Energy-saving fresh air system and fresh air processing method

Abstract

This invention relates to the field of air conditioning and discloses an energy-saving fresh air system and fresh air treatment method. The system includes collecting and registering age group information and historical physical condition information; constructing a human body heat demand benchmark model by combining it with preset human body heat demand parameter mapping rules; collecting historical movement trajectory data and current location information to generate high-probability activity areas; collecting indoor and outdoor ambient temperature data and current body surface temperature information at corresponding spatial nodes to construct an environmental and human body joint state dataset; generating candidate temperature range evolution paths based on the human body heat demand benchmark model, high-probability activity areas, and the environmental and human body joint state dataset, forming temperature range evolution path information; and generating a multi-node temperature collaborative control scheme by combining the mapping relationship of high-probability activity areas in spatial nodes. This invention has the advantages of improving temperature control accuracy and overall energy efficiency.

Description

Technical Field

[0001] This invention relates to the field of air conditioning, specifically to an energy-saving fresh air system and a fresh air treatment method. Background Technology

[0002] With the widespread application of building ventilation systems in energy conservation and indoor comfort, existing technologies mainly rely on static temperature control strategies or control methods based on preset schedules to uniformly set indoor temperatures. However, due to differences in age, gender, physical condition, and activity status among different users, traditional methods cannot accurately reflect the dynamic changes in human body thermal demand, resulting in low efficiency and increased energy consumption of air conditioning or ventilation systems. At the same time, it is difficult to ensure the comfort of users in various activity areas. In addition, existing technologies lack sufficient correlation analysis between user movement trajectories and spatial nodes, cannot identify high-probability activity areas, and lack the ability to coordinate temperature changes in multiple spatial nodes, resulting in a lag in temperature regulation response and insufficient consideration of human body thermal inertia, thus affecting temperature control accuracy and energy-saving effects. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides an energy-saving fresh air system and fresh air treatment method, which has the advantages of improving temperature control accuracy and overall energy efficiency, and solves the problems mentioned in the background technology.

[0004] To achieve the aforementioned goals of improving temperature control accuracy and overall energy efficiency, this invention provides the following technical solution: an energy-saving fresh air treatment method, comprising the following steps: Collect and register age group information and historical physical condition information, combine them with preset human body heat demand parameter mapping rules, perform parametric modeling of human body heat demand characteristics, and construct a human body heat demand benchmark model that characterizes human body heat demand level and heat response characteristics. Based on the human body thermal demand benchmark model, historical movement trajectory data and current location information are collected, and the movement trajectories under different human body thermal demand states are clustered to generate high-probability activity areas in the future preset time period. Based on high-probability activity areas, indoor ambient temperature data, outdoor ambient temperature data, and current body surface temperature information of corresponding spatial nodes are collected. Time alignment processing is performed under a unified time reference to construct an environmental and human joint state dataset that corresponds one-to-one with each high-probability activity area. Based on the human body heat demand benchmark model and the high-probability activity area and environment and human body joint state dataset, the air temperature change within a preset time period is predicted, candidate temperature domain evolution paths are generated, and the effective timing of the candidate temperature domain evolution paths is corrected by introducing the human body heat demand change rate parameter, forming temperature domain evolution path information that includes human body thermal inertia characteristics. Based on temperature evolution path information and the mapping relationship of high-probability activity regions in spatial nodes, the temperature coupling constraints between spatial nodes and their changing trends over time are calculated, and a multi-node temperature collaborative control scheme is proposed.

[0005] Preferably, the process of constructing a baseline model of human heat demand that characterizes the level and thermal response characteristics of human body heat demand is as follows: Based on the age range and identity information entered by the user during the initial access phase, obtain the corresponding set of preset human thermal demand parameters; Access the historical physical condition database to extract indicators including body temperature, heart rate, and activity tolerance; Age group information and historical physical condition indicators are normalized using parameter mapping rules to generate a standardized heat demand feature vector. A baseline model of human body heat demand is constructed based on a standardized heat demand feature vector and a parameter weighting and combination algorithm.

[0006] Preferably, the process of collecting historical movement trajectory data and current location information is as follows: Collect users' historical indoor activity trajectories at different time periods, including walking routes, dwell time, and activity density; Synchronously collect the current user location information and indoor space node numbers to construct a spatial coordinate mapping matrix; Historical trajectory data is linked to the human body thermal demand benchmark model, and each trajectory is assigned a thermal demand status label. The trajectory data and location information are integrated to form a trajectory data set.

[0007] Preferably, the process of generating high-probability activity areas within a preset future time period is as follows: The trajectory data set is classified according to the human body's thermal demand state, forming multiple thermal state trajectory subsets; Density clustering algorithm is applied to each subset to identify high-density activity regions; The frequency of visits and the probability of stay for each spatial node in the future preset time period are statistically analyzed to generate high-probability activity areas in the future preset time period.

[0008] Preferably, the process of collecting indoor ambient temperature data, outdoor ambient temperature data, and current body surface temperature information for the corresponding spatial nodes is as follows: Temperature and humidity sensors are deployed in indoor spaces corresponding to high-probability activity areas to collect indoor temperature and humidity data in real time. It simultaneously acquires outdoor ambient temperature data and uses a thermal imaging camera to collect non-contact information on the body surface temperature of people in the space. Indoor and outdoor environmental data, as well as body surface temperature data, are initially integrated according to spatial nodes and collection order to form a preliminary combined environmental and human body data stream.

[0009] Preferably, the process of constructing a joint state dataset of environment and human body corresponding one-to-one with each high-probability activity area is as follows: Perform unified time alignment processing on indoor temperature, outdoor temperature and body surface temperature data in the preliminary environmental and human body combined data stream; Preprocessing is performed on the time-aligned joint data stream, including missing value interpolation completion, outlier removal, or smoothing filtering; The processed joint data stream is associated with the corresponding spatial node number and human thermal demand status label to form a structured environment and human joint status dataset.

[0010] Preferably, the process of generating candidate temperature range evolution paths is as follows: By combining indoor temperature, outdoor temperature, and body surface temperature information from the environmental and human body joint state dataset, and by combining spatial node distribution and human body heat demand characteristics, an air temperature prediction model is established. Simulate the activity distribution of users in various high-probability activity areas and the changes in heat load at spatial nodes within a preset time period in the future, and generate multiple candidate temperature range evolution paths; Multiple candidate temperature range evolution paths are mapped to the distribution of each high-probability activity region in spatial nodes to form an initial draft of temperature range evolution. Based on the initial draft of the temperature domain evolution, the temperature change characteristics of the spatial nodes corresponding to each path are extracted to generate candidate temperature domain evolution paths.

[0011] Preferably, the process of forming temperature range evolution path information that includes the thermal inertia characteristics of the human body is as follows: For each candidate temperature range evolution path, based on the human body heat demand change rate parameter, the temperature control response lag of each spatial node is calculated, and the human body thermal inertia correction coefficient is generated. Based on the human body thermal inertia correction coefficient, the temperature values ​​at each time point in the candidate temperature range evolution path are numerically corrected. The corrected path is subjected to time series smoothing and spatial node coupling correction to form temperature domain evolution path information that includes human thermal inertia characteristics.

[0012] Preferably, the process of generating a multi-node temperature collaborative control scheme is as follows: Coupled calculations were performed on the temperature changes of each spatial node in the temperature domain evolution path information to analyze the temperature difference between nodes, temperature control response lag and changing trends. Based on the coupling analysis results, multi-node temperature collaborative constraint rules are constructed and mapped to the fresh air control strategy execution module; By combining human body heat demand parameters and node temperature coordination constraints, a multi-node temperature coordination control scheme is generated, including air flow rate, supply air temperature and control time series parameters for each node.

[0013] An energy-saving fresh air treatment system includes: Thermal demand modeling module: Parametrically processes users' age, identity, and historical physical condition information to generate a baseline model of human thermal demand that characterizes the level and thermal response characteristics of human body thermal demand. Trajectory Analysis Module: Based on the human body thermal demand benchmark model, it performs cluster analysis on historical movement trajectories and current location to identify high-probability activity areas in the future within a preset time period; Environmental data acquisition module: Deploy sensors in high-probability activity areas to collect indoor and outdoor temperatures and body surface temperatures, and integrate the data according to spatial nodes and time references to form a joint state dataset; Temperature prediction module: Based on the human body's heat demand baseline and joint state data, predict air temperature changes and introduce human body thermal inertia parameters for correction, and generate temperature evolution path information. Collaborative control module: Based on temperature evolution path information and spatial node mapping relationship, calculate the temperature coupling constraints and changing trends between nodes, and generate a multi-node temperature collaborative control scheme.

[0014] Compared with the prior art, the present invention provides an energy-saving fresh air system and a fresh air treatment method, which have the following beneficial effects: This invention systematically collects user age group and historical physical condition information, and combines it with preset human thermal demand parameter mapping rules to establish a benchmark model that can characterize the level of human thermal demand and thermal response characteristics. This model is then used to analyze historical movement trajectories and real-time location information to identify high-probability activity areas within a preset future time period, achieving precise prediction of human behavior space and refined quantification of thermal demand. Based on this, indoor environment, outdoor environment, and body surface temperature information are jointly processed under a unified time benchmark to construct a high-dimensional environment-human joint state dataset. Furthermore, by introducing the rate of change of human thermal demand to correct candidate temperature domain evolution paths, a temperature domain evolution path containing human thermal inertia characteristics is generated, achieving dynamic response and hysteresis optimization of temperature control. Combined with temperature coupling constraints and change trends between spatial nodes, a multi-node temperature collaborative control scheme can achieve intelligent regulation of the entire room temperature, enabling air conditioning to accurately match human thermal demand, thereby significantly improving user comfort, reducing energy consumption, and minimizing temperature fluctuations. Simultaneously, it considers the system's intelligence, scalability, and energy-saving effects applicable to various indoor environments. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the method of the present invention;

[0016] Figure 2 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1: Please refer to Figure 1 As shown in the figure, an energy-saving fresh air treatment method according to an embodiment of the present invention includes the following steps: S1: Collect and register age group information and historical physical condition information, combine them with preset human body heat demand parameter mapping rules, perform parametric modeling of human body heat demand characteristics, and construct a human body heat demand benchmark model that characterizes the level of human body heat demand and heat response characteristics.

[0019] The process of constructing a baseline model of human heat demand in S1, representing the level and thermal response characteristics of human body heat demand, is as follows: Based on the age range and identity information entered by the user during the initial access phase, obtain the corresponding set of preset human thermal demand parameters; When a user registers or connects for the first time, the system records the user's age, gender, occupation, and type of physical activity through the interface or sensors. Based on a pre-established database of age groups and identity classifications, the system matches corresponding basic heat load parameters, such as resting heat production, basal metabolic rate, and typical activity heat consumption range, to form a set of preset human heat demand parameters specific to the user, providing initial input for the construction of the heat demand model.

[0020] Access the historical physical condition database to extract indicators including body temperature, heart rate, and activity tolerance; The system collects users' physiological data periodically or in real time. It acquires users' historical body temperature curves, heart rate changes, and exercise tolerance data through wearable devices, smart terminals, or vital sign monitoring systems. It filters historical records that match the current user from the database to ensure that the data covers physiological states at different time periods and activity intensities. It also processes outliers and missing data, such as by using interpolation or filtering algorithms to correct measurement errors, in order to ensure the accuracy and continuity of the extracted data.

[0021] Age group information and historical physical condition indicators are normalized using parameter mapping rules to generate a standardized heat demand feature vector. Physiological indicators of different dimensions are numerically normalized, such as mapping body temperature, heart rate, and activity tolerance to a unified 0-1 interval. By defining parameter mapping rules, the basal heat load corresponding to age group and the dynamic characteristics of historical physical state are weighted and fused to generate a standardized heat demand feature vector containing dimensions such as basal heat demand level, activity regulation ability, and physiological response amplitude, which serves as the core input for model construction.

[0022] A benchmark model of human body heat demand is constructed based on a standardized heat demand feature vector and a parameter weighting and combination algorithm. Weights are assigned based on the importance of each indicator in the feature vector. Linear weighting, principal component analysis, or adaptive fusion algorithms are used to combine the features of each dimension to generate the final human body thermal demand benchmark model. This model can characterize the user's thermal demand level and thermal response characteristics under different environmental conditions and activity states. It can be further used for personalized temperature control strategies, environmental adaptability adjustment, and human comfort assessment to achieve accurate and dynamic human body thermal management.

[0023] S2: Based on the human body thermal demand benchmark model, historical movement trajectory data and current location information are collected, and the movement trajectories under different human body thermal demand states are clustered to generate high-probability activity areas in the future within a preset time period.

[0024] The process of collecting historical motion trajectory data and current location information in S2 is as follows: Collect users' historical indoor activity trajectories at different time periods, including walking routes, dwell time, and activity density; By collecting users' movement trajectory data at different times indoors through indoor positioning systems or environmental sensors, the system records the user's movement path between different spatial nodes, the duration of stay at each node, and activity density indicators such as step frequency or acceleration changes. At the same time, the trajectory is processed into a time series by combining timestamp information to ensure the continuity and analyzability of historical trajectory data, and to provide an accurate reference for thermal demand analysis.

[0025] Synchronously collect the current user location information and indoor space node numbers to construct a spatial coordinate mapping matrix; By utilizing real-time indoor positioning technologies, such as Wi-Fi positioning, Bluetooth beacons, or UWB systems, the user's current spatial location and corresponding node number are obtained. The spatial coordinates of each node are then mapped onto the indoor layout model to form a spatial coordinate mapping matrix. This matrix establishes a spatial correspondence between historical trajectories and current location information, providing a unified spatial reference for the correlation analysis between trajectories and thermal demand.

[0026] Historical trajectory data is linked to the human body thermal demand benchmark model, and each trajectory is assigned a thermal demand status label. Based on the previously constructed human thermal demand benchmark model, the thermal load demand and physiological response of users at different trajectory nodes are analyzed. For each segment of historical trajectory data, the corresponding thermal demand state value is calculated according to the activity intensity, dwell time and current environmental conditions. This value is then attached to the trajectory data as a label to form a trajectory record with thermal demand information, thereby realizing the correlation between trajectory spatial behavior and individual thermal demand characteristics.

[0027] Integrate trajectory data and location information to form a trajectory data set; Historical trajectory data with heat demand status labels are uniformly organized with current location information, and a complete data set is generated according to spatial node number and time order. Any missing data or outliers in the set are processed, such as by interpolation, smoothing or removing outliers, to ensure the integrity and accuracy of the data set. Finally, a trajectory data set that can be directly used for heat demand prediction, behavior analysis and personalized environmental control is formed, realizing continuous dynamic management of historical trajectory and real-time location.

[0028] The process of generating high-probability activity regions within a preset future time period in S2 is as follows: The trajectory data set is classified according to the human body's thermal demand state, forming multiple thermal state trajectory subsets; Based on the previously constructed human thermal demand benchmark model, the thermal demand status labels corresponding to each trajectory in the trajectory data set are analyzed. The trajectory data are grouped according to the level or range of thermal demand status, such as high thermal demand, medium thermal demand and low thermal demand, forming corresponding trajectory subsets. Each subset reflects the user's spatial behavior pattern under a specific thermal state, providing a clear classification basis for the identification of high-probability activity areas.

[0029] Density clustering algorithm is applied to each subset to identify high-density activity regions; For each subset of hot-state trajectories, density clustering algorithms, such as DBSCAN or OPTICS, are used to analyze the distribution of spatial nodes. By calculating the density of trajectory points in the neighborhood of each node, high-density clustered spatial areas are identified, which are the activity areas where users frequently appear or stay. For nodes with low density distribution, they can be marked as transitional or occasional activity areas. This method can automatically discover spatial usage hotspots without pre-specifying the number of areas, ensuring that the identification results are highly consistent with actual user behavior.

[0030] Statistically analyze the access frequency and dwell probability of each spatial node in the future preset time period to generate high-probability activity areas in the future preset time period; By combining historical trajectory time series data and current environmental conditions, the access frequency and average stay time of each high-density node in the future preset time period are predicted. Weighted statistics or probability models, such as Markov chains or time series prediction algorithms, are used to calculate the stay probability of each node. Nodes with higher access probabilities are selected according to preset thresholds to form a set of high-probability activity areas in the future. This can be used for environmental control strategies, personalized temperature control solutions, and intelligent space management to achieve scientific prediction of the spatial distribution of users' future behavior.

[0031] S3: Based on high-probability activity areas, collect indoor and outdoor ambient temperature data and current body surface temperature information of corresponding spatial nodes, perform time alignment processing under a unified time reference, and construct an environmental and human joint state dataset that corresponds one-to-one with each high-probability activity area.

[0032] The process of collecting indoor ambient temperature data, outdoor ambient temperature data, and current body surface temperature information for the corresponding spatial nodes in S3 is as follows: Temperature and humidity sensors are deployed in indoor spaces corresponding to high-probability activity areas to collect indoor temperature and humidity data in real time. Within the high-probability activity area predicted by the system, each key spatial node is equipped with a high-precision temperature and humidity sensor. The sensor is connected to the data acquisition platform in real time via a wired or wireless communication network to continuously collect ambient temperature, relative humidity, and air temperature change curves. The sampling frequency and data caching strategy can be set to ensure the continuity and real-time nature of temperature and humidity data. The sensor can also calibrate errors through its self-test function to ensure accurate and reliable data.

[0033] It simultaneously acquires outdoor ambient temperature data and uses a thermal imaging camera to collect non-contact information on the body surface temperature of people in the space. Outdoor temperature and related meteorological information are acquired through meteorological interfaces or local environmental sensors. At the same time, infrared thermal imaging cameras or non-contact body temperature monitoring devices are deployed in key indoor locations to capture the body surface temperature of people in real time. The data collected by the cameras is processed by image processing and temperature mapping algorithms to accurately map the body surface temperature value to the spatial node, so as to realize the synchronous acquisition of indoor human body temperature and ambient temperature and ensure that the data reflects the true thermal comfort state.

[0034] Indoor and outdoor environmental data, as well as body surface temperature data, are initially integrated according to spatial nodes and collection order to form a preliminary combined environmental and human body data stream. The collected indoor temperature and humidity data, outdoor temperature data, and body surface temperature data are time-stamped and spatial node identifiers are unified. A data integration algorithm is used to combine the three types of data according to spatial nodes and time order to form a continuous environment-human joint data stream. During the integration process, outliers or missing data can be filtered or interpolated to ensure the integrity and analyzability of the data stream, providing a reliable data foundation for personalized thermal regulation, human thermal response analysis, and environmental optimization.

[0035] The process of constructing a joint state dataset of environment and human body corresponding one-to-one with each high-probability activity region in S3 is as follows: Perform unified time alignment processing on indoor temperature, outdoor temperature and body surface temperature data in the preliminary environmental and human body combined data stream; For data streams from different acquisition devices, a unified time base is used to align the various types of data to ensure that indoor temperature, outdoor temperature, and body surface temperature correspond at the same point in time. Time interpolation algorithms can be used to handle time misalignment caused by different sampling frequencies, such as linear interpolation or higher-order interpolation methods. After time alignment, various types of data can form a continuous and synchronous joint time series, providing an accurate basis for analysis and modeling.

[0036] Preprocessing is performed on the time-aligned joint data stream, including missing value interpolation completion, outlier removal, or smoothing filtering; To detect missing or abnormal temperature data points in the joint data stream, missing values ​​are filled by interpolation or prediction based on historical data. Obvious outliers are determined by standard deviation or removed or corrected based on the average of neighboring nodes. Secondly, to reduce the impact of measurement noise, smoothing filtering algorithms such as moving average filtering, exponential smoothing, or Kalman filtering can be applied to the joint data stream. After preprocessing, the data stream is continuous, smooth, and has minimal abnormal interference, ensuring that the data quality meets the requirements of subsequent modeling.

[0037] The processed joint data stream is associated with the corresponding spatial node number and human thermal demand status label to form a structured environment and human joint status dataset. Based on the spatial node number of each data record, the joint data stream is mapped to the spatial nodes corresponding to each high-probability activity area. At the same time, the human thermal demand status label corresponding to each record is attached to the joint data, forming a ternary association structure of environmental data, spatial nodes, and thermal demand status. Finally, a structured environmental and human joint status dataset is generated. Each record contains time, spatial node, indoor temperature, outdoor temperature, body surface temperature, and thermal demand status, which can be used for personalized thermal regulation, thermal comfort assessment, and environmental optimization algorithm training.

[0038] S4: Based on the human body heat demand benchmark model and the high-probability activity area and environment and human body joint state dataset, predict the air temperature change within a preset time period in the future, generate candidate temperature domain evolution paths, and modify the effective timing of the candidate temperature domain evolution paths by introducing the human body heat demand change rate parameter, forming temperature domain evolution path information that includes human body thermal inertia characteristics.

[0039] The process of generating candidate temperature range evolution paths in S4 is as follows: By combining indoor temperature, outdoor temperature, and body surface temperature information from the environmental and human body joint state dataset, and by combining spatial node distribution and human body heat demand characteristics, an air temperature prediction model is established. By utilizing temperature information from environmental and human body joint state datasets, indoor air temperature changes in high-probability activity areas are modeled. Spatial node distribution information and human body thermal demand characteristics are used as input features. Physical heat balance models, empirical regression models, or machine learning methods, such as LSTM, GRU, or multivariate regression, are employed to predict air temperature changes over time. This approach can simultaneously consider the influence of the external environment, human body heat dissipation, and spatial thermal inertia, enabling scientific prediction of future temperature trends.

[0040] Simulate the activity distribution of users in various high-probability activity areas and the changes in heat load at spatial nodes within a preset time period in the future, and generate multiple candidate temperature range evolution paths; Based on a high-probability activity area and a baseline model of human thermal demand, the possible spatial movement paths of users in the future are simulated. Considering different activity intensities, dwell times, and changes in thermal load, the thermal load changes of each spatial node in each simulated path are cumulatively calculated. Combined with an air temperature prediction model, multiple possible temperature evolution sequences are generated. Through different activity strategies and thermal load combinations, multiple candidate temperature range evolution paths are formed to cover the uncertainties of future environmental and human interaction.

[0041] Multiple candidate temperature range evolution paths are mapped to the distribution of each high-probability activity region in spatial nodes to form an initial draft of temperature range evolution. For each candidate temperature domain evolution path, its temperature change sequence is mapped one-to-one with the spatial node number. The temperature values ​​in the simulated path are assigned to the spatial nodes of specific high-probability activity areas, forming a preliminary draft of the temperature domain evolution that includes time, spatial nodes, and temperature values. This draft can intuitively reflect the future temperature change trends of each spatial node and provide a structured basis for further path optimization.

[0042] Based on the initial draft of the temperature domain evolution, the temperature change characteristics of the spatial nodes corresponding to each path are extracted to generate candidate temperature domain evolution paths. For the spatial node temperature sequence of each path in the initial draft of temperature domain evolution, key temperature change features such as peak temperature, temperature fluctuation amplitude, heating rate and cooling rate are extracted. Combined with the heat conduction relationship between nodes and the thermal response characteristics of the human body, the path features are quantified to generate the final candidate temperature domain evolution path set. This set can be used for subsequent temperature control strategy optimization, personalized environmental adjustment and comfort assessment, so as to achieve scientific prediction and operable management of future temperature domain changes.

[0043] The process of forming temperature evolution path information containing human thermal inertia characteristics in S4 is as follows: For each candidate temperature range evolution path, based on the human body heat demand change rate parameter, the temperature control response lag of each spatial node is calculated, and the human body thermal inertia correction coefficient is generated. Based on the thermal response parameters in the human body thermal demand baseline model, the rate of human adaptation to changes in environmental temperature is determined, such as the rate of change in body surface temperature, the delay in core temperature change, and the delay in thermal sensation. For each spatial node in each candidate temperature range evolution path, the response lag time of the human body to temperature control changes is calculated, and the lag effect is quantified into a human body thermal inertia correction coefficient, which can be used to describe the dynamic buffering capacity of the human body to temperature changes and provide a scientific basis for temperature range path correction.

[0044] Based on the human body thermal inertia correction coefficient, the temperature values ​​at each time point in the candidate temperature range evolution path are numerically corrected. The calculated human thermal inertia correction coefficient is applied to the temperature sequence of each candidate path. The temperature change curve is adjusted according to the human thermal inertia delay law. Through numerical correction algorithm, the temperature value is shifted forward or backward on the time axis to simulate the lag effect of human body temperature perception. At the same time, the temperature gradient relationship between spatial nodes is preserved. The corrected path more realistically reflects the user's thermal comfort experience in different spaces and at different times.

[0045] The corrected path is smoothed over time and the coupling between spatial nodes is corrected to form temperature domain evolution path information that includes the thermal inertia characteristics of the human body. Smoothing filtering algorithms, such as moving average filtering, low-pass filtering, or Kalman filtering, are applied to the corrected temperature sequence to eliminate sharp fluctuations caused by numerical correction. At the same time, the temperature sequences of adjacent spatial nodes are coupled and corrected to ensure the continuity and spatial consistency of temperature distribution. Finally, temperature domain evolution path information containing human thermal inertia characteristics is formed. Each path reflects both the evolution of ambient temperature and the thermal response characteristics of the human body. It can serve as the core data foundation for personalized temperature control strategy optimization, thermal comfort prediction, and environmental regulation decision-making.

[0046] S5: Based on temperature evolution path information and the mapping relationship of high-probability activity regions in spatial nodes, calculate the temperature coupling constraints and time-varying trends between spatial nodes, and propose a multi-node temperature collaborative control scheme.

[0047] The process of generating a multi-node temperature collaborative control scheme in S5 is as follows: Coupled calculations were performed on the temperature changes of each spatial node in the temperature domain evolution path information to analyze the temperature difference between nodes, temperature control response lag and changing trends. Using the temperature sequence of each spatial node in the temperature domain evolution path containing the thermal inertia characteristics of the human body as input, the coupled calculation model is used to analyze the temperature gradient, air flow influence and heat conduction relationship between nodes. Combined with the temperature control response hysteresis parameter, the dynamic differences and trends of temperature of each node in the future time period are calculated. The analysis results can reflect the temperature deviation, potential non-uniformity and thermal interaction between different nodes, providing a quantitative basis for collaborative control.

[0048] Based on the coupling analysis results, multi-node temperature collaborative constraint rules are constructed and mapped to the fresh air control strategy execution module; Based on the temperature difference, response lag, and trend obtained from the inter-node coupling calculations, multi-node collaborative constraint rules are formulated, such as maximum allowable temperature difference, heating / cooling rate limits, and priority control node order. The collaborative constraint rules are associated with the fresh air system control logic, and the constraint parameters are mapped into executable instructions, such as fan adjustment, supply air temperature adjustment, and air flow distribution strategies, through the control module. This ensures that the system meets human thermal comfort while maintaining energy efficiency during multi-node collaborative control.

[0049] By combining human body heat demand parameters and node temperature coordination constraints, a multi-node temperature coordination control scheme is generated, including air flow rate, supply air temperature and control time series parameters for each node. By integrating real-time heat load, thermal response rate, and personalized comfort thresholds with collaborative constraint rules from the human body thermal demand benchmark model, a comprehensive control objective function is formed. Using optimization algorithms, such as linear programming, model predictive control, or reinforcement learning strategies, the optimal airflow, supply air temperature, and control time series of each node are calculated to generate a multi-node temperature collaborative control scheme. This scheme satisfies the requirements of multi-node temperature balance and thermal comfort, while also considering the human body's thermal inertia effect and spatial thermal coupling, thus achieving dynamic and refined multi-node temperature collaborative control.

[0050] Example 2: Please refer to Figure 2 As shown, an energy-saving fresh air handling system includes: Thermal demand modeling module: Parametrically processes users' age, identity, and historical physical condition information to generate a baseline model of human thermal demand that characterizes the level and thermal response characteristics of human body thermal demand. Trajectory Analysis Module: Based on the human body thermal demand benchmark model, it performs cluster analysis on historical movement trajectories and current location to identify high-probability activity areas in the future within a preset time period; Environmental data acquisition module: Deploy sensors in high-probability activity areas to collect indoor and outdoor temperatures and body surface temperatures, and integrate the data according to spatial nodes and time references to form a joint state dataset; Temperature prediction module: Based on the human body's heat demand baseline and joint state data, predict air temperature changes and introduce human body thermal inertia parameters for correction, and generate temperature evolution path information. Collaborative control module: Based on temperature evolution path information and spatial node mapping relationship, calculate the temperature coupling constraints and changing trends between nodes, and generate a multi-node temperature collaborative control scheme.

[0051] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0052] Although embodiments of the 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 invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An energy-saving fresh air treatment method, characterized in that, Includes the following steps: Collect and register age group information and historical physical condition information, combine them with preset human body heat demand parameter mapping rules, perform parametric modeling of human body heat demand characteristics, and construct a human body heat demand benchmark model that characterizes human body heat demand level and heat response characteristics. Based on the human body thermal demand benchmark model, historical movement trajectory data and current location information are collected, and the movement trajectories under different human body thermal demand states are clustered to generate high-probability activity areas in the future preset time period. Based on high-probability activity areas, indoor ambient temperature data, outdoor ambient temperature data, and current body surface temperature information of corresponding spatial nodes are collected. Time alignment processing is performed under a unified time reference to construct an environmental and human joint state dataset that corresponds one-to-one with each high-probability activity area. Based on the human body heat demand benchmark model and the high-probability activity area and environment and human body joint state dataset, the air temperature change within a preset time period is predicted, candidate temperature domain evolution paths are generated, and the effective timing of the candidate temperature domain evolution paths is corrected by introducing the human body heat demand change rate parameter, forming temperature domain evolution path information that includes human body thermal inertia characteristics. Based on temperature evolution path information and the mapping relationship of high-probability activity regions in spatial nodes, the temperature coupling constraints between spatial nodes and their changing trends over time are calculated, and a multi-node temperature collaborative control scheme is proposed.

2. The energy-saving fresh air treatment method according to claim 1, characterized in that, The process of constructing a baseline model of human heat demand that characterizes the level and thermal response characteristics of human body heat demand is as follows: Based on the age range and identity information entered by the user during the initial access phase, obtain the corresponding set of preset human thermal demand parameters; Access the historical physical condition database to extract indicators including body temperature, heart rate, and activity tolerance; Age group information and historical physical condition indicators are normalized using parameter mapping rules to generate a standardized heat demand feature vector. A baseline model of human body heat demand is constructed based on a standardized heat demand feature vector and a parameter weighting and combination algorithm.

3. The energy-saving fresh air treatment method according to claim 1, characterized in that, The process of collecting historical movement trajectory data and current location information is as follows: Collect users' historical indoor activity trajectories at different time periods, including walking routes, dwell time, and activity density; Synchronously collect the current user location information and indoor space node numbers to construct a spatial coordinate mapping matrix; Historical trajectory data is linked to the human body thermal demand benchmark model, and each trajectory is assigned a thermal demand status label. The trajectory data and location information are integrated to form a trajectory data set.

4. The energy-saving fresh air treatment method according to claim 3, characterized in that, The process of generating high-probability activity areas within a preset future time period is as follows: The trajectory data set is classified according to the human body's thermal demand state, forming multiple thermal state trajectory subsets; Density clustering algorithm is applied to each subset to identify high-density activity regions; The frequency of visits and the probability of stay for each spatial node in the future preset time period are statistically analyzed to generate high-probability activity areas in the future preset time period.

5. The energy-saving fresh air treatment method according to claim 3, characterized in that, The process of collecting indoor ambient temperature data, outdoor ambient temperature data, and current body surface temperature information for the corresponding spatial nodes is as follows: Temperature and humidity sensors are deployed in indoor spaces corresponding to high-probability activity areas to collect indoor temperature and humidity data in real time. It simultaneously acquires outdoor ambient temperature data and uses a thermal imaging camera to collect non-contact information on the body surface temperature of people in the space. Indoor and outdoor environmental data, as well as body surface temperature data, are initially integrated according to spatial nodes and collection order to form a preliminary combined environmental and human body data stream.

6. The energy-saving fresh air treatment method according to claim 5, characterized in that, The process of constructing a joint state dataset of environment and human body corresponding one-to-one with each high-probability activity region is as follows: Perform unified time alignment processing on indoor temperature, outdoor temperature and body surface temperature data in the preliminary environmental and human body combined data stream; Preprocessing is performed on the time-aligned joint data stream, including missing value interpolation completion, outlier removal, or smoothing filtering; The processed joint data stream is associated with the corresponding spatial node number and human thermal demand status label to form a structured environment and human joint status dataset.

7. The energy-saving fresh air treatment method according to claim 6, characterized in that, The process of generating candidate temperature range evolution paths is as follows: By combining indoor temperature, outdoor temperature, and body surface temperature information from the environmental and human body joint state dataset, and by combining spatial node distribution and human body heat demand characteristics, an air temperature prediction model is established. Simulate the activity distribution of users in various high-probability activity areas and the changes in heat load at spatial nodes within a preset time period in the future, and generate multiple candidate temperature range evolution paths; Multiple candidate temperature range evolution paths are mapped to the distribution of each high-probability activity region in spatial nodes to form an initial draft of temperature range evolution. Based on the initial draft of the temperature domain evolution, the temperature change characteristics of the spatial nodes corresponding to each path are extracted to generate candidate temperature domain evolution paths.

8. The energy-saving fresh air treatment method according to claim 7, characterized in that, The process of forming temperature range evolution path information that includes the thermal inertia characteristics of the human body is as follows: For each candidate temperature range evolution path, based on the human body heat demand change rate parameter, the temperature control response lag of each spatial node is calculated, and the human body thermal inertia correction coefficient is generated. Based on the human body thermal inertia correction coefficient, the temperature values ​​at each time point in the candidate temperature range evolution path are numerically corrected. The corrected path is subjected to time series smoothing and spatial node coupling correction to form temperature domain evolution path information that includes human thermal inertia characteristics.

9. The energy-saving fresh air treatment method according to claim 8, characterized in that, The process of generating a multi-node temperature coordinated control scheme is as follows: Coupled calculations were performed on the temperature changes of each spatial node in the temperature domain evolution path information to analyze the temperature difference between nodes, temperature control response lag and changing trends. Based on the coupling analysis results, multi-node temperature collaborative constraint rules are constructed and mapped to the fresh air control strategy execution module; By combining human body heat demand parameters and node temperature coordination constraints, a multi-node temperature coordination control scheme is generated, including air flow rate, supply air temperature and control time series parameters for each node.

10. An energy-saving fresh air treatment system, applied to the method described in any one of claims 1-9, characterized in that, include: Thermal demand modeling module: Parametrically processes users' age, identity, and historical physical condition information to generate a baseline model of human thermal demand that characterizes the level and thermal response characteristics of human body thermal demand. Trajectory Analysis Module: Based on the human body thermal demand benchmark model, it performs cluster analysis on historical movement trajectories and current location to identify high-probability activity areas in the future within a preset time period; Environmental data acquisition module: Deploy sensors in high-probability activity areas to collect indoor and outdoor temperatures and body surface temperatures, and integrate the data according to spatial nodes and time references to form a joint state dataset; Temperature prediction module: Based on the human body's heat demand baseline and joint state data, predict air temperature changes and introduce human body thermal inertia parameters for correction, and generate temperature evolution path information. Collaborative control module: Based on temperature evolution path information and spatial node mapping relationship, calculate the temperature coupling constraints and changing trends between nodes, and generate a multi-node temperature collaborative control scheme.

Images