Student field safety early warning method based on environment and physiological information
By monitoring environmental and physiological information in real time during students' field activities and combining this with machine learning algorithms to generate early warning information, the problem of insufficient monitoring in existing technologies has been solved, enabling early detection and timely warning of altitude sickness.
Patent Information
- Application Number
- CN202511691328.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-18
- Publication Date
- 2026-04-17
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing technologies lack real-time and comprehensive monitoring of the environment and physiological state during students' outdoor activities, making it impossible to detect potential safety hazards and health abnormalities in a timely manner. Furthermore, the lack of a scientific early warning mechanism leads to delays in rescue opportunities.
A safety early warning system based on environmental and physiological information is adopted. Sensors collect plateau environmental parameters in real time and wearable devices monitor students' physiological parameters. Combined with data processing and analysis modules and machine learning algorithms, early warning information is generated and transmitted, and different risk thresholds are set to trigger early warnings.
It enables early detection and timely warning of altitude sickness in students, accurately assesses health risk levels, generates rich warning information, and facilitates the implementation of rapid response measures.
Smart Images
Figure CN121867716A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of outdoor safety monitoring and early warning technology, and in particular to a student outdoor safety early warning method based on environmental and physiological information. Background Technology
[0002] When students participate in outdoor activities, especially in special environments such as high altitudes, their safety and health face many potential risks. High-altitude environments are characterized by low oxygen, low temperature, low air pressure, and strong ultraviolet radiation. These factors can easily lead to altitude sickness, with symptoms such as headache, dizziness, difficulty breathing, and fatigue. In severe cases, it can even cause life-threatening diseases such as high-altitude pulmonary edema and high-altitude cerebral edema.
[0003] However, traditional methods for ensuring safety during student outdoor activities have significant shortcomings. On the one hand, there is a lack of real-time and comprehensive monitoring of the environment and students' physiological states, making it impossible to promptly detect potential safety hazards and abnormal student health conditions. On the other hand, even when monitoring equipment is available, it often operates independently, failing to effectively integrate and analyze environmental and physiological data, making it difficult to accurately assess the degree of health risk to students. Furthermore, there is a lack of a scientific and efficient system mechanism for generating and transmitting early warning information and managing personnel, resulting in the inability to promptly issue accurate and effective early warning information to relevant personnel in the face of emergencies, thus delaying rescue opportunities.
[0004] With the continuous development of IoT, sensor, wireless communication, and artificial intelligence technologies, strong technical support has been provided for student outdoor safety early warning. Based on this, this invention proposes a student outdoor safety early warning method based on environmental and physiological information. Summary of the Invention
[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a student outdoor safety early warning method based on environmental and physiological information.
[0006] To achieve the above objectives, the present invention adopts the following technical solution:
[0007] A student outdoor safety early warning method based on environmental and physiological information, implemented using a safety early warning system, which includes:
[0008] The environmental data acquisition module collects key environmental parameters in the plateau environment in real time through sensors; and transmits the collected data to the data processing center wirelessly.
[0009] The physiological data acquisition module, based on wearable devices, monitors students' physiological parameters in real time; the data is transmitted wirelessly to the data processing center.
[0010] The data processing and analysis module receives data from the environmental and physiological data acquisition modules and performs data cleaning, preprocessing, and feature extraction.
[0011] The early warning information generation module generates corresponding early warning information based on the health risk assessment results obtained from the data processing and analysis module. Different risk thresholds are set, and different levels of early warnings are triggered when the health risk level exceeds the corresponding threshold.
[0012] The information transmission module sends early warning information to the terminal devices of teachers and management platforms in a timely manner via wireless network. At the same time, the management platform records and analyzes the early warning information.
[0013] The user management module categorizes and manages system users, including different roles such as students, teachers, and administrators, and sets corresponding permissions.
[0014] Preferably, the environmental data acquisition module includes:
[0015] The temperature sensing unit is equipped with a high-precision temperature sensor that collects the current ambient temperature data at set intervals.
[0016] The atmospheric pressure sensing unit uses an atmospheric pressure sensor to acquire atmospheric pressure data in real time and accurately reflect the changes in air pressure at different altitudes.
[0017] The oxygen concentration sensing unit, based on an oxygen concentration sensor, continuously monitors the oxygen content in the air;
[0018] Humidity sensing unit, which collects ambient humidity data based on a humidity sensor;
[0019] The environmental data acquisition module collects data and sends it to the data processing center via wireless transmission to form an environmental data set.
[0020] Preferably, the physiological data acquisition module includes:
[0021] The heart rate monitoring unit, a wristband or chest strap device using photoplethysmography technology, collects the student's heart rate data every set number of seconds to capture heart rate changes.
[0022] The blood oxygen saturation monitoring unit uses a wearable blood oxygen saturation sensor to monitor students' blood oxygen saturation.
[0023] The body temperature monitoring unit uses a contact body temperature sensor to measure the student's body temperature every set minutes to determine whether the student has a fever.
[0024] The step count and activity level monitoring unit records students' step count and activity level through a built-in accelerometer to assess their physical exertion.
[0025] The physiological data acquisition module transmits the collected data wirelessly to the data processing center to form a set of student physiological data.
[0026] Preferably, the data processing and analysis module calculates the rate of change of temperature and atmospheric pressure over a period of time for environmental data; calculates the average heart rate and standard deviation of blood oxygen saturation for physiological parameter data; and establishes a health risk assessment model to calculate the student's health risk level in the environment based on environmental and physiological parameters.
[0027] Preferably, the data processing and analysis module includes:
[0028] The data processing unit cleans the received environmental and physiological data, removing outliers and noise interference; and performs data standardization.
[0029] The feature extraction unit extracts feature indicators from the cleaned data;
[0030] The model building unit uses machine learning or deep learning algorithms to construct a health risk assessment model. The extracted feature indicators are used as input variables, and the model is trained and optimized using training set data so that it can accurately predict the health risk level of students based on environmental and physiological parameters. The health risk level output by the model is divided into four levels: no risk, low risk, medium risk, and high risk.
[0031] Preferably, the data processing and analysis module constructs a health risk assessment model based on the stochastic sensible algorithm, as follows:
[0032] During training, multiple subsets are randomly selected from the original dataset, and each subset is used to construct a decision tree. At the same time, when constructing each decision tree, some features are randomly selected for splitting operations.
[0033] Let the training dataset be: ,in, It is the input vector. It is the corresponding target variable;
[0034] The random forest model is represented as: Where M is the number of decision trees; Indicates the first The output of each decision tree; The final prediction result is obtained through voting or averaging, and the prediction result is the predicted value of the student's health risk level.
[0035] Preferably, the early warning information generation module includes:
[0036] The risk level judgment unit determines the student's current health risk level based on the output of the health risk assessment model. When the risk level reaches the preset warning threshold, the warning mechanism is triggered.
[0037] The early warning information generation unit generates early warning information based on the risk level and relevant data. The early warning information includes the student's unique identifier, location coordinates, current environmental parameter information, abnormal physiological parameters, health risk level, and targeted recommended measures.
[0038] The early warning information conversion unit converts the generated early warning information into different formats to adapt to the requirements of different notification channels and terminal devices.
[0039] Preferably, the information transmission module includes:
[0040] The network communication unit adopts one or more communication methods, such as 4G / 5G, WiFi, and satellite communication, to achieve stable data transmission;
[0041] The teacher-side notification unit sends warning information to designated teachers in real time via a terminal APP or SMS platform;
[0042] The management platform notification unit sends early warning information to the management platform, whose terminal device is a computer or server; the management platform is used for centralized management and processing of early warning information.
[0043] Preferably, the user management module includes:
[0044] The user login unit is used for user registration and login.
[0045] The permission allocation unit assigns different operation permissions according to the user's role; specifically, students have the right to view their own physiological data and early warning information; teachers have the right to view relevant information and perform management operations for the students under their care; administrators have the highest system privileges to perform system configuration and data maintenance.
[0046] The permission verification unit verifies the permissions for each user's operation request. Only when the user has the corresponding permissions can they access the corresponding resources or perform the corresponding operations.
[0047] Preferably, the data processing and analysis module constructs a health risk assessment model based on the support vector machine algorithm, as follows:
[0048] For linearly separable data, the optimal hyperplane is found by solving a quadratic programming problem to separate the different categories of data as much as possible; for non-linearly separable data, the data is mapped to a high-dimensional space based on a kernel function to make it linearly separable before further processing.
[0049] Assume we have a training sample set ,in, These represent different health risk levels; the equation of the target hyperplane is... ,in It is the normal vector, which determines the direction of the hyperplane; The intercept term determines the specific location of the hyperplane; the optimization objective is to maximize the margin. , equivalent to minimizing The constraints are The optimal solution is obtained by solving the constrained optimization problem using the Lagrange multiplier method. and The parameter values are then used to determine the classification decision function. When faced with new input data When the value is substituted into the function, its corresponding health risk level category is predicted.
[0050] The beneficial effects of this invention are as follows:
[0051] 1. This invention is specifically optimized for the unique characteristics of the plateau environment, effectively addressing the unique safety risks of plateau regions. By monitoring key parameters such as blood oxygen saturation, atmospheric pressure, and oxygen concentration, the system can detect students' altitude sickness symptoms early, providing valuable time for timely intervention. It has significant safety assurance value for schools conducting field teaching activities in plateau regions.
[0052] 2. This invention uses machine learning or deep learning algorithms to construct a health risk assessment model, which can clean, preprocess, and extract features from the collected data, and accurately calculate various feature indicators, thereby accurately predicting the health risk level of students.
[0053] 3. Based on the health risk assessment results, this invention can set different risk thresholds to trigger corresponding levels of early warning, and the generated early warning information is rich in content, including student identity, location, health status and suggested measures, which facilitates rapid response. Attached Figure Description
[0054] Figure 1 This is a framework diagram of a student outdoor safety early warning system based on environmental and physiological information proposed in this invention. Detailed Implementation
[0055] The technical solution of the present invention will be further described in detail below with reference to specific embodiments.
[0056] Example 1:
[0057] A student outdoor safety early warning method based on environmental and physiological information, implemented using a safety early warning system, which includes:
[0058] The environmental data acquisition module collects key environmental parameters in the plateau environment in real time through sensors; and transmits the collected data to the data processing center wirelessly.
[0059] The physiological data acquisition module, based on wearable devices, monitors students' physiological parameters in real time; the data is transmitted wirelessly to the data processing center.
[0060] The data processing and analysis module receives data from the environmental and physiological data acquisition modules, cleans, preprocesses, and extracts features from the data; for environmental data, it calculates characteristic indicators such as the rate of temperature change and the rate of atmospheric pressure change over a period of time; for physiological parameter data, it calculates the average heart rate and the standard deviation of blood oxygen saturation; and it establishes a health risk assessment model to calculate the student's health risk level in the environment based on environmental and physiological parameters.
[0061] The early warning information generation module generates corresponding early warning information based on the health risk assessment results obtained from the data processing and analysis module. Different risk thresholds are set, and different levels of early warnings are triggered when the health risk level exceeds the corresponding threshold.
[0062] The information transmission module sends early warning information to the terminal devices of teachers and management platforms in a timely manner via wireless network. At the same time, the management platform records and analyzes the early warning information.
[0063] The user management module categorizes and manages system users, including different roles such as students, teachers, and administrators, and sets corresponding permissions.
[0064] The environmental data acquisition module includes:
[0065] The temperature sensing unit is equipped with a high-precision temperature sensor that collects the current ambient temperature data at set intervals.
[0066] The atmospheric pressure sensing unit uses an atmospheric pressure sensor to acquire atmospheric pressure data in real time and accurately reflect the changes in air pressure at different altitudes.
[0067] The oxygen concentration sensing unit, based on an oxygen concentration sensor, continuously monitors the oxygen content in the air;
[0068] Humidity sensing unit, which collects ambient humidity data based on a humidity sensor;
[0069] The environmental data acquisition module collects data and sends it to the data processing center via wireless transmission to form an environmental data set.
[0070] The physiological data acquisition module includes:
[0071] The heart rate monitoring unit, a wristband or chest strap device using photoplethysmography technology, collects the student's heart rate data every set number of seconds to capture heart rate changes.
[0072] The blood oxygen saturation monitoring unit uses a wearable blood oxygen saturation sensor to monitor students' blood oxygen saturation.
[0073] The body temperature monitoring unit uses a contact body temperature sensor to measure the student's body temperature every set minutes to determine whether the student has a fever.
[0074] The step count and activity level monitoring unit records students' step count and activity level through a built-in accelerometer to assess their physical exertion.
[0075] The physiological data acquisition module transmits the collected data wirelessly to the data processing center to form a set of student physiological data.
[0076] The data processing and analysis module includes:
[0077] The data processing unit cleans the received environmental and physiological data, removing outliers and noise interference; and performs data standardization.
[0078] The feature extraction unit extracts feature indicators from the cleaned data. For environmental data, it calculates the rate of change of temperature, the rate of change of atmospheric pressure, and the fluctuation range of oxygen concentration over a certain period of time. For physiological data, it calculates the average heart rate, the standard deviation of blood oxygen saturation, and the mean body temperature.
[0079] The model building unit uses machine learning or deep learning algorithms to construct a health risk assessment model. The extracted feature indicators are used as input variables, and the model is trained and optimized using training set data so that it can accurately predict the health risk level of students based on environmental and physiological parameters. The health risk level output by the model is divided into four levels: no risk, low risk, medium risk, and high risk.
[0080] The data processing and analysis module constructs a health risk assessment model based on the stochastic sensible algorithm, as detailed below:
[0081] During training, multiple subsets are randomly selected from the original dataset, and each subset is used to construct a decision tree. At the same time, when constructing each decision tree, some features are randomly selected for splitting operations.
[0082] Let the training dataset be: ,in, It is an input vector (containing environmental and physiological parameter features). The corresponding target variable is (student's health risk level).
[0083] The random forest model is represented as: Where M is the number of decision trees; Indicates the first The output of each decision tree; The final prediction result is obtained through voting or averaging, and the prediction result is the predicted value of the student's health risk level.
[0084] The early warning information generation module includes:
[0085] The risk level judgment unit determines the student's current health risk level based on the output of the health risk assessment model. When the risk level reaches the preset warning threshold, the warning mechanism is triggered. For example, a level 1 warning corresponds to high risk, a level 2 warning corresponds to medium risk, and so on. The warning information includes the student's identity information, location, current health status assessment, and recommended measures.
[0086] The early warning information generation unit generates early warning information based on the risk level and relevant data. The early warning information includes the student's unique identifier, location coordinates, current environmental parameter information, abnormal physiological parameters (such as high heart rate, low blood oxygen saturation, etc.), health risk level, and targeted recommended measures (such as resting immediately, supplementing oxygen, contacting medical staff, etc.).
[0087] The early warning information conversion unit converts the generated early warning information into different formats to adapt to the requirements of different notification channels and terminal devices; for example, it converts the information into JSON format for APP notifications and HTML format for web page display.
[0088] The information transmission module includes:
[0089] The network communication unit adopts one or more communication methods, such as 4G / 5G, WiFi, and satellite communication, to achieve stable data transmission;
[0090] The teacher-side notification unit sends warning information to designated teachers in real time via a terminal APP or SMS platform;
[0091] The management platform notification unit sends the early warning information to the management platform, whose terminal device is a computer or server. The management platform is used to centrally manage and process the early warning information, such as recording the early warning time, location, and processing results.
[0092] The user management module includes:
[0093] The user login unit is used for user registration and login.
[0094] The permission allocation unit assigns different operation permissions according to the user's role; specifically, students have the right to view their own physiological data and early warning information; teachers have the right to view relevant information and perform management operations for the students under their care; administrators have the highest system privileges to perform system configuration and data maintenance.
[0095] The permission verification unit verifies the permissions for each user's operation request. Only when the user has the corresponding permissions can they access the corresponding resources or perform the corresponding operations.
[0096] Example 2:
[0097] A student outdoor safety early warning method based on environmental and physiological information is proposed in this embodiment. Building upon Embodiment 1, the data processing and analysis module constructs a health risk assessment model based on the support vector machine algorithm, as detailed below:
[0098] For linearly separable data, the optimal hyperplane is found by solving a quadratic programming problem to separate the different categories of data as much as possible; for non-linearly separable data, the data is mapped to a high-dimensional space based on a kernel function to make it linearly separable before further processing.
[0099] Assume we have a training sample set ,in, These represent different health risk levels; the equation of the target hyperplane is... ,in It is the normal vector, which determines the direction of the hyperplane; The intercept term determines the specific location of the hyperplane; the optimization objective is to maximize the margin. , equivalent to minimizing The constraints are The optimal solution is obtained by solving the constrained optimization problem using the Lagrange multiplier method. and The parameter values are then used to determine the classification decision function. When faced with new input data When the value is substituted into the function, its corresponding health risk level category is predicted.
[0100] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.
Claims
1. A student outdoor safety early warning method based on environmental and physiological information, characterized in that, This is based on a security early warning system, which includes: The environmental data acquisition module collects key environmental parameters in the plateau environment in real time through sensors; and transmits the collected data to the data processing center wirelessly. The physiological data acquisition module, based on wearable devices, monitors students' physiological parameters in real time; the data is transmitted wirelessly to the data processing center. The data processing and analysis module receives data from the environmental and physiological data acquisition modules and performs data cleaning, preprocessing, and feature extraction. The early warning information generation module generates corresponding early warning information based on the health risk assessment results obtained from the data processing and analysis module. Different risk thresholds are set, and different levels of early warnings are triggered when the health risk level exceeds the corresponding threshold. The information transmission module sends early warning information to the terminal devices of teachers and management platforms in a timely manner via wireless network. At the same time, the management platform records and analyzes the early warning information. The user management module categorizes and manages system users, including different roles such as students, teachers, and administrators, and sets corresponding permissions.
2. The student outdoor safety early warning method based on environmental and physiological information according to claim 1, characterized in that, The environmental data acquisition module includes: The temperature sensing unit is equipped with a high-precision temperature sensor that collects the current ambient temperature data at set intervals. The atmospheric pressure sensing unit uses an atmospheric pressure sensor to acquire atmospheric pressure data in real time and accurately reflect the changes in air pressure at different altitudes. The oxygen concentration sensing unit, based on an oxygen concentration sensor, continuously monitors the oxygen content in the air; Humidity sensing unit, which collects ambient humidity data based on a humidity sensor; The environmental data acquisition module collects data and sends it to the data processing center via wireless transmission to form an environmental data set.
3. The student outdoor safety early warning method based on environmental and physiological information according to claim 1, characterized in that, The physiological data acquisition module includes: The heart rate monitoring unit, a wristband or chest strap device using photoplethysmography technology, collects the student's heart rate data every set number of seconds to capture heart rate changes. The blood oxygen saturation monitoring unit uses a wearable blood oxygen saturation sensor to monitor students' blood oxygen saturation. The body temperature monitoring unit uses a contact body temperature sensor to measure the student's body temperature every set minutes to determine whether the student has a fever. The step count and activity level monitoring unit records students' step count and activity level through a built-in accelerometer to assess their physical exertion. The physiological data acquisition module transmits the collected data wirelessly to the data processing center to form a set of student physiological data.
4. The student outdoor safety early warning method based on environmental and physiological information according to claim 1, characterized in that, The data processing and analysis module calculates the rate of change of temperature and atmospheric pressure over a period of time for environmental data; it calculates the average heart rate and standard deviation of blood oxygen saturation for physiological parameter data; and it establishes a health risk assessment model to calculate the student's health risk level in the environment based on environmental and physiological parameters.
5. A student outdoor safety early warning method based on environmental and physiological information according to claim 4, characterized in that, The data processing and analysis module includes: The data processing unit cleans the received environmental and physiological data, removing outliers and noise interference; and performs data standardization. The feature extraction unit extracts feature indicators from the cleaned data; The model building unit uses machine learning or deep learning algorithms to construct a health risk assessment model. The extracted feature indicators are used as input variables, and the model is trained and optimized using training set data so that it can accurately predict the health risk level of students based on environmental and physiological parameters. The health risk level output by the model is divided into four levels: no risk, low risk, medium risk, and high risk.
6. A student outdoor safety early warning method based on environmental and physiological information according to claim 5, characterized in that, The data processing and analysis module constructs a health risk assessment model based on the stochastic Senli algorithm, as detailed below: During training, multiple subsets are randomly selected from the original dataset, and each subset is used to construct a decision tree. At the same time, when constructing each decision tree, some features are randomly selected for splitting operations. Let the training dataset be: ,in, It is the input vector. It is the corresponding target variable; The random forest model is represented as: Where M is the number of decision trees; Indicates the first The output of each decision tree; The final prediction result is obtained through voting or averaging, and the prediction result is the predicted value of the student's health risk level.
7. A student outdoor safety early warning method based on environmental and physiological information according to claim 1, characterized in that, The early warning information generation module includes: The risk level judgment unit determines the student's current health risk level based on the output of the health risk assessment model. When the risk level reaches the preset warning threshold, the warning mechanism is triggered. The early warning information generation unit generates early warning information based on the risk level and relevant data. The early warning information includes the student's unique identifier, location coordinates, current environmental parameter information, abnormal physiological parameters, health risk level, and targeted recommended measures. The early warning information conversion unit converts the generated early warning information into different formats to adapt to the requirements of different notification channels and terminal devices.
8. A student outdoor safety early warning method based on environmental and physiological information according to claim 1, characterized in that, The information transmission module includes: The network communication unit adopts one or more communication methods, such as 4G / 5G, WiFi, and satellite communication, to achieve stable data transmission; The teacher-side notification unit sends warning information to designated teachers in real time via a terminal APP or SMS platform; The management platform notification unit sends early warning information to the management platform, whose terminal device is a computer or server; the management platform is used for centralized management and processing of early warning information.
9. A student outdoor safety early warning method based on environmental and physiological information according to claim 1, characterized in that, The user management module includes: The user login unit is used for user registration and login. The permission allocation unit assigns different operation permissions based on the user's role; specifically, students have the right to view their own physiological data and early warning information; teachers have the right to view relevant information and perform management operations for the students under their care; administrators have the highest system privileges to perform system configuration and data maintenance. The permission verification unit verifies the permissions for each user's operation request. Only when the user has the corresponding permissions can they access the corresponding resources or perform the corresponding operations.
10. A student outdoor safety early warning method based on environmental and physiological information according to claim 5, characterized in that, The data processing and analysis module constructs a health risk assessment model based on the support vector machine algorithm, as detailed below: For linearly separable data, the optimal hyperplane is found by solving a quadratic programming problem to separate the different categories of data as much as possible; for non-linearly separable data, the data is mapped to a high-dimensional space based on a kernel function to make it linearly separable before further processing. Assume we have a training sample set ,in, These represent different levels of health risk; The equation of the target hyperplane is: ,in It is the normal vector, which determines the direction of the hyperplane; The intercept term determines the specific location of the hyperplane; the optimization objective is to maximize the margin. , equivalent to minimizing The constraints are The optimal solution is obtained by solving the constrained optimization problem using the Lagrange multiplier method. and The parameter values are then used to determine the classification decision function. When faced with new input data When the value is substituted into the function, its corresponding health risk level category is predicted.