Historical block offline consumption vitality identification method, system, device and medium
By collecting merchant consumption data and multi-dimensional driving factors, combined with geographically weighted regression and K-means clustering, the problem of refining the offline consumption vitality assessment of historical blocks was solved, accurate consumption vitality identification and planning were achieved, and the sustainable development of the blocks was promoted.
Patent Information
- Application Number
- CN202510665894.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-22
- Publication Date
- 2025-09-16
AI Technical Summary
Existing technologies lack detailed analysis of offline consumption vitality, especially in historical blocks, in the overall urban vitality assessment, and fail to effectively identify its spatial distribution and driving factors, resulting in inaccurate and lack of targeted assessment.
By collecting merchant consumption data and consumer reviews, grid-level consumption scale data is generated. Combined with driving factors such as POI points, road density, distance to transportation stations, and residential population, the geographically weighted regression model and K-means clustering method are used to identify and plan the consumption vitality characteristics of historical blocks.
It has achieved refined identification and accurate assessment of consumption vitality in historical blocks, provided scientific planning support, improved the accuracy and practicality of identifying consumption vitality, and promoted the sustainable development of historical blocks.
Smart Images

Figure CN120654016A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of urban planning technology, and in particular to a method, system, equipment and medium for identifying offline consumption vitality in historical blocks. Background Art
[0002] With the acceleration of urbanization and rapid economic development, assessing urban vitality has become a crucial component of urban planning, management, and decision-making. Urban vitality not only reflects a city's prosperity but is also directly linked to residents' quality of life and economic benefits. Currently, most related patents focus on identifying and assessing overall urban vitality. These methods utilize a variety of data sources, such as traffic flow, social media data, and population mobility data, to construct a comprehensive assessment system that effectively reflects a city's overall vitality.
[0003] For example, among existing patented technologies, one widely used method involves urban vitality assessment systems based on big data analysis. These systems typically construct comprehensive assessment models of urban vitality by collecting and integrating information from diverse data sources, such as public transportation, mobile communications, and social media activity. Through in-depth data analysis and mining, these models can comprehensively reflect the level of vitality in various aspects of a city, including traffic conditions, population distribution, and social activities. Furthermore, some patents involve the use of machine learning and artificial intelligence technologies to train models using historical data to predict future distributions of urban vitality, providing a scientific basis for urban planning and management.
[0004] Although existing technologies have made significant progress in the comprehensive assessment of urban vitality, they still have some obvious shortcomings and deficiencies. First, existing methods mostly focus on the assessment of the overall vitality of the city and lack a specific analysis of the vitality of specific aspects of the city. For example, offline consumption vitality, as an important component of urban economic vitality, has not received enough attention in its assessment. However, existing patented technologies have failed to conduct in-depth analysis of this specific area of offline consumption vitality and lack detailed identification of its spatial distribution and driving factors. Second, the assessment methods of existing technologies are relatively general and fail to conduct refined analysis of specific areas. For example, as an area with unique historical and cultural value in the city, the assessment of offline consumption vitality in historical blocks is of special importance. However, existing technologies often ignore the particularity of historical blocks and fail to conduct specific analysis of the distribution and changes of their offline consumption vitality. Summary of the Invention
[0005] The purpose of the present invention is to provide a method, system, equipment and medium for identifying offline consumption vitality in historical blocks, identify offline consumption vitality in historical blocks and its potential driving factors, improve the accuracy and practicality of consumption vitality identification, and provide solutions for the sustainable development of historical blocks.
[0006] To achieve the above objectives, the present invention provides a method for identifying offline consumption vitality in historical blocks, comprising:
[0007] Collect the average per capita consumption amount and number of consumer reviews for each merchant in the identified area to generate grid-level offline consumption scale data;
[0008] Obtaining data on driving factors of consumption vitality in the area to be identified; wherein the driving factors include the number of POI points, road density, distance to public transportation stations, resident population, and employed population;
[0009] Inputting the offline consumption scale data and the consumption vitality driving factor data into a pre-built geographically weighted regression model to obtain the coefficient results of each driving factor number;
[0010] Based on the coefficient results, the K-means clustering method is used to cluster the area to be identified to obtain multiple cluster areas;
[0011] Analyze the offline consumption vitality characteristics of each cluster area and plan the areas to be identified.
[0012] Optionally, the collection of the per capita consumption amount and the number of consumer reviews for each merchant in the area to be identified to generate grid-level offline consumption scale data includes:
[0013] Collect the average spending amount and number of consumer reviews for each merchant in the identified area, and calculate the estimated offline spending amount for each merchant;
[0014] The estimated offline consumption amounts are aggregated into a grid of preset size according to geographical location using a geographic information system tool to generate grid-level offline consumption scale data.
[0015] Optionally, after collecting the per capita consumption amount and the number of consumer reviews of each merchant in the area to be identified and generating grid-level offline consumption scale data, the method further includes:
[0016] Aggregating the grid-level offline consumption scale data according to street boundaries to generate street-level offline consumption scale data;
[0017] Performing a correlation analysis on the offline consumption scale data at the street level, the GDP data at the street level, and the per capita disposable income data to obtain a correlation analysis result;
[0018] When the correlation analysis result does not meet the preset requirements, the offline consumption scale data at the grid level is regenerated until the correlation analysis result meets the preset requirements, thereby obtaining the verified offline consumption scale data.
[0019] Optionally, the geographically weighted regression model is constructed by the following steps:
[0020] A geographically weighted regression model was constructed with the number of POI points, road density, distance to public transportation stations, residential population, and employed population as independent variables and grid-level offline consumption scale data as the dependent variable.
[0021] Optionally, obtaining the consumption activity driving factor data in the area to be identified includes:
[0022] Using GIS tools to calculate the number of POI points distributed in a preset grid size; wherein the POI points include residential areas, companies and entertainment facilities;
[0023] Calculate road density of preset grid sizes based on open source road network data;
[0024] Based on the POI point data of public transportation, calculate the distance between each grid and the nearest public transportation station;
[0025] Based on mobile phone signaling data, the residential population and employed population in each grid are calculated.
[0026] Optionally, after clustering the to-be-identified area using a K-means clustering method based on the coefficient result to obtain a plurality of cluster areas, the method further includes:
[0027] Validating the multiple cluster areas by a cross-validation method to obtain validation results;
[0028] Optimizing the clustering parameters of K-means clustering according to the verification results;
[0029] The region to be identified is re-clustered using the optimized clustering parameters to obtain a plurality of optimized cluster regions.
[0030] To achieve the above objectives, the present invention also provides a system for identifying offline consumption vitality in historical blocks, comprising:
[0031] The offline consumption scale data generation module is used to collect the average consumption amount and number of consumer reviews for each merchant in the identified area and generate grid-level offline consumption scale data;
[0032] A driving factor data acquisition module is used to obtain data on driving factors of consumption vitality in the area to be identified; wherein the driving factors include the number of POI points, road density, distance to public transportation stations, resident population, and employed population;
[0033] A geographically weighted regression module, configured to input the offline consumption scale data and the consumption vitality driving factor data into a pre-built geographically weighted regression model to obtain coefficient results for each driving factor;
[0034] A clustering module, configured to cluster the to-be-identified area using a K-means clustering method based on the coefficient result to obtain a plurality of cluster areas;
[0035] The regional planning module is used to analyze the offline consumption vitality characteristics of each cluster area and plan the area to be identified.
[0036] Optionally, the historical block offline consumption vitality identification system further includes an offline consumption scale data verification module, which is used to:
[0037] Aggregating the grid-level offline consumption scale data according to street boundaries to generate street-level offline consumption scale data;
[0038] Performing a correlation analysis on the offline consumption scale data at the street level, the GDP data at the street level, and the per capita disposable income data to obtain a correlation analysis result;
[0039] When the correlation analysis result does not meet the preset requirements, the offline consumption scale data at the grid level is regenerated until the correlation analysis result meets the preset requirements, thereby obtaining the verified offline consumption scale data.
[0040] To achieve the above objectives, the present invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the method for identifying offline consumption vitality in historical blocks as described in any one of the above items.
[0041] To achieve the above objectives, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the offline consumption vitality identification method for historical blocks as described in any one of the above items.
[0042] Compared with the existing technology, the present invention provides a method, system, equipment and medium for identifying offline consumption vitality in historical blocks. First, grid-level offline consumption scale data is generated by collecting the per capita consumption amount and the number of consumer evaluations of each merchant, which can accurately reflect the consumption situation in the block; then multi-dimensional driving factor data including the number of POI point distribution, road density, distance to public transportation stations, resident population and employed population are obtained, which comprehensively covers the factors affecting consumption vitality and can more accurately analyze the influencing mechanism of consumption vitality, thereby improving the accuracy and practicality of consumption vitality identification; and considering the spatial location factor through the geographically weighted regression model, the spatial differences in the impact of various driving factors on consumption vitality are explored, revealing the differences in the influencing mechanisms of consumption vitality in different regions; then, the K-means clustering method is used for clustering based on the coefficient results, and multiple cluster areas are divided to realize classified management of the blocks. Finally, differentiated strategies are formulated according to the characteristics of different cluster areas, and the offline consumption vitality characteristics of the cluster areas are analyzed, providing scientific support for the planning of historical blocks, which can enhance the overall consumption vitality of historical blocks and promote sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings used in the implementation methods. Obviously, the drawings described below are only some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0044] Figure 1 This is a flow chart of a method for identifying offline consumption vitality in a historical district provided by an embodiment of the present invention;
[0045] Figure 2 This is a schematic diagram of a 100-meter grid offline consumption feature visualization analysis provided by an embodiment of the present invention;
[0046] Figure 3 This is a relationship diagram between offline consumption amount, total retail sales of consumer goods, and per capita disposable income provided by an embodiment of the present invention;
[0047] Figure 4 This is a structural block diagram of a system for identifying offline consumption vitality in historical blocks provided by an embodiment of the present invention;
[0048] Figure 5 This is a structural block diagram of a terminal device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.
[0050] See also Figure 1 , Figure 1 : This is a flow chart of a method for identifying offline consumer activity in a historical block provided by an embodiment of the present invention. The method for identifying offline consumer activity in a historical block includes steps S1 to S5:
[0051] Step S1: Collect the per capita consumption amount and number of consumer reviews of each merchant in the area to be identified, and generate grid-level offline consumption scale data;
[0052] In an optional embodiment, the step S1 includes steps S101 to S102:
[0053] S101. Collect the average spending amount and number of consumer reviews for each merchant in the area to be identified, and calculate the estimated offline spending amount for each merchant;
[0054] S102. Aggregating the estimated offline consumption amounts into a grid of a preset size according to geographic location using a geographic information system tool to generate grid-level offline consumption scale data;
[0055] For example, within the identified area, detailed data for each merchant, including average spending per capita and number of consumer reviews, is collected from popular offline store data platforms (such as Meituan and Dianping). This data is then cleaned to remove outliers and missing items to ensure data integrity and accuracy.
[0056] The estimated offline spending for each merchant is calculated using the following formula:
[0057] Estimated offline consumption = per capita consumption amount × number of consumer reviews.
[0058] Furthermore, the geographic location of each merchant is associated with its estimated amount through a geographic information system (GIS) tool.
[0059] For example, the estimated amount data of each merchant can be aggregated into a 100-meter by 100-meter grid according to its geographical location to generate offline consumption scale data at the 100-meter grid scale of the city. GIS tools can also be used to map the aggregated data onto a city map to generate a spatial distribution map of offline consumption scale.
[0060] See also Figure 2 , Figure 2 100-meter grid offline consumption characteristics visualization analysis diagram provided by the embodiment of the present invention. Figure 2 As shown, Figure 2 a in the figure is the spatial distribution map of offline consumption scale. Figure 2 b in the figure is the spatial distribution of the number of offline stores in operation. From the spatial distribution of the two, we can see that the distribution of offline consumption amount is relatively more concentrated. Further coupling the two indicators of the number of stores and offline consumption amount at the 100-grid scale, the results are as follows: Figure 2 As shown in c, Figure 2 Where c is the correlation between the number of offline stores in a 100-meter grid and the amount of consumption. Figure 2 The c results in the figure show that there is a high correlation between the two. The fitting R-square and Pearson correlation coefficients are 0.387 and 0.622 respectively. The two outliers found in the fitting scatter plot are both representative shopping malls in a certain city, namely, the representative high-end shopping mall - Mall A, such as Figure 2 As shown in the d grid 1 in the figure, and the representative mass shopping mall - Plaza B, as shown in the figure Figure 2 The two grids are the grids with the highest offline consumption amount and the highest number of merchants, respectively. This is in line with common sense and objective facts, and also demonstrates the rationality and scientificity of the offline consumption amount estimation method proposed in the embodiment of the present invention.
[0061] Furthermore, in an optional embodiment, after step S1, the method further includes:
[0062] Aggregating the grid-level offline consumption scale data according to street boundaries to generate street-level offline consumption scale data;
[0063] Performing a correlation analysis on the offline consumption scale data at the street level, the GDP data at the street level, and the per capita disposable income data to obtain a correlation analysis result;
[0064] When the correlation analysis result does not meet the preset requirements, the offline consumption scale data at the grid level is regenerated until the correlation analysis result meets the preset requirements, thereby obtaining the verified offline consumption scale data.
[0065] It should be noted that since the offline consumption scale of the 100-meter grid in the embodiment of the present invention is an estimate and there are sample coverage limitations in big data in the specific implementation, the embodiment of the present invention conducts a comparative test on the distribution trend of the data. When the correlation analysis result does not meet the preset requirements, the grid-level offline consumption scale data is regenerated until the correlation analysis result meets the preset requirements, and the verified offline consumption scale data is obtained, and then the geographically weighted regression analysis is performed.
[0066] For example, offline consumption scale data of 100-meter grid size are aggregated according to the street boundary range to generate street-level offline consumption scale data, and then street-level GDP data and per capita disposable income data are obtained through public data sources (such as government statistical data). The Pearson correlation coefficient or Spearman rank correlation coefficient is used to calculate the correlation between street-level offline consumption scale data and GDP data and per capita disposable income data, and a significance test (such as a t-test or an F-test) is used to verify whether the correlation is significant. The distribution trend of offline consumption scale data and GDP and per capita disposable income can be compared through a trend chart or a scatter plot. If the correlation analysis results show a highly significant correlation, the feasibility and scientificity of the method of the embodiment of the present invention are verified.
[0067] See also Figure 3 , Figure 3 This is a relationship diagram between offline consumption amount, total retail sales of consumer goods, and per capita disposable income provided by an embodiment of the present invention. Figure 3 As shown, the embodiment of the present invention performs a correlation check between the estimated offline consumption amount and two related statistical data, namely, the total retail sales of consumer goods and the per capita disposable income. Figure 3 In the figure, the blue square data points and the corresponding blue broken line represent the relationship between offline consumption amount and per capita disposable income. The fitting line equation is y = 0.1113x + 6.1733, R 2 =0.5913. This indicates that there is a certain linear relationship between the two. The orange circular data points and the corresponding orange broken line represent the relationship between offline consumption and total retail sales of consumer goods. The fitted line equation is y=63.233x+143.04, R 2 =0.9647. 2 The value is close to 1, indicating that there is a strong linear relationship between the offline consumption amount and the total retail sales of consumer goods, which further verifies the rationality of the embodiment of the present invention using street-level GDP data and per capita disposable income data to verify the offline consumption scale data.
[0068] Step S2: Acquire data on driving factors of consumption vitality in the area to be identified; wherein the driving factors include the number of POI points, road density, distance to public transportation stations, resident population, and employed population;
[0069] In an optional embodiment, step S2 includes steps S201 and S204:
[0070] S201. Calculate the number of POI points distributed in a preset size grid using a GIS tool; wherein the POI points include residential areas, companies and enterprises, and entertainment facilities;
[0071] S202. Calculate the road density of a preset grid size based on open source road network data;
[0072] S203, calculating the distance between each grid and the nearest public transportation station based on the public transportation POI point data;
[0073] S204. Calculate the resident population and employed population in each grid based on mobile phone signaling data.
[0074] For example, GIS tools are used to calculate the distribution number of these POI points at a 100-meter grid scale. Based on the open street map open source road network data, the road density at a 100-meter grid scale is calculated. Based on the bus stop and subway station POI point data, the distance of each grid to the nearest bus stop and subway station is calculated. Based on mobile phone signaling data, the residential population and employed population in each grid are calculated.
[0075] It is worth noting that the offline consumption vitality driving factors selected in the embodiment of the present invention include the number of POI points, road density, public transportation distance, resident population and employed population. Among them, POI points include residential communities, companies and enterprises, entertainment facilities (including shopping, catering, cultural and sports entertainment facilities), etc., and public transportation stations include bus stops and subway stations.
[0076] The standards and reasons for selecting these driving factors in the embodiment of the present invention are as follows:
[0077] Residential communities provide a permanent population base with robust daily consumer demand. Surrounding businesses are often designed to cater to residents' needs, and greater convenience leads to higher spending. Businesses represent a vibrant economy with numerous jobs and employees with strong income and spending power. This in turn drives the development of surrounding businesses, increasing both the frequency and value of consumption. Entertainment facilities cater to people's cultural needs and leisure, attracting large numbers of consumers, extending their stay and stimulating consumption. They also tend to create a clustering effect, driving consumption in surrounding areas. Road density reflects convenient transportation, facilitating consumer access to consumer destinations, facilitating freight transportation and distribution, reducing logistics costs, and boosting commercial vitality. Convenient public transportation attracts more consumers to consumer destinations, expanding their consumer base. Customer traffic flows tend to converge around stations, creating numerous consumption opportunities. The residential population forms the foundation of consumption. A larger population means greater potential consumer demand. Different demographics have different consumption preferences, resulting in a broader and more diverse consumer market. The income of employed individuals underpins consumption, providing both the ability and confidence to spend. Their work and rest schedules influence the timing and context of consumption, and thus the scale of consumption.
[0078] Therefore, in one embodiment of the invention, the geographically weighted regression model is constructed by the following steps:
[0079] A geographically weighted regression model was constructed with the number of POI points, road density, distance to public transportation stations, residential population and employed population as independent variables, and grid-level offline consumption scale data as the dependent variable.
[0080] For example, based on POI data, residential areas, businesses, and entertainment facilities (including shopping, dining, and cultural and sports facilities) were selected as independent variables. The number of these POIs at a 100-meter grid was calculated as the independent variable. Based on OpenStreetMap open-source road network data, the road density at a 100-meter grid was calculated as the independent variable. Based on bus stop and subway station POI data, the distance from each grid to the nearest bus stop and subway station was calculated as the independent variable. Based on mobile phone signaling data, the residential population and employed population in each grid were calculated as independent variables. A geographically weighted regression model was constructed using the estimated offline consumption scale at a 100-meter grid as the dependent variable.
[0081] It is worth noting that the existing technology often relies on a single data source in the assessment of urban vitality, which makes it difficult to fully reflect the true situation of offline consumption vitality. The embodiment of the present invention constructs a comprehensive model by integrating multi-source data such as mass store big data, POI data, road network data, bus station and subway station POI point data, and mobile phone signaling data. This multi-source data fusion method can not only accurately identify the scale of offline consumption at the 100-meter grid scale, but also finely analyze its spatial distribution characteristics. For example, the embodiment of the present invention refines the estimation accuracy of offline consumption scale through spatial gridding processing, making up for the shortcomings of the existing technology in specific field analysis.
[0082] Step S3: inputting the offline consumption scale data and the consumption vitality driving factor data into a pre-built geographically weighted regression model to obtain coefficient results for each driving factor;
[0083] It is worth noting that existing technologies are often too general when identifying the driving factors of urban vitality and fail to deeply explore the key influencing factors. The embodiment of the present invention identifies the spatial heterogeneity characteristics that affect the scale of offline consumption by constructing a geographically weighted regression model. Specifically, the embodiment of the present invention comprehensively considers multiple factors such as the business environment, population mobility, and social activities. Through multi-level and multi-dimensional data analysis, it deeply explores potential driving factors such as residential areas, companies, entertainment facilities, road density, traffic convenience, and demographics. This scientific and effective driving factor identification method provides more accurate decision-making support for urban management and improves the pertinence and effectiveness of strategies.
[0084] Furthermore, heat maps or coefficient distribution maps can be used to intuitively display the impact intensity of each driving factor in different spatial locations, analyze which driving factors have the most significant impact on the scale of offline consumption, and identify their spatial distribution patterns.
[0085] Step S4: clustering the to-be-identified area using a K-means clustering method based on the coefficient result to obtain a plurality of cluster areas;
[0086] For example, K-means clustering is performed based on the coefficient results of the geographically weighted regression model to generate several sub-class areas, and an appropriate number of clusters K is selected to ensure that the clustering results have significant regional characteristic differences.
[0087] Furthermore, in an optional embodiment, after step S4, the method further includes:
[0088] Validating the multiple cluster areas by a cross-validation method to obtain validation results;
[0089] Optimizing the clustering parameters of K-means clustering according to the verification results;
[0090] The region to be identified is re-clustered using the optimized clustering parameters to obtain a plurality of optimized cluster regions.
[0091] It is worth noting that the stability and reliability of cluster analysis can be verified through methods such as cross-validation. Based on the verification results, clustering parameters and strategies can be optimized to ensure the effectiveness and feasibility of the strategy.
[0092] Step S5: Analyze the offline consumption activity characteristics of each cluster area and plan the area to be identified.
[0093] It is worth noting that the existing technology usually adopts a "one-size-fits-all" approach in urban management and planning strategy formulation, which lacks pertinence and flexibility. The embodiment of the present invention divides the city into several cluster areas with significant differences in offline consumption scale characteristics based on the coefficient results of the geographically weighted regression model through K-means cluster analysis. Customized management and planning can be carried out according to the characteristics of different cluster areas. For example, a cluster area finds that its offline consumption scale is lower than the overall average level, and entertainment facilities and subway stations have a significant promoting effect on it. A strategy can be proposed to increase the distribution density of entertainment facilities and subway stations to enhance the offline consumption popularity in the area. This customized strategy can not only significantly improve management efficiency, but also promote the high-quality development of the urban economy.
[0094] In summary, an embodiment of the present invention provides a method for identifying offline consumption vitality in a historical block. First, the per capita consumption amount and the number of consumer reviews of each merchant in the area to be identified are collected to generate grid-level offline consumption scale data, and then the consumption vitality driving factor data in the area to be identified are obtained; wherein, the driving factors include the number of POI point distributions, road density, distance to public transportation stations, resident population and employed population; the offline consumption scale data and the consumption vitality driving factor data are then input into a pre-constructed geographically weighted regression model to obtain coefficient results for each driving factor number; finally, based on the coefficient results, the K-means clustering method is used to cluster the area to be identified to obtain multiple cluster areas, and the offline consumption vitality characteristics of each cluster area are analyzed to plan the area to be identified.
[0095] The embodiment of the present invention generates grid-level offline consumption scale data by collecting the per capita consumption amount and the number of consumer reviews of each merchant, which can accurately reflect the consumption situation in the block; obtains multi-dimensional driving factor data including the distribution number of POI points, road density, distance to public transportation stations, resident population and employed population, comprehensively covers the factors affecting consumption vitality, and can more accurately analyze the influencing mechanism of consumption vitality, thereby improving the accuracy and practicality of consumption vitality identification; considers the spatial location factor through the geographically weighted regression model, and can explore the spatial differences in the impact of various driving factors on consumption vitality, revealing the differences in the influencing mechanism of consumption vitality in different regions; clustering is performed based on the coefficient results using the K-means clustering method, and multiple cluster areas are divided to realize classified management of the block, formulate differentiated strategies based on the characteristics of different cluster areas, analyze the offline consumption vitality characteristics of the cluster areas, provide scientific support for block planning, and can enhance the overall consumption vitality of the block and promote sustainable development.
[0096] Based on the above method items, the present invention provides corresponding embodiments of the system items.
[0097] See also Figure 4 , Figure 4 This is a block diagram of a system for identifying offline consumer activity in historical districts provided by an embodiment of the present invention. The system comprises:
[0098] The offline consumption scale data generation module 21 is used to collect the average consumption amount and the number of consumer reviews for each merchant in the identified area and generate grid-level offline consumption scale data;
[0099] A driving factor data acquisition module 23 is used to acquire data on driving factors of consumption activity in the area to be identified; wherein the driving factors include the number of POI points, road density, distance to public transportation stations, resident population, and employed population;
[0100] A geographically weighted regression module 24 is used to input the offline consumption scale data and the consumption vitality driving factor data into a pre-built geographically weighted regression model to obtain coefficient results of each driving factor number;
[0101] A clustering module 25 is configured to cluster the to-be-identified area using a K-means clustering method based on the coefficient result to obtain a plurality of cluster areas;
[0102] The regional planning module 26 is used to analyze the offline consumption activity characteristics of each cluster area and plan the area to be identified.
[0103] like Figure 3 As shown, the historical block offline consumption vitality identification system further includes an offline consumption scale data verification module 22 for:
[0104] Aggregating the grid-level offline consumption scale data according to street boundaries to generate street-level offline consumption scale data;
[0105] Performing a correlation analysis on the offline consumption scale data at the street level, the GDP data at the street level, and the per capita disposable income data to obtain a correlation analysis result;
[0106] When the correlation analysis result does not meet the preset requirements, the offline consumption scale data at the grid level is regenerated until the correlation analysis result meets the preset requirements, thereby obtaining the verified offline consumption scale data.
[0107] In an optional embodiment, the offline consumption scale data generating module 21 is specifically configured to:
[0108] Collect the average spending amount and number of consumer reviews for each merchant in the identified area, and calculate the estimated offline spending amount for each merchant;
[0109] The estimated offline consumption amounts are aggregated into a grid of preset size according to geographical location using a geographic information system tool to generate grid-level offline consumption scale data.
[0110] In an optional embodiment, the driving factor data acquisition module 23 is specifically configured to:
[0111] Using GIS tools to calculate the number of POI points distributed in a preset grid size; wherein the POI points include residential areas, companies and entertainment facilities;
[0112] Calculate road density of preset grid sizes based on open source road network data;
[0113] Based on the POI point data of public transportation, calculate the distance between each grid and the nearest public transportation station;
[0114] Based on mobile phone signaling data, the residential population and employed population in each grid are calculated.
[0115] In an optional embodiment, the system for identifying offline consumption vitality in historical blocks further includes a cluster verification module for:
[0116] Validating the multiple cluster areas by a cross-validation method to obtain validation results;
[0117] Optimizing the clustering parameters of K-means clustering according to the verification results;
[0118] The region to be identified is re-clustered using the optimized clustering parameters to obtain a plurality of optimized cluster regions.
[0119] It should be noted that the offline consumption vitality identification system for historical blocks provided by the embodiment of the present invention is used to execute all the process steps of the offline consumption vitality identification method for historical blocks in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.
[0120] The embodiment of the present invention further provides a terminal device, such as Figure 5 , which is a block diagram of a preferred embodiment of a terminal device provided by the present invention. The terminal device includes a processor 31, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 31. When the processor 31 executes the computer program, it implements the method for identifying offline consumption vitality in a historical district as described in any of the above embodiments.
[0121] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for identifying offline consumption vitality in historical blocks as described in any of the above embodiments.
[0122] When the processor 31 executes the computer program, the steps in the above-mentioned embodiment of the method for identifying offline consumption vitality in historical blocks are implemented, for example Figure 1 Alternatively, when the processor 31 executes the computer program, it implements the functions of each module in the embodiment of the above-mentioned historical block offline consumption vitality identification system, such as Figure 4 The functions of each module of the offline consumption vitality identification system for historical blocks are shown.
[0123] Preferably, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor 31 to implement the present invention. The one or more modules / units can be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.
[0124] The processor 31 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or the processor 31 can be any conventional processor. The processor 31 is the control center of the terminal device, and uses various interfaces and lines to connect the various parts of the terminal device.
[0125] The memory 32 mainly includes a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function, and the data storage area can store related data. In addition, the memory 32 can be a high-speed random access memory or a non-volatile memory such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, or a flash card. Alternatively, the memory 32 can be other volatile solid-state memory devices.
[0126] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 5 The structural block diagram shown is only an example of the structure of the terminal device and does not constitute a structural limitation of the terminal device. The terminal device may include more or fewer components than shown in the figure, or a combination of certain components, or different components.
[0127] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for identifying offline consumption vitality in historical blocks, characterized by: include: Collect the average per capita consumption amount and number of consumer reviews for each merchant in the identified area to generate grid-level offline consumption scale data; Obtaining data on driving factors of consumption vitality in the area to be identified; wherein the driving factors include the number of POI points, road density, distance to public transportation stations, resident population, and employed population; Inputting the offline consumption scale data and the consumption vitality driving factor data into a pre-built geographically weighted regression model to obtain the coefficient results of each driving factor number; Based on the coefficient results, the K-means clustering method is used to cluster the area to be identified to obtain multiple cluster areas; Analyze the offline consumption vitality characteristics of each cluster area and plan the areas to be identified.
2. The method for identifying offline consumption vitality in a historical district as claimed in claim 1, characterized in that: The collection of per capita consumption amount and number of consumer reviews for each merchant in the identified area to generate grid-level offline consumption scale data includes: Collect the average spending amount and number of consumer reviews for each merchant in the identified area, and calculate the estimated offline spending amount for each merchant; The estimated offline consumption amounts are aggregated into a grid of preset size according to geographical location using a geographic information system tool to generate grid-level offline consumption scale data.
3. The method for identifying offline consumption vitality in a historical district according to claim 1, characterized in that: After collecting the per capita consumption amount and the number of consumer reviews for each merchant in the area to be identified and generating grid-level offline consumption scale data, the following steps are also included: Aggregating the grid-level offline consumption scale data according to street boundaries to generate street-level offline consumption scale data; Performing a correlation analysis on the offline consumption scale data at the street level, the GDP data at the street level, and the per capita disposable income data to obtain a correlation analysis result; When the correlation analysis result does not meet the preset requirements, the offline consumption scale data at the grid level is regenerated until the correlation analysis result meets the preset requirements, thereby obtaining the verified offline consumption scale data.
4. The method for identifying offline consumption vitality in a historical district according to claim 1, characterized in that: The geographically weighted regression model is constructed through the following steps: A geographically weighted regression model was constructed with the number of POI points, road density, distance to public transportation stations, residential population and employed population as independent variables, and grid-level offline consumption scale data as the dependent variable.
5. The method for identifying offline consumption vitality in a historical district as claimed in claim 1, characterized in that: The acquiring of consumption vitality driving factor data in the to-be-identified area includes: Using GIS tools to calculate the number of POI points distributed in a preset grid size; wherein the POI points include residential areas, companies and entertainment facilities; Calculate road density of preset grid sizes based on open source road network data; Based on the POI point data of public transportation, calculate the distance between each grid and the nearest public transportation station; Based on mobile phone signaling data, the residential population and employed population in each grid are calculated.
6. The method for identifying offline consumption vitality in a historical district according to claim 1, characterized in that: After clustering the to-be-identified area based on the coefficient result using the K-means clustering method to obtain a plurality of cluster areas, the method further includes: Validating the multiple cluster areas by a cross-validation method to obtain validation results; Optimizing the clustering parameters of K-means clustering according to the verification results; The region to be identified is re-clustered using the optimized clustering parameters to obtain a plurality of optimized cluster regions.
7. A system for identifying offline consumption vitality in historical blocks, characterized by: include: The offline consumption scale data generation module is used to collect the average consumption amount and number of consumer reviews for each merchant in the identified area and generate grid-level offline consumption scale data; A driving factor data acquisition module is used to obtain data on driving factors of consumption vitality in the area to be identified; wherein the driving factors include the number of POI points, road density, distance to public transportation stations, resident population, and employed population; A geographically weighted regression module, configured to input the offline consumption scale data and the consumption vitality driving factor data into a pre-built geographically weighted regression model to obtain coefficient results for each driving factor; A clustering module, configured to cluster the to-be-identified area using a K-means clustering method based on the coefficient result to obtain a plurality of cluster areas; The regional planning module is used to analyze the offline consumption vitality characteristics of each cluster area and plan the area to be identified.
8. The offline consumption activity identification system for historical blocks according to claim 7, characterized in that: It also includes an offline consumption scale data verification module for: Aggregating the grid-level offline consumption scale data according to street boundaries to generate street-level offline consumption scale data; Performing a correlation analysis on the offline consumption scale data at the street level, the GDP data at the street level, and the per capita disposable income data to obtain a correlation analysis result; When the correlation analysis result does not meet the preset requirements, the offline consumption scale data at the grid level is regenerated until the correlation analysis result meets the preset requirements, thereby obtaining the verified offline consumption scale data.
9. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method for identifying offline consumption vitality in a historical district as described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for identifying offline consumption vitality in a historical block as described in any one of claims 1 to 6.