Vital sign management system and method based on wearable device

Abstract

The invention provides a vital sign management system and method based on wearable equipment, and belongs to the technical field of medical health, the wearable equipment collects vital sign time sequence data, motion state time sequence data and environment time sequence data of a target object; the data processing terminal selects an influence coefficient sequence corresponding to the motion state time sequence data and the environment time sequence data; determining a streaming update threshold value based on the time sequence according to the influence coefficient sequence and a predetermined initial threshold value; and performing abnormal data detection on the vital sign time sequence data according to the streaming update threshold, and / or performing vital sign management on the target object according to the vital sign time sequence data, the motion state time sequence data, the environment time sequence data and the streaming update threshold. According to the method, abnormal data detection or vital sign management is carried out by using the streaming update threshold, and accurate sign analysis under special conditions or environments can be realized.

Description

Technical Field

[0001] The present invention relates to the field of medical health technology, and in particular to a vital sign management system and method based on wearable devices. Background Art

[0002] In the field of medical health, accurately monitoring and analyzing human activities and their vital signs time series data has become an increasing demand. In order to achieve dynamic monitoring of human vital signs signals, wearable vital signs monitoring systems have become people's ideal products. With the widespread popularization of short-range wireless communication technology, more and more intelligent wearable devices have come into people's daily lives. Wearable vital signs monitoring systems are not only a tool for future smart life and work, but also an important terminal for collecting and processing various user data in the networking era.

[0003] Existing wearable devices such as smart watches and bracelets are prone to distortion of vital signs signals under motion conditions or vibration environments, making it difficult to achieve accurate analysis of vital signs under special conditions or environments. Summary of the invention

[0004] The present invention provides a vital sign management system and method based on a wearable device, which solves the defect that the existing wearable devices are prone to distortion of vital sign signals under motion conditions or vibration environments, and it is difficult to achieve accurate analysis of vital signs under special conditions or environments.

[0005] The present invention provides a vital sign management system based on a wearable device, comprising a wearable device and a data processing terminal communicatively connected to the wearable device; The wearable device is used to collect the vital sign time series data, the motion state time series data and the environment time series data of the target object, and transmit them to the data processing terminal, wherein the vital sign time series data and the environment time series data are both multi-parameter time series data; The data processing terminal is used to select an influence coefficient sequence corresponding to the motion state time series data and the environmental time series data, the influence coefficient being used to characterize the influence of the target object on vital signs in different motion states and different environments; determine a streaming update threshold based on the time series according to the influence coefficient sequence and a predetermined initial threshold; perform abnormal data detection on the vital sign time series data according to the streaming update threshold, and / or perform vital sign management on the target object according to the vital sign time series data, the motion state time series data, the environmental time series data and the streaming update threshold.

[0006] As an embodiment, the performing vital sign management on the target object according to the vital sign time series data, the motion state time series data, the environment time series data and the streaming update threshold includes: The motion state time series data and the environment time series data perform weighted processing on the vital sign time series data based on a time attention mechanism to obtain weighted vital sign time series data; Performing correlation analysis on the vital sign time series data or the weighted vital sign time series data based on principal component analysis and grey correlation analysis, and taking parameter time series data with a correlation degree higher than a threshold as target vital sign time series data; performing abnormal data detection on the weighted vital sign time series data and / or the target vital sign time series data according to the streaming update threshold to determine the overall condition of the vital signs of the target object; Inputting the vital sign time series data, the weighted vital sign time series data and / or the target vital sign time series data into a pre-trained prediction model to obtain a vital sign prediction result of the target object; If the overall condition of the target object's vital signs or the predicted results of the vital signs are abnormal, an alarm message is issued.

[0007] As an embodiment, the wearable device includes an adaptive feedback device, which includes a control module and at least one self-rescue module. The control module is used to control the self-rescue module to execute preset self-rescue measures in response to the alarm information initiated by the data processing terminal or in response to the received adaptive feedback measure command.

[0008] As an embodiment, the self-rescue module includes at least one of a heating module, an electrical stimulation module and a microneedle drug delivery module, and the microneedle drug delivery module includes a micro-airbag pressurization module and a flexible microneedle patch, and the flexible microneedle patch is integrated with the carrier of the wearable device.

[0009] As an embodiment, the heating module outputs heating power or cooling power to achieve temperature regulation based on the difference between a preset temperature and the ambient temperature, the difference between the preset temperature and the body temperature of the target object, and a preset first control coefficient. The electrical stimulation module dynamically adjusts the electrical stimulation parameters based on the electromyographic signal of the target object. The micro-airbag pressurization module outputs heating power or airbag pressurization data based on the difference between the preset heating temperature and the temperature of the flexible microneedle patch, the difference between the preset air pressure and the airbag air pressure, and a preset first control coefficient.

[0010] As an embodiment, it also includes a team-based analysis and decision-making platform, which is used to obtain the vital sign time series data, the motion state time series data and the environmental time series data uploaded by the wearable device or the data processing terminal, and perform vital sign management on the target object based on a target scenario data model that successfully matches the current application scenario of the target object, the historical monitoring data of the target object and / or the vital sign parameters of the same team as the target object.

[0011] As an embodiment, the team-based analysis and decision-making platform is provided with a plurality of scenario data models, and members corresponding to each scenario data model are used as team members. Correspondingly, the matching step of the target scenario data model includes: Based on principal component analysis, respectively determine the principal components of vital signs and motion status of the target object and the team members; Determine the grey correlation between the principal components of the vital signs and the motion status of the target object and the team members based on the grey correlation analysis; The scene data model corresponding to the team member with the highest grey correlation matching degree is used as the target scene data model of the target object.

[0012] As an embodiment, the team-based analysis and decision-making platform is also used to execute rescue / dispatch measures based on the vital sign management data of the target object.

[0013] As an embodiment, the vital signs time series data include time series data of multiple parameters including heart rate, respiration, blood oxygen, blood pressure, body temperature, and sweat of the target object, and the environmental time series data include time series data of multiple parameters including temperature, humidity, altitude, air pressure, and position.

[0014] The present invention also provides a vital sign management method based on a wearable device, comprising: Collecting the vital sign time series data, motion state time series data and environment time series data of the target object, wherein both the vital sign time series data and the environment time series data are multi-parameter time series data; Selecting an influence coefficient sequence corresponding to the motion state time series data and the environment time series data, the influence coefficient being used to characterize the influence of the target object on vital signs in different motion states and different environments; Determining a time series-based streaming update threshold according to the influence coefficient sequence and a predetermined initial threshold; Abnormal data detection is performed on the vital sign time series data according to the streaming update threshold, and / or vital sign management is performed on the target object according to the vital sign time series data, the motion state time series data, the environment time series data and the streaming update threshold.

[0015] The wearable device-based vital signs management system and method provided by the present invention can achieve accurate analysis of vital signs under special conditions or environments by selecting an influence coefficient sequence corresponding to the motion state time series data and the environmental time series data to determine a streaming update threshold, and using the streaming update threshold to perform abnormal data detection on the vital signs time series data or perform vital signs management on the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is one of the structural schematic diagrams of the vital sign management system based on wearable devices provided by the present invention.

[0018] Figure 2 It is a structural schematic diagram of the wearable device provided by the present invention.

[0019] Figure 3 It is a flow chart of deep fusion analysis and abnormality monitoring performed by the data processing terminal provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the adaptive feedback device provided by the present invention.

[0021] Figure 5 This is the second structural schematic diagram of the vital signs management system based on wearable devices provided by the present invention.

[0022] Figure 6 It is a structural diagram of the team-based analysis and decision-making platform provided by the present invention.

[0023] Figure 7 It is a flow chart of the vital sign management method based on wearable device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] It should be noted that all actions of acquiring signals, information or data in the present invention are performed in compliance with the corresponding data protection laws and policies of the location and with the authorization given by the owner of the corresponding device.

[0026] Figure 1 is one of the structural diagrams of the vital signs management system based on wearable devices provided by the present invention, such as Figure 1 As shown, the present invention also provides a vital sign management system based on a wearable device, including a wearable device 10 and a data processing terminal 20 communicatively connected to the wearable device. The data processing terminal 20 can be integrated on the wearable device 10 and connected to the wearable device 10 by wire or wireless communication, or can be separately arranged from the wearable device 10 and connected to the wearable device 10 by wireless communication.

[0027] The wearable device 10 is used to collect the vital sign time series data, motion state time series data and environmental time series data of the target object, and transmit them to the data processing terminal, wherein the vital sign time series data and the environmental time series data are both multi-parameter time series data.

[0028] The data processing terminal 20 is used to select an influence coefficient sequence corresponding to the motion state time series data and the environmental time series data, the influence coefficient being used to characterize the influence of the target object on the vital signs in different motion states and different environments; determine a streaming update threshold based on the time series according to the influence coefficient sequence and a predetermined initial threshold; perform abnormal data detection on the vital sign time series data according to the streaming update threshold, and / or perform vital sign management on the target object according to the vital sign time series data, the motion state time series data, the environmental time series data and the streaming update threshold.

[0029] By detecting abnormal data on the vital sign time series data according to the streaming update threshold, the data collection stability of the wearable device can be determined. If abnormal data is detected continuously, it is determined that the stability of the wearable device 10 is insufficient. The vital sign management of the target object includes determining, predicting and warning the overall condition of the vital signs of the target object.

[0030] It can be understood that the present invention determines the streaming update threshold by selecting the influence coefficient sequence corresponding to the motion state time series data and the environmental time series data, and uses the streaming update threshold to detect abnormal data on the vital signs time series data or perform vital signs management on the target object, thereby realizing accurate analysis of vital signs under special conditions or environments.

[0031] Based on the above embodiment, as an optional embodiment, the vital signs time series data includes time series data of multiple parameters in the target object's heart rate, respiration, blood oxygen, blood pressure, body temperature, and sweat, and the environmental time series data includes time series data of multiple parameters in temperature, humidity, altitude, air pressure, and position.

[0032] like Figure 2 As shown, the wearable device integrates a vital sign signal and motion state monitoring unit, an environmental signal monitoring unit, a processing chip and a multi-dimensional data transmission unit. The vital sign signal monitoring unit includes but is not limited to an electrocardiogram sensor, a respiration sensor, a blood oxygen sensor, a blood pressure sensor, a temperature sensor, a sweat sensor and an accelerometer. The electrocardiogram sensor, the respiration sensor, the blood oxygen sensor, the blood pressure sensor, the temperature sensor, the sweat sensor and other sensors are respectively used to collect vital sign parameters such as heart rate, respiration, blood oxygen, blood pressure, body temperature, sweat and other vital sign parameters of the target object. The accelerometer is used to collect the motion state of the target object. The environmental signal monitoring unit includes but is not limited to a temperature sensor, a humidity sensor, an air pressure height sensor, an ambient light sensor, and a positioning system, which is used to collect parameters such as temperature, humidity, height, air pressure, light, and position of the environment in which the target object is located. The processing chip processes the real-time data collected by the vital sign signal and motion state monitoring unit and the environmental signal monitoring unit respectively to obtain multi-parameter and multi-dimensional time series data and transmits it to the multi-dimensional data transmission unit via the multi-dimensional data transmission unit.

[0033] Preferably, wearable devices include but are not limited to smart bracelets, smart hats, and monitoring vests, which are used to collect real-time physiological data such as heart rate, respiration, blood pressure, blood sugar, blood oxygen saturation, temperature, electromyography, electroencephalography, sweat, etc. of the target object; environmental data such as temperature, humidity, altitude, air pressure, and location; behavioral data such as movement speed, exercise time, number of steps, and step frequency, as well as personal basic information, medical history records, and previous health management data input by the target object.

[0034] The time series data collected by the wearable device needs to be preprocessed to improve the monitoring accuracy, which can be performed on the wearable device or on the data processing terminal. The embodiment of the present invention is described by taking the data processing terminal as an example.

[0035] Preprocessing includes noise removal, outlier detection, and outlier coefficient calculation. The outlier coefficient is used to provide a reference for the wearing stability of wearable devices and the validity of sensor data.

[0036] Motion state sensors such as accelerometers and environmental signal monitoring units do not need to be close to the skin of the target object, and data preprocessing can be performed directly through low-pass filtering, zero-bias error correction, Kalman filtering and other methods.

[0037] The sensors used to collect the target object's vital signs need to be in close contact with the target object's skin and are affected to a certain extent by the body's movement state or sweat. There are problems such as electrode detachment and slippage to varying degrees, which affect the validity of the data.

[0038] Based on the statistical process control over the threshold (SPOT), the present invention introduces the human body motion state and the influence coefficients corresponding to different states ( I ms ) to detect abnormal data, for example, I ms = 1; human body jogging I ms =1.08; human body in rapid motion I ms =1.21, etc. An influence coefficient library can be constructed based on a large amount of measured data, and after the wearable device detects the vital sign signal, motion state signal and environmental signal of the target object, the corresponding influence coefficient is selected from the influence coefficient library.

[0039] The initial threshold is obtained based on a large amount of measured data and can be expressed as t 0 , streaming update threshold I t The update formula under time series is as follows: in, q is the probability of an extreme event, n is the number of all monitoring time points, N t is more than t 0 The peak number of σ is the extreme value index and γ is the scale parameter.

[0040] Streaming update threshold based on time series I t It can effectively detect abnormal data in vital signs time series data.

[0041] Update thresholds based on abnormal data and streaming I t Can be used to calculate the anomaly coefficient (Anomaly coefficient, A c ), the calculation formula is as follows: in, X t It's at the time t The actual observed value at I t It's at the time t The streaming update threshold at .

[0042] The instability of the physiological sign detection electrodes of the wearable device can be preliminarily judged through abnormal fluctuations of a single parameter in a short period of time (higher abnormal coefficient) and abnormal fluctuations of other parameters (lower abnormal coefficient), thereby issuing a prompt of insufficient wearing stability.

[0043] It is understandable that the monitoring parameters of the present invention include heart rate, respiration, blood oxygen, blood pressure, body temperature, sweat, exercise status, etc., which can monitor not only common heart rate, respiration, and body temperature signals, but also complex sweat signals, solving the defects of the existing vital signs monitoring system, which has relatively single functions, relatively limited monitoring range, and cannot meet the needs of comprehensive and continuous monitoring. The present invention uses wearable close-fitting clothing as a carrier and based on algorithm optimization, can effectively avoid data deviations caused by strenuous exercise, avoid high false alarms in physiological monitoring abnormal warnings and omission of real abnormal data, and improve the quality of real-time data collection of wearable devices.

[0044] Based on the above embodiments, as an optional embodiment, a wearable device based on a clothing carrier sends the collected vital signs, motion status, and environmental time series data to a data processing terminal in real time. The data processing terminal is used for deep fusion analysis, anomaly monitoring, anomaly prediction, and anomaly alarm of multi-dimensional time series data to achieve management of the vital signs of the target object.

[0045] The data processing terminal normalizes the vital signs, motion status, and environmental time series data respectively to make them have the same time scale, and performs corresponding denoising filtering and signal amplification processing, and then extracts features respectively to obtain vital signs features, motion status features, and environmental feature time series data. Based on the streaming update thresholds corresponding to different motion states and environmental information, abnormal judgments and threshold alarms can be made for single or multiple vital signs.

[0046] like Figure 3As shown, the vital sign management of the target object according to the vital sign time series data, the motion state time series data, the environment time series data and the streaming update threshold includes the following steps.

[0047] The motion state time series data and the environment time series data perform weighted processing on the vital sign time series data based on a time attention mechanism to obtain weighted vital sign time series data.

[0048] Based on principal component analysis and grey correlation analysis, correlation analysis is performed on the vital sign time series data or the weighted vital sign time series data, and parameter time series data with a correlation degree higher than a threshold is used as target vital sign time series data.

[0049] The weighted vital sign time series data and / or the target vital sign time series data are detected for abnormal data according to the streaming update threshold value to determine the overall condition of the vital signs of the target object.

[0050] The vital sign time series data, the weighted vital sign time series data and / or the target vital sign time series data are input into a pre-trained prediction model to obtain a vital sign prediction result of the target object.

[0051] If the overall condition of the target object's vital signs or the predicted results of the vital signs are abnormal, an alarm message is issued.

[0052] Optionally, after abnormal data is removed from the vital sign time series data or the weighted vital sign time series data, a standardization calculation is performed, a covariance matrix is ​​calculated based on the standardized data, and a principal component analysis is performed based on the covariance matrix.

[0053] The formula for normalization calculation is as follows: in, X is the coefficient for eliminating abnormalities in the time series A c Data greater than 0.95, μ is the coefficient for eliminating abnormalities A c The mean of data greater than 0.95, ε is the coefficient for eliminating abnormalities A c The standard deviation of the data is greater than 0.95, X stand is the normalized data matrix.

[0054] The weighted vital sign time series data include exercise training status time series data and physical and mental health status time series data. The principal components of vital signs include eigenvector matrices of 5 or more parameters such as heart rate, respiration, blood pressure, blood oxygen saturation, temperature, electromyography, movement speed, ambient temperature, altitude, and air pressure; the principal components of exercise training status include eigenvector matrices of 5 or more parameters such as heart rate, respiration, blood oxygen saturation, temperature, electromyography, sweat ion concentration, sweat pH, sweat lactic acid value, exercise speed, exercise time, number of steps, step frequency, ambient temperature, altitude, and air pressure; the principal components of physical and mental health status include eigenvector matrices of 5 or more parameters such as heart rate, respiration, blood pressure, blood sugar, sweat ion concentration, sweat pH, sweat lactic acid value, ambient temperature, and air pressure.

[0055] The correlation between the principal components of vital signs, exercise training status, and physical and mental health status is evaluated based on grey correlation analysis, and multiple parameters with strong correlation are used to reflect the vital sign status of the target object.

[0056] Optionally, the pre-trained prediction model is a long short-term memory autoencoder, which is trained to predict normal vital sign time series data, and compare the difference between the predicted value and the actual value. If the difference is greater than a preset threshold, it is determined that the vital sign of the target object is abnormal. The prediction model can also be combined with a streaming update threshold to improve the accuracy of detection.

[0057] Based on the above embodiment, as an optional embodiment, Figure 4 As shown, the wearable device includes an adaptive feedback device, which includes a control module and at least one self-rescue module. The control module is used to control the self-rescue module to execute preset self-rescue measures in response to the alarm information initiated by the data processing terminal or in response to the received adaptive feedback measure command.

[0058] The adaptive feedback device of the wearable intelligent device based on the clothing carrier receives the alarm information and adaptive feedback measure commands from the data processing terminal through the signal receiving module, the control module completes the instruction requirements, and the self-rescue module completes the instruction requirements issued by the control module.

[0059] Optionally, the self-rescue module includes at least one of a heating module, an electrical stimulation module and a microneedle drug delivery module, and the microneedle drug delivery module includes a micro-airbag pressurization module and a flexible microneedle patch, and the flexible microneedle patch is integrated with the carrier of the wearable device. The wearable device is a clothing carrier, and correspondingly, the heating module, the electrical stimulation module and the microneedle drug delivery module are all flexible structures. The flexible electric heating module is woven by flexible electric heating fibers and integrated with the clothing carrier in the front chest and back of the body, and is connected by fiber conductors, a control module and a matching power supply module, which can realize heating and warming self-rescue measures when the human body is hypothermic. The flexible electrical stimulation module is woven by flexible conductive fibers and integrated with the clothing carrier in different body surface positions such as the arms, abdomen, and chest, and is connected by flexible fiber conductors, a control module and a matching power supply module to relieve muscle fatigue through electrical stimulation. The flexible microneedle drug delivery module is integrated with a flexible microneedle patch and a clothing carrier. It can carry different drug molecules, including but not limited to cardiovascular disease drugs, inflammatory drugs, hemostatic drugs, etc., and is connected by a flexible fiber conductor, a control module and a matching power supply module. It promotes controllable drug delivery through airbag pressurization and electric heating to dissolve the microneedles.

[0060] Optionally, the heating module outputs heating power or cooling power to achieve temperature regulation based on the difference between the preset temperature and the ambient temperature, the difference between the preset temperature and the human body temperature of the target object, and a preset first control coefficient. The temperature control formula of the heating module is as follows: in, u(t) is the controller output (heating / cooling power), e(t 1 ) is the temperature difference (the difference between the set temperature and the ambient temperature), e(t 2 ) is the temperature difference (the difference between the set temperature and the human body temperature), ρ is the ambient temperature coefficient, θ is the human body temperature coefficient K p1 、K i1 、K d1 They are the proportional, integral and differential control coefficients of the ambient temperature; K p2 、K i2 、K d2 They are the proportional, integral and differential control coefficients of human body temperature respectively.

[0061] The electrical stimulation module dynamically adjusts the electrical stimulation parameters based on the electromyographic signal (Root Mean Square, RMS) of the target object. The RMS calculation formula is as follows: in, x i To remove the sampling values ​​with abnormal coefficients > 0.95, N is the number of sampling points.

[0062] The micro-airbag pressurization module outputs heating power or airbag pressurization data based on the difference between the preset heating temperature and the temperature of the flexible microneedle patch, the difference between the preset air pressure and the airbag air pressure, and the preset first control coefficient. The micro-airbag pressurization module performs controllable drug delivery based on the temperature control algorithm and the micro-airbag pressurization control algorithm. The specific formula is as follows: in, u(P,T) is the controller output (micro airbag inflation / electric heating power), e P (t) is the pressure difference (the difference between the set pressure and the airbag pressure), e T (t) is the temperature difference (the difference between the heating setting temperature and the microneedle patch temperature), is the integral of the pressure difference is the integral of the temperature difference; ψAir pressure coefficient, τ is the temperature coefficient, K Pp 、K Pi 、K Pd They are the proportional, integral, and differential control coefficients of air pressure; K Tp 、K Ti 、K Td They are the temperature proportional, integral and differential control coefficients respectively.

[0063] It can be understood that the present invention monitors multi-dimensional vital signs and environmental signal data at different times through wearable smart devices, and forms a comparative analysis of the physical condition before and after the adaptive feedback unit by the data processing terminal, which can trigger self-rescue measures after the threshold alarm, and expand conventional vital signs monitoring and early warning to real-time adaptive feedback measures.

[0064] Based on the above embodiment, as an optional embodiment, Figure 5As shown, the present invention also includes a team-based analysis and decision-making platform, wearable devices and data processing terminals for monitoring individuals, and the team-based analysis and decision-making platform can access the wearable devices and data processing terminals of several different individual users (such as the target object in this application), obtain multi-source, multi-dimensional vital signs information data and, fusion information results and whether there are abnormal conditions, to form a vital signs information parameter set for each individual user. According to different scenarios such as smart elderly care, intensive care, daily sports training, military training, battlefield rescue, extreme environment rescue, etc., individuals are divided into several teams, and the vital signs of one or more groups of personnel are centrally managed and data is shared.

[0065] like Figure 6 As shown, the team-based analysis and decision-making platform is also used to conduct data comparison and analysis on parameter sets to evaluate health conditions. The comparison and analysis includes using the scenario data model as a reference. The various scenario models in the scenario model matching unit include: 1. Major disease data model, disease prevention data model, and sports training data model can match the user's current application scenario to conduct multi-dimensional data comparison and analysis; 2. Using historical monitoring data as a reference, conduct time series comparison and analysis of multi-dimensional data; 3. Using the vital sign information parameter set of different users as a reference, conduct horizontal comparison of individual multi-dimensional data. Based on the scenario data model, historical monitoring data, and the vital sign information parameter set of the same user, based on the current vital sign information parameters, conduct health status assessment, predict possible vital sign changes, and further implement rescue dispatch arrangements.

[0066] Specifically, the team-based analysis and decision-making platform is used to obtain the vital signs time series data, the motion state time series data and the environmental time series data uploaded by the wearable device or the data processing terminal, and perform vital signs management on the target object based on a target scenario data model that successfully matches the current application scenario of the target object, the historical monitoring data of the target object and / or the vital signs parameters of the same team as the target object.

[0067] Optionally, the team-based analysis and decision-making platform is provided with a plurality of scenario data models, and the members corresponding to each scenario data model are used as team members. Correspondingly, the matching step of the target scenario data model includes the following steps.

[0068] Based on principal component analysis, the principal components of vital signs and motion status of the target object and each of the team members are determined respectively.

[0069] Based on the grey correlation analysis, the grey correlation between the principal components of the vital signs and the motion status of the target object and the team members is determined respectively.

[0070] The scene data model corresponding to the team member with the highest grey correlation matching degree is used as the target scene data model of the target object.

[0071] Optionally, the team-based analysis and decision-making platform is also used to execute rescue / dispatch measures based on the vital signs management data of the target object.

[0072] The principal components of the team members' vital signs status, exercise training status, and physical and mental health status are extracted from the scenario model in different scenarios. The correlation coefficients and calculated correlations between the principal component data sets of different states of the team members and the data sets of each state of the model are analyzed through grey correlation to match the scenario data model with the highest correlation.

[0073] The calculation formula of the correlation coefficient is as follows: in, ξ i,j It is the grey correlation coefficient between the principal component data sets of different states of team members and the data sets of each state of the model; Δ min It is the minimum absolute value of the difference between the two sequences (the subsequence of the principal component data set of different states of the team members and the parent sequence of the data set of each state of the model); Δ max It is the maximum absolute value of the difference between the two sequences (the subsequence of the principal component data set of different states of the team members and the parent sequence of the data set of each state of the model); ρ is the resolution coefficient; Δ t(i,j) It is the absolute value of the difference between the values ​​of the two sequences, that is, the absolute value of the difference between the observation values ​​of the subsequence and the parent sequence at the same observation time (the same row).

[0074] The calculation formula of correlation is as follows: R i,j It is the subsequence of the principal component dataset of different status of team members i The parent sequence of each state data set of the model j Grey relational degree of ξ i,j is the grey correlation coefficient; L is the length of the sequence, i.e. the number of observations; num Is the sequence number of the data in the sequence.

[0075] The calculation formula for the overall similarity is as follows: ROverall similarity; α, β, …, ω is the correlation weight coefficient of different parameter sequences, m is the logarithm of the sequence.

[0076] The overall similarity between the principal components of different states and the data of each state of the model can be R The value size is matched to obtain the scene data model with the highest correlation and use it as the target scene data model.

[0077] The team analysis and decision-making platform can predict the development of the vital signs of team members based on the target scenario data model and provide feedback. In addition, the above method can also be used to compare the historical monitoring data sequence with the real-time monitoring data sequence to prevent the recurrence of diseases, etc.; by comparing the sequence data between different users of team members, the main components of the vital signs status, the main components of the sports training status, and the main components of the physical and mental health of the team members can be analyzed, and reasonable deployment arrangements for the team members can be proposed.

[0078] It can be understood that the present invention sets up a team-based analysis and decision-making platform for centralized management / data sharing of the vital signs of one or more groups of personnel in a centralized and unified manner, thereby realizing functions such as centralized management, data sharing, efficient response, unified standards, and resource optimization.

[0079] The following is a description of the vital sign management method based on a wearable device provided by the present invention. The vital sign management method based on a wearable device described below and the vital sign management system based on a wearable device described above can correspond to each other.

[0080] Figure 7 is a flow chart of a vital sign management method based on a wearable device provided by the present invention, such as Figure 7 As shown, the present invention also provides a vital sign management method based on a wearable device, comprising the following steps.

[0081] Step S100, collecting vital sign time series data, motion state time series data of a target object and environmental time series data of the environment in which the target object is located, wherein the vital sign time series data and the environmental time series data are both multi-parameter time series data.

[0082] Step S200 , selecting an influence coefficient sequence corresponding to the motion state time series data and the environment time series data, where the influence coefficient is used to characterize the influence of the target object on vital signs in different motion states and different environments.

[0083] Step S300: determining a time series-based streaming update threshold according to the influence coefficient sequence and a predetermined initial threshold.

[0084] Step S400, performing abnormal data detection on the vital sign time series data according to the streaming update threshold, and / or performing vital sign management on the target object according to the vital sign time series data, the motion state time series data, the environment time series data and the streaming update threshold.

[0085] It should be noted that the wearable device-based vital signs management method provided by the present invention, when specifically run, is implemented based on the wearable device-based vital signs management system described in any of the above embodiments, and has a technical effect corresponding to the system, which will not be elaborated in this embodiment.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vital sign management system based on wearable devices, characterized in that: A wearable device and a data processing terminal connected to the wearable device for communication; The wearable device is used to collect the vital sign time series data, the motion state time series data and the environment time series data of the target object, and transmit them to the data processing terminal, wherein the vital sign time series data and the environment time series data are both multi-parameter time series data; The data processing terminal is used to select an influence coefficient sequence corresponding to the motion state time series data and the environmental time series data, the influence coefficient being used to characterize the influence of the target object on vital signs in different motion states and different environments; determine a streaming update threshold based on the time series according to the influence coefficient sequence and a predetermined initial threshold; perform abnormal data detection on the vital sign time series data according to the streaming update threshold, and / or perform vital sign management on the target object according to the vital sign time series data, the motion state time series data, the environmental time series data and the streaming update threshold.

2. The wearable device-based vital sign management system according to claim 1, characterized in that: The performing vital sign management on the target object according to the vital sign time series data, the motion state time series data, the environment time series data and the streaming update threshold comprises: The motion state time series data and the environment time series data perform weighted processing on the vital sign time series data based on a time attention mechanism to obtain weighted vital sign time series data; Performing correlation analysis on the vital sign time series data or the weighted vital sign time series data based on principal component analysis and grey correlation analysis, and taking parameter time series data with a correlation degree higher than a threshold as target vital sign time series data; performing abnormal data detection on the weighted vital sign time series data and / or the target vital sign time series data according to the streaming update threshold to determine the overall condition of the vital signs of the target object; Inputting the vital sign time series data, the weighted vital sign time series data and / or the target vital sign time series data into a pre-trained prediction model to obtain a vital sign prediction result of the target object; If the overall condition of the target object's vital signs or the predicted results of the vital signs are abnormal, an alarm message is issued.

3. The wearable device-based vital sign management system according to claim 2, characterized in that: The wearable device includes an adaptive feedback device, which includes a control module and at least one self-rescue module. The control module is used to control the self-rescue module to execute preset self-rescue measures in response to the alarm information initiated by the data processing terminal or in response to the received adaptive feedback measure command.

4. The wearable device-based vital sign management system according to claim 3, characterized in that: The self-rescue module includes at least one of a heating module, an electrical stimulation module and a microneedle drug delivery module, and the microneedle drug delivery module includes a micro-airbag pressurization module and a flexible microneedle patch, and the flexible microneedle patch is integrated with the carrier of the wearable device.

5. The wearable device-based vital sign management system according to claim 4, characterized in that: The heating module outputs heating power or cooling power to achieve temperature regulation based on the difference between the preset temperature and the ambient temperature, the difference between the preset temperature and the body temperature of the target object, and a preset first control coefficient. The electrical stimulation module dynamically adjusts the electrical stimulation parameters based on the electromyographic signal of the target object. The micro-airbag pressurization module outputs heating power or airbag pressurization data based on the difference between the preset heating temperature and the temperature of the flexible microneedle patch, the difference between the preset air pressure and the airbag air pressure, and a preset first control coefficient.

6. The wearable device-based vital sign management system according to any one of claims 1 to 5, characterized in that: It also includes a team-based analysis and decision-making platform, which is used to obtain the vital sign time series data, the motion state time series data and the environmental time series data uploaded by the wearable device or the data processing terminal, and perform vital sign management on the target object based on a target scenario data model that successfully matches the current application scenario of the target object, the historical monitoring data of the target object and / or the vital sign parameters of the same team as the target object.

7. The wearable device-based vital sign management system according to claim 6, characterized in that: The team-based analysis and decision-making platform is provided with a plurality of scenario data models, and the members corresponding to each scenario data model are used as team members. Correspondingly, the matching step of the target scenario data model includes: Based on principal component analysis, respectively determine the principal components of vital signs and motion status of the target object and the team members; Determine the grey correlation between the principal components of the vital signs and the motion status of the target object and the team members based on the grey correlation analysis; The scene data model corresponding to the team member with the highest grey correlation matching degree is used as the target scene data model of the target object.

8. The wearable device-based vital sign management system according to claim 6, characterized in that: The team-based analysis and decision-making platform is also used to execute rescue / dispatch measures based on the vital sign management data of the target object.

9. The wearable device-based vital sign management system according to any one of claims 1-5, 7-8, characterized in that: The vital sign time series data includes time series data of multiple parameters including heart rate, respiration, blood oxygen, blood pressure, body temperature, and sweat of the target object, and the environmental time series data includes time series data of multiple parameters including temperature, humidity, altitude, air pressure, and position.

10. A vital sign management method based on a wearable device, characterized in that: include: Collecting the vital sign time series data, motion state time series data and environment time series data of the target object, wherein both the vital sign time series data and the environment time series data are multi-parameter time series data; Selecting an influence coefficient sequence corresponding to the motion state time series data and the environment time series data, the influence coefficient being used to characterize the influence of the target object on vital signs in different motion states and different environments; Determining a time series-based streaming update threshold according to the influence coefficient sequence and a predetermined initial threshold; Abnormal data detection is performed on the vital sign time series data according to the streaming update threshold, and / or vital sign management is performed on the target object according to the vital sign time series data, the motion state time series data, the environment time series data and the streaming update threshold.

Images