A Smart Site Selection Method and System Based on Spatiotemporal Data Platform

Abstract

This invention relates to the field of urban planning technology, specifically providing a smart site selection method and system based on a spatiotemporal data platform. The method includes: collecting multi-source spatiotemporal data on key industries in a target area; constructing a set of enterprise demand characteristics based on the multi-source spatiotemporal data; establishing quantitative demand standards based on the characteristic set; constructing an industrial ecosystem adaptation model based on the current industrial base data of the target area; calculating the matching degree between the characteristic set and the industrial ecosystem of the target area through the industrial ecosystem adaptation model, with industrial ecosystem clustering as the goal, and outputting candidate parks based on the matching degree; establishing multi-factor adaptation relationships between target enterprises and candidate parks based on the quantitative demand standards; performing matching verification through multi-dimensional compliance verification units, and eliminating parks that do not meet the constraints of the quantitative demand standards; and outputting site selection schemes based on the verification results, ultimately achieving a high degree of matching between enterprise needs and public resources, improving site selection efficiency and quality, and contributing to the sustainable development of regional industries.

Description

Technical Field

[0001] This invention relates to the field of urban planning technology, specifically to a smart site selection method and system based on a spatiotemporal data platform. Background Technology

[0002] With the advancement of smart city construction, big data and spatiotemporal analysis technologies are increasingly being applied in urban planning, industrial layout, and other fields. Smart site selection, as a key link in resource optimization, is gradually transforming from traditional manual decision-making to data-driven intelligent decision-making. Existing technologies typically integrate multi-source information such as geospatial data and socio-economic data, combined with GIS spatial analysis, indicator weight calculation, and visualization, to assist in site selection decisions for commercial facilities and public service institutions, thus improving the scientific rigor and efficiency of site selection to some extent. For example, some methods construct evaluation index systems (such as transportation accessibility, population density, and supporting facilities), and use models such as the analytic hierarchy process (AHP) and entropy method to calculate comprehensive scores, thereby ranking and filtering candidate areas.

[0003] However, in the specific scenario of smart investment promotion, existing technologies still have significant limitations:

[0004] On the one hand, existing site selection methods often focus on static analysis of single factors (such as land area and transportation conditions) or are designed for general scenarios (such as commercial stores and security facilities), failing to fully consider the deep synergistic matching needs of "enterprise needs - industrial ecosystem - spatial resources" in investment promotion scenarios. This leads to a disconnect between site selection solutions and the actual operational needs of enterprises. For example, when attracting investment for industrial projects, existing methods often only rely on basic indicators such as land use and plot ratio for screening, ignoring the enterprise's supply chain linkage needs (such as the distribution radius of suppliers / customers), production process characteristics (such as energy consumption and load requirements), and the complementarity of the regional industrial ecosystem (such as the maturity of upstream and downstream supporting facilities). This results in a disconnect between site selection solutions and the goals of industrial cluster development. On the other hand, the evaluation models of existing systems are mostly statically constructed, relying on fixed indicator weights or single algorithms (such as genetic algorithms and comprehensive scoring). They do not iteratively optimize based on the actual implementation effects of investment promotion in different industries, making it difficult to cope with dynamic scenarios such as regional industrial evolution and changes in enterprise needs. This easily leads to insufficient long-term adaptability of site selection solutions.

[0005] The aforementioned issues make it difficult for existing technologies to achieve the goals of "precise matching, industrial collaboration, and dynamic adaptation" in smart investment promotion scenarios, resulting in frequent problems such as low project implementation rates and weak industrial agglomeration effects. Therefore, there is an urgent need for a site selection method specifically designed for smart investment promotion scenarios that can integrate dynamic enterprise needs, industrial ecosystem characteristics, and spatial resource elements, and possess closed-loop optimization capabilities. Summary of the Invention

[0006] To overcome the shortcomings of existing technologies, this invention provides a smart location selection method and system based on a spatiotemporal data platform to solve the problems in existing technologies.

[0007] One embodiment of the present invention provides a smart location selection method based on a spatiotemporal data platform, comprising the following steps:

[0008] Collect multi-source spatiotemporal data of key industries in the target area, construct an enterprise demand feature set based on the multi-source spatiotemporal data, the enterprise demand feature set includes at least industry attributes, fixed asset investment amount, industrial chain related demand and production process demand; establish quantitative demand standards based on the enterprise demand feature set, the quantitative demand standards include at least land use scale, building function parameters, and municipal and supporting element thresholds.

[0009] Based on the current industrial base data of the target region, an industrial ecosystem adaptation model is constructed. The matching degree between the enterprise demand feature set and the industrial ecosystem of the target region is calculated through the industrial ecosystem adaptation model. The matching degree includes the industrial chain correlation, industrial agglomeration fit, and supporting infrastructure completeness. The industrial ecosystem adaptation model aims at industrial ecosystem clustering and outputs candidate parks based on the matching degree.

[0010] Based on the quantitative demand standard of the enterprise demand feature set, a multi-factor matching relationship is established between the target enterprise and the candidate park in terms of land use space scale and building function parameters; the municipal and supporting element thresholds and restrictive elements of the candidate park are matched and verified by a multi-dimensional compliance verification unit, and parks that do not meet the constraints of the quantitative demand standard are eliminated.

[0011] Based on the verification results, a site selection plan is output. The site selection plan includes a recommended ranking of industrial parks, suitable industrial land and industrial buildings, and includes customized resource matching suggestions and risk response strategies for restrictive factors that match the enterprise's demand feature set.

[0012] Based on feedback data from key industries in the target region, the quantitative demand standards and industrial ecosystem adaptation model parameters are dynamically updated.

[0013] By adopting the above scheme, deep integration and efficient utilization of multi-source spatiotemporal data can be achieved. This enables the precise construction of a set of enterprise demand characteristics, encompassing industry attributes, fixed asset investment, supply chain linkages, and production process requirements. These characteristics are then transformed into quantitative standards such as land use scale, building function parameters, and thresholds for municipal and supporting elements, providing a solid data foundation and clear benchmarks for subsequent processes. The industrial ecosystem adaptation model, guided by industrial ecosystem clustering, calculates the supply chain linkage, industrial agglomeration fit, and supporting facility completeness of the enterprise demand characteristic set with the target region's industrial ecosystem. This achieves deep collaborative matching of "enterprise demand - industrial ecosystem - spatial resources," effectively solving the problem of disconnect between existing site selection schemes and industrial clustering goals, and powerfully promoting regional industrial collaborative development and clustering construction. The multi-dimensional compliance verification unit rigorously verifies candidate parks based on quantitative demand standards, accurately eliminating those that do not meet the criteria, greatly improving the feasibility and compliance of site selection. The output site selection scheme includes recommended parks, suitable industrial land and buildings, coupled with customized resource matching suggestions and risk mitigation strategies for restrictive factors, optimizing resource allocation and reducing potential risks. Meanwhile, by dynamically updating quantitative demand standards and model parameters through feedback data from key industries in the target area, the site selection method has good adaptability and iterativeness, effectively overcoming the problem of poor long-term adaptability of existing solutions, and ultimately achieving a high degree of matching between enterprise needs and public resources, significantly improving site selection efficiency and quality, and contributing to the sustainable development of regional industries.

[0014] In one embodiment, before the step of outputting the location selection scheme based on the verification result, the following step is further included:

[0015] A virtual simulation scenario of the target area is constructed based on digital twin technology. The verified candidate park data, enterprise demand feature set, and current industrial base data of the target area are input into the virtual simulation scenario. The simulation simulates the industrial driving effect, economic benefits, and input-output ratio of supporting measures of the target enterprise after it settles in the candidate park within a preset period. The industrial driving effect includes the number of upstream and downstream enterprises and the improvement of industrial chain collaboration efficiency. The economic benefits include the annual tax contribution and the number of new jobs. The input-output ratio of supporting measures is the ratio of park infrastructure investment to the enterprise's expected output value.

[0016] Based on the simulation results, the candidate parks are prioritized and ranked. The weighted comprehensive score of each candidate park in terms of industrial driving effect, economic benefits and input-output ratio of supporting measures within the preset simulation period is calculated, and the candidate park with the best comprehensive score is selected.

[0017] By adopting the above scheme and using digital twin technology to construct a virtual simulation scenario, the verified candidate park data, enterprise demand feature set, and current industrial base data of the target area are incorporated into the simulation analysis. This allows for the accurate simulation of the industrial driving effect, economic benefits, and input-output ratio of supporting measures within a preset period after the target enterprises settle in, transforming the long-term impact of industrial development from "experience-based prediction" to "data-driven quantitative assessment." By calculating the weighted comprehensive score of each candidate park within the preset period and prioritizing them, the park with the best comprehensive benefits can be selected. This further enhances the depth of consideration for long-term industrial synergy, economic benefits, and resource input efficiency in the site selection scheme, effectively avoiding the problem of neglecting long-term development adaptability due to short-term matching. The final output site selection scheme is more in line with the regional industrial sustainable development goals, enhancing the foresight and scientific nature of smart investment attraction and site selection.

[0018] In one embodiment, the step of collecting multi-source spatiotemporal data of key industries in the target area and constructing a set of enterprise demand features based on the multi-source spatiotemporal data further includes, while constructing the set of enterprise demand features:

[0019] Construct a community feature set for the target area, which includes at least community population structure data, community public service carrying capacity data, and community environmental sensitive element data;

[0020] The step of calculating the matching degree between the enterprise demand feature set and the target region's industrial ecosystem through the industrial ecosystem adaptation model specifically includes:

[0021] Calculate the first degree of matching between the enterprise demand feature set and the target area industrial ecosystem. The first degree of matching is determined based on the degree of industrial chain correlation, the degree of industrial agglomeration fit and the degree of supporting facilities.

[0022] Calculate the second matching degree between the enterprise demand feature set and the community feature set. The second matching degree is determined based on the adaptability of enterprise talent demand and community population structure data, the incremental demand of enterprise operation on community public service carrying capacity data, and the compatibility of enterprise environmental impact and community environmental sensitive element data.

[0023] The first matching degree and the second matching degree are weighted and fused to obtain the final matching degree between the enterprise and the target region, which serves as the basis for the output of candidate parks by the industrial ecosystem adaptation model.

[0024] By adopting the above scheme, a community feature set is constructed, and a two-dimensional matching mechanism of "industrial ecosystem - community features" is established. This ensures that the matching degree calculation not only covers the correlation and adaptation between enterprises and the regional industrial ecosystem, but also incorporates the compatibility assessment of enterprises and community population structure, public service carrying capacity, and environmentally sensitive factors. The weighted fusion result of the first and second matching degrees reflects both the economic value of industrial synergy and takes into account the social adaptability and environmental compliance at the community level. This effectively avoids neglecting the potential impact of enterprise operations on the community (such as environmental conflicts, overload of public services) or insufficient community resources to support enterprises (such as talent supply imbalance) due to focusing only on industrial matching. This results in a balance between industrial synergy and harmonious community development in the final candidate parks, further enhancing the smart investment promotion and site selection scheme's consideration of the comprehensive benefits of "economic-social-environment," and improving the sustainability and social acceptance of the site selection results.

[0025] In one embodiment, the step of establishing a multi-factor matching relationship between the target enterprise and the candidate park in terms of land use space scale and building function parameters based on the quantitative demand standard of the enterprise demand feature set specifically includes:

[0026] A multi-factor quantitative adaptation model is constructed. The multi-factor quantitative adaptation model is based on the quantitative demand standard of enterprise demand feature set and establishes a quantitative mapping relationship between the land use spatial scale parameters, building function parameters and enterprise demand feature set of candidate parks.

[0027] The multi-dimensional adaptation index for determining the quantitative mapping relationship includes at least the land use space adaptation dimension and the building function adaptation dimension. Each dimension adaptation index includes at least one quantitative index parameter and a corresponding weight coefficient.

[0028] Each quantitative indicator parameter is standardized to generate comparable quantitative values. The standardization process includes, but is not limited to, deviation rate calculation, fit calculation, and compliance rate calculation.

[0029] The quantitative values ​​of each dimension are weighted and aggregated based on the weight coefficients to generate a comprehensive fit score for multiple factors.

[0030] Set an adaptation threshold and include candidate parks that meet the overall adaptation threshold in the subsequent verification process, while remove candidate parks that do not meet the adaptation threshold.

[0031] By adopting the above scheme, the multi-factor quantitative matching model transforms the enterprise demand feature set and candidate park parameters into a calculable quantitative mapping relationship, solving the problem of insufficient quantitative accuracy in multi-factor matching relationships. The multi-dimensional matching indicator system covers land use space and building function dimensions, with weight coefficients reflecting industry priority differences, enhancing model adaptability. Standardized processing unifies the indicator calculation benchmark, improving the objectivity of the evaluation; weighted aggregation scoring achieves multi-dimensional scientific integration, providing accurate quantitative evaluation; threshold screening reduces subsequent verification redundancy, optimizing process efficiency. This model transforms experience-based judgment into data-driven decision-making, significantly improving the accuracy and efficiency of "enterprise demand - park resources" matching, providing key support for core solutions, and enhancing the scientific nature and reliability of smart investment attraction and site selection.

[0032] In one embodiment, the step of constructing an industrial ecosystem adaptation model based on the current industrial base data of the target region, and calculating the matching degree between the enterprise demand feature set and the industrial ecosystem of the target region through the industrial ecosystem adaptation model, specifically includes the following steps:

[0033] Collect enterprise demand feature sets and target area current industrial base data, preprocess them to obtain standardized feature data that can be used for machine learning model training;

[0034] The standardized feature data is used to train an industry ecosystem adaptation model using machine learning algorithms to obtain a trained industry ecosystem adaptation model, which is then used for:

[0035] Real-time calculation of the matching degree between enterprise demand feature set and target area industrial ecosystem;

[0036] With the goal of industrial ecosystem clustering, the candidate park ranking results are output based on the matching degree.

[0037] By adopting the above scheme, the collected enterprise demand feature set and the current industrial base data of the target area are preprocessed to make the data suitable for the input requirements of the machine learning model. The preprocessed standardized feature data is then used to train the industrial ecosystem adaptation model using machine learning algorithms. The resulting model can then output the matching degree between enterprises and the industrial ecosystem based on the real-time input data, and output the candidate park ranking results with the goal of industrial ecosystem clustering, providing a quantitative basis for accurate site selection.

[0038] In one embodiment, the step of preprocessing the collected enterprise demand feature set and the current industrial base data of the target area to obtain standardized feature data that can be used for machine learning model training specifically includes:

[0039] Collect the enterprise demand feature set and the current industrial base data of the target area. The current industrial base data includes industrial chain structure data, industrial cluster distribution data and supporting facility data.

[0040] The collected data is cleaned and processed, including missing value imputation, outlier correction, and data format standardization.

[0041] Based on the relationship between the enterprise demand feature set and the industrial ecosystem of the target area, feature mapping is performed on the cleaned data to generate an initial feature set containing industrial chain linkage features, industrial agglomeration features and supporting features.

[0042] The initial feature set is standardized by normalizing each feature value to a preset range, resulting in standardized feature data that can be directly used for training machine learning models.

[0043] By adopting the above scheme, the collected enterprise demand feature set and the current industrial base data of the target area are cleaned, feature mapped and standardized. This removes noise from the data and establishes correlations, resulting in standardized feature data suitable for machine learning model training. Feature mapping clarifies the correspondence between enterprise demand and industrial ecosystem, and standardization unifies the data benchmark, avoiding model input bias caused by data chaos and ensuring the effectiveness of model training data.

[0044] In one embodiment, the step of training the standardized feature data into an industry ecosystem adaptation model using a machine learning algorithm to obtain the trained industry ecosystem adaptation model specifically includes:

[0045] The standardized feature data is divided into a training set and a validation set;

[0046] The initial industrial ecosystem adaptation model is trained based on the training set. The initial industrial ecosystem adaptation model takes the industrial chain association dimension, industrial agglomeration fit dimension and supporting dimension as the core evaluation dimensions, and sets corresponding quantitative indicators and weight coefficients for each dimension.

[0047] The comprehensive matching score of the training set is calculated using the initial industrial ecosystem adaptation model. The score is the weighted sum of the standardized quantitative indicators of each dimension.

[0048] The model performance is verified using the verification set, requiring that the matching accuracy of the core evaluation dimensions is not lower than a preset threshold, and the weight coefficients and indicator parameters of the industrial ecosystem adaptation model are optimized based on the verification results.

[0049] A trained industry ecosystem adaptation model is generated based on the optimized weight coefficients and indicator parameters. The industry ecosystem adaptation model is configured as follows:

[0050] Receive real-time enterprise demand feature sets and target area industrial ecosystem data, and output a comprehensive matching score between the two;

[0051] With the goal of industrial ecosystem clustering, the comprehensive matching score is weighted twice to generate a ranking result of candidate parks. Among them, parks with a high degree of correlation with existing industrial clusters receive additional weight bonuses.

[0052] By adopting the above scheme, the standardized feature data is divided into a training set and a validation set. The training set is used to train the initial industrial ecosystem adaptation model and calculate the comprehensive matching score. The test set is used to verify the model performance and optimize the parameters so that the model's matching accuracy meets the preset threshold. The optimized model can receive data output in real time and highlight the industrial cluster correlation through secondary weighting. This makes the candidate park ranking results not only meet the quantitative matching requirements but also fit the industrial ecosystem clustering goal, thus improving the accuracy and applicability of site selection matching.

[0053] This application also relates to a smart location system based on a spatiotemporal data platform, comprising:

[0054] The multi-source data acquisition module is used to collect multi-source spatiotemporal data of key industries in the target area, and to construct an enterprise demand feature set based on the multi-source spatiotemporal data. The enterprise demand feature set includes at least industry attributes, fixed asset investment amount, industrial chain related demand and production process demand. Based on the enterprise demand feature set, a quantitative demand standard is established. The quantitative demand standard includes at least land use scale, building function parameters and municipal and supporting element thresholds.

[0055] The candidate park generation module is used to construct an industrial ecosystem adaptation model based on the current industrial base data of the target area. The industrial ecosystem adaptation model calculates the matching degree between the enterprise demand feature set and the industrial ecosystem of the target area. The matching degree includes the industrial chain correlation, industrial agglomeration fit and supporting facility completeness. The industrial ecosystem adaptation model aims at industrial ecosystem clustering and outputs candidate parks according to the matching degree.

[0056] The candidate park screening module is used to establish a multi-factor matching relationship between the target enterprise and the candidate park in terms of land use space scale and building function parameters based on the quantitative demand standards of the enterprise demand feature set; and to perform matching verification on the municipal and supporting element thresholds and restrictive elements of the candidate park through a multi-dimensional compliance verification unit, and to eliminate parks that do not meet the constraints of the quantitative demand standards.

[0057] The site selection scheme generation module is used to output a site selection scheme based on the verification results. The site selection scheme includes a recommended ranking of the parks to be settled in, suitable industrial land and industrial buildings, and includes customized resource matching suggestions and risk response strategies for restrictive factors that match the enterprise's demand feature set.

[0058] The dynamic optimization module is used to dynamically update the quantitative demand standards and industrial ecosystem adaptation model parameters based on feedback data from key industries in the target region.

[0059] By adopting the above scheme, deep integration and efficient utilization of multi-source spatiotemporal data can be achieved. This enables the precise construction of a set of enterprise demand characteristics, encompassing industry attributes, fixed asset investment, supply chain linkages, and production process requirements. These characteristics are then transformed into quantitative standards such as land use scale, building function parameters, and thresholds for municipal and supporting elements, providing a solid data foundation and clear benchmarks for subsequent processes. The industrial ecosystem adaptation model, guided by industrial ecosystem clustering, calculates the supply chain linkage, industrial agglomeration fit, and supporting facility completeness of the enterprise demand characteristic set with the target region's industrial ecosystem. This achieves deep collaborative matching of "enterprise demand - industrial ecosystem - spatial resources," effectively solving the problem of disconnect between existing site selection schemes and industrial clustering goals, and powerfully promoting regional industrial collaborative development and clustering construction. The multi-dimensional compliance verification unit rigorously verifies candidate parks based on quantitative demand standards, accurately eliminating those that do not meet the criteria, greatly improving the feasibility and compliance of site selection. The output site selection scheme includes recommended parks, suitable industrial land and buildings, coupled with customized resource matching suggestions and risk mitigation strategies for restrictive factors, optimizing resource allocation and reducing potential risks. Meanwhile, by dynamically updating quantitative demand standards and model parameters through feedback data from key industries in the target area, the site selection method has good adaptability and iterativeness, effectively overcoming the problem of poor long-term adaptability of existing solutions, and ultimately achieving a high degree of matching between enterprise needs and public resources, significantly improving site selection efficiency and quality, and contributing to the sustainable development of regional industries.

[0060] This application also relates to a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described intelligent addressing method based on a spatiotemporal data platform.

[0061] This application also relates to a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned intelligent location method based on a spatiotemporal data platform.

[0062] The intelligent site selection method and system based on a spatiotemporal data platform provided in the above embodiments have the following beneficial effects:

[0063] This system enables deep fusion and efficient utilization of multi-source spatiotemporal data, accurately constructing a set of enterprise demand characteristics covering industry attributes, fixed asset investment, supply chain linkages, and production process requirements. This is then transformed into quantitative standards such as land use scale, building function parameters, and thresholds for municipal and supporting elements, providing a solid data foundation and clear benchmarks for subsequent processes. The industrial ecosystem adaptation model, guided by industrial ecosystem clustering, calculates the supply chain linkage, industrial agglomeration fit, and supporting facility completeness of the enterprise demand characteristic set with the target region's industrial ecosystem. This achieves deep collaborative matching of "enterprise demand - industrial ecosystem - spatial resources," effectively solving the problem of disconnect between existing site selection schemes and industrial clustering goals, and powerfully promoting regional industrial collaborative development and clustering construction. A multi-dimensional compliance verification unit rigorously verifies candidate parks based on quantitative demand standards, accurately eliminating those that do not meet the criteria, greatly improving the feasibility and compliance of site selection. The output site selection scheme includes recommended parks, suitable industrial land and buildings, coupled with customized resource matching suggestions and risk mitigation strategies for restrictive factors, optimizing resource allocation and reducing potential risks. Meanwhile, by dynamically updating quantitative demand standards and model parameters through feedback data from key industries in the target area, the site selection method has good adaptability and iterativeness, effectively overcoming the problem of poor long-term adaptability of existing solutions, and ultimately achieving a high degree of matching between enterprise needs and public resources, significantly improving site selection efficiency and quality, and contributing to the sustainable development of regional industries. Attached Figure Description

[0064] Figure 1 A flowchart illustrating the intelligent location selection method based on a spatiotemporal data platform provided in an embodiment of the present invention;

[0065] Figure 2 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0066] The technical solutions in the embodiments of the present invention will now be clearly and completely described in conjunction with the accompanying drawings.

[0067] Reference Figure 1 One embodiment of the present invention provides a smart location selection method based on a spatiotemporal data platform, comprising the following steps:

[0068] S10. Collect multi-source spatiotemporal data of key industries in the target area, and construct an enterprise demand feature set based on the multi-source spatiotemporal data. The enterprise demand feature set includes at least industry attributes, fixed asset investment, industrial chain related demand, and production process demand. Establish quantitative demand standards based on the enterprise demand feature set. The quantitative demand standards include at least land use scale, building function parameters, and municipal and supporting element thresholds.

[0069] In this embodiment, the target area refers to the specific geographical area for which investment attraction and site selection assessments are planned. Key industry categories are those industries within the target area that are identified as requiring focused attention, analysis, or research, based on factors such as the region's development positioning, its status as an economic pillar, and its strategic planning goals or policy orientation. For example, if the target area is a new energy industry base, its key industry categories might include photovoltaic manufacturing, energy storage battery research and development, and wind power equipment production; if the target area is a coastal economic zone, its key industry categories might cover port logistics, marine engineering, and shipbuilding.

[0070] For industry-related data in multi-source spatiotemporal data, information can be obtained from industry development white papers and key industry lists published by industry regulatory authorities; fixed asset investment amounts can be referenced from enterprise project filing documents, investment agreements, and project database information from investment promotion departments; supply chain-related demand data comes from industry cluster mapping reports, enterprise cooperation agreements, and transaction records from supply chain management platforms; production process requirements are based on industry technical standard manuals, enterprise production specifications, and technical parameter descriptions from equipment suppliers. Those skilled in the art can obtain this data through the internet via relevant official websites, enterprise websites, industry platforms, and other channels.

[0071] For constructing enterprise demand feature sets based on multi-source spatiotemporal data, the collected raw data needs to be screened and refined during the construction process. Core characteristics such as industry category and development stage are extracted from industry attribute-related data; fixed asset investment data is summarized and calculated to clarify the total amount of funds and the proportion of each use; supply chain-related demand data is sorted out to determine the specific collaborative relationships with upstream, downstream, and supporting enterprises; production process demand data is analyzed to obtain key information such as the required technology level and equipment specifications, ultimately forming an enterprise demand feature set that includes industry attributes, fixed asset investment, supply chain-related demands, and production process demands. Industry attributes, fixed asset investment, supply chain-related demands, and production process demands are the core elements for constructing the enterprise demand feature set. They aim to accurately characterize enterprise features from the perspective of enterprise attributes and operational needs, providing a foundation for subsequent industry collaboration and resource allocation. Specifically, their functions include:

[0072] Industry attributes: Clearly defining the specific industry sector to which the enterprise belongs (such as auto parts manufacturing or biopharmaceutical research and development) is the basis for judging whether the target enterprise is compatible with the key industries of the target region (for example, if the region focuses on developing the new energy industry, then priority will be given to matching enterprises engaged in the research and development of new energy batteries), ensuring that the investment projects are consistent with the region's industrial positioning.

[0073] Fixed asset investment: This reflects the size and investment intensity of enterprises (e.g., fixed asset investment ≥ 500 million yuan). It is used to screen enterprises that match the carrying capacity of the region (for example, industrial parks can use this indicator to determine whether they have sufficient land and capital support capabilities) to avoid difficulties in landing due to the mismatch between enterprise size and regional resources.

[0074] Supply chain linkage requirements: This reflects a company's position in the supply chain and its dependence on upstream and downstream partners (e.g., core suppliers need to be located within a 30-kilometer radius or adjacent to logistics hubs). It is key to calculating the degree of industrial synergy and matching (e.g., if a region has formed an automobile manufacturing cluster, parts companies with this characteristic will be given priority due to the complementarity of the supply chain), supporting the goal of industrial ecosystem clustering.

[0075] Production process requirements: These cover the special requirements of the enterprise's production process (such as cleanroom level, high temperature resistant workshop, annual electricity consumption ≥10 million kWh, etc.), which are directly related to the subsequent space and resource adaptation (for example, the explosion-proof process requirements of chemical enterprises need to match the safety facility standards of the park), to ensure that the basic conditions for the enterprise's production and operation are met.

[0076] For establishing quantitative demand standards based on enterprise demand characteristic sets, the quantification process needs to combine the actual operational needs of enterprises with industry-standard practices. The land use spatial scale is determined based on the enterprise's production scale, equipment footprint, and future development plans, referencing the land use of similar enterprises in the same industry to determine specific numerical ranges. Building function parameters are determined based on the specific requirements of the production process for the factory building, such as floor height, load-bearing capacity, and fire protection rating, referring to building design codes to determine specific parameter values. Municipal and supporting element thresholds comprehensively consider the enterprise's production water, electricity, and gas needs, as well as its requirements for transportation and logistics support conditions, combining municipal infrastructure planning standards to determine various thresholds, such as water supply capacity in tons per hour and power supply capacity in kilovolt-amperes. The land use spatial scale, building function parameters, and municipal and supporting element thresholds are the core content of the quantitative demand standards, aiming to transform enterprise needs into verifiable and implementable spatial and resource indicators, providing a rigid basis for the selection and verification of candidate parks. Specifically, their functions are as follows:

[0077] Land use spatial scale: including plot area, shape, plot ratio, etc. (e.g., land area ≥ 50 mu, plot ratio ≤ 1.2), to match the space occupation needs of enterprises (for example, large equipment manufacturing enterprises need large plots, while science and technology innovation enterprises may focus more on the regularity of plot shape to adapt to the layout of R&D buildings), to ensure that enterprises have enough physical space to carry out production.

[0078] Building functional parameters: These are functional indicators of buildings such as factories and office buildings (e.g., factory floor height ≥ 8 meters, load-bearing capacity ≥ 5 tons / square meter, R&D building floor slab thickness ≥ 0.2 meters) to adapt to the production process or office needs of enterprises (e.g., heavy machinery enterprises need high load-bearing factory buildings, and biopharmaceutical enterprises need sterile clean workshops) to avoid production restrictions caused by substandard building conditions.

[0079] Municipal and supporting element thresholds: These include quantitative standards for basic guarantees such as water, electricity, gas, and transportation (e.g., power supply capacity ≥ 2000KVA, distance from highway entrance ≤ 5 km, sewage treatment capacity ≥ 500 tons / day). These standards are used to determine whether the park's infrastructure can support enterprise operations (e.g., the high requirements of data centers for power stability need to match the park's dual-circuit power grid threshold), ensuring the continuous and stable operation of enterprises after they are put into production.

[0080] It should be noted that the data screening, calculation, and analysis operations involved in the collection and processing of multi-source spatiotemporal data, the construction of enterprise demand feature sets, and the establishment of quantitative demand standards are all conventional methods in the field of data processing. Those skilled in the art can use appropriate methods to complete these tasks according to the actual situation, so they will not be elaborated here.

[0081] S20. Based on the current industrial base data of the target area, construct an industrial ecosystem adaptation model. Calculate the matching degree between the enterprise demand feature set and the industrial ecosystem of the target area through the industrial ecosystem adaptation model. The matching degree includes the degree of industrial chain correlation, the degree of industrial agglomeration fit, and the degree of completeness of supporting facilities. The industrial ecosystem adaptation model aims at industrial ecosystem clustering and outputs candidate parks based on the matching degree.

[0082] The construction of the industrial ecosystem adaptation model includes the following steps:

[0083] S210. Collect enterprise demand feature sets and current industrial base data of the target region, and preprocess them to obtain standardized feature data that can be used for machine learning model training. This specifically includes the following steps:

[0084] S211. Collect the enterprise demand feature set and the current industrial base data of the target area. The current industrial base data includes industrial chain structure data, industrial cluster distribution data and supporting facility data.

[0085] S212. Clean the collected data, including filling in missing values, correcting outliers, and standardizing the data format;

[0086] S213. Based on the relationship between the enterprise demand feature set and the target area industrial ecosystem, perform feature mapping on the cleaned data to generate an initial feature set containing industrial chain association features, industrial agglomeration features and supporting features.

[0087] S214. The initial feature set is standardized by normalizing each feature value to a preset range to obtain standardized feature data that can be directly used for training machine learning models.

[0088] S220. The standardized feature data is used to train an industrial ecosystem adaptation model using a machine learning algorithm to obtain a trained industrial ecosystem adaptation model. This trained model is used to: calculate in real-time the matching degree between the enterprise demand feature set and the target region's industrial ecosystem; and, with the goal of industrial ecosystem clustering, output a ranking result of candidate parks based on the matching degree. Specifically, this includes the following steps:

[0089] S221. Divide the standardized feature data into a training set and a validation set;

[0090] S222. Train an initial industrial ecosystem adaptation model based on the training set. The initial industrial ecosystem adaptation model takes the industrial chain association dimension, industrial agglomeration fit dimension and supporting dimension as the core evaluation dimensions, and sets corresponding quantitative indicators and weight coefficients for each dimension.

[0091] S223. Calculate the comprehensive matching score of the training set through the initial industrial ecosystem adaptation model. The score is the weighted sum of the quantitative indicators of each dimension after standardization.

[0092] S224. Verify the model performance using the verification set, requiring the matching accuracy of the core evaluation dimensions to be no less than a preset threshold, and optimize the weight coefficients and indicator parameters of the industrial ecosystem adaptation model based on the verification results.

[0093] S225. Based on the optimized weight coefficients and index parameters, a trained industry ecosystem adaptation model is generated. The industry ecosystem adaptation model is configured as follows:

[0094] Receive real-time enterprise demand feature sets and target area industrial ecosystem data, and output a comprehensive matching score between the two;

[0095] With the goal of industrial ecosystem clustering, the comprehensive matching score is weighted twice to generate a ranking result of candidate parks. Among them, parks with a high degree of correlation with existing industrial clusters receive additional weight bonuses.

[0096] In this embodiment, as described in step S20 above, an industrial ecosystem adaptation model is constructed based on the current industrial base data of the target region. The core is to quantify the degree of matching between enterprise needs and the regional industrial ecosystem through standardized data processing and machine learning training, such as the Gradient Boosting Tree (XGBoost) algorithm, and finally select candidate parks that meet the goal of industrial clustering. The specific implementation process is as follows:

[0097] (1) Data preprocessing and feature engineering (i.e. step S210)

[0098] In step S211, the collected enterprise demand feature set and the current industrial base data of the target area need to form a complete data chain: the enterprise demand feature set is the structured data constructed in step S10, which includes industrial attributes, fixed asset investment amount, etc.

[0099] The current industrial infrastructure data encompasses three core types of information: industrial chain structure data (such as the number of upstream and downstream enterprises in the region, frequency of cooperation, and the radiation range of core enterprises), industrial cluster distribution data (such as the dominant industry type, enterprise density, and annual output value of each industrial cluster), and supporting facility data (such as water / electricity / gas supply capacity within the park, throughput of surrounding logistics hubs, and the number of research institutions). This data can be obtained through regional industrial big data platforms, park management systems, and statistical yearbooks from relevant departments. Those skilled in the art can extract it through corresponding official websites or government data interfaces.

[0100] In step S212, the collected data is cleaned:

[0101] Missing values ​​are filled using industry mean interpolation (e.g., if "gas capacity" is missing in the data of supporting facilities in a certain park, it is filled with the average gas capacity of parks of the same type) or by extrapolating the data trend of adjacent years.

[0102] Outlier correction is achieved through the 3σ criterion (e.g., if a company's operating indicator is more than three times the standard deviation of the industry average, it is marked as an outlier and replaced with the 95th percentile of the industry).

[0103] The data format is uniformly structured tables (e.g., the "collaboration frequency" is changed from the text description "5 times per month" to the numerical value "5", and the time format is uniformly "YYYY-MM").

[0104] In step S213, feature mapping is performed based on the association relationship:

[0105] Industrial chain linkage characteristics: The industrial chain linkage needs of enterprises (such as "the need for parts suppliers within 5 kilometers") are mapped to regional industrial chain structure data (such as "the number of parts companies within 5 kilometers of the park") as characteristics such as "supply and demand matching degree" and "cooperation distance compliance rate".

[0106] Industrial cluster characteristics: The industrial attributes of enterprises (such as "new energy battery R&D") are mapped with regional industrial cluster distribution data (such as "proportion of new energy industry enterprises in the park") to characteristics such as "industrial type matching degree" and "cluster scale suitability".

[0107] Supporting features: The threshold values ​​of municipal and supporting elements of enterprises (such as "power supply capacity ≥ 1500KVA") are mapped to the supporting facility data of the park (such as "actual power supply capacity of the park 2000KVA") as features such as "facility compliance rate" and "resource redundancy", and finally an initial feature set is formed.

[0108] In step S214, the standardization process uses min-max normalization: each feature value in the initial feature set is mapped to the [0,1] interval (e.g., the original value of "cooperation distance compliance rate" is normalized to 0.5 by 50%, and the original value of "industry type matching degree" is normalized to 0.8 by 80%), eliminating the difference in units and obtaining standardized feature data that can be directly input into the machine learning model.

[0109] (2) Training and optimization of industrial ecosystem adaptation model (i.e. step S220)

[0110] In step S221, the standardized feature data is divided into a training set (for model parameter learning) and a validation set (for model performance evaluation) in a 7:3 ratio, while maintaining consistency in data distribution during the division (e.g., the proportion of each industry type is consistent in the training set and the validation set).

[0111] In step S222, the initial industry ecosystem adaptation model adopts a multi-dimensional weighted evaluation architecture:

[0112] The industrial chain linkage dimension includes quantitative indicators such as "number of upstream and downstream enterprises matched" and "collaboration frequency compliance rate", with a weight coefficient of 0.4 (emphasizing industrial synergy).

[0113] Industrial cluster fit dimension: Quantitative indicators include "density of similar enterprises" and "adaptability of industrial scale", with a weight coefficient set at 0.3 (emphasizing cluster integration);

[0114] Supporting dimensions: Quantitative indicators include "facility threshold compliance rate" and "resource redundancy", with a weighting coefficient of 0.3 (emphasizing basic guarantees).

[0115] The initial weights of each dimension's indicators are determined using the Analytic Hierarchy Process (AHP) to ensure their relevance to the goals of industrial clustering. During the initial construction of the industrial ecosystem adaptation model, the Gradient Boosting Tree (XGBoost) algorithm is simultaneously introduced. Standardized feature data (such as the "collaboration distance achievement rate" of the industrial chain linkage feature and the "density of similar enterprises" of the industrial agglomeration feature) are used as input features. The importance of each feature is calculated using decision tree splitting rules, and the initially set weight coefficients are automatically iteratively optimized (e.g., gradually increasing the importance of the feature "number of upstream and downstream enterprise matches," adjusting its weight from 0.4 to 0.45) to enhance the model's ability to fit the actual industrial ecosystem linkages.

[0116] In step S223, the calculation of the comprehensive matching score relies on the ensemble learning characteristics of the XGBoost algorithm: the algorithm inputs quantitative indicators of each dimension (such as the "number of upstream and downstream matching enterprises" in the industrial chain association dimension and the "density of similar enterprises" in the industrial cluster dimension) into 100 decision trees for parallel calculation. Each decision tree outputs a local matching score for that dimension according to the feature splitting rules (e.g., a certain decision tree predicts a score of 0.85 for the "cooperation frequency compliance rate"). Finally, the algorithm's output layer performs weighted fusion of the local partial values ​​of all decision trees (the fusion weight is negatively correlated with the training error of the tree; the smaller the error, the higher the weight of the tree), generating the comprehensive matching score of the training set. For example, after calculation by the algorithm, the weighted sum of the local partial values ​​of the industrial chain association dimension of a certain park is 0.32, the industrial cluster dimension is 0.21, the supporting dimension is 0.18, and the comprehensive matching score is 0.71.

[0117] In step S224, model validation requires that the matching accuracy of the core evaluation dimensions be no less than 85% (e.g., the match rate between the predicted "cooperation feasibility" of the industrial chain linkage dimension and the actual cooperation records is ≥85%). If the validation fails, the weight coefficients are optimized using the grid search method (e.g., the weight of the industrial chain linkage dimension is adjusted to 0.45), and the indicator parameters are corrected (e.g., the calculation range of "compliance rate of supporting facilities" is expanded).

[0118] In step S224, the model performance verification and optimization process is deeply integrated with the parameter tuning logic of the XGBoost algorithm:

[0119] Validation phase: After inputting the validation set into the model, the algorithm outputs the predicted matching degree of each core evaluation dimension (e.g., the predicted value of the industrial chain correlation dimension is 0.78 vs. the actual value is 0.82), calculates the dimension matching accuracy (required to be ≥85%) and the mean square error of the comprehensive score (required to be ≤0.05).

[0120] Optimization Phase: If validation fails to meet standards, adjust key XGBoost parameters using a grid search method—including maximum tree depth (to control overfitting, range 3-8), learning rate (to control iteration step size, range 0.01-0.1), and minimum leaf node weight (to control tree complexity, range 0.1-0.5). Simultaneously optimize the parameters of each dimension (e.g., increase the calculation factor for "supporting facility compliance rate" to include logistics node data within a 3km radius). For example, when the accuracy of the industrial cluster dimension is only 82%, adjust the maximum tree depth from 5 to 6 and decrease the learning rate from 0.05 to 0.03, improving the dimension accuracy to 87%.

[0121] In step S225, the trained industry ecosystem adaptation model leverages the efficient inference capabilities of the XGBoost algorithm to achieve two core functions:

[0122] Real-time computing: After receiving real-time enterprise demand feature sets (such as "new annual production capacity of 2 million units") and regional industrial ecosystem data (such as "existing supporting production capacity of 5 million units in the park"), the model quickly completes feature matching through a pre-trained decision tree model library (inference time ≤ 0.5 seconds) and outputs a comprehensive matching score (such as 0.82).

[0123] Sorting Output: With the goal of industrial ecosystem clustering, the algorithm performs a second weighting on the comprehensive score—through the feature gain mechanism of XGBoost, an additional gain coefficient is set for the feature of "relevance with existing industrial clusters" (such as the proportion of shared core suppliers and the frequency of historical collaboration) (the feature gain is increased by 20% when the relevance is >60%). Finally, the candidate parks are sorted from high to low according to the weighted score (e.g., Park A score 0.89, Park B score 0.81, Park C score 0.73), ensuring that the sorting results not only meet the needs of enterprises but also strengthen the orientation of industrial clustering.

[0124] Through the above process, the industrial ecosystem adaptation model achieves a precise quantitative match between enterprise needs and regional industrial ecosystems, providing a data-driven decision-making basis for subsequent park selection, and ensuring that candidate parks not only meet the individual needs of enterprises, but also conform to the regional industrial cluster development direction.

[0125] S30. Based on the quantitative demand standard of the enterprise demand feature set, establish a multi-factor matching relationship between the target enterprise and the candidate park in terms of land use space scale and building function parameters; and perform matching verification on the municipal and supporting element thresholds and restrictive elements of the candidate park through a multi-dimensional compliance verification unit, and eliminate parks that do not meet the constraints of the quantitative demand standard.

[0126] In this embodiment, the core of this step is to achieve accurate matching and compliant screening of candidate parks and enterprise needs: on the one hand, based on the quantitative demand standards of the enterprise demand feature set, a multi-element adaptation relationship between the target enterprise and the candidate park in terms of land use space scale and building function parameters is established to clarify the degree of matching between the two; on the other hand, through a multi-dimensional compliance verification unit, the municipal and supporting element thresholds and restrictive elements of the candidate park are checked for matching, and parks that do not meet the constraints of the quantitative demand standards are eliminated, and finally, candidate parks that meet the basic requirements are retained to provide screened alternatives for subsequent site selection scheme output.

[0127] S40. Based on the verification results, output a site selection plan, which includes a recommended ranking of industrial parks, suitable industrial land and industrial buildings, and includes customized resource matching suggestions and risk response strategies for limiting factors that match the enterprise's demand feature set.

[0128] In this embodiment, this step generates a final site selection plan based on the aforementioned verification results. The core is to integrate matching information and risk response strategies to provide enterprises with a comprehensive basis for their entry decisions. The specific content is as follows:

[0129] The site selection plan is based on the results of multiple rounds of verification. First, a ranking of recommended industrial parks is formed. The ranking is determined from high to low based on the comprehensive suitability (such as the suitability score of multiple factors and the industrial ecosystem matching degree). For example, Park A (comprehensive score 0.89), Park B (0.81), and Park C (0.73) are ranked in that order. At the same time, the suitable industrial land and industrial buildings in each recommended park are clearly defined. For example, Plot 3 in Park A (area of ​​50 mu, plot ratio of 1.2) and Standard Factory Building No. 2 (floor height of 9 meters, load-bearing capacity of 15 tons / square meter) are accurately matched with the land space scale and building function requirements of enterprises.

[0130] The plan also includes two core supporting information categories: First, customized resource matching suggestions, providing targeted resource matching solutions based on the characteristics of enterprise needs. For example, for enterprises with supply chain-related needs, it recommends a list of core suppliers within 3 kilometers and logistics cooperation solutions; for enterprises with high energy consumption needs, it matches dual-circuit power grids and energy-saving subsidy strategies. Second, risk management strategies for restrictive factors, proposing solutions for restrictive factors (such as ecological red line constraints and production capacity limits) discovered during the verification process. For example, if a certain industrial park has restrictions on pollution discharge quotas, it suggests that enterprises adopt reclaimed water reuse technology to reduce emissions, or assists in applying for regional pollution discharge rights replacement quotas.

[0131] Through the above content, the site selection plan not only clarifies the specific options for settling in, but also provides a path for resource matching and risk mitigation, realizing a closed loop from "screening results" to "implementation plan".

[0132] S50. Based on feedback data from key industries in the target region, dynamically update the quantitative demand standards and industrial ecosystem adaptation model parameters.

[0133] In this embodiment, this step continuously collects feedback data from key industries in the target area to achieve dynamic iteration of quantitative demand standards and industrial ecosystem adaptation models, ensuring that the site selection method always aligns with the actual development of regional industries. The specific implementation is as follows:

[0134] (1) Core sources and types of feedback data

[0135] Feedback data focuses on the actual operation and development dynamics of key industries in the target region, mainly including three categories:

[0136] Enterprise operation feedback: The actual production data of the resident enterprises (such as land utilization rate, actual building function adaptation rate), operating indicators (such as capacity achievement rate, supply chain collaboration efficiency) and demand deviation records (such as whether the originally set municipal element thresholds meet the actual energy consumption demand).

[0137] Industrial ecosystem change data: changes in the cluster size of key regional industries (such as the number of newly added upstream and downstream enterprises), the carrying capacity pressure of supporting facilities (such as the gap between the actual throughput of transportation hubs and the original threshold), and the impact of strategy adjustments (such as the restrictions on industrial layout imposed by new ecological protection strategies).

[0138] Model prediction bias data: the deviation between the predicted matching degree of the industrial ecosystem adaptation model in the early stage and the actual settlement effect (e.g., the model predicts that the industrial chain correlation degree of a certain park is 0.8, but the actual correlation degree is only 0.6).

[0139] (2) Dynamic updates of quantitative demand standards

[0140] Based on feedback data, the quantitative demand standards set in step S10 were adjusted to ensure that the standards are adapted to the actual needs of enterprises and the regional carrying capacity.

[0141] If most enterprises report that "the original land use space scale standard is too small" (e.g., the actual land use utilization rate reaches 110%), then the land area threshold will be adjusted upwards (e.g., from 50 mu to 60 mu), or the plot ratio parameter will be optimized (e.g., from 1.2 to 1.5).

[0142] If the actual adaptability of building functions is low (e.g., the actual cleanroom level requirement of a certain type of enterprise is 2 levels higher than the original standard), then update the building function parameters (e.g., adjust Class 10000 to Class 1000).

[0143] If municipal and supporting elements frequently experience overload (e.g., the power supply capacity of a certain park often reaches more than 95% of the threshold), then the corresponding threshold should be increased (e.g., from 2000KVA to 2500KVA), or supplementary indicators should be added (e.g., "emergency power supply switching time ≤ 10 seconds" should be added).

[0144] (3) Dynamic optimization of parameters of industrial ecosystem adaptation model

[0145] In response to the model prediction bias identified in the feedback data, the core parameters of the industry ecosystem adaptation model were adjusted to improve the model's prediction accuracy.

[0146] If the feedback shows that "the impact of the industrial chain correlation on the actual entry effect is greater than the original model setting" (e.g., for every 10% increase in correlation, the enterprise survival rate increases by 15%), then increase the weight coefficient of the "industrial chain correlation dimension" in the model (e.g., from 0.4 to 0.5).

[0147] If the prediction error of a certain feature is significant (e.g., the predicted value of "completeness of supporting facilities" deviates from the actual value by more than 15%), then the quantitative index of that feature should be optimized (e.g., changed from "number of facilities" to "actual utilization rate of facilities + response time").

[0148] If there are significant adjustments to the regional industrial strategy (such as the addition of mandatory "green manufacturing" requirements), an "environmental compliance" feature dimension will be added to the model and assigned a corresponding weight (such as 0.2) to ensure that the model is adapted to the latest policy direction.

[0149] Through the aforementioned dynamic update mechanism, the quantitative demand standards always align with the actual operational needs of enterprises, and the industrial ecosystem adaptation model continuously adapts to changes in the regional industrial ecosystem. Ultimately, this enables the self-optimization and iterative upgrading of the site selection method, providing more accurate and adaptable decision support for subsequent enterprise site selection.

[0150] In one embodiment, before step S40, the following step is further included:

[0151] S301. Construct a virtual simulation scene of the target area based on digital twin technology. Input the verified candidate park data, enterprise demand feature set, and current industrial base data of the target area into the virtual simulation scene. Simulate the industrial driving effect, economic benefits, and input-output ratio of supporting measures within a preset period after the target enterprise settles in the candidate park. The industrial driving effect includes the number of upstream and downstream enterprises and the improvement of industrial chain collaboration efficiency. The economic benefits include the annual tax contribution and the number of new jobs. The input-output ratio of supporting measures is the ratio of park infrastructure investment to the enterprise's expected output value.

[0152] In this embodiment, this step relies on digital twin technology to construct a virtual simulation scene of the target area. The core is to predict the long-term effects after enterprises move in through virtual-real mapping. The specific process is as follows:

[0153] Virtual simulation scenario construction: A digital twin foundation is built based on geographic information data (such as terrain, road network, and park layout) and industry data (such as existing enterprise distribution and industrial chain structure) of the target area. A virtual mirror of the park's buildings, infrastructure, and surrounding environment is then recreated using 3D modeling technology, ensuring that the simulation scenario is consistent with the spatial scale and resource distribution of the physical world. Geographic information data can be obtained through a GIS system, and industry data can be obtained by those skilled in the art from the relevant official websites via the internet.

[0154] Input data integration: The verified candidate park data (such as land use space parameters and building function indicators), enterprise demand feature sets (such as production capacity and industrial chain related demand) and target area current industrial base data (such as the number of existing upstream and downstream enterprises and the carrying capacity of supporting facilities) are imported into the virtual simulation scene to establish a data association model (such as the mapping relationship between enterprise production capacity and surrounding logistics capacity).

[0155] Multi-dimensional simulation: Simulates the dynamic changes of the target enterprise within a preset period (e.g., 3 years, 5 years) after its entry into the virtual environment, focusing on outputting three types of indicators, including:

[0156] Industrial driving effect: The number of upstream and downstream enterprises clustered is calculated through the industrial chain transmission algorithm (e.g., it is expected to attract 5 parts suppliers and 2 logistics service providers within 3 years). The improvement of industrial chain collaboration efficiency is measured through the collaboration efficiency model (e.g., the raw material transportation cycle is shortened from 7 days to 3 days, and the efficiency is improved by 57%).

[0157] Economic benefits: Based on the company's fixed asset investment, production capacity planning and regional tax strategies, the annual tax contribution is estimated (e.g., an estimated annual tax payment of 20 million yuan). Based on the company's employment scale and the industrial chain driving effect, the number of new jobs is estimated (e.g., 300 direct jobs and 500 indirect jobs).

[0158] Input-output ratio of supporting measures: The park needs to increase infrastructure investment to meet the needs of enterprises (such as an investment of 5 million yuan to expand the substation and an investment of 3 million yuan to build a new sewage treatment plant). Combined with the expected annual output value of enterprises (such as 500 million yuan), the ratio is calculated as ((500+300) / 50000=1.6%).

[0159] During the simulation, dynamic adjustment parameters (such as market demand fluctuations and regional strategy changes) are set simultaneously to ensure the robustness of the simulation results (e.g., when market demand increases by 20%, the number of new jobs is recalculated to 900).

[0160] S302. Based on the simulation results, prioritize the candidate parks, calculate the weighted comprehensive score of each candidate park in terms of industrial driving effect, economic benefits and input-output ratio of supporting measures within the preset simulation period, and select the candidate park with the best comprehensive score.

[0161] In this embodiment, this step achieves accurate ranking of candidate parks through weighted comprehensive scoring. The core is to transform multi-dimensional simulation indicators into comparable comprehensive scores. The specific process is as follows:

[0162] Indicator weight setting: The weight of each indicator is determined according to the regional development priority (such as industrial upgrading orientation, economic benefit orientation), for example:

[0163] The industrial driving effect has a weight of 0.4 (if the region focuses on the completeness of the industrial chain).

[0164] Economic benefit weighting is 0.35 (if the region prioritizes tax revenue and employment).

[0165] The input-output ratio of supporting measures is weighted at 0.25 (if the region focuses on resource utilization efficiency).

[0166] Comprehensive score calculation: Standardize the simulation index values ​​of each candidate park (e.g., normalize the "number of upstream and downstream enterprises clustered" in the industrial driving effect to the range of 0-1 according to the maximum possible value of the region), and then sum them according to the weights. The formula is:

[0167] Overall score = (Standardized value of industrial driving effect × 0.4) + (Standardized value of economic benefit × 0.35) + (Standardized value of input-output ratio × 0.25).

[0168] For example, if the three standardized values ​​of Park A are 0.9, 0.85, and 0.8, then the comprehensive score = 0.9×0.4 + 0.85×0.35 + 0.8×0.25 = 0.36 + 0.2975 + 0.2 = 0.8575.

[0169] Optimal park selection: Sort by comprehensive score from high to low, and select the candidate park with the highest score (e.g., park A has a score of 0.8575, which is higher than park B's 0.82 and park C's 0.79, and becomes the optimal candidate).

[0170] Through the above steps, a deeper evaluation is achieved, moving from "static adaptation verification" to "dynamic effect simulation." This process considers both the current compatibility between the park and the enterprise, and also predicts the long-term industrial value and economic and social benefits, providing a more comprehensive decision-making basis for step S40 to output a scientific site selection plan.

[0171] In one embodiment, step S10, while constructing the enterprise demand feature set, also includes:

[0172] Construct a community feature set for the target area, which includes at least community population structure data, community public service carrying capacity data, and community environmental sensitive element data;

[0173] Specifically, step S20, which involves calculating the matching degree between the enterprise demand feature set and the target region's industrial ecosystem using the industrial ecosystem adaptation model, includes:

[0174] S201. Calculate the first matching degree between the enterprise demand feature set and the target area industrial ecosystem. The first matching degree is determined based on the industrial chain correlation, industrial agglomeration fit and supporting infrastructure completeness.

[0175] S202. Calculate the second matching degree between the enterprise demand feature set and the community feature set. The second matching degree is determined based on the adaptability of enterprise talent demand and community population structure data, the incremental demand of enterprise operation on community public service carrying capacity data, and the compatibility of enterprise environmental impact and community environmental sensitive element data.

[0176] S203. The first matching degree and the second matching degree are weighted and fused to obtain the final matching degree between the enterprise and the target area, which serves as the basis for the output of candidate parks by the industrial ecosystem adaptation model.

[0177] In this embodiment, by constructing a community feature set and incorporating it into the matching degree calculation, an upgrade from "industry adaptation" to "industry-community collaborative adaptation" is achieved. The specific implementation is as follows:

[0178] (1) Construction logic of community feature set

[0179] Community feature sets serve as implicit constraints for business site selection, focusing on capturing the interaction between regional social resources and business operations.

[0180] Community demographic data: including age distribution (e.g., working-age population accounts for 70%), education level (e.g., population with college degree or above accounts for 35%), and occupational skills composition (e.g., number of skilled workers in manufacturing), used to assess the feasibility of localizing corporate talent recruitment.

[0181] Community public service carrying capacity data includes the number of beds in medical facilities (e.g., 200 beds in community hospitals), the capacity of educational resources (e.g., 3,000 primary school places), and the daily throughput of transportation hubs (e.g., 50,000 daily passenger flows in subway stations), which are used to predict the incremental demand for public services from newly added employees of enterprises.

[0182] Community environmental sensitive element data: including environmental functional zoning (such as whether it is located in an ecological protection red line area), distribution of noise sensitive points (such as the nearest distance to residential areas within 500 meters), and air pollutant emission thresholds (such as the upper limit of sulfur dioxide emissions of 100 tons / year), used to assess the compatibility of corporate environmental impact with the community.

[0183] (2) Calculation dimensions and methods of the second matching degree

[0184] The second matching degree is used to quantitatively assess the synergistic compatibility between enterprises and communities through multiple dimensions:

[0185] Talent demand adaptability:

[0186] Calculation logic: The cosine similarity between the company's job requirements (e.g., 40% of positions are in technical R&D) and the community's population's occupational skills composition (e.g., 30% are skilled workers) is calculated using the following formula:

[0187]

[0188] For example, if a company needs 100 technical personnel and the community currently has 80 similar talents, then the suitability is 80 / 100 = 0.8.

[0189] Incremental demand for public services:

[0190] Calculation logic: Based on the size and structure of the enterprise's employees, predict the new demand for public services (e.g., new medical demand = number of employees × average number of outpatient visits per year), and compare it with the community's carrying capacity. The formula is as follows:

[0191] Incremental demand pressure = new demand / (existing carrying capacity × safety redundancy coefficient).

[0192] For example: If a company adds 500 employees, it is expected that the daily demand for medical treatment will increase by 10 people. The community hospital currently has a daily reception capacity of 200 people (safety redundancy coefficient of 1.2). Then the pressure = 10 / (200×1.2)≈0.042 (the smaller the pressure value, the better the fit).

[0193] Environment compatibility:

[0194] Calculation logic: Compare the enterprise's pollutant emission inventory (e.g., annual COD emissions of 50 tons) with the community's environmentally sensitive element threshold (e.g., remaining regional COD capacity of 100 tons / year). The formula is as follows:

[0195] Compatibility = 1 - (Enterprise emissions / Remaining environmental capacity).

[0196] For example, if a company's noise emission compliance rate is 95% and its distance from residential areas meets the requirements, then the compatibility = 0.95 × 1 = 0.95.

[0197] (3) Double-matching degree weighted fusion mechanism

[0198] The final matching degree is achieved by weighted fusion of the first matching degree (industrial ecosystem) and the second matching degree (community collaboration), using the following formula:

[0199] Final match degree = First match degree × +Second matching degree × .

[0200] in, , These are weighting coefficients, dynamically adjusted according to regional development strategies.

[0201] If the region focuses on industrial agglomeration (such as a national-level economic and technological development zone), then =0.7, =0.3;

[0202] If the region emphasizes the integration of industry and city (such as a new urban area), then =0.5, =0.5;

[0203] If the community environment is sensitive (such as an ecological conservation area), then =0.4, =0.6.

[0204] Through this mechanism, the candidate industrial parks output by the industrial ecosystem adaptation model not only meet the needs of industrial chain collaboration (such as a matching rate of ≥80%), but also take into account the sustainable development of the community (such as public service pressure ≤0.3). For example, a biopharmaceutical company ultimately chose to locate in [location missing]. =0.5、 For a region with a score of 0.5, the final matching degree of candidate park A is 0.8 (industry) × 0.5 + 0.9 (community) × 0.5 = 0.85, which is better than park B (matching degree 0.82), which only has industry matching but has high community pressure.

[0205] This mechanism aims to prevent a decline in employees' quality of life (such as traffic congestion and a shortage of school places) or environmental conflicts (such as noise complaints) due to insufficient community carrying capacity. It also prioritizes selecting parks that complement the community's resources (such as opening corporate training centers to the community and providing green channels for corporate employees through community medical care) and regularly optimizes the community feature set indicators through community feedback data (such as public service satisfaction surveys and environmental monitoring data) to ensure the timeliness of matching degree calculation.

[0206] In one embodiment, step S30 specifically includes:

[0207] S310. Construct a multi-factor quantitative adaptation model. The multi-factor quantitative adaptation model is based on the quantitative demand standard of the enterprise demand feature set and establishes a quantitative mapping relationship between the land use spatial scale parameters, building function parameters and enterprise demand feature set of the candidate park.

[0208] In this embodiment, this step uses the quantitative demand standard of the enterprise demand feature set determined in step S10 as a benchmark to construct a multi-factor quantitative adaptation model. The core is to establish a precise quantitative mapping relationship between candidate park parameters and enterprise needs, such as:

[0209] The land use spatial scale parameters of the candidate parks include the actual area of ​​the plot, plot ratio, plot length-to-width ratio, terrain slope, etc. (these data can be obtained by those skilled in the art through corresponding channels, such as data from the park's land planning archives and GIS system).

[0210] Building functional parameters include factory floor height, ground load-bearing capacity, cleanroom grade, fire protection facility configuration, etc. (these data are all obtainable by those skilled in the art through corresponding channels, such as data from the park building completion acceptance report and structural design drawings).

[0211] The quantitative mapping relationship is achieved through feature association algorithm. For example, the enterprise's requirement of "land area ≥ 50 mu" is mapped to the park's "actual land area of ​​55 mu" as "area matching coefficient 1.1", and the enterprise's requirement of "factory building height ≥ 8 meters" is mapped to the park's "actual building height of 9 meters" as "building height matching coefficient 1.125", so that the abstract requirement is transformed into a computable numerical association.

[0212] The construction of the multi-factor quantitative adaptation model is based on the quantitative demand standards of the enterprise demand feature set. The core is to establish a quantitative correlation between candidate parks and enterprise needs. Specifically, firstly, the quantitative standards related to land use space and building functions in the enterprise demand feature set are clarified (such as land area requirements, floor height requirements, functional zoning ratios, etc.); secondly, the land use space scale parameters (such as actual land area, plot ratio, etc.) and building function parameters (such as building type, usable functional area area, etc.) of candidate parks are sorted out; finally, the above parameters of candidate parks are matched with the quantitative demand standards of enterprises through quantitative methods (such as parameter correspondence, numerical association rules, etc.) to form a clear quantitative mapping relationship—that is, how park parameters correspond to, meet, or deviate from enterprise needs in a specific quantitative expression. This constructs a model framework that can quantitatively measure the adaptation relationship between the two, providing a foundation for subsequent calculation of the adaptation degree through indicators.

[0213] S320. Determine the multi-dimensional adaptation index of the quantitative mapping relationship. The multi-dimensional adaptation index includes at least the land use space adaptation dimension and the building function adaptation dimension. Each dimension adaptation index includes at least one quantitative index parameter and a corresponding weight coefficient.

[0214] In this embodiment, this step clarifies the specific dimensions and indicator system of the assessment to ensure that the assessment direction is consistent with the core needs of the enterprise:

[0215] Land use space adaptation dimension: includes at least one quantitative indicator parameter, such as "area deviation rate" ((actual area of ​​the park - area required by the enterprise) / area required by the enterprise, the smaller the absolute value, the better the adaptation) and "plot ratio fit" (actual plot ratio of the park / plot ratio required by the enterprise, the closer to 1, the better the adaptation). The weight coefficient can be set to 0.4 (set according to the importance of land use requirements to the enterprise).

[0216] Building function adaptation dimension: includes at least one quantitative indicator parameter, such as "floor height standard rate" (1 when the actual floor height of the park is greater than or equal to the floor height required by the enterprise, otherwise 0) and "load-bearing matching degree" (actual load-bearing capacity of the park / load-bearing capacity required by the enterprise, ≥1 is calculated as 1, <1 is calculated according to the actual ratio). The weight coefficient can be set to 0.6 (if the enterprise has higher requirements for building functions).

[0217] The weighting coefficients are determined using the analytic hierarchy process (AHP), taking into account the production characteristics of enterprises (e.g., heavy manufacturing enterprises may increase the weight of "load-bearing matching") and industry-standard practices to ensure that the importance of the indicators is consistent with actual needs.

[0218] S330. Standardize the parameters of each quantitative indicator to generate comparable quantitative values. The standardization process includes, but is not limited to, deviation rate calculation, fit calculation, and compliance rate calculation.

[0219] In this embodiment, this step eliminates the dimensional differences between different indicators through standardization processing, generating directly comparable quantitative values. The specific method includes:

[0220] Deviation rate calculation: Applicable to continuous parameters (such as area, plot ratio), the formula is "(actual value of the park - enterprise demand value) / enterprise demand value", and the result is normalized according to the range of "-1~1" (for example, if the actual area is 55 mu and the demand is 50 mu, the deviation rate = (55-50) / 50 = 0.1, and the normalized value is 0.1).

[0221] Fit degree calculation: Applicable to proportional parameters (such as load-bearing matching degree), directly take the ratio of "actual value of the park / enterprise demand value" (≥1 is calculated as 1), and the result falls in the "0~1" range (for example, actual load-bearing capacity is 10 tons / square meter, demand is 8 tons / square meter, fit degree = 1).

[0222] Compliance rate calculation: Applicable to discrete parameters (such as fire protection facility configuration), calculated as "number of indicators that meet the requirements / total number of indicators" (for example, if 2 out of 3 fire protection indicators meet the requirements, the compliance rate = 2 / 3 ≈ 0.67).

[0223] After standardization, all indicator values ​​are unified to the "0~1" range, providing a comparable basis for subsequent weighted aggregation.

[0224] S340. Based on the weight coefficients, the quantitative values ​​of each dimension are weighted and aggregated to generate a multi-factor comprehensive suitability score.

[0225] In this embodiment, this step, based on the weighting coefficients determined in S320, performs a weighted aggregation of the quantized values ​​of each dimension after standardization in S330. The calculation formula is as follows:

[0226] Overall adaptability score = (quantitative value of land space adaptability dimension × land weight) + (quantitative value of building function adaptability dimension × building weight).

[0227] For example: The standardized value of the land use space adaptation dimension of a candidate park is 0.9 (area deviation rate 0.1, plot ratio matching degree 0.8, take the average), with a weight of 0.4; the standardized value of the building function adaptation dimension is 0.85 (floor height standard rate 1, load-bearing matching degree 0.7, take the average), with a weight of 0.6. Then the comprehensive adaptation score = 0.9×0.4+0.85×0.6=0.36+0.51=0.87.

[0228] S350. Set an adaptation threshold. Incorporate candidate parks that meet the overall adaptation threshold into the subsequent verification process, and remove candidate parks that do not meet the adaptation threshold.

[0229] In this embodiment, this step completes the first round of screening by setting a threshold, ensuring that the parks entering the subsequent processes meet the basic compatibility requirements:

[0230] The fit threshold is set based on the fit score distribution of historical successful site selection cases (e.g., taking the lowest score of historical successful cases, 0.7, as the threshold), or determined through expert review (in combination with industry characteristics, such as the threshold for precision manufacturing companies can be increased to 0.8).

[0231] If the overall suitability score of a candidate park is greater than or equal to the threshold (e.g., 0.87 ≥ 0.7), it will be included in the subsequent verification process; if the score is less than the threshold (e.g., 0.65 < 0.7), it will be directly eliminated.

[0232] Through the above steps, a full-process quantitative assessment is achieved, from "parameter mapping" to "quantitative scoring" and then to "threshold screening," accurately retaining candidate parks that match the company's land use and building needs, laying the foundation for subsequent compliance verification.

[0233] In one embodiment, the current industrial base data of the target area also includes a regional resource feature set, which consists of at least basic support elements, industrial synergy elements, and development potential elements.

[0234] The basic support elements include data on the completeness of infrastructure and supporting public services within the target area;

[0235] The industrial synergy elements include the scale and structure of the industrial clusters already formed in the target area, the density of upstream and downstream enterprise connections, and information on shareable technology R&D platforms.

[0236] The development potential factors include future industry orientation data, land reserve and development planning data, and data on the expected impact of the progress of transportation hub construction on the industrial radiation range.

[0237] In this embodiment, the inclusion of the current industrial base data of the target area into the regional resource feature set further expands the dimensions of industrial ecosystem assessment, enabling a more comprehensive reflection of the matching potential between regional resource endowment and industrial development. Its specific composition and function are as follows:

[0238] (1) Basic guarantee elements

[0239] Basic support elements focus on the region's fundamental resource supply capacity to support industrial operations, which is a prerequisite for enterprises to settle in:

[0240] Infrastructure completeness data: covering quantitative indicators of hardware facilities such as transportation, energy, and water conservancy, such as road network density (road length of 5 kilometers per square kilometer), power supply reliability (annual power outage duration ≤ 8 hours), and sewage treatment plant treatment capacity (daily treatment capacity of 20,000 tons), used to assess whether the region can meet the basic production and operation needs of enterprises;

[0241] Data on public service facilities includes the supply of talent apartments (e.g., 5,000 units), the number of vocational skills training institutions (e.g., 3 national-level high-skilled talent training bases), and the coverage of legal service institutions (e.g., 1 per 10 square kilometers), reflecting the region's ability to support the living and development needs of enterprise employees.

[0242] This type of data mainly comes from the annual reports of municipal management departments and GIS spatial databases. It is a key input for calculating the "completeness of supporting facilities" (the core indicator of the first matching degree in step S201). For example, if the infrastructure completeness data compliance rate of a certain park is 85%, it will directly improve its basic adaptability to the needs of enterprises.

[0243] (2) Industrial synergy factors

[0244] Industrial synergy elements focus on the synergistic potential of the existing regional industrial ecosystem and serve as a core reference for enterprises to integrate into the local industrial network.

[0245] The scale and structure of existing industrial clusters: For example, the annual output value of the electronic information industry cluster reaches 50 billion yuan, covering sub-segments such as chip design, terminal manufacturing, and software services. This can be used to determine the complementarity between enterprises and existing clusters (for example, terminal manufacturing enterprises can rely on chip suppliers within the cluster to reduce costs).

[0246] Upstream and downstream enterprise linkage density: quantified by "number of core suppliers within a 30-kilometer radius" and "percentage of annual collaborative transaction volume" (e.g., a certain auto parts company's annual collaborative volume with local vehicle manufacturers accounts for 60%), which directly affects the calculation of the industrial chain linkage.

[0247] Shareable technology R&D platform information: including the number of national key laboratories (e.g., 2), the annual transformation volume of industry-university-research cooperation projects (e.g., 10 projects / year), etc., reflecting the region's ability to support enterprises' technological innovation needs.

[0248] This type of data comes from the cluster development report and enterprise collaboration ledger of the industrial park management bureau. It is the core basis for calculating "industrial chain correlation" and "industrial agglomeration fit" in the first matching degree. For example, if the industrial synergy factor score of a certain park is 0.85, its matching degree with enterprises with industrial chain demand will be significantly improved.

[0249] (3) Factors related to development potential

[0250] The development potential factors focus on the evolutionary trends of future regional resource supply and industrial layout, providing a forward-looking assessment for the long-term development of enterprises:

[0251] Future industry guidance data: Based on the industry plans released by relevant departments, the data clarifies the key industries to be cultivated in the region (such as new energy and artificial intelligence) and the areas to be supported by strategies (such as providing R&D subsidies to high-tech enterprises), which is used to judge the fit between enterprises and the region's long-term development strategy.

[0252] Land reserve and development planning data: including the area of ​​industrial land available for transfer (e.g., 1,000 mu), the space for adjustment of planned plot ratio (e.g., from 1.2 to 2.0), etc., reflecting whether the region can meet the expansion needs of enterprises;

[0253] The expected impact of the progress of transportation hub construction on the industrial radiation range: For example, the planned high-speed rail station is expected to open to traffic in 2026. After completion, the regional radiation radius will expand from 50 kilometers to 100 kilometers, which will directly affect the prediction of enterprises' logistics costs and market coverage capabilities.

[0254] This type of data mainly comes from the land use planning of the Natural Resources Bureau and the major project database of the National Development and Reform Commission. Its role is reflected in the dynamic correction of the first matching degree. For example, due to the construction of a transportation hub, the industrial radiation range of a certain park will expand by 50% in the next 3 years, and its matching degree with logistics-dependent enterprises can be increased by 10%.

[0255] The inclusion of regional resource characteristic sets enables the industrial ecosystem adaptation model to not only assess "current adaptability" but also take into account "long-term sustainability":

[0256] Basic support elements ensure that enterprises can "settle down," industrial synergy elements ensure that enterprises can "integrate," and development potential elements ensure that enterprises can "grow big."

[0257] In the first matching degree calculation, these data are weighted and incorporated into indicators such as "completeness of supporting facilities" and "industrial chain relevance" (e.g., basic guarantee elements weight 0.3, industrial synergy elements weight 0.5, development potential elements weight 0.2), so that the final matching degree is more in line with the actual regional resources and the needs of enterprises throughout their entire life cycle.

[0258] In one embodiment, after step S50, the method further includes:

[0259] Step S60: Construct a dynamic adaptation and adjustment mechanism. This mechanism aims to build a dynamic optimization capability for the entire lifecycle of site selection solutions. Through real-time monitoring, triggered recalculation, dynamic adjustment, and difference verification, it ensures that site selection decisions are always synchronized with changes in enterprise needs and the regional industrial ecosystem. The specific implementation is as follows:

[0260] S610. Set a dynamic monitoring cycle and collect real-time change data of enterprise demand feature set and dynamic update data of target area industrial ecosystem.

[0261] In this embodiment, this step captures dynamic changes in enterprises and regions through routine monitoring, providing a data foundation for the adjustment mechanism:

[0262] Dynamic monitoring cycle setting: The cycle is determined based on industry characteristics and the rate of change in regional industries (e.g., heavy industry enterprises are set to quarterly monitoring, high-tech enterprises are set to monthly monitoring, and real-time monitoring is activated when there is a sudden adjustment in strategy).

[0263] Data types collected:

[0264] Real-time change data of enterprise demand characteristics: including production capacity adjustment (e.g., from 1 million units to 1.5 million units per year), process demand upgrade (e.g., cleanroom level is upgraded from Class 1000 to Class 100), and talent demand changes (e.g., adding 50 R&D personnel).

[0265] Dynamic updates of the industrial ecosystem in the target area include: new supply chain enterprises (such as two new core suppliers within 30 kilometers), upgraded supporting facilities (such as a new 110KV substation in the park), and strategic adjustments (such as stricter environmental emission standards).

[0266] S620. When the key indicators of the enterprise demand feature set are detected to change beyond the preset threshold or the structural indicators of the regional industrial ecosystem are adjusted, the industrial ecosystem adaptation model is recalculated.

[0267] In this embodiment, this step explicitly defines the threshold and scenario that triggers dynamic adjustment to avoid invalid recalculation:

[0268] Thresholds for changes in key indicators of enterprise demand: set based on industry stability (e.g., changes in fixed asset investment ≥20%, adjustments to core process parameters ≥1 level, increases in talent demand ≥30%). For example, if an auto parts company plans to increase its annual production capacity from 500,000 sets to 700,000 sets (an increase of 40% > 20%), adjustments will be triggered.

[0269] Adjustments to regional industrial ecosystem structural indicators include changes in industrial planning direction (such as a shift from "traditional manufacturing" to "intelligent manufacturing"), major infrastructure changes (such as the addition of a high-speed rail hub that alters the logistics coverage area), and upgraded environmental constraints (such as the addition of PM2.5 emission limits). For example, a region's release of a "prohibition of new chemical production capacity" policy directly triggers recalculation for relevant enterprises.

[0270] The triggering logic is automatically determined by the rule engine, and the subsequent adjustment process is initiated when any condition is met.

[0271] S630. Based on the collected dynamically updated data, re-execute the matching degree calculation step and re-verify the matching degree. Eliminate parks that do not meet the quantitative requirement standard constraints, generate a dynamically adjusted candidate park ranking, and output a matching degree change analysis report.

[0272] In this embodiment, this step updates the evaluation results based on the latest data to ensure the suitability of candidate parks:

[0273] Recalculate the matching degree: Call the industrial ecosystem adaptation model, input the enterprise's real-time needs (such as adding "annual electricity consumption ≥ 15 million kWh") and regional dynamic data (such as the park's power supply capacity has been upgraded to 2000 KVA), and recalculate the first matching degree (industrial chain correlation, etc.) and the second matching degree (community adaptability, etc.).

[0274] Re-matching verification: Reuse the multi-dimensional compliance verification unit of step S30 to re-verify the municipal elements (such as new sewage treatment capacity) and restrictive elements (such as the latest ecological red line) of the candidate parks, and remove parks that fail to meet the standards due to changes (such as a park that has been included in the ecological red line due to strategy adjustment, and is directly removed).

[0275] Output results: Generate a dynamically adjusted ranking of candidate parks (e.g., the park originally ranked 3rd is promoted to 1st due to supporting facilities upgrades), and output a matching degree change analysis report (including the reasons for the change, such as "the matching degree of park A increased from 0.89 to 0.92 due to the addition of 2 upstream suppliers").

[0276] S640. Compare the dynamically adjusted candidate park ranking with the recommended park ranking in the initial output site selection scheme, calculate the difference between the two, and if the difference exceeds a preset threshold, output the optimized site selection scheme, which includes:

[0277] If the company has not yet settled in, we will directly update the recommended park ranking and supporting resource matching suggestions.

[0278] If the enterprise has already settled in, provide resource adaptation and optimization strategies or phased relocation and transition plans based on the existing park.

[0279] In this embodiment, this step determines whether to update the site selection scheme based on the degree of difference, balancing decision-making stability and flexibility:

[0280] Difference calculation: quantified by "rank change rate" (e.g., 3 out of the original top 5 parks changed, change rate 60%), or by calculating the mean square error of the comprehensive score (e.g., the mean difference between the dynamic ranking and the initial ranking is >0.1).

[0281] Preset threshold setting: Determined according to the company's development stage (e.g., 30% for startups and 50% for mature companies) to avoid frequent adjustments affecting operations;

[0282] Scenario-specific output solutions:

[0283] If the company has not yet settled in: directly update the recommended park ranking (e.g., adjust park A to the first choice), and simultaneously update the matching suggestions for supporting resources (e.g., add "sign cooperation agreements with 2 new suppliers in park A").

[0284] If the enterprise has already settled in: provide resource adaptation and optimization strategies (such as coordinating the connection of temporary power generation equipment when the existing park's power supply is insufficient) or phased relocation and transition plans (such as completing the relocation to Park B within 6 months, while retaining the existing factory buildings as transitional warehouses).

[0285] Through the above mechanism, the dynamic adaptation and adjustment mechanism has upgraded the site selection decision from "one-time static plan" to "full-cycle dynamic optimization", ensuring the long-term compatibility between enterprises and regional resources.

[0286] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0287] In one embodiment, a smart location selection system based on a spatiotemporal data platform is provided, which corresponds to the smart location selection method based on a spatiotemporal data platform described in the above embodiments. This smart location selection system based on a spatiotemporal data platform includes:

[0288] The multi-source data acquisition module is used to collect multi-source spatiotemporal data of key industries in the target area, and to construct an enterprise demand feature set based on the multi-source spatiotemporal data. The enterprise demand feature set includes at least industry attributes, fixed asset investment amount, industrial chain related demand and production process demand. Based on the enterprise demand feature set, a quantitative demand standard is established. The quantitative demand standard includes at least land use scale, building function parameters and municipal and supporting element thresholds.

[0289] The candidate park generation module is used to construct an industrial ecosystem adaptation model based on the current industrial base data of the target area. The industrial ecosystem adaptation model calculates the matching degree between the enterprise demand feature set and the industrial ecosystem of the target area. The matching degree includes the industrial chain correlation, industrial agglomeration fit and supporting facility completeness. The industrial ecosystem adaptation model aims at industrial ecosystem clustering and outputs candidate parks according to the matching degree.

[0290] The candidate park screening module is used to establish a multi-factor matching relationship between the target enterprise and the candidate park in terms of land use space scale and building function parameters based on the quantitative demand standards of the enterprise demand feature set; and to perform matching verification on the municipal and supporting element thresholds and restrictive elements of the candidate park through a multi-dimensional compliance verification unit, and to eliminate parks that do not meet the constraints of the quantitative demand standards.

[0291] The site selection scheme generation module is used to output a site selection scheme based on the verification results. The site selection scheme includes a recommended ranking of the parks to be settled in, suitable industrial land and industrial buildings, and includes customized resource matching suggestions and risk response strategies for restrictive factors that match the enterprise's demand feature set.

[0292] The dynamic optimization module is used to dynamically update the quantitative demand standards and industrial ecosystem adaptation model parameters based on feedback data from key industries in the target region.

[0293] For specific limitations regarding the intelligent location system based on a spatiotemporal data platform, please refer to the limitations of the intelligent location method based on a spatiotemporal data platform mentioned above, which will not be repeated here. Each module in the aforementioned intelligent location system based on a spatiotemporal data platform can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0294] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 2As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database is used for data storage, data processing, and data analysis. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a smart addressing method based on a spatiotemporal data platform.

[0295] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a smart addressing method based on a spatiotemporal data platform.

[0296] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a smart addressing method based on a spatiotemporal data platform.

[0297] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0298] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0299] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A smart site selection method based on a space-time data platform, characterized in that, Comprising the following steps: Collecting multi-source spatio-temporal data of target area key industry categories, constructing enterprise demand feature set based on the multi-source spatio-temporal data, the enterprise demand feature set at least including industry attributes, fixed asset investment, industry chain associated demand and production process demand; establishing quantitative demand standard based on the enterprise demand feature set, the quantitative demand standard at least including land space scale, building function parameter, municipal and supporting element threshold; wherein, while constructing the enterprise demand feature set, it also includes: constructing community feature set of the target area, the community feature set at least containing community population structure data, community public service carrying capacity data and community environmental sensitive element data; Based on the current industrial base data of the target area, an industrial ecological adaptation model is constructed, and the matching degree of the enterprise demand feature set and the industrial ecology of the target area is calculated through the industrial ecological adaptation model, the matching degree including industry chain correlation degree, industry agglomeration fit degree and supporting facility completeness; the industrial ecological adaptation model takes industrial ecological clustering as the goal, and outputs candidate parks according to the matching degree; Based on the quantitative demand standard of the enterprise demand feature set, a multi-element adaptation relationship of land space scale and building function parameter between the target enterprise and the candidate park is established; the municipal and supporting element threshold and the restrictive element of the candidate park are matched and verified by the multi-dimensional compliance verification unit, and the park that does not meet the constraint conditions of the quantitative demand standard is eliminated; Based on the verification result, an site selection scheme is output, the site selection scheme including recommended park entry ranking, adapted industrial land and industrial building, and containing customized resource matching suggestions and restrictive element risk response strategies matched with the enterprise demand feature set; According to the feedback data of the target area key industry categories, dynamically update the quantitative demand standard and the industrial ecological adaptation model parameters; Before the step of outputting the site selection scheme based on the verification result, the following steps are further included: Based on digital twin technology, a virtual simulation scene of the target area is constructed, the verified candidate park data, the enterprise demand feature set and the current industrial base data of the target area are input into the virtual simulation scene, and the industrial driving effect, economic benefit and supporting measure input-output ratio within a preset period after the target enterprise enters the candidate park are simulated; wherein, the industrial driving effect includes the number of upstream and downstream enterprise agglomeration and the improvement range of industry chain synergy efficiency, the economic benefit includes annual tax contribution value and new employment positions, and the supporting measure input-output ratio is the ratio of park infrastructure input to enterprise expected output value; Based on the simulation result, the candidate parks are prioritized, the weighted comprehensive score of the industrial driving effect, economic benefit and supporting measure input-output ratio of each candidate park within the preset period of simulation simulation is calculated, and the candidate park with the optimal comprehensive score is selected; In the step of calculating the matching degree of the enterprise demand feature set and the industrial ecology of the target area through the industrial ecological adaptation model, it specifically includes: Calculate a first matching degree of the enterprise demand feature set and the target regional industry ecology, the first matching degree being determined based on an industry chain correlation degree, an industry cluster fitting degree, and a supporting facility completeness degree; Calculate a second matching degree of the enterprise demand feature set and the community feature set, the second matching degree being determined based on an adaptability of enterprise talent demand and community population structure data, an incremental demand of enterprise operation on community public service carrying capacity data, and a compatibility of enterprise environmental impact and community environmental sensitive element data; Weight and fuse the first matching degree and the second matching degree to obtain a final matching degree of the enterprise and the target region, serving as a basis for outputting a candidate park by the industry ecology adaptation model.

2. The smart site selection method based on the space-time data platform of claim 1, wherein, In the step of establishing a multi-element adaptation relationship of land use spatial scale and building function parameters of the target enterprise and the candidate park based on the quantitative demand standard of the enterprise demand feature set, the step specifically includes: Construct a multi-element quantitative adaptation model, which establishes a quantitative mapping relationship between the land use spatial scale parameter, the building function parameter of the candidate park, and the enterprise demand feature set based on the quantitative demand standard of the enterprise demand feature set; Determine a multi-dimensional adaptation index of the quantitative mapping relationship, the multi-dimensional adaptation index including at least a land use spatial adaptation dimension and a building function adaptation dimension, each dimension adaptation index containing at least one quantitative index parameter and a corresponding weight coefficient; Standardize each quantitative index parameter to generate comparable quantitative values, the standardization including deviation rate calculation, fitting degree calculation, and standard reaching rate calculation; Weight and aggregate the quantitative values of each dimension based on the weight coefficient to generate a multi-element comprehensive adaptation degree score; Set an adaptation degree threshold, and include the candidate park with a comprehensive adaptation degree score reaching the adaptation degree threshold into a subsequent verification process, and exclude the candidate park not reaching the adaptation degree threshold.

3. The smart site selection method based on the space-time data platform of claim 1, wherein, In the step of constructing an industry ecology adaptation model based on the current industrial foundation data of the target region, and calculating a matching degree of the enterprise demand feature set and the target regional industry ecology through the industry ecology adaptation model, the construction of the industry ecology adaptation model specifically includes the following steps: Collect and preprocess the enterprise demand feature set and the current industrial foundation data of the target region to obtain standardized feature data for machine learning model training; Train the industry ecology adaptation model through a machine learning algorithm based on the standardized feature data to obtain a trained industry ecology adaptation model, which is used for: Real-time calculation of the matching degree of the enterprise demand feature set and the target regional industry ecology; Output a candidate park ranking result according to the matching degree, with the goal of industry ecology clustering.

4. The smart site selection method based on the space-time data platform of claim 3, wherein, In the step of collecting and preprocessing the enterprise demand feature set and the current industrial foundation data of the target region to obtain standardized feature data for machine learning model training, the step specifically includes: Collect the enterprise demand feature set and the current industrial foundation data of the target region, the current industrial foundation data covering industry chain structure data, industry cluster distribution data, and supporting facility data; Clean the collected data, including missing value filling, abnormal value correction, and data format unification; Based on the association between the enterprise demand feature set and the target regional industrial ecology, the cleaned data is mapped to generate an initial feature set containing industrial chain association features, industrial agglomeration features, and supporting feature features; The initial feature set is standardized to normalize each feature value to a preset value range, obtaining standardized feature data that can be directly used for machine learning model training.

5. The smart site selection method based on the space-time data platform of claim 4, wherein, The step of training an industrial ecology adaptation model based on the standardized feature data by a machine learning algorithm includes: Divide the standardized feature data into a training set and a validation set; Train an initial industrial ecology adaptation model based on the training set, which takes industrial chain association dimensions, industrial agglomeration compatibility dimensions, and supporting dimensions as core evaluation dimensions, and sets corresponding quantitative indicators and weight coefficients for each dimension; Calculate the comprehensive matching score of the training set using the initial industrial ecology adaptation model, which is the weighted sum of the standardized quantitative indicators of each dimension; Verify the model performance using the validation set, requiring a matching accuracy of the core evaluation dimensions to be no less than a preset threshold, and optimizing the weight coefficients and indicator parameters of the industrial ecology adaptation model based on the verification results; Based on the optimized weight coefficients and indicator parameters, generate a trained industrial ecology adaptation model, which is configured to: Receive real-time enterprise demand feature sets and target regional industrial ecology data, and output the comprehensive matching score of the two; For the purpose of industrial ecology clustering, the comprehensive matching score is calculated again to generate a ranking result of candidate parks, and parks with high correlation to existing industrial clusters receive additional weight bonuses.

6. A smart site selection system based on a space-time data platform, for implementing the steps of a smart site selection method based on a space-time data platform according to any one of claims 1-5, characterized in that, It includes: A multi-source data acquisition module is used to acquire multi-source spatio-temporal data of key industries in the target region, and to construct an enterprise demand feature set based on the multi-source spatio-temporal data, the enterprise demand feature set at least including industrial attributes, fixed asset investment, industrial chain association demand and production process demand; a quantitative demand standard is established based on the enterprise demand feature set, the quantitative demand standard at least including land space scale, building function parameter, municipal and supporting element threshold; A candidate park generation module is used to construct an industrial ecology adaptation model based on the current industrial foundation data of the target region, and to calculate the matching degree of the enterprise demand feature set and the target regional industrial ecology through the industrial ecology adaptation model, the matching degree including industrial chain association degree, industrial agglomeration compatibility degree and supporting facility completeness degree; the industrial ecology adaptation model aims to industrial ecology clustering, and outputs candidate parks according to the matching degree; A candidate park screening module is used to establish a multi-element adaptation relationship between the land space scale, building function parameter of the target enterprise and the candidate park based on the quantitative demand standard of the enterprise demand feature set; the municipal and supporting element threshold, restrictive elements of the candidate park are matched and verified by a multi-dimensional compliance verification unit, and parks that do not meet the quantitative demand standard constraints are excluded. The site selection scheme generation module is configured to output a site selection scheme based on the check result, the site selection scheme including recommended park entry ranking, adapted industrial land and industrial buildings, and containing customized resource matching suggestions and restrictive factor risk response strategies matched with the enterprise demand feature set; The dynamic optimization module is configured to dynamically update the quantitative demand standard and the industrial ecological adaptation model parameter according to the feedback data of the target area key industry category.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the intelligent site selection method based on the spatiotemporal data platform according to any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to implement the steps of the intelligent site selection method based on the spatiotemporal data platform according to any one of claims 1-5.

Images