CN-121997419-A - Health space design optimization method and system based on multi-mode human factor data

CN121997419ACN 121997419 ACN121997419 ACN 121997419ACN-121997419-A

Abstract

The invention discloses a health space design optimization method and system based on multi-mode human factor data, and relates to the technical field of health buildings. The method comprises the steps of synchronously collecting physiological, behavioral, subjective and other multi-mode human factor data and environment data of a person in a target space, carrying out data fusion and feature extraction, constructing an environment parameter-health efficacy prediction model, carrying out design parameter sensitivity analysis and setting an optimization target, linking a parameterized design tool and the prediction model, automatically iterating to generate an optimal design scheme set, and finally outputting a evidence-based design report. According to the invention, the real response depth of the human body is integrated into the design flow in a data driving mode, so that the quantification, the refinement and the personalized optimization of the healthy space design are realized, the method is particularly suitable for solving the health human living challenges in special environments such as a plateau and the like, and the scientificity and the health efficacy guarantee of the design are remarkably improved.

Inventors

XU JIAN
Ma Ruiqu
JIA XINMING
XU GENYU
YU MULIANG

Assignees

云南大学

Dates

Publication Date: 20260508
Application Date: 20260120

Claims (8)

1. A health space design optimization method based on multi-mode human factor data is characterized by comprising the following steps: S1, synchronously collecting multi-modal human factor data and corresponding physical environment data of a subject in a target space or a simulation space, wherein the multi-modal human factor data comprises physiological data, behavior data and subjective evaluation data; S2, cleaning, aligning and fusing the synchronous data with the space-time labels acquired in the step S1 to form a structured data set, and extracting key indexes reflecting the human body state and the environmental characteristics from the structured data set; s3, analyzing the association relation between the key indexes based on a machine learning or statistical method, and constructing a prediction model or an influence mechanism model which takes the space environment parameters as input and takes the human health efficacy indexes as output; s4, carrying out sensitivity analysis on design parameters based on the model constructed in the step S3, identifying key influence factors, and setting an optimization target by combining health standards or project requirements; S5, linking the parameterized design tool with the prediction model constructed in the step S3, automatically or semi-automatically adjusting design scheme parameters, simulating and predicting health efficacy indexes under different schemes, and screening out an optimization scheme set meeting the optimization target; S6, generating a evidence-based design report containing specific design strategies, parameter suggestions and expected health benefits based on the optimization scheme set.
2. The method according to claim 1, wherein in step S1, the physiological data comprises at least one of heart rate variability, electroencephalogram, skin electrical activity, blood oxygen saturation acquired by a portable physiological monitoring device; The behavior data comprise at least one of visual attention distribution, spatial activity track, stay time and distribution density acquired by an eye tracker, an indoor positioning system, an accelerometer or computer visual analysis equipment; The physical environment data includes at least one of air temperature, humidity, illuminance, color temperature, wind speed, carbon dioxide concentration, atmospheric pressure, solar radiation intensity collected by an environment sensor.
3. The method according to claim 1 or 2, wherein step S1 is performed in a climatic chamber capable of reproducing plateau or special geographical climatic conditions including low oxygen, low air pressure, large temperature differences, strong solar radiation, and/or, Step S1 is executed in a real built environment, and large-scale and long-period data acquisition is performed by using the unmanned aerial vehicle, the mobile monitoring equipment and the fixed sensing network.
4. The method according to claim 1, wherein in step S3, the human health performance indicators include at least one of cognitive task performance scores, physiological stress/recovery indices, emotional state indices, subjective comfort achievement rates; the algorithm adopted for constructing the prediction model comprises at least one of random forest, support vector machine, neural network and geographic weighted regression.
5. The method of claim 1, wherein in step S4, the design parameters include at least one of a light environment parameter, a thermal environment parameter, an air quality parameter, a space geometry parameter, a material property parameter, and a facility layout parameter of a building or space; In step S5, the linkage between the parameterized design tool and the prediction model is implemented through an application program interface, and the optimization process searches the pareto optimal solution set by adopting a multi-objective optimization algorithm.
6. A geospatial design optimization system for implementing the method of any of claims 1-5, comprising: the data acquisition module is configured to synchronously acquire physiological data, behavior data, subjective evaluation data and physical environment data; the data fusion and processing module is in communication connection with the data acquisition module and is used for carrying out time synchronization, spatial registration, cleaning and feature extraction on the multi-source data and outputting a structured fusion data set; The data analysis and modeling module is in communication connection with the data fusion and processing module and is used for training a health efficacy prediction model or carrying out influence mechanism analysis based on the fusion data set and executing design parameter sensitivity analysis; The parameterized design and optimization engine module is in communication connection with the data analysis and modeling module and is used for integrating the parameterized design platform and the health efficacy prediction model, automatically adjusting design parameters according to an optimization target, performing health efficacy simulation and outputting an optimization scheme set; and the report generation and visualization module is in communication connection with the parameterized design and optimization engine module and is used for outputting analysis results, optimization schemes and prediction efficiency in the form of a visual chart and a structural report.
7. The system of claim 6, wherein the data acquisition module comprises at least two of a wearable physiological signal acquisition device, an eye tracker, an indoor positioning base station and tag, an environmental sensor network, a digital questionnaire terminal, and an unmanned aerial vehicle-mounted remote sensing sensor.
8. The system of claim 6, wherein the parameterized design and optimization engine module is built-in or can call a plurality of parameterized modeling software and multi-objective optimization algorithm libraries; the report generation and visualization module is capable of generating a specific health space design guideline for different regional climate conditions.

Description

Health space design optimization method and system based on multi-mode human factor data Technical Field The invention relates to the technical field of healthy buildings and smart cities, in particular to a healthy space design optimization method and system based on multi-mode human factor data. Background How to design a building space capable of promoting the physiological and psychological health of a user is an important subject. At present, space design depends on experience, specification and static environment simulation, and quantitative evidence-based on dynamic and comprehensive reaction of a human body in a real or simulated environment is lacking. Especially in special environment areas such as mountain areas of high land, stress factors such as hypoxia and strong radiation have remarkable influence on human bodies, and the traditional design method is difficult to accurately cope with. In the prior art, a plurality of technologies for monitoring environmental parameters based on sensors or collecting subjective feedback through questionnaires exist, but the problems that data dimension is single, subjective and objective data are split, an environment-human interaction deep mechanism cannot be revealed and the like exist generally. A set of method and technical system capable of systematically acquiring, fusing, physiological, behavioral, subjective, physical environment and other multi-mode data and based on the closed-loop driving space design optimization is lacking. Disclosure of Invention The invention aims to provide a healthy space design optimization method and system based on multi-mode human factor data, wherein the method systematically collects, fuses and analyzes multi-dimensional data such as physiology, behavior, subjective feeling and the like of a person in a specific space, and a quantitative relation model of 'environmental stimulus-human response' is constructed by combining high-precision environmental data, so that objective and quantitative evidence-based basis is provided for the health efficacy of space design, and an intelligent generation or optimization design scheme is realized, and the transition from 'empirical design' to 'evidence-based design' is realized. According to the purpose of the invention, the invention provides a health space design optimization method based on multi-mode human factor data, which comprises the following steps: S1, synchronously collecting multi-modal human factor data and corresponding physical environment data of a subject in a target space or a simulation space, wherein the multi-modal human factor data comprises physiological data, behavior data and subjective evaluation data; S2, cleaning, aligning and fusing the synchronous data with the space-time labels acquired in the step S1 to form a structured data set, and extracting key indexes reflecting the human body state and the environmental characteristics from the structured data set; s3, analyzing the association relation between the key indexes based on a machine learning or statistical method, and constructing a prediction model or an influence mechanism model which takes the space environment parameters as input and takes the human health efficacy indexes as output; s4, carrying out sensitivity analysis on design parameters based on the model constructed in the step S3, identifying key influence factors, and setting an optimization target by combining health standards or project requirements; S5, linking the parameterized design tool with the prediction model constructed in the step S3, automatically or semi-automatically adjusting design scheme parameters, simulating and predicting health efficacy indexes under different schemes, and screening out an optimization scheme set meeting the optimization target; S6, generating a evidence-based design report containing specific design strategies, parameter suggestions and expected health benefits based on the optimization scheme set. Further, in step S1, the physiological data includes at least one of heart rate variability, electroencephalogram, skin electrical activity, and blood oxygen saturation acquired by the portable physiological monitoring device; The behavior data comprise at least one of visual attention distribution, spatial activity track, stay time and distribution density acquired by an eye tracker, an indoor positioning system, an accelerometer or computer visual analysis equipment; The physical environment data includes at least one of air temperature, humidity, illuminance, color temperature, wind speed, carbon dioxide concentration, atmospheric pressure, solar radiation intensity collected by an environment sensor. Further, step S1 is performed in a climatic chamber capable of reproducing altitude or special geographical climatic conditions including hypoxia, low air pressure, large temperature differences, strong solar radiation, and/or, Step S1 is executed in a real built environment, and large-scale and long-p