CN113011925B - Commercial space quality evaluation method, system, equipment and medium based on big data - Google Patents

Commercial space quality evaluation method, system, equipment and medium based on big data Download PDF

Info

Publication number
CN113011925B
CN113011925B CN202110313101.4A CN202110313101A CN113011925B CN 113011925 B CN113011925 B CN 113011925B CN 202110313101 A CN202110313101 A CN 202110313101A CN 113011925 B CN113011925 B CN 113011925B
Authority
CN
China
Prior art keywords
commercial
street view
index
street
data
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
Application number
CN202110313101.4A
Other languages
Chinese (zh)
Other versions
CN113011925A (en
Inventor
魏宗财
彭丹丽
陈桂宇
魏纾晴
黄绍琪
刘晨瑜
唐琦婧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN202110313101.4A priority Critical patent/CN113011925B/en
Publication of CN113011925A publication Critical patent/CN113011925A/en
Priority to PCT/CN2021/120952 priority patent/WO2022198963A1/en
Priority to AU2021435561A priority patent/AU2021435561A1/en
Application granted granted Critical
Publication of CN113011925B publication Critical patent/CN113011925B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Probability & Statistics with Applications (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Fuzzy Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Remote Sensing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Indicating And Signalling Devices For Elevators (AREA)
  • Signal Processing For Digital Recording And Reproducing (AREA)

Abstract

The invention discloses a commercial space quality evaluation method, a system, equipment and a medium based on big data, wherein the method comprises the following steps: acquiring POI data and public comment data in a research range, generating a plurality of street view acquisition points and acquiring corresponding street view image data; calculating two indexes, and representing objective evaluation; obtaining attention indexes of commercial facilities according to the public comment data; constructing a random forest model, evaluating the score values of the secondary indexes of the street view image data of each street view acquisition point by using the trained random forest model to obtain the score values of three indexes, and forming a primary index together with the attention of commercial facilities to characterize subjective evaluation; and calculating the score values of the objective evaluation index and the subjective evaluation index of each street view acquisition point to obtain the comprehensive evaluation of the commercial space quality. The invention integrates objective and subjective evaluation of commercial space quality, and realizes large-scale and high-precision measurement of commercial space quality by using a machine learning algorithm.

Description

Commercial space quality evaluation method, system, equipment and medium based on big data
Technical Field
The invention relates to the field of commercial space quality evaluation, in particular to a commercial space quality evaluation method, a commercial space quality evaluation system, a commercial space quality evaluation computer device and a commercial space quality evaluation storage medium based on big data.
Background
Commercial space is a high activity area of a city, attracting a large population of people. With the development of cities, traditional commercial spaces face various problems such as traffic jams, aging of building facilities, decline of vitality and the like. In recent years, the rapid development of mobile information communication technology and the popularization of smart phones accelerate the development and penetration of online shopping, bring huge impact to urban commercial space, and the improvement of the quality of the urban commercial space becomes a key for maintaining the competitiveness of the urban commercial space.
The existing research on the quality of the commercial space mostly adopts traditional questionnaires, field surveys and other modes, which are suitable for evaluating the quality of the commercial space in a small range, but the accurate measurement of the quality of the commercial space in a large-range area, even in the whole city, is difficult to realize. On the other hand, the measure of the commercial space quality should not only comprise objective commercial facilities, but also subjective individual demands and feelings, but most of the existing researches focus on a certain aspect, and the combination of subjective and objective elements is less, so that the urban commercial space quality is comprehensively measured.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a commercial space quality evaluation method, a system, a computer device and a storage medium based on big data, which can be used for evaluating large-scale commercial space quality, combining principal and objective factors and comprehensively evaluating the commercial space quality, so that the evaluation result is more in line with objective reality.
A first object of the present invention is to provide a commercial space quality evaluation method based on big data.
A second object of the present invention is to provide a commercial space quality evaluation system based on big data.
A third object of the present invention is to provide a computer device.
A fourth object of the present invention is to provide a storage medium.
The first object of the invention can be achieved by adopting the following technical scheme:
a method of commercial space quality assessment based on big data, the method comprising:
acquiring POI data and public comment data in a research range;
generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point;
calculating traffic convenience indexes and commercial state richness indexes of each street view acquisition point according to the POI data, and representing objective evaluation on commercial space quality;
Counting the total evaluation quantity of each street view acquisition point according to the public comment data to obtain a attention index of commercial facilities;
constructing a random forest model, and training the random forest model by utilizing data generated by the street view image data;
evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model to respectively obtain the score values of the commercial street space, the commercial space atmosphere and the commercial building elevation index, and forming a primary index together with the attention of commercial facilities to represent subjective evaluation of commercial space quality;
and calculating to obtain comprehensive evaluation of the commercial space quality according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality.
Further, generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point, specifically including:
determining commercial areas to be evaluated in the research scope according to the POI data;
and generating a plurality of street view acquisition points in the business area, and acquiring corresponding street view image data at each street view acquisition point.
Further, the determining the commercial area to be evaluated in the research scope according to the POI data specifically includes:
Screening out commercial facility POIs from the POI data, performing cluster analysis on the commercial facility POIs, and classifying the commercial facility POIs into a plurality of classes according to the distribution density of the commercial facility POIs;
and synthesizing POI points of the same cluster into a region serving as a business region to be evaluated.
Further, generating a plurality of street view acquisition points in the business area, and acquiring corresponding street view image data at each street view acquisition point, specifically including:
selecting road network data in each business area;
generating a plurality of street view acquisition points at set intervals based on the road network data;
and respectively acquiring street view images of four horizontal visual angles parallel to and perpendicular to the road direction according to the road direction of each street view acquisition point, and eliminating the non-street view images and repeated acquisition points.
Further, the calculating the traffic convenience index and the commercial amateur state richness index of each street view acquisition point according to the POI data specifically includes:
according to the POI data, acquiring the spatial distribution conditions of bus stations and subway stations and the spatial distribution conditions of various commercial facilities;
respectively summarizing the number of bus stations and the number of subway stations of each street view acquisition point, and calculating the traffic convenience index of each street view acquisition point:
Figure BDA0002990074080000031
Wherein Q is i For the number of buses with the ith street view acquisition point in a first preset range, Q max For the maximum number of bus stations, ri is the number of subway stations of which the ith street view acquisition point is in a second preset range, and Rmax is the maximum number of subway stations; a, b respectively represent importance weight values of bus stations and subway stations;
counting the number of commercial property types of each street view acquisition point in a third preset range, and calculating the commercial property mixing degree of each street view acquisition point by adopting shannon entropy:
Figure BDA0002990074080000032
wherein m is the number of commercial amateur types, and the commercial amateur types comprise catering, shopping, finance, life service and leisure entertainment; t (T) j The number of the commercial facility POIs of the commercial property type j accounts for the proportion of the number of all commercial facility POIs of the ith street view acquisition point in a third preset range;
calculating commercial richness indexes of each street view acquisition point:
Figure BDA0002990074080000033
wherein P is i Commercial property mixing degree, P, for ith street view acquisition point max Maximum commercial off-state mix; u (U) i For the number of POIs of commercial facilities with the ith street view acquisition point in a third preset range, U max Is the maximum number of commercial establishment POIs; x and y represent weights for commercial property mixes and the number of commercial facilities, respectively.
Further, the constructing a random forest model, and training the random forest model by using the data generated by the street view image data specifically includes:
semantic segmentation is carried out on the street view image data by using a full convolution neural network, and feature data of the street view image data are obtained;
randomly selecting part of street view image data, and acquiring the score input by a volunteer aiming at a secondary index of the street view image data as scoring sample data; the secondary indexes of the street view image data comprise the cleanliness of industrial streets, the suitability of the aspect ratio of the commercial streets, the openness of the commercial streets, the walkability of the commercial streets, the greening degree of the commercial streets, the atmosphere of commercial spaces and the cleanliness of the elevation of commercial buildings;
constructing a random forest model, and randomly selecting partial data and corresponding street view image characteristic data from scoring sample data as a training set;
in the training set, training a random forest model by taking scoring sample data as a dependent variable and street view image characteristic data as an independent variable;
and when the model performance measurement index reaches a standard value, training of the random forest model is completed.
Further, the step of evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model to respectively obtain the score values of the indexes of the commercial street space, the commercial space atmosphere and the commercial building elevation, specifically comprises the following steps:
And evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model, and summing the score values of the secondary index to obtain the score values of the indexes of the commercial street space, the commercial space atmosphere and the commercial building elevation.
Further, the calculating to obtain the comprehensive evaluation of the commercial space quality according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality specifically includes:
the evaluation weight of the traffic convenience index K and the commercial richness index D is calculated according to statistics to be w Ki 、w Di The evaluation weights of the commercial street space STR, the commercial space atmosphere ENV, the commercial building facade BUI and the commercial facility attention ATT are s 1i 、s 2i 、s 3i 、s 4i The importance weight value of the objective evaluation index and the subjective evaluation index is g 1i 、g 2i ；
The method comprises the following steps of adopting dimensionless treatment on commercial street space indexes, commercial space atmosphere indexes, commercial building elevation indexes and attention indexes of commercial facilities, wherein the dimensionless treatment comprises the following formula:
Figure BDA0002990074080000041
Figure BDA0002990074080000042
Figure BDA0002990074080000043
Figure BDA0002990074080000044
wherein STR i 、ENV i 、BUI i 、ATT i Score values of the ith street view collection point commercial street space index, commercial space atmosphere index, commercial building elevation index and commercial facility attention index are respectively STR (short distance channel) max 、ENV max 、BUI max 、ATT max Respectively representing the maximum value of the score values of the corresponding indexes;
And calculating to obtain the comprehensive evaluation value of the commercial space quality of the street view acquisition point i according to the following formula:
C i ＝g 1i (w Ki K i +w Di D i )+g 2i (s 1i O STRi +s 2i O ENVi +s 3i O BUIi +s 4i O ATTi )×100
wherein K is i 、D i The traffic convenience index and the commercial richness index of the ith street view collection point are respectively.
The second object of the invention can be achieved by adopting the following technical scheme:
a big data based commercial space quality assessment system, the system comprising:
the data acquisition module is used for acquiring POI data and public comment data in a research range;
the generating street view acquisition point module is used for generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point;
the objective evaluation module is used for calculating the traffic convenience index and the commercial state richness index of each street view acquisition point according to the POI data and representing objective evaluation on commercial space quality;
the attention degree module of the commercial facility is used for counting the total evaluation quantity of each street view acquisition point according to the public comment data to obtain attention degree indexes of the commercial facility;
the random forest module is used for constructing a random forest model, and training the random forest model by utilizing data generated by the street view image data;
The subjective evaluation module is used for evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model to respectively obtain the score values of the commercial street space, the commercial space atmosphere and the commercial building elevation index, and the score values and the attention degree of the commercial facilities form a primary index together to represent subjective evaluation on the quality of the commercial space;
and the comprehensive evaluation module is used for calculating and obtaining the comprehensive evaluation of the commercial space quality according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality.
The third object of the present invention can be achieved by adopting the following technical scheme:
a computer device comprising a processor and a memory for storing a program executable by the processor, the processor implementing the commercial space quality assessment method described above when executing the program stored by the memory.
The fourth object of the present invention can be achieved by adopting the following technical scheme:
a storage medium storing a program which, when executed by a processor, implements the commercial space quality assessment method described above.
Compared with the prior art, the invention has the following beneficial effects:
The invention adopts the combination of the machine learning algorithm and the street view image to construct a random forest model for evaluating the commercial space quality, which is beneficial to realizing large-scale and high-precision measurement of the urban commercial space quality; and meanwhile, by combining with other types of big data, the quality of the commercial space is evaluated from an objective level, and subjective perception of microcosmic individuals on the quality of the commercial space is fused, namely, the quality of the commercial space is comprehensively evaluated from two dimensions of main dimension and objective dimension, so that the evaluation result is more in line with objective reality.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a commercial space quality evaluation method based on big data of embodiment 1 of the present invention.
FIG. 2 is a distribution diagram of business areas of a more scenic spot according to example 1 of the present invention.
Fig. 3 is a spatial distribution diagram of traffic convenience index in a more-to-show area according to embodiment 1 of the present invention.
FIG. 4 is a spatial distribution of commercial richness index for the more scenic region of example 1 of the present invention.
Fig. 5 is a spatial distribution diagram of subjective evaluation index of the more beautiful area according to example 1 of the present invention.
FIG. 6 is a spatial distribution diagram for comprehensive evaluation of commercial spatial quality in a more-to-show area according to example 1 of the present invention.
Fig. 7 is a block diagram showing the construction of a commercial space quality evaluation system according to embodiment 2 of the present invention.
Fig. 8 is a block diagram showing the structure of a computer device according to embodiment 3 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Example 1:
in the embodiment, the Guangzhou city viewful area is taken as an example, and the commercial space quality evaluation method based on big data is provided, and a model for evaluating the commercial space quality is constructed by adopting the combination of multi-source big data and a machine learning algorithm, so that the commercial space quality of a large range of cities is accurately evaluated.
As shown in fig. 1, the commercial space quality evaluation method based on big data includes the following steps:
s1, data acquisition and processing.
Firstly, POI data, OSM road network data and public comment data of the Guangzhou urban off-show area are obtained, commercial facility POIs are screened from the POI data, and commercial areas to be evaluated in the research range are further analyzed and determined. And selecting road network data in the business area, and determining the positions of street view acquisition points at specific intervals along the road network. And based on the position coordinates of the acquisition points, crawling street view image data from the hundred-degree map open platform.
Further, the specific implementation manner of step S1 is as follows:
screening commercial facility POIs from the acquired POI data, performing DBSCAN cluster analysis on the commercial facility POIs by using ArcGIS Pro software, and classifying the commercial facility POIs into a plurality of classes according to the distribution density of the commercial facility POIs; and synthesizing POI points of the same cluster into a surface area through an European distribution tool. Specifically, since the distribution density of POIs in the urban commercial area is far higher than that in the community commercial area, in order to avoid the loss of the community commercial area, two clustering analyses are sequentially performed. Firstly, performing DBSCAN cluster analysis on all POIs of commercial facilities, and setting the minimum clustering pixel number as e to obtain POI clusters of a core commercial area; and secondly, removing clustered POIs of the core business region, performing secondary DBSCAN cluster analysis on the rest POIs, and setting the minimum clustering element number as f (e > f) to obtain POI clusters of the secondary core business region. On this basis, the results of the two clusters were converted into areas using the European distribution tool as the business area for this study.
In particular, to the View area of Guangzhou city, the business area distribution is shown in FIG. 2, wherein the core business area is mainly distributed in Beijing area, ring city area, chinese square, santa Classification, five sheep and other areas, and the secondary core business area is mainly distributed near the core business area, such as east Xian Li district, six banyan street-like blessing community, northwest area and the like.
The street view image of the embodiment is from a hundred-degree map open platform (http:// lbsyun. Baidu. Com), and road network data in each business area is selected according to the business area range. Based on the road network data, a plurality of street view acquisition points are generated at specific intervals by using a densification tool in the ArcGIS Pro. And respectively acquiring street view images of four horizontal visual angles parallel to and perpendicular to the road direction according to the road direction of each acquisition point. And finally, 9424 street view images on 2356 acquisition points in the commercial area of the Guangzhou city View district are obtained after the street view images and repeated acquisition points are removed.
S2, objectively evaluating.
And measuring traffic convenience indexes and commercial property state richness indexes in the commercial area, namely acquiring the spatial distribution condition of public transportation stations (including bus stations and subway stations) and the spatial mixing degree of various commercial facilities by using POI data of the Vietnam commercial region, and representing objective evaluation on commercial space quality.
Further, the specific implementation manner of step S2 is as follows:
in the aspect of objective evaluation of commercial space quality, starting from a traffic convenience index and a commercial richness index, firstly, respectively summarizing the number of bus stations in a buffer area range of 500 meters at each acquisition point and the number of subway stations in a buffer area range of 1000 meters at each acquisition point, and then calculating the traffic convenience index of each acquisition point:
Figure BDA0002990074080000071
wherein Q is i 500m buffer for the ith acquisition pointBus station number in the flushing area range; q (Q) max The number of the largest bus stations; ri is the number of subway stations within the 1000m buffer area of the ith acquisition point; rmax is the maximum subway station number; wherein a and b respectively represent importance weight values of bus stations and subway stations in a commercial area by adopting a network questionnaire, and the bus is obtained through statistics: subway=a: b=0.08: 0.92. on this basis, the spatial distribution of the traffic convenience index is represented by a nuclear density analysis.
As shown in fig. 3, the regions with the best traffic convenience are mainly distributed in the memorial hall, the north of the great square of the group, the three roads of the big sand head and the district, and the regions such as the post and telecommunication district, the north of the intersection of the liberation south road and the great new road, and the like. Notably, the urban residents in Guangzhou mostly consider that the importance of subway stations around a commercial area is much higher than that of bus stations, and thus the convenience of traffic in commercial areas near the subway stations is generally high.
Further, counting the number of commercial property types in the 100 m buffer area range of each acquisition point, and calculating the commercial property mixing degree of each acquisition point by adopting shannon entropy:
Figure BDA0002990074080000081
wherein m is the number of business performance types, and the business performance types j are catering, shopping, finance, life service, leisure entertainment and the like; t (T) j The number of facility POIs of business performance type j is a proportion of the number of all business facility POIs in the 100 meter buffer range of the ith acquisition point. On this basis, the commercial richness index of each collection point is calculated:
Figure BDA0002990074080000082
wherein P is i Commercial property mixing degree, P, for the ith collection point max Maximum commercial off-state mix; u (U) i For the quantity of POIs of commercial facilities in the range of 100 m buffer area of the ith acquisition point, U max For maximum commercial establishment POI quantityThe method comprises the steps of carrying out a first treatment on the surface of the Wherein x and y respectively represent weights of commercial property state mixture degree and commercial facility quantity obtained by adopting a web questionnaire; statistical results show that the commercial business state mixing degree: number of commercial facilities = x: y=0.89: 0.11. on this basis, the spatial distribution of commercial richness index is represented by nuclear density analysis.
As shown in fig. 4, the high value areas of the commercial richness index are mainly distributed at the intersections of the memorial hall, foot Jing Lu, five sheep , the eastern road of the city of the ring and the first southward road and near the three roads of the big sand head, while the commercial richness index of the areas of the Beijing road business circle, the Chinese square, the ternary lining and the like is relatively low.
S3, machine learning.
And performing semantic segmentation on the acquired street view image data by using a full convolution neural network to acquire the feature data of the street view image. And randomly selecting part of street view image data to perform manual scoring to obtain scoring sample data.
Constructing a random forest model for evaluating the quality of a commercial space, taking 75% of scoring sample data and corresponding street view image characteristic data as a training set, and taking the rest 25% of scoring sample data and street view image characteristic data as a prediction set; and training a random forest model by taking the scoring sample data as an independent variable and the image characteristic data as an independent variable.
Further, the specific implementation manner of step S3 is as follows:
first, the acquired street view images are semantically segmented using a fully convolutional neural network FCN-8s (Yao Y, et al, 2019) developed by cug.hpscil laboratory, which can predict each pixel in each street view image as one of 151 feature types including "unknown" and further acquire segmented PNG image files and image feature statistics csv files (including image feature data). And secondly, selecting four volunteers with building or urban and rural planning professional backgrounds, randomly extracting 800 street view images of 200 acquisition points from each volunteer, and giving scoring values of various indexes according to the cognition of the volunteers on the commercial space quality. The index for evaluating the quality of the commercial space determined in this embodiment includes 87 secondary indexes of the cleanliness of the commercial street, the suitability of the aspect ratio of the commercial street, the openness of the commercial street, the walkability of the commercial street, the greening degree of the commercial street, the atmosphere of the commercial space and the cleanliness of the elevation of the commercial building, wherein the scoring fields of the indexes are set as [0, n ],0 is the lowest score, n is the highest score, and n is greater than 0. And finally obtaining scoring results of 800 acquisition points as scoring sample data.
Further, constructing a random forest model for evaluating the quality of the commercial space, and taking the obtained 800 scoring sample data as a data set of a training and predicting model;
specifically, randomly selecting a commercial space quality index scoring result of 75% of street view images and corresponding street view image characteristic data from the scoring sample data as a training set, and taking the rest 25% of street view image scoring results and street view image characteristic data as a test set. And further taking the commercial space quality index score as an independent variable, taking the street view image characteristic data as the independent variable, and training a random forest model for commercial space quality assessment. When the model performance measurement index reaches a standard value (specifically, the classification precision reaches 0.8, and the kappa coefficient is more than or equal to 0.6), the random forest model training is completed.
The model performance measurement index is the classification precision and Kappa coefficient of the commercial space quality evaluation random forest model on a test set, wherein the classification precision refers to the proportion of a street view image with correct scoring to all images of the test set, and the classification precision reaches 0.8 to indicate that the accuracy of a prediction result is higher; and the Kappa coefficient is used for evaluating the correlation degree of the predicted result and the scoring result of the volunteer, wherein the Kappa coefficient is more than or equal to 0.6, and the correlation of the predicted result and the scoring result is good.
S4, subjective evaluation.
And measuring attention indexes of commercial facilities according to the evaluation data of the public critique.
And (3) evaluating 87 secondary index scores of street view images in the commercial area by using the random forest model trained in the step (S3), further summing to obtain score values of commercial street space, commercial space atmosphere and commercial building elevation indexes, and forming 4 primary indexes together with commercial facility attention indexes to represent subjective evaluation of individuals on commercial space quality.
Further, the specific implementation manner of step S4 is as follows:
based on the obtained public comment evaluation data, the total evaluation quantity of public comment shops in the range of a 100-meter buffer area of each acquisition point is counted to represent the attention degree of commercial facilities.
And (3) evaluating scores of 7 secondary indexes in the commercial area on a large scale by using the trained random forest model, further summing to obtain score values of commercial street space, commercial space atmosphere and commercial building elevation indexes, and forming 4 primary indexes together with commercial facility attention to represent subjective evaluation of individuals on commercial space quality. On this basis, the spatial distribution of the first-order index scores of each subjective evaluation is represented by nuclear density analysis.
As shown in fig. 5, the area of highest interest in commercial facilities is beijing road business district, next, the ring city eastern business district, the north side of the large square of the group, and the attractive levels of the two are equivalent. The scores of commercial street space, commercial space atmosphere and commercial building elevation indexes in Guangzhou railway stations, foot Jing Lu, ring city eastern business circles, memorial halls, northways, big sand head three roads, five sheep , and northern sides of a large square of group A are all higher. From the above index scores, the areas with higher overall subjective evaluation level of commercial space quality are Guangzhou railway station, foot Jing Lu, guangdong business district, commemorative hall, and big sand three roads.
S5, comprehensively evaluating.
Weighting and calculating subjective and objective commercial space quality indexes of commercial facilities to form a comprehensive evaluation chart of commercial space quality evaluation, and determining weights by adopting network questionnaire investigation on 2 objective evaluation indexes and the first-level indexes of 4 subjective evaluations in the step S4 in the aspect of concrete calculation; the comprehensive weights are further determined in the same manner.
Further, the specific implementation manner of step S5 is as follows:
first, the evaluation weight w of the traffic convenience index (K) and the commercial richness index (D) is obtained according to the network questionnaire statistics Ki 、w Di Evaluation weight s of commercial street Space (STR), commercial space atmosphere (ENV), commercial building facade (BUI), and commercial facility Attention (ATT) 1i 、s 2i 、s 3i 、s 4i . Statistical result shows that w Ki ：w Di ＝0.47：0.53；s 1i ：s 2i ：s 3i ：s 4i =0.36: 0.28:0.20:0.16. obtaining an importance weight value g of objective evaluation indexes and subjective evaluation indexes by adopting network questionnaire survey statistics 1i 、g 2i G is obtained through statistics 1i ：g 2i ＝0.56：0.44。
Secondly, as the magnitude order difference of each subjective first-order index is larger, dimensionless treatment is adopted for each subjective first-order index:
Figure BDA0002990074080000101
Figure BDA0002990074080000102
Figure BDA0002990074080000103
Figure BDA0002990074080000104
wherein STR i 、ENV i 、BUI i 、ATT i Score, STR, of index of interest of business street space, atmosphere of business space, business building elevation and business facility of ith acquisition point respectively max 、ENV max 、BUI max 、ATT max Respectively represent the maximum value of the corresponding index score.
Thus, the comprehensive evaluation value of the commercial space quality of the acquisition point i is obtained:
C i ＝g 1i (w Ki K i +w Di D i )+g 2i (s 1i O STRi +s 2i O ENVi +s 3i O BUIi +s 4i O ATTi )×100
wherein K is i 、D i The traffic convenience index and the commercial richness index of the ith street view collection point are respectively.
According to the method, the commercial space quality in the off-show area is evaluated in a subjective and objective mode, the comprehensive evaluation result is shown in fig. 6, and the comprehensive evaluation high-value area is concentrated in the areas such as a memorial hall, an foot Jing Lu, a district village, the northern side of a large square of a group, a three-road of a large sand head and the like.
In summary, the invention searches the commercial space quality evaluation application based on big data by selecting the typical commercial area to perform data mining, street view image semantic segmentation and machine learning. In the aspect of objective evaluation, evaluating the traffic convenience index and the commercial richness index of the commercial area by using the acquired multi-source big data; in the aspect of subjective evaluation, seven dimension index systems are constructed, street view images are manually scored from the dimensions, a random forest model for evaluating commercial space quality is constructed by using a machine learning algorithm, and the random forest model is used for predicting subjective evaluation of large-scale commercial space quality. On the basis of the above, the weight calculation is carried out on the subjective and objective evaluation of the commercial space, so as to form the comprehensive evaluation of the commercial space quality score. The method evaluates the quality of the commercial space from an objective level, fuses subjective perception of microscopic individuals on the quality of the commercial space, and simultaneously utilizes a machine learning algorithm to be beneficial to realizing large-scale and high-precision measurement on the quality of the commercial space of the city.
Those skilled in the art will appreciate that all or part of the steps in a method implementing the above embodiments may be implemented by a program to instruct related hardware, and the corresponding program may be stored in a computer readable storage medium.
It should be noted that although the method operations of the above embodiments are depicted in the drawings in a particular order, this does not require or imply that the operations must be performed in that particular order or that all illustrated operations be performed in order to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.
Example 2:
as shown in fig. 7, the present embodiment provides a commercial space quality evaluation system based on big data, which includes a data acquisition module 701, a street view acquisition point generation module 702, an objective evaluation module 703, a attention degree module 704 of a commercial facility, a random forest construction module 705, a subjective evaluation module 706 and a comprehensive evaluation module 707, wherein the specific functions of the modules are as follows:
an acquisition data module 701, configured to acquire POI data and public critique data within a research scope;
The streetscape acquisition point generation module 702 is configured to generate a plurality of streetscape acquisition points according to the POI data, and acquire corresponding streetscape image data at each streetscape acquisition point;
an objective evaluation module 703, configured to calculate, according to the POI data, a traffic convenience index and a commercial status richness index of each street view acquisition point, and characterize objective evaluation on commercial space quality;
the attention degree module 704 of the commercial facility is configured to count the sum of the evaluation numbers of the street view acquisition points according to the public comment data, so as to obtain an attention degree index of the commercial facility;
the random forest module 705 is configured to construct a random forest model, and train the random forest model by using data generated by the street view image data;
the subjective evaluation module 706 is configured to evaluate, using the trained random forest model, score values of secondary indexes of the street view image data of each street view acquisition point, to obtain score values of indexes of commercial street space, commercial space atmosphere, and commercial building facade, and form a primary index together with the attention degree of the commercial facility, so as to characterize subjective evaluation of quality of the commercial space;
and the comprehensive evaluation module 707 is configured to obtain a comprehensive evaluation of the quality of the commercial space according to the objective evaluation of the quality of the commercial space and the subjective evaluation of the quality of the commercial space, and calculate the comprehensive evaluation of the quality of the commercial space.
Specific implementation of each module in this embodiment may be referred to embodiment 1 above, and will not be described in detail herein; it should be noted that, in the system provided in this embodiment, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be performed by different functional modules according to needs, that is, the internal structure is divided into different functional modules to perform all or part of the functions described above.
Example 3:
the present embodiment provides a computer apparatus, which may be a computer, as shown in fig. 8, including a processor 802, a memory, an input device 803, a display 804 and a network interface 805, which are connected through a system bus 801, the processor being configured to provide computing and control capabilities, the memory including a nonvolatile storage medium 806 and an internal memory 807, the nonvolatile storage medium 806 storing an operating system, a computer program and a database, the internal memory 807 providing an environment for the operating system and the computer program in the nonvolatile storage medium, and the processor 802 executing the computer program stored in the memory implementing the commercial space quality evaluation method of the above embodiment 1, as follows:
Acquiring POI data and public comment data in a research range;
generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point;
calculating traffic convenience indexes and commercial state richness indexes of each street view acquisition point according to the POI data, and representing objective evaluation on commercial space quality;
counting the total evaluation quantity of each street view acquisition point according to the public comment data to obtain a attention index of commercial facilities;
constructing a random forest model, and training the random forest model by utilizing data generated by the street view image data;
evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model to respectively obtain the score values of the commercial street space, the commercial space atmosphere and the commercial building elevation index, and forming a primary index together with the attention of commercial facilities to represent subjective evaluation of commercial space quality; and calculating to obtain comprehensive evaluation of the commercial space quality according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality.
Example 4:
The present embodiment provides a storage medium that is a computer-readable storage medium storing a program that, when executed by a processor, implements the commercial space quality evaluation method of embodiment 1 described above, as follows:
acquiring POI data and public comment data in a research range;
generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point;
calculating traffic convenience indexes and commercial state richness indexes of each street view acquisition point according to the POI data, and representing objective evaluation on commercial space quality;
counting the total evaluation quantity of each street view acquisition point according to the public comment data to obtain a attention index of commercial facilities;
constructing a random forest model, and training the random forest model by utilizing data generated by the street view image data;
evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model to respectively obtain the score values of the commercial street space, the commercial space atmosphere and the commercial building elevation index, and forming a primary index together with the attention of commercial facilities to represent subjective evaluation of commercial space quality;
And calculating to obtain comprehensive evaluation of the commercial space quality according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality.
The storage medium in the above embodiments may be a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a usb disk, a removable hard disk, or the like.
In summary, the random forest model for evaluating the commercial space quality is constructed by adopting the combination of the machine learning algorithm and the street view image, which is beneficial to realizing large-scale and high-precision measure of the commercial space quality of the city; and meanwhile, by combining with other types of big data, the quality of the commercial space is evaluated from an objective level, and subjective perception of microcosmic individuals on the quality of the commercial space is fused, namely, the quality of the commercial space is comprehensively evaluated from two dimensions of main dimension and objective dimension, so that the evaluation result is more in line with objective reality.
The above-mentioned embodiments are only preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can make equivalent substitutions or modifications according to the technical solution and the inventive concept of the present invention within the scope of the present invention disclosed in the present invention patent, and all those skilled in the art belong to the protection scope of the present invention.

Claims (7)

1. A method for evaluating commercial spatial quality based on big data, the method comprising:
acquiring POI data and public comment data in a research range;
generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point;
calculating traffic convenience indexes and commercial state richness indexes of each street view acquisition point according to the POI data, and representing objective evaluation on commercial space quality;
counting the total evaluation quantity of each street view acquisition point according to the public comment data to obtain a attention index of commercial facilities, wherein the counting of the total evaluation quantity of each street view acquisition point refers to counting of the total evaluation quantity of public comment shops in a 100-meter buffer area of each street view acquisition point;
constructing a random forest model, and training the random forest model by utilizing data generated by the street view image data;
evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model to respectively obtain the score value of the commercial street space, the commercial space atmosphere and the commercial building elevation index, forming a primary index together with the attention degree of commercial facilities, and characterizing the subjective evaluation of the commercial space quality, wherein the secondary index of the street view image data comprises the commercial street cleanliness, the commercial street aspect ratio suitability, the commercial street openness, the commercial street walker, the commercial street greening degree, the commercial space atmosphere and the commercial building elevation cleanliness;
According to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality, calculating to obtain the comprehensive evaluation of the commercial space quality;
according to POI data, calculating the traffic convenience index and the commercial amateur state richness index of each street view acquisition point, wherein the method specifically comprises the following steps:
according to the POI data, acquiring the spatial distribution conditions of bus stations and subway stations and the spatial distribution conditions of various commercial facilities;
respectively summarizing the number of bus stations in the 500-meter buffer area of each street view acquisition point and the number of subway stations in the 1000-meter buffer area of each street view acquisition point, and calculating the traffic convenience index of each street view acquisition point:
Figure QLYQS_1
wherein Q is i For the number of buses with the ith street view acquisition point in the buffer area of 500 meters, Q max For maximum number of bus stops, R i For the number of subway stations with the ith street view acquisition point in the range of 1000 meters of buffer zone, rmax is the maximum number of subway stations; a, b represent the importance weight values of the bus station and the subway station respectively, a: b=0.08: 0.92;
counting the commercial property type quantity in a 100-meter buffer area of each street view acquisition point, and calculating the commercial property mixing degree of each street view acquisition point by adopting shannon entropy:
Figure QLYQS_2
wherein m is the number of commercial amateur types, and the commercial amateur types comprise catering, shopping, finance, life service and leisure entertainment; t (T) j The quantity of the facility POIs of the commercial property type j accounts for the proportion of the quantity of all commercial facility POIs in the 100-meter buffer area range of the ith street view acquisition point;
calculating commercial richness indexes of each street view acquisition point:
Figure QLYQS_3
wherein P is i Commercial property mixing degree, P, for ith street view acquisition point max Maximum commercial off-state mix; u (U) i For the quantity of POIs (point of interest) of commercial facilities in 100 m buffer area of ith street view acquisition point, U max Is the maximum number of commercial establishment POIs; x and y respectively represent weights of commercial property state mixing degree and commercial facility quantity;
the construction of the random forest model, and training of the random forest model by utilizing the data generated by the street view image data specifically comprises the following steps:
semantic segmentation is carried out on the street view image data by using a full convolution neural network, and feature data of the street view image data are obtained;
randomly selecting part of street view image data, and acquiring the score input by a volunteer aiming at a secondary index of the street view image data as scoring sample data;
constructing a random forest model, and randomly selecting partial data and corresponding street view image characteristic data from scoring sample data as a training set;
in the training set, training a random forest model by taking scoring sample data as a dependent variable and street view image characteristic data as an independent variable;
When the model performance measurement index reaches a standard value, training of a random forest model is completed;
the comprehensive evaluation of the commercial space quality is obtained by calculation according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality, and specifically comprises the following steps:
the evaluation weight of the traffic convenience index K and the commercial richness index D is calculated according to statistics to be w Ki 、w Di The evaluation weights of the commercial street space STR, the commercial space atmosphere ENV, the commercial building facade BUI and the commercial facility attention ATT are s 1i 、s 2i 、s 3i 、s 4i The importance weight value of the objective evaluation index and the subjective evaluation index is g 1i 、g 2i ；
The method comprises the following steps of adopting dimensionless treatment on a commercial street space index, a commercial space atmosphere index, a commercial building elevation index and a commercial facility attention index, wherein the following formula is adopted:
Figure QLYQS_4
Figure QLYQS_5
Figure QLYQS_6
Figure QLYQS_7
wherein STR i 、ENV i 、BUI i 、ATT i Score values of the ith street view collection point commercial street space index, commercial space atmosphere index, commercial building elevation index and commercial facility attention index are respectively STR (short distance channel) max 、ENV max 、BUI max 、ATT max Respectively represent corresponding fingersMarking the maximum value of the score value;
and calculating to obtain the comprehensive evaluation value of the commercial space quality of the street view acquisition point i according to the following formula:
C i ＝g 1i (w Ki K i +w Di D i )+g 2i (s 1i O STRi +s 2i O ENVi +s 3i O BUIi +s 4i O ATTi )×100
wherein K is i 、D i The traffic convenience index and the commercial richness index of the ith street view collection point are respectively.
2. The method for evaluating the quality of a commercial space according to claim 1, wherein generating a plurality of street view acquisition points according to POI data, and acquiring corresponding street view image data at each street view acquisition point, specifically comprises:
determining commercial areas to be evaluated in the research scope according to the POI data;
and generating a plurality of street view acquisition points in the business area, and acquiring corresponding street view image data at each street view acquisition point.
3. The method for evaluating the quality of a commercial space according to claim 2, wherein the determining the commercial area to be evaluated in the research area according to the POI data specifically comprises:
screening out commercial facility POIs from the POI data, performing cluster analysis on the commercial facility POIs, and classifying the commercial facility POIs into a plurality of classes according to the distribution density of the commercial facility POIs;
and synthesizing POI points of the same cluster into a region serving as a business region to be evaluated.
4. The method for evaluating the quality of a commercial space according to claim 2, wherein generating a plurality of street view acquisition points in the commercial area, and acquiring corresponding street view image data at each street view acquisition point, specifically comprises:
Selecting road network data in each business area;
generating a plurality of street view acquisition points at set intervals based on the road network data;
and respectively acquiring street view images of four horizontal visual angles parallel to and perpendicular to the road direction according to the road direction of each street view acquisition point, and eliminating the non-street view images and repeated acquisition points.
5. The method for evaluating the quality of the commercial space according to claim 1, wherein the step of evaluating the score values of the secondary indexes of the street view image data of each street view acquisition point by using the trained random forest model respectively obtains the score values of the commercial street space, the commercial space atmosphere and the commercial building elevation indexes, specifically comprises the following steps:
and evaluating the score value of the secondary index of the street view image data of each street view acquisition point by using the trained random forest model, and summing the score values of the secondary index to obtain the score values of the indexes of the commercial street space, the commercial space atmosphere and the commercial building elevation.
6. A big data based commercial space quality assessment system, the system comprising:
the data acquisition module is used for acquiring POI data and public comment data in a research range;
The generating street view acquisition point module is used for generating a plurality of street view acquisition points according to the POI data, and acquiring corresponding street view image data at each street view acquisition point;
the objective evaluation module is used for calculating the traffic convenience index and the commercial state richness index of each street view acquisition point according to the POI data and representing objective evaluation on commercial space quality;
the attention degree module of the commercial facility is used for counting the total evaluation quantity of each street view acquisition point according to the public comment data to obtain attention degree indexes of the commercial facility, wherein the total statistics of the evaluation quantity of each street view acquisition point refers to the statistics of the total evaluation quantity of public comment shops in a 100-meter buffer area of each street view acquisition point;
the random forest module is used for constructing a random forest model, and training the random forest model by utilizing data generated by the street view image data;
the subjective evaluation module is used for evaluating the score value of the secondary index of the street view image data of each street view acquisition point by utilizing the trained random forest model to respectively obtain the score value of the index of the commercial street space, the commercial space atmosphere and the commercial building elevation, and the score value and the attention degree of the commercial facilities form a primary index together to represent subjective evaluation on the quality of the commercial space, wherein the secondary index of the street view image data comprises the cleanliness of the commercial street, the suitability of the aspect ratio of the commercial street, the openness of the commercial street, the walkability of the commercial street, the greening degree of the commercial street, the commercial space atmosphere and the cleanliness of the commercial building elevation;
The comprehensive evaluation module is used for obtaining comprehensive evaluation of the commercial space quality according to objective evaluation of the commercial space quality and subjective evaluation of the commercial space quality, and calculating to obtain comprehensive evaluation of the commercial space quality;
according to POI data, calculating the traffic convenience index and the commercial amateur state richness index of each street view acquisition point, wherein the method specifically comprises the following steps:
according to the POI data, acquiring the spatial distribution conditions of bus stations and subway stations and the spatial distribution conditions of various commercial facilities;
respectively summarizing the number of bus stations in the 500-meter buffer area of each street view acquisition point and the number of subway stations in the 1000-meter buffer area of each street view acquisition point, and calculating the traffic convenience index of each street view acquisition point:
Figure QLYQS_8
wherein Q is i For the number of buses with the ith street view acquisition point in the buffer area of 500 meters, Q max For maximum number of bus stops, R i For the number of subway stations with the ith street view acquisition point in the range of 1000 meters of buffer zone, rmax is the mostThe number of large subway stations; a, b respectively represent importance weight values of bus stations and subway stations;
counting the commercial property type quantity in a 100-meter buffer area of each street view acquisition point, and calculating the commercial property mixing degree of each street view acquisition point by adopting shannon entropy:
Figure QLYQS_9
Wherein m is the number of commercial amateur types, and the commercial amateur types comprise catering, shopping, finance, life service and leisure entertainment; t (T) j The quantity of the facility POIs of the commercial property type j accounts for the proportion of the quantity of all commercial facility POIs in the 100-meter buffer area range of the ith street view acquisition point;
calculating commercial richness indexes of each street view acquisition point:
Figure QLYQS_10
wherein P is i Commercial property mixing degree, P, for ith street view acquisition point max Maximum commercial off-state mix; u (U) i For the quantity of POIs (point of interest) of commercial facilities in 100 m buffer area of ith street view acquisition point, U max Is the maximum number of commercial establishment POIs; x and y respectively represent weights of commercial property state mixing degree and commercial facility quantity;
the construction of the random forest model, and training of the random forest model by utilizing the data generated by the street view image data specifically comprises the following steps:
semantic segmentation is carried out on the street view image data by using a full convolution neural network, and feature data of the street view image data are obtained;
randomly selecting part of street view image data, and acquiring the score input by a volunteer aiming at a secondary index of the street view image data as scoring sample data;
constructing a random forest model, and randomly selecting partial data and corresponding street view image characteristic data from scoring sample data as a training set;
In the training set, training a random forest model by taking scoring sample data as a dependent variable and street view image characteristic data as an independent variable;
when the model performance measurement index reaches a standard value, training of a random forest model is completed;
the comprehensive evaluation of the commercial space quality is obtained by calculation according to the objective evaluation of the commercial space quality and the subjective evaluation of the commercial space quality, and specifically comprises the following steps:
the evaluation weight of the traffic convenience index K and the commercial richness index D is calculated according to statistics to be w Ki 、w Di The evaluation weights of the commercial street space STR, the commercial space atmosphere ENV, the commercial building facade BUI and the commercial facility attention ATT are s 1i 、s 2i 、s 3i 、s 4i The importance weight value of the objective evaluation index and the subjective evaluation index is g 1i 、g 2i ；
The method comprises the following steps of adopting dimensionless treatment on a commercial street space index, a commercial space atmosphere index, a commercial building elevation index and a commercial facility attention index, wherein the following formula is adopted:
Figure QLYQS_11
Figure QLYQS_12
Figure QLYQS_13
Figure QLYQS_14
wherein STR i 、ENV i 、BUI i 、ATT i Respectively acquiring the commercial street space index and the commercial space atmosphere of the ith street viewScore values of index, commercial building elevation index and commercial facility attention index, STR max 、ENV max 、BUI max 、ATT max Respectively representing the maximum value of the score values of the corresponding indexes;
and calculating to obtain the comprehensive evaluation value of the commercial space quality of the street view acquisition point i according to the following formula:
C i ＝g 1i (w Ki K i +w Di D i )+g 2i (s 1i O STRi +s 2i O ENVi +s 3i O BUIi +s 4i O ATTi )×100
Wherein K is i 、D i The traffic convenience index and the commercial richness index of the ith street view collection point are respectively.
7. A computer device comprising a processor and a memory for storing a program executable by the processor, wherein the processor, when executing the program stored in the memory, implements the commercial space quality assessment method of any one of claims 1-5.
CN202110313101.4A 2021-03-24 2021-03-24 Commercial space quality evaluation method, system, equipment and medium based on big data Active CN113011925B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202110313101.4A CN113011925B (en) 2021-03-24 2021-03-24 Commercial space quality evaluation method, system, equipment and medium based on big data
PCT/CN2021/120952 WO2022198963A1 (en) 2021-03-24 2021-09-27 Big data-based commercial space quality evaluation method and system, device, and medium
AU2021435561A AU2021435561A1 (en) 2021-03-24 2021-09-27 Big data-based commercial space quality evaluation method and system, device, and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110313101.4A CN113011925B (en) 2021-03-24 2021-03-24 Commercial space quality evaluation method, system, equipment and medium based on big data

Publications (2)

Publication Number Publication Date
CN113011925A CN113011925A (en) 2021-06-22
CN113011925B true CN113011925B (en) 2023-06-20

Family

ID=76406003

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110313101.4A Active CN113011925B (en) 2021-03-24 2021-03-24 Commercial space quality evaluation method, system, equipment and medium based on big data

Country Status (3)

Country Link
CN (1) CN113011925B (en)
AU (1) AU2021435561A1 (en)
WO (1) WO2022198963A1 (en)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113011925B (en) * 2021-03-24 2023-06-20 华南理工大学 Commercial space quality evaluation method, system, equipment and medium based on big data
JP7008958B1 (en) * 2021-10-05 2022-01-25 三信トレーディング株式会社 Nishikigoi show implementation equipment and programs and Nishikigoi show system
CN113919892A (en) * 2021-12-13 2022-01-11 深圳小库科技有限公司 Business space value quantification method and device based on ABM model
CN115660759A (en) * 2022-12-29 2023-01-31 成都阿卡林科技发展有限公司 Real estate value prediction system and method based on big data analysis
CN116415499B (en) * 2023-04-07 2024-02-27 广州市城市规划勘测设计研究院 Community comfort simulation prediction method
CN116402548B (en) * 2023-06-09 2023-10-03 广西大也智能数据有限公司 Method and device for determining saturation state of commercial area based on signaling data and POI data
CN116957633B (en) * 2023-09-19 2023-12-01 武汉创知致合科技有限公司 Product design user experience evaluation method based on intelligent home scene
CN117808504A (en) * 2023-12-27 2024-04-02 中国科学院重庆绿色智能技术研究院 Business area liveness measuring and calculating method and system based on noctilucent remote sensing
CN117973821A (en) * 2024-04-02 2024-05-03 浙江和达科技股份有限公司 Commercial site selection method based on water service asset data
CN118037983A (en) * 2024-04-12 2024-05-14 华中师范大学 Mass city street panoramic picture quality evaluation and rapid three-dimensional modeling method

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909659A (en) * 2017-02-27 2017-06-30 携程旅游网络技术（上海）有限公司 Hotel's sort method based on traffic convenience degree in OTA websites

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933286B (en) * 2015-03-13 2018-01-05 华南理工大学 A kind of Urban spatialquality evaluation method based on big data
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
CN111126864A (en) * 2019-12-26 2020-05-08 中国地质大学（武汉） Street quality assessment method based on man-machine confrontation score
CN111242223B (en) * 2020-01-15 2020-11-13 中国科学院地理科学与资源研究所 Street space quality evaluation method based on streetscape image multi-feature fusion
CN111242493B (en) * 2020-01-17 2020-11-24 广州市城市规划勘测设计研究院 Street quality evaluation method, device and system and storage medium
CN112418674A (en) * 2020-11-24 2021-02-26 中国地质大学（武汉） City multi-source data-based street space quality measure evaluation method and system
CN113011925B (en) * 2021-03-24 2023-06-20 华南理工大学 Commercial space quality evaluation method, system, equipment and medium based on big data

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106909659A (en) * 2017-02-27 2017-06-30 携程旅游网络技术（上海）有限公司 Hotel's sort method based on traffic convenience degree in OTA websites

Also Published As

Publication number Publication date
AU2021435561A1 (en) 2022-11-03
WO2022198963A1 (en) 2022-09-29
CN113011925A (en) 2021-06-22

Similar Documents

Publication Publication Date Title
CN113011925B (en) Commercial space quality evaluation method, system, equipment and medium based on big data
CN108446470B (en) Medical facility accessibility analysis method based on vehicle trajectory data and population distribution
CN112949413B (en) City landscape element classification and locality measurement method based on street view picture
CN111401692B (en) Method for measuring urban space function compactness
CN104881472B (en) A kind of travelling route sight spot combined recommendation method based on network data collection
CN112966899B (en) Urban public service facility construction decision method influencing population density
CN114662774A (en) City block vitality prediction method, storage medium and terminal
CN109840272B (en) Method for predicting user demand of shared electric automobile station
CN116341967A (en) Park green scheme evaluation and optimization method, device and equipment based on GIS model and storage medium
CN112561401A (en) City vitality measurement and characterization method and system based on multi-source big data
CN116415756B (en) Urban virtual scene experience management system based on VR technology
CN113672788A (en) Urban building function classification method based on multi-source data and weight coefficient method
CN116882831A (en) Urban historical cultural neighborhood public space vitality evaluation method and system
CN115983681A (en) System and method for evaluating green-path rest service value based on rest fairness
CN116307857A (en) Built-up area environment evaluation method based on remote sensing image scene understanding
CN113408867B (en) Urban burglary crime risk assessment method based on mobile phone user and POI data
Ibrahim et al. Planning transit-oriented development (TOD): a systematic literature review of measuring the transit-oriented development levels
CN114254893A (en) Urban public welfare service facility space service performance acquisition method
CN109446285B (en) College campus space cognition and activity interaction system and method, and processor
CN117077037B (en) Building scale dynamic population estimation method and system
CN114613139B (en) Travel generation prediction method suitable for large-scale sports activity traffic prediction
CN117128977B (en) High-quality green road path planning method, device and equipment based on double-image fusion
Dong et al. Spatial equity of city public open spaces based on G2SFCA: A case study of Wuhan, China
Qiang et al. Evaluating Shanghai new towns' maturity of urban form: an exploration index based on new urban data
Niu et al. A novel optimal road layout model based on urban cloud data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant