Firefighter safety warning communication method, system, and medium that fuse radio and physical signs

Abstract

This invention provides a firefighter safety early warning communication method, system, and medium that integrates breathing apparatus (BBA) and vital signs. The method includes: locally on the firefighter's terminal, real-time fusion of BBA operating parameters, physiological parameters, and motion parameters to generate comprehensive status data; based on this data and combined with group situational information obtained from the on-site communication network, using a local dynamic risk prediction model to calculate the comprehensive risk level in real time. This model simultaneously assesses individual resource reserves, physiological load, and relative risk to the group; generating structured early warning messages based on the risk level, and sending them to target nodes via an on-site self-organizing network according to an adaptive communication strategy bound to that level. This strategy dynamically adjusts the message sending frequency, range, and reliability. This invention achieves a leap from "isolated individual" monitoring to "group collaborative perception, local intelligent assessment, and adaptive scheduling of communication resources," improving the timeliness, accuracy, and efficiency of on-site communication.

Description

Technical Field

[0001] This invention belongs to the field of fire emergency rescue equipment and safety monitoring technology, and in particular relates to a firefighter safety early warning communication method, system and medium that integrates breathing apparatus and vital signs. Background Technology

[0002] When operating in complex and dangerous environments such as firefighting, petrochemical operations, and underground rescue, firefighters' safety is highly dependent on the operational status of their self-contained breathing apparatus (SCBA) and their own physiological endurance. Current technology primarily relies on sensors on firefighters' individual equipment to wirelessly transmit data such as SCBA residual pressure and heart rate back to the command center for centralized monitoring and manual assessment. However, this approach has significant shortcomings. The wireless communication environment at hazardous sites is complex and variable, with signals easily blocked, interfered with, or delayed, resulting in the inability to transmit critical data in real time. This makes it difficult for the command center to detect emergencies promptly. Furthermore, existing solutions often rely on single, fixed thresholds (such as cylinder pressure below a certain value) for alarms, leading to simplistic and rigid risk assessments, high false alarm and false negative rates, and the same transmission frequency and power regardless of the urgency of the data. In disaster sites with limited communication resources, a large amount of low-value data occupies the channel, potentially preventing timely transmission of critical alarms at truly high-risk nodes. Summary of the Invention

[0003] In view of this, the present invention aims to overcome the defects in the prior art and proposes a firefighter safety early warning communication method, system and medium that integrates breathing apparatus and vital signs to solve the problems of early warning delay, inaccurate assessment and low communication efficiency.

[0004] To achieve the above objectives, the technical solution created by this invention is implemented as follows: A firefighter safety early warning communication method that integrates breathing apparatus data and vital signs includes the following steps: S1. Real-time collection of individual firefighters' air respirator operating parameters, physiological state parameters, and movement posture parameters. The collected parameters are then spatiotemporally aligned and fused at the firefighter's terminal to generate comprehensive status data including derived safety indicators. Spatiotemporal alignment establishes a common platform for all data to communicate. Then, through multi-level data fusion processing, information directly guiding safety early warning, such as "residual air time," "physiological load," "resting state," and ultimately, "comprehensive risk level," is extracted from this aligned data. The spatiotemporal alignment and data fusion processing steps are as follows: When collecting each parameter sample, the sample is timestamped using the unified clock of the firefighter's terminal, and each parameter is cached into the corresponding first-in-first-out queue according to its respective sampling rate. With a preset fusion cycle To trigger, that is, at a preset fusion cycle. Using time as a reference, the data alignment and fusion calculation process is triggered periodically (e.g., once per second) to ensure that data from different sensors are processed at the same time. For each parameter queue, the most recent valid sample is retrieved; for high-frequency parameters, the fusion period is used. The mean or variance of the in-sample is used as the representative value for that period. For the multi-axis acceleration and angular velocity data in the motion posture parameters, according to the preset installation position and angle of each sensor on the firefighter's body, the data are transformed into the same body coordinate system centered on the firefighter's torso using a rotation matrix. The derived security index is calculated; S2. Based on the comprehensive status data generated in step S1, combined with the preset individual behavior baseline library and the group situation information obtained from the on-site communication network, a comprehensive risk level is calculated in real time on the firefighter terminal using a dynamic risk prediction model. The dynamic risk prediction model simultaneously considers the sustainability of life support resources, the real-time deviation of individual physiological state, abnormal movement behavior and the risk difference with surrounding teammates. S3. Based on the comprehensive risk level obtained in step S2, automatically generate a structured early warning message containing the risk level identifier, key risk data snapshot, personnel identity, and timestamp; the firefighter terminal exchanges the structured early warning message with neighboring teammates' terminals through the on-site communication network; if its own risk level is determined to be significantly higher than the average level of its surrounding teammates, a cross-validation alarm is activated; if its own risk level is significantly lower than the average level and does not match its own historical status, a sensor self-check procedure is triggered. S4. Based on the communication strategy dynamically associated with the comprehensive risk level, the structured early warning message generated in step S3 is sent to the command node and associated nodes through the field communication network. The communication strategy dynamically adjusts the message sending cycle, target node range, and transmission reliability guarantee mechanism at least according to the comprehensive risk level.

[0005] Furthermore, in step S1, the data fusion processing generates the derived security index by performing the following computational processes in parallel: a. Based on the spatiotemporally aligned cylinder pressure value P and real-time gas flow rate Q, combined with the preset critical pressure And the conversion coefficient k, through the formula Continuous calculation of residual gas usage time , Characterizes the remaining effective operating time of the air respirator at the current consumption rate; b. Heart rate (HR) and body surface temperature values ​​based on spatiotemporal alignment and preset individual resting heart rate Combined with ambient temperature Through weighted fusion formula The physiological load index L was calculated, which quantifies the firefighter's real-time comprehensive physiological stress level. In this index, α is the heart rate load weighting coefficient and β is the body temperature regulation load weighting coefficient. c. Based on the spatiotemporally aligned multi-axis acceleration and angular velocity data, calculate the attitude angular change rate and the composite acceleration amplitude; when within a continuous time window... Within, the rate of change of attitude angle was detected to be consistently below the threshold. Furthermore, if the magnitude of the composite acceleration remains within the range of [0.9g, 1.1g], the firefighter is determined to be in a stationary state and a stationary state indicator S=1 is generated; otherwise, S=0. The results obtained through parallel calculations of processes a, b, and c are as follows. L and S together constitute the derived security index in the comprehensive status data.

[0006] Furthermore, in step S2, the operating logic of the dynamic risk prediction model includes: Based on the comprehensive status data L, S, through functions Calculate individual real-time risk score ; Based on the acquired group situation information, the average risk level of the group is obtained. and the aforementioned group risk dispersion ; Calculate the individual risk value With the average risk level of the group Standard score : When Z is greater than the preset threshold When the risk level is determined to be high, the Z-value and the risk dispersion are then considered together. The final comprehensive risk level R is output through the function R = G(Z, σ).

[0007] Furthermore, record the data related to the final risk level for each warning event. The time series data of L, S, and Z values ​​are analyzed offline to automatically correct the individual real-time risk score used to calculate the firefighter's score for the next mission. The individualized weighting coefficient or threshold of the overall risk level R.

[0008] Furthermore, in step S2, the preset individual behavior baseline library is obtained and maintained by performing the following steps: During routine training or low-risk emergency response missions, firefighters continuously collect their resting heart rate and body surface temperature, as well as their air intake and motion acceleration data during operational situations. The collected data are statistically analyzed to establish and store an individual behavioral baseline database for each firefighter. The individual behavioral baseline database includes at least: individual resting heart rate, individual baseline body surface temperature, individual average air intake under typical operational conditions, and feature vectors extracted from historical motion acceleration data to characterize typical motion intensity. In the comprehensive risk level calculation in step S2, the individual behavior baseline library is called as a personalized benchmark for assessing the deviation of an individual's physiological state and behavioral abnormalities. After each mission, based on the relevant data recorded during the mission, the individual behavior baseline database is smoothly corrected and updated using a weighted average algorithm, so that the individual behavior baseline database can adaptively evolve with the long-term changes in the physical condition of firefighters.

[0009] Furthermore, in step S2, the group situation information obtained from the field communication network is generated in real time through the following steps: S21. Through the on-site communication network, listen to and receive messages broadcast by other firefighter terminals within the communication radius at preset intervals, and parse the individual real-time risk scores of other teammates from the messages. Based on the overall risk level R, and cached locally; S22, Based on the cached data from step S51, including the current risk score of this terminal itself and all teammates. A set of values, performing the following calculations in real time: a. Calculate the arithmetic mean of the set to obtain the group average risk level, which characterizes the overall risk level of the group. ; b. Calculate the standard deviation of the set to obtain the group risk dispersion σ, which characterizes the degree of risk difference within the group; S23. The direct shared information obtained in step S21 and the derivative potential index calculated in step S22 are used together as the group situation information and provided to the dynamic risk prediction model in step S2.

[0010] Furthermore, in step S3, the structured warning message is generated, which is specifically achieved through the following encapsulation steps: S31. Obtain the comprehensive risk level R determined by step S2, and the key risk-causing data that triggers the level R. The key risk-causing data includes at least: residual gas usage time Tr, physiological load index L, resting state indicator S, and individual and group risk deviation Z-score values. S32. The data prepared in step S31, along with the firefighter's unique ID and current timestamp, are encoded and assembled according to a predefined communication protocol format to generate a structured data packet, wherein: a. Set a message header at the beginning of the data packet to identify the protocol version, total data packet length, and message type; b. After the message header, sequentially encapsulate the identity ID, the timestamp, the numerical code of the comprehensive risk level R, and a snapshot field containing the key risk data; c. Append a cyclic redundancy check code calculated based on the content of the data packet to the end of the data packet; S33. Message output step: The structured data packet generated in step S32 that conforms to the protocol format is output as the structured early warning message for network transmission in step S4.

[0011] Furthermore, the transmission based on the communication strategy described in step S4 specifically includes performing the following control steps according to the current comprehensive risk level R: S41. Communication parameter decision-making step: Query the predefined control rules dynamically associated with the comprehensive risk level R, and decide on the current communication parameter combination to be used. The communication parameter combination includes at least: Sending period parameters Its value satisfies the following: the higher the risk level, the shorter the transmission cycle, that is... , , and ; The target node range parameter has the following value rules: when R=1, it is defined as broadcast to the entire network; when R=2, it is defined as multicast to the command node and one-hop neighbor nodes in the network topology; when R=3, it is defined as unicast only to the command node. The transmission guarantee mechanism activation flag has the following rules: when R=1, the flag indicates that the enhanced guarantee mechanism is enabled; when R=2 or R=3, the flag indicates that the basic guarantee mechanism or the partial guarantee mechanism is enabled. S42. Communication behavior execution steps: Based on the communication parameter combination determined in step S41, control the wireless communication module to send the structured early warning message, wherein: According to the aforementioned transmission period parameters Timed trigger for sending; Set the destination address or address mode of the data packet according to the target node range parameters; When the transmission guarantee mechanism enable flag indicates that the enhanced guarantee mechanism is enabled, at least one of the following operations is performed simultaneously: increasing the radio frequency transmission power, enabling reception acknowledgment and automatic retransmission for messages to be sent, and selecting or enabling multi-hop relay paths in the routing table.

[0012] A system for implementing the above method includes: The firefighter terminal is used to perform the data processing and transmission actions in steps S1, S2, S3 and S4. The field command terminal is used to receive, parse, and display early warning messages from the field communication network; The on-site communication network, constructed by the firefighter terminal and the on-site command terminal, is used to perform message routing and transmission in step S4.

[0013] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, performs the steps of the method described above.

[0014] Compared with existing technologies, the present invention has the following advantages: Through local multi-source sensing and fusion, multi-dimensional data such as breathing apparatus, physiological data, and motion data are integrated at the firefighter terminal, building a comprehensive data foundation for accurate assessment and upgrading from single-parameter monitoring to comprehensive status perception. Based on this comprehensive data and creatively introducing group situational information obtained from the on-site network, dynamic risk collaborative assessment is performed locally. This not only overcomes the latency problem of relying on remote transmission, but more importantly, the assessment model can keenly identify relative risk deviations by comparing individual safety indicators with the real-time risk level of teammates, thus adding early warning capabilities based on group anomalies in addition to absolute threshold alarms, greatly improving the contextualization and accuracy of risk assessment. On this basis, the comprehensive risk level output by the assessment is strongly coupled with subsequent communication behavior, and an adaptive communication strategy bound to the risk level is designed. This strategy dynamically and differentially adjusts the sending frequency, transmission range, and reliability guarantee mechanism of warning messages according to the level of risk, so that high-risk emergency alarms can be rapidly disseminated with the highest priority and the most reliable method, while low-risk status reports reduce communication overhead, thereby realizing the intelligent on-demand allocation of valuable on-site wireless communication resources. Therefore, this solution organically integrates the three links of "edge intelligent perception", "group collaborative assessment" and "communication adaptive scheduling" into a closed loop, realizing a fundamental transformation from passive, lagging and rigid centralized monitoring to proactive, real-time and efficient distributed intelligent early warning and communication. Attached Figure Description

[0015] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This invention provides a flowchart of a firefighter safety early warning communication method that integrates breathing apparatus and vital signs. Figure 2 A schematic diagram of the structure of a firefighter safety early warning communication system that integrates breathing apparatus and vital signs for this invention; Figure 3 This invention provides a structural schematic diagram of a firefighter safety early warning communication terminal that integrates breathing apparatus and vital signs. Detailed Implementation

[0016] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0017] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0018] The terms and descriptions used in the description of this invention are as follows: Operating parameters of breathing apparatus (BBA): These refer to the data generated when the positive pressure breathing apparatus worn by firefighters is in operation. These parameters include at least cylinder pressure, gas flow rate, and air supply valve status, and are used to calculate key safety indicators such as remaining usable time.

[0019] Physiological parameters: These refer to vital signs data of firefighters monitored through wearable devices, such as heart rate, body temperature, and blood oxygen saturation, which are used to reflect the physiological load and fatigue state of personnel.

[0020] Motion posture parameters: These refer to data collected by sensors such as inertial measurement units, including acceleration, angular velocity, and Euler angles, which are used to identify a person's motion state (such as running, walking, standing still, falling, etc.).

[0021] Comprehensive status data: refers to the data set generated after spatiotemporal alignment, filtering, calculation, and other fusion processing of the above-mentioned raw data from multiple sources such as breathing apparatus, physiological data, and exercise data. This data includes derived safety indicators (such as estimated usable time and physiological load index). Estimated usable time refers to the estimated duration of use that the remaining air can support based on the current cylinder pressure, real-time gas consumption flow rate, and preset alarm threshold pressure. It is a key indicator for assessing respiratory safety.

[0022] Physiological stress index: a quantitative index calculated by combining physiological parameters such as heart rate and body temperature, used to characterize the physiological stress and fatigue of firefighters under current environment and task.

[0023] Group situational awareness refers to information reflecting the overall safety status obtained from other firefighter terminals or nodes within the on-site ad hoc network communication range. Its core is the real-time risk assessment results or raw status data of other teammates, which can be used to calculate the group's average risk level, risk distribution dispersion, etc.

[0024] Dynamic Risk Prediction Model: An algorithmic model deployed locally on the firefighter's terminal. It takes individual comprehensive status data and group situation information as input, and calculates and outputs a quantitative comprehensive risk level in real time through preset or self-learning rules and functions. Its core feature is "dynamic," capable of updating in real time as individual status and group situation change.

[0025] Overall risk level: The classification result output by the dynamic risk prediction model is usually divided into low, medium and high limited levels, which are used to characterize the overall degree of danger currently faced by firefighters.

[0026] Adaptive communication strategy: A set of communication control rules that corresponds one-to-one with the overall risk level. It defines parameters such as message sending period, target node range (e.g., unicast, multicast, broadcast), transmission power, retransmission mechanism, and whether reception acknowledgment is required under different risk levels, aiming to match communication behavior with the urgency of the event.

[0027] Field communication network: refers to a wireless multi-hop network dynamically constructed on-site by nodes such as firefighter terminals and command terminals, such as low-power mesh networks. Its characteristics include no need for fixed infrastructure, nodes can relay to each other, and the network has self-organizing and self-healing capabilities.

[0028] Structured alert messages: A data packet encapsulated according to a predetermined format, containing at least: a risk level identifier, a snapshot of key data that triggered the alert (such as remaining time and heart rate), a unique personnel identifier, and a timestamp, facilitating quick parsing and display by the recipient. It should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0029] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0030] A firefighter safety early warning communication method that integrates breathing apparatus data and vital signs, such as Figure 1 As shown, it includes the following steps: S1. Real-time collection of individual firefighters' air respirator operating parameters, physiological state parameters, and movement posture parameters on the firefighter terminal; spatiotemporal alignment and data fusion processing of the collected parameters to generate comprehensive status data including derived safety indicators; wherein, the spatiotemporal alignment and data fusion processing steps are as follows: When collecting each parameter sample, the sample is timestamped using the unified clock of the firefighter's terminal, and each parameter is cached into the corresponding first-in-first-out queue according to its respective sampling rate. Triggered by a preset fusion period, for each parameter queue, the most recent valid sample is retrieved; for high-frequency parameters, the mean or variance of the samples within that fusion period is taken as the representative value for that period. For the multi-axis acceleration and angular velocity data in the motion posture parameters, according to the preset installation position and angle of each sensor on the firefighter's body, the data are transformed into the same body coordinate system centered on the firefighter's torso using a rotation matrix. The derived security index is calculated; S2. Based on the comprehensive status data, combined with the preset individual behavior baseline library and the group situation information obtained from the on-site communication network, a comprehensive risk level is calculated in real time on the firefighter terminal using a dynamic risk prediction model. S3. Based on the comprehensive risk level, automatically generate a structured early warning message containing the risk level identifier, key risk data snapshot, personnel identity, and timestamp; the firefighter terminal exchanges the structured early warning message with the firefighter terminals of neighboring teammates through the on-site communication network; if its own comprehensive risk level is determined to be higher than the average level of the surrounding teammates, a cross-validation alarm is activated; if its own comprehensive risk level is lower than the average level of the surrounding teammates, a sensor self-check procedure is triggered. S4. Based on the communication strategy dynamically associated with the comprehensive risk level, the structured early warning message generated in step S3 is sent to the command node and associated nodes through the field communication network.

[0031] The "cross-validation alarm" in this invention is not a simple "alarm," but a multi-layered verification, alerting, and handling process. Its implementation is based on data sharing within the field communication network, aiming to intelligently identify and respond to potential false alarms (high risk) or missed alarms (low risk / equipment failure) generated by individual terminals through group status comparison. Specifically, it includes: 1. Triggering and Judgment After completing its own risk assessment, the firefighter terminal periodically exchanges the overall risk level R and key hazard data snapshots (including at least the individual risk score) with neighboring teammates' terminals within its communication range via the on-site communication network. and (Value). The terminal uses the received information to calculate the average risk level and average risk score of nearby teammates in real time.

[0032] The triggering criteria are as follows: High-risk cross-validation alarm trigger condition: When its own risk level R is high risk (e.g., R=1) and its own When the value is greater than the preset high threshold (e.g., Z>2.5), it indicates that the status of the product is significantly worse than the overall level of the surrounding team, triggering a high-risk cross-validation process.

[0033] Low-risk anomaly / sensor malfunction alarm trigger condition: When its own risk level R is low risk (e.g., R=3) but its own... When the value is less than the preset low threshold (e.g., Z < -2.0) and this low-risk state is significantly inconsistent with its recent (e.g., the previous 5 minutes) historical average state, the low-risk anomaly verification process is triggered.

[0034] 2. Response and Execution The system executes differentiated responses based on different triggering conditions: (1) High-risk cross-validation alarm response When an endpoint determines that its own condition is significantly worse than that of the team, it should perform the following actions to confirm the risk and escalate the alert: Local high-intensity alarm: Immediately activate a combination of sound, light, and vibration alarms that differ from conventional warnings (such as a rapid beeping sound at a specific frequency and a red flashing light) to alert the firefighter that "the situation is abnormal, please be careful".

[0035] Requesting manual confirmation: A brief confirmation request will pop up on the terminal interface (or a prompt tone will play on a terminal with voice functionality), giving the firefighter a brief window (e.g., 5 seconds) to manually confirm (e.g., by pressing a specific button). If confirmation is successful, it indicates that the firefighter is conscious but in a high-risk situation; if there is no response within the time limit, it strongly suggests that the firefighter may have lost the ability to act.

[0036] Generate and send an escalation warning message: Regardless of whether manual confirmation is received, the terminal will immediately generate a new structured warning message. This message will maintain the highest level (R=1) in its "Risk Level Core Field" and additionally encapsulate a "Cross-Validation Flag" and the team's average risk level as a reference in its "Key Risk Data Snapshot Field". Subsequently, the terminal will send this message using the highest priority communication strategy (i.e., the shortest cycle, maximum power, network-wide broadcast, and strong reliability guarantee corresponding to R=1).

[0037] (2) Low-risk anomaly / sensor failure alarm response When a terminal determines that its own status is abnormally better than the team's and inconsistent with historical data, it first suspects its own sensor system and executes the following self-check and notification process: Triggering sensor self-test procedure: The system calls the built-in diagnostic module to quickly verify the main sensors, including: Signal validity check: Determine whether the data from each sensor are within the physically possible range (e.g., heart rate between 40-200 bpm, body temperature between 30-45℃).

[0038] Signal continuity check: Check whether the data stream is continuous and whether there are any abnormalities such as remaining unchanged for a long time or suddenly jumping to zero.

[0039] Data logic consistency check: Compare the logical relationships between different sensor data (e.g., whether the heart rate increases accordingly when the IMU shows strenuous exercise; whether the pressure continues to decrease when the expiratory flow is greater than zero).

[0040] Local prompts and status reporting: The terminal provides a gentle prompt to the firefighter (such as a slow flashing yellow indicator light) and generates an equipment status message. This message includes the self-test results (such as "heart rate sensor signal abnormal") and is reported to the command terminal with normal priority, prompting the commander "the equipment data of this firefighter has low reliability, please pay attention."

[0041] 3. Coordinated response between the command center and teammates When the command terminal receives an upgrade warning message with a "cross-validation flag", it will issue a top-level warning on the monitoring interface (such as a pop-up window, special icon, or voice broadcast) and automatically associate and display the location and status comparison of the alarming team member with the surrounding team members, providing the commander with the key decision-making context of "the isolated deterioration of the team member's status".

[0042] Commanders can immediately verify this information via voice communication and instruct nearby teammates to check, thus enabling collaborative verification.

[0043] After receiving a device status message, the command terminal can add a "suspicious device" marker to the team member's status identifier to remind the commander to carefully refer to subsequent data.

[0044] The cross-validation alarm mechanism in this invention not only achieves intelligent fault tolerance for single-point failures or false alarms, but also uncovers deeper isolated risks through comparison between individuals and groups, forming a closed loop of data collection, local assessment, group cross-validation, hierarchical response and reporting, thereby improving the level of intelligent security early warning and ensuring high reliability.

[0045] As an example, the structured warning message in this invention follows a predefined binary or text protocol format, and the message contains at least the following data fields in sequence: Message header: contains protocol version number, total message length, and message type identifier; Identity and timestamp fields: contain the firefighter's unique ID and the Greenwich Mean Time (GMT) timestamp of the message generation time; The core field of the risk level includes the numerical code for the comprehensive risk level R. Key risk-causing data snapshot field: contains key data values ​​that trigger the current risk level, including at least the remaining gas usage time Tr, physiological load index L, resting state indicator S, and the risk deviation Z-score value between the individual and the group; Message verification field: Contains a cyclic redundancy check code used to verify the integrity of message transmission.

[0046] In step S1, the operating parameters of the air respirator include the cylinder pressure value P and the real-time gas flow rate Q, and the physiological state parameters include the heart rate value HR and the body surface temperature value. and preset individual resting heart rate The motion attitude parameters include multi-axis acceleration and angular velocity data; data fusion processing generates the derived safety indicators by performing the following calculations in parallel: a. Based on the spatiotemporally aligned cylinder pressure value P and real-time gas flow rate Q, combined with the preset critical pressure And the conversion coefficient k, through the formula Continuous calculation of residual gas usage time , Characterizes the remaining effective operating time of the air respirator at the current consumption rate; b. Heart rate (HR) and body surface temperature values ​​based on spatiotemporal alignment and preset individual resting heart rate Combined with ambient temperature Through weighted fusion formula The physiological load index L is calculated, where α is the heart rate load weighting coefficient and β is the thermoregulation load weighting coefficient. α and β can be preset and adjusted based on experimental data, historical task statistics, or different disaster scenario types to optimize the accuracy of physiological load assessment. c. Based on the spatiotemporally aligned multi-axis acceleration and angular velocity data, calculate the attitude angular change rate and the composite acceleration amplitude; when within a continuous time window... Within, the rate of change of attitude angle was detected to be consistently below the threshold. Furthermore, if the magnitude of the composite acceleration remains within the range of [0.9g, 1.1g], the firefighter is determined to be in a stationary state and a stationary state indicator S=1 is generated; otherwise, S=0. The results obtained through parallel calculations of processes a, b, and c are as follows. L and S together constitute the derived security index in the comprehensive status data.

[0047] The rate of change of attitude angle and the magnitude of the composite acceleration are derived from the inertial measurement unit (IMU) built into the firefighter terminal.

[0048] The specific explanation is as follows: Attitude angle change rate: derived from the gyroscope in the IMU. The gyroscope directly measures the angular velocity of the firefighter's body in three-dimensional space (i.e., the rate of attitude change). The attitude angle change rate can be obtained by integration or direct reading, and is used to determine whether the firefighter is in a state of violent movement or loss of posture.

[0049] Composite acceleration amplitude: derived from the accelerometer in the IMU. The accelerometer measures linear acceleration in three axes (X, Y, Z). By calculating the vector composition of the three-axis acceleration (i.e., the square root of the sum of squares), the composite acceleration amplitude is obtained, which is used to determine whether the firefighter is stationary, walking, running, or has fallen.

[0050] In step S2, the operating logic of the dynamic risk prediction model includes: Based on the comprehensive status data L, S, through functions Calculate individual real-time risk score ; Based on the acquired group situation information, the average risk level of the group is obtained. and the aforementioned group risk dispersion ; Calculate the individual risk value With the average risk level of the group Standard score : When Z is greater than the preset threshold When the risk level is determined to be high, the Z-value and the risk dispersion are then considered together. The final comprehensive risk level R is output through the function R = G(Z, σ).

[0051] Record the information related to the final risk level in each warning event. The time series data of L, S, and Z values ​​are analyzed offline to automatically correct the individual real-time risk score used to calculate the firefighter's score for the next mission. The individualized weighting coefficient or threshold of the overall risk level R.

[0052] The group situation information described in this invention refers to information related to the safety status obtained from other firefighter terminals within the current firefighter's communication range via a field communication network (Mesh network). This information includes at least the real-time risk level or risk score of other teammates, and may further include statistical characteristics (such as average value, distribution variance, etc.) of key parameters such as their air respirator capacity and physiological load, which are used for group collaborative analysis and relative risk judgment in local risk assessment.

[0053] In step S2, the preset individual behavior baseline library is obtained and maintained by performing the following steps: During routine training or low-risk emergency response missions, firefighters continuously collect their resting heart rate and body surface temperature, as well as their air intake and motion acceleration data during operational situations. The collected data are statistically analyzed to establish and store an individual behavioral baseline database for each firefighter. The individual behavioral baseline database includes at least: individual resting heart rate, individual baseline body surface temperature, individual average air intake under typical operational conditions, and feature vectors extracted from historical motion acceleration data to characterize typical motion intensity. In the comprehensive risk level calculation in step S2, the individual behavior baseline library is called as a personalized benchmark for assessing the deviation of an individual's physiological state and behavioral abnormalities. After each mission, based on the relevant data recorded during the mission, the individual behavior baseline database is smoothly corrected and updated using a weighted average algorithm, so that the individual behavior baseline database can adaptively evolve with the long-term changes in the physical condition of firefighters.

[0054] In step S2, the group situation information obtained from the field communication network is generated in real time through the following steps: S21. Through the on-site communication network, listen to and receive messages broadcast by other firefighter terminals within the communication radius at preset intervals, and parse the individual real-time risk scores of other teammates from the messages. Based on the overall risk level R, and cached locally; S22, Based on the cached data from step S51, including the current risk score of this terminal itself and all teammates. A set of values, performing the following calculations in real time: a. Calculate the arithmetic mean of the set to obtain the group average risk level, which characterizes the overall risk level of the group. ; b. Calculate the standard deviation of the set to obtain the group risk dispersion σ, which characterizes the degree of risk difference within the group; S23. The direct shared information obtained in step S21 and the derivative potential index calculated in step S22 are used together as the group situation information and provided to the dynamic risk prediction model in step S2.

[0055] In step S3, the structured warning message is generated, which is specifically achieved through the following encapsulation steps: S31. Obtain the comprehensive risk level R determined by step S2, and the key risk-causing data that triggers the level R. The key risk-causing data includes at least: residual gas usage time Tr, physiological load index L, resting state indicator S, and individual and group risk deviation Z-score values. S32. The data prepared in step S31, along with the firefighter's unique ID and current timestamp, are encoded and assembled according to a predefined communication protocol format to generate a structured data packet, wherein: a. Set a message header at the beginning of the data packet to identify the protocol version, total data packet length, and message type; b. After the message header, sequentially encapsulate the identity ID, the timestamp, the numerical code of the comprehensive risk level R, and a snapshot field containing the key risk data; c. Append a cyclic redundancy check code calculated based on the content of the data packet to the end of the data packet; S33. Message output step: The structured data packet generated in step S32 that conforms to the protocol format is output as the structured early warning message for network transmission in step S4.

[0056] In step S4, the transmission based on the communication strategy specifically includes performing the following control steps according to the current comprehensive risk level R: S41. Communication parameter decision-making step: Query the predefined control rules dynamically associated with the comprehensive risk level R, and decide on the current communication parameter combination to be used. The communication parameter combination includes at least: Sending period parameters Its value satisfies the following: the higher the risk level, the shorter the transmission cycle, that is... , , and ; The target node range parameter has the following value rules: when R=1, it is defined as broadcast to the entire network; when R=2, it is defined as multicast to the command node and one-hop neighbor nodes in the network topology; when R=3, it is defined as unicast only to the command node. The transmission guarantee mechanism activation flag has the following rules: when R=1, the flag indicates that the enhanced guarantee mechanism is enabled; when R=2 or R=3, the flag indicates that the basic guarantee mechanism or the partial guarantee mechanism is enabled. S42. Communication behavior execution steps: Based on the communication parameter combination determined in step S41, control the wireless communication module to send the structured early warning message, wherein: According to the aforementioned transmission period parameters Timed trigger for sending; Set the destination address or address mode of the data packet according to the target node range parameters; When the transmission guarantee mechanism enable flag indicates that the enhanced guarantee mechanism is enabled, at least one of the following operations is performed simultaneously: increasing the radio frequency transmission power, enabling reception acknowledgment and automatic retransmission for messages to be sent, and selecting or enabling multi-hop relay paths in the routing table.

[0057] A system for implementing the above method, such as Figure 2 As shown, it includes: The firefighter terminal is used to perform the data processing and transmission actions in steps S1, S2, S3 and S4. The field command terminal is used to receive, parse, and display early warning messages from the field communication network; The on-site communication network, constructed by the firefighter terminal and the on-site command terminal, is used to perform message routing and transmission in step S4.

[0058] In an optional embodiment, the aforementioned firefighter safety early warning communication system includes multiple firefighter terminals, at least one on-site command terminal, and an adaptive mesh communication network dynamically constructed from them, wherein: A firefighter terminal is an embedded device worn by firefighters, which integrates at least the following: The multi-source sensing module is used to collect the cylinder pressure and gas flow of the air respirator, the physiological parameters of the firefighter, and the motion posture parameters. The data processing and fusion module is connected to the multi-source sensing module and is used to perform spatiotemporal alignment of the collected multi-source parameters and perform data fusion processing to generate comprehensive status data including residual gas usage time Tr, physiological load index L and resting state identifier S. The local risk assessment module is connected to the data processing and fusion module. It has an internally stored individual behavior baseline library and is configured to: calculate the comprehensive risk level R based on the comprehensive status data, combined with the baseline library and the group situation information obtained from the field communication network, using a dynamic risk prediction model. The early warning message encapsulation module is connected to the local risk assessment module and is used to generate a structured early warning message containing a risk level identifier, a snapshot of key risk-causing data, an identity ID, and a timestamp based on the comprehensive risk level R. A communication module, connected to the early warning message encapsulation module, is used to send the structured early warning message to the field communication network according to a communication strategy dynamically associated with the comprehensive risk level R; the communication strategy is configured to dynamically adjust the message sending cycle, target node range, and transmission reliability guarantee mechanism at least according to the R value. The on-site command terminal is a monitoring device deployed at the command node, and it includes at least: The network access module is used to access and monitor the field communication network; The message parsing and alarm module is used to receive and parse the structured early warning messages from the network, and extract the risk level, key risk data and identity information from them; The integrated situation display interface is used to locate and visualize the status of each firefighter on the map, and to provide graded audible and visual alarms for different risk levels. The on-site communication network is a wireless network jointly constructed by the communication modules of each firefighter terminal and the network access module of the on-site command terminal. It is used to route and transmit the structured early warning messages and necessary signaling between each node, and supports providing differentiated link layer and network layer services for data of different priorities according to the communication strategy.

[0059] The communication strategy described in this invention also includes adaptive adjustment of channel conditions: the firefighter terminal continuously monitors the link quality indicators of the on-site communication network; when the comprehensive risk level R=1 and the link quality is detected to be lower than a preset threshold, it automatically switches to a more robust modulation and coding scheme and further shortens the transmission period T. send .

[0060] In this invention, the key risk-causing data, processed through steps S1 and S2, consists of core indicators and a chain of evidence that directly lead to an increased risk level. It uses minimal data to clearly reveal to the recipient (command terminal or teammate terminal) "what the risk is" and "why the risk occurred." The snapshots of key risk-causing data collectively constitute an "evidence matrix" explaining the source of the risk, including but not limited to the following four types of indicators: Indicators of evidence for resource sustainability: For example, the remaining air usage time Tr is an estimated number of minutes that firefighters can continue working at their current breathing intensity, calculated dynamically based on real-time cylinder pressure and flow rate. The calculation formula is as follows: Where Pc is the minimum critical pressure required for a safe return. It is the most direct indicator of life support. When Tr falls below a preset threshold (e.g., 10 minutes), a high-risk "resource exhaustion" condition is triggered. It is the primary decisive evidence in determining whether immediate evacuation is necessary.

[0061] Physiological load evidence indicators: For example, the physiological stress index (L) is a dimensionless index that comprehensively quantifies the cardiovascular and heat stress levels of firefighters. A high L value (e.g., L>2.5) clearly indicates that firefighters are under extremely high physiological stress, which may stem from overwork, high-temperature environments, or dehydration. It is a core warning signal for sudden death and heatstroke. It explains whether the risk stems from "human physiological limits being reached."

[0062] Indicators of evidence of abnormal behavior: For example, the static state indicator S is a binary identifier (S=1 or 0), determined by the behavior state fusion module through analysis of the rate of change of attitude angle and the magnitude of the composite acceleration within a continuous time window. S=1 indicates that the firefighter is physically in a "static" state (i.e., without overall movement or rotation). In proactive firefighting and rescue operations, unplanned prolonged static states (S=1 lasting more than 30 seconds) are a strong indication of an accident, potentially signifying a fall and injury, being trapped under heavy objects, unconsciousness, or loss of mobility. It is direct evidence of whether the risk involves "behavioral incapacity."

[0063] Indicators of evidence of group deviation: For example, the individual-to-group risk deviation Z-score is a statistic that quantifies the individual risk score of a firefighter. Deviation from the average risk level of his surrounding teammates The degree of risk, expressed in standard deviation σ, is the core of this invention for achieving intelligent collaborative early warning. A large positive Z value (e.g., Z>3) means that the team member's risk status is an "outlier" or "isolated high point" within the team. For example, when all teammates have normal physiological load ( The Z value is relatively low, but when only one person's remaining energy time decreases sharply and they become still (resulting in an extremely high real-time F value), a huge Z value will be generated. This provides two key pieces of information: 1. Verify the urgency of the risk, indicating that the team member's danger was not caused by the common environment (such as high temperature), but by his / her own unique and potentially more critical situation (such as personal equipment failure or being trapped alone).

[0064] 2. Root cause of auxiliary positioning problems: Combined with other evidence, a high Z value can help commanders focus quickly. For example, a high Z value accompanied by a low Tr strongly suggests that "the team member's personal air is about to run out"; a high Z value accompanied by a high L and S=1 strongly suggests that "the team member may have collapsed due to heat stress or injury".

[0065] At the command terminal, when a high-risk warning message is parsed, the system displays the "Risk Level (R=1)" and its corresponding "Key Risk-Causing Data Snapshot" side-by-side. For example, an alarm might display: [High Risk] Team Member 107 | Evidence: =5.2 minutes, L=2.8, S=1, Z=3.5. The commander can instantly interpret the complete picture of the danger: "Team member No. 107 is about to run out of air, and at the same time, his physiological load is extremely high and he has collapsed to the ground. His condition is far more dangerous than that of his teammates, and targeted rescue must be carried out immediately." Therefore, the design of the key danger data snapshot upgrades the early warning from a simple "status alarm" to a "diagnostic alarm." It enables the back-end command system not only to know that "there is danger," but also to understand "what kind of danger" and "where the danger comes from," thus realizing a leap from passively receiving alarms to proactive and accurate decision-making.

[0066] A firefighter safety early warning communication terminal that integrates breathing apparatus and vital signs includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the above method.

[0067] Figure 3 A block diagram of an exemplary electronic device terminal suitable for implementing embodiments of the present invention is shown. It is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0068] like Figure 3 As shown, terminal 12 is presented in the form of a general-purpose computing device. The components of terminal 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0069] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0070] Terminal 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by terminal 12, including volatile and non-volatile media, removable and non-removable media.

[0071] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Terminal 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0072] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0073] Terminal 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with terminal 12, and / or with any device that enables terminal 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, terminal 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of terminal 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with terminal 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0074] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the firefighter safety early warning communication method that integrates breathing apparatus and vital signs provided in the embodiments of the present invention.

[0075] A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the above-described method.

[0076] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0077] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0078] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0079] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0080] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A firefighter safety early warning communication method integrating breathing apparatus data and vital signs, characterized in that, Includes the following steps: S1. Real-time collection of individual firefighters' air respirator operating parameters, physiological state parameters, and movement posture parameters on the firefighter terminal; spatiotemporal alignment and data fusion processing of the collected parameters to generate comprehensive status data including derived safety indicators; wherein, the spatiotemporal alignment and data fusion processing steps are as follows: When collecting each parameter sample, the sample is timestamped using the unified clock of the firefighter's terminal, and each parameter is cached into the corresponding first-in-first-out queue according to its respective sampling rate. Triggered by a preset fusion period, for each parameter queue, the most recent valid sample is retrieved; for high-frequency parameters, the mean or variance of the samples within that fusion period is taken as the representative value for that period. For the multi-axis acceleration and angular velocity data in the motion posture parameters, according to the preset installation position and angle of each sensor on the firefighter's body, the data are transformed into the same body coordinate system centered on the firefighter's torso using a rotation matrix. The derived security index is calculated; S2. Based on the comprehensive status data, combined with the preset individual behavior baseline library and the group situation information obtained from the on-site communication network, a comprehensive risk level is calculated in real time on the firefighter terminal using a dynamic risk prediction model. S3. Based on the comprehensive risk level, automatically generate a structured early warning message containing the risk level identifier, key risk data snapshot, personnel identity, and timestamp; the firefighter terminal exchanges the structured early warning message with the firefighter terminals of neighboring teammates through the on-site communication network; if its own comprehensive risk level is determined to be higher than the average level of the surrounding teammates, a cross-validation alarm is activated; if its own comprehensive risk level is lower than the average level of the surrounding teammates, a sensor self-check procedure is triggered. S4. Based on the communication strategy dynamically associated with the comprehensive risk level, the structured early warning message generated in step S3 is sent to the command node and associated nodes through the field communication network.

2. The method according to claim 1, characterized in that, In step S1, the operating parameters of the air respirator include the cylinder pressure value P and the real-time gas flow rate Q, and the physiological state parameters include the heart rate value HR and the body surface temperature value. and preset individual resting heart rate The motion attitude parameters include multi-axis acceleration and angular velocity data; Data fusion processing generates the derived security metrics by performing the following computational processes in parallel: a. Based on the spatiotemporally aligned cylinder pressure value P and real-time gas flow rate Q, combined with the preset critical pressure And the conversion coefficient k, through the formula Continuous calculation of residual gas usage time , Characterizes the remaining effective operating time of the air respirator at the current consumption rate; b. Heart rate (HR) and body surface temperature values ​​based on spatiotemporal alignment and preset individual resting heart rate Combined with ambient temperature Through weighted fusion formula Calculate the physiological load index L, where α is the heart rate load weighting coefficient and β is the body temperature regulation load weighting coefficient; c. Based on the spatiotemporally aligned multi-axis acceleration and angular velocity data, calculate the attitude angular change rate and the composite acceleration amplitude; when within a continuous time window... Within, the rate of change of attitude angle was detected to be consistently below the threshold. Furthermore, if the magnitude of the composite acceleration remains within the range of [0.9g, 1.1g], the firefighter is determined to be in a stationary state and a stationary state indicator S=1 is generated; otherwise, S=0. The results obtained through parallel calculations of processes a, b, and c are as follows. L and S together constitute the derived security index in the comprehensive status data.

3. The method according to claim 2, characterized in that: In step S2, the operating logic of the dynamic risk prediction model includes: Based on the comprehensive status data L, S, through functions Calculate individual real-time risk score ; Based on the acquired group situation information, the average risk level of the group is obtained. and the aforementioned group risk dispersion ; Calculate the individual risk value With the average risk level of the group Standard score : When Z is greater than the preset threshold When the risk level is determined to be high, the Z-value and the risk dispersion are then considered together. The final comprehensive risk level R is output through the function R = G(Z, σ).

4. The method according to claim 3, characterized in that: Record the information related to the final risk level in each warning event. The time series data of L, S, and Z values ​​are analyzed offline to automatically correct the individual real-time risk score used to calculate the firefighter's score for the next mission. The individualized weighting coefficient or threshold of the overall risk level R.

5. The method according to claim 1, characterized in that, In step S2, the preset individual behavior baseline library is obtained and maintained by performing the following steps: During routine training or low-risk emergency response missions, firefighters' heart rate and body surface temperature at rest, as well as air flow rate and acceleration data of their breathing apparatus during work, are continuously collected. The collected data are statistically analyzed to establish and store a set of individual behavioral baseline databases for each firefighter. The individual behavioral baseline database includes at least: individual resting heart rate, individual baseline body surface temperature, individual average gas flow rate under typical working conditions, and feature vectors extracted from historical motion acceleration data to characterize the intensity of typical motion. In the comprehensive risk level calculation in step S2, the individual behavior baseline library is called as a personalized benchmark for assessing the deviation of an individual's physiological state and behavioral abnormalities. After each mission, based on the relevant data recorded during the mission, the individual behavior baseline database is smoothly corrected and updated using a weighted average algorithm, so that the individual behavior baseline database can adaptively evolve with the long-term changes in the physical condition of firefighters.

6. The method according to claim 1, characterized in that, In step S2, the group situation information obtained from the field communication network is generated in real time through the following steps: S21. Through the on-site communication network, listen to and receive messages broadcast by other firefighter terminals within the communication radius at preset intervals, and parse the individual real-time risk scores of other teammates from the messages. Based on the overall risk level R, and cached locally; S22, Based on the cached data from step S51, including the current risk score of this terminal itself and all teammates. A set of values, performing the following calculations in real time: a. Calculate the arithmetic mean of the set to obtain the group average risk level, which characterizes the overall risk level of the group. ; b. Calculate the standard deviation of the set to obtain the group risk dispersion σ, which characterizes the degree of risk difference within the group; S23. The direct shared information obtained in step S21 and the derivative potential index calculated in step S22 are used together as the group situation information and provided to the dynamic risk prediction model in step S2.

7. The method according to claim 1, characterized in that, In step S3, the structured warning message is generated, which is specifically achieved through the following encapsulation steps: S31. Obtain the comprehensive risk level R determined by step S2, and the key risk-causing data that triggers the level R. The key risk-causing data includes at least: residual gas usage time Tr, physiological load index L, resting state indicator S, and individual and group risk deviation Z-score values. S32. The data prepared in step S31, along with the firefighter's unique ID and current timestamp, are encoded and assembled according to a predefined communication protocol format to generate a structured data packet, wherein: a. Set a message header at the beginning of the data packet to identify the protocol version, total data packet length, and message type; b. After the message header, sequentially encapsulate the identity ID, the timestamp, the numerical code of the comprehensive risk level R, and a snapshot field containing the key risk data; c. Append a cyclic redundancy check code calculated based on the content of the data packet to the end of the data packet; S33. Message output step: The structured data packet generated in step S32 that conforms to the protocol format is output as the structured early warning message for network transmission in step S4.

8. The method according to claim 1, characterized in that: In step S4, the transmission based on the communication strategy specifically includes performing the following control steps according to the current comprehensive risk level R: S41. Communication parameter decision-making step: Query the predefined control rules dynamically associated with the comprehensive risk level R, and decide on the current communication parameter combination to be used. The communication parameter combination includes at least: Sending period parameters Its value satisfies the following: the higher the risk level, the shorter the transmission cycle, that is... , , and ; The target node range parameter has the following value rules: when R=1, it is defined as broadcast to the entire network; when R=2, it is defined as multicast to the command node and one-hop neighbor nodes in the network topology; when R=3, it is defined as unicast only to the command node. The transmission guarantee mechanism activation flag has the following rules: when R=1, the flag indicates that the enhanced guarantee mechanism is enabled; when R=2 or R=3, the flag indicates that the basic guarantee mechanism or the partial guarantee mechanism is enabled. S42. Communication behavior execution steps: Based on the communication parameter combination determined in step S41, control the wireless communication module to send the structured early warning message, wherein: According to the aforementioned transmission period parameters Timed trigger for sending; Set the destination address or address mode of the data packet according to the target node range parameters; When the transmission guarantee mechanism enable flag indicates that the enhanced guarantee mechanism is enabled, at least one of the following operations is performed simultaneously: increasing the radio frequency transmission power, enabling reception acknowledgment and automatic retransmission for messages to be sent, and selecting or enabling multi-hop relay paths in the routing table.

9. A system for implementing the method according to any one of claims 1 to 8, characterized in that, include: The firefighter terminal is used to perform the data processing and transmission actions in steps S1, S2, S3 and S4. The field command terminal is used to receive, parse, and display early warning messages from the field communication network; The on-site communication network, constructed by the firefighter terminal and the on-site command terminal, is used to perform message routing and transmission in step S4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 8.

Images