CN111177587A - Shopping street recommendation method and device - Google Patents

Shopping street recommendation method and device Download PDF

Info

Publication number
CN111177587A
CN111177587A CN201911273412.1A CN201911273412A CN111177587A CN 111177587 A CN111177587 A CN 111177587A CN 201911273412 A CN201911273412 A CN 201911273412A CN 111177587 A CN111177587 A CN 111177587A
Authority
CN
China
Prior art keywords
shopping
density
street
average
index
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.)
Granted
Application number
CN201911273412.1A
Other languages
Chinese (zh)
Other versions
CN111177587B (en
Inventor
邓应彬
许剑辉
严滢伟
陈仁容
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.)
Guangzhou Institute of Geography of GDAS
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Original Assignee
Guangzhou Institute of Geography of GDAS
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
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 Guangzhou Institute of Geography of GDAS, Southern Marine Science and Engineering Guangdong Laboratory Guangzhou filed Critical Guangzhou Institute of Geography of GDAS
Priority to CN201911273412.1A priority Critical patent/CN111177587B/en
Publication of CN111177587A publication Critical patent/CN111177587A/en
Application granted granted Critical
Publication of CN111177587B publication Critical patent/CN111177587B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • 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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0639—Item locations

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to a shopping street recommendation method and device, wherein the shopping interest point average density of each street is obtained according to each street and the corresponding shopping interest point, the average vegetation density and the average water density of each street are calculated according to vegetation information and water body information, the shopping interest point average density, the average vegetation density and the average water body density of each street are subjected to weighted summation to obtain the shopping index of each street, and the shopping street is recommended to a user according to the shopping index. Compared with the prior art, the method and the system have the advantages that the gathering condition and the walking environment of the shopping interest points on the corresponding streets are intuitively reflected through the shopping indexes, convenience is brought to citizens to go out and select shopping places, and the shopping experience of the citizens is improved.

Description

Shopping street recommendation method and device
Technical Field
The invention relates to the technical field of geographic information, in particular to a shopping street recommendation method and device.
Background
At present, urban streets are mainly classified according to functions mainly based on vehicles, such as expressways, main roads and the like. When going out, citizens often obtain the gathering area of a certain interest point through a map or public comment and the like to obtain shopping information of the street. The existing software only reflects street shopping position information and user evaluation information, more accurate shopping street recommendation cannot be provided for users, the recommendation accuracy is low, citizens often need to browse a large number of user evaluations to judge whether shopping streets are suitable for going out, and the time consumption is long.
Disclosure of Invention
The embodiment of the application provides a shopping street recommendation method and device, which can perform more accurate intelligent recommendation on travel shopping of a user according to shopping interest points and street environments of streets. The technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a shopping street recommendation method, including the following steps:
acquiring the average shopping interest point density of each street according to each street and the corresponding shopping interest points; wherein each shopping interest point corresponds to the street closest thereto;
acquiring remote sensing image data, and extracting vegetation information and water body information from the remote sensing image data;
calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information;
carrying out weighted summation on the average density of the shopping interest points, the average vegetation density and the average water body density of each street to obtain the shopping index of each street;
and recommending shopping streets to the user according to the shopping index.
Optionally, the step of extracting vegetation information and water body information from the remote sensing image data includes:
calculating a normalized vegetation index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000011
wherein NVDI is the normalized vegetation index, BnirAnd BredRespectively reflecting values of a near infrared band and a red band of the remote sensing image data;
converting the normalized vegetation index into point data to obtain vegetation information of the remote sensing image data;
calculating a normalized water body index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000012
wherein NDWI is normalized water body index, BgreenAnd BnirRespectively reflecting values of a green wave band and a near infrared wave band of the remote sensing image data;
and converting the normalized water body index into point data to obtain the water body information of the remote sensing image data.
Optionally, the step of calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information includes:
deleting the normalized vegetation index points outside the first distance range on both sides of the road, and calculating the average vegetation density of each street according to the remaining normalized vegetation index points;
and deleting the normalized water body index points outside the second distance range on the two sides of the road, and calculating the average water body density of each street according to the remaining normalized water body index points.
Optionally, the step of performing weighted summation on the shopping interest point average density, the average vegetation density and the average water density of each street specifically includes:
setting the weight values of the average density of the shopping interest points, the average vegetation density and the average water body density as omega respectively1、ω2And ω3；
Calculating the shopping index of each street according to the following formula:
SSI＝POIs×ω1+V×ω2+W×ω3
wherein SSI is shopping index, POIs is shopping point density, V is average vegetation density, W is average water density, omega1、ω2And ω3The weight values of the average density of the shopping interest points, the average vegetation density and the average water body density are respectively.
Optionally, the step of recommending shopping streets to the user according to the shopping index specifically includes:
carrying out grade evaluation on the shopping index of each street to obtain a recommended grade of the street; wherein the recommended rating for each street is as follows:
SSI < ═ 0, not available;
SSI < ═ 0.2, not recommended;
SSI < ═ 0.4, acceptable;
SSI < ═ 0.6, recommended;
SSI < ═ 0.8, strongly recommended;
SSI < ═ 1, recommended as far as possible;
SSI >1, shopping lobby;
wherein SSI is a shopping index;
and recommending shopping streets to the user according to the street recommendation level.
Optionally, the method further comprises the following steps:
and displaying the recommended grade of each street in different color levels, and carrying out space visualization on the recommended grade of each street.
In a second aspect, an embodiment of the present application provides a shopping street recommendation device, including:
the interest point density calculation module is used for acquiring the shopping interest point average density of each street according to each street and the shopping interest points corresponding to the street; wherein each shopping interest point corresponds to the street closest thereto;
the information extraction module is used for acquiring remote sensing image data and extracting vegetation information and water body information from the remote sensing image data;
the environment density calculation module is used for calculating the average vegetation density and the average water body density of each street according to the vegetation information and the water body information;
the shopping index calculation module is used for carrying out weighted summation on the average shopping interest point density, the average vegetation density and the average water body density of each street to obtain the shopping index of each street;
and the shopping street recommending module is used for recommending shopping streets to the user according to the shopping index.
Optionally, the information extraction module includes:
the vegetation index calculation unit is used for calculating the normalized vegetation index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000031
wherein NVDI is the normalized vegetation index, BnirAnd BredRespectively reflecting values of a near infrared band and a red band of the remote sensing image data;
the vegetation information acquisition unit is used for converting the normalized vegetation index into point data and acquiring vegetation information of the remote sensing image data;
the water body index calculation unit is used for calculating the normalized water body index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000032
wherein NDWI is normalized water body index, BgreenAnd BnirRespectively reflecting values of a green wave band and a near infrared wave band of the remote sensing image data;
and the water body information acquisition unit is used for converting the normalized water body index into point data and acquiring the water body information of the remote sensing image data.
Optionally, the environment density calculating module includes:
the average vegetation density calculation module is used for deleting the normalized vegetation index points outside the first distance range on the two sides of the road and calculating the average vegetation density of each street according to the remaining normalized vegetation index points;
and the average water density calculation module is used for deleting the normalized water index points outside the second distance range on the two sides of the road and calculating the average water density of each street according to the remaining normalized water index points.
Optionally, the shopping index calculating module includes:
a weight value setting unit for setting the weight values of the shopping interest point average density, the average vegetation density and the average water body density as omega respectively1、ω2And ω3；
The shopping index calculating unit is used for calculating the shopping index of each street according to the following formula:
SSI＝POIs×ω1+V×ω2+W×ω3
wherein SSI is shopping index, POIs is shopping point density, V is average vegetation density, W is average water density, omega1、ω2And ω3The weight values of the average density of the shopping interest points, the average vegetation density and the average water body density are respectively.
In the embodiment of the application, the average density of the shopping interest points of each street is obtained according to each street and the corresponding shopping interest points thereof, calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information, calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information, carrying out weighted summation on the average density of shopping interest points, the average vegetation density and the average water body density of each street to obtain a shopping index, and intuitively reflects the gathering condition of the shopping interest points on the corresponding streets and the walking environment of the streets through the shopping index, shopping streets are recommended to the user according to the shopping index, more accurate intelligent recommendation of travel shopping of the user is achieved, the recommendation accuracy is improved, convenience is brought to citizens to travel to select shopping places, and citizen shopping experience is improved.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a shopping street recommendation method in an exemplary embodiment of the invention;
FIG. 2 is a flowchart of step S2 in an exemplary embodiment of the invention;
FIG. 3 is a histogram of NDVI values of vegetation and non-vegetation samples in an exemplary embodiment of the invention;
FIG. 4 is a histogram of NDWI values of water and shadow samples in an exemplary embodiment of the invention;
FIG. 5 is a block diagram of shopping street recommendations in an exemplary embodiment of the invention;
fig. 6 is a schematic structural diagram of the information extraction module 2 in an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
It should be understood that the embodiments described are only some embodiments of the present application, and not all embodiments. All other examples, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments in the present application, belong to the scope of protection of the embodiments in the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the present application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims. In the description of the present application, it is to be understood that the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not necessarily used to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Referring to fig. 1, the present invention provides a shopping street recommendation method, which includes the following steps:
step S1: acquiring the average shopping interest point density of each street according to each street and the corresponding shopping interest points; wherein each shopping interest point corresponds to the street closest thereto.
The Point of Interest of shopping refers to shopping class data in a POI (Point of Interest), including text information such as names of shopping places such as a shopping mall, a supermarket, a convenience store and the like, and geographical location information.
The street can be an existing street or a custom street formed by re-segmenting the existing street, in a specific example, the length of each street is segmented by 50 meters at the maximum, the shopping index of each street segment is calculated after segmentation, the calculation process relates to small data volume, the obtained shopping index of each street segment has higher precision and is more accurate in recommendation.
If a shopping interest point is beside a street, the shopping interest point corresponds to the street, and if a shopping interest point is not beside any street, the shopping interest point is attributed to the street closest to the shopping interest point.
Step S2: remote sensing image data are obtained, and vegetation information and water body information are extracted from the remote sensing image data.
The remote sensing image data refers to films or photos recording electromagnetic waves of various ground objects, and is mainly divided into aerial photos and satellite photos; in the embodiment of the application, the remote sensing image data is multispectral remote sensing image data acquired by a high-resolution second satellite, the high-resolution second satellite is a civil land observation satellite with the highest resolution at present in China, the multispectral remote sensing image data is remote sensing image data comprising spectrum information of a plurality of wave bands, the spatial resolution of the multispectral remote sensing image data is 3.2 meters, and the simulated color ground object image is obtained by endowing RGB colors to different wave bands respectively.
The vegetation information and the water body information refer to vegetation coverage and water body distribution information on the remote sensing image data, and in the embodiment of the application, the vegetation information and the water body information can be normalized vegetation index point data and normalized water body index point data on each street.
Step S3: and calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information.
In one example, the average vegetation density and the average water density of each street may be obtained by calculating the ratio of the normalized vegetation index point and the normalized water index point on each street to the street area.
Step S4: and carrying out weighted summation on the average shopping interest point density, the average vegetation density and the average water body density of each street to obtain the shopping index of each street.
The shopping interest point average density, the average vegetation density and the average water body density of the streets are fused in a weighted summation mode, shopping index scores including the gathering condition and the walking environment condition of the shopping interest points on the corresponding streets are obtained, the shopping portability and the environment friendliness of each street are visually displayed, and convenience is brought to citizens to go out.
Step S5: and recommending shopping streets to the user according to the shopping index.
When shopping streets are recommended, the shopping streets with the highest shopping indexes can be displayed on the mobile terminal, and the shopping indexes of all the streets can be sorted from high to low and displayed on the mobile terminal.
In the embodiment of the application, the average density of the shopping interest points of each street is obtained according to each street and the corresponding shopping interest points thereof, calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information, calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information, carrying out weighted summation on the average density of shopping interest points, the average vegetation density and the average water body density of each street to obtain a shopping index, and intuitively reflects the gathering condition of the shopping interest points on the corresponding streets and the walking environment of the streets through the shopping index, shopping streets are recommended to the user according to the shopping index, more accurate intelligent recommendation of travel shopping of the user is achieved, the recommendation accuracy is improved, convenience is brought to citizens to travel to select shopping places, and citizen shopping experience is improved.
Referring to fig. 2, in an exemplary embodiment, the step of extracting vegetation information and water body information from the remote sensing image data includes:
step S201: calculating a normalized vegetation index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000061
wherein NVDI is the normalized vegetation index, BnirAnd BredRespectively reflecting values of a near infrared band and a red band of the remote sensing image data;
step S202: converting the normalized vegetation index into point data to obtain vegetation information of the remote sensing image data;
step S203: calculating a normalized water body index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000071
wherein NDWI is normalized water body index, BgreenAnd BnirRespectively reflecting values of a green wave band and a near infrared wave band of the remote sensing image data;
step S204: and converting the normalized water body index into point data to obtain the water body information of the remote sensing image data.
The normalized vegetation index and the normalized water body index of each grid on the remote sensing image data are converted into point data, so that the point data can be conveniently counted subsequently, and the vegetation information and the remote sensing information in the point data are extracted.
Specifically, in an exemplary embodiment, in the step of obtaining vegetation information of the remote sensing image data, a large number of vegetation and non-vegetation samples are selected from the remote sensing image, and corresponding NDVI values are extracted to make a histogram as shown in fig. 3, according to a boundary between vegetation and non-vegetation in the histogram, an NDVI threshold value is set to be 0.1, vegetation is considered as if the NDVI value is greater than 0.1, and vegetation is considered as if the NDVI value is less than or equal to 0.1. In other examples, the NDVI threshold may be set according to actual requirements.
Specifically, in an exemplary embodiment, in the step of acquiring the water body information of the remote sensing image data, the water body and the non-water body information are segmented by using a threshold value. The water body has obvious difference on NDWI index from vegetation and impervious surface, but has certain confusion with shadow. Therefore, by selecting a large number of water and shadow samples, calculating their histograms, and extracting the optimal segmentation threshold values of water and shadow from the histograms. From fig. 4, the NDWI threshold is set to 0.199, and when the NDWI value is greater than 0.199, it is considered as a water body, and conversely, it is a non-water body. In other examples, the NDWI threshold may also be set according to actual requirements.
In an exemplary embodiment, the step of calculating the average vegetation density and the average water density of each street from the vegetation information and the water information comprises:
deleting the normalized vegetation index points outside the first distance range on both sides of the road, and calculating the average vegetation density of each street according to the remaining normalized vegetation index points;
and deleting the normalized water body index points outside the second distance range on the two sides of the road, and calculating the average water body density of each street according to the remaining normalized water body index points.
Specifically, in this embodiment, the first distance range is 20 meters, and the second distance range is 15 meters, in other examples, the first distance range and the second distance range may also be set according to actual requirements.
In an exemplary embodiment, the step of performing a weighted summation of the shopping interest point average density, the average vegetation density and the average water density of each street specifically includes:
setting the weight values of the average density of the shopping interest points, the average vegetation density and the average water body density as omega respectively1、ω2And ω3；
Calculating the shopping index of each street according to the following formula:
SSI＝POIs×ω1+V×ω2+W×ω3
wherein SSI is the shopping index, POIs is the shopping point density, V is the average vegetation density, and W is the average water density.
In the embodiment of the application, the weight values of the shopping interest point average density, the average vegetation density and the average water body density are 0.6, 0.3 and 0.1 respectively, and the shopping index calculation formula of each street is as follows:
SSI＝POIs×0.6+V×0.3+W×0.1
wherein SSI is the shopping index, POIs is the shopping point density, V is the average vegetation density, and W is the average water density.
In other examples, the weight values of the shopping interest point average density, the average vegetation density and the average water body density can also be set according to actual requirements
In an exemplary embodiment, in the step of performing rating evaluation on the shopping index of each street to obtain a recommended rating of each street, the recommended rating of each street is as follows:
SSI < ═ 0, not available;
SSI < ═ 0.2, not recommended;
SSI < ═ 0.4, acceptable;
SSI < ═ 0.6, recommended;
SSI < ═ 0.8, strongly recommended;
SSI < ═ 1, recommended as far as possible;
SSI >1, shopping lobby;
wherein SSI is a shopping index;
and recommending shopping streets to the user according to the street recommendation level.
Referring to fig. 5, the present invention further provides a shopping street recommending apparatus, including:
the interest point density calculating module 1 is used for acquiring the shopping interest point average density of each street according to each street and the shopping interest points corresponding to the street; wherein each shopping interest point corresponds to the street closest thereto;
the information extraction module 2 is used for acquiring remote sensing image data and extracting vegetation information and water body information from the remote sensing image data;
the environment density calculation module 3 is used for calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information;
the shopping index calculation module 4 is used for carrying out weighted summation on the average shopping interest point density, the average vegetation density and the average water body density of each street to obtain the shopping index of each street;
and the shopping street recommending module 5 is used for recommending shopping streets to the user according to the shopping index.
In an exemplary embodiment, as shown in fig. 6, the information extraction module 2 includes:
a vegetation index calculation unit 201, configured to calculate a normalized vegetation index on the remote sensing image data according to the following formula:
wherein NVDI is the normalized vegetation index, BnirAnd BredRespectively reflecting values of a near infrared band and a red band of the remote sensing image data;
a vegetation information obtaining unit 202, configured to convert the normalized vegetation index into point data, and obtain vegetation information of remote sensing image data;
the water body index calculation unit 203 is configured to calculate a normalized water body index on the remote sensing image data according to the following formula:
Figure BDA0002314862030000092
wherein NDWI is normalized water body index, BgreenAnd BnirRespectively reflecting values of a green wave band and a near infrared wave band of the remote sensing image data;
and the water body information obtaining unit 204 is configured to convert the normalized water body index into point data, and obtain water body information of the remote sensing image data.
In an exemplary embodiment, the environment density calculation module 3 includes:
the average vegetation density calculation module is used for deleting the normalized vegetation index points outside the first distance range on the two sides of the road and calculating the average vegetation density of each street according to the remaining normalized vegetation index points;
and the average water density calculation module is used for deleting the normalized water index points outside the second distance range on the two sides of the road and calculating the average water density of each street according to the remaining normalized water index points.
In an exemplary embodiment, the shopping index calculation module 4 includes:
a weight value setting unit for setting the weight values of the shopping interest point average density, the average vegetation density and the average water body density as omega respectively1、ω2And ω3；
The shopping index calculating unit is used for calculating the shopping index of each street according to the following formula:
SSI＝POIs×ω1+V×ω2+W×ω3
wherein SSI is street shopping index, POIs is shopping point density, V is average vegetation density, and W is average water density.
In an exemplary embodiment, the recommendation levels for streets in the shopping street recommendation module 5 are as follows:
SSI < ═ 0, not available;
SSI < ═ 0.2, not recommended;
SSI < ═ 0.4, acceptable;
SSI < ═ 0.6, recommended;
SSI < ═ 0.8, strongly recommended;
SSI < ═ 1, recommended as far as possible;
SSI >1, shopping lobby;
wherein SSI is a shopping index;
and recommending shopping streets to the user according to the street recommendation level.
According to the method and the device for assessing the environment friendliness of the streets, the gathering condition and walking environment of shopping interest points on the corresponding streets are directly reflected, the recommended grades of the streets are given according to the shopping index scores of the streets, the citizens can conveniently choose to go out, satisfied services or goods can be found to the maximum degree, and meanwhile, better shopping experience can be enjoyed.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.

Claims (10)

1. A shopping street recommendation method is characterized by comprising the following steps:
acquiring the average shopping interest point density of each street according to each street and the corresponding shopping interest points; wherein each shopping interest point corresponds to the street closest thereto;
acquiring remote sensing image data, and extracting vegetation information and water body information from the remote sensing image data;
calculating the average vegetation density and the average water density of each street according to the vegetation information and the water body information;
carrying out weighted summation on the average density of the shopping interest points, the average vegetation density and the average water body density of each street to obtain the shopping index of each street;
and recommending shopping streets to the user according to the shopping index.
2. The shopping street recommendation method of claim 1, wherein the step of extracting vegetation information and water body information from the remote sensing image data comprises:
calculating a normalized vegetation index on the remote sensing image data according to the following formula:
Figure FDA0002314862020000011
wherein NVDI is the normalized vegetation index, BnirAnd BredRespectively reflecting values of a near infrared band and a red band of the remote sensing image data;
converting the normalized vegetation index into point data to obtain vegetation information of the remote sensing image data;
calculating a normalized water body index on the remote sensing image data according to the following formula:
Figure FDA0002314862020000012
wherein NDWI is normalized water body index, BgreenAnd BnirRespectively reflecting values of a green wave band and a near infrared wave band of the remote sensing image data;
and converting the normalized water body index into point data to obtain the water body information of the remote sensing image data.
3. The shopping street recommendation method of claim 2, wherein the step of calculating the average vegetation density and the average water density for each street from the vegetation information and the water information comprises:
deleting the normalized vegetation index points outside the first distance range on both sides of the road, and calculating the average vegetation density of each street according to the remaining normalized vegetation index points;
and deleting the normalized water body index points outside the second distance range on the two sides of the road, and calculating the average water body density of each street according to the remaining normalized water body index points.
4. The shopping street recommendation method of claim 1, wherein the step of performing a weighted summation of the shopping interest point average density, the average vegetation density and the average water density of each street specifically comprises:
setting the weight values of the average density of the shopping interest points, the average vegetation density and the average water body density as omega respectively1、ω2And ω3；
Calculating the shopping index of each street according to the following formula:
SSI＝POIs×ω1+V×ω2+W×ω3
wherein SSI is shopping index, POIs is shopping point density, V is average vegetation density, W is average water density, omega1、ω2And ω3The weight values of the average density of the shopping interest points, the average vegetation density and the average water body density are respectively.
5. The shopping street recommendation method as claimed in claim 1, wherein the step of recommending shopping streets to the user based on the shopping index specifically comprises:
carrying out grade evaluation on the shopping index of each street to obtain a recommended grade of the street; wherein the recommended rating for each street is as follows:
SSI < ═ 0, not available;
SSI < ═ 0.2, not recommended;
SSI < ═ 0.4, acceptable;
SSI < ═ 0.6, recommended;
SSI < ═ 0.8, strongly recommended;
SSI < ═ 1, recommended as far as possible;
SSI >1, shopping lobby;
wherein SSI is a shopping index;
and recommending shopping streets to the user according to the street recommendation level.
6. The shopping street recommendation method as claimed in claim 5, further comprising the steps of:
and displaying the recommended grade of each street in different color levels, and carrying out space visualization on the recommended grade of each street.
7. A shopping street recommendation device, comprising:
the interest point density calculation module is used for acquiring the shopping interest point average density of each street according to each street and the shopping interest points corresponding to the street; wherein each shopping interest point corresponds to the street closest thereto;
the information extraction module is used for acquiring remote sensing image data and extracting vegetation information and water body information from the remote sensing image data;
the environment density calculation module is used for calculating the average vegetation density and the average water body density of each street according to the vegetation information and the water body information;
the shopping index calculation module is used for carrying out weighted summation on the average shopping interest point density, the average vegetation density and the average water body density of each street to obtain the shopping index of each street;
and the shopping street recommending module is used for recommending shopping streets to the user according to the shopping index.
8. The shopping street recommendation device as claimed in claim 7, wherein said information extraction module comprises:
the vegetation index calculation unit is used for calculating the normalized vegetation index on the remote sensing image data according to the following formula:
Figure FDA0002314862020000031
wherein NVDI is the normalized vegetation index, BnirAnd BredRespectively reflecting values of a near infrared band and a red band of the remote sensing image data;
the vegetation information acquisition unit is used for converting the normalized vegetation index into point data and acquiring vegetation information of the remote sensing image data;
the water body index calculation unit is used for calculating the normalized water body index on the remote sensing image data according to the following formula:
Figure FDA0002314862020000032
wherein NDWI is normalized water body index, BgreenAnd BnirRespectively reflecting values of a green wave band and a near infrared wave band of the remote sensing image data;
and the water body information acquisition unit is used for converting the normalized water body index into point data and acquiring the water body information of the remote sensing image data.
9. The shopping street recommendation device as recited in claim 8, wherein said environmental density calculation module comprises:
the average vegetation density calculation module is used for deleting the normalized vegetation index points outside the first distance range on the two sides of the road and calculating the average vegetation density of each street according to the remaining normalized vegetation index points;
and the average water density calculation module is used for deleting the normalized water index points outside the second distance range on the two sides of the road and calculating the average water density of each street according to the remaining normalized water index points.
10. The shopping street recommendation device as claimed in claim 7, wherein said shopping index calculation module comprises:
a weight value setting unit for setting the weight values of the shopping interest point average density, the average vegetation density and the average water body density as omega respectively1、ω2And ω3；
The shopping index calculating unit is used for calculating the shopping index of each street according to the following formula:
SSI＝POIs×ω1+V×ω2+W×ω3
wherein SSI is shopping index, POIs is shopping point density, V is average vegetation density, W is average water density, omega1、ω2And ω3The weight values of the average density of the shopping interest points, the average vegetation density and the average water body density are respectively.
CN201911273412.1A 2019-12-12 2019-12-12 Shopping street recommendation method and device Active CN111177587B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911273412.1A CN111177587B (en) 2019-12-12 2019-12-12 Shopping street recommendation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911273412.1A CN111177587B (en) 2019-12-12 2019-12-12 Shopping street recommendation method and device

Publications (2)

Publication Number Publication Date
CN111177587A true CN111177587A (en) 2020-05-19
CN111177587B CN111177587B (en) 2023-05-23

Family

ID=70650195

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911273412.1A Active CN111177587B (en) 2019-12-12 2019-12-12 Shopping street recommendation method and device

Country Status (1)

Country Link
CN (1) CN111177587B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102436625A (en) * 2010-11-15 2012-05-02 微软公司 Displaying product recommendations on a map
CN103329147A (en) * 2010-11-04 2013-09-25 数字标记公司 Smartphone-based methods and systems
US20140006129A1 (en) * 2011-09-15 2014-01-02 Stephan HEATH Systems and methods for mobile and online payment systems for purchases related to mobile and online promotions or offers provided using impressions tracking and analysis, location information, 2d and 3d mapping, mobile mapping, social media, and user behavior and information for generating mobile and internet posted promotions or offers for, and/or sales of, products and/or services in a social network, online or via a mobile device
CN103620640A (en) * 2011-06-29 2014-03-05 英特尔公司 Customized travel route system
CN105913299A (en) * 2015-06-15 2016-08-31 金荣德 Travel destination one stop shopping system based on 3D panoramic image and control method thereof
CN106197444A (en) * 2016-06-29 2016-12-07 厦门趣处网络科技有限公司 A kind of route planning method, system
CN106713380A (en) * 2015-08-14 2017-05-24 江贻芳 Position sensing based information sharing, pushing and exchanging system
US20180248954A1 (en) * 2016-07-19 2018-08-30 Xenio Corporation Establishing and configuring iot devices
CN108764193A (en) * 2018-06-04 2018-11-06 北京师范大学 Merge the city function limited region dividing method of POI and remote sensing image
CN108871286A (en) * 2018-04-25 2018-11-23 中国科学院遥感与数字地球研究所 The completed region of the city density of population evaluation method and system of space big data collaboration
CN110073301A (en) * 2017-08-02 2019-07-30 强力物联网投资组合2016有限公司 The detection method and system under data collection environment in industrial Internet of Things with large data sets
US20190240471A1 (en) * 2016-09-02 2019-08-08 The General Hospital Corporation Methods and Systems for Non-Contact Construction of an Internal Structure
CN110263717A (en) * 2019-06-21 2019-09-20 中国科学院地理科学与资源研究所 It is a kind of incorporate streetscape image land used status determine method
US20190332983A1 (en) * 2018-12-10 2019-10-31 Ahe Li Legal intelligence credit business: a business operation mode of artificial intelligence + legal affairs + business affairs

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103329147A (en) * 2010-11-04 2013-09-25 数字标记公司 Smartphone-based methods and systems
CN102436625A (en) * 2010-11-15 2012-05-02 微软公司 Displaying product recommendations on a map
CN103620640A (en) * 2011-06-29 2014-03-05 英特尔公司 Customized travel route system
US20140006129A1 (en) * 2011-09-15 2014-01-02 Stephan HEATH Systems and methods for mobile and online payment systems for purchases related to mobile and online promotions or offers provided using impressions tracking and analysis, location information, 2d and 3d mapping, mobile mapping, social media, and user behavior and information for generating mobile and internet posted promotions or offers for, and/or sales of, products and/or services in a social network, online or via a mobile device
CN105913299A (en) * 2015-06-15 2016-08-31 金荣德 Travel destination one stop shopping system based on 3D panoramic image and control method thereof
CN106713380A (en) * 2015-08-14 2017-05-24 江贻芳 Position sensing based information sharing, pushing and exchanging system
CN106197444A (en) * 2016-06-29 2016-12-07 厦门趣处网络科技有限公司 A kind of route planning method, system
US20180248954A1 (en) * 2016-07-19 2018-08-30 Xenio Corporation Establishing and configuring iot devices
US20190240471A1 (en) * 2016-09-02 2019-08-08 The General Hospital Corporation Methods and Systems for Non-Contact Construction of an Internal Structure
CN110073301A (en) * 2017-08-02 2019-07-30 强力物联网投资组合2016有限公司 The detection method and system under data collection environment in industrial Internet of Things with large data sets
CN108871286A (en) * 2018-04-25 2018-11-23 中国科学院遥感与数字地球研究所 The completed region of the city density of population evaluation method and system of space big data collaboration
CN108764193A (en) * 2018-06-04 2018-11-06 北京师范大学 Merge the city function limited region dividing method of POI and remote sensing image
US20190332983A1 (en) * 2018-12-10 2019-10-31 Ahe Li Legal intelligence credit business: a business operation mode of artificial intelligence + legal affairs + business affairs
CN110263717A (en) * 2019-06-21 2019-09-20 中国科学院地理科学与资源研究所 It is a kind of incorporate streetscape image land used status determine method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
宋婷婷: "线下购物情境下消费者对品牌推荐的影响因素" *
张菲菲等: "一种基于Sentine-2A影像的高分辨率不透水面提取遥感指数" *

Also Published As

Publication number Publication date
CN111177587B (en) 2023-05-23

Similar Documents

Publication Publication Date Title
Guan et al. Integration of orthoimagery and lidar data for object-based urban thematic mapping using random forests
US10648922B2 (en) Crack analysis device, crack analysis method, and crack analysis program
Zhan et al. Quality assessment for geo‐spatial objects derived from remotely sensed data
CN109299673B (en) City group greenness space extraction method and medium
Soheilian et al. 3D road marking reconstruction from street-level calibrated stereo pairs
Pan et al. Mapping asphalt pavement aging and condition using multiple endmember spectral mixture analysis in Beijing, China
Visser et al. An evaluation of a low-cost pole aerial photography (PAP) and structure from motion (SfM) approach for topographic surveying of small rivers
Yu et al. Urban impervious surface estimation from remote sensing and social data
CN111428582B (en) Method for calculating urban sky width by using Internet streetscape photo
Sameen et al. A simplified semi-automatic technique for highway extraction from high-resolution airborne LiDAR data and orthophotos
US9372081B2 (en) Method and system for geo-referencing at least one sensor image
JP2007128141A (en) System and method for determining road lane number in road image
CN110749323B (en) Method and device for determining operation route
Liu et al. A framework of road extraction from airborne lidar data and aerial imagery
CN111177587B (en) Shopping street recommendation method and device
Ashilah et al. Urban slum identification in bogor tengah sub-district, bogor city using unmanned aerial vehicle (uav) images and object-based image analysis
Schiewe Status and future perspectives of the application potential of digital airborne sensor systems
Chen et al. Multi-type change detection of building models by integrating spatial and spectral information
Villa Imperviousness indexes performance evaluation for mapping urban areas using remote sensing data
Asad et al. Use of remote sensing for urban impervious surfaces: a case study of Lahore
Li et al. Object-based urban land cover mapping using high-resolution airborne imagery and LiDAR data
Marchesi et al. Detection of moving vehicles with WorldView-2 satellite data
Török-Oance et al. Object-oriented image analysis for detection of the barren karst areas. A case study: the central sector of the Mehedinţi Mountains (Southern Carpathians)
Liu et al. Improvement of etx metric base on olsr
CN111814692B (en) Method for acquiring influence distance of ground object type on ground surface temperature

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