Urban center commercial network evaluation and optimization method based on mapping knowledge domain

Abstract

The invention discloses an urban center commercial network evaluation and optimization method based on a knowledge graph, and the method comprises the following steps: collecting and processing the national urban center data, and constructing a case urban center knowledge graph; according to the knowledge graph, a random forest algorithm is adopted to construct a correlation model about crowd intensity and commercial network construction, and an optimal commercial network construction mode is obtained through a genetic algorithm; judging whether the commercial network construction needs to be adjusted according to the optimal commercial network construction mode based on the commercial network construction data of the central area of the target city; if adjustment is needed, optimization adjustment results of various commercial network points are automatically solved and output through adjustment of the optimization model; and outputting an optimization adjustment result to a digital space sand table of the central area of the target city for interactive display, and outputting an adjustment report. According to the invention, accurate adjustment of central area commercial network points based on the knowledge graph is realized, so that different central area commercial compositions are more reasonable.

Description

Technical Field

[0001] The present invention relates to the field of urban planning, and specifically to a method for evaluating and optimizing commercial points in a city center based on a knowledge graph. Background Art

[0002] As the core area of ​​the city, the city center is an important carrier for busy commercial activities in the city. It is also a traffic flow gathering area and a dense place for social interaction. Accurately evaluating the development trend and status of commercial outlets in these areas and making reasonable adjustments and optimizations are one of the key tasks in urban management and planning. Traditional outlet evaluation methods mainly rely on expert evaluation, questionnaires and simple statistical analysis. The limitations of these methods are that the data source is single, the subjective evaluation standards are not unified, and the response speed is seriously lagging; similarly, in terms of commercial outlet layout optimization, although the existing technology provides basic optimization tools and methods, there are still problems such as insufficient data integration, imperfect models, poor real-time performance and much manual intervention. Comprehensive and accurate evaluation and optimization of commercial outlets is not only conducive to the efficient allocation of resources, sustainable economic growth and friendly improvement of the environment, but also improves the quality of life, convenience and happiness of the radiated population. On the other hand, the acquisition of big data from multiple sources in real time, the development of advanced algorithms and machine learning technologies, make it possible to develop more accurate, efficient, dynamic and comprehensive central area evaluation and optimization methods. Based on knowledge graphs, random forest models and genetic algorithms, the business structure of current urban central areas is evaluated, and the output adjustment mode is automatically solved according to the optimal model, which can provide targeted adjustment layout optimization methods for different urban central areas. Summary of the invention

[0003] In view of the shortcomings of the existing technology, the present invention provides a method for evaluating and optimizing commercial outlets in urban central areas based on knowledge graphs, which solves the problems of data fragmentation, insufficient correlation analysis, static evaluation limitations, incomplete optimization suggestions and difficulty in meeting personalized needs in the traditional evaluation and optimization process.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0005] A method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph includes the following steps:

[0006] Step 1: Data collection and processing of urban center areas and knowledge graph construction

[0007] Obtain urban population data, commercial network data, building vector data, and central area boundary data for urban central areas across the country, input them into the geographic information platform for format unification, and form a case city central area database;

[0008] Based on the database, three types of entities, namely, crowd, commercial outlets and central area, are identified and extracted and numbered, and the location and quantity attributes of crowd entities, the location, type and area attributes of commercial outlet entities, and the location and area attributes of central area entities are calculated respectively, and the association relationship between the three types of entities is determined based on spatial location; the above results are input into the NEO4J graph database platform to construct a knowledge graph of the central area of ​​the case city;

[0009] Step 2: Construction of a correlation model between crowd intensity and commercial outlets

[0010] Based on the knowledge graph, extract the entity data of each central area and the crowd and commercial outlets associated therewith, and aggregate and calculate the data into a human-industry association data set containing crowd intensity data and commercial outlet composition data; use the random forest algorithm to train the association model about crowd intensity and commercial outlet composition based on the data set, and determine the optimal association model through the grid search method; based on the commercial outlet composition data and the obtained optimal association model, use the genetic algorithm to solve and obtain the optimal commercial outlet composition model;

[0011] Step 3: Evaluation of the commercial network structure in the city center

[0012] Obtain a target city central area commercial outlet composition data set containing the proportion and area information of each type of commercial outlets, obtain the actual commercial outlet composition pattern of the central area, and compare it with the determined optimal commercial outlet composition pattern. If the results are inconsistent, it is determined that the commercial outlet composition of the target city central area needs to be adjusted;

[0013] Step 4: Optimize the composition of commercial outlets in the city center

[0014] Based on the optimal proportion of each type of commercial outlets obtained from the optimal commercial outlets composition model and the commercial outlets composition data of the target city center, a commercial outlets optimization adjustment model is established; the optimization adjustment results of each type of commercial outlets are automatically solved and output through the optimization adjustment model;

[0015] Step 5: Interactive display of optimization solutions and output of adjustment reports

[0016] Based on the DataEase data visualization platform, the optimization and adjustment results are projected onto a large touch screen for interactive display, and a commercial outlet adjustment report for the target city center is issued.

[0017] Preferably, the urban population data, commercial network data, building vector data and central area boundary data of the national urban central areas are obtained, and input into the geographic information platform for format unification processing to form a case urban central area database, specifically including:

[0018] Using the Intel Core i9-10980XE high-performance processor, the obtained crowd point data, commercial network POI data, building vector data and central area boundary data of urban central areas across the country were deduplicated, cleaned and normalized, and then merged and input into the ArcGIS10.8 geographic information platform, unified the data coordinates and data format types, formed a case city central area database, and stored the results in the Samsung PM1733 NVMe SSD storage;

[0019] The crowd point data refers to the population point vector data of the central areas of cities across the country from 9:00 to 22:00 for two consecutive weeks obtained at intervals of 2 hours through the Baidu Huiyan open data platform, specifically including the number of people and longitude and latitude information of the points; the commercial outlet POI data refers to the commercial outlet POI data of the central areas of cities across the country obtained based on the official platform of Dianping.com, specifically including the name, category, number of floors of the building where the commercial outlet is located and longitude and latitude information; the building vector data refers to the building vector data obtained through the OpenStreetMap open data platform, specifically including the building area, number of floors and longitude and latitude information; the central area boundary data refers to the current drawings containing the central area boundary information obtained from the official website of the city government, planning bureau or natural resources bureau, and the central area boundary data containing the area and longitude and latitude information is obtained by drawing through spatial correction and drawing tools in the ArcGIS10.8 geographic information platform;

[0020] Preferably, based on the database, three types of entities, namely, crowd, commercial outlets and central area, are identified and extracted and numbered, and the location and quantity attributes of crowd entities, the location, type and area attributes of commercial outlet entities, and the location and area attributes of central area entities are calculated respectively, and the association relationship between the three types of entities is determined based on spatial location; the above results are input into the NEO4J graph database platform to construct a knowledge graph of the central area of ​​the case city, which specifically includes:

[0021] Based on the crowd point data, commercial network POI data and central area boundary data in the central area of ​​the case city, three types of entities, namely crowd, commercial network and central area, are identified and extracted, and numbered respectively;

[0022] The location attributes and quantity attributes of crowd entity data are determined by extracting and calculating the latitude and longitude information and quantity information of crowd points in the ArcGIS 10.8 geographic information platform; the location attributes of commercial outlets entities are determined by extracting the latitude and longitude information of commercial outlets POI data; the type information of commercial outlets is extracted and the commercial service facility land classification standards in the "Urban Land Classification and Planning and Construction Land Standards" are referred to, and the commercial outlets data are reclassified. The type attributes of commercial outlets entities are determined based on the reclassification results. The reclassification results specifically include seven categories: retail business, wholesale market, catering services, hotel services, entertainment services, health services and life services. The specific classification standards and characteristics are as follows:

[0023]

[0024]

[0025] The number of floors, area, longitude and latitude information of building vector data and the number of floors of buildings where commercial outlets POI data are located are extracted. In the ArcGIS10.8 geographic information platform, the spatial association tool is used to extract the building area of ​​the floors of buildings that intersect with the commercial outlets in geographic space based on the number of floors, and combined with field survey corrections, the area attributes of the commercial outlet entities are determined based on the final results; the area information and longitude and latitude information of the central area boundary data are extracted to determine the area attributes and location attributes of the central area entities.

[0026] The specific indicator names, symbol representations and calculation methods of the three types of entities are as follows:

[0027]

[0028] Based on the latitude and longitude information of the three types of entities, the spatial association tool is used in the ArcGIS 10.8 geographic information platform to determine the crowd entity and the commercial outlet entity located in the central area entity in geographic space. According to the results, the association relationship between the crowd entity, the commercial outlet entity and the central area entity is obtained. The specific association relationship and calculation method are as follows:

[0029]

[0030] The numbers of the three types of entities that are successfully associated are used as unique identifiers, and the data structure is sorted out in combination with the location coordinates and the corresponding entity attributes. The processed entities, entity attributes and association relationship data are imported into the Neo4j4.4 graph database platform using Cypher statements. The node types are determined to be crowds, commercial outlets and central areas. Neo4jBrowser and Bloom are used for data visualization to construct a knowledge graph of the case city central area.

[0031] Preferably, based on the knowledge graph, the entity data of each central area and the crowd and commercial outlets associated therewith are extracted, and the data are aggregated and calculated into a human-industry association data set containing crowd intensity data and commercial outlet composition data, specifically including:

[0032] According to the entity association relationship obtained in step 2, the crowd entities and their quantity attributes associated with each central area entity are extracted, and the commercial outlets entities and their type attributes and area attributes associated with each central area entity are extracted; the per capita intensity index I corresponding to each central area entity is calculated by using the multi-core high-threaded processor Intel Xeon Platinum 8280 i Data and the area ratio of various types of commercial outlets ij Data, the area proportion of each type of commercial outlets entity R ij The data is aggregated to form the data of commercial outlets;

[0033] The per capita intensity index I i The specific calculation formula is:

[0034]

[0035] Among them, I i represents the crowd intensity index of the i-th central area entity; P j A represents the number of people in the jth crowd entity of the central area entity, and n is the total number of crowd entities associated with the central area entity; 中 Indicates the area attribute value of the central area entity; D indicates the total number of days in the time period of the acquired crowd data; H indicates the total number of times in the time period of the acquired crowd data per day;

[0036] The area proportion of each type of commercial outlets R ij The specific calculation formula is:

[0037]

[0038] Among them, R ij S represents the area proportion of the j-th type of commercial outlets in the i-th central area entity, where j is retail business, wholesale market, catering, hotel, finance and insurance, art and media, other business, entertainment, fitness, gas station, other public utility business online stores, and other service facilities; j-k S represents the area attribute value of the kth commercial outlet entity belonging to the jth type of commercial outlet associated with the central area, l is the total number of commercial outlet entities of this type associated with the central area; m It represents the sum of the area attribute values ​​of all commercial outlets entities associated with the central area;

[0039] The above calculation results are transferred to the Samsung PM1733 NVMe SSD storage and summarized to form a human-industry related data set containing crowd intensity index data and commercial network composition data.

[0040] Preferably, a random forest algorithm is used to train a correlation model between crowd intensity and commercial outlets composition based on the data set, and an optimal correlation model is determined by a grid search method; based on the commercial outlets composition data and the obtained optimal correlation model, a genetic algorithm is used to solve and obtain the optimal commercial outlets composition pattern, specifically including:

[0041] A random forest association model of crowd intensity and commercial outlets was constructed, the crowd-industry association data set was divided into a training set and a test set in a ratio of 8:2, the training set was put into the random forest model for training based on a workstation equipped with a high-performance graphics card NVIDIAA100 Tensor Core GPU, and the optimal parameters of the model were determined by a grid search method, wherein the parameters specifically included the number of decision trees in the model, the maximum depth of the decision tree, the minimum number of sample splits for each decision tree, and the minimum number of sample leaves for each decision tree; based on the optimal parameters, the test set was put into the trained model for verification, and finally the optimal crowd intensity and commercial outlets association model was obtained;

[0042] The genetic algorithm is used to input the optimal association model obtained above and the commercial outlets composition data of the central area of ​​the case city, and the configuration pattern of the commercial outlets is represented in the form of real number coding, where each individual (commercial outlet composition pattern) is composed of the proportion R of each type of commercial outlets. x Composition; randomly generate multiple individuals to form an initial population, each individual represents a commercial network configuration mode, based on given constraints By repeating the selection, crossover and mutation operations, the population is continuously updated and finally the optimal commercial network structure pattern {C1:C2:…:C n}.

[0043] Preferably, the step of obtaining a target city central area commercial outlet composition data set including the proportion and area information of each type of commercial outlets, obtaining an actual commercial outlet composition pattern of the central area, and comparing the actual commercial outlet composition pattern with the determined optimal commercial outlet composition pattern, and if the results are inconsistent, determining that the commercial outlet composition of the target city central area needs to be adjusted, specifically includes:

[0044] Download the planning and design publicity documents of the central area of ​​the target city from the official website of the target city government, planning bureau or natural resources bureau, the publicity documents including the project description, design drawings and other relevant documents containing the economic and technical indicator information of the planning scheme of the central area of ​​the target city; use the Python text analysis library to automatically identify and extract the proportion data and land area data of each type of commercial outlets in the planning scheme from the publicity documents to form a commercial outlet composition data set of the central area of ​​the target city, and transfer it to the Samsung PM1733 NVMe SSD storage; based on the commercial outlet type described in step one, reclassify the data set so that the commercial outlets in the target city are consistent with the commercial outlet type described in step one, and calculate the proportion R of the i-th type of commercial outlets in the central area of ​​the target city based on the reclassified commercial outlet composition data using a workstation equipped with a high-performance graphics card NVIDIA A100 TensorCore GPU. 0i and land area S 0i ;

[0045] Based on the obtained proportion of all types of commercial outlets in the central area of ​​the target city, R 0i , and summarize the actual commercial network structure model {C 01 :C 02 :…:C 0n}, and compare it with the optimal commercial network structure model {C1:C2:…:C n} for comparison. If the results are inconsistent, it is determined that the composition of commercial outlets in the central area of ​​the target city needs to be adjusted.

[0046] Preferably, based on the optimal proportion of each type of commercial outlets obtained by the optimal commercial outlets composition model and the commercial outlets composition data of the target city center, a commercial outlets optimization adjustment model is established; the optimization adjustment results of each type of commercial outlets are automatically solved and outputted through the optimization adjustment model, specifically including:

[0047] Based on the optimal commercial network structure model {C1:C2:…:C n The optimal proportion R of the i-th type of commercial outlets determined by i The land area S of the i-th commercial network in the central area of ​​the target city is obtained 0i , construct a commercial network optimization adjustment model, the commercial network optimization adjustment model is specifically:

[0048]

[0049] Among them, k i is the adjustment coefficient of the i-th type of commercial outlets, satisfying the following constraints:

[0050]

[0051] When k i When it is greater than 1, it is determined that this type of commercial outlets needs to be increased, otherwise it needs to be reduced; C i is the land area adjustment of the i-th type of commercial outlets. i >0, it is judged that the land area of ​​this type of commercial outlets needs to be increased|C i |, otherwise, it is judged that the land area used by such commercial outlets needs to be reduced|C i |;

[0052] Based on the optimization adjustment model and constraints, a workstation equipped with a high-performance graphics card NVIDIA A100 TensorCore GPU is used to automatically solve the optimal solution using a greedy algorithm. According to the calculated adjustment coefficient k of the i-th commercial outlet i Adjustment amount C i As a result, the increase, decrease and adjustment of land area of ​​various types of commercial outlets in the central area of ​​the target city are finally determined.

[0053] Preferably, the optimization adjustment results are projected onto a touch display screen for interactive display based on the DataEase data visualization platform, and a commercial outlet adjustment report for the target city center is issued, specifically including:

[0054] The DataEase data visualization platform is used to output the spatial distribution and attribute information of various commercial outlets in the target city center, as well as the optimization and adjustment results of the commercial outlet composition in multiple formats such as charts, texts, and maps, and project them onto a touch display screen with a resolution of 3840×2160. The operator can browse and query the results before and after the optimization of the commercial outlet composition in the target city center or the specific attribute information of the commercial outlets through various gesture commands such as clicking and grabbing; and output a commercial outlet adjustment report including a commercial outlet distribution map of the target city center, evaluation results of the commercial outlet composition, commercial outlet adjustment plans and adjustment basis, and comparison information of indicators before and after the commercial outlet composition adjustment.

[0055] Beneficial effects:

[0056] (1) The present invention provides a method for evaluating and optimizing the commercial network in the central area of ​​an urban area based on a knowledge graph. By constructing a knowledge graph of the central area of ​​a case city containing three types of entities: people, commercial outlets, and central areas, the system integration and deep correlation analysis of data are realized. The knowledge graph not only effectively integrates multi-source data, but also provides a comprehensive entity relationship view, so that the layout optimization of commercial outlets can be accurately analyzed based on structured data and complex spatial relationships. This method significantly improves the scientific nature of commercial outlet evaluation, provides reliable decision-making support for urban planners, and ensures that the optimization plan meets actual needs and has efficient implementation.

[0057] (2) The present invention provides a method for evaluating and optimizing the commercial network in the central area of ​​an urban area based on a knowledge graph. The random forest algorithm is used to construct a correlation model between crowd density and commercial outlets, and the commercial outlets configuration is optimized by a genetic algorithm. This method effectively captures the complex relationship between crowd density and commercial outlets by using the comprehensive data of the knowledge graph and the precise prediction of the random forest algorithm, and intelligently searches for the optimal configuration in a wide solution space through a genetic algorithm, significantly improving the accuracy of commercial outlet evaluation and optimization efficiency. In addition, the dynamic adjustment capability of this method ensures that the commercial outlets configuration can adapt to market and environmental changes, thereby providing an efficient, scientific and flexible commercial outlets optimization solution.

[0058] (3) The present invention provides a method for evaluating and optimizing the commercial network in the central area of ​​an urban area based on a knowledge graph. Based on the commercial network composition data of the central area of ​​the target city and in comparison with the optimal commercial network composition model, it accurately determines whether the existing configuration needs to be adjusted. If adjustment is required, the optimization model will automatically solve and generate the optimization adjustment results for various commercial outlets. This method not only improves the accuracy of optimization judgment and reduces manual intervention, but also realizes the dynamic evaluation and adjustment of commercial outlets, and can adapt to changes in the market and environment at any time. At the same time, it is forward-looking, ensuring that the configuration of commercial outlets always meets future needs, and improving the efficient use of commercial resources and the sustainable vitality of the urban economy.

[0059] (4) The present invention provides a method for evaluating and optimizing the commercial network in the central area of ​​an urban area based on a knowledge graph. Through the DataEase data visualization platform, the optimization and adjustment results are projected onto a high-resolution touch display screen for interactive display, and a detailed commercial network adjustment report is generated. The operator can conveniently browse and query the data and specific attribute information before and after the optimization of the commercial network through gestures such as clicking and grabbing. This visualization display and report generation not only improves the intuitiveness and interactivity of the data, but also provides a comprehensive and systematic basis for decision-making, ensuring the transparency and effectiveness of the adjustment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a method flow chart of an embodiment of the present invention.

[0061] Figure 2 This is a schematic diagram of the distribution of commercial outlets in the central area before adjustment in an embodiment of the present invention.

[0062] Figure 3 Schematic diagram of problem network point identification of commercial network points in the central area according to an embodiment of the present invention.

[0063] Figure 4 This is a schematic diagram of the adjusted distribution of commercial outlets in the central area of ​​an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of the present invention.

[0065] like Figure 1 As shown, the embodiment of the present invention discloses a method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph, including:

[0066] The urban population data, commercial network data, building vector data and central area boundary data of urban central areas across the country are obtained and input into the geographic information platform for format unification to form a case city central area database.

[0067] Based on the database, three types of entities, namely, crowd, commercial outlets and central area, are identified and extracted and numbered. The location and quantity attributes of crowd entities, the location, type and area attributes of commercial outlet entities, and the location and area attributes of central area entities are calculated respectively. The association between the three types of entities is determined based on spatial location. The above results are input into the NEO4J graph database platform to construct a knowledge graph of the central area of ​​the case city.

[0068] Based on the knowledge graph, the entity data of each central area and the associated crowd and commercial outlets are extracted, and the data are aggregated and calculated into a human-industry association data set containing crowd intensity data and commercial outlet composition data; the random forest algorithm is used to train the association model about crowd intensity and commercial outlet composition based on the data set, and the optimal association model is determined by the grid search method; based on the commercial outlet composition data and the obtained optimal association model, the genetic algorithm is used to solve and obtain the optimal commercial outlet composition pattern.

[0069] Obtain a target city central area commercial outlet composition data set containing the proportion and area information of each type of commercial outlets, obtain the actual commercial outlet composition pattern of the central area, and compare it with the determined optimal commercial outlet composition pattern. If the results are inconsistent, it is determined that the commercial outlet composition of the target city central area needs to be adjusted.

[0070] Based on the optimal proportion of each type of commercial outlets obtained from the optimal commercial outlets composition model and the commercial outlets composition data in the central area of ​​the target city, a commercial outlets optimization adjustment model is established; the optimization adjustment results of each type of commercial outlets are automatically solved and output through the optimization adjustment model.

[0071] Based on the DataEase data visualization platform, the optimization and adjustment results are projected onto a large touch screen for interactive display, and a commercial outlet adjustment report for the target city center is issued.

[0072] Example

[0073] The following will take the central area of ​​Nanjing as an example to explain the technical solution of the present invention in detail.

[0074] Using the Intel Core i9-10980XE high-performance processor, the obtained crowd point data, commercial network POI data, building vector data and central area boundary data of urban central areas across the country were deduplicated, cleaned and normalized, and then merged and input into the ArcGIS10.8 geographic information platform, unified the data coordinates and data format types, formed a case city central area database, and stored the results in the Samsung PM1733 NVMe SSD storage;

[0075] The crowd point data refers to the population point vector data of the central areas of cities across the country from 9:00 to 22:00 for two consecutive weeks obtained at intervals of 2 hours through the Baidu Huiyan open data platform, specifically including the number of people and longitude and latitude information of the points; the commercial outlet POI data refers to the commercial outlet POI data of the central areas of cities across the country obtained based on the official platform of Dianping.com, specifically including the name, category, number of floors of the building where the commercial outlets are located, and longitude and latitude information; the building vector data refers to the building vector data obtained through the OpenStreetMap open data platform, specifically including the building area, number of floors, and longitude and latitude information; the central area boundary data refers to the current drawings containing the central area boundary information obtained from the official website of the city government, planning bureau or natural resources bureau, and the central area boundary data containing the area and longitude and latitude information is obtained by drawing the spatial correction and drawing tools in the ArcGIS10.8 geographic information platform.

[0076] Based on the crowd point data, commercial network POI data and central area boundary data in the central area of ​​the case city, three types of entities, namely crowd, commercial network and central area, are identified and extracted, and numbered respectively;

[0077] The location attribute and quantity attribute of the crowd entity data are determined by extracting the latitude and longitude information and quantity information of the calculated crowd points in the ArcGIS 10.8 geographic information platform; the location attribute of the commercial outlet entity is determined by extracting the latitude and longitude information of the commercial outlet POI data; the type information of the commercial outlet is extracted and the commercial service facility land classification standard in the "Urban Land Classification and Planning and Construction Land Standard" is referred to, and the commercial outlet data is reclassified, and the type attribute of the commercial outlet entity is determined according to the reclassification result, and the reclassification result specifically includes seven categories: retail business, wholesale market, catering service, hotel service, entertainment service, health service and life service; the number of floors, area and longitude and latitude information of the building vector data and the number of floors of the building where the commercial outlet POI data is located are extracted, and the building area of ​​the number of floors of the building intersecting with the commercial outlet in the geographic space is extracted in the ArcGIS 10.8 geographic information platform through the spatial association tool based on the number of building floors, and combined with field survey correction, the area attribute of the commercial outlet entity is determined according to the final result; the area information and longitude and latitude information of the central area boundary data are extracted to determine the area attribute and location attribute of the central area entity;

[0078] Based on the latitude and longitude information of the three types of entities, the crowd entities and commercial outlets entities located in the central area entity in the geographic space are determined by the spatial association tool in the ArcGIS 10.8 geographic information platform, and the association relationship between the crowd entity, the commercial outlet entity and the central area entity is obtained according to the results;

[0079] The numbers of the three types of entities that are successfully associated are used as unique identifiers, and the data structure is sorted out in combination with the location coordinates and the corresponding entity attributes. The processed entities, entity attributes and association relationship data are imported into the Neo4j4.4 graph database platform using Cypher statements. The node types are determined to be crowds, commercial outlets and central areas. Neo4jBrowser and Bloom are used for data visualization to construct a knowledge graph of the case city central area.

[0080] According to the entity association relationship obtained in step 2, the crowd entities and their quantity attributes associated with each central area entity are extracted, and the commercial outlets entities and their type attributes and area attributes associated with each central area entity are extracted; the per capita intensity index I corresponding to each central area entity is calculated by using the multi-core high-threaded processor Intel Xeon Platinum 8280 i Data and the area ratio of various types of commercial outlets ij Data, the area proportion of each type of commercial outlets entity R ij The data is aggregated to form the data of commercial outlets;

[0081] The per capita intensity index I iThe specific calculation formula is:

[0082]

[0083] Among them, I i represents the crowd intensity index of the i-th central area entity; P j A represents the number of people in the jth crowd entity of the central area entity, and n is the total number of crowd entities associated with the central area entity; 中 Indicates the area attribute value of the central area entity; D indicates the total number of days in the time period of the acquired crowd data; H indicates the total number of times in the time period of the acquired crowd data per day;

[0084] The area proportion of each type of commercial outlets R ij The specific calculation formula is:

[0085]

[0086] Among them, R ij S represents the area proportion of the j-th type of commercial outlets in the i-th central area entity, where j is retail business, wholesale market, catering service, hotel, entertainment service, health service, and life service facilities; j-k S represents the area attribute value of the kth commercial outlet entity belonging to the jth type of commercial outlet associated with the central area, l is the total number of commercial outlet entities of this type associated with the central area; m It represents the sum of the area attribute values ​​of all commercial outlets entities associated with the central area;

[0087] The above calculation results are transferred to the Samsung PM1733 NVMe SSD storage and summarized to form a human-industry related data set containing crowd intensity index data and commercial network composition data.

[0088] A random forest association model of crowd intensity and commercial outlets was constructed, the crowd-industry association data set was divided into a training set and a test set in a ratio of 8:2, the training set was put into the random forest model for training based on a workstation equipped with a high-performance graphics card NVIDIAA100 Tensor Core GPU, and the optimal parameters of the model were determined by a grid search method, wherein the parameters specifically included the number of decision trees in the model, the maximum depth of the decision tree, the minimum number of sample splits for each decision tree, and the minimum number of sample leaves for each decision tree; based on the optimal parameters, the test set was put into the trained model for verification, and finally the optimal crowd intensity and commercial outlets association model was obtained;

[0089] The genetic algorithm is used to input the optimal association model obtained above and the commercial outlets composition data of the central area of ​​the case city, and the configuration pattern of the commercial outlets is represented in the form of real number coding, where each individual (commercial outlet composition pattern) is composed of the proportion R of each type of commercial outlets. x Composition; randomly generate multiple individuals to form an initial population, each individual represents a commercial network configuration mode, based on given constraints By repeating the selection, crossover and mutation operations, the population is continuously updated and finally the optimal commercial network structure pattern {C1:C2:…:C n}.

[0090] like Figure 2 , download the planning and design publicity documents of the central area of ​​Nanjing from the official website of Nanjing Planning and Natural Resources Bureau, the publicity documents include project specifications, design drawings and other relevant documents containing economic and technical indicators of the central area of ​​Nanjing; use Python text analysis library to automatically identify and extract the proportion data and land area data of various types of commercial outlets in the central area of ​​Nanjing from the publicity documents, form a commercial outlet composition data set of the central area of ​​Nanjing, and transfer it to Samsung PM1733 NVMe SSD storage; based on the commercial outlet type described in step 1, reclassify the data set so that the commercial outlets in the central area of ​​Nanjing are consistent with the commercial outlet type described in step 1, and according to the reclassified commercial outlet composition data, use a workstation equipped with a high-performance graphics card NVIDIA A100 Tensor Core GPU to calculate the proportion R of the i-th commercial outlet in the central area of ​​Nanjing. 0i and land area S 0i ;

[0091] like Figure 3 , based on the proportion of all types of commercial outlets in the central area of ​​Nanjing 0i , and summarize the actual commercial network structure model {C 01 :C 02 :…:C 0n}, and compare it with the optimal commercial network structure model {C1:C2:…:C n}, and based on the comparison results, it was determined that the composition of commercial outlets in the central area of ​​Nanjing needed to be adjusted.

[0092] Based on the optimal commercial network structure model {C1:C2:…:C n The optimal proportion R of the i-th type of commercial outlets determined by i The land area S of the i-th commercial network in the central area of ​​Nanjing obtained above 0i , construct a commercial network optimization adjustment model, the commercial network optimization adjustment model is specifically:

[0093]

[0094] Among them, k i is the adjustment coefficient of the i-th type of commercial outlets, satisfying the following constraints:

[0095]

[0096] When k i When it is greater than 1, it is determined that this type of commercial outlets needs to be increased, otherwise it needs to be reduced; C i is the land area adjustment of the i-th type of commercial outlets. i >0, it is judged that the land area of ​​this type of commercial outlets needs to be increased|C i |, otherwise, it is judged that the land area used by such commercial outlets needs to be reduced|C i |;

[0097] like Figure 4 Based on the optimization adjustment model and constraints, a workstation equipped with a high-performance graphics card NVIDIA A100 Tensor Core GPU is used to automatically solve the optimal solution using a greedy algorithm. i Adjustment amount C i As a result, the increase, decrease and adjustment of land area of ​​various types of commercial outlets in the central area of ​​Nanjing were finally determined.

[0098] The DataEase data visualization platform is used to output the spatial distribution and attribute information of various commercial outlets in the central area of ​​Nanjing, as well as the optimization and adjustment results of the commercial outlet composition in multiple formats such as charts, texts, and maps, and project them onto a large touch display screen with a resolution of 3840×2160. The operator can browse and query the results before and after the optimization of the commercial outlet composition in the central area of ​​Nanjing or the specific attribute information of the commercial outlets through various gesture commands such as clicking and grabbing; and output a commercial outlet adjustment report including a commercial outlet distribution map of the central area of ​​Nanjing, evaluation results of the commercial outlet composition, commercial outlet adjustment plans and adjustment basis, and comparison information of indicators before and after the commercial outlet composition adjustment.

Claims

1. A method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph, characterized in that: include: Step 1: Data collection and processing of urban center areas and knowledge graph construction Obtain urban population data, commercial network data, building vector data, and central area boundary data for urban central areas across the country, input them into the geographic information platform for format unification, and form a case city central area database; Based on the database, three types of entities, namely, crowd, commercial outlets and central area, are identified and extracted and numbered, and the location and quantity attributes of crowd entities, the location, type and area attributes of commercial outlet entities, and the location and area attributes of central area entities are calculated respectively, and the association relationship between the three types of entities is determined based on spatial location; the above results are input into the NEO4J graph database platform to construct a knowledge graph of the central area of ​​the case city; Step 2: Construction of a correlation model between crowd intensity and commercial outlets Based on the knowledge graph, extract the entity data of each central area and the crowd and commercial outlets associated therewith, and aggregate and calculate the data into a human-industry association data set containing crowd intensity data and commercial outlet composition data; use the random forest algorithm to train the association model about crowd intensity and commercial outlet composition based on the data set, and determine the optimal association model through the grid search method; based on the commercial outlet composition data and the obtained optimal association model, use the genetic algorithm to solve and obtain the optimal commercial outlet composition model; Step 3: Evaluation of the commercial network structure in the city center Obtain a target city central area commercial outlet composition data set containing the proportion and area information of each type of commercial outlets, obtain the actual commercial outlet composition pattern of the central area, and compare it with the determined optimal commercial outlet composition pattern. If the results are inconsistent, it is determined that the commercial outlet composition of the target city central area needs to be adjusted; Step 4: Optimize the composition of commercial outlets in the city center Based on the optimal proportion of each type of commercial outlets obtained from the optimal commercial outlets composition model and the commercial outlets composition data of the target city center, a commercial outlets optimization adjustment model is established; Automatically solve and output the optimization adjustment results of various types of commercial outlets through the optimization adjustment model; Step 5: Interactive display of optimization solutions and output of adjustment reports Based on the DataEase data visualization platform, the optimization and adjustment results are projected onto a large touch screen for interactive display, and a commercial outlet adjustment report for the target city center is issued.

2. According to claim 1, a method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph is characterized in that: In the step 1, the urban population data, commercial network data, building vector data and central area boundary data of the national urban central areas are obtained, and input into the geographic information platform for format unification processing to form a case urban central area database, which specifically includes: Using the Intel Core i9-10980XE high-performance processor, the obtained crowd point data, commercial network POI data, building vector data and central area boundary data of urban central areas across the country were deduplicated, cleaned and normalized, and then merged and input into the ArcGIS10.8 geographic information platform, unified the data coordinates and data format types, formed a case city central area database, and stored the results in the Samsung PM1733 NVMe SSD storage; The crowd point data refers to the population point vector data of the central areas of cities across the country from 9:00 to 22:00 for two consecutive weeks obtained at intervals of 2 hours through the Baidu Huiyan open data platform, specifically including the number of people and longitude and latitude information of the points; the commercial outlet POI data refers to the commercial outlet POI data of the central areas of cities across the country obtained based on the official platform of Dianping.com, specifically including the name, category, number of floors of the building where the commercial outlet is located, and longitude and latitude information; The building vector data refers to the building vector data obtained through the OpenStreetMap open data platform, specifically including building area, number of floors and longitude and latitude information; the central area boundary data refers to the current status drawings containing central area boundary information obtained from the official website of the city government, planning bureau or natural resources bureau, and the central area boundary data containing area and longitude and latitude information is obtained by drawing through spatial correction and drawing tools in the ArcGIS10.8 geographic information platform.

3. According to claim 2, a method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph is characterized in that: In the step 1, based on the database, three types of entities, namely, crowd, commercial outlets and central area, are identified and extracted and numbered, and the location and quantity attributes of crowd entities, the location, type and area attributes of commercial outlet entities, and the location and area attributes of central area entities are calculated respectively, and the association relationship between the three types of entities is determined based on spatial location; the above results are input into the NEO4J graph database platform to construct a knowledge graph of the central area of ​​the case city, specifically including: Based on the crowd point data, commercial network POI data and central area boundary data in the central area of ​​the case city, three types of entities, namely crowd, commercial network and central area, are identified and extracted, and numbered respectively; The location attribute and quantity attribute of the crowd entity data are determined by extracting the latitude and longitude information and quantity information of the calculated crowd points in the ArcGIS 10.8 geographic information platform; the location attribute of the commercial outlet entity is determined by extracting the latitude and longitude information of the commercial outlet POI data; the type information of the commercial outlet is extracted and the commercial service facility land classification standard in the "Urban Land Classification and Planning and Construction Land Standard" is referred to, and the commercial outlet data is reclassified, and the type attribute of the commercial outlet entity is determined according to the reclassification result, and the reclassification result specifically includes seven categories: retail business, wholesale market, catering service, hotel service, entertainment service, health service and life service; the number of floors, area and longitude and latitude information of the building vector data and the number of floors of the building where the commercial outlet POI data is located are extracted, and the building area of ​​the number of floors of the building intersecting with the commercial outlet in the geographic space is extracted in the ArcGIS 10.8 geographic information platform through the spatial association tool based on the number of building floors, and combined with field survey correction, the area attribute of the commercial outlet entity is determined according to the final result; the area information and longitude and latitude information of the central area boundary data are extracted to determine the area attribute and location attribute of the central area entity; Based on the latitude and longitude information of the three types of entities, the crowd entities and commercial outlets entities located in the central area entity in the geographic space are determined by the spatial association tool in the ArcGIS 10.8 geographic information platform, and the association relationship between the crowd entity, the commercial outlet entity and the central area entity is obtained according to the results; The numbers of the three types of entities that are successfully associated are used as unique identifiers, and the data structure is sorted out in combination with the location coordinates and the corresponding entity attributes. The processed entities, entity attributes and association relationship data are imported into the Neo4j4.4 graph database platform using Cypher statements. The node types are determined to be crowds, commercial outlets and central areas. Neo4jBrowser and Bloom are used for data visualization to construct a knowledge graph of the case city central area.

4. According to claim 3, a method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph is characterized in that: In the step 2, based on the knowledge graph, each central area entity and the associated crowd and commercial outlet entity data are extracted, and the data are aggregated and calculated into a human-industry associated data set containing crowd intensity data and commercial outlet composition data, specifically including: According to the entity association relationship obtained in step 2, the crowd entities and their quantity attributes associated with each central area entity are extracted, and the commercial outlets entities and their type attributes and area attributes associated with each central area entity are extracted; the per capita intensity index I corresponding to each central area entity is calculated by using the multi-core high-threaded processor Intel Xeon Platinum 8280 i Data and the area ratio of various types of commercial outlets ij Data, the area proportion of each type of commercial outlets entity R ij The data is aggregated to form the data of commercial outlets; The per capita intensity index I i The specific calculation formula is: Among them, I i represents the crowd intensity index of the i-th central area entity; P j A represents the number of people in the jth crowd entity of the central area entity, and n is the total number of crowd entities associated with the central area entity; 中 Indicates the area attribute value of the central area entity; D indicates the total number of days in the time period of the acquired crowd data; H indicates the total number of times in the time period of the acquired crowd data per day; The area proportion of each type of commercial outlets R ij The specific calculation formula is: Among them, R ij S represents the area proportion of the j-th type of commercial outlets in the i-th central area entity, where j is retail business, wholesale market, catering service, hotel, entertainment service, health service, and life service facilities; j-k S represents the area attribute value of the kth commercial outlet entity belonging to the jth type of commercial outlet associated with the central area, l is the total number of commercial outlet entities of this type associated with the central area; m It represents the sum of the area attribute values ​​of all commercial outlets entities associated with the central area; The above calculation results are transferred to the Samsung PM1733 NVMe SSD storage and summarized to form a human-industry related data set containing crowd intensity index data and commercial network composition data.

5. According to claim 4, a method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph is characterized in that: In the step 2, a random forest algorithm is used to train a correlation model between crowd intensity and commercial network composition based on the data set, and an optimal correlation model is determined by a grid search method; based on the commercial network composition data and the obtained optimal correlation model, a genetic algorithm is used to solve and obtain the optimal commercial network composition model, which specifically includes: A random forest association model of crowd intensity and commercial outlets was constructed, the crowd-industry association data set was divided into a training set and a test set in a ratio of 8:2, the training set was put into the random forest model for training based on a workstation equipped with a high-performance graphics card NVIDIAA100 Tensor Core GPU, and the optimal parameters of the model were determined by a grid search method, wherein the parameters specifically included the number of decision trees in the model, the maximum depth of the decision tree, the minimum number of sample splits for each decision tree, and the minimum number of sample leaves for each decision tree; based on the optimal parameters, the test set was put into the trained model for verification, and finally the optimal crowd intensity and commercial outlets association model was obtained; The genetic algorithm is used to input the optimal association model obtained above and the data of commercial outlets in the central area of ​​the case city, and the configuration mode of commercial outlets is represented in the form of real number coding, where each individual is represented by the proportion R of each type of commercial outlets. x Composition; randomly generate multiple individuals to form an initial population, each individual represents a commercial network configuration mode, based on given constraints By repeating the selection, crossover and mutation operations, the population is continuously updated and finally the optimal commercial network structure pattern {C1:C2:…:C n }.

6. The method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph according to claim 5 is characterized in that: The step 3 includes obtaining a target city center commercial outlet composition data set including the proportion and area information of each type of commercial outlets, obtaining an actual commercial outlet composition pattern in the center, and comparing it with the determined optimal commercial outlet composition pattern. If the results are inconsistent, it is determined that the commercial outlet composition of the target city center needs to be adjusted, specifically including: Download the planning and design publicity documents of the central area of ​​the target city from the official website of the target city government, planning bureau or natural resources bureau, the publicity documents including the project description, design drawings and other relevant documents containing the economic and technical indicator information of the planning scheme of the central area of ​​the target city; use the Python text analysis library to automatically identify and extract the proportion data and land area data of each type of commercial outlets in the planning scheme from the publicity documents to form a commercial outlet composition data set of the central area of ​​the target city, and transfer it to the Samsung PM1733 NVMe SSD storage; based on the commercial outlet type described in step one, reclassify the data set so that the commercial outlets in the target city are consistent with the commercial outlet type described in step one, and calculate the proportion R of the i-th type of commercial outlets in the central area of ​​the target city based on the reclassified commercial outlet composition data using a workstation equipped with a high-performance graphics card NVIDIA A100 Tensor CoreGPU 0i and land area S 0i ; Based on the obtained proportion of all types of commercial outlets in the central area of ​​the target city, R 0i , and summarize the actual commercial network structure model {C 01 :C 02 :…:C 0n }, and compare it with the optimal commercial network structure model {C1:C2:…:C n } for comparison. If the results are inconsistent, it is determined that the composition of commercial outlets in the central area of ​​the target city needs to be adjusted.

7. The method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph according to claim 6, characterized in that: In the step 4, a commercial outlet optimization adjustment model is established based on the optimal proportion of each type of commercial outlets obtained from the optimal commercial outlet composition model and the commercial outlet composition data of the target city center; The optimization adjustment model is used to automatically solve and output the optimization adjustment results of various types of commercial outlets, including: Based on the optimal commercial network structure model {C1:C2:…:C n The optimal proportion R of the i-th type of commercial outlets determined by i The land area S of the i-th commercial network in the central area of ​​the target city is obtained 0i , construct a commercial network optimization adjustment model, the commercial network optimization adjustment model is specifically: Among them, k i is the adjustment coefficient of the i-th type of commercial outlets, satisfying the following constraints: When k i When it is greater than 1, it is determined that this type of commercial outlets needs to be increased, otherwise it needs to be reduced; C i is the land area adjustment of the i-th type of commercial outlets. i >0, it is judged that the land area of ​​this type of commercial outlets needs to be increased|C i |, otherwise it is judged that the land area used by such commercial outlets needs to be reduced|C i |; Based on the optimization adjustment model and constraints, a workstation equipped with a high-performance graphics card NVIDIA A100 Tensor Core GPU is used to automatically solve the optimal solution using a greedy algorithm. According to the calculated adjustment coefficient k of the i-th commercial outlet i Adjustment amount C i As a result, the increase, decrease and adjustment of land area of ​​various types of commercial outlets in the central area of ​​the target city are finally determined.

8. The method for evaluating and optimizing commercial outlets in a city center based on a knowledge graph according to claim 7, characterized in that: In step 5, the optimization adjustment results are projected onto a touch display screen for interactive display based on the DataEase data visualization platform, and a commercial outlet adjustment report for the central area of ​​the target city is issued, specifically including: The DataEase data visualization platform is used to output the spatial distribution and attribute information of various commercial outlets in the target city center, as well as the optimization and adjustment results of the commercial outlet composition in multiple formats such as charts, texts, and maps, and project them onto a large touch display screen with a resolution of 3840×2160. The operator can browse and query the results before and after the optimization of the commercial outlet composition in the target city center or the specific attribute information of the commercial outlets by clicking and grabbing these various gesture commands; and output a commercial outlet adjustment report including a commercial outlet distribution map of the target city center, commercial outlet composition evaluation results, commercial outlet adjustment plans and adjustment basis, and comparison information of indicators before and after the commercial outlet composition adjustment.

Images