Intelligent monitoring method and system for children's bronchial asthma symptoms based on multi-source data

Abstract

The present invention discloses a method and system for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data, which relates to the field of medical technology, including obtaining historical physiological monitoring data and historical asthma information, classifying historical physiological monitoring data based on historical asthma information, and obtaining physiological monitoring data classification information. The present invention uses a data deviation evaluation coefficient to screen historical data, obtain baseline physiological parameters, and achieve accurate analysis of children's physiological states, so as to facilitate timely discovery of abnormal physiological data and improve the efficiency of asthma symptom monitoring. Through the environmental impact coefficient, the impact of the environment on physiological data during asthma is accurately analyzed, so as to accurately set the physiological monitoring threshold, ensure the stability and reliability of the monitoring system, and accurately adjust asthma monitoring in abnormal environments through breathing audio data, ensuring a rapid response to asthma symptom warnings.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a method and system for intelligently monitoring symptoms of bronchial asthma in children based on multi-source data. Background Art

[0002] Asthma is an episodic chronic disease that involves disruption of normal respiratory function. Although asthma affects people of all ages, it is the most common chronic disease in childhood and requires asthma treatment to prevent possible extreme deterioration of respiratory function, which requires monitoring of asthma symptoms in subjects with asthma. In the case of children with asthma, parents currently usually only have subjective information about the condition of their asthmatic children, relying on the subjective description of the parents, lacking objective data to support the results, and parents cannot follow up their children's symptoms enough to intervene early during changes and / or deterioration in health status.

[0003] At present, there is still a problem in the monitoring of children's bronchial asthma symptoms, which is that it is impossible to achieve real-time monitoring of children's asthma symptoms, resulting in the failure to detect changes in the disease in time. The existing technology often only directly monitors the children's physiological data and sets a fixed threshold for early warning. In this case, if the threshold is too high, asthma symptoms often cannot be monitored in time. In an emergency, it is impossible to respond quickly, which may lead to worsening of the disease. If the threshold is too low, it is impossible to accurately distinguish whether asthma symptoms appear when the physiological data changes. Frequent hospital visits caused by asthma symptom early warnings increase the economic burden on families. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data are provided. This technical solution solves the problem that it is impossible to realize real-time monitoring of asthma symptoms in children proposed in the above background technology, resulting in the failure to detect changes in the disease in time. The existing technology often only directly monitors the physiological data of children and sets a fixed threshold for early warning. In this case, if the threshold is too high, asthma symptoms often cannot be monitored in time. In an emergency, it is impossible to respond quickly, which may lead to worsening of the disease. If the threshold is too low, it is impossible to accurately distinguish whether asthma symptoms occur when physiological data changes. Frequent hospital visits caused by asthma symptom early warning increase the economic burden on the family.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An intelligent monitoring method for children's bronchial asthma symptoms based on multi-source data, including:

[0007] Acquire historical physiological monitoring data, wherein the historical physiological monitoring data includes historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, and historical respiratory audio data;

[0008] Acquiring historical asthma information, wherein the historical asthma information includes historical asthma time node information and historical asthma duration information;

[0009] Based on historical asthma information, historical physiological monitoring data are classified to obtain physiological monitoring data classification information;

[0010] Among them, the historical physiological monitoring data within the duration of asthma is taken as the historical asthma physiological data, and the historical physiological monitoring data outside the duration of asthma is taken as the historical routine physiological data;

[0011] Obtain baseline physiological parameters based on historical routine physiological data;

[0012] According to the historical asthma physiological data, corresponding historical environmental monitoring data are obtained, wherein the historical environmental monitoring data includes allergen concentration data and air pollutant concentration data;

[0013] Obtain environmental impact coefficients based on baseline physiological parameters, historical asthma physiological data, and historical environmental monitoring data;

[0014] Using the baseline physiological parameters as the baseline threshold of physiological data;

[0015] Monitor children's physiological data and activity environment, and obtain actual physiological data and environmental monitoring data;

[0016] Based on the actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, it is judged whether the child's physiological data is abnormal. If so, an early warning will be issued for the child's bronchial asthma symptoms. If not, real-time monitoring will continue.

[0017] Preferably, obtaining the baseline physiological parameters based on historical conventional physiological data specifically includes:

[0018] Calculate the average value of historical routine physiological data to obtain the mean value of physiological data;

[0019] According to the historical routine physiological data, the difference between each routine physiological data and the mean value of the physiological data is used as the calibration deviation value of the routine physiological data;

[0020] Based on the calibration deviation value of each conventional physiological data, a set of conventional physiological data with a calibration deviation value smaller than the calibration deviation value of the conventional physiological data is constructed to obtain a deviation data set corresponding to each conventional physiological data;

[0021] According to the deviation data set, obtain the data deviation assessment coefficient;

[0022] The conventional physiological data with the largest data deviation evaluation coefficient is used as the basic physiological data;

[0023] According to the deviation data set corresponding to the basic physiological data, the normal extreme values ​​of the physiological data are obtained, that is, the minimum value of the normal physiological data and the maximum value of the normal physiological data in the deviation data set corresponding to the basic physiological data;

[0024] Obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value;

[0025] The calculation formula of the data deviation evaluation coefficient is:

[0026]

[0027] In the formula, represents the data deviation evaluation coefficient of the xth routine physiological data, represents the deviation dataset of the xth conventional physiological data, Represents the total number of data in the deviation data set of the xth conventional physiological data, is the xth routine physiological data, Indicates the maximum value of the conventional physiological data in the deviation data set of the xth conventional physiological data, represents the minimum value of the conventional physiological data in the deviation data set of the xth conventional physiological data;

[0028] The reference physiological parameters are specifically:

[0029]

[0030] Where E is the baseline physiological parameter, As basic physiological data, is the physiological data correction coefficient, is the mean value of physiological data, and It is the normal extreme value of physiological data.

[0031] Preferably, the environmental impact coefficient is obtained according to the baseline physiological parameters, historical asthma physiological data and historical environmental monitoring data, specifically including:

[0032] The difference between the historical asthma physiological data and the baseline physiological parameters is used as a physiological difference index, wherein the physiological difference index represents the sum of the differences between each historical asthma physiological data and the baseline physiological parameters;

[0033] Obtain environmental monitoring assessment index based on historical environmental monitoring data;

[0034] The ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring assessment index was used as the data clustering index;

[0035] Obtain environmental change coefficient based on environmental monitoring and evaluation index;

[0036] Sort the historical asthma physiological data in the order of small to large data clustering index to obtain the order information of asthma physiological data;

[0037] According to the order information of asthma physiological data and the environmental change coefficient, the historical asthma physiological data are clustered to obtain asthma physiological data clusters;

[0038] Among them, the ratio of the data clustering index of any two historical asthma physiological data in each asthma physiological data cluster is less than the environmental variation coefficient;

[0039] Obtain environmental impact coefficients based on asthma physiological data clusters and historical environmental monitoring data;

[0040] The data clustering index is specifically:

[0041]

[0042] In the formula, is the data clustering index of the y-th historical asthma physiological data, is the physiological difference index of the y-th historical asthma physiological data, is the environmental monitoring evaluation index of the yth historical asthma physiological data, represents the i-th baseline physiological parameter, where if ,but is the baseline heart rate in the baseline physiological parameters, if ,but is the baseline blood oxygen saturation in the baseline physiological parameters. ,but is the baseline respiratory rate in the baseline physiological parameters, is the ith physiological data item in the yth historical asthma physiological data, is the concentration of the jth substance in the historical environmental monitoring data corresponding to the yth historical asthma physiological data, and n is the total number of allergens and air pollutant types in the historical environmental monitoring data;

[0043] The environmental variation coefficient is specifically:

[0044]

[0045] In the formula, is the environmental variation coefficient, Indicates the maximum value of the environmental monitoring assessment index of historical asthma physiological data, It represents the minimum value of the environmental monitoring assessment index of historical asthma physiological data, and m is the total number of historical asthma physiological data.

[0046] Preferably, the step of obtaining the environmental impact coefficient based on the asthma physiological data cluster and the historical environmental monitoring data specifically includes:

[0047] According to the asthma physiological data cluster, the historical asthma physiological data is matched with the corresponding historical environmental monitoring data to obtain the asthma data cluster;

[0048] The historical asthma physiological data with the smallest physiological difference index in each asthma data cluster is used as the calibrated asthma physiological data of the asthma data cluster;

[0049] The historical environmental monitoring data corresponding to the calibrated asthma physiological data are used as the baseline environmental monitoring data;

[0050] An environmental impact model was established based on calibrated asthma physiological data and baseline environmental monitoring data;

[0051] According to the asthma data clusters, the environmental impact model is fitted to obtain the basic environmental impact coefficient corresponding to each asthma data cluster;

[0052] Obtain the environmental impact coefficient according to the basic environmental impact coefficient and the asthma data cluster;

[0053] The environmental impact model is specifically:

[0054]

[0055] In the formula, represents the i-th physiological data in the z-th historical asthma physiological data in the asthma data cluster, represents the ith physiological data item in the calibrated asthma physiological data of the asthma data cluster, It represents the basic environmental impact coefficient of the j-th substance concentration in the historical environmental monitoring data on the i-th physiological data in the historical asthma physiological data. represents the jth substance concentration in the historical environmental monitoring data corresponding to the zth historical asthma physiological data in the asthma data cluster, represents the concentration of the jth substance in the baseline environmental monitoring data of the asthma data cluster;

[0056] The environmental impact coefficient is specifically:

[0057]

[0058] In the formula, is the environmental impact coefficient of the jth substance concentration on the ith physiological data in the environmental monitoring data, It represents the basic environmental impact coefficient of the j-th substance concentration in the historical environmental monitoring data of the s-th asthma data cluster on the i-th physiological data in the historical asthma physiological data. Environmental variation coefficient, represents the minimum value of the data clustering index in the sth asthma data cluster, represents the maximum value of the data clustering index in the sth asthma data cluster, represents the sth asthma data cluster, and h is the total number of asthma data clusters.

[0059] Preferably, judging whether the child's physiological data is abnormal based on the actual monitored physiological data, environmental monitoring data, physiological data reference threshold and environmental impact coefficient specifically includes:

[0060] Obtain the environmental offset value of physiological data based on environmental monitoring data and environmental impact coefficient;

[0061] Obtaining an actual threshold value of the physiological data according to a physiological data baseline threshold value and a physiological data environment offset value;

[0062] According to the historical routine physiological data, the corresponding historical environmental monitoring data is obtained as the routine environmental monitoring data;

[0063] According to conventional environmental monitoring data, the average value of the concentration of each substance in the conventional environmental monitoring data is used as the baseline environmental data, and the substance concentration represents the concentration of allergens and air pollutants;

[0064] According to the actually monitored physiological data and the actual threshold of the physiological data, determining whether the actually monitored physiological data exceeds the actual threshold of the physiological data;

[0065] Among them, if the actual monitoring of physiological data , then continue to monitor the child's physiological data in real time. , then early warning of bronchial asthma symptoms in children;

[0066] like , then obtain the breathing audio data, and further determine whether to issue an early warning for the symptoms of bronchial asthma in children based on the breathing audio data;

[0067] The actual threshold of the physiological data is specifically:

[0068]

[0069] In the formula, represents the first actual threshold value of the physiological data of the i-th item of physiological data, represents the second actual threshold value of the physiological data of the i-th item of physiological data, represents the i-th baseline physiological parameter, The environmental impact coefficient of the jth substance concentration in the environmental monitoring data on the ith physiological data, represents the concentration of the jth substance in the environmental monitoring data, Represents the concentration of the jth substance in the benchmark environmental data.

[0070] Preferably, the further determining whether to issue an early warning for the symptoms of bronchial asthma in children based on the breathing audio data specifically includes:

[0071] According to the historical breathing audio data, the breathing time-frequency diagram is obtained based on short-time Fourier transform;

[0072] Based on the Mel frequency scale, the respiratory time-frequency graph is scaled to obtain the respiratory time-frequency conversion spectrum information;

[0073] According to the spectrum information of respiratory time-frequency conversion, the Mel frequency cepstrum coefficients are obtained based on logarithmic transformation and discrete cosine transformation;

[0074] According to the Mel frequency cepstral coefficients, the Mel frequency cepstral coefficients corresponding to the historical conventional physiological data are used as normal Mel frequency cepstral coefficients to obtain a normal frequency coefficient set;

[0075] According to the historical breathing audio data, based on the frequency band division, the normal frequency coefficient set is divided into a low-frequency band frequency coefficient set and a high-frequency band frequency coefficient set;

[0076] According to the low-frequency band frequency coefficient set, obtain the standard deviation of the Mel-frequency cepstral coefficients;

[0077] According to the high-frequency band frequency coefficient set, obtain the maximum difference of the Mel-frequency cepstral coefficients;

[0078] According to the breathing audio data, based on frequency band division, low-frequency band breathing audio data and high-frequency band breathing audio data are obtained;

[0079] According to the low-frequency breathing audio data, the maximum value of the low-frequency Mel frequency cepstral coefficient is obtained;

[0080] According to the high-frequency breathing audio data, the maximum value of the high-frequency Mel-frequency cepstrum coefficient fluctuation is obtained;

[0081] According to the standard deviation of the Mel frequency cepstral coefficient, the maximum value of the low-frequency Mel frequency cepstral coefficient, the maximum difference of the Mel frequency cepstral coefficient and the maximum fluctuation value of the high-frequency Mel frequency cepstral coefficient, it is judged whether to issue an early warning for the symptoms of bronchial asthma in children;

[0082] Among them, if the maximum value of the low-frequency Mel frequency cepstrum coefficient Or the maximum value of high-frequency Mel-frequency cepstral coefficient fluctuation , then early warning of bronchial asthma symptoms in children, is the standard deviation of the Mel-frequency cepstral coefficients, is the maximum difference of Mel-frequency cepstral coefficients.

[0083] Furthermore, a child bronchial asthma symptom intelligent monitoring system based on multi-source data is proposed to implement the above-mentioned monitoring method, including:

[0084] A main control module, wherein the main control module is used to establish an environmental impact model based on calibrated asthma physiological data and baseline environmental monitoring data, fit the environmental impact model based on asthma data clusters, obtain a basic environmental impact coefficient corresponding to each asthma data cluster, obtain an environmental impact coefficient based on the basic environmental impact coefficient and the asthma data cluster, classify historical physiological monitoring data based on historical asthma information, obtain physiological monitoring data classification information, obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value, determine whether the child's physiological data is abnormal based on actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, and further determine whether to issue an early warning for children's bronchial asthma symptoms based on breathing audio data;

[0085] An information acquisition module, the information acquisition module is used to acquire historical physiological monitoring data, historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, historical respiratory audio data, historical asthma information, historical asthma time node information and historical asthma duration information, monitor the physiological data and activity environment of the child, acquire actual monitoring physiological data and environmental monitoring data, and transmit them to the evaluation unit;

[0086] An evaluation module, wherein the evaluation module is used to construct a set of conventional physiological data with a calibration deviation value less than the calibration deviation value of the conventional physiological data based on the calibration deviation value of each conventional physiological data, obtain a deviation data set corresponding to each conventional physiological data, obtain a data deviation evaluation coefficient based on the deviation data set, obtain an environmental monitoring evaluation index based on historical environmental monitoring data, and use the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index as a data clustering index;

[0087] The display module interacts with the main control module and is used to output and display reference physiological parameters, actual monitored physiological data, environmental monitoring data and actual threshold values ​​of physiological data.

[0088] Optionally, the main control module specifically includes:

[0089] A control unit, the control unit is used to classify historical physiological monitoring data based on historical asthma information, obtain physiological monitoring data classification information, obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value, determine whether the child's physiological data is abnormal based on actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, and further determine whether to issue an early warning for children's bronchial asthma symptoms based on breathing audio data;

[0090] An information receiving unit, which interacts with the information acquisition module and the evaluation module to receive data and transmit it to the model training unit;

[0091] A model training unit, wherein the model training unit is used to establish an environmental impact model based on calibrated asthma physiological data and baseline environmental monitoring data, fit the environmental impact model according to the asthma data cluster, obtain the basic environmental impact coefficient corresponding to each asthma data cluster, and obtain the environmental impact coefficient based on the basic environmental impact coefficient and the asthma data cluster.

[0092] Optionally, the information acquisition module specifically includes:

[0093] A first acquisition unit, the first acquisition unit is used to acquire historical physiological monitoring data, historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, historical respiratory audio data, historical asthma information, historical asthma time node information and historical asthma duration information;

[0094] The second acquisition unit is used to monitor the physiological data and activity environment of the child, obtain the actual monitored physiological data and environmental monitoring data, and transmit them to the evaluation unit.

[0095] Optionally, the evaluation unit specifically includes:

[0096] a first evaluation unit, the first evaluation unit being used to construct a set of conventional physiological data whose calibration deviation value is smaller than the calibration deviation value of the conventional physiological data based on the calibration deviation value of each conventional physiological data, obtain a deviation data set corresponding to each conventional physiological data, and obtain a data deviation evaluation coefficient according to the deviation data set;

[0097] The second evaluation unit is used to obtain an environmental monitoring evaluation index based on historical environmental monitoring data, and use the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index as the data clustering index.

[0098] Compared with the prior art, the present invention has the following beneficial effects:

[0099] The present invention proposes an intelligent monitoring method and system for bronchial asthma symptoms in children based on multi-source data. Through the data deviation assessment coefficient, historical data is screened to obtain baseline physiological parameters, so as to achieve accurate analysis of the physiological state of children, facilitate timely discovery of abnormal physiological data, and improve the efficiency of asthma symptom monitoring. Through the environmental impact coefficient, the impact of the environment on the physiological data during asthma is accurately analyzed, so as to accurately set the physiological monitoring threshold, ensure the stability and reliability of the monitoring system, and accurately adjust the asthma monitoring in abnormal environments through breathing audio data, ensuring a rapid response to asthma symptom warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] Figure 1 This is a flow chart of the method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data proposed by the present invention;

[0101] Figure 2 A flowchart for obtaining the reference physiological parameters in the present invention;

[0102] Figure 3 A flow chart for obtaining the environmental impact coefficient in the present invention;

[0103] Figure 4 This is a flowchart of asthma symptom warning in the present invention;

[0104] Figure 5 A flow chart for obtaining the maximum value of the high-frequency Mel-frequency cepstral coefficient fluctuation in the present invention;

[0105] Figure 6 This is a structural block diagram of the intelligent monitoring system for children's bronchial asthma symptoms based on multi-source data proposed by the present invention. DETAILED DESCRIPTION

[0106] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0107] Reference Figure 1 - Figure 5 As shown, the intelligent monitoring method for children's bronchial asthma symptoms based on multi-source data in an embodiment of the present invention includes:

[0108] Acquire historical physiological monitoring data, wherein the historical physiological monitoring data includes historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, and historical respiratory audio data;

[0109] Acquiring historical asthma information, wherein the historical asthma information includes historical asthma time node information and historical asthma duration information;

[0110] Based on historical asthma information, historical physiological monitoring data are classified to obtain physiological monitoring data classification information;

[0111] Among them, the historical physiological monitoring data within the duration of asthma is taken as the historical asthma physiological data, and the historical physiological monitoring data outside the duration of asthma is taken as the historical routine physiological data;

[0112] Obtain baseline physiological parameters based on historical routine physiological data;

[0113] Specifically, based on historical routine physiological data, baseline physiological parameters are obtained, including:

[0114] Calculate the average value of historical routine physiological data to obtain the mean value of physiological data;

[0115] According to the historical routine physiological data, the difference between each routine physiological data and the mean value of the physiological data is used as the calibration deviation value of the routine physiological data;

[0116] Based on the calibration deviation value of each conventional physiological data, a set of conventional physiological data with a calibration deviation value smaller than the calibration deviation value of the conventional physiological data is constructed to obtain a deviation data set corresponding to each conventional physiological data;

[0117] According to the deviation data set, obtain the data deviation assessment coefficient;

[0118] The conventional physiological data with the largest data deviation evaluation coefficient is used as the basic physiological data;

[0119] According to the deviation data set corresponding to the basic physiological data, the normal extreme values ​​of the physiological data are obtained, that is, the minimum value of the normal physiological data and the maximum value of the normal physiological data in the deviation data set corresponding to the basic physiological data;

[0120] Obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value;

[0121] The calculation formula of the data deviation evaluation coefficient is:

[0122]

[0123] In the formula, represents the data deviation evaluation coefficient of the xth routine physiological data, represents the deviation dataset of the xth conventional physiological data, Represents the total number of data in the deviation data set of the xth conventional physiological data, is the xth routine physiological data, Indicates the maximum value of the conventional physiological data in the deviation data set of the xth conventional physiological data, represents the minimum value of the conventional physiological data in the deviation data set of the xth conventional physiological data;

[0124] The reference physiological parameters are specifically:

[0125]

[0126] Where E is the baseline physiological parameter, As basic physiological data, is the physiological data correction coefficient, is the mean value of physiological data, and It is the normal extreme value of physiological data.

[0127] In this scheme, the average value of historical heart rate data, historical blood oxygen saturation data and historical respiratory rate data in historical routine physiological data is calculated to obtain the mean value of physiological data of each physiological data, and the difference between each routine physiological data and the mean value of physiological data is used as the calibration deviation value of the routine physiological data. The calibration deviation value of each routine physiological data is used as a benchmark, and a set of routine physiological data with a calibration deviation value less than the calibration deviation value of the routine physiological data is constructed. According to the deviation data set, the data deviation evaluation coefficient is obtained, and the routine physiological data with the largest data deviation evaluation coefficient is used as the basic physiological data. According to the basic physiological data, the mean value of physiological data and the normal extreme value of physiological data, the benchmark physiological parameters are obtained;

[0128] It is understandable that physiological data are quite different between different individuals even under normal conditions, and it is not possible to directly use a unified physiological data standard to monitor the physiological condition of children. However, if the mean value of children's physiological data is directly used as the normal physiological data of children, it not only ignores the differences in daily life, but also fails to accurately analyze the physiological condition of children. Therefore, in this scheme, the deviation of physiological data is analyzed by the data deviation evaluation coefficient. The larger the data deviation evaluation coefficient, the closer the physiological data is to the normal physiological data of children. At the same time, the data is further corrected by the mean value of physiological data and the normal extreme value of physiological data to ensure the accuracy and reliability of the data.

[0129] It is common sense that historical routine physiological data must be concentratedly distributed. The closer to the normal physiological data of children, the more historical monitoring data there are and the more concentrated the values ​​are. Therefore, the larger the data deviation assessment coefficient is, the closer the physiological data is to the normal physiological data of children, and the normal physiological data of children must be between the physiological monitoring data with the largest data deviation assessment coefficient and the mean of the physiological data. However, it is also known that there must be some small errors between the physiological monitoring data at this time and the actual normal physiological data of children. Mathematical analysis shows that in the data distribution, the difference between the actual value and the theoretical value is positively correlated with the difference between the median and the mean. Therefore, in this scheme, the basic physiological data is further adjusted by the physiological data correction coefficient to ensure the accuracy of the data.

[0130] It should be noted that in this scheme, the baseline physiological parameters are baseline heart rate, baseline blood oxygen saturation and baseline respiratory rate. The historical heart rate data, historical blood oxygen saturation data and historical respiratory rate data in the historical routine physiological data are respectively brought into the steps to calculate the baseline physiological parameters corresponding to each physiological data.

[0131] According to the historical asthma physiological data, corresponding historical environmental monitoring data are obtained, wherein the historical environmental monitoring data includes allergen concentration data and air pollutant concentration data;

[0132] Obtain environmental impact coefficients based on baseline physiological parameters, historical asthma physiological data, and historical environmental monitoring data;

[0133] Specifically, the environmental impact coefficients were obtained based on baseline physiological parameters, historical asthma physiological data, and historical environmental monitoring data, including:

[0134] The difference between the historical asthma physiological data and the baseline physiological parameters is used as a physiological difference index, wherein the physiological difference index represents the sum of the differences between each historical asthma physiological data and the baseline physiological parameters;

[0135] Obtain environmental monitoring assessment index based on historical environmental monitoring data;

[0136] The ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring assessment index was used as the data clustering index;

[0137] Obtain environmental change coefficient based on environmental monitoring and evaluation index;

[0138] Sort the historical asthma physiological data in the order of small to large data clustering index to obtain the order information of asthma physiological data;

[0139] According to the order information of asthma physiological data and the environmental change coefficient, the historical asthma physiological data are clustered to obtain asthma physiological data clusters;

[0140] Among them, the ratio of the data clustering index of any two historical asthma physiological data in each asthma physiological data cluster is less than the environmental variation coefficient;

[0141] Obtain environmental impact coefficients based on asthma physiological data clusters and historical environmental monitoring data;

[0142] The data clustering index is specifically:

[0143]

[0144] In the formula, is the data clustering index of the y-th historical asthma physiological data, is the physiological difference index of the y-th historical asthma physiological data, is the environmental monitoring evaluation index of the yth historical asthma physiological data, represents the i-th baseline physiological parameter, where if ,but is the baseline heart rate in the baseline physiological parameters, if ,but is the baseline blood oxygen saturation in the baseline physiological parameters. ,but is the baseline respiratory rate in the baseline physiological parameters, is the ith physiological data item in the yth historical asthma physiological data, is the concentration of the jth substance in the historical environmental monitoring data corresponding to the yth historical asthma physiological data, and n is the total number of allergens and air pollutant types in the historical environmental monitoring data;

[0145] The environmental variation coefficient is specifically:

[0146]

[0147] In the formula, is the environmental variation coefficient, Indicates the maximum value of the environmental monitoring assessment index of historical asthma physiological data, It represents the minimum value of the environmental monitoring assessment index of historical asthma physiological data, and m is the total number of historical asthma physiological data.

[0148] In this scheme, the historical asthma physiological data are clustered, and the data clustering is performed according to the order information of the asthma physiological data, with the first historical asthma physiological data as the clustering center, until the ratio of the data clustering index of the historical asthma physiological data to the data clustering index of the first historical asthma physiological data is greater than or equal to the environmental change coefficient. At this time, the first asthma physiological data cluster distance is completed, and the first historical asthma physiological data that is not clustered in the order information of the asthma physiological data is used as the clustering center, and the clustering steps are repeated until all data clustering is completed, ensuring that the maximum value of the ratio of the data clustering index in each asthma physiological data cluster is less than the environmental change coefficient;

[0149] It is understandable that the data clustering index reflects the relative degree of change in the physiological state of asthma (represented by the physiological difference index) under specific environmental conditions (represented by the environmental monitoring and assessment index). This ratio can initially establish a quantitative relationship between environmental factors and asthma physiological responses, help analyze the sensitivity of asthma physiological changes under different environmental conditions, and provide a basis for subsequent clustering analysis of historical asthma physiological data, so that data with similar environmental-physiological response relationships can be classified into one category. The ratio of the data clustering index of any two historical asthma physiological data represents the change between the environment and the physiological response in each data. However, when the basic physiological condition of children is stable, the range of change of the data clustering index ratio should be smaller than the environmental change, unless there are differences in the basic physiological condition due to factors such as individual daily activities, in which case data clustering is required for separate analysis.

[0150] Specifically, the environmental impact coefficient is obtained based on the asthma physiological data cluster and historical environmental monitoring data, including:

[0151] According to the asthma physiological data cluster, the historical asthma physiological data is matched with the corresponding historical environmental monitoring data to obtain the asthma data cluster;

[0152] The historical asthma physiological data with the smallest physiological difference index in each asthma data cluster is used as the calibrated asthma physiological data of the asthma data cluster;

[0153] The historical environmental monitoring data corresponding to the calibrated asthma physiological data are used as the baseline environmental monitoring data;

[0154] An environmental impact model was established based on calibrated asthma physiological data and baseline environmental monitoring data;

[0155] According to the asthma data clusters, the environmental impact model is fitted to obtain the basic environmental impact coefficient corresponding to each asthma data cluster;

[0156] Obtain the environmental impact coefficient according to the basic environmental impact coefficient and the asthma data cluster;

[0157] The environmental impact model is specifically:

[0158]

[0159] In the formula, represents the i-th physiological data in the z-th historical asthma physiological data in the asthma data cluster, represents the ith physiological data item in the calibrated asthma physiological data of the asthma data cluster, It represents the basic environmental impact coefficient of the j-th substance concentration in the historical environmental monitoring data on the i-th physiological data in the historical asthma physiological data. represents the jth substance concentration in the historical environmental monitoring data corresponding to the zth historical asthma physiological data in the asthma data cluster, represents the concentration of the jth substance in the baseline environmental monitoring data of the asthma data cluster;

[0160] The environmental impact coefficient is specifically:

[0161]

[0162] In the formula, is the environmental impact coefficient of the jth substance concentration on the ith physiological data in the environmental monitoring data, It represents the basic environmental impact coefficient of the j-th substance concentration in the historical environmental monitoring data of the s-th asthma data cluster on the i-th physiological data in the historical asthma physiological data. Environmental variation coefficient, represents the minimum value of the data clustering index in the sth asthma data cluster, represents the maximum value of the data clustering index in the sth asthma data cluster, represents the sth asthma data cluster, and h is the total number of asthma data clusters.

[0163] In this scheme, the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index is used as the data clustering index, and the historical asthma physiological data are sorted in the order of the data clustering index from small to large to obtain the order information of the asthma physiological data. According to the order information of the asthma physiological data and the environmental change coefficient, the historical asthma physiological data are clustered to obtain asthma physiological data clusters. The historical asthma physiological data with the smallest physiological difference index in each asthma data cluster is used as the calibrated asthma physiological data of the asthma data cluster. The historical environmental monitoring data corresponding to the calibrated asthma physiological data is used as the baseline environmental monitoring data. An environmental impact model is established with the calibrated asthma physiological data and the baseline environmental monitoring data as the benchmark. According to the asthma data cluster, the environmental impact model is fitted to obtain the basic environmental impact coefficient corresponding to each asthma data cluster. According to the basic environmental impact coefficient and the asthma data cluster, the environmental impact coefficient is obtained.

[0164] It is understandable that different environments have different effects on children's bronchial asthma symptoms, and it is crucial to monitor children's bronchial asthma symptoms. When the air quality is poor or the allergen concentration is high, the child's respiratory system may be under additional pressure, causing asthma symptoms to worsen. Therefore, the environmental impact coefficient is used to accurately analyze the impact of the environment on children's physiological data;

[0165] It should be noted that when analyzing environmental impacts through historical asthma physiological data, it is not possible to directly perform a comprehensive calculation on all data. Even in the same environment, differences in individual daily activities will also cause differences in physiological data. Therefore, it is necessary to cluster the data to reduce the impact of other factors on physiological data and ensure the accuracy of data analysis results.

[0166] Using the baseline physiological parameters as the baseline threshold of physiological data;

[0167] Monitor children's physiological data and activity environment, and obtain actual physiological data and environmental monitoring data;

[0168] Based on the actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, it is judged whether the child's physiological data is abnormal. If so, an early warning will be issued for the child's bronchial asthma symptoms. If not, real-time monitoring will continue.

[0169] Specifically, based on the actual monitored physiological data, environmental monitoring data, physiological data baseline thresholds and environmental impact coefficients, determine whether the child's physiological data is abnormal, including:

[0170] Obtain the environmental offset value of physiological data based on environmental monitoring data and environmental impact coefficient;

[0171] Obtaining an actual threshold value of the physiological data according to a physiological data baseline threshold value and a physiological data environment offset value;

[0172] According to the historical routine physiological data, the corresponding historical environmental monitoring data is obtained as the routine environmental monitoring data;

[0173] According to conventional environmental monitoring data, the average value of the concentration of each substance in the conventional environmental monitoring data is used as the baseline environmental data, and the substance concentration represents the concentration of allergens and air pollutants;

[0174] According to the actually monitored physiological data and the actual threshold of the physiological data, determining whether the actually monitored physiological data exceeds the actual threshold of the physiological data;

[0175] Among them, if the actual monitoring of physiological data , then continue to monitor the child's physiological data in real time. , then early warning of bronchial asthma symptoms in children;

[0176] like , then obtain the breathing audio data, and further determine whether to issue an early warning for the symptoms of bronchial asthma in children based on the breathing audio data;

[0177] The actual threshold of the physiological data is specifically:

[0178]

[0179] In the formula, represents the first actual threshold value of the physiological data of the i-th item of physiological data, represents the second actual threshold value of the physiological data of the i-th item of physiological data, represents the i-th baseline physiological parameter, The environmental impact coefficient of the jth substance concentration in the environmental monitoring data on the ith physiological data, represents the concentration of the jth substance in the environmental monitoring data, Represents the concentration of the jth substance in the benchmark environmental data.

[0180] In this scheme, the environmental offset value of physiological data is obtained according to the environmental monitoring data and the environmental impact coefficient, the actual threshold value of physiological data is obtained according to the physiological data baseline threshold value and the physiological data environmental offset value, and the actual monitored physiological data and the actual threshold value of physiological data are used to determine whether the actual monitored physiological data exceeds the actual threshold value of physiological data, thereby ensuring timely early warning of children's bronchial asthma symptoms and improving the efficiency and accuracy of coefficient monitoring;

[0181] It is understandable that in a poor air quality environment (such as high PM2.5 concentrations, high concentrations of pollutants or allergens in the air), the child's respiratory system is easily irritated, asthma symptoms may worsen, airway constriction, shortness of breath or hypoxia may become more obvious, and fluctuations in heart rate and blood oxygen saturation may become more drastic due to the interference of these external factors. In order to more accurately identify worsening conditions, smart monitoring systems may set stricter thresholds, that is, the allowable difference becomes smaller relative to the normal fluctuation range, so as to capture possible abnormal signals earlier. For example, if the air quality is poor, even a slight drop in blood oxygen may be regarded as a warning signal, indicating that intervention measures are needed;

[0182] Specifically, based on the breathing audio data, it is further determined whether to issue an early warning for the symptoms of bronchial asthma in children, including:

[0183] According to the historical breathing audio data, the breathing time-frequency diagram is obtained based on short-time Fourier transform;

[0184] Based on the Mel frequency scale, the respiratory time-frequency graph is scaled to obtain the respiratory time-frequency conversion spectrum information;

[0185] According to the spectrum information of respiratory time-frequency conversion, the Mel frequency cepstrum coefficients are obtained based on logarithmic transformation and discrete cosine transformation;

[0186] According to the Mel frequency cepstral coefficients, the Mel frequency cepstral coefficients corresponding to the historical conventional physiological data are used as normal Mel frequency cepstral coefficients to obtain a normal frequency coefficient set;

[0187] According to the historical breathing audio data, based on the frequency band division, the normal frequency coefficient set is divided into a low-frequency band frequency coefficient set and a high-frequency band frequency coefficient set;

[0188] According to the low-frequency band frequency coefficient set, obtain the standard deviation of the Mel-frequency cepstral coefficients;

[0189] According to the high-frequency band frequency coefficient set, obtain the maximum difference of the Mel-frequency cepstral coefficients;

[0190] According to the breathing audio data, based on frequency band division, low-frequency band breathing audio data and high-frequency band breathing audio data are obtained;

[0191] According to the low-frequency breathing audio data, the maximum value of the low-frequency Mel frequency cepstral coefficient is obtained;

[0192] According to the high-frequency breathing audio data, the maximum value of the high-frequency Mel-frequency cepstrum coefficient fluctuation is obtained;

[0193] According to the standard deviation of the Mel frequency cepstral coefficient, the maximum value of the low-frequency Mel frequency cepstral coefficient, the maximum difference of the Mel frequency cepstral coefficient and the maximum fluctuation value of the high-frequency Mel frequency cepstral coefficient, it is judged whether to issue an early warning for the symptoms of bronchial asthma in children;

[0194] Among them, if the maximum value of the low-frequency Mel frequency cepstrum coefficient Or the maximum value of high-frequency Mel-frequency cepstral coefficient fluctuation , then early warning of bronchial asthma symptoms in children, is the standard deviation of the Mel-frequency cepstral coefficients, is the maximum difference of Mel-frequency cepstral coefficients.

[0195] In this scheme, the standard deviation of Mel-frequency cepstral coefficients is obtained according to the low-frequency frequency coefficient set, the maximum difference of Mel-frequency cepstral coefficients is obtained according to the high-frequency frequency coefficient set, low-frequency breathing audio data and high-frequency breathing audio data are obtained based on frequency band division according to the breathing audio data, the maximum value of low-frequency Mel-frequency cepstral coefficients is obtained according to the low-frequency breathing audio data, the maximum value of high-frequency Mel-frequency cepstral coefficient fluctuation is obtained according to the high-frequency breathing audio data, and whether to issue an early warning for the symptoms of bronchial asthma in children is determined according to the standard deviation of Mel-frequency cepstral coefficients, the maximum value of low-frequency Mel-frequency cepstral coefficients, the maximum difference of Mel-frequency cepstral coefficients and the maximum value of high-frequency Mel-frequency cepstral coefficient fluctuation;

[0196] It is understandable that in the analysis of breath sounds, Mel frequency cepstral coefficients (MFCC) can help extract features related to airway sounds and breath sound patterns. By analyzing different types of breath sounds, normal and abnormal breath sounds can be effectively distinguished. These features can help identify different types of breath sounds, such as wheezing, coughing, rales, etc., and then assist in the diagnosis of diseases such as asthma, apnea, pneumonia, etc. In this scheme, the low frequency band is (0-500Hz) and the high frequency band is (100-2000Hz), corresponding to the wheezing sound range. In the low frequency band, if the absolute value of the MFCC coefficient is significantly higher than the normal mean, and multiple continuous coefficients show this change, it may indicate asthma-related airway changes such as airway stenosis and increased secretions, resulting in enhanced low-frequency energy. In the high frequency band (above 500Hz), the MFCC features are stable and low in energy under normal circumstances. If significant fluctuations in the MFCC coefficients are detected, abnormal asthma breath sounds such as wheezing may exist.

[0197] In this solution, when the maximum value of the low-frequency Mel-frequency cepstral coefficient is obtained based on the low-frequency breathing audio data, and the maximum value of the fluctuation of the high-frequency Mel-frequency cepstral coefficient is obtained based on the high-frequency breathing audio data, the steps for obtaining the Mel-frequency cepstral coefficients are consistent with the steps for obtaining the Mel-frequency cepstral coefficients of the historical breathing audio data, and both are well-known calculation formulas, so they are not described in detail.

[0198] Reference Figure 6 As shown, further, in combination with the above-mentioned method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data, an intelligent monitoring system for bronchial asthma symptoms in children based on multi-source data is proposed, including:

[0199] A main control module, wherein the main control module is used to establish an environmental impact model based on calibrated asthma physiological data and baseline environmental monitoring data, fit the environmental impact model based on asthma data clusters, obtain a basic environmental impact coefficient corresponding to each asthma data cluster, obtain an environmental impact coefficient based on the basic environmental impact coefficient and the asthma data cluster, classify historical physiological monitoring data based on historical asthma information, obtain physiological monitoring data classification information, obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value, determine whether the child's physiological data is abnormal based on actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, and further determine whether to issue an early warning for children's bronchial asthma symptoms based on breathing audio data;

[0200] An information acquisition module, the information acquisition module is used to acquire historical physiological monitoring data, historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, historical respiratory audio data, historical asthma information, historical asthma time node information and historical asthma duration information, monitor the physiological data and activity environment of the child, acquire actual monitoring physiological data and environmental monitoring data, and transmit them to the evaluation unit;

[0201] An evaluation module, wherein the evaluation module is used to construct a set of conventional physiological data with a calibration deviation value less than the calibration deviation value of the conventional physiological data based on the calibration deviation value of each conventional physiological data, obtain a deviation data set corresponding to each conventional physiological data, obtain a data deviation evaluation coefficient based on the deviation data set, obtain an environmental monitoring evaluation index based on historical environmental monitoring data, and use the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index as a data clustering index;

[0202] The display module interacts with the main control module and is used to output and display reference physiological parameters, actual monitored physiological data, environmental monitoring data and actual threshold values ​​of physiological data.

[0203] Main control module, specifically including:

[0204] A control unit, the control unit is used to classify historical physiological monitoring data based on historical asthma information, obtain physiological monitoring data classification information, obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value, determine whether the child's physiological data is abnormal based on actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, and further determine whether to issue an early warning for children's bronchial asthma symptoms based on breathing audio data;

[0205] An information receiving unit, which interacts with the information acquisition module and the evaluation module to receive data and transmit it to the model training unit;

[0206] A model training unit, wherein the model training unit is used to establish an environmental impact model based on calibrated asthma physiological data and baseline environmental monitoring data, fit the environmental impact model according to the asthma data cluster, obtain the basic environmental impact coefficient corresponding to each asthma data cluster, and obtain the environmental impact coefficient based on the basic environmental impact coefficient and the asthma data cluster.

[0207] Information acquisition module, specifically including:

[0208] A first acquisition unit, the first acquisition unit is used to acquire historical physiological monitoring data, historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, historical respiratory audio data, historical asthma information, historical asthma time node information and historical asthma duration information;

[0209] The second acquisition unit is used to monitor the physiological data and activity environment of the child, obtain the actual monitored physiological data and environmental monitoring data, and transmit them to the evaluation unit.

[0210] Assessment units include:

[0211] a first evaluation unit, the first evaluation unit being used to construct a set of conventional physiological data whose calibration deviation value is smaller than the calibration deviation value of the conventional physiological data based on the calibration deviation value of each conventional physiological data, obtain a deviation data set corresponding to each conventional physiological data, and obtain a data deviation evaluation coefficient according to the deviation data set;

[0212] The second evaluation unit is used to obtain an environmental monitoring evaluation index based on historical environmental monitoring data, and use the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index as the data clustering index.

[0213] In summary, the advantages of the present invention are: historical data is screened through the data deviation assessment coefficient, baseline physiological parameters are obtained through basic physiological data, physiological data mean and physiological data normal extreme value, the physiological state of children is accurately analyzed through the baseline physiological parameters, the baseline physiological condition of children is determined, it is convenient to timely discover abnormal physiological data, and the efficiency of asthma symptom monitoring is improved, the environmental impact coefficient is obtained through the baseline physiological parameters, historical asthma physiological data and historical environmental monitoring data, and the impact of the environment on the physiological data during asthma is accurately analyzed through the environmental impact coefficient, so as to accurately set the physiological monitoring threshold, ensure the stability and reliability of the monitoring system, and accurately adjust the asthma monitoring in abnormal environment through breathing audio data, to ensure a rapid response to asthma symptom warning.

[0214] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent monitoring method for children's bronchial asthma symptoms based on multi-source data, characterized in that: include: Acquire historical physiological monitoring data, wherein the historical physiological monitoring data includes historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, and historical respiratory audio data; Acquiring historical asthma information, wherein the historical asthma information includes historical asthma time node information and historical asthma duration information; Based on historical asthma information, historical physiological monitoring data are classified to obtain physiological monitoring data classification information; Among them, the historical physiological monitoring data within the duration of asthma is taken as the historical asthma physiological data, and the historical physiological monitoring data outside the duration of asthma is taken as the historical routine physiological data; Obtain baseline physiological parameters based on historical routine physiological data; According to the historical asthma physiological data, corresponding historical environmental monitoring data are obtained, wherein the historical environmental monitoring data includes allergen concentration data and air pollutant concentration data; Obtain environmental impact coefficients based on baseline physiological parameters, historical asthma physiological data, and historical environmental monitoring data; Using the baseline physiological parameters as the baseline threshold of physiological data; Monitor children's physiological data and activity environment, and obtain actual physiological data and environmental monitoring data; Based on the actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, it is judged whether the child's physiological data is abnormal. If so, an early warning will be issued for the child's bronchial asthma symptoms. If not, real-time monitoring will continue.

2. The method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data according to claim 1, characterized in that: The obtaining of the baseline physiological parameters according to the historical conventional physiological data specifically includes: Calculate the average value of historical routine physiological data to obtain the mean value of physiological data; According to the historical routine physiological data, the difference between each routine physiological data and the mean value of the physiological data is used as the calibration deviation value of the routine physiological data; Based on the calibration deviation value of each conventional physiological data, a set of conventional physiological data with a calibration deviation value smaller than the calibration deviation value of the conventional physiological data is constructed to obtain a deviation data set corresponding to each conventional physiological data; According to the deviation data set, obtain the data deviation assessment coefficient; The conventional physiological data with the largest data deviation evaluation coefficient is used as the basic physiological data; According to the deviation data set corresponding to the basic physiological data, the normal extreme values ​​of the physiological data are obtained, that is, the minimum value of the normal physiological data and the maximum value of the normal physiological data in the deviation data set corresponding to the basic physiological data; Obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value; The calculation formula of the data deviation evaluation coefficient is: In the formula, represents the data deviation evaluation coefficient of the xth routine physiological data, represents the deviation dataset of the xth conventional physiological data, Represents the total number of data in the deviation data set of the xth conventional physiological data, is the xth routine physiological data, Indicates the maximum value of the conventional physiological data in the deviation data set of the xth conventional physiological data, represents the minimum value of the conventional physiological data in the deviation data set of the xth conventional physiological data; The reference physiological parameters are specifically: Where E is the baseline physiological parameter, As basic physiological data, is the physiological data correction coefficient, is the mean value of physiological data, and It is the normal extreme value of physiological data.

3. The method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data according to claim 1, characterized in that: The environmental impact coefficient is obtained according to the baseline physiological parameters, historical asthma physiological data and historical environmental monitoring data, specifically including: The difference between the historical asthma physiological data and the baseline physiological parameters is used as a physiological difference index, wherein the physiological difference index represents the sum of the differences between each historical asthma physiological data and the baseline physiological parameters; Obtain environmental monitoring assessment index based on historical environmental monitoring data; The ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring assessment index was used as the data clustering index; Obtain environmental change coefficient based on environmental monitoring and evaluation index; Sort the historical asthma physiological data in the order of small to large data clustering index to obtain the order information of asthma physiological data; According to the order information of asthma physiological data and the environmental change coefficient, the historical asthma physiological data are clustered to obtain asthma physiological data clusters; Among them, the ratio of the data clustering index of any two historical asthma physiological data in each asthma physiological data cluster is less than the environmental variation coefficient; Obtain environmental impact coefficients based on asthma physiological data clusters and historical environmental monitoring data; The data clustering index is specifically: In the formula, is the data clustering index of the y-th historical asthma physiological data, is the physiological difference index of the y-th historical asthma physiological data, is the environmental monitoring evaluation index of the yth historical asthma physiological data, represents the i-th baseline physiological parameter, where if ,but is the baseline heart rate in the baseline physiological parameters, if ,but is the baseline blood oxygen saturation in the baseline physiological parameters. ,but is the baseline respiratory rate in the baseline physiological parameters, is the ith physiological data item in the yth historical asthma physiological data, is the concentration of the jth substance in the historical environmental monitoring data corresponding to the yth historical asthma physiological data, and n is the total number of allergens and air pollutant types in the historical environmental monitoring data; The environmental variation coefficient is specifically: In the formula, is the environmental variation coefficient, Indicates the maximum value of the environmental monitoring assessment index of historical asthma physiological data, It represents the minimum value of the environmental monitoring assessment index of historical asthma physiological data, and m is the total number of historical asthma physiological data.

4. The method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data according to claim 3, characterized in that: The environmental impact coefficient is obtained according to the asthma physiological data cluster and the historical environmental monitoring data, specifically including: According to the asthma physiological data cluster, the historical asthma physiological data is matched with the corresponding historical environmental monitoring data to obtain the asthma data cluster; The historical asthma physiological data with the smallest physiological difference index in each asthma data cluster is used as the calibrated asthma physiological data of the asthma data cluster; The historical environmental monitoring data corresponding to the calibrated asthma physiological data are used as the baseline environmental monitoring data; An environmental impact model was established based on calibrated asthma physiological data and baseline environmental monitoring data; According to the asthma data clusters, the environmental impact model is fitted to obtain the basic environmental impact coefficient corresponding to each asthma data cluster; Obtain the environmental impact coefficient according to the basic environmental impact coefficient and the asthma data cluster; The environmental impact model is specifically: In the formula, represents the i-th physiological data in the z-th historical asthma physiological data in the asthma data cluster, represents the ith physiological data item in the calibrated asthma physiological data of the asthma data cluster, It represents the basic environmental impact coefficient of the j-th substance concentration in the historical environmental monitoring data on the i-th physiological data in the historical asthma physiological data. represents the jth substance concentration in the historical environmental monitoring data corresponding to the zth historical asthma physiological data in the asthma data cluster, represents the concentration of the jth substance in the baseline environmental monitoring data of the asthma data cluster; The environmental impact coefficient is specifically: In the formula, is the environmental impact coefficient of the jth substance concentration on the ith physiological data in the environmental monitoring data, It represents the basic environmental impact coefficient of the j-th substance concentration in the historical environmental monitoring data of the s-th asthma data cluster on the i-th physiological data in the historical asthma physiological data. Environmental variation coefficient, represents the minimum value of the data clustering index in the sth asthma data cluster, represents the maximum value of the data clustering index in the sth asthma data cluster, represents the sth asthma data cluster, and h is the total number of asthma data clusters.

5. The method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data according to claim 1, characterized in that: The determining whether the child's physiological data is abnormal based on the actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient specifically includes: Obtain the environmental offset value of physiological data based on environmental monitoring data and environmental impact coefficient; Obtaining an actual threshold value of the physiological data according to a physiological data baseline threshold value and a physiological data environment offset value; According to the historical routine physiological data, the corresponding historical environmental monitoring data is obtained as the routine environmental monitoring data; According to conventional environmental monitoring data, the average value of the concentration of each substance in the conventional environmental monitoring data is used as the baseline environmental data, and the substance concentration represents the concentration of allergens and air pollutants; According to the actually monitored physiological data and the actual threshold of the physiological data, determining whether the actually monitored physiological data exceeds the actual threshold of the physiological data; Among them, if the actual monitoring of physiological data , then continue to monitor the child's physiological data in real time. , then early warning of bronchial asthma symptoms in children; like , then obtain the breathing audio data, and further determine whether to issue an early warning for the symptoms of bronchial asthma in children based on the breathing audio data; The actual threshold of the physiological data is specifically: In the formula, represents the first actual threshold value of the physiological data of the i-th item of physiological data, represents the second actual threshold value of the physiological data of the i-th item of physiological data, represents the i-th baseline physiological parameter, The environmental impact coefficient of the jth substance concentration in the environmental monitoring data on the ith physiological data, represents the concentration of the jth substance in the environmental monitoring data, Represents the concentration of the jth substance in the benchmark environmental data.

6. The method for intelligent monitoring of bronchial asthma symptoms in children based on multi-source data according to claim 5, characterized in that: Further determining whether to issue an early warning for the symptoms of bronchial asthma in children based on the breathing audio data specifically includes: According to the historical breathing audio data, the breathing time-frequency diagram is obtained based on short-time Fourier transform; Based on the Mel frequency scale, the respiratory time-frequency graph is scaled to obtain the respiratory time-frequency conversion spectrum information; According to the spectrum information of respiratory time-frequency conversion, the Mel frequency cepstrum coefficients are obtained based on logarithmic transformation and discrete cosine transformation; According to the Mel frequency cepstral coefficients, the Mel frequency cepstral coefficients corresponding to the historical conventional physiological data are used as normal Mel frequency cepstral coefficients to obtain a normal frequency coefficient set; According to the historical breathing audio data, based on the frequency band division, the normal frequency coefficient set is divided into a low-frequency band frequency coefficient set and a high-frequency band frequency coefficient set; According to the low-frequency band frequency coefficient set, obtain the standard deviation of the Mel-frequency cepstral coefficients; According to the high-frequency band frequency coefficient set, obtain the maximum difference of the Mel-frequency cepstral coefficients; According to the breathing audio data, based on frequency band division, low-frequency band breathing audio data and high-frequency band breathing audio data are obtained; According to the low-frequency breathing audio data, the maximum value of the low-frequency Mel frequency cepstral coefficient is obtained; According to the high-frequency breathing audio data, the maximum value of the high-frequency Mel-frequency cepstrum coefficient fluctuation is obtained; According to the standard deviation of the Mel frequency cepstral coefficient, the maximum value of the low-frequency Mel frequency cepstral coefficient, the maximum difference of the Mel frequency cepstral coefficient and the maximum fluctuation value of the high-frequency Mel frequency cepstral coefficient, it is judged whether to issue an early warning for the symptoms of bronchial asthma in children; Among them, if the maximum value of the low-frequency Mel frequency cepstrum coefficient Or the maximum value of high-frequency Mel-frequency cepstral coefficient fluctuation , then early warning of bronchial asthma symptoms in children, is the standard deviation of the Mel-frequency cepstral coefficients, is the maximum difference of Mel-frequency cepstral coefficients.

7. An intelligent monitoring system for children's bronchial asthma symptoms based on multi-source data, used to implement the monitoring method according to any one of claims 1 to 6, characterized in that: include: A main control module, wherein the main control module is used to establish an environmental impact model based on calibrated asthma physiological data and baseline environmental monitoring data, fit the environmental impact model based on asthma data clusters, obtain a basic environmental impact coefficient corresponding to each asthma data cluster, obtain an environmental impact coefficient based on the basic environmental impact coefficient and the asthma data cluster, classify historical physiological monitoring data based on historical asthma information, obtain physiological monitoring data classification information, obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value, determine whether the child's physiological data is abnormal based on actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, and further determine whether to issue an early warning for children's bronchial asthma symptoms based on breathing audio data; An information acquisition module, the information acquisition module is used to acquire historical physiological monitoring data, historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, historical respiratory audio data, historical asthma information, historical asthma time node information and historical asthma duration information, monitor the physiological data and activity environment of the child, acquire actual monitoring physiological data and environmental monitoring data, and transmit them to the evaluation unit; An evaluation module, wherein the evaluation module is used to construct a set of conventional physiological data with a calibration deviation value less than the calibration deviation value of the conventional physiological data based on the calibration deviation value of each conventional physiological data, obtain a deviation data set corresponding to each conventional physiological data, obtain a data deviation evaluation coefficient based on the deviation data set, obtain an environmental monitoring evaluation index based on historical environmental monitoring data, and use the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index as a data clustering index; The display module interacts with the main control module and is used to output and display reference physiological parameters, actual monitored physiological data, environmental monitoring data and actual threshold values ​​of physiological data.

8. The intelligent monitoring system for children's bronchial asthma symptoms based on multi-source data according to claim 7, characterized in that: The main control module specifically includes: A control unit, the control unit is used to classify historical physiological monitoring data based on historical asthma information, obtain physiological monitoring data classification information, obtain baseline physiological parameters based on basic physiological data, physiological data mean and physiological data normal extreme value, determine whether the child's physiological data is abnormal based on actual monitored physiological data, environmental monitoring data, physiological data baseline threshold and environmental impact coefficient, and further determine whether to issue an early warning for children's bronchial asthma symptoms based on breathing audio data; An information receiving unit, which interacts with the information acquisition module and the evaluation module to receive data and transmit it to the model training unit; A model training unit, wherein the model training unit is used to establish an environmental impact model based on calibrated asthma physiological data and baseline environmental monitoring data, fit the environmental impact model according to the asthma data cluster, obtain the basic environmental impact coefficient corresponding to each asthma data cluster, and obtain the environmental impact coefficient based on the basic environmental impact coefficient and the asthma data cluster.

9. The intelligent monitoring system for children's bronchial asthma symptoms based on multi-source data according to claim 7, characterized in that: The information acquisition module specifically includes: A first acquisition unit, the first acquisition unit is used to acquire historical physiological monitoring data, historical heart rate data, historical blood oxygen saturation data, historical respiratory rate data, historical respiratory audio data, historical asthma information, historical asthma time node information and historical asthma duration information; The second acquisition unit is used to monitor the physiological data and activity environment of the child, obtain the actual monitored physiological data and environmental monitoring data, and transmit them to the evaluation unit.

10. The intelligent monitoring system for children's bronchial asthma symptoms based on multi-source data according to claim 7, characterized in that: The evaluation unit specifically comprises: a first evaluation unit, the first evaluation unit being used to construct a set of conventional physiological data whose calibration deviation value is smaller than the calibration deviation value of the conventional physiological data based on the calibration deviation value of each conventional physiological data, obtain a deviation data set corresponding to each conventional physiological data, and obtain a data deviation evaluation coefficient according to the deviation data set; The second evaluation unit is used to obtain an environmental monitoring evaluation index based on historical environmental monitoring data, and use the ratio of the physiological difference index of each historical asthma physiological data to the corresponding environmental monitoring evaluation index as the data clustering index.

Images