Urban creative area identification method and system based on ST-DBSCAN spatial-temporal clustering algorithm

Abstract

The invention provides a city creative area identification method and system based on an ST-DBSCAN spatial-temporal clustering algorithm. The method comprises the steps of 1, collecting target enterprise data of a target city and performing preprocessing; 2, generating a city creative enterprise electronic map based on the enterprise address of the target enterprise; step 3, on the urban creative enterprise electronic map, performing first clustering partition on the target enterprise based on a spatial distance DBSCAN algorithm, and preliminarily identifying a DBSCAN candidate area; 4, screening target enterprise calculation indexes based on the target enterprise data, determining the weight of each calculation index of the target enterprise through an entropy evaluation method, carrying out weighted summation, and calculating the creativity of the enterprise; step 5, in the DBSCAN candidate area, calculating kernel density by taking the enterprise creativity as a weight to form density partitions; and creative areas of different grades are divided according to different density grades. According to the urban creative area identification method and system based on the DBSCAN-KDE joint clustering algorithm, accurate identification of the urban creative area is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data analysis, and in particular relates to a method and system for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm. Background Art

[0002] Current methods for identifying urban creative districts primarily rely on traditional clustering algorithms (such as K-means and hierarchical clustering) and single-metric evaluation systems. However, existing technologies have limitations: First, traditional clustering algorithms are sensitive to noise and cannot effectively identify clusters with uneven density (such as core and peripheral areas), resulting in rough zoning results. Second, existing methods often use a single metric (such as the number of patents) to evaluate the distribution of urban functional areas, ignoring the synergistic effects of multi-dimensional attributes (such as employee size and revenue-generating capacity), resulting in one-sided and lacking objectivity in evaluation results. Third, traditional kernel density estimation (KDE) does not incorporate firm attribute weights and relies solely on spatial point density to divide regions. This makes it difficult to distinguish the agglomeration effect of highly innovative firms and cannot accurately identify core creative districts. Fourth, existing question-answering systems are mostly based on general knowledge bases and lack in-depth integration with specialized field data (such as firm attributes and creative district characteristics), making it difficult to provide targeted decision-making recommendations. Summary of the Invention

[0003] In response to the above-mentioned technical conditions and limitations, the present invention provides a method and system for identifying urban creative areas based on the DBSCAN-KDE joint clustering algorithm, so as to achieve accurate identification of urban creative areas, automatically identify user question types through intelligent question-answering functions, and provide convenient information acquisition and decision support.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: A method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm includes the following steps: Step 1: Collect target enterprise data in the target city and pre-process it; Step 2: generating an electronic map of urban creative enterprises based on the corporate address of the target enterprise; Step 3: On the electronic map of the city's creative enterprises, the target enterprises are first clustered and partitioned using the DBSCAN algorithm based on spatial distance, and DBSCAN candidate areas are preliminarily identified; Step 4: Filter the target enterprise calculation indicators based on the target enterprise data, determine the weight of each calculation indicator of the target enterprise by entropy method, and calculate the enterprise creativity by weighted summation; Step 5: In the DBSCAN candidate area, the kernel density is calculated with the enterprise creativity as the weight to form density partitions; different levels of creative areas are divided according to different density levels.

[0005] Furthermore, the target enterprise in step 1 is a cultural, sports and entertainment enterprise; Target enterprise data includes: enterprise name, registered address, industry classification, operating income, number of employees, and company size.

[0006] Furthermore, step 2 includes the following sub-steps: Step 2.1, obtaining the enterprise address information of the target enterprise and converting the enterprise address information into enterprise geographic coordinates; Step 2.2: Import the city basic map into the GIS platform, associate the target enterprise data with the region according to the enterprise's geographic coordinates through spatial connection, and generate an electronic map of the city's creative enterprises.

[0007] Furthermore, in step 3, based on the electronic map of the city's creative enterprises, the DBSCAN candidate areas are preliminarily identified by setting the area radius and the minimum K value parameters.

[0008] Furthermore, step 4 includes the following sub-steps: Step 4.1: Based on the number of target enterprises and the target enterprise calculation indicators, construct an original data matrix, including positive indicators and negative indicators, and perform standardization and normalization on the target enterprise calculation indicators; Step 4.2: Calculate the information entropy and weight of each target enterprise's calculation indicators, and perform weighted summation to determine the enterprise's creativity; Step 4.3: Import the enterprise creativity into the electronic map of urban creative enterprises.

[0009] Furthermore, the target enterprise calculation indicators include: registered capital, operating income, and number of employees.

[0010] Furthermore, the target enterprise calculation index information entropy and weight are:

[0011]

[0012] in, , Reflect the The degree of dispersion and importance of the calculated indicators, For target enterprises The information entropy of the calculation indicators, is the number of target enterprises, Calculate indicators for target enterprises for standardization and normalization; Target Enterprise No. The weight of the calculation indicator, For the kThe information utility value of the calculation indicator, Calculate the number of indicators for the enterprise, Target Enterprises Creativity for:

[0013] in, Calculate indicators for the standardized target enterprises.

[0014] Furthermore, the step 5 includes: Step 5.1: Calculate the kernel density of the DBSCAN candidate region using the creativity, output the kernel density result and optimize it through cross-validation. Step 5.2: Divide the kernel density results into high, medium, and low value areas, corresponding to the core creative area, general creative area, and potential creative area, respectively; Step 5.3: Convert the corresponding core creative area into a polygon.

[0015] Furthermore, it also includes: Step 6: Collect relevant knowledge documents and combine the results of steps 1 and 4 to upload document data based on the Coze platform to automatically build an intelligent question-answering device; Step 7: Based on Coze, a workflow of the question-answering device is constructed to respond to user question requests, identify user question information, and obtain question types, which include enterprise information, creative zone information and characteristics, and creative zone development strategy questions. Based on the question type, the corresponding workflow path is selected for execution; Step 8: Install the operating environment and dependencies on the sealos cloud server, configure network connections and security group rules, receive the Secret Tower AI call request from the question-answering device, and integrate the results returned by Secret Tower AI with the knowledge base call results through the large model inside the question-answering device and return them to the user.

[0016] On the other hand, the present invention also provides an urban creative district identification system based on the ST-DBSCAN spatiotemporal clustering algorithm, comprising: A data collection module, which is used to collect target enterprise data in the target city and perform pre-processing; An electronic map generation module, which is used to generate an electronic map of urban creative enterprises based on the enterprise address of the target enterprise; A DBSCAN candidate area identification module is used to perform a first clustering and partitioning of the target enterprises on the electronic map of the city's creative enterprises based on the DBSCAN algorithm of spatial distance, and preliminarily identify DBSCAN candidate areas; An enterprise creativity calculation module is used to screen target enterprise calculation indicators based on the target enterprise data, determine the weights of the target enterprise calculation indicators by entropy method, and calculate the enterprise creativity by weighted summation; The creative area classification module is used to calculate the kernel density within the DBSCAN candidate area with the enterprise creativity as the weight to form density partitions; different levels of creative areas are divided according to different density levels.

[0017] Compared with the prior art, the present invention has the following beneficial effects: This method utilizes DBSCAN and the k-nearest neighbor algorithm for combined clustering. Using the neighborhood radius (ε) and the minimum number of samples (MinPts), it first identifies high-density areas, effectively processing noisy data and discovering clusters of arbitrary shapes, addressing the rough partitioning results of traditional algorithms. Furthermore, information entropy is used to objectively calculate the weights of enterprise attributes (such as registered capital, revenue, number of employees, and number of patents), eliminating subjective weighting bias and comprehensively reflecting the multidimensional characteristics of enterprise creativity, thereby enhancing the scientific nature of creative zone assessment. Furthermore, combined with DBSCAN candidate zone results, kernel density analysis is performed based on enterprise creativity, deeply integrating spatial distribution with attribute characteristics to accurately delineate creative zones of varying degrees. Finally, combining knowledge bases with large-scale modeling technology, this method automatically identifies user question types (such as enterprise information, creative zone characteristics, and development strategies), generates precise responses, and provides dynamic decision support. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 It is a schematic diagram of the overall process of the present invention.

[0020] Figure 2 Schematic diagram of enterprise distribution in a city in an embodiment of the present invention.

[0021] Figure 3 Schematic diagram of DBSCAN initial clustering in an embodiment of the present invention.

[0022] Figure 4 This is a classification diagram for identifying urban creative spaces in an embodiment of the present invention.

[0023] Figure 5 Schematic diagram of the workflow of the question-answering device in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0025] Example 1 The present invention will be further described below with reference to the accompanying drawings.

[0026] like Figure 1 As shown, the present invention provides a method for identifying urban creative areas based on big data and an intelligent question-answering device, comprising the following steps: Step 1: Collect and pre-process the target enterprise data in the target city; crawl the "culture, sports and entertainment industry" enterprise data of the target city from the public enterprise information platform (Qichacha), including fields such as: enterprise name, registered address, industry classification, operating income, number of employees, company size, etc. The specific implementation is divided into the following sub-steps: Step 1.1: Use Python's Scrapy framework automation tool to crawl data based on the Qichacha API (interface permissions must be applied for) or simulate a browser; Step 1.2: Combine the Baidu Maps address resolution API ( / geocoding / v3) and regular expression matching to convert the unstructured address into a four-level administrative division label. It should be noted that in step 1, field cleaning may be required to filter out invalid data (such as records with empty revenue); Step 2: Generate an electronic map of urban creative enterprises based on the address of the target enterprise, such as Figure 2 The specific implementation sub-steps are as follows: Step 2.1: Use the Baidu Map API to obtain the geocode of the business address and convert the address information into the business geographic coordinates. In a specific embodiment, use the Baidu Map API for batch geocoding (a quota is required) to return the latitude and longitude coordinates (lng, lat). In step 2.2, import the city base map (including administrative divisions and road networks) into the GIS platform (ArcGIS) and associate the enterprise point data (including latitude and longitude coordinates) with the corresponding regions through spatial join.

[0027] Step 3: On the electronic map of the city's creative enterprises, the target enterprises are first clustered and partitioned using the DBSCAN algorithm based on spatial distance, and the DBSCAN candidate areas are preliminarily identified; Figure 3 As shown; The specific implementation is as follows: In step 3.1, open the Python environment in ArcGIS Pro (via Analyze → Python → Python Window) and install scikit-learn and necessary dependencies. Step 3.2, read the enterprise point data in the Python window and set the neighborhood parameters (ε, MinPts); Here ε describes the neighborhood distance threshold of a certain sample, and MinPts describes the threshold of the number of samples in the neighborhood of a certain sample with a distance of ε, that is, the K value; Step 4: Filter the target enterprise calculation indicators based on the target enterprise data, determine the weight of each calculation indicator of the target enterprise by entropy method, and calculate the enterprise creativity by weighted summation; The specific implementation is as follows: Step 4.1, determine the number of enterprises , specific calculation indicators (Registered capital, operating income, number of employees, etc. are optional), construct the original data matrix, which are all positive and negative indicators, and perform standardization and normalization on them. Finally, import the data into ArcGIS to form a new field "Enterprise Creativity"; Positive indicator standardization:

[0028] Negative indicator normalization:

[0029] in, Indicates the All values ​​of the column metric.

[0030] Normalization processing:

[0031] Step 4.2, calculate information entropy and weights , determine the degree of enterprise creativity ; No. Information entropy of an indicator for:

[0032] No. Weight of the indicator for:

[0033] enterprise Creativity The weighted sum of each indicator is:

[0034] Step 4.3: Import the enterprise creativity into the electronic map of urban creative enterprises.

[0035] Step 5: In the DBSCAN candidate area, calculate the kernel density with the enterprise creativity as the weight to form density partitions; divide the creative areas into different levels according to the different density levels. Figure 4 As shown; The specific implementation steps are as follows; Step 5.1: Open ArcGIS, open the Spatial Analyst toolbox → Density Analysis → Kernel Density Analysis. Set the parameters: Input point feature: Enterprise point → Field: Creativity (creativity as weight) → Output raster: Set the path (e.g., KernelDensity.tif) → Search radius (bandwidth): Adjust based on data distribution (e.g., 500 meters). This can be optimized through cross-validation. The cross-validation method specifically uses least squares cross validation (LSCV). This method does not require distribution assumptions and is applicable to complex big data. The formula is: ; By traversing the candidate bandwidth , for each , calculate the leave-one-out density estimate, and select the one that minimizes LSCV .

[0036] Step 5.2: Use the "Reclassify" tool to classify the kernel density results into high, medium, and low value areas. These distributions correspond to core creative areas, general creative areas, and potential creative areas. Step 5.3, use the "Raster to Polygon" tool to convert the high-density areas into polygons; like Figure 5 As shown; Step 6, collect relevant knowledge documents, and combine the results of Step 1 and Step 4, upload document data based on the Coze platform, and automatically build an intelligent question-answering device; Step 7: Based on Coze, a workflow of the question-answering device is constructed to respond to user question requests, identify user question information, and obtain question types, which include enterprise information, creative zone information and characteristics, and creative zone development strategy questions. Based on the question type, the corresponding workflow path is selected for execution; Step 8: Install the operating environment and dependencies on the sealos cloud server, configure network connections and security group rules, receive the Secret Tower AI call request from the question-answering device, and integrate the results returned by Secret Tower AI with the knowledge base call results through the large model inside the question-answering device and return them to the user.

[0037] Example 2 This embodiment provides an urban creative district identification system based on the ST-DBSCAN spatiotemporal clustering algorithm, which is characterized by including: A data collection module, which is used to collect target enterprise data in the target city and perform pre-processing; An electronic map generation module, which is used to generate an electronic map of urban creative enterprises based on the enterprise address of the target enterprise; A DBSCAN candidate area identification module is used to perform a first clustering and partitioning of the target enterprises on the electronic map of the city's creative enterprises based on the DBSCAN algorithm of spatial distance, and preliminarily identify DBSCAN candidate areas; An enterprise creativity calculation module is used to screen target enterprise calculation indicators based on the target enterprise data, determine the weights of the target enterprise calculation indicators by entropy method, and calculate the enterprise creativity by weighted summation; The creative area classification module is used to calculate the kernel density within the DBSCAN candidate area with the enterprise creativity as the weight to form density partitions; different levels of creative areas are divided according to different density levels.

[0038] It should be understood that parts not elaborated in detail in this specification belong to the prior art.

[0039] It should be understood that the above description of the preferred embodiments is relatively detailed and cannot be considered as limiting the scope of protection of the present invention. It is not necessary and impossible to list all embodiments here. Under the guidance of the present invention, ordinary technicians in this field can also make substitutions or modifications without departing from the scope of protection of the claims of the present invention, which fall within the scope of protection of the present invention. The scope of protection of the present invention shall be based on the attached claims.

Claims

1. A method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm, characterized in that: The following steps are involved: Step 1: Collect target enterprise data in the target city and pre-process it; Step 2: generating an electronic map of urban creative enterprises based on the corporate address of the target enterprise; Step 3: On the electronic map of the city's creative enterprises, the target enterprises are first clustered and partitioned using the DBSCAN algorithm based on spatial distance, and DBSCAN candidate areas are preliminarily identified; Step 4: Filter the target enterprise calculation indicators based on the target enterprise data, determine the weight of each calculation indicator of the target enterprise by entropy method, and calculate the enterprise creativity by weighted summation; Step 5: In the DBSCAN candidate area, the kernel density is calculated with the enterprise creativity as the weight to form density partitions; different levels of creative areas are divided according to different density levels.

2. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 1, characterized in that: The target enterprises in step 1 are cultural, sports and entertainment enterprises; Target enterprise data includes: enterprise name, registered address, industry classification, operating income, number of employees, and company size.

3. The urban creative district identification method based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 1 is characterized in that: The step 2 includes the following sub-steps: Step 2.1, obtaining the enterprise address information of the target enterprise and converting the enterprise address information into enterprise geographic coordinates; Step 2.2: Import the city basic map into the GIS platform, associate the target enterprise data with the region according to the enterprise's geographic coordinates through spatial connection, and generate an electronic map of the city's creative enterprises.

4. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 1, characterized in that: In step 3, based on the electronic map of urban creative enterprises, the DBSCAN candidate areas are preliminarily identified by setting the area radius and the minimum K value parameters.

5. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 1, characterized in that: The step 4 includes the following sub-steps: Step 4.1: Based on the number of target enterprises and the target enterprise calculation indicators, construct an original data matrix, including positive indicators and negative indicators, and perform standardization and normalization on the target enterprise calculation indicators; Step 4.2: Calculate the information entropy and weight of each target enterprise's calculation indicators, and perform weighted summation to determine the enterprise's creativity; Step 4.3: Import the enterprise creativity into the electronic map of urban creative enterprises.

6. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 5, characterized in that: The target enterprise calculation indicators include: registered capital, operating income, and number of employees.

7. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 5, characterized in that: The target enterprise calculation index information entropy and weight are: in, , Reflect the The degree of dispersion and importance of the calculated indicators, For target enterprises The information entropy of the calculation indicators, is the number of target enterprises, Calculate indicators for target enterprises for standardization and normalization; Target Enterprise No. The weight of the calculation indicator, For the k The information utility value of the calculation indicator, Calculate the number of indicators for the enterprise, Target Enterprises Creativity for: in, Calculate indicators for the standardized target enterprises.

8. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 6, characterized in that: The step 5 comprises: Step 5.1: Calculate the kernel density of the DBSCAN candidate region using the creativity, output the kernel density result and optimize it through cross-validation. Step 5.2: Divide the kernel density results into high, medium, and low value areas, corresponding to the core creative area, general creative area, and potential creative area, respectively; Step 5.3: Convert the corresponding core creative area into a polygon.

9. The method for identifying urban creative areas based on the ST-DBSCAN spatiotemporal clustering algorithm according to claim 1, characterized in that: Also includes: Step 6: Collect relevant knowledge documents and combine the results of steps 1 and 4 to upload document data based on the Coze platform to automatically build an intelligent question-answering device; Step 7: Based on Coze, a workflow of the question-answering device is constructed to respond to user question requests, identify user question information, and obtain question types, which include enterprise information, creative zone information and characteristics, and creative zone development strategy questions. Based on the question type, the corresponding workflow path is selected for execution; Step 8: Install the operating environment and dependencies on the sealos cloud server, configure network connections and security group rules, receive the Secret Tower AI call request from the question-answering device, and integrate the results returned by Secret Tower AI with the knowledge base call results through the large model inside the question-answering device and return them to the user.

10. An urban creative district identification system based on the ST-DBSCAN spatiotemporal clustering algorithm, characterized by: include: A data collection module, which is used to collect target enterprise data in the target city and perform pre-processing; An electronic map generation module, which is used to generate an electronic map of urban creative enterprises based on the enterprise address of the target enterprise; A DBSCAN candidate area identification module is used to perform a first clustering and partitioning of the target enterprises on the electronic map of the city's creative enterprises based on the DBSCAN algorithm of spatial distance, and preliminarily identify DBSCAN candidate areas; An enterprise creativity calculation module is used to screen target enterprise calculation indicators based on the target enterprise data, determine the weights of the target enterprise calculation indicators by entropy method, and calculate the enterprise creativity by weighted summation; The creative zone classification module is used to calculate the kernel density within the DBSCAN candidate area using the enterprise creativity as the weight to form density partitions; different levels of creative zones are divided according to different density levels; The urban creative district identification method based on the ST-DBSCAN spatiotemporal clustering algorithm is used to execute the steps in the urban creative district identification method based on the ST-DBSCAN spatiotemporal clustering algorithm described in any one of claims 1 to 9.

Images