High-speed rail station area dominant function identification and comprehensive development level evaluation method and system

Abstract

The invention discloses a high-speed rail station dominant function identification and comprehensive development level evaluation method and system, and the method comprises the steps: carrying out the multi-distance spatial clustering analysis of POI data around a high-speed rail station, determining an evaluation range, selecting feature parameters based on the spatial features of points, surfaces and bodies in the evaluation range, land utilization conditions and different types of POI data, and carrying out the recognition of the dominant function of the high-speed rail station; and carrying out station dominant function identification by utilizing a decision tree and clustering analysis, and selecting evaluation indexes to construct a comprehensive development level evaluation system so as to realize comprehensive function development level evaluation of the high-speed rail station. According to the method, different station area ranges caused by difference of functional development levels of stations of different grades are effectively defined through analysis of the POI gathering condition around the high-speed rail station; meanwhile, the accuracy and scientificity of classification are improved through high-speed rail station area dominant function identification and division under multiple methods, and a new quantification method is provided for high-speed rail station area function evaluation based on comprehensive function level index system construction considering multiple functions.

Description

Technical Field

[0001] The present invention relates to the technical field of comprehensive measurement and leading function analysis of high-speed rail network construction and station area development, and in particular to a method and system for identifying the leading functions of a high-speed rail station area and evaluating the comprehensive development level. Background Art

[0002] The construction of high-speed rail stations not only promotes inter-city transportation, but also promotes the construction of infrastructure for intra-city transportation connections, promotes the formation of good transportation facilities in the station area, and continuously enriches its status as a "node" of the urban and regional transportation network. At the same time, high-speed rail accelerates the rapid gathering and distribution of people and logistics, and a large number of various elements gather in the high-speed rail station area, which changes the land use mode and land development intensity around the station area, and continuously enriches the functional characteristics of the high-speed rail station area as an important "place" in the city. Under the comprehensive effects of urban development strategies, transportation connections, and land use policies, the functional development and spatial organization of high-speed rail station areas are no longer just transportation hubs in the traditional sense, but have evolved from a single transportation hub function to a comprehensive transportation body that undertakes multiple functions such as business, retail, and residential functions, becoming an important urban node with multiple functions and services.

[0003] However, the regions and cities on which the construction and development of different high-speed rail stations rely and their own advantages and disadvantages are different. There are obvious differences in the actual scope of high-speed rail stations, and the scale and functional development gaps of different high-speed rail stations are relatively large. While the construction of the high-speed rail network has brought new development opportunities to a large number of cities, some small and medium-sized cities are facing the problem of marginalization, population loss, industry and economic recession. These cities have a small overall passenger flow demand and insufficient urban development level. High-speed rail often only produces a channel effect, and the scale of high-speed rail stations is small and the function is single. In addition, the site selection of new stations is often far away from the city center. Many station areas lack efficient transportation connections, making it difficult to achieve the agglomeration of resource elements and the development of industries, and unable to generate linkage with the expansion of urban space and the evolution of the pattern. Some cities are even expanding blindly, building high-speed rail new cities based on station areas, but developing into high-speed rail "ghost cities", wasting land resources and having a low level of comprehensive functional development.

[0004] Therefore, with the transformation of station functions from a single transportation hub to a multifunctional complex, as well as the emergence of problems such as the high positioning of station development functions, single development model, excessive initial scale, and imperfect comprehensive supporting facilities, how to effectively evaluate the level of comprehensive functional development of high-speed railway station areas and reasonably identify the dominant functions of high-speed railway station areas has become a research issue worthy of attention. The existing technology generally lacks a comprehensive functional level evaluation index system that reflects the multiple functions of high-speed railway station areas in multiple dimensions, as well as the identification and classification of dominant functional types under quantitative indicators, and cannot scientifically and effectively measure the comprehensive development of high-speed railway station areas. Summary of the invention

[0005] The first purpose of the present invention is to overcome the problems existing in the above-mentioned prior art and provide a method for identifying the dominant functions and evaluating the comprehensive development level of high-speed railway station areas.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] A method for identifying the dominant functions and evaluating the comprehensive functional development level of a high-speed railway station area, comprising:

[0008] Obtain POI data around the high-speed rail station, perform multi-distance spatial clustering analysis on the POI data, and determine the optimal clustering range as the evaluation range;

[0009] A decision tree was established with the average building height, building land area ratio, transportation land area ratio, and transportation service POI ratio within the evaluation range of each high-speed railway station area as characteristic nodes, and the high-speed railway station area was divided into transportation-dominated and non-transportation-dominated categories. For high-speed railway station areas dominated by non-transportation functions, the proportion of residential POIs, the proportion of business and R&D POIs, POI diversity index, POI density, land use diversity index, and average building height were used as analysis parameters, and cluster analysis was used to divide them into residential-dominated, business and R&D-dominated, and comprehensive urban function-dominated categories.

[0010] The proportion of transportation service POIs, the proportion of residential POIs, the proportion of business and research and development POIs, the POI diversity index, POI density, the proportion of building land area, the proportion of transportation land area, the land use diversity index and the average building height within the assessment scope of each high-speed railway station area are used as evaluation indicators. The evaluation indicators are quantified and the weighted values ​​of the indicator quantification values ​​are calculated by the weighted method, which are used for the evaluation of the comprehensive functional development level of the high-speed railway station area.

[0011] As a preferred implementation, the decision tree uses the average building height as the root node, and layers the nodes in the order of average building height, proportion of construction land area, proportion of transportation land area, and proportion of transportation service POIs.

[0012] As a preferred implementation, for the decision tree, the feature values ​​of all feature nodes are divided into three parts: high, medium and low using trisection points, and classification is performed based on the high, medium and low values ​​of the feature nodes.

[0013] Furthermore, the decision tree branches are as follows: in the first-level branch, the station area with a high average building height characteristic value is divided into a high-speed railway station with a non-transportation function dominant type, and the station areas with medium and low characteristic values ​​are judged for the next node;

[0014] In the second-level branch, the station area with a high characteristic value of the proportion of building land area is determined as a non-transportation function-dominated type, the station area with a low characteristic value is determined as a transportation function-dominated type, and the station area with a medium characteristic value is determined as the next node;

[0015] At the third level, the station area with a low characteristic value of the proportion of transportation land area is determined as a non-transportation function-dominated type; the station area with a high characteristic value is determined as a transportation function-dominated type, and the station area with a medium characteristic value participates in the determination of the next node;

[0016] For the fourth-level branch, stations with high characteristic values ​​for the proportion of transportation service POIs are judged as transportation-dominated, while stations with medium or low characteristic values ​​are judged as non-transportation-dominated.

[0017] As a preferred implementation, K-means clustering is used to perform functional division of high-speed railway station areas dominated by non-transportation functions.

[0018] As a preferred implementation, the quantitative values ​​of the indicators are weighted after being standardized.

[0019] As a preferred implementation, the weights of the evaluation indicators are determined based on factor analysis.

[0020] The second object of the present invention is to provide a system for identifying the dominant functions of high-speed railway stations and assessing the level of comprehensive functional development, comprising:

[0021] Data acquisition module, which obtains POI data, building elevation data and land use data around high-speed rail stations;

[0022] The high-speed railway station area evaluation range calculation module performs multi-distance spatial clustering analysis on the POI data to determine the optimal clustering range as the evaluation range;

[0023] The module for identifying the dominant functions of high-speed railway stations uses the average building height, building land area ratio, transportation land area ratio, and transportation service POI ratio within the evaluation range of each high-speed railway station as characteristic nodes to establish a decision tree, and divides the high-speed railway station into transportation-dominated and non-transportation-dominated categories. For high-speed railway stations dominated by non-transportation functions, the module uses the ratio of residential POIs, the ratio of business and R&D POIs, POI diversity index, POI density, land use diversity index, and average building height as analysis parameters, and uses cluster analysis to divide them into residential-dominated, business and R&D-dominated, and comprehensive urban function-dominated categories.

[0024] The module for evaluating the comprehensive functional development level of high-speed railway station areas takes the proportion of transportation service POIs, the proportion of residential POIs, the proportion of business and research and development POIs, the POI diversity index, POI density, the proportion of building land area, the proportion of transportation land area, the land use diversity index, and the average building height within the evaluation scope of each high-speed railway station area as evaluation indicators, quantifies the evaluation indicators, and calculates the weighted values ​​of the indicator quantification values ​​through the weighted method, which is used for the evaluation of the comprehensive functional development level of high-speed railway station areas.

[0025] A third object of the present invention is to provide a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0026] A fourth object of the present invention is to provide a computer-readable storage medium having a computer program / instruction stored thereon, which implements the steps of the above method when the computer program / instruction is executed by a processor.

[0027] The present invention has the following beneficial effects:

[0028] (1) The present invention effectively defines the different station areas of different grades of stations due to differences in functional development levels by analyzing the POI agglomeration around high-speed railway stations. The multi-distance spatial clustering analysis method is used to obtain the optimal agglomeration range of the high-speed railway station as the evaluation range of the high-speed railway station, making the evaluation range a dynamic parameter. The average value or relative value is subsequently used as the functional identification / development level evaluation index of the station area, so that different station areas can be compared under the same indicator system.

[0029] (2) Starting from the perspective of multiple functions of station area development, the present invention constructs indicator characteristics that can reflect multiple functions including transportation service functions, residential life functions, business research and development functions, and comprehensive services. From the multi-dimensional spatial perspective of point data (POI data), surface data (land use type data), and three-dimensional data (building height data), a comprehensive evaluation index system for the comprehensive functional level of high-speed railway station areas is formed, providing a new quantitative method for the functional evaluation of high-speed railway station areas.

[0030] (3) The present invention identifies and divides the dominant functions of high-speed railway station areas through rule classification and cluster analysis based on decision trees. First, the dominant function types of high-speed railway station areas are divided into transportation function-dominated and non-transportation function-dominated categories using decision trees. Indicators closely related to transportation functions are selected for rule formulation. The order in which each indicator enters the classification rule is arranged. Starting from the root node, the best feature attributes are selected for classification. For areas in the non-transportation function-dominated category, cluster analysis is further used to divide the non-transportation function-dominated category into different categories. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The technical solution and technical effects of the present invention will become clearer and easier to understand through the following description of a preferred embodiment of the present invention in conjunction with the accompanying drawings.

[0032] Figure 1 The present invention is a flowchart of the method described in the embodiment of the present invention.

[0033] Figure 2 Schematic diagram of the high-speed rail network and high-speed rail station layout in an embodiment of the present invention.

[0034] Figure 3 This is a method for classifying the dominant functions of high-speed railway station areas in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0036] Example 1

[0037] In the embodiments, the high-speed railway station in the Yangtze River Delta region is taken as an example to further illustrate the technical solution of the present invention.

[0038] The method for identifying the dominant functions of high-speed railway station areas and evaluating the comprehensive functional development level mainly includes the following steps:

[0039] Step 1: Collection and preprocessing of high-speed rail station and city-related data, including collection and organization of various open source data, socio-economic data, etc., and data format conversion and unified data expression.

[0040] The various types of data include land use data, POI data and building elevation data.

[0041] Step 2: Based on the clustering of POIs around high-speed rail stations, the spatial scope of the station area is defined based on Ripley's K function.

[0042] The POIs mentioned above refer to various points of interest marked on the map, such as restaurants, hotels, shopping centers, scenic spots, etc. By analyzing the distribution and density of POIs, we can understand the activity center and demand distribution of a region. Although different high-speed rail stations have different influence radii, the station area of ​​high-speed rail stations under similar conditions can be inferred by analyzing the clustering of POIs.

[0043] The Ripley's K function is a statistical method for spatial point pattern analysis, which can effectively quantify the degree of aggregation or dispersion of point sets in space, and the range of aggregation or dispersion. It is usually used to describe the point density of spatial point sets in different distance ranges, and is defined as the difference between the average number of point pairs observed within the distance r range and the expected average number of point pairs of random distribution. The calculation formula is:

[0044]

[0045] in, is the number of observation points, is the point density per unit area, is the weight function, indicating that The contribution of points within the range to K(r) can usually be chosen as:

[0046]

[0047] in this case, It is an indicator function, which means that if the distance between two points is less than or equal to r, the contribution is 1, otherwise it is 0.

[0048] , indicating that the points are clustered within the distance r, that is, the number of points observed within this distance range is greater than that of random distribution.

[0049] , indicating that the point set is dispersed within the distance r, that is, the number of points observed within this distance range is less than that of random distribution.

[0050] , indicating that the point set has no significant difference from the random distribution within the distance r.

[0051] The optimal clustering range obtained based on Ripley's K function (ie: Maximum value) as the assessment range for subsequent functional identification and developmental level assessment.

[0052] Step 3: Combine the decision tree-based rule classification method and the machine learning K-means clustering method to identify and divide the dominant functional types of the high-speed rail station area ( Figure 3 ).

[0053] Drawing on the classification idea of ​​the decision tree algorithm, we select indicators closely related to traffic functions for rule formulation, arrange the order in which each indicator enters the classification rule, and layer the nodes in the order of average building height, non-construction land area ratio, traffic land area ratio, and traffic service POI ratio. Starting from the root node, we select the best feature attribute for classification. To improve the accuracy of the classification results, we select three equal points to divide all feature values ​​into three levels: high, medium, and low.

[0054] ① In the first-level branch, the station area with a high average building height characteristic value is judged to have a good station area development status and is classified as a high-speed railway station dominated by non-transportation functions to participate in the subsequent unsupervised learning algorithm classification; the station area with medium and low characteristic values ​​is judged as the next node.

[0055] ② In the second-level branch, the station area with a high proportion of building land area is classified as a non-transportation function-dominated category; the station area with a low characteristic value is judged to have fewer buildings and poor construction conditions, and is classified as a transportation function-dominated category; the station area with a medium characteristic value is judged as the next node.

[0056] ③ The third-level branch: Station areas with a low proportion of transportation land area are judged to have well-built buildings and facilities of a certain scale because they have medium and low building heights and medium proportion of building land area. They are classified into the non-transportation function-dominated category and participate in the subsequent unsupervised learning algorithm classification; station areas with high characteristic values ​​are classified into the transportation function-dominated category, and station areas with medium characteristic values ​​participate in the judgment of the next node.

[0057] ④ The fourth-level branch, through the verification of the proportion of traffic service POI features, for the station area with a high degree of this feature value, it is considered that it has a certain degree of buildings and facilities, a certain degree of traffic land and a high traffic service POI, so it is determined to be a traffic function-dominated class, and the remaining station areas are classified into non-traffic function-dominated classes, and other functions are explored through subsequent machine learning. The rule classification method of the decision tree is based on the classification idea of ​​the decision tree algorithm. The dominant function types of high-speed rail station areas are divided into traffic function-dominated classes and non-traffic function-dominated classes. Indicators closely related to traffic functions are selected for rule formulation, and the order of each indicator entering the classification rule is arranged. The nodes are layered in the order of average building height, non-construction land area ratio, traffic land area ratio, and traffic service POI ratio. Starting from the root node, the best feature attribute is selected for classification, and all feature values ​​are divided into three parts: high, medium and low using three equal points.

[0058] For the non-transportation-dominated station areas identified by decision trees, the proportion of residential POIs, the proportion of business and R&D POIs, POI diversity index, POI density, land use diversity index, and average building height are used as analysis parameters, and the K-means clustering method in the unsupervised learning algorithm is used for further classification, which mainly includes the following steps:

[0059] First, determine the optimal number of clusters. Assume there are n data points , ,…, , each data point It is a d-dimensional vector that represents the characteristics of the data. The K-means algorithm divides these data points into K clusters so that the distance between data points within a cluster is as small as possible, while the distance between data points in different clusters is as large as possible.

[0060] Then, an iterative assignment is performed. After determining the optimal number of clusters, the K-means algorithm is executed. Each data point is assigned to one of the three clusters. The assignment is based on the proximity of the data point to the cluster center in the feature space. The algorithm iteratively updates the cluster centers and reassigns data points until it converges, resulting in a stable and deterministic segmentation of the dataset.

[0061] For each data point , calculate its relationship with each cluster center The distance between them is calculated and assigned to the cluster with the closest cluster center. For each cluster, the mean of all its data points is calculated and the mean is used as the new cluster center. Repeat the steps until the cluster center no longer changes or the predetermined number of iterations is reached. The algorithm can be expressed mathematically as minimizing the objective function:

[0062]

[0063] In the formula, is the objective function, that is, the loss function that needs to be minimized. is the total number of data points. is the first data points. It is The centers of the clusters, Represents data points To cluster center The square of the Euclidean distance.

[0064] Finally, the clustering results are interpreted to identify the dominant functional type of the station area. Through training methods such as parameter adjustment, feature dimension adjustment, and initial center adjustment, the final cluster center represents the average value of each cluster feature, which is analyzed to interpret and label each cluster according to predefined categories. After standardization, the value of the cluster center represents the relative position of each cluster on each feature. The larger the value of the cluster center, the higher the value of the cluster on this feature. Based on this, the clustering results are specifically interpreted to determine the dominant functional type of the high-speed rail station area. Finally, four types of high-speed rail station areas with dominant functions are formed, namely, transportation service function-dominated, residential life function-dominated, business research and development function-dominated, and comprehensive service function-dominated.

[0065] Among the high-speed rail stations in the Yangtze River Delta, the number of stations dominated by transportation service functions is the largest, followed by those dominated by residential life functions, business research and development functions, and comprehensive service functions. This difference reflects, to a certain extent, the development process of high-speed rail stations from single transportation functions to diversified functions and comprehensive functions. Among them, high-speed rail stations dominated by transportation service functions are widely distributed in space, especially in the western and northern regions of the Yangtze River Delta, but their overall comprehensive function level is relatively low. High-speed rail stations dominated by business research and development functions are mainly distributed in the eastern and southern regions of the Yangtze River Delta, concentrated in the Yangtze River Development Belt, the Shanghai-Hangzhou-Jinhua Development Belt, and the Coastal Development Belt. High-speed rail stations dominated by residential life functions are mainly distributed in the core urban circles in the eastern and northern regions of the Yangtze River Delta, especially in Changzhou, Wuxi, Zhenjiang, Ma'anshan, Taizhou and nearby areas. The number of high-speed rail stations with comprehensive service functions is relatively small, mainly distributed along the Shanghai-Nanjing, Shanghai-Hangzhou, and Jinhua-Wenzhou lines in the core cities of the Yangtze River Delta, with the highest comprehensive function level.

[0066] Step 4: Construct a comprehensive functional level indicator system for stations that include multiple functions, use factor analysis to determine the weights, calculate the comprehensive functional level evaluation scores, and conduct a comprehensive assessment of the comprehensive functional level of high-speed rail stations.

[0067] The construction of a comprehensive functional level index system for a station area that includes multiple functions is to comprehensively evaluate the current status of the comprehensive functions of the station area. From the perspective of multiple functions of the station area development, it constructs indicator characteristics that can reflect multiple functions including transportation service functions, residential life functions, business research and development functions, and comprehensive services.

[0068] From the multi-dimensional spatial perspective of point data (POI data), surface data (land use type data), and three-dimensional data (building height data), a high-speed railway station area comprehensive functional level evaluation index system is formed, which is constructed by the proportion of transportation service POIs, the proportion of residential POIs, the proportion of business and research and development POIs, POI diversity index, POI density, the proportion of building land area, the proportion of transportation land area, land use diversity index, and average building height indicators.

[0069] The calculation formula of POI diversity index is:

[0070]

[0071] In the formula, Represents the relative frequency of different types of POIs.

[0072] The calculation formula of land use diversity index is:

[0073]

[0074] In the formula, Represents the proportion (probability) of each land type.

[0075] POI density = number of POIs / regional area; the regional area here refers to the area of ​​the high-speed railway station area delineated in step 2.

[0076] Building land area ratio = building land area / regional area;

[0077] Proportion of traffic land area = traffic land area / regional area;

[0078] The proportion of transportation service POIs = the number of transportation service POIs / the total number of POIs in the area; the area here refers to the high-speed rail station area defined in step 2;

[0079] The proportion of residential POIs = the number of residential POIs / the total number of POIs in the area;

[0080] The proportion of business R&D POIs = the number of business R&D POIs / the total number of POIs in the region;

[0081] Average building height = the average of all building elevations in the area.

[0082] The factor analysis method is used to determine the weight of each evaluation indicator, which mainly includes the following steps:

[0083] First, normalize each indicator and convert the absolute value of the indicator into a relative value. The calculation formula is:

[0084]

[0085] In the formula, is the i-th data in the j-th indicator, is the relative value of the indicator, and are the maximum and minimum values ​​of the jth index respectively;

[0086] Secondly, the number of factors was determined by the eigenvalue method. The eigenvalue is an indicator used to measure the importance of a factor or the degree to which it explains the variance of a variable. Generally, the larger the eigenvalue, the larger the variance of the variable explained by the corresponding factor, and the more important the factor. Finally, three factors with eigenvalues ​​greater than 1 were retained.

[0087] Then, the factor loadings are estimated using the maximum likelihood method, a step that aims to find the relationship between the variables and the latent factors. It can be represented by the following model:

[0088]

[0089] In the formula, is the standardized observed variable, is the factor score, is the uniqueness (the portion of variance that is unique to the variable).

[0090] Finally, after performing Varimax rotation on the factors, the weights are calculated.

[0091]

[0092]

[0093]

[0094] In the formula, is a variable The normalized weight of is the total number of variables, is a variable The average load value, is a variable In the factor The absolute value of the load on is the original load value, is the total number of factors.

[0095] The calculation of the comprehensive function level evaluation score is to comprehensively evaluate the comprehensive function level of the high-speed railway station area. The calculation formula is:

[0096]

[0097] In the formula, E(x) is the comprehensive functional level evaluation score of the high-speed railway station area, m is the number of indicators, , is the relative value of the i-th data of the j-th indicator, a j is the weight of the j-th indicator.

[0098] The final evaluation index weights of this embodiment are shown in Table 1.

[0099] Table 1 Comprehensive development level assessment indicator system and weights

[0100]

[0101] Among them, Shanghai Station ranks first among all high-speed railway stations with a station area comprehensive function level of 0.587. Shanghai West Station, Shanghai South Station, Shanghai Hongqiao Station, Nanxiang North Station in Shanghai, Hangzhou Station, Hangzhou East Station in Hangzhou, Nanjing South Station, Nanjing Station in Nanjing, and Changzhou North Station, Changzhou Station in Changzhou all show a high level of station area comprehensive function and good functional comprehensiveness. In contrast, Lumiao Station, Dingyuan Station, Taihe East Station, Linquan Station, Shexian North Station, Langxi South Station and other high-speed railway stations show a low level of station area comprehensive function.

Claims

1. A method for identifying the dominant functions of high-speed railway station areas and evaluating the level of comprehensive functional development, characterized in that: include: Obtain POI data around the high-speed rail station, perform multi-distance spatial clustering analysis on the POI data, and determine the optimal clustering range as the evaluation range; A decision tree was established with the average building height, building land area ratio, transportation land area ratio, and transportation service POI ratio within the evaluation range of each high-speed railway station area as characteristic nodes, and the high-speed railway station area was divided into transportation-dominated and non-transportation-dominated categories. For high-speed railway station areas dominated by non-transportation functions, the proportion of residential POIs, the proportion of business and R&D POIs, POI diversity index, POI density, land use diversity index, and average building height were used as analysis parameters, and cluster analysis was used to divide them into residential-dominated, business and R&D-dominated, and comprehensive urban function-dominated categories. The proportion of transportation service POIs, the proportion of residential POIs, the proportion of business and research and development POIs, the POI diversity index, POI density, the proportion of building land area, the proportion of transportation land area, the land use diversity index and the average building height within the assessment scope of each high-speed railway station area are used as evaluation indicators. The evaluation indicators are quantified and the weighted values ​​of the indicator quantification values ​​are calculated by the weighted method, which are used for the evaluation of the comprehensive functional development level of the high-speed railway station area.

2. The method according to claim 1, characterized in that The decision tree takes the average building height as the root node, and layers the nodes in the order of average building height, proportion of construction land area, proportion of transportation land area, and proportion of transportation service POIs.

3. The method according to claim 1 or 2, characterized in that: For the decision tree, the feature values ​​of all feature nodes are divided into three parts: high, medium and low using the trisection points, and classification is performed based on the high, medium and low values ​​of the feature nodes.

4. The method according to claim 3, characterized in that The decision tree branches are as follows: In the first-level branch, the station areas with high average building height characteristic values ​​are classified as non-transportation-dominated high-speed railway stations, and the stations with medium and low characteristic values ​​are judged as the next node; In the second-level branch, the station area with a high characteristic value of the proportion of building land area is determined as a non-transportation function-dominated type, the station area with a low characteristic value is determined as a transportation function-dominated type, and the station area with a medium characteristic value is determined as the next node; The third-level branch, the station area with a low characteristic value of the proportion of transportation land area is determined as a non-transportation function-dominated type; Station areas with high eigenvalues ​​are determined as traffic function-dominant types, and station areas with medium eigenvalues ​​participate in the determination of the next node; For the fourth-level branch, stations with high characteristic values ​​for the proportion of transportation service POIs are judged as transportation-dominated, while stations with medium or low characteristic values ​​are judged as non-transportation-dominated.

5. The method according to claim 1, characterized in that K-means clustering is used to divide the functions of high-speed railway station areas dominated by non-transportation functions.

6. The method according to claim 1, characterized in that The quantitative values ​​of the indicators are weighted after being standardized.

7. The method according to claim 1, characterized in that The weights of the evaluation indicators are determined based on factor analysis.

8. A system for identifying the dominant functions of high-speed railway stations and assessing the level of comprehensive functional development, characterized in that: include: Data acquisition module, which obtains POI data, building elevation data and land use data around high-speed rail stations; The high-speed railway station area evaluation range calculation module performs multi-distance spatial clustering analysis on the POI data to determine the optimal clustering range as the evaluation range; The module for identifying the dominant functions of high-speed railway stations uses the average building height, building land area ratio, transportation land area ratio, and transportation service POI ratio within the evaluation range of each high-speed railway station as characteristic nodes to establish a decision tree, and divides the high-speed railway station into transportation-dominated and non-transportation-dominated categories. For high-speed railway stations dominated by non-transportation functions, the module uses the ratio of residential POIs, the ratio of business and R&D POIs, POI diversity index, POI density, land use diversity index, and average building height as analysis parameters, and uses cluster analysis to divide them into residential-dominated, business and R&D-dominated, and comprehensive urban function-dominated categories. The module for evaluating the comprehensive functional development level of high-speed railway station areas takes the proportion of transportation service POIs, the proportion of residential POIs, the proportion of business and research and development POIs, the POI diversity index, POI density, the proportion of building land area, the proportion of transportation land area, the land use diversity index, and the average building height within the evaluation scope of each high-speed railway station area as evaluation indicators, quantifies the evaluation indicators, and calculates the weighted values ​​of the indicator quantification values ​​through the weighted method, which is used for the evaluation of the comprehensive functional development level of high-speed railway station areas.

9. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images