Method for monitoring health state of personnel in rear delivery cabin based on Internet of Things
By using IoT technology to monitor the health status of the evacuation cabin in real time, a monitoring benchmark is established and abnormal signals are identified. This solves the problem of multi-indicator collaborative analysis, enables early warning and dual protection, and improves the accuracy of health monitoring and environmental adaptability of the evacuation cabin.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CSSC HAISHEN MEDICAL TECH CO LTD
- Filing Date
- 2025-12-25
- Publication Date
- 2026-05-15
AI Technical Summary
Existing post-transfer cabin health monitoring systems rely on traditional portable devices and fixed threshold alarms, making it difficult to achieve multi-indicator collaborative analysis, lacking individualized anomaly judgment, and having insufficient stability in complex environments, thus failing to optimize the transfer environment in a timely manner to alleviate the deterioration of the condition.
The IoT-based method for monitoring the health status of the evacuation cabin establishes a monitoring benchmark by monitoring various health indicators in real time, identifies abnormal signals, and compares trends with historical data to achieve correlation identification between characteristic indicators and auxiliary indicators and coordinated control of environmental parameters.
It enables multi-indicator coordinated anomaly monitoring, provides early warning and dual protection, improves the scientific nature of medical rescue decisions and the adaptability to the transportation environment, and avoids misjudgment and data loss.
Smart Images
Figure CN122050797A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of health monitoring technology, specifically to a method for monitoring the health status of personnel in a reflux evacuation cabin based on the Internet of Things. Background Technology
[0002] In the field of medical transport, the evacuation cabin is a key mobile medical vehicle for transporting critically ill patients and injured or sick people from the scene to medical institutions. Continuous and accurate monitoring of the health status of the personnel inside the cabin is the core prerequisite for ensuring safe transport and improving the quality of medical care.
[0003] With the continuous upgrading of emergency medical needs, the application scenarios of evacuation cabins have expanded to diverse scenarios such as disaster relief, battlefield medical care, and remote medical transport, which puts forward higher requirements for the real-time performance, comprehensiveness, and intelligence level of health monitoring technology.
[0004] Currently, health monitoring in evacuation wards largely relies on traditional portable monitoring devices and fixed threshold alarm modes, depending primarily on manual monitoring and data interpretation by medical staff, which presents numerous technical bottlenecks. On one hand, existing monitoring devices are mostly single-point monitoring devices, with data on various health indicators (such as heart rate, blood pressure, and blood oxygen saturation) operating independently, making it difficult to achieve coordinated analysis of multiple indicators and capture abnormal signals related to each indicator. On the other hand, the transmission and processing of monitoring data are mostly local storage, lacking integration with historical medical data in the cloud, making it difficult to make differentiated anomaly judgments based on individual baseline data, and easily leading to false alarms or missed alarms due to universal threshold settings. Furthermore, in complex transport environments (such as turbulence, extreme temperature and humidity, and electromagnetic interference), the stability and anti-interference capabilities of existing monitoring devices are insufficient, easily resulting in data loss or distortion, further affecting monitoring reliability.
[0005] Meanwhile, traditional monitoring systems only have data acquisition and alarm functions, lacking the ability to coordinate and regulate cabin environmental parameters (such as temperature, humidity, and oxygen concentration), and cannot optimize the transfer environment in a timely manner to alleviate the deterioration of the condition when health abnormalities are detected.
[0006] Against this backdrop, building an intelligent and collaborative health status monitoring system for personnel in the post-transfer cabin based on Internet of Things (IoT) technology has become a key technological requirement for improving the level of mobile medical transport and ensuring the safety of transport. Summary of the Invention
[0007] To address the shortcomings of existing technologies, this invention provides an IoT-based method for monitoring the health status of personnel in the evacuation cabin, which solves the problems of independent health indicator data, difficulty in achieving collaborative analysis of multiple indicators, and inability to capture abnormal signals related to indicators.
[0008] To achieve the above objectives, the present invention provides a method for monitoring the health status of personnel in a evacuation cabin based on the Internet of Things, comprising the following steps:
[0009] Step 1: Based on the monitoring process, confirm the parameter changes of various health indicators, identify whether there are any abnormal states in the health indicators, and generate abnormal signals in real time, including:
[0010] Based on real-time monitoring of various health indicators, the corresponding indicator parameters at the corresponding time are identified, and the indicator change curves associated with the corresponding health indicators are generated in real time.
[0011] Using the current time as the calibration time, a set of traceability cycles is identified, and the traceability cycle is a preset cycle. Within the corresponding indicator change curve, the curve segment associated with the traceability cycle is recorded as the benchmark segment. The change trend of the corresponding indicator parameter at adjacent times is identified from the benchmark segment, and several sets of change trends generated by this indicator parameter within the traceability cycle are determined. The minimum and maximum values are identified from them, and the change trend interval belonging to the corresponding indicator parameter is generated as the monitoring benchmark.
[0012] For the corresponding indicator parameters, identify the trend of change of the next moment relative to the current moment, and assess whether this trend is within the confirmed monitoring benchmark. If so, no processing is required; otherwise, an abnormal signal is generated and output.
[0013] Step 2: Based on the abnormal signals, identify a set of abnormal monitoring periods, extract the correlation trend segments of various health indicators within the abnormal monitoring period, and record the extracted correlation trend segments as segments to be evaluated, specifically including:
[0014] Based on the generated abnormal signals, the health indicators associated with the abnormal signals are identified as feature indicators, and the duration of the feature indicators with respect to the abnormal signals is identified, and the duration of the generated duration is recorded as the abnormal monitoring period.
[0015] The curve segments of characteristic indicators within the abnormal monitoring period are recorded as characteristic trend segments. Then, other health indicators are identified as having abnormal states within the abnormal monitoring period. If they do, the health indicators with abnormal states are labeled as auxiliary indicators; otherwise, no labeling is performed.
[0016] The curve segments generated by the auxiliary indicators during the abnormal monitoring period are determined, and the part of the curve segments that belong to the abnormal state are determined from the determined curve segments. The part of the curve segments that belong to the abnormal state are recorded as the auxiliary trend segments.
[0017] The characteristic trend segments and associated trend segments identified within the anomaly monitoring period are integrated as the segments to be evaluated associated within the anomaly monitoring period.
[0018] Step 3: Based on the confirmed assessment segment and historical data, identify baseline data from the historical data according to trend changes. Then, evaluate multiple health indicators one by one based on the baseline data, confirm the proportional characteristics associated with the corresponding health indicators, and then output signals based on the proportional characteristics. The specific confirmation method is as follows:
[0019] Identify the characteristic trend segments associated with the characteristic indicators within the segment to be evaluated, determine the indicator parameters of these characteristic trend segments, and identify the minimum and maximum values as the characteristic intervals of the characteristic trend segments. Based on these characteristic intervals, extract the associated data located within these intervals from historical data, and generate the associated data change curves based on the time relationships associated with the associated data.
[0020] Place the related data change curve and the characteristic trend segment in the same two-dimensional coordinate system, and translate the characteristic trend segment back and forth. Record the partial overlap between the characteristic trend segment and the related data change curve in several translation processes, and record the proportion of the partial overlap segment located in the characteristic trend segment. The proportion value = the length of the partial overlap segment bus ÷ the length of the characteristic trend segment bus. From the determined proportion values, select the maximum value, and record the translation process associated with the maximum value as the standard process. Record the partial curve associated with the standard process as the selected curve. This selected curve is located within the related data change curve.
[0021] The relevant indicator parameters of the selected curve with respect to other health indicators are recorded as auxiliary parameters, and the corresponding auxiliary parameter change curves are generated based on the time relationship.
[0022] The changing trends of different indicator parameters at adjacent time points are identified from the variation curves of the auxiliary parameters. The average value of the identified trends is then calculated and recorded as the curve characteristic TZ1 of the corresponding indicator parameter in the corresponding time period. i Then, extract the corresponding indicator parameters from the segment to be evaluated, simultaneously confirm the changing trend of the corresponding trend segment with respect to adjacent time points, and simultaneously perform mean processing, recording it as the trend characteristic TZ2 of the corresponding corresponding trend segment. i , where i represents different index parameters.
[0023] Preferably, the process of determining the trend of change includes:
[0024] The proposed index parameter for the next adjacent time step is C1. i The index parameter at the previous moment was C2. i Where i represents different indicator parameters, and its changing trend = C2 i -C1 i .
[0025] Preferred options also include:
[0026] Step 4: If all proportional characteristics meet the standards, the generated abnormal signals can be displayed directly. If one or more of the proportional characteristics fail to meet the standards, the cabin parameter characteristic adjustment process will be executed, and abnormal signals of other health indicators will be generated and displayed simultaneously, including:
[0027] The indicator parameters associated with abnormal signals are denoted as characteristic indicators, and other indicator parameters are denoted as auxiliary indicators. The trend characteristics TZ2 are confirmed based on the corresponding auxiliary trend segments. i Confirm a set of floating ranges [TZ2] i -0.3TZ2 i TZ2 i +0.3TZ2 i If the curve characteristic TZ1 of the indicator parameter corresponding to the subordinate trend segment i All satisfy: TZ1 i ∈[TZ2 i -0.3TZ2 i TZ2 i +0.3TZ2 i If the abnormal signal of this characteristic indicator is displayed, then the abnormal signal of this characteristic indicator will be displayed directly; otherwise, the cabin parameter characteristic debugging process will be executed.
[0028] Identify the curve features TZ1 associated with the auxiliary indicators. i And the associated floating range, if TZ1 i If the range is less than the floating range, the associated debugging parameters will be locked directly, and the corresponding debugging parameters will be adjusted upwards. At the same time, an abnormal signal for this auxiliary indicator will be generated and displayed.
[0029] If TZ1 i If the range is floating, the associated debugging parameters will be locked directly, and the corresponding debugging parameters will be adjusted downwards. At the same time, an abnormal signal for this auxiliary indicator will be generated and displayed.
[0030] This invention provides a method for monitoring the health status of personnel in a reflux evacuation cabin based on the Internet of Things (IoT). Compared with existing technologies, it has the following advantages:
[0031] On the one hand, by monitoring the changes in health indicator parameters in real time and constructing a monitoring benchmark by combining the trend range of changes within the traceability period, it is possible to identify potential abnormal trends in advance when the indicator values are within the normal range, thus achieving early warning of "abnormal changes without exceeding the standard"; on the other hand, by directly comparing with the preset standard range, it can quickly respond to serious abnormalities that clearly exceed the standard, forming a dual protection system of "trend warning + threshold warning".
[0032] This innovative approach introduces a correlation identification logic between characteristic indicators and auxiliary indicators. After confirming an anomaly in a characteristic indicator, it simultaneously investigates the abnormal states of other health indicators within the anomaly monitoring period, integrating the characteristic trend segment and the auxiliary trend segment to form an evaluation segment, thus achieving collaborative monitoring of multiple indicator anomalies. By constructing a benchmark data system based on historical data and analyzing the correlation changes between various indicators through trend feature comparison, it can accurately distinguish between "fluctuations in auxiliary indicators caused by abnormal characteristic indicators" and "independent anomalies in multiple indicators." This provides data support for medical personnel to comprehensively assess the health status of individuals and pinpoint the root causes of abnormalities, avoiding misjudgments caused by interpreting single indicator data in isolation and improving the scientific rigor of medical care decisions. Attached Figure Description
[0033] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation
[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0035] First Embodiment
[0036] Please see Figure 1 This application provides a method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things, including the following steps:
[0037] Step 1: Monitor the health indicators of relevant personnel in the cabin in real time, and identify any abnormal health conditions based on the parameter changes of each health indicator. Generate abnormal signals in real time. Specifically, in the monitoring process of the corresponding parameter indicators, there is a process of parameter changes. When a parameter indicator changes abnormally, it is necessary to take timely analysis measures, plan for possible health risks in advance, and output signals in a timely manner so that relevant medical staff can take rescue measures in advance.
[0038] Step 2: Based on the abnormal signals, identify a set of abnormal monitoring cycles, and extract the correlation trend segments of various health indicators within the abnormal monitoring cycles. Record the extracted multiple sets of correlation trend segments as segments to be evaluated.
[0039] Step 3: Based on the confirmed evaluation segment and historical data, identify the baseline data from the historical data according to the trend change relationship, and then evaluate multiple health indicators one by one according to the baseline data, confirm the proportional characteristics associated with the corresponding health indicators, and output signals based on the proportional characteristics.
[0040] Step 4: If all ratio characteristics meet the standards, the generated abnormal signals can be displayed directly. If one or more of the ratio characteristics fail to meet the standards, the cabin parameter characteristic debugging process will be executed, and abnormal signals of other health indicators will be generated and displayed simultaneously.
[0041] Second Embodiment
[0042] In this embodiment, compared to the above embodiments, this embodiment mainly focuses on the confirmation process of abnormal signals in step one.
[0043] In step one, the specific methods for generating abnormal signals include:
[0044] Based on real-time monitoring of various health indicators, the corresponding indicator parameters at the corresponding time are identified, and the indicator change curves associated with the corresponding health indicators are generated in real time.
[0045] Using the current time as the calibration time, a set of traceability cycles is identified. These cycles are preset and typically 3 minutes in length. The specific value is determined in advance by the operator based on experience. Within the corresponding indicator change curve, the curve segment associated with the traceability cycle is recorded as the baseline segment. The changing trend of the corresponding indicator parameters at adjacent times is identified from the baseline segment, and the indicator parameter at the next adjacent time is determined as C1. i The index parameter at the previous moment was C2. i Where i represents different indicator parameters, and its changing trend = C2 i -C1 i The system will determine several sets of change trends for this indicator parameter within the traceability period, identify the minimum and maximum values, and generate the change trend range for the corresponding indicator parameter as a monitoring benchmark.
[0046] For the corresponding indicator parameters, identify the trend of change of the next moment relative to the current moment, and assess whether this trend is within the confirmed monitoring benchmark. If so, no processing is required; otherwise, an abnormal signal is generated and output.
[0047] The monitoring process also includes: comparing and verifying each health indicator with the preset standard range. When the monitored health indicator does not fall within the corresponding standard range, an early warning is directly displayed for external personnel to view. This indicates that the monitored parameter indicator has obvious abnormalities and an early warning can be issued directly. The above monitoring process is in the case that the corresponding values are within the normal range and no obvious abnormalities have occurred.
[0048] Specifically, all parameters of the personnel inside the cabin are under real-time monitoring. When all parameters are within the normal range, it is necessary to monitor in real time whether there are any abnormal changes in the corresponding parameters. Such abnormal changes refer to whether there are any abnormal changes in the trend. If so, it is necessary to issue an alert, analyze and warn of the abnormal data, and identify whether there are any deteriorating indicators or other situations.
[0049] The specific methods for confirming the sections to be evaluated include:
[0050] Based on the generated abnormal signals, the health indicators associated with the abnormal signals are identified as feature indicators, and the duration of the feature indicators with respect to the abnormal signals is identified, and the duration of the generated duration is recorded as the abnormal monitoring period.
[0051] The curve segments of characteristic indicators within the abnormal monitoring period are recorded as characteristic trend segments. Then, other health indicators are identified as having abnormal states within the abnormal monitoring period. If they do, the health indicators with abnormal states are labeled as auxiliary indicators; otherwise, no labeling is performed.
[0052] The curve segments generated by the auxiliary indicators during the abnormal monitoring period are determined, and the part of the curve segments that belong to the abnormal state are determined from the determined curve segments. The part of the curve segments that belong to the abnormal state are recorded as the auxiliary trend segments.
[0053] The characteristic trend segments and associated trend segments identified within the anomaly monitoring period are integrated as the segments to be evaluated associated within the anomaly monitoring period.
[0054] Specifically, in order to more accurately identify abnormal indicators, we must first confirm the specific indicator with an abnormal state based on the abnormal signal, then confirm the associated benchmark data based on this abnormal indicator and historical cloud data, and then identify the relevant changes of other indicators with respect to the corresponding data from the associated benchmark data, so as to confirm the relevant trend of change, and thus comprehensively confirm the corresponding signal and make relevant adjustments.
[0055] Third Embodiment
[0056] In this embodiment, compared to the above embodiments, the specific confirmation process of the proportional characteristics is the main focus. Specifically, in step three, the methods for confirming the proportional characteristics include:
[0057] Identify the characteristic trend segments associated with the characteristic indicators within the segment to be evaluated, determine the indicator parameters of these characteristic trend segments, and identify the minimum and maximum values as the characteristic intervals of the characteristic trend segments. Based on these characteristic intervals, extract the associated data located within these intervals from historical data, and generate a curve of associated data change based on the time relationship between the associated data (this curve is a discontinuous curve, and there is no corresponding associated curve in some time periods).
[0058] Place the related data change curve and the characteristic trend segment in the same two-dimensional coordinate system, and translate the characteristic trend segment back and forth. Record the partial overlap between the characteristic trend segment and the related data change curve in several translation processes, and record the proportion of the partial overlap segment located in the characteristic trend segment. The proportion value = the length of the partial overlap segment bus ÷ the length of the characteristic trend segment bus. From the determined proportion values, select the maximum value, and record the translation process associated with the maximum value as the standard process. Record the partial curve associated with the standard process as the selected curve. This selected curve is located within the related data change curve.
[0059] The relevant parameters of the selected curve related to other health indicators are recorded as auxiliary parameters (that is, in the historical data, there is not only one health indicator, but multiple sets, all of which are evaluated according to the corresponding time relationship. After the selected curve is determined, there is a corresponding time period. Then, the other data belonging to this time period are confirmed, and the auxiliary parameters associated with other health indicators can be effectively obtained). Based on the time relationship, the auxiliary parameter change curve of the corresponding auxiliary parameter is generated.
[0060] The changing trends of different indicator parameters at adjacent time points are identified from the variation curves of the auxiliary parameters. The average value of the identified trends is then calculated and recorded as the curve characteristic TZ1 of the corresponding indicator parameter in the corresponding time period. i Then, extract the corresponding indicator parameters from the segment to be evaluated, simultaneously confirm the changing trend of the corresponding trend segment with respect to adjacent time points, and simultaneously perform mean processing, recording it as the trend characteristic TZ2 of the corresponding corresponding trend segment. i , where i represents different index parameters.
[0061] The specific assessment process for step four also includes:
[0062] The indicator parameters associated with abnormal signals are denoted as characteristic indicators, and other indicator parameters are denoted as auxiliary indicators. The trend characteristics TZ2 are confirmed based on the corresponding auxiliary trend segments. i Confirm a set of floating ranges [TZ2] i -0.3TZ2 i TZ2 i +0.3TZ2 iIf the curve characteristic TZ1 of the indicator parameter corresponding to the subordinate trend segment i All satisfy: TZ1 i ∈[TZ2 i -0.3TZ2 i TZ2 i +0.3TZ2 i If the abnormal signal of this characteristic indicator is displayed, then the abnormal signal of this characteristic indicator will be displayed directly; otherwise, the cabin parameter characteristic debugging process will be executed.
[0063] Identify the curve features TZ1 associated with the auxiliary indicators. i And the associated floating range, if TZ1 i If the floating range is less than 1, the associated debugging parameters will be locked directly (in the preset state, the debugging parameters associated with the corresponding indicator can be directly confirmed), and the corresponding debugging parameters will be adjusted upwards, and an abnormal signal of this auxiliary indicator will be generated and displayed simultaneously.
[0064] If TZ1 i > If the range is floating, the associated debugging parameters will be locked directly, and the corresponding debugging parameters will be adjusted downwards. At the same time, an abnormal signal for this auxiliary indicator will be generated and displayed.
[0065] Specifically, in the monitoring environment of the cabin, when the characteristic indicators of the monitored abnormal signals are abnormal, other auxiliary indicators will generally also be abnormal. In the specific evaluation process, a comprehensive evaluation can be made based on the corresponding change characteristics and ranges. When the identified abnormality is within the fluctuation range, it means that the corresponding abnormality is caused by the abnormality of the corresponding characteristic indicator, and the abnormality signal of the corresponding characteristic indicator can be directly generated. If the abnormality associated with the corresponding auxiliary indicator exceeds the corresponding range, it means that not only is the corresponding characteristic indicator abnormal, but other auxiliary indicators are also abnormal. This type of abnormality is not caused by the abnormality of the characteristic indicator, but by other parameter indicators or physical condition. In this case, the signal is directly displayed to facilitate timely response and treatment by medical staff.
[0066] Some of the data in the above formulas are numerical calculations with dimensions removed, and the contents not described in detail in this specification are all prior art known to those skilled in the art.
[0067] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.
Claims
1. A method for monitoring the health status of personnel in a reflux evacuation cabin based on the Internet of Things, characterized in that, Includes the following steps: Step 1: Based on the monitoring process, confirm the parameter change process of each health indicator, identify whether there are any abnormal states in the health indicators, and generate abnormal signals in real time. Step 2: Based on the abnormal signals, identify a set of abnormal monitoring cycles, extract the correlation trend segments of various health indicators within the abnormal monitoring cycle, and record the extracted multiple sets of correlation trend segments as segments to be evaluated. Step 3: Based on the confirmed evaluation segment and historical data, identify the baseline data from the historical data according to the trend change relationship, and then evaluate multiple health indicators one by one according to the baseline data, confirm the proportional characteristics associated with the corresponding health indicators, and then output signals based on the proportional characteristics.
2. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 1, characterized in that, In step one, the process of generating the abnormal signal specifically includes: Based on real-time monitoring of various health indicators, the corresponding indicator parameters at the corresponding time are identified, and the indicator change curves associated with the corresponding health indicators are generated in real time. Using the current time as the calibration time, a set of traceability cycles is identified, and the traceability cycle is a preset cycle. Within the corresponding indicator change curve, the curve segment associated with the traceability cycle is recorded as the benchmark segment. The change trend of the corresponding indicator parameter at adjacent times is identified from the benchmark segment, and several sets of change trends generated by this indicator parameter within the traceability cycle are determined. The minimum and maximum values are identified from them, and the change trend interval belonging to the corresponding indicator parameter is generated as the monitoring benchmark. For the corresponding indicator parameters, identify the trend of change of the next moment relative to the current moment, and assess whether this trend is within the confirmed monitoring benchmark. If so, no processing is required; otherwise, an abnormal signal is generated and output.
3. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 2, characterized in that, The process of determining the trend of change includes: The proposed index parameter for the next adjacent time step is C1. i The index parameter at the previous moment was C2. i Where i represents different indicator parameters, and its changing trend = C2 i -C1 i .
4. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 1, characterized in that, In step two, the specific methods for confirming the segment to be evaluated include: Based on the generated abnormal signals, the health indicators associated with the abnormal signals are identified as feature indicators, and the duration of the feature indicators with respect to the abnormal signals is identified, and the duration is recorded as the abnormal monitoring period. The curve segments of characteristic indicators within the abnormal monitoring period are recorded as characteristic trend segments. Then, other health indicators are identified as having abnormal states within the abnormal monitoring period. If they do, the health indicators with abnormal states are labeled as auxiliary indicators; otherwise, no labeling is performed. The curve segments generated by the auxiliary indicators during the abnormal monitoring period are determined, and the part of the curve segments that belong to the abnormal state are determined from the determined curve segments. The part of the curve segments that belong to the abnormal state are recorded as the auxiliary trend segments. The characteristic trend segments and associated trend segments identified within the anomaly monitoring period are integrated and used as the evaluation segments associated with the anomaly monitoring period.
5. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 1, characterized in that, In step three, the specific method for confirming the proportional characteristics is as follows: Identify the characteristic trend segments associated with the characteristic indicators within the segment to be evaluated, determine the indicator parameters of these characteristic trend segments, and identify the minimum and maximum values as the characteristic intervals of the characteristic trend segments. Based on these characteristic intervals, extract the associated data located within these intervals from historical data, and generate the associated data change curves based on the time relationships associated with the associated data. Place the related data change curve and the characteristic trend segment in the same two-dimensional coordinate system, and translate the characteristic trend segment back and forth. Record the partial overlap between the characteristic trend segment and the related data change curve in several translation processes, and record the proportion of the partial overlap segment located in the characteristic trend segment. The proportion value = the length of the partial overlap segment bus ÷ the length of the characteristic trend segment bus. From the determined proportion values, select the maximum value, and record the translation process associated with the maximum value as the standard process. Record the partial curve associated with the standard process as the selected curve. This selected curve is located within the related data change curve. The relevant indicator parameters of the selected curve with respect to other health indicators are recorded as auxiliary parameters, and the corresponding auxiliary parameter change curves are generated based on the time relationship. The changing trends of different indicator parameters at adjacent time points are identified from the variation curves of the auxiliary parameters. The average value of the identified trends is then calculated and recorded as the curve characteristic TZ1 of the corresponding indicator parameter in the corresponding time period. i Then, extract the corresponding indicator parameters from the segment to be evaluated, simultaneously confirm the changing trend of the corresponding trend segment with respect to adjacent time points, and simultaneously perform mean processing, recording it as the trend characteristic TZ2 of the corresponding corresponding trend segment. i , where i represents different index parameters.
6. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 5, characterized in that, Also includes: Step 4: If all ratio characteristics meet the standards, the generated abnormal signals can be displayed directly. If one or more of the ratio characteristics fail to meet the standards, the cabin parameter characteristic debugging process will be executed, and abnormal signals of other health indicators will be generated and displayed simultaneously.
7. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 6, characterized in that, In step four, the evaluation process for proportional characteristics specifically includes: The indicator parameters associated with abnormal signals are denoted as characteristic indicators, and other indicator parameters are denoted as auxiliary indicators. The trend characteristics TZ2 are confirmed based on the corresponding auxiliary trend segments. i Confirm a set of floating ranges [TZ2] i -0.3TZ2 i TZ2 i +0.3TZ2 i If the curve characteristic TZ1 of the indicator parameter corresponding to the subordinate trend segment i All satisfy: TZ1 i ∈[TZ2 i -0.3TZ2 i TZ2 i +0.3TZ2 i If the abnormal signal of this characteristic indicator is displayed, then the abnormal signal of this characteristic indicator will be displayed directly; otherwise, the cabin parameter characteristic debugging process will be executed. Identify the curve features TZ1 associated with the auxiliary indicators. i And the associated floating range, if TZ1 i If the value is less than the floating range, the associated debugging parameters will be locked directly, and the corresponding debugging parameters will be adjusted upwards. At the same time, an abnormal signal for this auxiliary indicator will be generated and displayed.
8. The method for monitoring the health status of personnel in the evacuation cabin based on the Internet of Things according to claim 7, characterized in that, If TZ1 i If the range is floating, the associated debugging parameters will be locked directly, and the corresponding debugging parameters will be adjusted downwards. At the same time, an abnormal signal for this auxiliary indicator will be generated and displayed.