Iot-based health and wellness space environment regulation method and system

Abstract

The application discloses a health-care space environment regulation method and system based on the Internet of Things, relates to the technical field of intelligent environment regulation of the Internet of Things, and comprises the following steps: collecting health-care space environment parameters and target crowd physiological parameters, constructing an environment data change vector field, forming a physiological state evolution curve, and extracting a physiological sensitive direction set; determining a comfortable environment distribution area according to a time period during which the physiological parameters are in a healthy range; searching for a candidate regulation path leading to the comfortable environment distribution area along the physiological sensitive direction, and screening a stable regulation vector in combination with accumulated energy consumption; generating a segmented regulation sequence according to an environment propagation rate, and converting the segmented regulation sequence into environment regulation equipment execution parameters for control. The application can improve the stability, comfort and energy consumption control capability of health-care space environment regulation.

Description

Technical Field

[0001] This invention relates to the field of IoT-based intelligent environmental control technology, specifically to a method and system for controlling the environment of health and wellness spaces based on IoT. Background Technology

[0002] With the development of the Internet of Things, intelligent sensing, and smart healthcare technologies, healthcare spaces are gradually evolving towards intelligence and dynamism. Existing healthcare spaces typically deploy environmental monitoring equipment for temperature, humidity, air quality, lighting, and noise, while also incorporating physiological monitoring equipment for heart rate, blood oxygen, body temperature, and sleep patterns to achieve real-time perception of both human health and the spatial environment. By automatically controlling air conditioning, ventilation, lighting, and humidification equipment through environmental control devices, the comfort of living and the quality of healthcare services can be improved to a certain extent, thus leading to their widespread application in smart elderly care, rehabilitation nursing, and healthy housing scenarios.

[0003] Most existing environmental control methods employ fixed threshold control, rule-based control, or feedback control based on a single physiological indicator. This means that corresponding devices are triggered to adjust when environmental parameters exceed set ranges. These methods typically only provide localized control over a single environmental parameter, lacking the ability to comprehensively analyze the relationships and trends between multiple environmental parameters. Existing solutions rely heavily on the body's current instantaneous physiological state for regulation, making it difficult to establish a dynamic relationship between the body's physiological state and environmental changes. Therefore, they are prone to problems such as frequent fluctuations in environmental regulation, uneven environmental transitions, and poor overall comfort.

[0004] Furthermore, people of different ages and health statuses have varying sensitivities to environmental changes. For example, the elderly, patients with chronic diseases, and those in recovery are more sensitive to changes in temperature, humidity, airflow, and light. Traditional environmental control systems typically employ a uniform regulation strategy, lacking dynamic control mechanisms tailored to individual differences. Rapid changes in environmental parameters can easily lead to decreased human comfort or even physiological discomfort. Existing technologies often use the target environmental value as a single control objective, lacking comprehensive consideration of the stability of the control path, the rate of environmental propagation, and the coordinated adjustment process of equipment. This results in problems such as high energy consumption, low equipment linkage efficiency, and insufficient environmental stability.

[0005] Therefore, there is an urgent need for a method for regulating the health and wellness space environment that can combine the changing trends of environmental parameters with the evolutionary characteristics of human physiological state, and dynamically perceive, stably plan paths, and coordinate and regulate the health and wellness space environment in stages. Summary of the Invention

[0006] The purpose of this invention is to provide a method and system for regulating the health and wellness space environment based on the Internet of Things, aiming to solve at least one of the technical problems existing in the prior art.

[0007] The technical solution of this invention is: a method for regulating the environment of health and wellness spaces based on the Internet of Things, comprising the following steps: Environmental parameters and physiological parameters of the target population within the health and wellness space were collected to obtain environmental data sequences and physiological data sequences; A change vector field of environmental data sequence is constructed, and physiological data sequence is mapped to the change vector field to form physiological state evolution curve. The direction of change of environmental parameters corresponding to the curvature change point in the physiological state evolution curve is extracted to obtain a set of physiologically sensitive directions. Extract time periods from physiological data sequences where physiological parameters are within a preset healthy range, record the positional distribution of environmental parameters in the change vector field within the time periods, and obtain the comfortable environment distribution area. The adjustment path from the current environmental parameter location to the comfortable environment distribution area is searched along the physiologically sensitive direction set, and the cumulative energy consumption of each adjustment path is calculated to obtain multiple candidate regulation paths; Identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector; The difference vector between the stable regulation vector and the current environmental parameter vector is calculated. The difference vector is decomposed into components along the physiologically sensitive direction. The components are then arranged in time according to their environmental propagation rates to obtain a segmented regulation sequence. The segmented control sequence is converted into execution parameters for environmental control equipment and control commands are sent.

[0008] A change vector field is constructed for the environmental data sequence. The physiological data sequence is then mapped to the change vector field to form a physiological state evolution curve. The direction of environmental parameter change corresponding to the curvature abrupt change point in the physiological state evolution curve is extracted to obtain the set of physiologically sensitive directions, including: Calculate the gradient vector of each environmental parameter in the environmental data sequence along the time dimension, and construct a matrix by using each time point as the row index and the gradient value of each environmental parameter as the column index to obtain the environmental gradient matrix; Singular value decomposition is performed on the environmental gradient matrix, and the right singular vectors corresponding to the singular values ​​are extracted as orthogonal basis vectors. The coordinate space constructed by the orthogonal basis vectors is used as the transformation vector field. The physiological parameter values ​​at each moment in the physiological data sequence are projected onto the change vector field, the projection coordinates at each moment in the change vector field are recorded, and the projection coordinates are connected sequentially to form the physiological state evolution curve. Calculate the rate of change of the angle between the direction vectors of adjacent projected coordinates on the physiological state evolution curve, and identify the projected coordinates corresponding to the local maxima of the rate of change of the angle as curvature abrupt change points. Extract the time markers corresponding to the curvature abrupt change points, map the time markers back to the environmental gradient matrix to obtain the gradient values ​​of each environmental parameter at the corresponding time markers, extract the projection components of the gradient values ​​on the orthogonal basis vectors as the direction of change of environmental parameters, and obtain the set of physiologically sensitive directions.

[0009] Extract time periods from physiological data sequences where physiological parameters fall within a preset healthy range, and record the positional distribution of environmental parameters in the change vector field within these time periods to obtain the comfortable environment distribution area, including: Mark the moments in the physiological data sequence where the physiological parameter values ​​are within a preset healthy range, and group the moments with a time difference of less than a preset time interval into time periods to obtain a set of healthy time periods; Calculate the duration of each time period in the set of healthy time periods, use the duration as an exponent to perform a power operation on a preset base to obtain a weight coefficient, and assign it to each time period to obtain a weighted time period set; The environmental parameter values ​​within each time period in the weighted time period set are mapped to the change vector field to obtain the location coordinates, and the corresponding weight coefficients of the time period are assigned to each location coordinate to obtain the weighted location distribution. A probability density distribution function is constructed by weighted kernel density estimation of the weighted location distribution. Local maxima of the probability density distribution function are extracted, and the distribution is expanded to the spatial region enclosed by preset isodensity lines with the local maxima as the center to obtain the comfortable environment distribution region.

[0010] The system searches along physiologically sensitive directions to find adjustment paths from the current environmental parameter location to the comfortable environment distribution area, calculates the cumulative energy consumption of each adjustment path, and obtains multiple candidate regulation paths, including: Starting from the current environmental parameter location, construct search rays along each physiologically sensitive direction in the set of physiologically sensitive directions, calculate the intersection points of each search ray with the boundary of the comfortable environment distribution area, and use the lines connecting the current environmental parameter location to each intersection point as adjustment paths to obtain the set of adjustment paths; For each adjustment path in the adjustment path set, a piecewise linear function of environmental parameter change is established. The rate of change of environmental parameters is obtained by differentiating each piecewise linear function in the time dimension. The rate of change of environmental parameters is multiplied by the power response coefficient of the environmental control equipment and integrated over time to obtain the piecewise energy consumption sequence of each adjustment path. Extract the physiologically sensitive direction of each segment in the segmented energy consumption sequence of each adjustment path, obtain the sensitivity value corresponding to each physiologically sensitive direction and normalize it as a weight coefficient, and perform weighted summation on the segmented energy consumption sequence to obtain the cumulative energy consumption of each adjustment path. Multiple candidate control paths are obtained by screening adjustment paths whose cumulative energy consumption is less than the preset energy consumption threshold.

[0011] Identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector including: Multiple candidate control paths are sampled in the changing vector field to obtain sampling points. The gradient vector at each sampling point is calculated and the field is superimposed. The spatial location where the gradient magnitude appears to be local maximum after field superposition is extracted as the path convergence point, and the path convergence point set is obtained. Spatial connectivity analysis is performed on the set of path convergence points to merge spatially connected path convergence points into intersection regions. The gradient magnitude distribution entropy value of path convergence points in each intersection region is calculated to obtain intersection regions labeled with entropy values. Extract the environmental parameter vectors corresponding to the path convergence points within the intersection area labeled with entropy values, and calculate the centroid of the environmental parameter vectors of each intersection area to obtain the centroid environmental parameter vectors of each intersection area. The centroid environmental parameter vectors of each intersection region are weighted and averaged using the reciprocal of the entropy value of each intersection region as the weight, to obtain the stable control vector.

[0012] The difference vector is decomposed into components along the physiologically sensitive direction, and time-series arranged according to the environmental propagation rate of each component to obtain the segmented regulation sequence, including: The difference vector is decomposed by projection along the set of physiologically sensitive directions to obtain the components and projection magnitudes of the set along the physiologically sensitive directions. Obtain the environmental propagation rate of each component corresponding to the component along the physiologically sensitive direction set, sort the environmental propagation rates of each component to construct a cumulative distribution function, calculate the derivative value of each sampling point of the cumulative distribution function, and mark the range of environmental propagation rates corresponding to adjacent sampling points whose derivative values ​​are less than the median of the derivative values ​​as plateau intervals to obtain the set of propagation rate plateau intervals. The components along the physiologically sensitive direction are assigned to the corresponding platform intervals of the propagation rate platform interval set according to the environmental propagation rate of each component. The arithmetic mean of the product of the projection amplitude and the environmental propagation rate of each component in each platform interval is calculated to obtain the energy characteristic value of each platform interval. Based on the environmental propagation rate of each component, the propagation rate platform intervals are sorted according to the energy characteristic values ​​of each platform interval and assigned incremental execution numbers for time-series arrangement. The components along the physiologically sensitive direction within each platform interval are extracted sequentially according to the execution sequence number and assigned to continuous time periods to obtain the segmented regulation sequence.

[0013] Converting the segmented control sequence into execution parameters for environmental control equipment and sending control commands includes: Extract the control target values ​​for each time period in the segmented control sequence, query the correspondence between the environmental control equipment and the control target values, calculate the difference between the current output value of the environmental control equipment and the control target value as the control quantity, and obtain the equipment execution parameter sequence; Extract the duration of each time period in the segmented control sequence, calculate the control rate corresponding to each device execution parameter in the device execution parameter sequence, sort the execution priorities according to the control rate from large to small, and obtain the priority-bearing device execution parameter sequence; The sequence of priority-based device execution parameters is bound to the start time of each time period in the segmented control sequence. After being sorted by execution priority within the time period, it is converted into a communication protocol format and control commands are sent to the environmental control equipment.

[0014] This invention provides an IoT-based health and wellness space environment control system, the system comprising: The data acquisition module is used to collect environmental parameters and physiological parameters of the target population within the health and wellness space, and to obtain environmental data sequences and physiological data sequences. The sensitive direction analysis module is used to construct a change vector field of environmental data sequence, map physiological data sequence to change vector field to form physiological state evolution curve, extract the change direction of environmental parameters corresponding to curvature change point in physiological state evolution curve, and obtain physiological sensitive direction set; The comfort zone determination module is used to extract time periods from physiological data sequences where physiological parameters are within a preset healthy range, record the positional distribution of environmental parameters in the change vector field during the time periods, and obtain the comfortable environment distribution area. The regulation path generation module is used to search along the physiologically sensitive direction set for adjustment paths leading from the current environmental parameter position to the comfortable environment distribution area, calculate the cumulative energy consumption of each adjustment path, and obtain multiple candidate regulation paths; The stable vector extraction module is used to identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector. The segmented regulation generation module is used to calculate the difference vector between the stable regulation vector and the current environmental parameter vector. The difference vector is decomposed into components along the physiologically sensitive direction set, and the components are arranged in time sequence according to the environmental propagation rate of each component to obtain the segmented regulation sequence. The control execution module is used to convert the segmented control sequence into execution parameters for the environmental control equipment and send control commands.

[0015] One technical solution provided in this embodiment of the invention is an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any of the aforementioned methods.

[0016] One technical solution provided in this embodiment of the invention is a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement the steps in any of the aforementioned methods.

[0017] This invention constructs an environmental data change vector field and combines it with the evolution process of human physiological state to establish a dynamic correlation between environmental changes and human health status, enabling accurate identification of physiological sensitivities in different population groups. By determining the distribution area of ​​comfortable environment and searching for low-energy-consumption regulation paths, the stability of environmental regulation process and energy consumption control capability can be improved. By generating stable regulation vectors using the intersection area of ​​candidate regulation paths and combining them with environmental propagation rate for segmented temporal regulation, the impact of sudden changes in environmental parameters on human comfort can be reduced, and the efficiency of coordinated regulation of multiple environmental parameters and the overall comfort of health and wellness space can be improved. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the IoT-based health and wellness space environment control method provided in this embodiment of the invention; Figure 2 This is a schematic diagram of the structure of the Internet of Things-based health and wellness space environment control system according to an embodiment of the present invention. Detailed Implementation

[0019] like Figure 1 As shown, Figure 1 A flowchart of an IoT-based method for regulating the environment of a health and wellness space, provided in an embodiment of the present invention, is included. The method comprises the following steps: Step 101: Collect environmental parameters and physiological parameters of the target population within the health and wellness space to obtain environmental data sequences and physiological data sequences.

[0020] Step 102: Construct a change vector field for the environmental data sequence, map the physiological data sequence to the change vector field to form a physiological state evolution curve, extract the direction of change of environmental parameters corresponding to the curvature change point in the physiological state evolution curve, and obtain a set of physiologically sensitive directions.

[0021] In some embodiments of the present invention, step 102 may specifically include the following sub-steps: Sub-step 1021: Calculate the gradient vector of each environmental parameter in the environmental data sequence in the time dimension, and construct a matrix by using each time point as the row index and the gradient value of each environmental parameter as the column index to obtain the environmental gradient matrix. Sub-step 1022: Perform singular value decomposition on the environmental gradient matrix, extract the right singular vectors corresponding to the singular values ​​as orthogonal basis vectors, and use the coordinate space constructed by the orthogonal basis vectors as the transformation vector field. Sub-step 1023: Project the physiological parameter values ​​at each moment in the physiological data sequence onto the change vector field, record the projection coordinates of each moment in the change vector field and connect the projection coordinates sequentially to form a physiological state evolution curve. Sub-step 1024: Calculate the rate of change of the angle between the direction vectors of adjacent projected coordinates on the physiological state evolution curve, and identify the projected coordinates corresponding to the local maxima of the rate of change of the angle as the curvature abrupt change point. Sub-step 1025: Extract the time markers corresponding to the curvature abrupt change points, map the time markers back to the environmental gradient matrix to obtain the gradient values ​​of each environmental parameter at the time corresponding to the time markers, extract the projection components of the gradient values ​​on the orthogonal basis vectors as the direction of change of environmental parameters, and obtain the set of physiologically sensitive directions.

[0022] Environmental parameters and physiological parameters of the target population within the wellness and health space were collected to form a time-series dataset. Environmental parameters included multi-dimensional indicators such as air temperature, humidity, light intensity, air quality index, and noise level, which were continuously monitored through a sensor network distributed throughout the wellness and health space, with a collection frequency set to once per minute. Physiological parameters covered key health indicators such as heart rate, blood pressure, body temperature, and blood oxygen saturation, which were monitored in real time by wearable devices to ensure the synchronicity and accuracy of data collection. The collected data were aligned according to timestamps to establish a correspondence between the environmental data series and the physiological data series, laying the data foundation for subsequent analysis and processing.

[0023] The gradient vector of each environmental parameter in the environmental data sequence is calculated along the time dimension. For each environmental parameter, the ratio of the numerical difference between adjacent time points to the time interval is calculated to obtain the rate of change of that parameter at the corresponding time point. The gradient values ​​of all environmental parameters at each time point are organized into a matrix, where the row index represents the time point and the column index represents different environmental parameters, forming an environmental gradient matrix. This matrix reflects the dynamic change characteristics of the environmental parameters in the health and wellness space and can comprehensively describe the coordinated change patterns of multi-dimensional environmental factors.

[0024] Singular value decomposition (SVD) is performed on the environmental gradient matrix, which decomposes the original matrix into a product of three matrices: a left singular vector matrix, a singular value diagonal matrix, and a right singular vector matrix. The right singular vectors corresponding to the first few components with larger singular values ​​are selected as orthogonal basis vectors. These basis vectors represent the main directions and patterns of environmental parameter changes. A multidimensional coordinate space is constructed using these orthogonal basis vectors as a vector field describing environmental changes. This vector field effectively reduces dimensionality while preserving key information about environmental changes, mapping complex multidimensional environmental changes to a lower-dimensional space for analysis.

[0025] For each physiological parameter vector at any given time, its projection components along the directions of each orthogonal basis vector are calculated using inner product operations, yielding the coordinate representation of that time in the vector field. The projected coordinates of each time step are then connected sequentially in chronological order to form a continuous trajectory curve, i.e., a physiological state evolution curve. This curve geometrically reflects the dynamic evolution of the target population's physiological state driven by environmental changes, providing an intuitive visual representation for identifying sensitive responses.

[0026] Three consecutive projected coordinate points on the curve are selected, and the direction vectors from the previous point to the current point and from the current point to the next point are calculated respectively. The curvature of the curve at the current point is obtained by calculating the angle between the vectors. The ratio of the change in angle at adjacent positions to the corresponding time interval is calculated to obtain the numerical value of the angle change rate. By finding local maxima in the angle change rate sequence, curvature abrupt change points on the physiological state evolution curve are identified. These abrupt change points mark the key moment nodes when significant changes occur in the physiological state.

[0027] The time markers corresponding to curvature abrupt change points are extracted, and a precise mapping relationship with changes in environmental parameters is established. The identified abrupt change moments are remapped back into the original environmental gradient matrix to obtain the specific gradient values ​​of each environmental parameter at these key moments. Vector projection calculations are performed on the gradient value of each environmental parameter to obtain its decomposition components along each orthogonal basis vector direction. The projected components are combined according to weights to form a feature vector describing the direction of environmental parameter change. All environmental change direction vectors corresponding to curvature abrupt change points are collected to form a complete set of physiologically sensitive directions.

[0028] The set of physiologically sensitive directions quantitatively describes the patterns and trends of environmental parameter changes that cause significant changes in the physiological state of the target population. Each directional vector not only indicates the dominant factor of environmental change but also reflects the composite effect of multiple environmental parameters working together. By analyzing the distribution characteristics and statistical regularities of the sensitive directions, the most critical environmental regulation dimensions affecting physiological health can be identified. These sensitive directions provide a scientific basis for the subsequent formulation of intelligent environmental regulation strategies, enabling regulatory measures to precisely target specific environmental change patterns that cause physiological discomfort.

[0029] Based on the analysis of the set of physiologically sensitive directions, the most critical environmental regulation dimensions and change thresholds affecting physiological health can be identified. By statistically analyzing the distribution patterns and frequency of occurrence of sensitive direction vectors, the importance ranking of various environmental parameters in inducing physiological mutations can be determined. When real-time monitoring detects changes in environmental parameters along the identified sensitive directions, the degree of physiological state alteration that the trend may be caused is judged based on the correspondence between changes in that direction and physiological responses in historical data. Using the direction vectors in the sensitive direction set as target guides for environmental regulation, control strategies can be formulated to avoid changes along sensitive directions or to adjust in the opposite direction, thereby realizing a shift from a passive response to a proactive prevention management model.

[0030] This invention achieves effective identification of the complex nonlinear relationship between changes in environmental parameters and physiological responses through vector field mapping and curvature analysis. It can accurately capture key environmental factors that cause sudden changes in physiological state, providing precise parameter configuration guidance for intelligent health and wellness environment regulation, significantly improving the pertinence and effectiveness of environmental regulation, and promoting the in-depth development of personalized health management.

[0031] Step 103: Extract time periods from the physiological data sequence where the physiological parameters are within a preset healthy range, record the position distribution of environmental parameters in the change vector field within the time period, and obtain the comfortable environment distribution area.

[0032] In some embodiments of the present invention, step 103 may specifically include the following sub-steps: Sub-step 1031: Mark the moments when the physiological parameter values ​​in the physiological data sequence are within the preset healthy range, and group the moments when the time difference between adjacent moments is less than the preset time interval into time periods to obtain a set of healthy time periods; Sub-step 1032: Calculate the duration of each time period in the set of healthy time periods, use the duration as an exponent to perform a power operation on a preset base to obtain a weight coefficient, and assign it to each time period to obtain a weighted time period set. Sub-step 1033: Map the environmental parameter values ​​within each time period in the weighted time period set to the change vector field to obtain the location coordinates, and assign the corresponding weight coefficients for each location coordinate to obtain the weighted location distribution. Sub-step 1034 involves performing weighted kernel density estimation on the weighted location distribution to construct a probability density distribution function, extracting local maxima of the probability density distribution function, and expanding from the local maxima to the spatial region enclosed by preset isodensity lines to obtain the comfortable environment distribution region.

[0033] The system extracts time periods from physiological data sequences where physiological parameters fall within a preset healthy range to establish a foundational dataset for comfortable environment recognition. The preset healthy range is set based on medical standards and individual differences, including heart rate between 60 and 100 beats per minute, systolic blood pressure between 90 and 140 mmHg, and blood oxygen saturation above 95%. The system iterates through the entire physiological data sequence, checking each moment to ensure that all physiological parameter values ​​simultaneously meet the healthy range conditions. Moments meeting these conditions are marked, forming a sequence of identifiers for healthy state moments.

[0034] After marking, a temporal continuity analysis is performed on adjacent health status moments to calculate the time interval between adjacent marked moments. A preset time interval of 5 minutes is set; when the time difference between two adjacent marked moments is less than this threshold, these moments are merged into a single continuous time period. By traversing all marked moments and applying the merging rule, several independent health time periods are obtained, each containing start and end time information. All independent health time periods are collected and organized to form a complete set of health time periods.

[0035] The duration of each time period in the set of healthy time periods is calculated, and a duration-based weighting mechanism is established. The duration is obtained by subtracting the start time from the end time, calculated in minutes. A natural constant is chosen as the base, and the duration is used as the exponent for power operation to obtain the weight coefficient for each time period. The formula for calculating the weight coefficient is: w = e t / 60 Where w represents the weighting coefficient, t represents the duration of the time period, and 60 in the denominator is used to standardize the duration. Longer healthy time periods receive higher weighting coefficients, reflecting their importance in comfort environment identification. The calculated weighting coefficients are assigned to the corresponding time periods to form a weighted time period set.

[0036] The environmental parameter values ​​within each time period of the weighted time period set are mapped to the previously constructed change vector field to obtain the position coordinates of the environmental state in the vector field. For each time period, the environmental parameter values ​​at all times within that period are extracted, and these parameter values ​​are converted into coordinate representations in the change vector field through vector projection operations. The weight coefficients corresponding to the time period are assigned to all position coordinates within that period to establish a weighted position distribution dataset. The weighted position distribution not only records the spatial distribution of environmental parameters in the vector field under comfortable conditions, but also reflects the importance and reliability of different positions through weights.

[0037] A weighted kernel density estimation is performed on the weighted location distribution to construct a probability density function describing the distribution of the comfortable environment. A Gaussian kernel function is chosen as the basic function for density estimation, and its bandwidth parameter is adaptively adjusted according to the distribution density of the data points. The weighted kernel density estimation formula is as follows: Where f(x) represents the probability density value at position x, n represents the total number of data points, and w i x represents the weight coefficient of the i-th data point. i Let represent the position coordinates of the i-th data point, K represent the kernel function, and h represent the bandwidth parameter. This formula is used to calculate the probability density values ​​at each position in the changing vector field, forming a continuous probability density distribution function.

[0038] Local maxima are identified within the constructed probability density distribution function; these points represent the concentrated distribution centers of the comfortable environment in the vector field. All local maxima locations are identified by calculating the gradient of the density function and finding points where the gradient is zero. For each local maximum, its density value is calculated, and the threshold for the isodensity lines is set to 70% of the maximum value. The distribution region of the comfortable environment is formed by expanding outwards from the local maximum points to the closed region enclosed by the isodensity lines.

[0039] The distribution of comfortable environments manifests as several irregular spatial regions in the changing vector field, each corresponding to a typical comfortable environment configuration pattern. The size of each region reflects the stability and adaptability of that configuration, and the location coordinates within each region can be mapped back to the original environmental parameter space to obtain specific combinations of environmental parameters. By analyzing the characteristics and distribution patterns of different regions, various effective comfortable environment configuration schemes can be identified, providing target references for environmental regulation.

[0040] The establishment of comfortable environment distribution zones provides clear optimization targets and adjustment directions for intelligent environmental control. When the real-time monitored environmental state deviates from the comfortable zone, the distance and direction from the current location to the nearest comfortable zone can be calculated, and corresponding environmental parameter adjustment strategies can be formulated. The control strategy prioritizes the parameter combination with the smallest adjustment amplitude and the most significant effect, achieving efficient and precise environmental optimization.

[0041] This invention effectively identifies the distribution areas of environmental parameters corresponding to a good physiological state through time-weighted and kernel density estimation, providing a scientific standard for the configuration of a comfortable environment for health and wellness spaces. It significantly improves the target clarity and optimization effect of environmental regulation, and realizes the precise definition and intelligent maintenance of a personalized comfortable environment.

[0042] Step 104: Search along the physiologically sensitive direction set for adjustment paths leading from the current environmental parameter position to the comfortable environment distribution area, calculate the cumulative energy consumption of each adjustment path, and obtain multiple candidate regulation paths.

[0043] In some embodiments of the present invention, step 104 may specifically include the following sub-steps: Sub-step 1041: Starting from the current environmental parameter position, construct search rays along each physiologically sensitive direction in the set of physiologically sensitive directions, calculate the intersection points of each search ray with the boundary of the comfortable environment distribution area, and use the lines connecting the current environmental parameter position to each intersection point as adjustment paths to obtain the set of adjustment paths; Sub-step 1042: Establish piecewise linear functions of environmental parameter changes for each adjustment path in the adjustment path set; differentiate each piecewise linear function in the time dimension to obtain the rate of change of environmental parameters; multiply the rate of change of environmental parameters by the power response coefficient of the environmental control equipment and integrate over time to obtain the piecewise energy consumption sequence of each adjustment path. Sub-step 1043: Extract the physiologically sensitive direction of each segment in the segmented energy consumption sequence of each adjustment path, obtain the sensitivity value corresponding to each physiologically sensitive direction and normalize it as a weight coefficient, and perform weighted summation on the segmented energy consumption sequence to obtain the cumulative energy consumption of each adjustment path. Sub-step 1044: Filter adjustment paths with cumulative energy consumption less than the preset energy consumption threshold to obtain multiple candidate control paths.

[0044] Starting from the position of the current environmental parameters in the changing vector field, search rays are constructed along each sensitive direction in the set of physiologically sensitive directions to find a path leading to the comfortable environment distribution area. The current environmental parameter values ​​are mapped onto the changing vector field through projection transformation to obtain the coordinate representation of the current position. Using this position as the starting point, each direction vector in the set of physiologically sensitive directions is used as the ray direction to construct multiple search rays originating from the current position. Each search ray extends until it intersects the boundary of the comfortable environment distribution area. The endpoint position of each ray is determined by calculating the intersection point of the ray equation and the boundary curve of the area.

[0045] Calculate the coordinates of the intersection points between each search ray and the boundary of the comfortable environment distribution area, establishing a direct path from the current location to the comfortable area. For each search ray, an intersection algorithm between the ray and the boundary curve is used. The ray equation is parameterized and solved simultaneously with the boundary function to obtain the precise coordinates of the intersection points. The lines connecting the current environmental parameter location to each intersection point are used as candidate paths for environmental adjustment, forming a set of adjustment paths. Each adjustment path represents a specific environmental parameter change scheme; the direction of the path reflects the combination of environmental parameters to be adjusted, and the length of the path reflects the overall magnitude of the adjustment.

[0046] For each path in the adjustment path set, a piecewise linear function is established to describe the changes in environmental parameters over time. Each path is divided into several linear segments according to the complexity of parameter changes, with the rate of change of environmental parameters within each segment remaining constant. When establishing the piecewise linear function, the time length of each segment is allocated according to the magnitude of parameter changes, with segments having larger magnitudes allocated longer adjustment times to avoid excessively rapid parameter jumps. The piecewise linear function is differentiated along the time dimension to obtain the numerical rate of change of environmental parameters within each segment.

[0047] The instantaneous power demand for each path segment is calculated by multiplying the rate of change of environmental parameters by the power response coefficient of the corresponding control equipment. The power response coefficient reflects the energy consumption characteristics of the control equipment under unit parameter changes, including the power coefficient of air conditioning equipment for temperature regulation, the power coefficient of lighting equipment for light intensity regulation, and the power coefficient of ventilation equipment for air quality regulation. The instantaneous power of each segment is integrated over the corresponding time period to obtain the energy consumption value of each path segment, forming a segmented energy consumption sequence for each adjustment path. The formula for calculating the segmented energy consumption sequence is: E k Let P represent the energy consumption of the k-th segment. k Let s represent the average power of the k-th segment. k and s k+1 These represent the start and end times of the k-th segment, respectively.

[0048] The physiologically sensitive directions of each segment in the segmented energy consumption sequence of each adjustment path are extracted, and a sensitivity-weighted energy consumption assessment mechanism is established. By analyzing the matching degree between the direction vector of each path segment and the set of physiologically sensitive directions, the dominant sensitive direction corresponding to each path segment is determined. The sensitivity value obtained from curvature analysis for each physiologically sensitive direction is acquired; this value reflects the intensity of the influence of changes along that direction on the physiological state. The sensitivity values ​​are normalized and converted into weight coefficients between 0 and 1. A weighted summation operation is performed on the segmented energy consumption sequences to obtain the cumulative energy consumption of each adjustment path. The cumulative energy consumption calculation formula is: E t α represents the cumulative energy consumption of the path. k E represents the normalized weight coefficient corresponding to the sensitive direction of the k-th segment. k Let m represent the energy consumption of the k-th segment, and m represent the total number of path segments.

[0049] The sensitivity-weighted cumulative energy consumption calculation not only considers the actual energy cost of the path but also incorporates the importance assessment of physiological impacts. Environmental adjustments along high-sensitivity directions may have higher energy consumption, but their significant improvement in physiological comfort may result in a better overall cost-effectiveness after weighted calculation. Conversely, adjustments along low-sensitivity directions, even with lower energy consumption, may have limited effects, leading to a less than ideal overall evaluation.

[0050] Each adjustment path is screened based on a preset energy consumption threshold, retaining paths with cumulative energy consumption less than the threshold as candidate control schemes. The preset energy consumption threshold is set based on the energy budget of the health and wellness space and the power limitations of the control equipment, typically set to 80% of the equipment's rated power consumption to ensure the feasibility and stability of the control process. The screened adjustment paths are organized into a candidate control path set, with each path containing a complete parameter adjustment sequence, expected adjustment time, and cumulative energy consumption information.

[0051] The candidate control path set provides a variety of optimization options for environmental control in health and wellness spaces. Control decisions can be flexibly selected based on real-time energy consumption limitations, the urgency of control, and user preferences. When energy consumption is sufficient, the most effective high-sensitivity path can be selected, while when energy consumption is limited, a path with lower energy consumption but still effectively improves the environment can be selected, achieving a dynamic balance between control effectiveness and energy cost.

[0052] This invention establishes a path optimization mechanism that balances regulation effectiveness and energy cost through sensitive direction-oriented path search and sensitivity-weighted energy consumption assessment. It provides diversified environmental regulation options for health and wellness spaces, significantly improves the scientific nature and adaptability of regulation decisions, and achieves highly efficient and energy-saving personalized environmental optimization.

[0053] Step 105: Identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector.

[0054] In some embodiments of the present invention, step 105 may specifically include the following sub-steps: Sub-step 1051: Sample multiple candidate control paths in the changing vector field to obtain sampling points, calculate the gradient vector at each sampling point and perform field superposition, extract the spatial location where the gradient magnitude appears to be a local maximum after field superposition as the path convergence point, and obtain the path convergence point set. Sub-step 1052: Perform spatial connectivity analysis on the set of path convergence points, merge spatially connected path convergence points into intersection regions, calculate the gradient magnitude distribution entropy value of path convergence points in each intersection region, and obtain intersection regions labeled with entropy values. Sub-step 1053: Extract the environmental parameter vectors corresponding to the path convergence points in the intersection area labeled with entropy values, and calculate the centroid of the environmental parameter vectors of each intersection area to obtain the centroid environmental parameter vectors of each intersection area. Sub-step 1054: The centroid environmental parameter vectors of each intersection region are weighted and averaged using the reciprocal of the entropy value of each intersection region as the weight to obtain the stable control vector.

[0055] Multiple candidate control paths are uniformly sampled in a changing vector field to obtain a set of discrete sampling points along the paths. The sampling interval is set to one-tenth of the total path length, and sampling is performed at equal intervals from the starting point to the ending point along each candidate control path to ensure that the sampling points fully represent the overall characteristics of the path. The sampling points from all candidate paths are aggregated to form a unified sampling point dataset, where each sampling point contains its position coordinates in the changing vector field and corresponding environmental parameter information.

[0056] The gradient vector at each sampling point is calculated to describe the changing trend and intensity of environmental parameters at that location. Partial derivatives for each parameter dimension are obtained by differential calculation of environmental parameter values ​​at neighboring locations around the sampling point, and these are combined to form a complete gradient vector. A field superposition operation is performed on the gradient vectors of all sampling points, summing the gradient vectors at the same or neighboring locations in space to obtain the superimposed composite gradient field. During the field superposition process, gradient vectors in the same direction reinforce each other, while gradient vectors in opposite directions cancel each other out, forming a composite field distribution with a clear directional orientation.

[0057] Gradient magnitudes are calculated at various locations within the synthetic gradient field. Spatial locations exhibiting local maxima of gradient magnitude are identified as path convergence points. The gradient magnitude is obtained by taking the square root of the sum of the squares of the gradient vector components, reflecting the overall intensity of environmental parameter changes at that location. A sliding window approach is used to search for local maxima throughout the field space, and locations with gradient magnitudes greater than their neighboring locations and exceeding a preset threshold are marked as path convergence points. Path convergence points represent the concentrated spatial manifestation of the influence of multiple control paths and are key areas for the effectiveness of environmental control.

[0058] Spatial connectivity analysis is performed on the identified set of path convergence points, grouping spatially close and connected convergence points into the same intersection region. A connectivity distance threshold is set at 5% of the distance between two points in the changing vector field space. The Euclidean distance between any two convergence points is calculated, and points with distances less than the threshold are marked as connected. A connected component algorithm is used to group all convergence points, merging those with direct or indirect connectivity into the same intersection region, forming several independent spatial regions.

[0059] Calculate the gradient magnitude distribution entropy of path convergence points within each intersection region to quantify the stability and consistency of environmental control effects within the region. For each intersection region, collect gradient magnitude data from all convergence points within the region, divide the magnitude range into equally spaced bins, and calculate the probability distribution of the number of convergence points within each magnitude interval. The entropy calculation formula is: Where H represents the entropy value of the intersection region, L represents the total number of amplitude bins, and p j This represents the proportion of convergence points within the j-th sub-bin to the total number. A smaller entropy value indicates a more concentrated distribution of gradient amplitudes within the region, resulting in a more stable control effect; a larger entropy value indicates a more dispersed distribution, leading to poorer consistency in the control effect.

[0060] Environmental parameter vectors corresponding to path convergence points within each intersection region are extracted to establish a mathematical representation of the regional environmental characteristics. The position coordinates of each convergence point in the change vector field are inversely mapped back to the original environmental parameter space to obtain the corresponding combination of environmental parameters. The centroid of the environmental parameter vectors of all convergence points within each intersection region is calculated. By averaging each parameter dimension, the centroid environmental parameter vector representing the overall environmental characteristics of the region is obtained. The centroid vector comprehensively reflects the dominant trend and typical configuration of environmental regulation within the intersection region.

[0061] Using the reciprocal of the entropy value of each intersection region as a weighting coefficient, a weighted average is performed on the centroid environmental parameter vectors of each region to obtain the stable control vector. The weighting coefficient is calculated using the reciprocal of the entropy value, giving higher weights to stable regions with lower entropy values ​​and lower weights to unstable regions with higher entropy values. The formula for calculating the stable control vector is: V s Let H represent the stable control vector, R represent the total number of intersection regions, and H represent the stable control vector. r Let C represent the entropy value of the r-th intersection region. r This represents the centroid environmental parameter vector of the r-th intersection region.

[0062] The stable control vector represents the comprehensive optimization direction of multiple candidate control paths, integrating the control advantages of different paths and eliminating the local biases of individual paths. This vector not only considers the convergence degree of each path in space but also ensures the stability and reliability of the control scheme through entropy weighting. Compared to single-path control schemes, the stable control vector maintains better adaptability and robustness under complex environmental conditions.

[0063] Environmental control strategies based on stable control vectors have a higher success rate and better control effects, effectively avoiding control failures caused by environmental disturbances or equipment response deviations. Stable control vectors provide a scientifically reliable control benchmark for intelligent environmental management in health and wellness spaces, significantly improving the stability of the control system and user experience satisfaction.

[0064] This invention effectively integrates the advantages of multiple control paths through path convergence analysis and entropy weighting, constructing a comprehensive control scheme that balances control effectiveness and system stability. It provides a highly reliable environmental optimization strategy for health and wellness spaces, significantly improves the robustness and adaptability of the control system, and achieves stable and efficient intelligent environmental management.

[0065] Step 106: Calculate the difference vector between the stable regulation vector and the current environmental parameter vector, decompose the difference vector into components along the physiologically sensitive direction set, and arrange them in time sequence according to the environmental propagation rate of each component to obtain the segmented regulation sequence.

[0066] In some embodiments of the present invention, step 106 may specifically include the following sub-steps: Sub-step 1061: Project the difference vector along the set of physiologically sensitive directions to obtain the components and projection magnitudes of the set along the physiologically sensitive directions. Sub-step 1062: Obtain the environmental propagation rate of each component corresponding to the component of the set along the physiologically sensitive direction, sort the environmental propagation rates of each component to construct a cumulative distribution function, calculate the derivative value of each sampling point of the cumulative distribution function, and mark the range of environmental propagation rates corresponding to adjacent sampling points whose derivative values ​​are less than the median of the derivative values ​​as plateau intervals to obtain the set of propagation rate plateau intervals. Sub-step 1063: Assign the components of the set along the physiologically sensitive direction to the corresponding platform intervals of the set of propagation rate platform intervals according to the environmental propagation rate of each component, calculate the arithmetic mean of the product of the projection amplitude and the environmental propagation rate of each component in each platform interval, and obtain the energy characteristic value of each platform interval. Sub-step 1064: Based on the environmental propagation rate of each component, sort the platform intervals of the propagation rate platform interval set according to the energy characteristic values ​​of each platform interval and assign incremental execution numbers for time-series arrangement. Sub-step 1065: Extract the components along the physiologically sensitive direction within each platform interval according to the execution sequence number and assign them to continuous time periods to obtain the segmented regulation sequence.

[0067] The difference vector between the stable control vector and the current environmental parameter vector is calculated to determine the overall direction and magnitude of environmental control. Subtracting the current environmental parameter vector from the stable control vector yields the parameter change that needs to be controlled. Each component of the difference vector represents the value and direction of adjustment for environmental parameters such as temperature, humidity, light intensity, and air quality; positive values ​​indicate an increase in the parameter, while negative values ​​indicate a decrease. The difference vector provides the foundational data for subsequent control decomposition and time-series arrangement.

[0068] The difference vector is decomposed by projection along the set of physiologically sensitive directions to obtain the components and corresponding projection magnitudes in each sensitive direction. For each physiologically sensitive direction, the projection of the difference vector in that direction is calculated using vector dot product operations. The projection magnitude reflects the magnitude of the components of the difference vector in each sensitive direction, representing the intensity requirement for environmental regulation along that direction. The projection components of all sensitive directions are combined to form a complete decomposition result, ensuring that each component is independent and can completely reconstruct the original difference vector.

[0069] The environmental propagation rate corresponding to each projection component is obtained to describe the propagation characteristics of different control directions in space. The environmental propagation rate reflects the time required for changes in environmental parameters to diffuse and reach a stable state in the health and wellness space. The propagation rate of temperature regulation is relatively slow, the propagation rate of humidity regulation is moderate, the propagation rate of light regulation is relatively fast, and the propagation rate of air quality regulation depends on ventilation conditions. The environmental propagation rates of each component are sorted from smallest to largest, and a cumulative distribution function is constructed to describe the distribution law and statistical characteristics of the propagation rate.

[0070] The cumulative distribution function is differentiated using numerical differentiation to obtain the derivative values ​​at each sampling point. The median of all derivative values ​​is calculated as the criterion for determining the smoothness of the distribution. Adjacent sampling points with derivative values ​​less than the median are marked as candidate points for plateau regions. Adjacent candidate points are connected to form continuous plateau intervals, each representing a range where the propagation rate distribution is relatively concentrated. Identifying plateau intervals helps to classify and process control components with similar propagation characteristics.

[0071] Each projection component is assigned to a corresponding propagation rate plateau interval according to its environmental propagation rate, establishing a mapping relationship between components and intervals. For each plateau interval, all projection components assigned to that interval are collected, and the arithmetic mean of the product of the projection amplitude of each component and the environmental propagation rate is calculated to obtain the energy characteristic value of that interval. The formula for calculating the energy characteristic value is: E zone N represents the energy characteristic value of the plateau region. zone A represents the total number of components that fall into this interval. q V represents the projected amplitude of the q-th component. q This represents the environmental propagation rate of the q-th component.

[0072] The energy characteristic value comprehensively reflects the overall strength and propagation efficiency of the control components within a platform interval. A larger value indicates a more significant control effect within that interval, and it should be given priority in timing orchestration. The intervals are sorted according to their energy characteristic values, with intervals having larger energy characteristic values ​​receiving higher priority and those having smaller values ​​receiving lower priority. Incremental execution sequence numbers are assigned to each platform interval, forming the basic framework for timing orchestration.

[0073] The projected components within each platform interval are extracted sequentially according to the execution sequence number to construct a segmented control sequence. For each platform interval, all projected components within the interval are organized into a control segment, and consecutive execution time periods are allocated to them. The timing arrangement formula for the segmented control sequence is as follows: T seg T represents the execution duration of the control segment. base E represents the base time unit. zone E represents the energy characteristic value of the current interval. max This represents the maximum energy eigenvalue across all intervals.

[0074] The allocation of execution time ensures that control segments with higher energy characteristic values ​​receive more sufficient execution time, guaranteeing the full realization of the control effect. Control segments are sequentially linked according to their execution numbers, forming a complete segmented control sequence. Each segment contains specific environmental parameter adjustment instructions and expected adjustment time, providing detailed operational guidelines for the precise execution of the control equipment.

[0075] The segmented control sequence takes into account the differences in propagation characteristics of various environmental parameters and the required control intensity, and optimizes the control process through scientific timing arrangement. Control operations with rapid propagation are executed first to quickly improve the environmental state, while slow-propagating control operations are executed subsequently to ensure environmental stability. This arrangement avoids mutual interference between different control operations, improving the overall efficiency and accuracy of control.

[0076] This invention establishes a temporal control mechanism based on environmental propagation characteristics through differential vector decomposition and propagation rate analysis. It effectively solves the temporal conflict problem in multi-parameter parallel control, provides a scientific and reasonable control execution scheme for health and wellness spaces, significantly improves the coordination and effectiveness of environmental control, and achieves high-precision environmental parameter management.

[0077] Step 107: Convert the segmented control sequence into execution parameters for the environmental control equipment and send control commands.

[0078] In some embodiments of the present invention, step 107 may specifically include the following sub-steps: Sub-step 1071: Extract the control target value for each time period in the segmented control sequence, query the correspondence between the environmental control equipment and the control target value, calculate the difference between the current output value of the environmental control equipment and the control target value as the control quantity, and obtain the equipment execution parameter sequence; Sub-step 1072: Extract the duration of each time period in the segmented control sequence, calculate the control rate corresponding to each device execution parameter in the device execution parameter sequence, sort the execution priorities according to the control rate from large to small, and obtain the priority-bearing device execution parameter sequence. Sub-step 1073: Bind the priority-bearing device execution parameter sequence to the start time of each time period in the segmented control sequence, sort them according to execution priority within the time period, convert them into a communication protocol format, and send control commands to the environmental control equipment.

[0079] Target values ​​for environmental parameters such as temperature, humidity, light intensity, and air quality are read from each time period of the segmented control sequence. These abstract environmental parameter targets are then converted into control parameters that can be executed by specific equipment. A data table mapping environmental control equipment to target values ​​is queried. This data table pre-establishes mapping rules between environmental parameter values ​​and equipment operating parameters, including the correspondence between temperature setpoints and cooling / heating power for air conditioning equipment, humidity setpoints and operating levels for humidifiers / dehumidifiers, light intensity and brightness adjustment parameters for lighting equipment, and air quality indicators and purification intensity for air purifiers.

[0080] The difference between the current output value and the target value of each environmental control device is calculated to obtain the specific control quantity that the device needs to execute. The current operating status and output parameters of each control device are acquired in real time through an IoT sensor network, and the current output value is compared with the corresponding target value. The control quantity is calculated by subtracting the current value from the target value; a positive value indicates that the device output needs to be increased, a negative value indicates that the device output needs to be decreased, and a zero value indicates that the current state should be maintained. The control quantities of all devices are organized in time-period order to form a complete sequence of device execution parameters, providing the basic data for subsequent priority allocation and command transmission.

[0081] The duration information of each time period in the segmented control sequence is extracted, and the control rate is calculated in combination with the equipment execution parameters to establish a mechanism for assessing the urgency of equipment operation. The control rate is calculated by dividing the absolute value of the control quantity by the duration, reflecting the intensity of control that the equipment needs to complete per unit time.

[0082] A higher control rate indicates a higher level of urgency for the equipment operation, requiring a significant parameter adjustment within a limited timeframe. All equipment control rates are sorted from highest to lowest, with higher-rate equipment assigned higher execution priority and lower-rate equipment assigned lower execution priority. This priority allocation ensures that urgent control operations receive priority execution opportunities, avoiding delays in control effects due to equipment response latency.

[0083] By binding device execution parameters with corresponding priority information, a priority-based sequence of device execution parameters is formed. This sequence includes not only the specific operational parameters of the device but also the priority identifier and execution order information. The priority identifier is represented numerically, with smaller values ​​indicating higher priority and larger values ​​indicating lower priority. This priority-based sequence of device execution parameters provides a scientific scheduling basis for subsequent timing control and concurrent execution.

[0084] A precise time-dimensional control mechanism is established by binding the priority sequence of device execution parameters with the start times of each time period in the segmented control sequence. The start timestamp of each time period in the segmented control sequence is read and associated with all device execution parameters within that time period. This time binding ensures that all control operations can be initiated accurately at the predetermined time, achieving time synchronization for coordinated operation of multiple devices. Within each time period, the device execution parameters are rearranged according to their priority order to form a device operation list for that time period.

[0085] The equipment operation list is converted into a standardized communication protocol format to meet the communication interface requirements of different types of control equipment. The communication protocol format includes key information fields such as equipment identification code, operation type, parameter value, execution time, and priority. The equipment identification code uniquely identifies the target control equipment, the operation type identifies the specific control action, the parameter value contains the target state the equipment needs to be adjusted to, the execution time specifies the start time of the operation, and the priority information is used for task scheduling on the device side. The protocol format conversion process takes into account the interface differences between different equipment manufacturers, using a common data structure and encoding method to ensure compatibility.

[0086] Standardized control commands are sent to various environmental control devices to achieve the physical execution of segmented control sequences. These commands are transmitted to the corresponding control devices via an Internet of Things (IoT) communication network. Upon receiving the commands, the devices adjust their operations according to the specified parameters and timing. A reliable transmission mechanism is employed, including command confirmation, retransmission mechanisms, and status feedback, to ensure that each control command accurately reaches the target device and is correctly executed. The priority mechanism for device execution parameters is implemented at the device level; high-priority operations gain priority access to device resources, while low-priority operations are executed when resources are available.

[0087] A lower priority index indicates a higher priority. Normalization ensures the rationality and comparability of priority allocation. After receiving control commands, the equipment adjusts its internal task queue according to the priority index, prioritizing the execution of high-priority tasks to ensure the timely completion of critical control operations.

[0088] The execution status of control commands is monitored through a device feedback mechanism, tracking the completion of various control operations in real time. During the execution of control commands, the device periodically sends status updates to the control center, including current execution progress, device operating parameters, and any abnormal situations. This status feedback information is used to verify the control effectiveness and promptly identify execution deviations, providing data support for subsequent control optimization.

[0089] This invention achieves precise conversion of abstract control sequences into specific equipment operations through equipment parameter conversion and priority scheduling, establishes an efficient and reliable equipment control mechanism, ensures the accurate realization of complex environmental control needs at the physical level, significantly improves the execution accuracy and response speed of control commands, and provides stable and efficient intelligent environmental management capabilities for health and wellness spaces.

[0090] like Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of an IoT-based health and wellness space environment control system provided in an embodiment of the present invention. The system includes: The data acquisition module 201 is used to collect environmental parameters and physiological parameters of the target population within the health and wellness space, and to obtain environmental data sequences and physiological data sequences. The sensitive direction analysis module 202 is used to construct a change vector field of environmental data sequence, map physiological data sequence to change vector field to form physiological state evolution curve, extract the change direction of environmental parameters corresponding to curvature change point in physiological state evolution curve, and obtain physiological sensitive direction set. The comfort zone determination module 203 is used to extract time periods from physiological data sequences where physiological parameters are within a preset healthy range, record the position distribution of environmental parameters in the change vector field during the time periods, and obtain the comfortable environment distribution area. The regulation path generation module 204 is used to search along the physiologically sensitive direction set for adjustment paths leading from the current environmental parameter position to the comfortable environment distribution area, calculate the cumulative energy consumption of each adjustment path, and obtain multiple candidate regulation paths. The stable vector extraction module 205 is used to identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector. The segmented regulation generation module 206 is used to calculate the difference vector between the stable regulation vector and the current environmental parameter vector, decompose the difference vector into components along the physiologically sensitive direction set, and arrange them in time sequence according to the environmental propagation rate of each component to obtain the segmented regulation sequence. The control execution module 207 is used to convert the segmented control sequence into the execution parameters of the environmental control equipment and send control commands.

[0091] One technical solution provided in this embodiment of the invention is an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in any of the aforementioned methods.

[0092] One technical solution provided in this embodiment of the invention is a computer-readable storage medium storing a computer program, wherein the processor executes the computer program to implement the steps in any of the aforementioned methods.

[0093] The specific embodiments described above are preferred embodiments of the present invention and are not intended to limit the specific scope of the present invention. The scope of the present invention includes, but is not limited to, these specific embodiments. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for regulating the environment of health and wellness spaces based on the Internet of Things, characterized in that, Includes the following steps: Environmental parameters and physiological parameters of the target population within the health and wellness space were collected to obtain environmental data sequences and physiological data sequences; A change vector field of environmental data sequence is constructed, and physiological data sequence is mapped to the change vector field to form physiological state evolution curve. The direction of change of environmental parameters corresponding to the curvature change point in the physiological state evolution curve is extracted to obtain a set of physiologically sensitive directions. Extract time periods from physiological data sequences where physiological parameters are within a preset healthy range, record the positional distribution of environmental parameters in the change vector field within the time periods, and obtain the comfortable environment distribution area. The adjustment path from the current environmental parameter location to the comfortable environment distribution area is searched along the physiologically sensitive direction set, and the cumulative energy consumption of each adjustment path is calculated to obtain multiple candidate regulation paths; Identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector; The difference vector between the stable regulation vector and the current environmental parameter vector is calculated. The difference vector is decomposed into components along the physiologically sensitive direction. The components are then arranged in time according to their environmental propagation rates to obtain a segmented regulation sequence. The segmented control sequence is converted into execution parameters for environmental control equipment and control commands are sent.

2. The method according to claim 1, characterized in that, A change vector field is constructed for the environmental data sequence. The physiological data sequence is then mapped to the change vector field to form a physiological state evolution curve. The direction of environmental parameter change corresponding to the curvature abrupt change point in the physiological state evolution curve is extracted to obtain the set of physiologically sensitive directions, including: Calculate the gradient vector of each environmental parameter in the environmental data sequence along the time dimension, and construct a matrix by using each time point as the row index and the gradient value of each environmental parameter as the column index to obtain the environmental gradient matrix; Singular value decomposition is performed on the environmental gradient matrix, and the right singular vectors corresponding to the singular values ​​are extracted as orthogonal basis vectors. The coordinate space constructed by the orthogonal basis vectors is used as the transformation vector field. The physiological parameter values ​​at each moment in the physiological data sequence are projected onto the change vector field, the projection coordinates at each moment in the change vector field are recorded, and the projection coordinates are connected sequentially to form the physiological state evolution curve. Calculate the rate of change of the angle between the direction vectors of adjacent projected coordinates on the physiological state evolution curve, and identify the projected coordinates corresponding to the local maxima of the rate of change of the angle as curvature abrupt change points. Extract the time markers corresponding to the curvature abrupt change points, map the time markers back to the environmental gradient matrix to obtain the gradient values ​​of each environmental parameter at the corresponding time markers, extract the projection components of the gradient values ​​on the orthogonal basis vectors as the direction of change of environmental parameters, and obtain the set of physiologically sensitive directions.

3. The method according to claim 1, characterized in that, Extract time periods from physiological data sequences where physiological parameters fall within a preset healthy range, and record the positional distribution of environmental parameters in the change vector field within these time periods to obtain the comfortable environment distribution area, including: Mark the moments in the physiological data sequence where the physiological parameter values ​​are within a preset healthy range, and group the moments with a time difference of less than a preset time interval into time periods to obtain a set of healthy time periods; Calculate the duration of each time period in the set of healthy time periods, use the duration as an exponent to perform a power operation on a preset base to obtain a weight coefficient, and assign it to each time period to obtain a weighted time period set; The environmental parameter values ​​within each time period in the weighted time period set are mapped to the change vector field to obtain the location coordinates, and the corresponding weight coefficients of the time period are assigned to each location coordinate to obtain the weighted location distribution. A probability density distribution function is constructed by weighted kernel density estimation of the weighted location distribution. Local maxima of the probability density distribution function are extracted, and the distribution is expanded to the spatial region enclosed by preset isodensity lines with the local maxima as the center to obtain the comfortable environment distribution region.

4. The method according to claim 1, characterized in that, The system searches along physiologically sensitive directions to find adjustment paths from the current environmental parameter location to the comfortable environment distribution area, calculates the cumulative energy consumption of each adjustment path, and obtains multiple candidate regulation paths, including: Starting from the current environmental parameter location, construct search rays along each physiologically sensitive direction in the set of physiologically sensitive directions, calculate the intersection points of each search ray with the boundary of the comfortable environment distribution area, and use the lines connecting the current environmental parameter location to each intersection point as adjustment paths to obtain the set of adjustment paths; For each adjustment path in the adjustment path set, a piecewise linear function of environmental parameter change is established. The rate of change of environmental parameters is obtained by differentiating each piecewise linear function in the time dimension. The rate of change of environmental parameters is multiplied by the power response coefficient of the environmental control equipment and integrated over time to obtain the piecewise energy consumption sequence of each adjustment path. Extract the physiologically sensitive direction of each segment in the segmented energy consumption sequence of each adjustment path, obtain the sensitivity value corresponding to each physiologically sensitive direction and normalize it as a weight coefficient, and perform weighted summation on the segmented energy consumption sequence to obtain the cumulative energy consumption of each adjustment path. Multiple candidate control paths are obtained by screening adjustment paths whose cumulative energy consumption is less than the preset energy consumption threshold.

5. The method according to claim 1, characterized in that, Identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector including: Multiple candidate control paths are sampled in the changing vector field to obtain sampling points. The gradient vector at each sampling point is calculated and the field is superimposed. The spatial location where the gradient magnitude appears to be local maximum after field superposition is extracted as the path convergence point, and the path convergence point set is obtained. Spatial connectivity analysis is performed on the set of path convergence points to merge spatially connected path convergence points into intersection regions. The gradient magnitude distribution entropy value of path convergence points in each intersection region is calculated to obtain intersection regions labeled with entropy values. Extract the environmental parameter vectors corresponding to the path convergence points within the intersection area labeled with entropy values, and calculate the centroid of the environmental parameter vectors of each intersection area to obtain the centroid environmental parameter vectors of each intersection area. The centroid environmental parameter vectors of each intersection region are weighted and averaged using the reciprocal of the entropy value of each intersection region as the weight, to obtain the stable control vector.

6. The method according to claim 1, characterized in that, The difference vector is decomposed into components along the physiologically sensitive direction, and time-series arranged according to the environmental propagation rate of each component to obtain the segmented regulation sequence, including: The difference vector is decomposed by projection along the set of physiologically sensitive directions to obtain the components and projection magnitudes of the set along the physiologically sensitive directions. Obtain the environmental propagation rate of each component corresponding to the component along the physiologically sensitive direction set, sort the environmental propagation rates of each component to construct a cumulative distribution function, calculate the derivative value of each sampling point of the cumulative distribution function, and mark the range of environmental propagation rates corresponding to adjacent sampling points whose derivative values ​​are less than the median of the derivative values ​​as plateau intervals to obtain the set of propagation rate plateau intervals. The components along the physiologically sensitive direction are assigned to the corresponding platform intervals of the propagation rate platform interval set according to the environmental propagation rate of each component. The arithmetic mean of the product of the projection amplitude and the environmental propagation rate of each component in each platform interval is calculated to obtain the energy characteristic value of each platform interval. Based on the environmental propagation rate of each component, the propagation rate platform intervals are sorted according to the energy characteristic values ​​of each platform interval and assigned incremental execution numbers for time-series arrangement. The components along the physiologically sensitive direction within each platform interval are extracted sequentially according to the execution sequence number and assigned to continuous time periods to obtain the segmented regulation sequence.

7. The method according to claim 1, characterized in that, Converting the segmented control sequence into execution parameters for environmental control equipment and sending control commands includes: Extract the control target values ​​for each time period in the segmented control sequence, query the correspondence between the environmental control equipment and the control target values, calculate the difference between the current output value of the environmental control equipment and the control target value as the control quantity, and obtain the equipment execution parameter sequence; Extract the duration of each time period in the segmented control sequence, calculate the control rate corresponding to each device execution parameter in the device execution parameter sequence, sort the execution priorities according to the control rate from large to small, and obtain the priority-bearing device execution parameter sequence; The sequence of priority-based device execution parameters is bound to the start time of each time period in the segmented control sequence. After being sorted by execution priority within the time period, it is converted into a communication protocol format and control commands are sent to the environmental control equipment.

8. An IoT-based health and wellness space environment control system, used to implement the method described in any one of claims 1-7, characterized in that, The system includes: The data acquisition module is used to collect environmental parameters and physiological parameters of the target population within the health and wellness space, and to obtain environmental data sequences and physiological data sequences. The sensitive direction analysis module is used to construct a change vector field of environmental data sequence, map physiological data sequence to change vector field to form physiological state evolution curve, extract the change direction of environmental parameters corresponding to curvature change point in physiological state evolution curve, and obtain physiological sensitive direction set; The comfort zone determination module is used to extract time periods from physiological data sequences where physiological parameters are within a preset healthy range, record the positional distribution of environmental parameters in the change vector field during the time periods, and obtain the comfortable environment distribution area. The regulation path generation module is used to search along the physiologically sensitive direction set for adjustment paths leading from the current environmental parameter position to the comfortable environment distribution area, calculate the cumulative energy consumption of each adjustment path, and obtain multiple candidate regulation paths; The stable vector extraction module is used to identify the intersection region of multiple candidate control paths, extract the centroid environmental parameter vector of the intersection region, and obtain the stable control vector. The segmented regulation generation module is used to calculate the difference vector between the stable regulation vector and the current environmental parameter vector. The difference vector is decomposed into components along the physiologically sensitive direction set, and the components are arranged in time sequence according to the environmental propagation rate of each component to obtain the segmented regulation sequence. The control execution module is used to convert the segmented control sequence into execution parameters for the environmental control equipment and send control commands.

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 7.

Images