Urban network red business street tombstone-of-mouth evaluation method, system and device, and storage medium

By building a reputation evaluation system for urban Internet celebrity commercial blocks and using multi-source data to measure network popularity, business vitality and consumption experience, the problem that existing technology cannot comprehensively evaluate the reputation of Internet celebrity commercial blocks is solved, and the urban Internet celebrity commercial blocks are realized Efficient and accurate evaluation to provide support for urban planning.

CN118886971APending Publication Date: 2024-11-01SOUTH CHINA UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410944544.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-01

AI Technical Summary

Technical Problem

The existing technology is difficult to systematically analyze and comprehensively evaluate the reputation of Internet celebrity commercial districts, ignore social media interaction data and platform user feedback, and cannot fully reflect the diverse influencing elements of physical space and cyberspace.

Method used

By obtaining video platform data, evaluation website data, POI location interest data, road data and street scene image data, we will build a reputation evaluation system for urban Internet celebrity commercial districts, and measure secondary indicator data from three aspects: network popularity, business vitality, and consumption experience. , and determine the weights of each indicator through normalization and entropy weighting method, and calculate the final reputation evaluation results of urban Internet celebrity commercial districts.

Benefits of technology

It has achieved a comprehensive and objective evaluation of the reputation of urban Internet celebrity commercial districts, providing efficient and accurate guidance for urban planning and optimizing functional configuration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118886971A_ABST
    Figure CN118886971A_ABST
Patent Text Reader

Abstract

The invention discloses an urban network red business street praise evaluation method, system and device and a storage medium, and the method comprises the steps: obtaining related data in an evaluation region, including video platform data, evaluation website data, POI position interest point data, road data and streetscape image data; constructing a public praise evaluation system of the urban network red business street area, wherein the public praise evaluation system comprises three first-level indexes of network popularity, business vitality and consumption experience and corresponding second-level indexes; according to the related data in the evaluation area, measuring secondary index data corresponding to network popularity, commercial vitality and consumption experience in the evaluation area; performing normalization processing on the second-level index data, and determining the weight of each second-level index; and the weights of the secondary index data are superposed and summarized, and a final evaluation result of the public praise of the urban network red business street area is calculated. The public praise evaluation method comprehensively evaluates the public praise of the urban network red business street area, enables the evaluation result to more accord with objective reality, and provides guidance and support for high-quality development of the urban network red business street area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a method, system, computer equipment and storage medium for evaluating the reputation of a popular commercial block in a city, and belongs to the field of urban planning and urban geography. Background Art

[0002] Internet-famous commercial blocks in cities refer to urban commercial activity clusters that have received extremely high attention on online platforms, with strong visual appeal, large passenger flow and fast dissemination speed. With the development of mobile Internet technology and the rise of new consumption patterns, Internet-famous commercial blocks have become core areas with high vitality in cities, covering a variety of business formats such as retail shopping, catering, leisure and entertainment, and have profoundly affected the daily lives of citizens and the consumption experience of tourists.

[0003] However, existing commercial space evaluation methods have limitations in comprehensively evaluating the reputation of Internet celebrity commercial blocks. Traditional urban space evaluation methods focus on the built environment, supporting facilities, and transportation accessibility, ignoring the role of social media interaction data and platform user feedback. It is difficult to systematically analyze the multiple influencing factors in physical space and cyberspace and comprehensively evaluate the reputation of Internet celebrity commercial blocks. Summary of the invention

[0004] In view of this, the present invention provides a method, system, computer equipment and storage medium for evaluating the reputation of urban Internet celebrity commercial blocks, which comprehensively utilizes multi-source data obtained from the network platform, starts from the characteristics of urban Internet celebrity commercial blocks, evaluates from three aspects: network popularity, business vitality, and consumer experience, determines quantitative evaluation indicators, and comprehensively evaluates the reputation of urban Internet celebrity commercial blocks, so that the evaluation results are more in line with objective reality, and provides guidance and support for the high-quality development of urban Internet celebrity commercial blocks.

[0005] The first object of the present invention is to provide a method for evaluating the reputation of a city's popular commercial district.

[0006] The second object of the present invention is to provide a reputation evaluation system for a city’s popular commercial district.

[0007] A third object of the present invention is to provide a computer device.

[0008] A fourth object of the present invention is to provide a storage medium.

[0009] The first object of the present invention can be achieved by adopting the following technical solutions:

[0010] A method for evaluating the reputation of a popular commercial district in a city, the method comprising:

[0011] Acquire relevant data in the evaluation area, the relevant data including video platform data, evaluation website data, POI location point of interest data, road data and street view image data;

[0012] Constructing a reputation evaluation system for Internet-famous commercial blocks in cities, which includes three primary indicators, namely, network popularity, commercial vitality, and consumer experience, and corresponding secondary indicators;

[0013] Based on the relevant data in the evaluation area, measure the secondary indicator data corresponding to the network popularity, business vitality, and consumer experience in the evaluation area;

[0014] Normalize the secondary indicator data and determine the weight of each secondary indicator;

[0015] The data of each secondary indicator are summed up by adding up the weights and calculating the final evaluation result of the reputation of the city’s popular commercial district.

[0016] Furthermore, the network popularity includes traffic conversion efficiency, network attention and evaluation reputation; the commercial vitality includes business format mixing, density of Internet celebrity stores and consumer activity; the consumer experience includes pedestrian accessibility, construction intensity and landscape beauty;

[0017] The secondary indicator data corresponding to network popularity, business vitality, and consumer experience in the evaluation area are measured based on the relevant data in the evaluation area, specifically including:

[0018] Divide the evaluation area into grids according to the scope of the evaluation area;

[0019] Use video platform data to calculate traffic conversion efficiency and network attention;

[0020] Use the evaluation website data to calculate the evaluation reputation;

[0021] Use POI location point of interest data to calculate the business mix;

[0022] Use video platform data to calculate consumer activity;

[0023] Utilize POI location data and combine it with video platform data for verification and calculate the density of popular stores;

[0024] Calculate walking accessibility using POI location data and road data;

[0025] The visual image semantic technology of deep learning fully convolutional network is used to calculate the construction intensity and landscape beauty.

[0026] Furthermore, the use of video platform data to calculate traffic conversion efficiency and network attention specifically includes:

[0027] Calculate traffic conversion efficiency based on the number of video viewers and user check-ins at the popular store;

[0028] Calculate online attention based on the number of videos, pictures, and likes, comments, and collections of the popular stores;

[0029] The use of evaluation website data to calculate the evaluation reputation specifically includes:

[0030] The reputation of the reviews is calculated based on the total score and praise rate of the Internet celebrity store.

[0031] Furthermore, the method of calculating the business mix by utilizing the POI location point of interest data specifically includes:

[0032] Based on the POI location data related to the popular stores in the evaluation area, the Simpson index is used to calculate the business mix;

[0033] The use of video platform data to calculate consumption activity specifically includes:

[0034] Calculate consumption activity based on the number of people checking in at popular stores and the average amount of spending per person.

[0035] The method of using POI location point of interest data and combining it with video platform data for verification and calculating the density of Internet celebrity stores specifically includes:

[0036] Based on the POI location data, the number of all stores in the evaluation area is counted. Combined with the distribution pattern of the number of online viewers on the video platform, the number of Internet celebrity stores is screened and counted, and the density of Internet celebrity stores is calculated.

[0037] Further, the use of POI location point of interest data and road data to calculate walking accessibility specifically includes:

[0038] Calculate the distance from each popular store to the subway station, bus station, and parking lot entrance and exit, set the walking speed, divide the distance by the speed to get the walking time, and calculate the walking accessibility;

[0039] The visual image semantic technology using deep learning fully convolutional network is used to calculate the construction intensity and landscape beauty, specifically including:

[0040] Summarize street view image data, use deep learning full convolutional network semantic segmentation technology to identify and calculate the pixel ratio of buildings and skyscrapers in street view images, characterize the building enclosure and high-rise visibility, and calculate the construction intensity of each street view collection point;

[0041] The street view image data is aggregated, and the deep learning fully convolutional network semantic segmentation technology is used to identify and count the pixel proportions of the four elements of plants, sky, streets, and signs in the street view images, characterize the green view rate, sky view rate, openness, and sign density, and calculate the landscape style and beauty of each street view collection point.

[0042] Furthermore, the normalization of the secondary indicator data to determine the weight of each secondary indicator specifically includes:

[0043] The range standardization method is used to normalize the data of each secondary indicator;

[0044] According to the normalized data of each secondary indicator, the entropy weight method is used to determine the weight of each secondary indicator.

[0045] Furthermore, the entropy weight method is used to determine the weight of each secondary indicator according to the normalized secondary indicator data, specifically including:

[0046] Calculate the proportion of each secondary indicator data under each secondary indicator;

[0047] According to the proportion of each secondary indicator data under each secondary indicator, the information entropy value of each secondary indicator is calculated;

[0048] According to the information entropy value of each secondary indicator, the information entropy redundancy of each secondary indicator is calculated;

[0049] According to the information entropy redundancy of each secondary indicator, the weight of each secondary indicator is calculated.

[0050] The second object of the present invention can be achieved by adopting the following technical solutions:

[0051] A reputation evaluation system for a city's popular commercial district, the system comprising:

[0052] An acquisition module is used to acquire relevant data in the evaluation area, wherein the relevant data includes video platform data, evaluation website data, POI location point of interest data, road data and street view image data;

[0053] A construction module is used to construct a reputation evaluation system for Internet-famous commercial blocks in cities. The reputation evaluation system for Internet-famous commercial blocks in cities includes three primary indicators, namely, network popularity, commercial vitality, and consumer experience, and corresponding secondary indicators;

[0054] The first calculation module measures the secondary indicator data corresponding to network popularity, business vitality, and consumer experience in the evaluation area based on the relevant data in the evaluation area;

[0055] Determine the module, normalize the secondary indicator data, and determine the weight of each secondary indicator;

[0056] The second calculation module adds weights to the data of each secondary indicator and summarizes them to calculate the final evaluation result of the reputation of the city’s popular commercial district.

[0057] The third object of the present invention can be achieved by adopting the following technical solutions:

[0058] A computer device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned method for evaluating the reputation of a city's Internet celebrity commercial district is implemented.

[0059] The fourth object of the present invention can be achieved by adopting the following technical solutions:

[0060] A storage medium stores a program, which, when executed by a processor, implements the above-mentioned method for evaluating the reputation of a popular commercial district in a city.

[0061] The present invention has the following beneficial effects compared with the prior art:

[0062] The present invention is based on data mined from open source data, takes into account the characteristics of Internet celebrity commercial blocks that are different from other types of spaces, constructs a reputation evaluation system for urban Internet celebrity commercial blocks, measures the secondary indicator data corresponding to network popularity, commercial vitality, and consumer experience, and determines the weight of each secondary indicator, thereby calculating the final reputation evaluation result of the urban Internet celebrity commercial blocks. It can effectively evaluate the reputation of urban Internet celebrity commercial blocks, provide guidance for optimizing functional configuration and improving environmental quality, and provide assistance and reference for the efficient and accurate implementation of urban planning work. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0064] Figure 1 This is a flow chart of the method for evaluating the reputation of a city's popular commercial district according to Example 1 of the present invention.

[0065] Figure 2 It is a schematic diagram of the flow conversion efficiency evaluation results of Example 2 of the present invention.

[0066] Figure 3 This is a schematic diagram of the network attention evaluation result of Example 2 of the present invention.

[0067] Figure 4 This is a schematic diagram of the evaluation results of the word-of-mouth evaluation of Example 2 of the present invention.

[0068] Figure 5 This is a schematic diagram of the business format mixing evaluation results of Example 2 of the present invention.

[0069] Figure 6 This is a schematic diagram of the evaluation results of the density of Internet celebrity stores in Example 2 of the present invention.

[0070] Figure 7 This is a schematic diagram of the consumption activity evaluation results of Example 2 of the present invention.

[0071] Figure 8 Schematic diagram of the pedestrian accessibility evaluation results of Example 2 of the present invention.

[0072] Fig. 9 This is a schematic diagram of the construction strength evaluation results of Example 2 of the present invention.

[0073] Fig.10 Schematic diagram of the landscape beauty evaluation result of Example 2 of the present invention.

[0074] Fig.11 This is a schematic diagram of the word-of-mouth evaluation results of a popular commercial district in a city according to Example 2 of the present invention.

[0075] Fig.12 This is a structural block diagram of the city internet celebrity commercial district reputation evaluation system according to Example 3 of the present invention.

[0076] Fig.13 This is a structural block diagram of a computer device according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0078] Embodiment 1:

[0079] like Figure 1 As shown, this embodiment provides a method for evaluating the reputation of a city's Internet celebrity commercial block. A city's Internet celebrity commercial block refers to a commercial activity area that has received extremely high attention on the Internet platform. The method uses multi-source data obtained from the Internet platform and considers the characteristics of the Internet celebrity space for comprehensive evaluation, including the following steps:

[0080] S101, obtaining relevant data in the evaluation area.

[0081] The relevant data in this embodiment includes video platform data, evaluation website data, POI (Point of Interest) location data, road data and street view image data, among which the video platform data is Douyin data, and the evaluation website data is Dianping data.

[0082] The Dianping data comes from the Dianping website. A Python web crawler is written to obtain information such as the total evaluation score and positive review rate of popular stores in the evaluation area through the API interface.

[0083] The Douyin data comes from the Douyin video platform. A Python web crawler is written to obtain information such as the number of viewers and users of POI videos of Internet celebrity stores, the number of videos and pictures posted, the number of likes, comments and collections, and the average consumption amount per person through the API interface.

[0084] POI (Point of Interest) location data comes from the Baidu Map Open Platform, which obtains the name, location and business information of the stores in the evaluation area, as well as the location information of surrounding transportation facilities such as bus stops, subway stations, and parking lots.

[0085] The road data comes from the Open Street Map open platform. A Python web crawler is written to batch obtain vector road network data within the evaluation range through the API interface, including fields such as road location, road grade, and road length.

[0086] The street view image data comes from the Baidu map open platform. The road data is imported into ArcGIS software, and several street view collection points are generated in the study area at set intervals. According to the road direction of each street view collection point, street view images of four horizontal perspectives parallel and perpendicular to the road direction are obtained respectively. If some collection points have no street view images or the street view images are not clear, the online review images in Dianping.com are selected to supplement them.

[0087] S102. Construct a reputation evaluation system for popular commercial districts in cities.

[0088] This embodiment constructs a reputation evaluation system for urban Internet celebrity commercial blocks based on the characteristics of Internet celebrity commercial blocks, with reference to relevant papers on the formation mechanism and significant characteristics of Internet celebrity spaces, and combines quantitative evaluation methods for different types of spaces. The reputation evaluation system for urban Internet celebrity commercial blocks includes three primary indicators, namely, network popularity, commercial vitality, and consumer experience, and nine corresponding secondary indicators; among them, network popularity includes traffic conversion efficiency, network attention, and evaluation reputation, reflecting the influence of urban Internet celebrity commercial blocks on the network platform; commercial vitality includes business format mixing, Internet celebrity store density, and consumer activity, reflecting the business format layout characteristics and business atmosphere of urban Internet celebrity commercial blocks; consumer experience includes pedestrian accessibility, construction intensity, and landscape beauty, reflecting consumers' comprehensive evaluation of the indoor and outdoor environment and consumer activities of Internet celebrity commercial blocks.

[0089] S103. Based on the relevant data in the evaluation area, measure the secondary indicator data corresponding to the network popularity, business vitality, and consumer experience in the evaluation area.

[0090] Furthermore, step S103 specifically includes:

[0091] S1031. Divide the evaluation area into grids according to the scope of the evaluation area.

[0092] This embodiment uses the ArcGIS software's fishnet creation tool to create several 50*50m grids on a map of the evaluated area, and cuts the grids according to the boundaries of the evaluated area so that the grid boundaries completely correspond to the evaluated area.

[0093] S1032. Utilize video platform data to calculate traffic conversion efficiency and network attention.

[0094] This embodiment calculates the traffic conversion efficiency based on the number of people viewing the Tik Tok video and the number of users checking in, as shown in the following formula:

[0095]

[0096] Among them, C represents the traffic conversion efficiency, n represents the number of Internet celebrity stores in the evaluation area, and B i represents the number of users checking in at the i-th online celebrity store, A i Represents the number of video views of the i-th internet celebrity store.

[0097] This embodiment calculates the network attention based on the number of videos and pictures on the Douyin platform and the number of likes, comments and collections, as shown in the following formula:

[0098]

[0099] Among them, F represents the network attention index, n represents the number of Internet celebrity stores in the evaluation area, and G irepresents the total number of likes, comments and collections of the i-th online celebrity store, H i Represents the number of posts by the i-th internet celebrity store.

[0100] S1033. Calculate the evaluation reputation using evaluation website data.

[0101] This embodiment calculates the evaluation reputation based on the total score and favorable comment rate of the store on the Dianping website, as follows:

[0102]

[0103] Among them, K represents the evaluation reputation index, n represents the number of Internet celebrity stores in the evaluation area, and P i represents the Dianping score of the i-th online celebrity store, Q i Represents the praise rate of the i-th internet celebrity store.

[0104] S1034. Calculate the business mix using POI location point of interest data.

[0105] This embodiment uses the Simpson index to calculate the business format mixing degree based on the POI location point of interest data related to the stores in the evaluation area, as shown in the following formula:

[0106]

[0107] Among them, S represents the mixed degree of regional business formats. The business formats of Internet celebrity stores are mainly divided into five categories: shopping, food, tea and wine bars, pets, and leisure and entertainment. m represents the business type of Internet celebrity stores, and n k represents the number of stores of the kth business format distributed in the region, and n represents the total number of Internet celebrity stores of all business formats.

[0108] S1035. Calculate consumption activity using video platform data.

[0109] This embodiment calculates the consumption activity based on the number of check-ins and the average consumption amount per person in the Douyin data, as shown in the following formula:

[0110]

[0111] Among them, U represents the consumption activity index, n represents the number of Internet celebrity stores in the evaluation area, and B i represents the number of people checking in at the i-th online celebrity store, V i Indicates the average spending amount per person in a store.

[0112] S1036. Utilize the POI location point of interest data and combine it with the video platform data for verification, and calculate the density of Internet celebrity stores.

[0113] This embodiment counts the number of all stores in the evaluation area based on the POI location point of interest data, and combines the distribution pattern of the number of online viewers on Douyin to screen and count the number of Internet celebrity stores, and calculates the density of Internet celebrity stores as follows:

[0114]

[0115] Among them, U represents the consumption activity index, n represents the number of Internet celebrity stores in the evaluation area, and B i represents the number of people checking in at the i-th online celebrity store, V i Indicates the average spending amount per person in a store.

[0116] S1037: Calculate walking accessibility using POI location point of interest data and road data.

[0117] In this embodiment, the distance from each popular store to the subway station, bus station and parking lot entrance and exit is calculated by the neighbor analysis tool of ArcGIS software, the walking speed is set, the distance is divided by the speed to get the walking time, and the walking accessibility is calculated as follows:

[0118]

[0119] Among them, H represents walking accessibility, D ij is the walking time from the i-th internet celebrity store to the j-th location (bus stop, subway station, parking lot entrance and exit).

[0120] S1038. Use the visual image semantic technology of deep learning fully convolutional network to calculate the construction intensity and landscape beauty.

[0121] This embodiment aggregates street view image data, uses deep learning fully convolutional network (FCN) semantic segmentation software, identifies and statistically obtains the pixel ratios of buildings and skyscrapers in street view images, characterizes the building enclosure and high-rise visibility, and calculates the construction intensity of each street view collection point, as shown in the following formula:

[0122] Z=a*E t +b*F t

[0123] Among them, Z represents the construction intensity, E t is the building enclosure of the tth street view collection point, F t is the high-rise building visibility rate of the tth street view collection point, a and b represent the weights of the enclosure degree and the high-rise building visibility rate, respectively.

[0124] This embodiment collects street view image data, uses deep learning fully convolutional network (FCN) semantic segmentation software, identifies and statistically obtains the pixel proportions of plants, sky, streets, and signs in street view images, represents the green view rate, sky view rate, openness, and sign density, and calculates the landscape beauty of each street view collection point, as shown in the following formula:

[0125] After calculating the above-mentioned secondary indicator data, this embodiment uses the spatial connection tool of ArcGIS software to connect the indicator calculation results to the attribute table of the grid, and uses the natural break point classification method to classify the calculation results into five categories for visual expression. The darker the color, the higher the evaluation score.

[0126] S104: normalize the secondary indicator data and determine the weight of each secondary indicator.

[0127] Furthermore, step S104 specifically includes:

[0128] S1041. Use the range standardization method to normalize the data of each secondary indicator.

[0129] In this embodiment, find the maximum value of the index (X max ) and minimum value (X min ), and calculate the range (R = X max -X min ), and then subtract the minimum value (X) from each observation (X) min ), and then divided by the range (R), we get the standardized index X', the value range of which satisfies 0≤X'≤1, as shown in the following formula:

[0130] X′=(XX min ) / (X max -X min )

[0131] S1042. Determine the weight of each secondary indicator using the entropy weight method based on the normalized secondary indicator data.

[0132] This embodiment uses the entropy weight method to determine the weight of each secondary indicator, as follows:

[0133] (1) Calculate the weight of each secondary indicator data under each secondary indicator, that is, the variability index, as follows:

[0134]

[0135] Among them, P xy is the proportion of the indicator data of the xth plan under the yth secondary indicator, X xy is the indicator data of the xth plan under the yth indicator, y = 1, 2, ..., m.

[0136] (2) According to the weight of each secondary indicator data under each secondary indicator, the information entropy value of each secondary indicator is calculated, that is, the expected value of the sample, as follows:

[0137]

[0138] Among them, e y is the information entropy value of the y-th secondary indicator.

[0139] (3) According to the information entropy value of each secondary indicator, the information entropy redundancy of each secondary indicator, that is, the entropy weight coefficient, is calculated as follows:

[0140] g y =1-e y

[0141] Among them, g y is the information entropy redundancy of the y-th secondary indicator.

[0142] (4) According to the information entropy redundancy of each secondary indicator, the weight of each secondary indicator is calculated as follows:

[0143]

[0144] Among them, w y is the weight of the y-th secondary indicator.

[0145] S105. Summarize the weights of the secondary indicator data and calculate the final evaluation result of the reputation of the city's popular commercial district.

[0146] In this embodiment, the weights of the secondary indicator data are superimposed and summarized to calculate the final evaluation results of the reputation of the city's popular commercial blocks. The final evaluation results are imported into ArcGIS software, and two-dimensional graphic visualization and vector output are performed according to the natural break point method. The results are marked from small to large as low level, medium-low level, medium level, medium-high level, and high level.

[0147] Embodiment 2:

[0148] In order to verify the implementation effect of the reputation evaluation method of the urban Internet celebrity commercial block in the above implementation case 1, this embodiment is verified by taking Guangzhou Liuyun Community as an application example. Liuyun Community is located in the core commercial area of ​​Tianhe District, Guangzhou. The research area covers an area of ​​about 30 hectares and is home to a large number of Internet celebrity stores. It is a typical Internet celebrity commercial block. The specific implementation can be achieved through the following steps:

[0149] S1. Obtain relevant data in the evaluation area.

[0150] The relevant data in this embodiment includes video platform data, evaluation website data, POI (Point of Interest) location data, road data and street view image data, among which the video platform data is Douyin data, and the evaluation website data is Dianping data.

[0151] The Dianping data comes from the Dianping website. A Python web crawler is written to obtain information such as the total evaluation score and positive review rate of popular stores in the evaluation area through the API interface.

[0152] The Douyin data comes from the Douyin video platform. A Python web crawler is written to obtain information such as the number of viewers and users of POI videos of Internet celebrity stores, the number of videos and pictures posted, the number of likes, comments and collections, and the average consumption amount per person through the API interface.

[0153] POI (Point of Interest) location data comes from the Baidu Map Open Platform, which obtains the name, location and business information of the stores in the evaluation area, as well as the location information of surrounding transportation facilities such as bus stops, subway stations, and parking lots.

[0154] The road data comes from the Open Street Map open platform. A Python web crawler is written to batch obtain vector road network data within the evaluation range through the API interface, including fields such as road location, road grade, and road length.

[0155] The street view image data comes from the Baidu map open platform. The road data is imported into ArcGIS software, and several street view collection points are generated in the study area at set intervals. According to the road direction of each street view collection point, street view images of four horizontal perspectives parallel and perpendicular to the road direction are obtained respectively. If some collection points have no street view images or the street view images are not clear, the online review images in Dianping.com are selected to supplement them.

[0156] This implementation column uses the online popularity ranking as the basis for judging the city's popular commercial districts, specifically:

[0157] According to the POI point screening, a total of 147 stores within the evaluation range were obtained. Based on the four sets of Douyin data from September 15 to October 15, 2022, November 15 to December 15, 2022, January 15 to February 15, 2023, and March 15 to April 15, 2023, the number of online visitors to the stores was divided, and it was found that they showed a pyramid distribution trend. There were 69 stores with less than 500,000 online views, accounting for 46.9% of the total stores, while the number of stores with 500,000 to 1,000,000 online views dropped sharply, accounting for only 10.2% of the total, and the number of visitors in each interval (with 500,000 as an interval) with more than 1,000,000 people gradually decreased, all less than 8%. This shows that once the store's views exceed the key node of 500,000, the gap between its online popularity and other stores will significantly widen, showing obvious market differences and brand influence, and becoming an "Internet celebrity" that stands out from the fierce commercial competition. Therefore, stores with more than 500,000 views are considered Internet celebrity stores, totaling 78 stores.

[0158] S2. Construct a reputation evaluation system for popular commercial districts in the city.

[0159] This embodiment constructs a reputation evaluation system for urban Internet celebrity commercial blocks based on the characteristics of Internet celebrity commercial blocks, with reference to relevant papers on the formation mechanism and significant characteristics of Internet celebrity spaces, and combines quantitative evaluation methods for different types of spaces. The reputation evaluation system for urban Internet celebrity commercial blocks includes three primary indicators, namely, network popularity, commercial vitality, and consumer experience, and nine corresponding secondary indicators; among them, network popularity includes traffic conversion efficiency, network attention, and evaluation reputation, reflecting the influence of urban Internet celebrity commercial blocks on the network platform; commercial vitality includes business format mixing, Internet celebrity store density, and consumer activity, reflecting the business format layout characteristics and business atmosphere of urban Internet celebrity commercial blocks; consumer experience includes pedestrian accessibility, construction intensity, and landscape beauty, reflecting consumers' comprehensive evaluation of the indoor and outdoor environment and consumer activities of Internet celebrity commercial blocks.

[0160] S3. Based on the relevant data in the evaluation area, measure the secondary indicator data corresponding to the network popularity, business vitality and consumer experience in the evaluation area.

[0161] This embodiment uses the ArcGIS software to create a fishing net tool to create several 50*50m grids on the map of the evaluated area, and cuts the grids according to the boundaries of the evaluation area; measures the secondary indicator data corresponding to the network popularity, business vitality, and consumer experience in the evaluation area; among them, the number of Douyin video viewers and the number of users checking in related to the stores in the evaluation area are used to calculate the traffic conversion efficiency; the number of Douyin videos and pictures and texts related to the stores in the evaluation area and the number of likes, comments and collections are used to calculate the network attention; the total score and praise rate of the Dianping stores related to the stores in the evaluation area are used to calculate the evaluation reputation; the POI location point of interest data related to the stores in the evaluation area are used to calculate the mixed degree of business formats; the POI location point of interest data related to the stores within the evaluation range are used to count the number of all stores in the study area, and the number of online celebrity stores is screened and counted in combination with the distribution law of the number of online Douyin viewers, and the density of online celebrity stores is calculated; the POI location point of interest data related to the stores in the evaluation area are used to evaluate the consumption activity; the POI location point of interest data of bus stations and subway stations in the evaluation area are summarized, and the ArcGIS The software's neighbor analysis tool calculates the distance from popular online stores to subway stations, bus stops, and parking lot entrances and exits. The walking speed is set to 80m / min, and the distance is divided by the speed to get the walking time, and the walking accessibility is calculated. Based on the street view image data, the deep learning fully convolutional network (FCN) visual image semantic segmentation software SemanticSegmentation_v1.0 is used. The pixel comparison accuracy of the network in the training data set is 0.814426, and the pixel comparison accuracy in the test data set is 0.66839. The image was used for element recognition to obtain the proportion of 150 types of built environment elements in the street view image, and the pixel proportion of the two elements of buildings and skyscrapers in the image was identified and counted to represent the building enclosure and the visibility of high-rise buildings, and the construction intensity of each street view collection point was calculated. Based on the street view image data, the deep learning fully convolutional network (FCN) semantic segmentation software was used to identify and count the pixel proportions of the four elements of plants, sky, streets, and signs in the image, respectively, to represent the green view rate, sky view rate, openness, and signboard density, and to calculate the landscape style and beauty of each street view collection point.

[0162] The calculation results of traffic conversion efficiency, network attention, evaluation reputation, business mix, density of Internet celebrity stores, consumer activity, pedestrian accessibility, construction intensity and landscape beauty of this embodiment are as follows: Figure 2 to Figure 10 As shown; the spatial connection tool is used to export the indicator calculation results in the grid into a table in CSV format, assigned to the grid attribute table, and the natural break point classification method is used to divide the calculation results into five categories for visual expression. The darker the color, the higher the evaluation score.

[0163] S4. Normalize the secondary indicator data and determine the weight of each secondary indicator.

[0164] This embodiment uses the range standardization method to normalize the evaluation results, and uses the entropy weight method to determine the weights of each secondary indicator. The final weight calculation results are: network attention 0.24135, business format mixing 0.20745, traffic conversion efficiency 0.12098, evaluation reputation 0.08092, consumer activity 0.16421, Internet celebrity store density 0.08492, construction intensity 0.07837, landscape beauty 0.00894, and walkability 0.01285.

[0165] S5. Summarize the weights of each secondary indicator data and calculate the final evaluation result of the reputation of the city’s popular commercial district.

[0166] In this embodiment, ArcGIS software is used to perform two-dimensional graphic visualization and vector output according to the natural break point method. The final calculation results of the word-of-mouth evaluation of the Internet celebrity commercial blocks are ranked in order, from small to large, as low level 0.007315-0.084656, medium-low level 0.084657-0.192885, medium level 0.192886-0.272921, medium-high level 0.0272922-0.371437, and high level 0.371438-0.486672, as shown in Figure 2. Fig.11 shown.

[0167] It should be noted that although the method operations of the above embodiments are described in a specific order, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0168] Embodiment 3:

[0169] like Fig.12 As shown, this embodiment provides a reputation evaluation system for a city's popular commercial block, which includes an acquisition module 1201, a construction module 1202, a first calculation module 1203, a determination module 1204, and a second calculation module 1205. The specific functions of each module are as follows:

[0170] An acquisition module 1201 is used to acquire relevant data in the evaluation area, wherein the relevant data includes video platform data, evaluation website data, POI location point of interest data, road data and street view image data;

[0171] Construction module 1202, constructing a reputation evaluation system for a city's internet celebrity commercial block, wherein the reputation evaluation system for a city's internet celebrity commercial block includes three primary indicators of network popularity, commercial vitality, and consumer experience, and corresponding secondary indicators;

[0172] The first calculation module 1203 measures the secondary indicator data corresponding to the network popularity, business vitality, and consumer experience in the evaluation area according to the relevant data in the evaluation area;

[0173] Determination module 1204, normalizing the secondary index data to determine the weight of each secondary index;

[0174] The second calculation module 1205 adds weights to the data of each secondary indicator and summarizes them to calculate the final evaluation result of the reputation of the city's popular commercial district.

[0175] It should be noted that the system provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0176] Embodiment 4:

[0177] This embodiment provides a computer device, such as Fig.13 As shown, it includes a processor 1302, a memory, an input device 1303, a display device 1304 and a network interface 1305 connected through a system bus 1301. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 1306 and an internal memory 1307. The non-volatile storage medium 1306 stores an operating system, a computer program and a database. The internal memory 1307 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 1302 executes the computer program stored in the memory, the reputation evaluation method of the city Internet celebrity commercial block in the above-mentioned embodiment 1 is implemented as follows:

[0178] Relevant data within the evaluation area are obtained, wherein the relevant data include video platform data, evaluation website data, POI location point of interest data, road data and street view image data; a reputation evaluation system for urban Internet celebrity commercial blocks is constructed, wherein the reputation evaluation system for urban Internet celebrity commercial blocks includes three primary indicators of network popularity, commercial vitality and consumer experience and corresponding secondary indicators; based on the relevant data within the evaluation area, the secondary indicator data corresponding to the network popularity, commercial vitality and consumer experience within the evaluation area are measured; the secondary indicator data are normalized to determine the weight of each secondary indicator; the weight of each secondary indicator data is superimposed and summarized to calculate the final evaluation result of the reputation of the urban Internet celebrity commercial block.

[0179] Embodiment 5:

[0180] This embodiment provides a storage medium, which is a computer-readable storage medium, storing a computer program. When the computer program is executed by a processor, the method for evaluating the reputation of a city's popular commercial district in the above embodiment 1 is implemented as follows:

[0181] Relevant data within the evaluation area are obtained, wherein the relevant data include video platform data, evaluation website data, POI location point of interest data, road data and street view image data; a reputation evaluation system for urban Internet celebrity commercial blocks is constructed, wherein the reputation evaluation system for urban Internet celebrity commercial blocks includes three primary indicators of network popularity, commercial vitality and consumer experience and corresponding secondary indicators; based on the relevant data within the evaluation area, the secondary indicator data corresponding to the network popularity, commercial vitality and consumer experience within the evaluation area are measured; the secondary indicator data are normalized to determine the weight of each secondary indicator; the weight of each secondary indicator data is superimposed and summarized to calculate the final evaluation result of the reputation of the urban Internet celebrity commercial block.

[0182] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0183] In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device, or device. In this embodiment, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium, which may send, propagate, or transmit a program used by or in combination with an instruction execution system, device, or device. The computer program contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0184] The computer readable storage medium can be written in one or more programming languages ​​or a combination thereof to execute the computer program of the present embodiment, and the programming language includes an object-oriented programming language, such as Java, Python, C++, and also includes a conventional procedural programming language, such as C language or a similar programming language. The program can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0185] To sum up, the present invention is based on data mined from open source data, takes into account the characteristics of Internet celebrity commercial blocks that are different from other types of spaces, constructs a reputation evaluation system for urban Internet celebrity commercial blocks, measures the secondary indicator data corresponding to network popularity, commercial vitality, and consumer experience, and determines the weight of each secondary indicator, so as to calculate the final reputation evaluation result of the urban Internet celebrity commercial blocks. It can effectively evaluate the reputation of urban Internet celebrity commercial blocks, provide guidance for optimizing functional configuration and improving environmental quality, and provide assistance and reference for the efficient and accurate implementation of urban planning work.

[0186] The above description is only a preferred embodiment of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention.

Claims

1. A method for evaluating the reputation of a popular commercial district in a city. It is characterized in that The method comprises: Acquire relevant data in the evaluation area, the relevant data including video platform data, evaluation website data, POI location point of interest data, road data and street view image data; Constructing a reputation evaluation system for Internet-famous commercial blocks in cities, which includes three primary indicators, namely, network popularity, commercial vitality, and consumer experience, and corresponding secondary indicators; Based on the relevant data in the evaluation area, measure the secondary indicator data corresponding to the network popularity, business vitality, and consumer experience in the evaluation area; Normalize the secondary indicator data and determine the weight of each secondary indicator; The data of each secondary indicator are summed up by adding up the weights and calculating the final evaluation result of the reputation of the city’s popular commercial district.

2. The word-of-mouth evaluation method for a city's popular commercial district according to claim 1, It is characterized in that The network popularity includes traffic conversion efficiency, network attention and evaluation reputation; the commercial vitality includes business format mixing, density of Internet celebrity stores and consumer activity; the consumer experience includes pedestrian accessibility, construction intensity and landscape beauty; The secondary indicator data corresponding to network popularity, business vitality, and consumer experience in the evaluation area are measured based on the relevant data in the evaluation area, specifically including: Divide the evaluation area into grids according to the scope of the evaluation area; Use video platform data to calculate traffic conversion efficiency and network attention; Use the evaluation website data to calculate the evaluation reputation; Use POI location point of interest data to calculate the business mix; Use video platform data to calculate consumer activity; Utilize POI location data and combine it with video platform data for verification and calculate the density of popular stores; Calculate walking accessibility using POI location data and road data; The visual image semantic technology of deep learning fully convolutional network is used to calculate the construction intensity and landscape beauty.

3. The word-of-mouth evaluation method for a city's popular commercial district according to claim 2, It is characterized in that The use of video platform data to calculate traffic conversion efficiency and network attention specifically includes: Calculate traffic conversion efficiency based on the number of video viewers and user check-ins at the popular store; Calculate online attention based on the number of videos, pictures, and likes, comments, and collections of the popular stores; The use of evaluation website data to calculate the evaluation reputation specifically includes: The reputation of the reviews is calculated based on the total score and praise rate of the Internet celebrity store.

4. The word-of-mouth evaluation method for a city's popular commercial district according to claim 2, It is characterized in that The method of calculating the business mix by utilizing the POI location point of interest data specifically includes: Based on the POI location data related to the popular stores in the evaluation area, the Simpson index is used to calculate the business mix; The use of video platform data to calculate consumption activity specifically includes: Calculate consumption activity based on the number of people checking in at popular stores and the average amount of spending per person. The method of using POI location point of interest data and combining it with video platform data for verification and calculating the density of Internet celebrity stores specifically includes: Based on the POI location data, the number of all stores in the evaluation area is counted. Combined with the distribution pattern of the number of online viewers on the video platform, the number of Internet celebrity stores is screened and counted, and the density of Internet celebrity stores is calculated.

5. The word-of-mouth evaluation method for a city's popular commercial district according to claim 2, It is characterized in that The method of calculating the walking accessibility by using the POI location point of interest data and road data specifically includes: Calculate the distance from each popular store to the subway station, bus station, and parking lot entrance and exit, set the walking speed, divide the distance by the speed to get the walking time, and calculate the walking accessibility; The visual image semantic technology using deep learning fully convolutional network is used to calculate the construction intensity and landscape beauty, specifically including: Summarize street view image data, use deep learning full convolutional network semantic segmentation technology to identify and calculate the pixel ratio of buildings and skyscrapers in street view images, characterize the building enclosure and high-rise visibility, and calculate the construction intensity of each street view collection point; The street view image data is aggregated, and the deep learning fully convolutional network semantic segmentation technology is used to identify and count the pixel proportions of the four elements of plants, sky, streets, and signs in the street view images, characterize the green view rate, sky view rate, openness, and sign density, and calculate the landscape style and beauty of each street view collection point.

6. The word-of-mouth evaluation method for a city's popular commercial district according to any one of claims 1 to 5, It is characterized in that The normalization of the secondary indicator data to determine the weight of each secondary indicator specifically includes: The range standardization method is used to normalize the data of each secondary indicator; According to the normalized data of each secondary indicator, the entropy weight method is used to determine the weight of each secondary indicator.

7. The word-of-mouth evaluation method for a city's popular commercial district according to claim 6, It is characterized in that The entropy weight method is used to determine the weight of each secondary indicator according to the normalized secondary indicator data, specifically including: Calculate the proportion of each secondary indicator data under each secondary indicator; According to the proportion of each secondary indicator data under each secondary indicator, the information entropy value of each secondary indicator is calculated; According to the information entropy value of each secondary indicator, the information entropy redundancy of each secondary indicator is calculated; According to the information entropy redundancy of each secondary indicator, the weight of each secondary indicator is calculated.

8. A reputation evaluation system for popular commercial blocks in cities. It is characterized in that The system comprises: An acquisition module is used to acquire relevant data in the evaluation area, wherein the relevant data includes video platform data, evaluation website data, POI location point of interest data, road data and street view image data; A construction module is used to construct a reputation evaluation system for Internet-famous commercial blocks in cities. The reputation evaluation system for Internet-famous commercial blocks in cities includes three primary indicators, namely, network popularity, commercial vitality, and consumer experience, and corresponding secondary indicators; The first calculation module measures the secondary indicator data corresponding to network popularity, business vitality, and consumer experience in the evaluation area based on the relevant data in the evaluation area; Determine the module, normalize the secondary indicator data, and determine the weight of each secondary indicator; The second calculation module adds weights to the data of each secondary indicator and summarizes them to calculate the final evaluation result of the reputation of the city’s popular commercial district.

9. A computer device comprising a processor and a memory for storing a program executable by the processor, It is characterized in that When the processor executes the program stored in the memory, the method for evaluating the reputation of a celebrity commercial district in a city as described in any one of claims 1 to 7 is implemented.

10. A storage medium storing a program, It is characterized in that When the program is executed by the processor, the method for evaluating the reputation of a city's popular commercial district as described in any one of claims 1 to 7 is implemented.