Environmental health efficiency dynamic evaluation and diagnosis system established based on multi-source data fusion
By constructing a dynamic assessment and diagnosis system for the health effectiveness of the built environment through multi-source data fusion, the problems of data silos and disconnect between diagnosis and optimization in the assessment of the built environment have been solved. It has achieved spatiotemporal alignment and refined assessment of multi-source data in special regions such as plateaus, forming an intelligent closed loop and improving the accuracy and timeliness of the assessment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-20
- Publication Date
- 2026-04-14
AI Technical Summary
In existing technologies, the assessment of the built environment lacks dynamic coupling between multiple environmental factors and human-centered responses, suffers from severe data silos, disconnects diagnosis and optimization, has poor regional applicability, and makes it difficult to achieve spatiotemporal alignment and refined assessment of multi-source data.
A multi-source data fusion-based dynamic assessment and diagnosis system for environmental health performance is constructed, comprising a multi-source data perception layer, a data fusion and processing layer, a dynamic assessment and diagnosis layer for health performance, and an intelligent optimization and feedback layer. Through multi-source data perception, spatiotemporal alignment, health performance assessment models, and an optimization strategy library, real-time data acquisition, processing, and intelligent diagnosis and feedback are achieved.
It achieves deep fusion and real-time processing of multi-source heterogeneous data, establishes a unified spatiotemporal analysis framework, and forms an intelligent closed loop of "assessment-diagnosis-optimization," which improves the accuracy and timeliness of built environment health assessment and is applicable to special regions such as plateaus.
Smart Images
Figure CN121859098A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of building environment and health monitoring technology, and to a dynamic assessment and diagnosis system for the health performance of the built environment based on multi-source data fusion. Background Technology
[0002] With the advancement of the Healthy China strategy, the health impact of buildings and the urban environment has received increasing attention. Current technologies for assessing the built environment mostly focus on single indicators (such as temperature and humidity) or static evaluations (such as simulations and predictions during the design phase), lacking systematic and refined assessment methods for the dynamic coupling effects of multiple environmental factors (physiological, chemical, and biological) and human responses (physiological, psychological, and behavioral) under actual usage conditions. Especially in special regions such as plateaus and mountains, the interaction mechanisms between complex environmental factors such as low oxygen, strong radiation, and large temperature differences and built spaces are intricate, making existing general assessment systems difficult to apply.
[0003] Currently, the following technical bottlenecks exist: Data silos: Physical environment monitoring data, building operation and maintenance data, and human response data belong to different systems with different formats and standards, making it difficult to perform spatiotemporal alignment and fusion analysis.
[0004] Lack of human-centered response: Most assessments rely solely on environmental physical parameters or subjective questionnaires, lacking objective and continuous human physiological and behavioral data as direct evidence of health efficacy.
[0005] Diagnosis and optimization are disconnected: assessment results often remain at the report level and are difficult to link with specific space design, renovation strategies and operation and maintenance instructions in a closed loop.
[0006] Poor regional applicability: There is a lack of assessment models and diagnostic standards tailored to special climatic environments such as plateaus.
[0007] Therefore, there is an urgent need for a built environment health performance assessment system that can integrate multi-source dynamic data, couple environmental mechanisms with human-centered responses, and achieve intelligent diagnosis and optimization feedback. Summary of the Invention
[0008] The purpose of this invention is to provide a dynamic assessment and diagnosis system for the health performance of the built environment based on multi-source data fusion. This system can realize multi-source data fusion, dynamic assessment, intelligent diagnosis and strategy recommendation, and is especially suitable for complex environments such as plateaus and mountains.
[0009] According to the purpose of this invention, the present invention provides a dynamic assessment and diagnosis system for environmental health performance based on multi-source data fusion, comprising: The multi-source data perception layer is used to collect physical environment data, building data, human-centered response data, and geographic information data in the target built environment in real time. The data fusion and processing layer is used to clean, spatiotemporally align, and standardize the data collected by the perception layer, and store it in the spatiotemporal database; this layer has a built-in health efficacy assessment model. The dynamic assessment and diagnosis layer for health efficacy is used to calculate health efficacy indicators, identify health risks, and generate diagnostic reports based on the fused data and the health efficacy assessment model. The intelligent optimization and feedback layer is used to generate optimization suggestions or control instructions by calling the optimization strategy knowledge base based on the diagnostic report, and then feed them back to the user or device system.
[0010] Furthermore, the multi-source data sensing layer includes: The physical environment sensing module is used to collect at least one of the following: air temperature and humidity, wind speed, air pressure, solar radiation, ultraviolet radiation intensity, CO2 concentration, PM2.5 concentration, noise, and black sphere temperature. The building body perception module is used to acquire building geometric model information, thermal performance data of building envelope, building energy consumption data, and equipment operating status data; The human-centered response perception module is used to collect users' physiological signal data, behavioral trajectory data, and subjective evaluation data; The geographic information module is used to provide information on the elevation, topography, underlying surface attributes, and spatial coordinates of the target built environment.
[0011] Furthermore, the human-centered response perception module includes: Wearable physiological monitoring devices are used to continuously collect data on heart rate variability, blood oxygen saturation, electroencephalogram (EEG) signals, or electrodermal response. Behavioral monitoring units, including eye trackers, indoor positioning beacons, or video analytics devices, are used to acquire data on visual attention distribution, spatial dwell time, and activity trajectory. Subjective data collection interface, used to collect standardized subjective comfort, emotion or satisfaction scale data through mobile or fixed terminals.
[0012] Furthermore, the health efficacy assessment model is a coupled model constructed specifically for the unique geographical environment of plateau and mountainous regions, which includes: An environmental stress-building response mechanism sub-model was constructed based on experimental data of the interaction between plateau-characteristic climate elements and building components, and was used to quantify the impact of climate elements on building physical performance. The environmental exposure-human response ergonomic sub-model, constructed based on human factors ergonomic experimental data in a high-altitude environment, is used to quantify the threshold impact of environmental parameters on human physiological, psychological, and cognitive performance.
[0013] Furthermore, the optimization strategy knowledge base in the intelligent optimization and feedback layer includes at least one of the following sub-bases: The building envelope optimization strategy library includes insulation, shading, and ventilation construction solutions for different climate zones; The space design optimization strategy library includes layout, vision, lighting and material design solutions based on ergonomics; The equipment system control strategy library includes energy-saving and healthy collaborative operation strategies for HVAC, lighting, and fresh air equipment. The library of adaptive renovation strategies for historic buildings includes a list of preventative conservation and performance enhancement technologies for traditional architectural heritage.
[0014] Furthermore, the system also includes a digital twin engine for creating a digital twin of the target built environment based on the geometric model in the building ontology data; the operations of the health performance dynamic assessment and diagnosis layer and the intelligent optimization and feedback layer are simulated, previewed and verified on the digital twin.
[0015] According to another objective of the present invention, the present invention provides a method for dynamic assessment and diagnosis of built environment health performance based on multi-source data fusion, applied to the aforementioned system for dynamic assessment and diagnosis of built environment health performance based on multi-source data fusion, the method comprising: Through a multi-source data perception layer, physical environment data, building body data, human-centered response data, and geographic information data of the target built environment are collected simultaneously. Through the data fusion and processing layer, the collected multi-source data is spatiotemporally aligned and fused, and then input into the pre-set health efficacy assessment model. Through the dynamic assessment and diagnosis layer of health efficacy, based on the output of the assessment model, a multi-dimensional comprehensive health efficacy index and sub-indicators are calculated to locate the spatial location and time window of health risks and generate a visual diagnostic report. Through the intelligent optimization and feedback layer, the diagnostic report is analyzed, and customized design optimization suggestions, equipment control strategies or space transformation schemes are generated by matching from the optimization strategy knowledge base, and the results are output.
[0016] Furthermore, the method also includes an operational closed-loop optimization step: During the building operation phase, dynamic monitoring data from the multi-source sensing layer is continuously received; The monitoring data is continuously compared with the predicted values of the digital twin model or the health baseline to automatically diagnose abnormalities or deviations. Based on the diagnostic results, the system automatically generates and executes equipment control commands, or pushes maintenance and modification suggestions to management personnel. The data on the effects of the optimized intervention are fed back into the optimization strategy knowledge base for iterative updates of the model and strategy.
[0017] The beneficial effects of this invention are: This invention systematically solves key bottlenecks in existing technologies by constructing a complete technical closed loop of perception, fusion, evaluation, and optimization. Its core beneficial effects are reflected in three aspects: First, it achieves deep fusion and real-time processing of multi-source heterogeneous data, breaking down barriers between physical environment, building structure, and human-centered response data, establishing a unified spatiotemporal analysis framework, and laying a data foundation for refined evaluation. Second, it introduces a dynamic, evidence-based evaluation and diagnosis mechanism. Through a built-in health efficacy model (especially suitable for special environments such as high altitudes), it transforms real-time data streams into quantifiable health indicators and risk positioning, shifting evaluation conclusions from experience-based judgments to objective data-driven approaches. Third, it forms an intelligent closed loop of "evaluation-diagnosis-optimization." The system can not only identify problems but also automatically generate customized design, renovation, or control schemes based on a strategy knowledge base. Furthermore, it can directly guide decision-making or equipment operation through feedback interfaces, significantly improving the accuracy, timeliness, and operability of constructing healthy living environments, and possessing significant engineering application value. Attached Figure Description
[0018] Figure 1 This is a block diagram of the overall architecture of the system according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the dynamic assessment and optimization of health efficacy in historical settlements on plateaus in Embodiment 2 of the present invention. Figure 3 This is a flowchart illustrating the implementation of digital twin simulation and feedback for newly built healthy residences in high-altitude areas in Embodiment 3 of the present invention. Detailed Implementation
[0019] The specific embodiments of the present invention will be further described below. It should be noted that these descriptions are for the purpose of aiding understanding the present invention, but do not constitute a limitation thereof. Furthermore, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0020] Example 1 like Figure 1 As shown, a dynamic assessment and diagnosis system for environmental health performance based on multi-source data fusion includes: The multi-source data perception layer is used to collect physical environment data, building data, human-centered response data, and geographic information data in the target built environment in real time. The data fusion and processing layer is used to clean, spatiotemporally align, and standardize the data collected by the perception layer, and store it in the spatiotemporal database; this layer has a built-in health efficacy assessment model. The dynamic assessment and diagnosis layer for health efficacy is used to calculate health efficacy indicators, identify health risks, and generate diagnostic reports based on the fused data and the health efficacy assessment model. The intelligent optimization and feedback layer is used to generate optimization suggestions or control instructions by calling the optimization strategy knowledge base based on the diagnostic report, and then feed them back to the user or device system.
[0021] Specifically, the multi-source data sensing layer includes: The physical environment sensing module is used to collect at least one of the following: air temperature and humidity, wind speed, air pressure, solar radiation, ultraviolet radiation intensity, CO2 concentration, PM2.5 concentration, noise, and black sphere temperature. The building body perception module is used to acquire building geometric model information, thermal performance data of building envelope, building energy consumption data, and equipment operating status data; The human-centered response perception module is used to collect users' physiological signal data, behavioral trajectory data, and subjective evaluation data; The geographic information module is used to provide information on the elevation, topography, underlying surface attributes, and spatial coordinates of the target built environment.
[0022] The human-centered response perception module includes: Wearable physiological monitoring devices are used to continuously collect data on heart rate variability, blood oxygen saturation, electroencephalogram (EEG) signals, or electrodermal response. Behavioral monitoring units, including eye trackers, indoor positioning beacons, or video analytics devices, are used to acquire data on visual attention distribution, spatial dwell time, and activity trajectory. Subjective data collection interface, used to collect standardized subjective comfort, emotion or satisfaction scale data through mobile or fixed terminals.
[0023] Specifically, the health efficacy assessment model is a coupled model constructed for the special geographical environment of plateau and mountainous areas, which includes: An environmental stress-building response mechanism sub-model was constructed based on experimental data of the interaction between plateau-characteristic climate elements and building components, and was used to quantify the impact of climate elements on building physical performance. The environmental exposure-human response ergonomic sub-model, constructed based on human factors ergonomic experimental data in a high-altitude environment, is used to quantify the threshold impact of environmental parameters on human physiological, psychological, and cognitive performance.
[0024] The data for constructing the environmental stress-building response mechanism sub-model comes from an orthogonal experiment in an artificial climate chamber. This experiment systematically manipulates temperature, humidity, solar radiation intensity, and air pressure variables to test the thermal and optical properties of different building components.
[0025] The data for constructing the environmental exposure-human response ergonomics sub-model comes from controlled laboratory experiments or longitudinal field studies. These experiments monitor the physiological signals, cognitive task performance, and emotional state changes of subjects under different combinations of environmental parameters.
[0026] Specifically, the optimization strategy knowledge base in the intelligent optimization and feedback layer includes at least one of the following sub-bases: The building envelope optimization strategy library includes insulation, shading, and ventilation construction solutions for different climate zones; The space design optimization strategy library includes layout, vision, lighting and material design solutions based on ergonomics; The equipment system control strategy library includes energy-saving and healthy collaborative operation strategies for HVAC, lighting, and fresh air equipment. The library of adaptive renovation strategies for historic buildings includes a list of preventative conservation and performance enhancement technologies for traditional architectural heritage.
[0027] Specifically, the system also includes a digital twin engine, used to create a digital twin of the target built environment based on the geometric model in the building ontology data; the operations of the health performance dynamic assessment and diagnosis layer and the intelligent optimization and feedback layer are simulated, previewed and verified on the digital twin.
[0028] The digital twin engine can receive real-time data streams from the multi-source data perception layer, dynamically calibrate and update the digital twin, and achieve virtual-real synchronization and interaction.
[0029] This embodiment also provides a method for dynamic assessment and diagnosis of built environment health performance based on multi-source data fusion, applied to the above-mentioned system, the method comprising: Through a multi-source data perception layer, physical environment data, building body data, human-centered response data, and geographic information data of the target built environment are collected simultaneously. Through the data fusion and processing layer, the collected multi-source data is spatiotemporally aligned and fused, and then input into the pre-set health efficacy assessment model. Through the dynamic assessment and diagnosis layer of health efficacy, based on the output of the assessment model, a multi-dimensional comprehensive health efficacy index and sub-indicators are calculated to locate the spatial location and time window of health risks and generate a visual diagnostic report. Through the intelligent optimization and feedback layer, the diagnostic report is analyzed, and customized design optimization suggestions, equipment control strategies or space transformation schemes are generated by matching from the optimization strategy knowledge base, and the results are output.
[0030] Specifically, the application of the health efficacy assessment model includes: Real-time or historical physical environment data is input into the environmental stress-building response mechanism sub-model to predict the temperature and humidity field, radiation field and air flow state inside the building; The predicted internal environmental state data is input into the environmental exposure-human response ergonomics sub-model to assess its potential impact on the physiological comfort, cognitive performance, and emotional recovery of a preset typical population. The evaluation results are corrected by comparing and verifying the real-time human-centered response data.
[0031] Specifically, the method also includes a digital twin-driven optimization pre-running step: The health performance assessment model is embedded in the digital twin model of the target built environment; Modify design parameters or simulate external climate conditions within a digital twin environment; Run the model to predict changes in health performance indicators under different scenarios; Based on the prediction results, the optimal parameter combination or intervention plan with the best overall performance is recommended.
[0032] Specifically, the method also includes a closed-loop optimization step during the operation period: During the building operation phase, dynamic monitoring data from the multi-source sensing layer is continuously received; The monitoring data is continuously compared with the predicted values of the digital twin model or the health baseline to automatically diagnose abnormalities or deviations. Based on the diagnostic results, the system automatically generates and executes equipment control commands, or pushes maintenance and modification suggestions to management personnel. The data on the effects of the optimized intervention are fed back into the optimization strategy knowledge base for iterative updates of the model and strategy.
[0033] Example 2: Health Efficacy Diagnosis and Suitability Renovation of a Plateau Historical Settlement (Taking a Traditional Courtyard in Shaxi Ancient Town, Yunnan Province as an Example) like Figure 2 As shown, this embodiment aims to conduct a "health check" on the historical heritage buildings on the plateau, improve the health performance of their physical environment while protecting their historical features, and provide data support for their revitalization and utilization.
[0034] Step S101: Deployment and Acquisition of Multi-Source Data Sensing Layer Physical environment sensing: Low-power IoT sensor nodes are deployed in key locations such as the courtyard, main rooms (hall and bedrooms), and corridors to continuously monitor temperature, humidity, CO2, PM2.5, illuminance, and noise. Drones equipped with multispectral sensors are used to regularly take aerial photographs of the entire courtyard and surrounding streets and alleys to obtain surface temperature, vegetation index, and 3D point cloud models.
[0035] Building body perception: High-precision geometric models of the building's interior and exterior are acquired using a 3D laser scanner, and information such as the building envelope materials, thickness, and door and window construction is investigated and recorded to create a lightweight BIM model. Temperature sensors are attached to typical walls and timber frames to monitor their thermal performance.
[0036] Human-centered responsiveness: Residents and visitors are invited to volunteer, wearing smart bracelets (monitoring heart rate variability and blood oxygen saturation) during daily activities. Bluetooth beacons are deployed along typical visitor routes to anonymously collect visitor dwell time and trajectory data. Tablet terminals are placed at exits, inviting users to complete a short environmental satisfaction questionnaire.
[0037] Geographic information: Obtain the altitude, latitude and longitude, surrounding topography and underlying surface information of the courtyard from the GIS platform.
[0038] Step S102: Data Fusion and Application of Plateau-Specific Models All sensor data is uploaded to the cloud-based data fusion and processing layer via a LoRa / Wi-Fi gateway. The system aligns and correlates physical, geometric, and human data based on a unified spatiotemporal reference (GPS timestamps and coordinates). For example, it matches temperature and humidity data of a courtyard at a given moment with heart rate variability data of a tourist at that location at the same moment, along with data from a questionnaire completed by that tourist later.
[0039] The system invokes a health performance assessment model customized for "traditional wooden structures in plateau temperate zones." This model integrates: (a) the mechanism by which the "four courtyards and five patios" spatial form regulates the wind and heat environment, established based on long-term local monitoring data; and (b) the human factors criterion of "the positive impact of low-light wood-colored environment on tourists' emotional recovery," derived from laboratory research. The model comprehensively calculates sub-indices such as "thermal comfort compliance rate," "air quality excellence rate," and "environmental resilience index," as well as the overall health index of the courtyard.
[0040] Step S103: Dynamic assessment and diagnostic report generation System analysis revealed that: during winter nights, the temperature in the bedroom area was below the lower limit of thermal comfort, and the CO2 concentration was prone to exceed the standard when the doors and windows were closed; in the summer afternoons, the strong radiation from the courtyard led to excessive instantaneous thermal stress; visitor tracking showed that the dark and damp west wing corridor was visited for a very short time, indicating an imbalance in space utilization.
[0041] The system automatically generates a visual diagnostic report, highlighting the above-mentioned "health risk areas" and "spatial efficiency gaps" and analyzing their causes (such as the lack of insulation on the exterior walls of the west wing, poor airtightness of windows but small openable area, and lack of sunshade facilities in the courtyard).
[0042] Step S104: Intelligent Optimization and Feedback The system queries the "Historical Settlement Adaptive Transformation Strategy Library" and, based on the diagnostic results, generates a set of optimization suggestions that are harmonious with the landscape and require minimal intervention: For bedrooms: It is recommended to add thick curtains with ethnic characteristics to the room for use at night to enhance heat retention; it is also recommended to install a small, quiet smart fresh air system with heat recovery function, and preset the logic of starting and stopping based on CO2 concentration.
[0043] For courtyards: It is recommended to build a lightweight sunshade that can be seasonally installed and retracted, similar to the traditional "vine climbing trellis"; it is also recommended to add some permeable bricks to the paving material to regulate the microclimate through evaporative cooling.
[0044] For the west wing corridor: it is recommended to replace one solid wall with a traditional diamond-patterned openwork window without changing the structure, to improve natural lighting and ventilation; add low-illuminance, warm-color-temperature archaeological-style wall lamps to enhance the attractiveness of the space.
[0045] The above-mentioned proposed solutions are pushed to the ancient town protection and management agency and courtyard owners through the management platform, and provide simulation data comparison of expected health benefits before and after the renovation to assist in decision-making.
[0046] Example 3: Digital Twin Pre-simulation and Operation and Maintenance Feedback of Newly Built Healthy Residences in Plateau Areas (Taking a Model Room in a Healthy Community in Kunming as an Example) like Figure 3 As shown, this embodiment aims to use digital twin technology to simulate health performance during the later stages of new project design and operation, and to continuously optimize it after use.
[0047] Step S201: Create a digital twin base During the design phase, the project's BIM design model is imported into the system as the geometric and informational basis for the digital twin.
[0048] During the construction phase, drone-based oblique photography was used to update the model, ensuring consistency with the actual building.
[0049] Step S202: Pre-run and optimization The digital twin model incorporates two key components: the "Kunming Area Building-Climate Interaction Mechanism Model" (Direction 1) and the "Plateau Health Space Human Factors Criteria Library" (Direction 2).
[0050] Scenario preview: The homeowner or designer uses the interactive interface to set different external weather conditions (such as typical winter and summer) and tries to adjust design parameters, such as: Change the glass type of the south-facing windows from ordinary double-glazed glass to Low-E glass; Adjust the thickness of the external insulation layer on the bedroom's exterior wall; Change the color temperature and illuminance of the lighting fixtures in the children's room; The impact of different furniture layouts on natural ventilation paths.
[0051] Dynamic assessment: The system simulates in real time the impact of the above changes on indicators such as indoor temperature and humidity distribution, spatial distribution of PMV (expected average thermal sensation index), lighting uniformity, potential glare risk, and expected cognitive attention score based on human factors model.
[0052] Strategy Recommendation: Based on a multi-objective optimization algorithm, the system automatically recommends the optimal combination of design parameters under multiple constraints such as cost, energy saving, and health, and generates a multi-scheme comparison report for decision-making reference.
[0053] Step S203: Dynamic monitoring and closed-loop optimization during operation After the model room is delivered and put into use, a multi-source sensing network similar to that in Example 1 will be deployed for long-term monitoring.
[0054] The system continuously compares and calibrates actual monitoring data (physical environment + anonymized physiological and behavioral data of residents) with the predicted data of the digital twin model, making the model increasingly accurate.
[0055] When the system diagnoses a certain health indicator (such as the correlation between the proportion of deep sleep during nighttime sleep and bedroom temperature deviating from expectations), it will not only issue an alarm, but also automatically adjust the relevant parameters in the digital twin model and rerun the optimization algorithm.
[0056] Closed-loop feedback: The optimization strategies generated by the system can be directly translated into operation and maintenance instructions. For example, if a diagnosis reveals that afternoon afternoon afternoon sun exposure in the living room is causing heat discomfort, the system can automatically control the electric sunshade to lower during specific time periods via the smart home interface, or turn on the living room air conditioner to energy-saving comfort mode in advance. Simultaneously, this "problem-control" case study and its effects are fed back to the strategy knowledge base for design optimization in future similar projects.
[0057] As can be seen from the two embodiments above, the system of the present invention realizes closed-loop management of the entire process from data collection, fusion analysis, dynamic evaluation, intelligent diagnosis to optimization feedback. It is particularly suitable for solving the problem of improving the health efficiency of the built environment in special regions such as plateaus, and has significant scientific value and broad industrial application prospects.
[0058] This invention is the first to deeply integrate physical environment, building structure, human-centered response, and geographic information data into a single system, enabling a comprehensive and three-dimensional assessment of the health performance of the built environment.
[0059] This invention enables dynamic assessment and tracking of health efficacy through real-time / near real-time data streams, accurately locating the spatiotemporal nodes of problems; it also integrates an assessment model specifically designed for the unique environment of high-altitude regions, resulting in more scientific and reliable diagnostic results.
[0060] This invention uses objective physiological and behavioral data as the core evidence chain, shifting the evaluation conclusion from "experience-based judgment" to "data-driven evidence." Through intelligent diagnosis and strategy recommendation, it forms a complete closed loop of "evaluation-diagnosis-optimization," enhancing the practical value of the results.
[0061] The system framework of this invention is universal and can be extended to various geographical and climatic regions such as plains, coastlines, and hot and dry valleys by replacing or adjusting the core evaluation model.
[0062] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A dynamic assessment and diagnosis system for environmental health performance is built based on multi-source data fusion, characterized in that: include: The multi-source data perception layer is used to collect physical environment data, building data, human-centered response data, and geographic information data in the target built environment in real time. The data fusion and processing layer is used to clean, spatiotemporally align, and standardize the data collected by the perception layer, and store it in the spatiotemporal database; this layer has a built-in health efficacy assessment model. The dynamic assessment and diagnosis layer for health efficacy is used to calculate health efficacy indicators, identify health risks, and generate diagnostic reports based on the fused data and the health efficacy assessment model. The intelligent optimization and feedback layer is used to generate optimization suggestions or control instructions by calling the optimization strategy knowledge base based on the diagnostic report, and then feed them back to the user or device system.
2. The environmental health performance dynamic assessment and diagnosis system based on multi-source data fusion as described in claim 1, characterized in that, The multi-source data sensing layer includes: The physical environment sensing module is used to collect at least one of the following: air temperature and humidity, wind speed, air pressure, solar radiation, ultraviolet radiation intensity, CO2 concentration, PM2.5 concentration, noise, and black sphere temperature. The building body perception module is used to acquire building geometric model information, thermal performance data of building envelope, building energy consumption data, and equipment operating status data; The human-centered response perception module is used to collect users' physiological signal data, behavioral trajectory data, and subjective evaluation data; The geographic information module is used to provide information on the elevation, topography, underlying surface attributes, and spatial coordinates of the target built environment.
3. The environmental health performance dynamic assessment and diagnosis system based on multi-source data fusion as described in claim 2, characterized in that, The human-centered response perception module includes: Wearable physiological monitoring devices are used to continuously collect data on heart rate variability, blood oxygen saturation, electroencephalogram (EEG) signals, or electrodermal response. Behavioral monitoring units, including eye trackers, indoor positioning beacons, or video analytics devices, are used to acquire data on visual attention distribution, spatial dwell time, and activity trajectory. Subjective data collection interface, used to collect standardized subjective comfort, emotion or satisfaction scale data through mobile or fixed terminals.
4. The environmental health performance dynamic assessment and diagnosis system based on multi-source data fusion as described in claim 1, characterized in that, The health efficacy assessment model is a coupled model constructed specifically for the unique geographical environment of plateau and mountainous regions, and it includes: An environmental stress-building response mechanism sub-model was constructed based on experimental data of the interaction between plateau-characteristic climate elements and building components, and was used to quantify the impact of climate elements on building physical performance. The environmental exposure-human response ergonomic sub-model, constructed based on human factors ergonomic experimental data in a high-altitude environment, is used to quantify the threshold impact of environmental parameters on human physiological, psychological, and cognitive performance.
5. The environmental health performance dynamic assessment and diagnosis system based on multi-source data fusion as described in claim 1, characterized in that, The optimization strategy knowledge base in the intelligent optimization and feedback layer includes at least one of the following sub-bases: The building envelope optimization strategy library includes insulation, shading, and ventilation construction solutions for different climate zones; The space design optimization strategy library includes layout, vision, lighting and material design solutions based on ergonomics; The equipment system control strategy library includes energy-saving and healthy collaborative operation strategies for HVAC, lighting, and fresh air equipment. The library of adaptive renovation strategies for historic buildings includes a list of preventative conservation and performance enhancement technologies for traditional architectural heritage.
6. The environmental health performance dynamic assessment and diagnosis system based on multi-source data fusion as described in claim 1, characterized in that, The system also includes a digital twin engine, used to create a digital twin of the target built environment based on the geometric model in the building body data; the operations of the health performance dynamic assessment and diagnosis layer and the intelligent optimization and feedback layer are simulated, previewed and verified on the digital twin.
7. A method for dynamic assessment and diagnosis of environmental health performance based on multi-source data fusion, applied to the dynamic assessment and diagnosis system for environmental health performance based on multi-source data fusion as described in any one of claims 1-6, characterized in that, The method includes: Through a multi-source data perception layer, physical environment data, building body data, human-centered response data, and geographic information data of the target built environment are collected simultaneously. Through the data fusion and processing layer, the collected multi-source data is spatiotemporally aligned and fused, and then input into the pre-set health efficacy assessment model. Through the dynamic assessment and diagnosis layer of health efficacy, based on the output of the assessment model, a multi-dimensional comprehensive health efficacy index and sub-indicators are calculated to locate the spatial location and time window of health risks and generate a visual diagnostic report. Through the intelligent optimization and feedback layer, the diagnostic report is analyzed, and customized design optimization suggestions, equipment control strategies or space transformation schemes are generated by matching from the optimization strategy knowledge base, and the results are output.
8. The method according to claim 7, characterized in that, The method also includes a closed-loop optimization step during the operational phase: During the building operation phase, dynamic monitoring data from the multi-source sensing layer is continuously received; The monitoring data is continuously compared with the predicted values of the digital twin model or the health baseline to automatically diagnose abnormalities or deviations. Based on the diagnostic results, the system automatically generates and executes equipment control commands, or pushes maintenance and modification suggestions to management personnel. The data on the effects of the optimized intervention are fed back into the optimization strategy knowledge base for iterative updates of the model and strategy.