiving the data returned by the http request in batches by means of LocoySpider software, thereby completing the address resolution of the text information.
(3) Performing space dimensionality reduction, and after data collection is finished, performing coordinate conversion on the address resolution data obtained by the method to convert the address resolution data into position data which can be used by a GIS platform; and dividing the space units for the construction land efficiency analysis. According to population scale control of 3-5 ten thousand in planning and design specifications (2002) about urban residential areas, rasterization and combination of the data are carried out for 2km x 2km, and the data are converted into spatial data which can be analyzed by GIS software.
The Dongguan is selected as an example demonstration in the aspect of case objects, and the accumulated development scale and economic level of the Dongguan in more than 30 years are improved, so that the space scale and data scale required by data mining are ensured.
(4) On the basis of data mining, analysis and spatial dimension reduction, based on the multivariate characteristics of data, the zone bit difference measurement of the bearing efficiency of the construction land is realized through comprehensive measurement, specifically comprising the spatial measurement of single-element data and the spatial superposition of the comprehensive data, specifically comprising the following steps:
(4.1) measuring the spatial measurement of single-element data, measuring the distribution density of each activity of living, enterprises and rest, performing address resolution by using multidimensional data of an open platform and an enterprise and public address list, acquiring the location distribution of each activity, and reflecting the single-element bearing strength of the whole city level by combining the density distribution conditions of construction land and population;
and (4.2) spatially superposing the comprehensive data, after spatial rasterization processing is carried out on various index values in each index element, determining index weight by integrating an entropy value method and an analytic hierarchy process, carrying out subjective and objective comprehensive weighting calculation on the bearing strength of a single element, thus forming comprehensive evaluation on the bearing efficiency of the construction land, and carrying out spatial discrimination on high-value and low-value areas.
In the step (4.1), in the aspect of single element measurement of bearing efficiency of the construction site, starting from the intensity distribution of three major basic activities, living activities and rest activities in the grid are firstly carried outThe amount of the atomization data is collected, the enterprise activities are collected through turnover, and the activity intensity r of the kth element in the space unit i is calculatedikAnd carrying out normalization processing on the absolute intensity data of each activity, namely:
wherein SiArea of construction site for ith grid space cell, NiThe sum of the number of k activities of the ith grid; the spatial distribution is then three-dimensionally displayed by Arcscene software, as shown in FIGS. 2(a) -2 (d).
And calculating to obtain a distribution diagram of the living activity bearing efficiency of the online shopping data. Wherein the living activity intensity of the skimmia street is the highest. At the urban level, the living activities of Dongguan also present a multi-center distribution pattern, but the living activities of other town streets besides the Dongguan street are closer in intensity
And calculating to obtain an enterprise activity bearing efficiency distribution map of the enterprise turnover. The polarization characteristic of Dongguan is obvious, the enterprise activities of Guancheng-Dongcheng and Changan are more advantageous than other towns, in addition, the enterprise activity intensity is relatively high near the Ju town of Guangzhou, and the enterprise activities of the Dongbai, the Chang wood and the like are weaker.
And calculating to obtain a recreation activity intensity distribution map of the microblog data. As shown in the figure, compared with activities of living and enterprises, activities of rest are distributed more widely, activities of rest of streets such as wanjiang and south cities are reflected, but most of the activities are concentrated in the center and peripheral areas of the city, and the trend of descending from the center area to the outside is obvious.
In comparison, the continuous trend of the rest activities represented by the picture data is more obvious, which shows that the rest activity range of residents is larger than that of the activities such as living, employment and the like, and the polarization characteristics are not obvious. The rest activities of the east city, the tea mountain, the camphor wood and the like have higher areas, and the overall activity intensity is higher. No obvious continuous area is formed along the high-speed line of the wide and deep river.
In the step (4.2), as shown in fig. 3, in the aspect of comprehensive measure, four types of subelement activity data and population data are spatially overlapped, a hierarchy analysis method (AHP) and an entropy weight method are integrated, and five types of indexes are weighted and calculated to form comprehensive evaluation of the bearing efficiency of the construction land, and the comprehensive evaluation model of the construction land efficiency is as follows:
composite weight alpha for each type of element activitykBy comprehensive empowerment method, note pk、qkRespectively represents k
The item elements are weighted by an analytic hierarchy process AHP weighting method and an entropy weighting method,
αk＝c1 *pk+c2 *qk (3)。
then, determining the weight p of each element according to the analytic hierarchy process AHPkThe method specifically comprises the following steps:
(4.2.1) establishing a hierarchical structure model and constructing a judgment matrix A;
(4.2.2) determining importance ranking of each element activity through pairwise ranking; for the judgment matrix A, the condition that AW is equal to lambda is calculatedmaxW, wherein λmaxIs the maximum characteristic root of A, W is the root corresponding to λmaxNormalized feature vector of (1), component W of WkThe weight values corresponding to the element list ordering are solved by applying a square root method to the normalized eigenvector and the eigenvalue; the method specifically comprises the following steps:
firstly, the n-th square root of the product of each row scale of the judgment matrix is calculated
MkJudging the value of each row element in the matrix;
normalizing the square root vector to obtain the kth component of the characteristic vector W
Finally calculating the maximum characteristic root of the judgment matrix
(AW)kIs the kth component of the vector AW;
(4.2.3) finally determining the sequence of each element activity through consistency inspection;
checking the consistency of the judgment matrix, and calculating the consistency index:
CI＝(λmax-k)/(k-1) (9)
comparing CI with the average random consistency index RI, recording as CR, and judging that the matrix has satisfactory consistency when CR is CI/RI < 0.10;
(4.2.4) determining the weight p of the activity of each element of the analytic hierarchy processk；
In the formula pkAs an index layer weight, ajThe weights of the elements of the criterion layer relative to the target layer,
presenting the weight of each factor relative to the criterion layer for the index;
overall rank consistency formula:
when CR is less than 0.10, the total ordering is considered to have satisfactory consistency, namely the weight of each element is obtained.
Then, q is calculated according to an entropy weight methodkDetermining objective weights of various activities, wherein the specific method comprises the following steps:
(4.2.5) calculating the constant population density of each unit by taking the town street as a unit;
(4.2.6) determining the weighting coefficients according to the entropy method, if any
Wherein r ismax、rminRespectively representing the maximum value and the minimum value of the k-term elements in all grid units;
(4.2.7) calculating the entropy of each element evaluation index. First define
In the formula: i is 1,2, …, m; k is a number of bits of 1,2,3,4,5,
defining the entropy value of each element evaluation index according to the concept of entropy as follows:
due to fikWhen equal to 0, lnfikMeaningless, will fikAnd correcting, namely:
(4.2.8) calculating the entropy weight of each element by using the corrected measure indexes:
the above formula satisfies
In step S4, the comprehensive measure of the bearing efficiency is specifically:
(4.3) calculating the comprehensive bearing efficiency of each construction land grid unit in a manner of combining subjectivity and objectivity;
(4.4) displaying the spatial distribution in a three-dimensional manner through Arcscene software, thereby obtaining the comprehensive evaluation of the bearing efficiency of the construction land;
(4.5) calculating low-value scores, searching space units with lower bearing efficiency through a difference method according to the finally determined comprehensive scores, normalizing the data, and calculating the low-value scores of the space units
(4.6) calculating the average value mu, calculating the arithmetic average value of the bearing efficiency of the construction land in all the grid cells, wherein the number of effective grid cells is m,
(4.7) calculating a standard deviation, and calculating the standard deviation of the bearing efficiency of the construction land of all the grid units according to the low values and the average values obtained by the calculation in the last two steps;
(4.8) distinguishing low value areas, and finding out bearing efficiency depression by the multiple of deviation of the average difference value of each space unit from the standard deviation
(4.9) calculating the number N of each street-ballast gridtThe number N of grid units contained in each town street is calculated by taking the town street as a unit and using GIS software to select large area as attributiont；
(4.10) judging the effective depression by taking the town streets as a unit, and calculating the average value of the number of bearing depression units of each town street construction depression deviating from the multiple of the standard deviation of the whole city;
therefore, whether the construction land of each town street belongs to the depression area with bearing efficiency is judged.
It can be seen from the contents of fig. 4 that the areas with higher bearing efficiency are still concentrated in the central area of the city, and the east side of eastern guan is close to the town street of huizhou, so that the overall bearing efficiency is lower. The construction land of the middle town has the lowest bearing efficiency, and the second towns are the enterprise town, the xiu sentry town and the camphorwood town. The bearing efficiency is higher than the average level, and the bearing efficiency of tiger door, east city, skimmia city, great ann and the like is higher. The area with the highest bearing efficiency is in the skimmia-dong city area, but is not neglected to be adjacent to town streets such as Juyong, Zhongtang and the like in Guangzhou, and the construction land is expanded in a large scale, and the bearing efficiency needs to be improved.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (5)
1. A construction land bearing efficiency measuring method based on data mining is characterized by comprising the following steps:
s1, data mining, wherein network data are used as main data sources, population census traditional data are used as supplements, and spatial characteristics of bearing efficiency of the construction land are explored through mining and spatial positioning of various activity data; the network data comprises living activity data, enterprise activity data, recreation activity data, social network site data and online shopping consumption data;
s2, analyzing data, analyzing addresses in online shopping consumption data and enterprise activity data, and converting text information of the addresses into longitude and latitude coordinates through the service function of a Geocoding API under a Web API page in a Baidu LBS open platform;
s3, space matching, after data collection is completed, coordinate conversion is carried out on the address resolution data obtained in the step S2, the address resolution data are converted into position data which can be used by a GIS platform, and correlation matching is carried out on the position data and the construction land;
s4, on the basis of data mining, analysis and spatial dimension reduction, based on the multivariate characteristics of data, realizing the location difference measurement of the bearing efficiency of the construction land through the comprehensive measurement, specifically including the spatial measurement of single-element data and the spatial superposition of the comprehensive data, specifically comprising the following steps:
s4.1, measuring the distribution density of each activity of living, enterprises and rest by the spatial measurement of single-element data, performing address resolution by utilizing multidimensional data of an open platform and an enterprise and public address list, acquiring the location distribution of each activity, and combining the density distribution conditions of construction land and population to obtain the single-element bearing strength reflecting the whole city level: living activity bearing strength, enterprise activity bearing strength, recreation activity bearing strength, and population density bearing strength;
s4.2, spatial superposition of comprehensive data, rasterizing index values of living activity bearing strength, enterprise activity bearing strength, recreation activity bearing strength and population density bearing strength, determining index weight of each single-element bearing strength by an integrated Analytic Hierarchy Process (AHP) and an entropy method, and performing subjective and objective comprehensive weighted calculation on the index values of each single-element bearing strength, thereby forming comprehensive evaluation of the bearing efficiency of the construction land, and performing spatial discrimination on high-value and low-value areas;
s4.2, determining the weight p of each element according to the analytic hierarchy process AHPkThe method specifically comprises the following steps:
s4.2.1, establishing a hierarchical structure model, and constructing a judgment matrix A;
s4.2.2, determining importance ranking of each element activity through pairwise ranking; for the judgment matrix A, the condition that AW is equal to lambda is calculatedmaxW, wherein λmaxIs the maximum characteristic root of A, W is the root corresponding to λmaxNormalized feature vector of (1), component W of WkThe weight values corresponding to the element list ordering are solved by applying a square root method to the normalized eigenvector and the eigenvalue; the method specifically comprises the following steps:
firstly, the n-th square root of the product of each row scale of the judgment matrix is calculated
MkJudging the value of each row element in the matrix;
normalizing the square root vector to obtain the kth component of the characteristic vector W
Finally calculating the maximum characteristic root of the judgment matrix
(AW)kIs the kth component of the vector AW;
s4.2.3, checking consistency, and determining the sequence of each element activity;
checking the consistency of the judgment matrix, and calculating the consistency index:
CI＝(λmax-k)/(k-1) (9)
comparing CI with the average random consistency index RI, recording as CR, and judging that the matrix has satisfactory consistency when CR is CI/RI < 0.10;
s4.2.4, determining the weight p of each element activity of the analytic hierarchy processk；
In the formula pkAs an index layer weight, ajThe weights of the elements of the criterion layer relative to the target layer,
presenting the weight of each factor relative to the criterion layer for the index;
overall rank consistency formula:
when CR is less than 0.10, the total ordering is considered to have satisfactory consistency, and the weight of each element is obtained;
computing q according to an entropy weight methodkDetermining objective weights of various activities, wherein the specific method comprises the following steps:
s4.2.5, calculating the constant population density of each unit by taking the town street as a unit;
s4.2.6, determining the weight coefficient according to the entropy method, if any
Wherein r ismax、rminRespectively representing the maximum value and the minimum value of the k-term elements in all grid units;
s4.2.7 calculating entropy of each element evaluation index, defining
In the formula: i is 1,2, …, m; k is 1,2,3,4
Defining the entropy value of each element evaluation index according to the concept of entropy as follows:
due to fikWhen equal to 0, lnfikMeaningless, will fikAnd correcting, namely:
s4.2.8, calculating the entropy weight of each element by using the corrected measure indexes:
equation (16) satisfies
In step S4.2, in the aspect of comprehensive measure, the index values of the living activity bearing strength, the enterprise activity bearing strength, the recreation activity bearing strength, and the population density bearing strength are weighted and calculated to form a comprehensive evaluation of the bearing efficiency of the construction land, and the comprehensive evaluation model of the construction land efficiency is as follows:
composite weight alpha for each type of element activitykBy comprehensive empowerment method, note pk、qkRespectively represents the weight obtained by weighting the k elements by an analytic hierarchy process AHP and an entropy weight process,
αk＝c1 *pk+c2 *qk (3)；
the comprehensive measure of the bearing efficiency is specifically as follows:
s5.1, calculating the comprehensive bearing efficiency of each grid unit;
s5.2, displaying the spatial distribution in a three-dimensional manner through Arcscene software, thereby obtaining the comprehensive evaluation of the bearing efficiency of the construction land;
s5.3, calculating low-value scores, searching space units with lower bearing efficiency through a difference method according to the finally determined comprehensive scores, normalizing the data, and calculating the low-value scores of the space units
S5.4, calculating the average value mu, calculating the arithmetic average value of the bearing efficiency of the construction land in all the grid units, wherein the number of effective grid units is m,
s5.5, calculating a standard deviation, and calculating the standard deviation of the bearing efficiency of the construction land for all the grid units according to the low values and the average values obtained by the calculation in the last two steps;
s5.6, distinguishing low-value areas, and finding bearing efficiency depression by the multiple of deviation of the average difference value of each unit from the standard deviation
S5.7, calculating the number N of each town street gridstThe number N of grid units contained in each town street is calculated by taking the town street as a unit and using GIS software to select large area as attributiont；
S5.8, judging the efficiency depression by taking the town streets as a unit, and calculating the average value of the number of bearing depression units of each town street construction depression deviating from the multiple of the standard deviation of the whole city;
therefore, whether the construction land of each town street belongs to the depression area with bearing efficiency is judged.
2. The method for measuring bearing efficiency of construction land based on data mining according to claim 1, wherein in step S1, the social network site data includes data of a green microblog, and for the data acquisition of the green microblog, text information and geographic coordinate information of a microblog issued by the social network site are mainly acquired through a microblog interface and a geographic information interface in a microblog API service, specifically:
s1.1, filling in webpage application information according to related requirements, and acquiring an App Key and an App Secret;
s1.2, logging in an open platform of the Sina microblog, entering a data capture interface, setting parameters in a parameter setting area, clicking a calling interface, and displaying a result returned by the request;
s1.3, entering a '2/place/spare _ time' sub-interface in a geographic information interface, compiling a request URL according to request parameters, determining a captured central point, a search radius and start and stop time of search, and obtaining search contents in batches by Python files, wherein the search contents comprise: the method comprises the following specific steps of issuing time information, geographical coordinate information, issuing text content, user id, distance from a central point, gender and user location information of the microblog, and obtaining search content in batches through Python files:
s1.3.1, instantiating an APIClient class object, sending an Auth authentication request to a user, logging in by the client by using a stored user account password, and simulating to agree with authorization;
s1.3.2, obtaining URL after the user agrees to authorization: YOUR _ REGISTERED _ DIRECT _ URI/? Monitoring the HTTP process, and intercepting the CODE value in a callback webpage;
s1.3.3, submitting the code to the API server, and calling the API by using the obtained OAuth2.0Access Token;
s1.3.4, obtaining JSON format data containing the check-in number of POI points, microblogs with geographic positions, user information and other information by calling the interfaces of place/POIs/users, place/POIs/tips, place/POI _ time and the like;
s1.3.5, the data in the Json format is analyzed and stored locally.
3. The construction land bearing efficiency measurement method based on data mining as claimed in claim 1, wherein the network data further includes picture data, the capturing of the picture data is performed through a pantomio website, through a Web API service function under a Geocoding API page in a pantomio open platform, according to parameter requirements, a URL sending an http request is compiled, and data returned by the http request is sent and received in batches by means of LocoySpider software.
4. The method for measuring bearing efficiency of construction land based on data mining as claimed in claim 1, wherein in step S2, the specific method for data analysis is:
s2.1, obtaining an API interface key;
s2.2, compiling a URL (uniform resource locator) for sending the http request by using the acquired key according to the parameter requirement;
and S2.3, sending and receiving data returned by the http request in batch by means of LocoySpider software, thereby completing address resolution of the text information.
5. The method for measuring bearing efficiency of construction land based on data mining as claimed in claim 1, wherein in step S4.1, in terms of single element measurement of bearing efficiency of construction land, starting from the intensity distribution of three major basic activities, the number of the atomized data of living activities and rest activities in the grid is summarized first, the enterprise activities are summarized by turnover, and the activity intensity r of the kth element in the space unit i is calculatedikAnd carrying out normalization processing on the absolute intensity data of each activity, namely:
wherein s isiArea of construction site for ith grid space cell, NikThe sum of the number of k activities of the ith grid; and displaying the spatial distribution in three dimensions by using Arcscene software.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047806.0A CN104679942B (en) | 2015-01-29 | 2015-01-29 | Construction land bearing efficiency measuring method based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510047806.0A CN104679942B (en) | 2015-01-29 | 2015-01-29 | Construction land bearing efficiency measuring method based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104679942A CN104679942A (en) | 2015-06-03 |
| CN104679942B true CN104679942B (en) | 2020-11-24 |
Family
ID=53314981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510047806.0A Active CN104679942B (en) | 2015-01-29 | 2015-01-29 | Construction land bearing efficiency measuring method based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104679942B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156756B (en) * | 2016-07-28 | 2019-04-09 | 广州地理研究所 | The Method of fast estimating of construction land efficiency spatial distribution |
| CN107730310A (en) * | 2017-09-30 | 2018-02-23 | 平安科技（深圳）有限公司 | Electronic installation, the method and storage medium for building Retail networks Rating Model |
| CN108763349B (en) * | 2018-05-15 | 2021-08-31 | 邢汉发 | Urban land utilization mixedness measuring and calculating method and system based on social media data |
| CN109255080A (en) * | 2018-07-31 | 2019-01-22 | 平安科技（深圳）有限公司 | A kind of information processing method and device |
| CN109977323B (en) * | 2019-03-13 | 2021-09-03 | 南京大学 | Commuting data batch acquisition method based on electronic map |
| CN112632209B (en) * | 2020-12-29 | 2021-08-17 | 智慧足迹数据科技有限公司 | Data association method and device, computer equipment and readable storage medium |
| CN113742918B (en) * | 2021-09-06 | 2023-10-20 | 中国科学院地理科学与资源研究所 | Method for evaluating national park recreation bearing capacity based on system dynamics model |
| CN113762793B (en) * | 2021-09-13 | 2023-08-01 | 哈尔滨工业大学 | Point distribution method of mobile rural garbage disposal equipment based on DEA and nuclear density |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101831895A (en) * | 2010-03-18 | 2010-09-15 | 天津市市政工程设计研究院 | Method for determining soft soil foundation landfill site foundation treatment mode based on foundation bearing capacity |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955505B (en) * | 2014-04-24 | 2017-09-26 | 中国科学院信息工程研究所 | A kind of event method of real-time and system based on microblogging |
-
2015
- 2015-01-29 CN CN201510047806.0A patent/CN104679942B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101831895A (en) * | 2010-03-18 | 2010-09-15 | 天津市市政工程设计研究院 | Method for determining soft soil foundation landfill site foundation treatment mode based on foundation bearing capacity |
Non-Patent Citations (3)
| Title |
|---|
| Spatial Planning: Indicators to Assess the Efficiency of Land Consumption and Land-Use;Harry Storch等;《Standards and Thresholds for Impact Assessment Environmental Protection in the European Union》;20081231;全文 * |
| 城市土地综合承载力评价研究——以杭州市为例;虞晓芬等;《中国房地产》;20120620;全文 * |
| 基于多维数据模型的城市建设用地数据挖掘研究——以北京市为例;关丽等;《地理与地理信息科学》;20121115;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104679942A (en) | 2015-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104679942B (en) | Construction land bearing efficiency measuring method based on data mining | |
| CN104750799B (en) | A kind of construction land type method for quickly identifying based on address resolution data | |
| Drummond et al. | The future of GIS in planning: Converging technologies and diverging interests | |
| O'sullivan et al. | Geographic information analysis | |
| CN107133900B (en) | Urban land mixed utilization feature grid computing method and device | |
| Choi et al. | Supporting the measurement of the United Nations’ sustainable development goal 11 through the use of national urban information systems and open geospatial technologies: a case study of south Korea | |
| Hai-ling et al. | A GIS-based approach for information management in ecotourism region | |
| Zandbergen | Influence of street reference data on geocoding quality | |
| Corcoran et al. | Characterising the metric and topological evolution of OpenStreetMap network representations | |
| Galimberti | Forecasting GDP growth from outer space | |
| Li et al. | Dynamic changes analysis and hotspots detection of land use in the central core functional area of Jing‐Jin‐Ji from 2000 to 2015 based on remote sensing data | |
| CN106547842A (en) | A kind of method that location-based emotion is visualized on virtual earth platform | |
| Bazazo et al. | The effect of electronic tourism in enabling the disabled tourists to communicate with the touristic and archaeological sites case study–Jordan | |
| Zhang | A high-performance web-based information system for publishing large-scale species range maps in support of biodiversity studies | |
| Khan | The spatial distribution and relationship of tourist flow in Turkey | |
| Ibragimov et al. | Introduction to GIS Application in the Land Cadastre | |
| CN111125553A (en) | Intelligent urban built-up area extraction method supporting multi-source data | |
| Sylaiou et al. | The volunteered geographic information in archaeology | |
| Kilic et al. | Effects of reverse geocoding on OpenStreetMap tag quality assessment | |
| Zhou et al. | Validation analysis of OpenStreetMap data in some areas of China | |
| Zhao et al. | Impacts of LiDAR sampling methods and point spacing density on DEM generation | |
| Lafreniere | Reconstructing the spatial and temporal patterns of daily life in the 19th century city: a historical GIS approach | |
| Goodspeed et al. | Crowdsourcing street beauty: Visual preference surveys in the big data era | |
| Engler et al. | The internet, spatial data globalization, and data use: The case of Tibet | |
| Agus et al. | Hybrid participatory GIS-decision support model for increasing community participation in urban spatial planning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |