A method and system for intervening in the home environment of patients with chronic respiratory diseases

Abstract

The present invention discloses a method and system for home environmental intervention for patients with chronic respiratory diseases. The method includes sensor module construction, multi-node linkage tracing, sampling scheduling optimization, and environmental intervention. The present invention relates to the field of environmental health monitoring and intelligent intervention technology. The method realizes real-time collection of home environmental data by constructing a multimodal microsensor that integrates particulate matter, gas, temperature and humidity, and allergen detection; uses an improved propagation consistency index and parameter gradient mutation analysis to identify the propagation path and health risks of environmental factors that induce symptoms; combines a lightweight long-short-term memory network to dynamically optimize the sampling frequency and improve data collection efficiency; and ultimately realizes individual-oriented intelligent device linkage control and health behavior prompts. The method has the advantages of personalization, high response, and embeddability, which improves the intelligent level of chronic respiratory disease management.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental health monitoring and intelligent intervention, and specifically to a method and system for home environmental intervention for patients with chronic respiratory diseases. Background Art

[0002] Home environment intervention methods and systems for patients with chronic respiratory diseases, typically targeting patients with chronic respiratory diseases like asthma and chronic obstructive pulmonary disease (COPD), target factors in their daily living environment that may trigger or aggravate their condition (such as air pollution, abnormal temperature and humidity, and allergens). Through environmental monitoring, data analysis, and intelligent control, these systems promptly identify potential risks and implement intervention measures such as air purification, ventilation adjustment, or behavioral guidance, thereby reducing the frequency of symptom attacks, improving quality of life, and delaying disease progression. These systems generally include a sensor acquisition module, a data processing module, and an intervention execution module, and are characterized by long-term operation, individual adaptability, and high responsiveness.

[0003] However, existing home environmental intervention methods for patients with chronic respiratory diseases have technical problems such as lack of identification of the causes of the comprehensive linkage of multiple factors in the microenvironment, lack of dynamic intervention and adjustment strategies, delayed system response, and inability to personalize and adapt to differences in patient symptoms; in the existing risk tracing process of environmental factor sampling nodes, there are technical problems such as inability to effectively identify pollution transmission paths, lack of symptom causal reasoning capabilities, and rough health risk scoring; in the existing sampling scheduling optimization process of sensor nodes, there are technical problems such as waste of perception resources, sampling that does not dynamically adjust with changes in environmental conditions, and high algorithm computational complexity that makes it difficult to deploy on edge devices. Summary of the Invention

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a method and system for home environment intervention for patients with chronic respiratory diseases. In view of the technical problems in the existing home environment intervention methods for patients with chronic respiratory diseases, such as lack of identification of multi-factor integrated linkage inducements of microenvironment, lack of dynamic intervention adjustment strategy, delayed system response and inability to adapt to the differences in patients' symptoms, this solution creatively adopts a comprehensive home environment intervention method that combines multimodal micro-sensor module design, multi-node disease inducement risk linkage tracing and sampling node scheduling with disease inducement feature optimization, and realizes the inducing factors (PM2.5, , sudden changes in temperature and humidity, dust mite allergens) in the process of risk tracing of existing environmental factor sampling nodes, there are technical problems such as the inability to effectively identify pollution transmission paths, lack of symptom causal reasoning ability, and rough health risk scoring. This solution creatively adopts a spatiotemporal correlation parameter mutation analysis method that combines an improved transmission consistency index and parameter gradient changes to conduct multi-node linkage tracing, obtain characteristic data on the causes of respiratory disease symptoms, and realize the full-chain analysis of "factor fluctuation-node collaboration-transmission path-symptom risk"; In the process of sampling scheduling optimization of existing sensor nodes, there are technical problems such as waste of perception resources, sampling that does not dynamically adjust with changes in environmental conditions, and high algorithm computational complexity that is difficult to deploy on edge devices. This solution creatively adopts a lightweight improved long short-term memory network prediction method that combines parameter fluctuation characteristics to optimize the sampling scheduling of sensor modules, obtains predictive sampling strategy reference data, and realizes state-aware dynamic allocation of household microenvironment perception frequency.

[0005] The technical solution adopted by the present invention is as follows: The present invention provides a method for intervening in the home environment of patients with chronic respiratory diseases, the method comprising the following steps:

[0006] Step S1: sensor module construction;

[0007] Step S2: multi-node linkage tracing;

[0008] Step S3: sampling scheduling optimization;

[0009] Step S4: Family environment intervention.

[0010] Furthermore, in step S1, the sensor module is constructed to construct a multimodal micro-sensor module required for the home environment of patients with chronic respiratory diseases and realize real-time data collection. Specifically, a multimodal micro-sensor module including particulate matter detection, gas detection, temperature and humidity detection, and dust mite allergen detection is constructed in sequence, and by constructing the multimodal micro-sensor module, home environment sensor data is collected to obtain the original environmental data set.

[0011] Furthermore, in step S2, the multi-node linkage tracing is used for spatiotemporal correlation analysis of node data and identification of invisible health threats. Specifically, based on the original environmental data set, a spatiotemporal correlation parameter mutation analysis method combining an improved propagation consistency index and parameter gradient changes is used to perform multi-node linkage tracing to obtain characteristic data of respiratory disease symptom inducers, including the following steps:

[0012] Step S21: Node data preprocessing, specifically, constructing a multi-dimensional time series matrix by performing timestamp interpolation, Z-score normalization, and unit conversion on the asynchronous data of the sensor module based on the original environmental data set, thereby obtaining a multi-node basic data set;

[0013] The multi-node basic data set includes particulate matter detection data, gas detection data, temperature and humidity detection data, and dust mite allergen detection data;

[0014] Step S22: Propagation consistency index modeling is used to measure the synchronization of factor fluctuation propagation between different nodes. Specifically, based on the multi-node basic data set, the correlation coefficient model is improved by introducing the directional fluctuation gradient and the exponential time decay parameter to construct a propagation consistency index model;

[0015] Step S23: identifying parameter gradient changes, specifically, building a local adaptive parameter gradient mutation index based on a sliding window based on the multi-node basic data set to model abnormal changes in environmental factors and obtain environmental parameter gradient mutation index data;

[0016] Step S24: Spatiotemporal interaction path modeling is used to dynamically construct the propagation path of the suspected pollution source from the starting point to the symptom node. Specifically, based on the propagation consistency index model and the environmental parameter gradient mutation index data, the spatiotemporal interaction path modeling is performed by sequentially constructing the time series propagation graph data and screening the environmental factor pollution propagation path to obtain spatiotemporal interaction path reference data.

[0017] Step S25: Potential health risk identification, specifically, calculating a health risk score for each spatiotemporal interaction path based on the spatiotemporal interaction path reference data using an improved health risk weighting function, and screening the spatiotemporal interaction paths based on the health risk score to obtain potential risk identification reference data;

[0018] Step S26: Symptom alignment and linkage tracing, specifically, by constructing a symptom risk rule matching table, conducting rule mapping modeling between symptom types and environmental factors, and obtaining respiratory disease symptom inducement feature data through causal weight scoring and inducement feature screening.

[0019] Furthermore, in step S3, the sampling scheduling optimization is used to adjust the sensor sampling frequency. Specifically, based on the respiratory disease symptom inducement characteristic data and the environmental original data set, a lightweight improved long short-term memory network prediction method combined with parameter fluctuation characteristics is used to optimize the sampling scheduling of the sensor module to obtain predictive sampling strategy reference data, including the following steps:

[0020] Step S31: pre-processing the sampling state classification data, specifically, labeling the sampling state category data based on the respiratory disease symptom inducement feature data and the environmental original data set to obtain the sampling state classification data;

[0021] The sampling status classification data includes stable state, warning state and dangerous state;

[0022] Step S32: parameter fluctuation partitioning, specifically, constructing a parameter fluctuation attention index, performing sampling attention partitioning, and obtaining parameter fluctuation partition data;

[0023] The parameter fluctuation attention index is specifically calculated by weighted combination of the parameter dramatic jump score, the propagation distance normalized value and the environmental factor sensitivity score;

[0024] The parameter jump score is calculated by sliding window method combined with threshold setting;

[0025] Step S33: lightweight prediction network improvement, specifically using a lightweight long short-term memory neural network in combination with a custom parameter fluctuation partition gating function to perform lightweight prediction network improvement, performing prediction network model training based on the sampled state classification data to obtain a lightweight prediction network model, and using the lightweight prediction network model to perform parameter distribution prediction based on the respiratory disease symptom inducement characteristic data and the environmental original data set to obtain sampling node prediction state data;

[0026] Step S34: generating a sampling strategy, specifically, adjusting the sampling frequency by constructing a scoring function based on the predicted state data of the sampling node to obtain node sampling frequency reference data;

[0027] Step S35: Dynamically adjust the sampling scheduling strategy, specifically, dynamically adjust the multimodal micro-sensor module according to the node sampling frequency reference data to obtain sampling scheduling strategy reference data.

[0028] Furthermore, in step S4, the home environment intervention is used to perform targeted device control and user behavior prompts, specifically to conduct comprehensive home environment intervention based on the respiratory disease symptom inducement characteristic data and the predictive sampling strategy reference data to obtain personalized respiratory protection adjustment reference data.

[0029] The present invention provides a home environment intervention system for patients with chronic respiratory diseases, comprising a sensing and acquisition module, a detection and tracing module, a sampling and control module, and an environmental intervention module;

[0030] The sensing acquisition module is used for sensing module construction, obtains the original environmental data set through the sensing module construction, and sends the original environmental data set to the detection and tracing module, the sampling and control module, and the environmental intervention module;

[0031] The detection and tracing module is used for multi-node linkage tracing, obtains predictive sampling strategy reference data through multi-node linkage tracing, and sends the predictive sampling strategy reference data to the sampling control module;

[0032] The sampling control module is used for sampling scheduling optimization, obtains sampling scheduling strategy reference data through sampling scheduling optimization, and sends the sampling scheduling strategy reference data to the environmental intervention module;

[0033] The environmental intervention module is used for home environment intervention, and obtains sampling scheduling strategy reference data through home environment intervention.

[0034] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0035] (1) In view of the technical problems in the existing home environment intervention methods for patients with chronic respiratory diseases, such as the lack of identification of multi-factor integrated linkage inducements in the microenvironment, the lack of dynamic intervention adjustment strategies, the delayed system response and the inability to adapt to the differences in patient symptoms, this solution creatively adopts a comprehensive home environment intervention method that combines multimodal micro-sensor module design, multi-node disease inducement risk linkage tracing and sampling node scheduling with disease inducement feature optimization, and realizes the inducing factors (PM2.5, , sudden changes in temperature and humidity, and dust mite allergens);

[0036] (2) In response to the technical problems of being unable to effectively identify pollution transmission paths, lacking the ability to deduce symptom causality, and roughly scoring health risks in the existing risk tracing process of environmental factor sampling nodes, this scheme creatively adopts a spatiotemporal correlation parameter mutation analysis method that combines an improved transmission consistency index and parameter gradient changes to conduct multi-node linkage tracing, obtain characteristic data on the causes of respiratory disease symptoms, and realize a full-chain analysis of "factor fluctuation-node coordination-transmission path-symptom risk";

[0037] (3) In order to solve the technical problems in the sampling scheduling optimization process of existing sensor nodes, such as waste of sensing resources, sampling that does not dynamically adjust with changes in environmental conditions, and high algorithm computational complexity that makes it difficult to deploy on edge devices, this solution creatively adopts a lightweight improved long-short-term memory network prediction method that combines parameter fluctuation characteristics to optimize the sampling scheduling of the sensor module, obtains predictive sampling strategy reference data, and realizes state-aware dynamic allocation of the perception frequency of the home microenvironment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic flow chart of a method for intervening in the home environment of patients with chronic respiratory diseases provided by the present invention;

[0039] Figure 2 A schematic diagram of a home environment intervention system for patients with chronic respiratory diseases provided by the present invention;

[0040] Figure 3This is a flow chart of multi-node linkage tracing in step S2;

[0041] Figure 4 Schematic diagram of the process for optimizing the sampling schedule in step S3.

[0042] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0045] Example 1, see Figure 1 The present invention provides a method for intervening in the home environment of patients with chronic respiratory diseases, the method comprising the following steps:

[0046] Step S1: sensor module construction;

[0047] Step S2: multi-node linkage tracing;

[0048] Step S3: sampling scheduling optimization;

[0049] Step S4: Family environment intervention.

[0050] By performing the above operations, in view of the technical problems in the existing home environment intervention methods for patients with chronic respiratory diseases, such as the lack of identification of multi-factor integrated linkage inducements in the microenvironment, the lack of dynamic intervention adjustment strategies, the delayed system response and the inability to adapt to the differences in patients' symptoms, this solution creatively adopts a comprehensive home environment intervention method that combines multimodal micro-sensor module design, multi-node disease inducement risk linkage tracing and sampling node scheduling with disease inducement feature optimization, and realizes the inducing factors (PM2.5, , sudden changes in temperature and humidity, and dust mite allergens); for example, in the homes of elderly asthma patients during the rainy season, the linked changes in dust mite concentration and relative humidity may stimulate airway allergic reactions in a short period of time. Traditional systems cannot provide early warnings, while the present invention can combine multimodal sensor data with spatiotemporal propagation models to identify risk factors in advance and link air conditioners, dehumidifiers and other execution equipment to improve the real-time nature of intervention and individual adaptability.

[0051] Example 2, see Figure 1 and Figure 2 In step S1, the sensor module is constructed to construct a multimodal micro-sensor module required for the home environment of patients with chronic respiratory diseases and realize real-time data collection. Specifically, a multimodal micro-sensor module including particle detection, gas detection, temperature and humidity detection, and dust mite allergen detection is sequentially constructed, and by constructing the multimodal micro-sensor module, home environment sensor data is collected to obtain an original environmental data set;

[0052] Preferably, the multimodal micro-sensing module includes a particle detection module, a gas detection module, a temperature and humidity detection module, a dust mite allergen detection module, a communication module and a power supply module;

[0053] Table 1 is a schematic diagram of the structure of the multimodal microsensor module. As shown in the table, the particle detection module uses a laser scattering PM2.5 / PM10 sensor with a detection range of 0-1000 μg / m³, an error of no more than ±10%, and a resolution of 1 μg / m³. It is used for real-time monitoring of common particulate matter pollution sources such as kitchen fumes and dust accumulation.

[0054] The gas detection module includes a VOC detection submodule and Detection submodule: The VOC detection submodule adopts SGP30 metal oxide semiconductor gas sensor, which covers the detection range of common decoration pollutants and volatile components of cleaning agents, and has fast response and low power consumption characteristics; The detection submodule uses the SenseAir S8 sensor based on the non-dispersive infrared (NDIR) principle, with a detection range of 400–5000 ppm and an accuracy of ±(50 ppm + 3%), which is used to reflect ventilation status and carbon dioxide accumulation.

[0055] The temperature and humidity detection module uses an integrated digital temperature and humidity sensor SHT31, with a temperature measurement accuracy of ±0.3°C and a humidity accuracy of ±2% RH. It is used to assist in assessing the risk of allergen growth and regulating respiratory comfort, and to assist in establishing a correlation model between temperature and humidity environments and symptom induction.

[0056] The dust mite allergen detection module uses immunochromatographic test strips combined with camera colorimetric analysis to detect the main allergen, Der p1, a derivative of dust mite. Users can regularly replace the test strips and perform colorimetric concentration analysis to achieve a quantitative assessment of dust mite levels.

[0057] The communication module adopts Bluetooth BLE 5.2 low-power communication protocol, supports multi-node networking and scheduled data broadcasting;

[0058] The power supply module can be powered by a rechargeable button battery solution and a USB power supply solution. The rechargeable button battery solution supports low-frequency sampling operation for more than one month and is suitable for low-light environments such as the back of furniture and under beds. The USB power supply solution is suitable for long-term fixed deployment locations.

[0059] In terms of structural integration, all sensors are connected via a unified I²C bus, with the main control chip (STM32L or ESP32 series) performing polling sampling. The sensors can be configured to enter sleep or active states through software, achieving dynamic power consumption management.

[0060] Table 1 Schematic diagram of the structure of the multimodal micro-sensor module

[0061]

[0062] The multimodal micro-sensor module described in this embodiment can be flexibly deployed according to the type of home room, supports continuous monitoring of key health factors such as particulate matter, volatile gases, temperature and humidity, and biological allergens, and supports sampling scheduling optimization, health risk reasoning, and home environment intervention control through subsequent algorithms, providing patients with chronic respiratory diseases with efficient and intelligent environmental support means.

[0063] Example 3, see Figure 1 、 Figure 2 and Figure 3 This embodiment is based on the above embodiment. In step S2, the multi-node linkage tracing is used for spatiotemporal correlation analysis of node data and identification of invisible health threats. Specifically, based on the original environmental data set, a spatiotemporal correlation parameter mutation analysis method combining an improved propagation consistency index and parameter gradient changes is adopted to perform multi-node linkage tracing to obtain characteristic data of respiratory disease symptom inducers, including the following steps:

[0064] Step S21: Node data preprocessing, specifically, constructing a multi-dimensional time series matrix by performing timestamp interpolation, Z-score normalization, and unit conversion on the asynchronous data of the sensor module based on the original environmental data set, thereby obtaining a multi-node basic data set;

[0065] The multi-node basic data set includes particulate matter detection data, gas detection data, temperature and humidity detection data, and dust mite allergen detection data. The calculation formula is:

[0066] ;

[0067] Where, X t It is a multi-node basic data set. is the particle detection data, is the gas detection data, It is the temperature detection data. It is the humidity detection data, It is the dust mite allergen detection data;

[0068] Step S22: Propagation consistency index modeling is used to measure the synchronization of factor fluctuation propagation between different nodes. Specifically, based on the multi-node basic data set, the correlation coefficient model is improved by introducing the directional fluctuation gradient and the exponential time decay parameter to construct a propagation consistency index model;

[0069] The calculation formula of the propagation consistency index model is:

[0070] ;

[0071] Where C i,j (t) is the propagation consistency index model, i is the sampling node index, j is the sampling adjacent node index, T is the total sampling time, is the parameter gradient time index, t is the time index, is the i-th sampling node at time The parameter gradient when is the jth sampling node in the delay The parameter gradient after is used to capture the time delay characteristics of environmental pollution propagation. is the i-th sampling node at time The modulus of the parameter gradient when , is a minimal corrected positive number, The overall exponential time decay parameter is used to represent the time delay parameter With the increase of is the time decay coefficient, which is set to 0.3 by default;

[0072] Step S23: identifying parameter gradient changes, specifically, building a local adaptive parameter gradient mutation index based on a sliding window based on the multi-node basic data set to model abnormal changes in environmental factors and obtain environmental parameter gradient mutation index data;

[0073] The calculation formula for the abnormal change modeling is:

[0074] ;

[0075] Where, is the environmental parameter gradient mutation index data, is the parameter gradient of the i-th sampling node at time t, is the historical parameter gradient mean of the i-th sampling node, is the standard deviation of the parameter gradient of the i-th sampling node;

[0076] Step S24: Spatiotemporal interaction path modeling is used to dynamically construct the propagation path of the suspected pollution source from the starting point to the symptom node. Specifically, based on the propagation consistency index model and the environmental parameter gradient mutation index data, the spatiotemporal interaction path modeling is performed by sequentially constructing the time series propagation graph data and screening the environmental factor pollution propagation path to obtain spatiotemporal interaction path reference data.

[0077] The time series propagation graph data is constructed by taking sampling points as graph nodes and pollution propagation paths as edges, defining edge weights based on the environmental parameter gradient mutation index data and the propagation consistency index model, and using the edge weights as propagation intensity weights;

[0078] The calculation formula of the propagation intensity weight is:

[0079] ;

[0080] Where, is the propagation intensity weight, is the environmental parameter gradient mutation index data, C i,j (t) is the propagation consistency index model, E is the edge structure of the time series propagation graph data, where, It is used to indicate that the sampling node i and the sampling neighbor node j are adjacent nodes and are connected in the home space layout;

[0081] The environmental factor pollution propagation path screening specifically uses a graph traversal algorithm to perform threshold screening on the propagation intensity weight corresponding to each environmental factor. Through the threshold screening, the propagation path of the suspected pollution source from the starting point to the symptom node is screened as the spatiotemporal interaction path reference data;

[0082] Preferably, the threshold is set to 1.8, and the graph traversal algorithm uses the networkx.dfs_edges() algorithm to extract pollution propagation paths with a path length less than or equal to 4;

[0083] The calculation formula for the threshold screening is:

[0084] ;

[0085] Where, is the propagation intensity weight, is the threshold, path is the total set of all edges;

[0086] Step S25: Potential health risk identification, specifically, calculating a health risk score for each spatiotemporal interaction path based on the spatiotemporal interaction path reference data using an improved health risk weighting function, and screening the spatiotemporal interaction paths based on the health risk score to obtain potential risk identification reference data;

[0087] The calculation formula of the improved health risk weighting function is:

[0088] ;

[0089] Where, is the health risk score, where is the spatiotemporal interaction path reference data, Is the propagation strength weight, the default value is 0.5, PathStrength is the sum of all propagation strength edge weights on the path, is the sensitivity weight, with a default value of 0.3. NodeRiskIndex is the sensitivity parameter of the sampling point at the end of the path, which is used to indicate the risk contribution to the symptom triggering. is the sensitization intensity weight, with a default value of 0.2, and FactorSeverity is the sensitization intensity score of the dominant environmental factor in the pathway;

[0090] Step S26: Symptom alignment and linkage tracing, specifically, by constructing a symptom risk rule matching table, performing rule mapping modeling between symptom types and environmental factors, and combining the health risk score to perform causal weight scoring and inducement feature screening to obtain respiratory disease symptom inducement feature data;

[0091] Preferably, Table 2 is an association rule mapping example table of the rule mapping modeling. As shown in the table, the symptom types specifically include dry cough, nocturnal asthma, throat irritation, and nasal congestion and sneezing, and the corresponding weight scores are 1.0, 0.9, 0.85, and 0.8, respectively. The weight scores are used to assist in the calculation of the sensitization intensity score; the matching factor number is used to indicate the number of associated environmental factors that can trigger a certain symptom type; the matching factor number and the weight score are taken and calculated according to the association rule mapping example table;

[0092] The sensitization intensity score is calculated based on the matching factor book and weight score in the association rule mapping instance table, and the calculation formula is:

[0093] ;

[0094] Where, It is the sensitization intensity score of the dominant environmental factor in the pathway calculated based on the spatiotemporal interaction pathway reference data. is the number of matching factors corresponding to symptom type s, K is the total number of environmental factors in the path, k is the environmental factor index, and I k It is the symptom-environment matching indicator parameter, which is used to indicate the matching between the kth environmental factor and the previous symptom type s. When the kth environmental factor matches the symptom type s, the value is 1, and when it does not match, the value is 0. s is the weight score of symptom type s.

[0095] Table 2 Association rule mapping example table of rule mapping modeling

[0096]

[0097] By performing the above operations, in order to address the technical problems in the existing risk tracing process of environmental factor sampling nodes, such as the inability to effectively identify pollution transmission paths, the lack of symptom causal reasoning capabilities, and the rough health risk scoring, this solution creatively adopts a spatiotemporal correlation parameter mutation analysis method that combines an improved transmission consistency index and parameter gradient changes to conduct multi-node linkage tracing, obtain characteristic data on the causes of respiratory disease symptoms, and realize a full-chain analysis of "factor fluctuation-node collaboration-transmission path-symptom risk"; specifically, taking the example of kitchen fumes in the home affecting the PM2.5 concentration in the bedroom and inducing COPD nocturnal wheezing, this solution can identify the aerosol migration path during the peak period of fumes through the directional transmission index, and then use the sliding window mutation model to identify the "key transition points". Finally, combined with the symptom-factor rule library, it can infer the cause combination, providing a targeted decision-making basis for personalized intervention.

[0098] Example 4, see Figure 1 、 Figure 2 and Figure 4 This embodiment is based on the above embodiment. In step S3, the sampling scheduling optimization is used to adjust the sensor sampling frequency. Specifically, based on the respiratory disease symptom inducement characteristic data and the environmental original data set, a lightweight improved long short-term memory network prediction method combined with parameter fluctuation characteristics is used to optimize the sampling scheduling of the sensor module to obtain predictive sampling strategy reference data, including the following steps:

[0099] Step S31: pre-processing the sampling state classification data, specifically, labeling the sampling state category data based on the respiratory disease symptom inducement feature data and the environmental original data set to obtain the sampling state classification data;

[0100] The sampling status classification data includes stable state, warning state and dangerous state;

[0101] Step S32: parameter fluctuation partitioning, specifically, constructing a parameter fluctuation attention index, performing sampling attention partitioning, and obtaining parameter fluctuation partition data;

[0102] The parameter fluctuation attention index is specifically calculated by weighted combination of the parameter dramatic jump score, the normalized value of the propagation distance, and the sensitivity score of the environmental factors. The calculation formula is:

[0103] ;

[0104] Where, is the parameter fluctuation attention index, It is the parameter jump weight, the default value is 0.4, JumpScore t It is a score that changes dramatically when the parameters are changed. It is calculated by sliding window method combined with threshold setting. Is the propagation distance weight, the default value is 0.4, Proximity t is the normalized value of the propagation distance, which is used to represent the propagation distance from the sampling node i to the end of the propagation path corresponding to the nearest respiratory disease symptom inducer characteristic data. is the environmental factor sensitivity weight, with a default value of 0.2. FactorWeight is the sensitivity score of the environmental factor, which is calculated based on the weight scores in Table 2.

[0105] Step S33: lightweight prediction network improvement, specifically using a lightweight long short-term memory neural network in combination with a custom parameter fluctuation partition gating function to perform lightweight prediction network improvement, performing prediction network model training based on the sampled state classification data to obtain a lightweight prediction network model, and using the lightweight prediction network model to perform parameter distribution prediction based on the respiratory disease symptom inducement characteristic data and the environmental original data set to obtain sampling node prediction state data;

[0106] The calculation formula for the improved lightweight prediction network is:

[0107] ;

[0108] Where, is the output hidden state of the lightweight prediction network model, is a custom parameter fluctuation partition gating function, where is the parameter fluctuation attention index, LSTM(·) is the single-layer long short-term memory neural network model function, x t is the sampling state classification data, h t-1 is the hidden state at the previous moment, The whole is the activation partition, which is used to identify dynamic mutations. The whole is to maintain the partition, which is used to maintain the prediction stability;

[0109] The calculation formula of the custom parameter fluctuation partition gating function is:

[0110] ;

[0111] Where, is the upper gating threshold, is the lower gating threshold, and the custom parameter fluctuation partition gating function is specifically used to activate the prediction ability under high volatility state and retain only the historical state under low volatility state to reduce the risk of overfitting;

[0112] Preferably, the value of the upper gating threshold is set to 0.7, and the value of the lower gating threshold is set to 0.3;

[0113] Preferably, Table 3 is an example table of parameters of a lightweight prediction network model, such as the table, the parameter categories of the lightweight prediction network model include input dimension, number of hidden units, time step, gate activation function, network activation function and loss function;

[0114] Table 3 Parameter example of lightweight prediction network model

[0115]

[0116] Step S34: generating a sampling strategy, specifically, adjusting the sampling frequency by constructing a scoring function based on the predicted state data of the sampling node to obtain node sampling frequency reference data;

[0117] The calculation formula of the scoring function is:

[0118] ;

[0119] Where, f i (t) is the node sampling frequency reference data, f max is the high-frequency sampling frequency, f med is the intermediate frequency sampling frequency, f min is the low-frequency sampling frequency, is the predicted state data of the sampling node, It is a set of sampling nodes whose sampling status is classified into warning state and dangerous state. is the scoring threshold;

[0120] Preferably, the specific sampling frequency of the high frequency sampling frequency is set to be sampled once every 1 minute, the specific sampling frequency of the medium frequency sampling frequency is set to be sampled once every 5 minutes, and the specific sampling frequency of the low frequency sampling frequency is set to be sampled once every 15 minutes; the default value of the scoring threshold is set to 0.15;

[0121] Step S35: Dynamically adjust the sampling scheduling strategy, specifically, dynamically adjust the multimodal micro-sensor module according to the node sampling frequency reference data to obtain sampling scheduling strategy reference data.

[0122] By performing the above operations, in order to address the technical problems in the sampling scheduling optimization process of existing sensor nodes, such as waste of perception resources, sampling that does not dynamically adjust with changes in environmental conditions, and high algorithm computational complexity that makes it difficult to deploy on edge devices, this solution creatively adopts a lightweight improved long-short-term memory network prediction method that combines parameter fluctuation characteristics to optimize the sampling scheduling of the sensor module, obtains predictive sampling strategy reference data, and realizes state-aware dynamic allocation of the home microenvironment perception frequency. For example, during the peak period of respiratory sensitivity in children, the solution can identify the mutation trend of specific parameters (such as TVOC and humidity), and dynamically switch the perception frequency according to the "stable state-warning state-dangerous state" partitioning, avoiding information delays or excessive sensor energy consumption caused by fixed sampling frequencies. At the same time, the algorithm adopts a lightweight gating mechanism, which is suitable for deployment in home-level embedded systems to ensure a balance between performance and response speed.

[0123] Example 5, see Figure 1 、 Figure 2 This embodiment is based on the above embodiment. In step S4, the home environment intervention is used to perform targeted device control and user behavior prompts. Specifically, based on the respiratory disease symptom inducement characteristic data and the predictive sampling strategy reference data, a comprehensive home environment intervention is performed to obtain personalized respiratory protection adjustment reference data.

[0124] Preferably, the comprehensive intervention of the home environment can be achieved through the existing smart home system, specifically including device control intervention, user prompt intervention and intelligent output form intervention;

[0125] The device control intervention specifically generates control instructions based on the high-risk factors identified in the respiratory disease symptom-inducing characteristic data, and performs real-time adjustment of environmental factors by calling a preset control interface; the preset control interface includes on-off control of the smart air purifier, setting of humidity adjustment thresholds for the dehumidifier, and window opening and closing control;

[0126] The user prompt intervention is specifically based on the status level output in the predictive sampling strategy reference data, calling the voice broadcast prompt or the mobile APP push interface to perform user operation suggestion prompt intervention;

[0127] The intelligent output form intervention specifically structures the output data of the device control intervention and the user prompt intervention into personalized respiratory protection adjustment reference data for storage and reading; the personalized respiratory protection adjustment reference data specifically includes control object parameters, target environmental factor parameters, control strategy parameters, user suggestion parameters and timestamp;

[0128] The specific intervention execution method adopted in this embodiment belongs to the general functional component in the existing smart home control system that can be directly called and implemented by technical personnel in this field. Through a unified intervention strategy generation process, personalized, multi-factor environmental linkage adjustment capabilities are realized for patients with chronic respiratory diseases.

[0129] Example 6, see Figure 1 and Figure 2 , this embodiment is based on the above embodiment, and the present invention provides a home environment intervention system for patients with chronic respiratory diseases, including a sensing acquisition module, a detection and tracing module, a sampling and control module, and an environmental intervention module;

[0130] The sensing acquisition module is used for sensing module construction, obtains the original environmental data set through the sensing module construction, and sends the original environmental data set to the detection and tracing module, the sampling and control module, and the environmental intervention module;

[0131] The detection and tracing module is used for multi-node linkage tracing, obtains predictive sampling strategy reference data through multi-node linkage tracing, and sends the predictive sampling strategy reference data to the sampling control module;

[0132] The sampling control module is used for sampling scheduling optimization, obtains sampling scheduling strategy reference data through sampling scheduling optimization, and sends the sampling scheduling strategy reference data to the environmental intervention module;

[0133] The environmental intervention module is used for home environment intervention, and obtains sampling scheduling strategy reference data through home environment intervention.

[0134] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0135] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0136] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A method for intervening in the home environment of patients with chronic respiratory diseases, characterized by: The method comprises the following steps: Step S1: Sensing module construction, which is used to construct a multimodal micro-sensor module required for the home environment of patients with chronic respiratory diseases and realize real-time data collection. Specifically, a multimodal micro-sensor module including particle detection, gas detection, temperature and humidity detection, and dust mite allergen detection is sequentially constructed. By constructing the multimodal micro-sensor module, home environment sensing data is collected to obtain the original environmental data set; Step S2: Multi-node linkage tracing, using a spatiotemporal correlation parameter mutation analysis method that combines an improved propagation consistency index and parameter gradient changes to perform multi-node linkage tracing to obtain characteristic data of respiratory disease symptom inducers, including the following steps: Step S21: Node data preprocessing; Step S22: Propagation consistency index modeling, by introducing directional fluctuation gradients and exponential time decay parameters to improve the correlation coefficient model; Step S23: Parameter gradient change identification; Step S24: Spatiotemporal interaction path modeling; Step S25: Potential health risk identification; Step S26: Symptom alignment linkage tracing; Step S3: Sampling scheduling optimization, using a lightweight improved long short-term memory network prediction method combined with parameter fluctuation characteristics to optimize the sampling scheduling of the sensor module and obtain predictive sampling strategy reference data, including the following steps: Step S31: Sampling state classification data preprocessing; Step S32: Parameter fluctuation partitioning; Step S33: Lightweight prediction network improvement, using a lightweight long short-term memory neural network combined with a custom parameter fluctuation partition gating function to improve the lightweight prediction network; Step S34: Sampling strategy generation; Step S35: Dynamic adjustment of the sampling scheduling strategy; Step S4: Home environment intervention to obtain personalized respiratory protection adjustment reference data.

2. A method for home environment intervention for patients with chronic respiratory diseases according to claim 1, characterized in that: In step S2, the multi-node linkage tracing is used for spatiotemporal correlation analysis of node data and identification of invisible health threats. Specifically, based on the original environmental data set, a spatiotemporal correlation parameter mutation analysis method combining an improved propagation consistency index and parameter gradient changes is used to perform multi-node linkage tracing to obtain characteristic data of respiratory disease symptom inducers, including the following steps: Step S21: Node data preprocessing, specifically, constructing a multi-dimensional time series matrix by performing timestamp interpolation, Z-score normalization, and unit conversion on the asynchronous data of the sensor module based on the original environmental data set, thereby obtaining a multi-node basic data set; Step S22: Propagation consistency index modeling is used to measure the synchronization of factor fluctuation propagation between different nodes. Specifically, based on the multi-node basic data set, the correlation coefficient model is improved by introducing the directional fluctuation gradient and the exponential time decay parameter to construct a propagation consistency index model; Step S23: identifying parameter gradient changes, specifically, building a local adaptive parameter gradient mutation index based on a sliding window based on the multi-node basic data set to model abnormal changes in environmental factors and obtain environmental parameter gradient mutation index data; Step S24: Spatiotemporal interaction path modeling is used to dynamically construct the propagation path of the suspected pollution source from the starting point to the symptom node. Specifically, based on the propagation consistency index model and the environmental parameter gradient mutation index data, the spatiotemporal interaction path modeling is performed by sequentially constructing the time series propagation graph data and screening the environmental factor pollution propagation path to obtain spatiotemporal interaction path reference data. Step S25: Potential health risk identification, specifically, calculating a health risk score for each spatiotemporal interaction path based on the spatiotemporal interaction path reference data using an improved health risk weighting function, and screening the spatiotemporal interaction paths based on the health risk score to obtain potential risk identification reference data; Step S26: Symptom alignment and linkage tracing, specifically, by constructing a symptom risk rule matching table, conducting rule mapping modeling between symptom types and environmental factors, and obtaining respiratory disease symptom inducement feature data through causal weight scoring and inducement feature screening.

3. The method for home environment intervention for patients with chronic respiratory diseases according to claim 2, characterized in that: In step S2, the multi-node basic data set includes particulate matter detection data, gas detection data, temperature and humidity detection data, and dust mite allergen detection data.

4. A method for home environment intervention for patients with chronic respiratory diseases according to claim 3, characterized in that: In step S3, the sampling scheduling optimization is used to adjust the sensor sampling frequency. Specifically, based on the respiratory disease symptom inducement characteristic data and the environmental original data set, a lightweight improved long short-term memory network prediction method combined with parameter fluctuation characteristics is used to optimize the sampling scheduling of the sensor module to obtain predictive sampling strategy reference data, including the following steps: Step S31: pre-processing the sampling state classification data, specifically, labeling the sampling state category data based on the respiratory disease symptom inducement feature data and the environmental original data set to obtain the sampling state classification data; Step S32: parameter fluctuation partitioning, specifically, constructing a parameter fluctuation attention index, performing sampling attention partitioning, and obtaining parameter fluctuation partition data; Step S33: lightweight prediction network improvement, specifically using a lightweight long short-term memory neural network in combination with a custom parameter fluctuation partition gating function to perform lightweight prediction network improvement, performing prediction network model training based on the sampled state classification data to obtain a lightweight prediction network model, and using the lightweight prediction network model to perform parameter distribution prediction based on the respiratory disease symptom inducement characteristic data and the environmental original data set to obtain sampling node prediction state data; Step S34: generating a sampling strategy, specifically, adjusting the sampling frequency by constructing a scoring function based on the predicted state data of the sampling node to obtain node sampling frequency reference data; Step S35: Dynamically adjust the sampling scheduling strategy, specifically, dynamically adjust the multimodal micro-sensor module according to the node sampling frequency reference data to obtain sampling scheduling strategy reference data.

5. The method for home environment intervention for patients with chronic respiratory diseases according to claim 4, characterized in that: In step S31, the sampling state classification data includes stable state, warning state and dangerous state; In step S32, the parameter fluctuation attention index is specifically calculated by weighted combination of the parameter dramatic jump score, the propagation distance normalized value and the environmental factor sensitivity score; The parameter violent jump score is specifically calculated by a sliding window method combined with a threshold setting.

6. A method for home environment intervention for patients with chronic respiratory diseases according to claim 5, characterized in that: In step S4, the home environment intervention is used to perform targeted device control and user behavior prompts, specifically to perform comprehensive home environment intervention based on the respiratory disease symptom inducement characteristic data and the predictive sampling strategy reference data to obtain personalized respiratory protection adjustment reference data.

7. A home environment intervention system for patients with chronic respiratory diseases, for implementing a home environment intervention method for patients with chronic respiratory diseases according to any one of claims 1 to 6, characterized in that: It includes sensing and acquisition module, detection and traceability module, sampling and control module and environmental intervention module.

8. The home environment intervention system for patients with chronic respiratory diseases according to claim 7, characterized in that: The sensing acquisition module is used for sensing module construction, obtains the original environmental data set through the sensing module construction, and sends the original environmental data set to the detection and tracing module, the sampling and control module, and the environmental intervention module; The detection and tracing module is used for multi-node linkage tracing, obtains predictive sampling strategy reference data through multi-node linkage tracing, and sends the predictive sampling strategy reference data to the sampling control module; The sampling control module is used for sampling scheduling optimization, obtains sampling scheduling strategy reference data through sampling scheduling optimization, and sends the sampling scheduling strategy reference data to the environmental intervention module; The environmental intervention module is used for home environment intervention, and obtains sampling scheduling strategy reference data through home environment intervention.

Images