City built environment intelligent evaluation system based on multi-source data fusion

Abstract

The invention relates to the technical field of city construction, in particular to a city built-up environment intelligent evaluation system based on multi-source data fusion, which comprises multi-source data acquisition and processing, a city update potential recognition model, cross-scale quantitative evaluation system construction and built-up environment and city vitality nonlinear interaction mechanism analysis. The construction of the cross-scale quantitative evaluation system specifically comprises the step of establishing a comprehensive evaluation model of facility density, population matching degree and traffic network structure in combination with an AHP-entropy weight method and spatial syntactic analysis. According to the invention, through multi-source data fusion, cross-scale quantitative evaluation, machine learning modeling and interpretability analysis, an accurate, efficient and generalizable city update decision support system is constructed.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban planning, and in particular to a kind of urban built environment wisdom evaluation system based on multi-source data fusion. BACKGROUND

[0002] In the existing urban renewal research and practice, when formulating the renewal scheme, planners and managers often rely on traditional statistical indicators, such as population size, land structure, etc. The analysis of the relationship between urban vitality and built environment often stays at the static, linear and single scale level. In recent years, with the development of big data, cloud computing and artificial intelligence, the application of multi-source spatial information in the field of urban planning has become increasingly mature. By fusing geographic information (GIS), remote sensing images, street view images, POI data, traffic flow and social media check-in, etc. Multi-modal data, the dynamic description of urban spatial pattern, resident activity pattern and public service level can be realized.

[0003] Problems existing in the prior art: (1) Low potential identification accuracy: Lack of multi-source heterogeneous data fusion method for urban renewal, leading to insufficient accuracy of update potential area identification and not enough precision of priority division.

[0004] (2) Fragmentation of evaluation system: Most studies only construct evaluation indicators at a single scale, making it difficult to realize the coupling analysis of micro, meso and macro, resulting in systematic bias in the evaluation results.

[0005] (3) Non-transparent mechanism: Traditional linear statistical models cannot reveal the non-linear, high-order interaction effects between built environment elements and urban vitality, resulting in "black box effect", lack of explainability, and difficulty in guiding optimization scheme.

[0006] (4) Insufficient achievement transformation: The evaluation results and planning practice are not well connected, and there is a lack of visual and interactive decision support system, which affects the popularization and application of technology in actual urban renewal projects. SUMMARY

[0007] The purpose of the present application is to solve the problems existing in the prior art and to provide a kind of urban built environment wisdom evaluation system based on multi-source data fusion.

[0008] In order to achieve the above purpose, the technical scheme adopted by the present application is as follows: A kind of urban built environment wisdom evaluation system based on multi-source data fusion is designed, comprising: Multi-source data acquisition and processing, urban renewal potential identification model, cross-scale quantitative evaluation system construction, built environment and urban vitality non-linear interaction mechanism analysis; The cross-scale quantitative evaluation system construction is specifically: At the micro scale, we use street view image semantic segmentation technology to extract refined indicators such as greening rate and street interface continuity. At the meso scale, we combine building density, functional mixing degree and street accessibility to analyze the spatial performance of the block. At a macro scale, indicators such as nighttime light data, NDVI, Baidu heatmap, and social media sentiment analysis are integrated to assess regional economic vitality and ecological benefits.

[0009] Preferably, the multi-source data acquisition and processing specifically involves obtaining data from various channels such as Geographic Information Systems (GIS), socioeconomic statistics, environmental monitoring, building attributes, traffic flow, resident behavior, social media check-ins, satellite remote sensing imagery, and mobile phone signaling. Through data cleaning, format standardization, spatiotemporal alignment, and semantic fusion, a unified data warehouse or data lake is constructed to provide a high-quality and timely data foundation for subsequent analysis.

[0010] Preferably, the urban renewal potential identification model is based on GIS spatial analysis technology and machine learning algorithms to identify inefficient land use, infrastructure coverage blind spots, and urban vitality gaps, thereby achieving accurate positioning of renewal potential areas.

[0011] Preferably, the analysis of the nonlinear interaction mechanism between the built environment and urban vitality specifically involves using the XGBoost algorithm to establish a predictive model of built environment elements and urban vitality indicators, capturing the nonlinear relationships and higher-order interaction effects between variables. The SHAP interpretability method is introduced to quantify the marginal contribution and synergistic effect of each feature, clarifying the threshold rules of facility layout and spatial synergy.

[0012] Preferably, the provision of multi-scheme comparison and quantitative evaluation reports enables data-driven planning decisions, which are then validated in pilot projects such as the Hefei East Gate Transportation Compound plot, forming a replicable and scalable application model.

[0013] The present invention proposes an intelligent assessment system for urban built environment based on multi-source data fusion. The beneficial effects are as follows: This intelligent assessment system for urban built environment based on multi-source data fusion constructs an accurate, efficient, and scalable decision support system for urban renewal through multi-source data fusion, cross-scale quantitative evaluation, machine learning modeling, and interpretability analysis. Attached Figure Description

[0014] Figure 1 This is a system block diagram of a smart assessment system for urban built environment based on multi-source data fusion, which includes data acquisition, inefficient land use identification, and urban renewal and transformation potential evaluation.

[0015] Figure 2This is a system block diagram of the construction, data processing and integration of a quantitative evaluation system for an intelligent assessment system of urban built environment based on multi-source data fusion proposed in this invention.

[0016] Figure 3 This is a system block diagram of a smart assessment system for urban built environment based on multi-source data fusion proposed in this invention, which includes built environment data, urban vitality data, model construction, and result interpretation and analysis.

[0017] Figure 4 This is a system block diagram of a smart assessment system for urban built environment based on multi-source data fusion proposed in this invention, which includes on-site simulation, scheme comparison, and update effect evaluation. Detailed Implementation

[0018] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0019] Reference Figures 1-2 A smart assessment system for urban built environment based on multi-source data fusion, comprising: Multi-source data acquisition and processing, urban renewal potential identification model, construction of cross-scale quantitative evaluation system, and analysis of the nonlinear interaction mechanism between built environment and urban vitality; The construction of the cross-scale quantitative evaluation system is specifically as follows: At the micro scale, we use street view image semantic segmentation technology to extract refined indicators such as greening rate and street interface continuity. At the meso scale, we combine building density, functional mixing degree and street accessibility to analyze the spatial performance of the block. At a macro scale, indicators such as nighttime light remote sensing, NDVI, and social media sentiment analysis are integrated to assess regional economic vitality and ecological benefits.

[0020] The evaluation system is systematized: it enables coordinated evaluation across multiple scales, including micro, meso, and macro levels, to avoid systemic misjudgments caused by a single scale.

[0021] The multi-source data acquisition and processing specifically involves acquiring data from various channels such as Geographic Information Systems (GIS), socioeconomic statistics, environmental monitoring, building attributes, traffic flow, resident behavior, social media check-ins, satellite remote sensing images, and mobile phone signaling. Through data cleaning, format standardization, spatiotemporal alignment, and semantic fusion, a unified data warehouse or data lake is constructed to provide a high-quality and timely data foundation for subsequent analysis.

[0022] Significantly improved accuracy: Through the spatiotemporal fusion of multi-source heterogeneous data, potential areas for urban renewal can be identified comprehensively and precisely, and the prioritization can be more scientific.

[0023] The urban renewal potential identification model is specifically based on GIS spatial analysis technology and machine learning algorithms to identify inefficient land use, infrastructure coverage blind spots, and urban vitality gaps, thereby achieving accurate positioning of renewal potential areas.

[0024] The analysis of the nonlinear interaction mechanism between the built environment and urban vitality specifically involves using the XGBoost algorithm to establish a predictive model of built environment elements and urban vitality indicators, capturing the nonlinear relationships and higher-order interaction effects between variables, introducing the SHAP interpretability method to quantify the marginal contribution and synergistic effect of each feature, clarifying the threshold law of facility layout and spatial coordination, and making the mechanism analysis transparent: using the XGBoost-SHAP two-layer analytical framework, it breaks through the explanatory power limitations of traditional linear models and reveals the action path and threshold law of key elements.

[0025] The proposed solution provides multiple alternatives and quantitative evaluation reports, enabling data-driven planning decisions. This has been validated in pilot projects such as the Hefei East Gate Transportation Compound site, forming a replicable and scalable application model. The results can be directly used for real-time simulation and alternative selection in various urban renewal scenarios. The methods and platform are universal and highly practical, allowing for rapid deployment in different types of cities and renewal projects, contributing to refined governance and sustainable development, and possessing high promotional value.

[0026] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A city built environment intelligent evaluation system based on multi-source data fusion, characterized in that, The application relates to a data-driven urban renewal planning method. The method comprises the following steps: Multi-source data collection and processing, urban renewal potential identification model, cross-scale quantitative evaluation system construction, nonlinear interaction mechanism analysis of built environment and urban vitality; The cross-scale quantitative evaluation system construction is specifically as follows: On the micro scale, semantic segmentation technology of street view images is used to extract fine indicators such as greening rate and street interface continuity; on the meso scale, the spatial performance of blocks is analyzed by combining building density, functional mixing degree and street accessibility; on the macro scale, regional economic vitality and ecological benefits are evaluated by integrating night light data, NDVI, Baidu heat map and social media sentiment analysis and other indicators. 2.The urban built environment intelligent evaluation system based on multi-source data fusion according to claim 1, wherein, The multi-source data collection and processing is specifically as follows: data is obtained from various channels such as geographic information systems (GIS), social and economic statistics, environmental monitoring, building attributes, traffic flow, resident behavior, social media check-in, satellite remote sensing images and mobile phone signaling. Through data cleaning, format standardization, time and space alignment and semantic fusion and other processing steps, a unified data warehouse or data lake is constructed to provide high-quality and time-efficient data basis for subsequent analysis. 3.The urban built environment intelligent evaluation system based on multi-source data fusion of claim 1, wherein, The urban renewal potential identification model is specifically as follows: based on GIS spatial analysis technology and machine learning algorithm, inefficient land, facility coverage blind area and urban vitality depression are identified to realize accurate positioning of the renewal potential area. 4.The urban built environment intelligent evaluation system based on multi-source data fusion of claim 1, wherein, The nonlinear interaction mechanism analysis of built environment and urban vitality is specifically as follows: an XGBoost algorithm is used to establish a prediction model of built environment elements and urban vitality indicators to capture the nonlinear relationship and high-order interaction effect between variables. The SHAP interpretability method is introduced to quantify the marginal contribution and synergistic effect of each feature and to clarify the threshold law of facility layout and spatial coordination. 5.The urban built environment intelligent evaluation system based on multi-source data fusion of claim 1, wherein, The method provides multi-scheme comparison and quantitative evaluation report to realize data-driven planning decision, is verified in some actual projects and forms a replicable and generalizable application mode.

Images