An intelligent fire monitoring and early warning system based on the Internet of Things and an implementation method thereof

Abstract

The application relates to the technical field of fire-fighting monitoring and early warning, in particular to an intelligent fire-fighting monitoring and early warning system based on the Internet of Things and an implementation method. The system comprises a server and a sensing and detecting module, a feature mapping module, a risk identification module and a response scheduling module which are in communication connection with the server. The spatial topological correlation between monitoring points is established, and discrete risk deviation degrees are interpolated into a global risk distribution map, so that the defect that traditional methods cannot perceive the overall situation of risks by isolated analysis of point data is overcome. The personnel density grade and the material importance grade are introduced to perform weighted correction on the basis risk deviation degree to calculate a comprehensive response urgency, so that the single decision mode of the prior art which simply depends on environmental parameter thresholds for alarm is changed. Difference response strategies are generated, and fire-fighting facilities are controlled in stages according to response priorities, so that the system can take targeted measures for regions with different risk grades in the early stage of fire.

Description

Technical Field

[0001] This invention relates to the field of fire monitoring and early warning technology, specifically to an intelligent fire monitoring and early warning system and its implementation method based on the Internet of Things. Background Technology

[0002] With the accelerating pace of urbanization and increasingly complex building structures, fire risks have significantly increased. Traditional fire protection methods relying on manual inspections and simple sensor alarms are no longer sufficient to meet the demands of modern buildings for timely and accurate fire warnings. In recent years, the rapid development of Internet of Things (IoT) technology has provided a new technological path for the intelligent upgrading of fire protection systems. By deploying various sensors such as temperature, smoke, humidity, and carbon monoxide sensors within the fire monitoring area, real-time collection and remote transmission of environmental status data have been achieved, thereby improving the automation level of fire warnings to a certain extent.

[0003] However, existing IoT-based fire monitoring and early warning systems still have many shortcomings. Traditional fire early warning systems typically analyze data from each sensor independently and determine whether to trigger an alarm based on whether the environmental parameters collected by a single sensor exceed a preset threshold. This isolated analysis approach ignores the inherent spatial correlation between different monitoring points, resulting in the system only being able to perceive abnormal states at local points and failing to grasp the overall risk distribution of the entire fire monitoring area. It also struggles to proactively identify the direction and trend of risk spread. Furthermore, early warning parameters in existing systems (such as alarm thresholds and priority factors) are usually set manually based on experience, lacking a dynamic adjustment mechanism after the system is put into use. This makes it difficult to adapt to the natural fluctuations of the environmental base state under different seasons, time periods, or scenarios, and is highly susceptible to errors due to fixed thresholds and environmental dynamics. The mismatch between the state changes leads to a large number of false alarms or missed alarms. Most existing systems can only issue audible and visual warning signals after the alarm is triggered, and cannot adopt targeted hierarchical control strategies for different areas based on the degree of risk differentiation. As a result, when anomalies occur in multiple areas at the same time, the dispatch of fire-fighting resources (such as fire extinguishing devices and smoke extraction equipment) lacks a reasonable priority basis, which can easily cause response conflicts between high-risk, low-value areas and low-risk, high-value areas. Limited resources cannot be optimally allocated in complex fire scenarios. In addition, the response strategies of existing systems are relatively fixed and rigid, making it difficult to adjust the activation timing and intensity of fire-fighting facilities in real time according to the dynamic evolution of the fire. Often, effective measures are not taken in time to control the spread of the fire in the early stage of the fire, delaying the best time for disposal and seriously affecting the overall emergency response effectiveness of the fire monitoring and early warning system.

[0004] To address the shortcomings of the existing technologies, this invention provides an intelligent fire monitoring and early warning system and its monitoring and early warning method based on the Internet of Things. It aims to solve the technical problems of existing fire monitoring and early warning systems, such as poor risk perception capabilities, inability to adaptively optimize early warning parameters, lack of reasonable priority basis for fire resource scheduling, and rigid response strategies that are difficult to cope with the dynamic evolution of fires. Summary of the Invention

[0005] (a) Technical problems to be solved To address the shortcomings of existing technologies, this invention provides an intelligent fire monitoring and early warning system based on the Internet of Things (IoT). This system overcomes many deficiencies of current IoT-based fire monitoring and early warning systems. Traditional fire early warning systems typically analyze data from individual sensors independently, determining alarm triggering based on whether environmental parameters collected by a single sensor exceed preset thresholds. This isolated analysis ignores the inherent spatial correlation between different monitoring points, resulting in the system only being able to perceive abnormal states at local points and failing to grasp the overall risk distribution across the entire fire monitoring area. It also struggles to proactively identify the direction and trend of risk spread. Furthermore, early warning parameters in existing systems (such as alarm thresholds and priority factors) are usually set manually based on experience, lacking a dynamic adjustment mechanism after system deployment. This makes it difficult to adapt to different seasons, time periods, or environmental conditions. Natural fluctuations can easily lead to numerous false alarms or missed alarms due to the mismatch between fixed thresholds and dynamic environmental changes. Most existing systems can only issue audible and visual warning signals after an alarm is triggered, and cannot adopt targeted hierarchical control strategies for different areas based on the degree of risk differentiation. This results in a lack of reasonable priority for the dispatch of fire-fighting resources (such as fire extinguishing devices and smoke extraction equipment) when anomalies occur in multiple areas simultaneously. This can easily cause response conflicts between high-risk, low-value areas and low-risk, high-value areas. Limited resources cannot be optimally allocated in complex fire scenarios. In addition, the response strategies of existing systems are relatively fixed and rigid, making it difficult to adjust the activation timing and intensity of fire-fighting facilities in real time according to the dynamic evolution of the fire. Often, effective measures are not taken in time to control the spread of the fire in the early stages of the fire, delaying the best response time and seriously affecting the overall emergency response effectiveness of the fire monitoring and early warning system.

[0006] (II) Technical Solution To achieve the above objectives, the present invention provides the following technical solution: an intelligent fire monitoring and early warning system based on the Internet of Things, comprising: The server, and a sensor detection module, a feature mapping module, a risk identification module and a response scheduling module that are respectively connected to the server in communication; The sensing and detection module collects environmental status data from multiple monitoring points within the fire monitoring area and generates a time sequence of the status of the corresponding monitoring points. The feature mapping module maps the state time sequence of each monitoring point to a state feature vector in a high-dimensional feature space, and compares the state feature vector with a preset standard safety feature vector to calculate the risk deviation of each monitoring point. The risk identification module constructs a global risk distribution map of the fire monitoring area based on the risk deviation of each monitoring point and the spatial topological relationship between the monitoring points, and determines the risk evolution trend based on the global risk distribution map. The response scheduling module generates differentiated response strategies for different monitoring points based on the risk evolution trend, and performs hierarchical control of fire protection facilities according to response priority.

[0007] In some embodiments, the feature mapping module includes a temporal alignment unit, a feature extraction unit, and a deviation calculation unit; The timing alignment unit performs time base unification processing on the state timing sequences of different monitoring points; The feature extraction unit extracts the feature components of each monitoring point in the time domain and frequency domain according to the state time sequence after the time base is unified, and combines the feature components into the state feature vector. The deviation calculation unit calculates the generalized distance between the state feature vector and the standard safety feature vector, and uses the generalized distance as the risk deviation.

[0008] In some embodiments, the standard safety feature vector is the cluster center of the historical state feature vectors of each monitoring point in the fire monitoring area when there is no fire hazard.

[0009] In some embodiments, the risk identification module includes a spatial association unit and an evolution determination unit; The spatial association unit establishes a spatial topological association relationship between monitoring points based on the physical location of the monitoring points and the layout of fire protection facilities, and performs spatial interpolation on the risk deviation of each monitoring point according to the spatial topological association relationship to form the global risk distribution map. The evolution determination unit calculates the spatial gradient change and time rate of change of risk intensity based on the global risk distribution map at the current time and the previous time, and determines the risk evolution trend based on the spatial gradient change and the time rate of change.

[0010] In some embodiments, the risk evolution trend includes the direction of risk spread, the rate of risk spread, and the area of ​​risk clustering; The evolution determination unit determines the risk spread direction based on the spatial gradient change, determines the risk spread rate based on the time change rate, and determines the risk clustering area based on the spatial clustering degree of monitoring points where the risk deviation exceeds a preset threshold.

[0011] In some embodiments, the response scheduling module includes a policy generation unit and a priority management unit; The strategy generation unit generates differentiated response strategies for different risk levels based on the risk spread direction, the risk spread rate, and the risk clustering area. The differentiated response strategies include warning type, warning range, and emergency measure type. The priority management unit calculates the overall urgency of response for each monitoring point based on the risk deviation of each monitoring point, as well as the personnel density level and material importance level of the area where the monitoring point is located, and determines the response priority based on the overall urgency of response.

[0012] In some embodiments, when calculating the overall response urgency, the priority management unit uses the risk deviation as the basic urgency indicator and applies the personnel density level and the material importance level to weight and correct the basic urgency indicator to obtain the overall response urgency.

[0013] In some embodiments, the response scheduling module further includes a resource adaptation unit; The resource adaptation unit acquires the resource status information of available fire protection facilities within the fire monitoring area, and matches the target fire protection facility from the available fire protection facilities according to the differentiated response strategy and the response priority, and generates control instructions for the target fire protection facility.

[0014] An implementation method for intelligent fire monitoring and early warning based on the Internet of Things, the implementation method of the intelligent fire monitoring and early warning system includes the following steps: S1: Collect environmental status data from multiple monitoring points within the fire monitoring area through the sensor detection module, and generate the status time sequence of the corresponding monitoring points; S2: The state time sequence of each monitoring point is mapped to a state feature vector in a high-dimensional feature space through the feature mapping module, and the state feature vector is compared with the preset standard safety feature vector to calculate the risk deviation of each monitoring point; S3: Based on the risk deviation of each monitoring point and the spatial topological relationship between the monitoring points, the risk identification module constructs a global risk distribution map of the fire monitoring area and determines the risk evolution trend based on the global risk distribution map. S4: The response scheduling module generates differentiated response strategies for different monitoring points based on the risk evolution trend, and performs hierarchical control of fire protection facilities according to response priority.

[0015] In some embodiments, in step S3, the spatial gradient change and time change rate of risk intensity are calculated based on the global risk distribution map at the current time and the previous time, and the risk spread direction is determined based on the spatial gradient change, the risk spread rate is determined based on the time change rate, and the risk clustering area is determined based on the spatial clustering degree of monitoring points whose risk deviation exceeds a preset threshold.

[0016] (III) Beneficial Effects The beneficial effects of this invention are as follows: By mapping the environmental state time series of each monitoring point to a high-dimensional feature space and comparing it with a standard safety feature vector, this invention can effectively filter out interference caused by environmental noise and sensor drift, significantly improving the sensitivity of identifying weak abnormal signals in the early stage of a fire, thereby reducing the false alarm rate and the missed alarm rate; by establishing spatial topological relationships between monitoring points and interpolating discrete risk deviations into a global risk distribution map, this invention overcomes the shortcomings of traditional methods that isolate the analysis of data at each point and cannot perceive the overall risk situation, enabling the system to have the ability to actively perceive the direction and rate of risk spread; by introducing personnel density levels and material levels on top of the basic risk deviation, this invention effectively improves the detection sensitivity of weak abnormal signals in the early stage of a fire, thereby reducing the false alarm rate and the missed alarm rate. By weighting and adjusting the importance level of resources to calculate the overall urgency of the response, the system changes the single decision-making mode of existing technologies that rely solely on environmental parameter thresholds for alarms. This makes the dispatch of fire-fighting resources more scientific and rational, avoiding response conflicts between high-risk, low-value areas and low-risk, high-value areas, and achieving optimal allocation of limited fire-fighting resources in complex scenarios. By generating differentiated response strategies and classifying fire-fighting facilities according to response priorities, the system can take targeted measures for areas with different risk levels in the early stages of a fire, effectively curbing the spread of fire and buying valuable time for personnel evacuation, thus comprehensively improving the intelligence level and emergency response efficiency of the fire monitoring and early warning system. Attached Figure Description

[0017] Figure 1 This is a block diagram of the modules of the present invention.

[0018] Figure 2 This is a flowchart of the method of the present invention. Detailed Implementation

[0019] To better explain and facilitate understanding of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] This invention proposes an IoT-based intelligent fire monitoring and early warning system. This system maps the environmental state time-series of each monitoring point to a high-dimensional feature space and compares it with a standard safety feature vector. It establishes spatial topological relationships between monitoring points and interpolates discrete risk deviations into a global risk distribution map. By introducing personnel density levels and material importance levels for weighted correction on top of the basic risk deviation, it calculates the comprehensive response urgency. It generates differentiated response strategies and performs graded control of fire-fighting facilities according to response priorities. This aims to address many shortcomings of existing IoT-based fire monitoring and early warning systems. Traditional fire early warning systems typically analyze data from each sensor independently and determine alarm triggering based on whether environmental parameters collected by a single sensor exceed preset thresholds. This isolated analysis ignores the inherent spatial correlation between different monitoring points, resulting in the system only being able to perceive abnormal states at local points and failing to grasp the overall risk distribution of the entire fire monitoring area. It also struggles to proactively identify the direction and trend of risk spread. Existing systems' early warning... Parameters (such as alarm thresholds and priority factors) are usually set manually based on experience. After the system is put into use, there is a lack of dynamic adjustment mechanism, making it difficult to adapt to the natural fluctuations of the environmental base state under different seasons, time periods, or scenarios. This easily leads to a large number of false alarms or missed alarms due to the mismatch between fixed thresholds and dynamic environmental changes. Most existing systems can only issue audible and visual warning signals after triggering an alarm, and cannot adopt targeted hierarchical control strategies for different areas based on the degree of risk differentiation. As a result, when anomalies occur in multiple areas at the same time, the scheduling of fire-fighting resources (such as fire extinguishing devices and smoke extraction equipment) lacks a reasonable priority basis, which can easily cause response conflicts between high-risk, low-value areas and low-risk, high-value areas. Limited resources cannot be optimally configured in complex fire scenarios. In addition, the response strategies of existing systems are relatively fixed and rigid, making it difficult to adjust the activation timing and intensity of fire-fighting facilities in real time according to the dynamic evolution of the fire. Often, effective measures are not taken in time to control the spread of the fire in the early stages of the fire, delaying the best time for response and seriously affecting the overall emergency response effectiveness of the fire monitoring and early warning system.

[0021] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0022] Example 1 Please see Figure 1 As shown, the present invention provides a technical solution: an intelligent fire monitoring and early warning system based on the Internet of Things, comprising: The server, and the sensor detection module, feature mapping module, risk identification module and response scheduling module that are respectively connected to the server in communication; The sensing and detection module collects environmental status data from multiple monitoring points within the fire monitoring area and generates a time sequence of status data for the corresponding monitoring points. The feature mapping module maps the state time sequence of each monitoring point to a state feature vector in a high-dimensional feature space, and compares the state feature vector with the preset standard safety feature vector to calculate the risk deviation of each monitoring point. The risk identification module constructs a global risk distribution map of the fire monitoring area based on the risk deviation of each monitoring point and the spatial topological relationship between the monitoring points, and determines the risk evolution trend based on the global risk distribution map. The response scheduling module generates differentiated response strategies for different monitoring points based on the risk evolution trend, and performs hierarchical control of fire protection facilities according to response priority.

[0023] By setting up a sensor detection module, a feature mapping module, a risk identification module, and a response scheduling module, environmental state data is transformed into a state time series and then mapped to a high-dimensional feature space for comparative analysis. This enables the system to perceive the risk distribution of the fire monitoring area from a global perspective, overcoming the information fragmentation problem caused by independent judgment by a single sensor in traditional methods. The sensor detection module continuously collects multi-dimensional environmental state data through multiple monitoring points deployed within the fire monitoring area and generates state time series for each monitoring point, providing a rich and continuous data source for subsequent feature mapping. The feature mapping module maps the state time series to state feature vectors in the high-dimensional feature space and compares them with standard safety feature vectors to calculate the risk deviation of each monitoring point, presenting continuous numerical values. The formula quantitatively characterizes the degree of deviation of the current state of each monitoring point from the safe baseline state. Compared with the traditional binary judgment mode that only relies on whether a single environmental parameter exceeds a fixed threshold, it provides a more delicate and accurate risk quantification result. The risk identification module constructs a global risk distribution map and determines the risk evolution trend based on the risk deviation of each monitoring point and the spatial topological relationship between monitoring points. This enables the system to grasp the risk situation of the fire monitoring area from an overall perspective and realize the transformation from passive response to proactive prediction. The response scheduling module generates differentiated response strategies based on the risk evolution trend and performs hierarchical control of fire protection facilities according to response priority. This avoids the crude mode of uniform alarm and indiscriminate response in the traditional method, making the allocation of fire protection resources more precise and efficient.

[0024] Example 2 The main difference between this embodiment and Embodiment 1 is that, please refer to... Figure 1 As shown, the feature mapping module includes a temporal alignment unit, a feature extraction unit, and a deviation calculation unit; The timing alignment unit performs time base unification processing on the state timing sequences of different monitoring points; The feature extraction unit extracts the feature components of each monitoring point in the time domain and frequency domain based on the state time sequence after the time base is unified, and combines the feature components into a state feature vector. The deviation calculation unit calculates the generalized distance between the state feature vector and the standard safety feature vector, and uses the generalized distance as the risk deviation. The standard safety feature vector is the cluster center of the historical status feature vectors of each monitoring point in the fire monitoring area under the condition of no fire hazard.

[0025] Through the coordinated operation of the time-series alignment unit, feature extraction unit, and deviation calculation unit, the time-based standardization of state time-series sequences from different monitoring points can be achieved. Feature components in the time and frequency domains are extracted and combined into a state feature vector. Then, the cluster centers of historical state feature vectors are used as standard safety feature vectors for generalized distance calculation, effectively filtering out interference from environmental noise and sensor drift. The time-series alignment unit collects timestamps from each sensor and uses a dynamic time alignment algorithm to unify the time-based standard of the state time-series sequences from each monitoring point, ensuring that all monitoring points have a consistent time step and a unified time standard on the time axis. This fundamentally guarantees the accuracy and reliability of multi-source data fusion analysis. The feature extraction unit extracts feature components from each monitoring point in the time and frequency domains. The time-domain features reflect the environmental state of each monitoring point over time. The dynamic change pattern in dimensions and the frequency domain features reflect the energy distribution of environmental state data at different frequency components. Combining the two into a state feature vector allows this vector to comprehensively characterize the dynamic behavior pattern of the environmental state at each monitoring point from multiple dimensions. The deviation calculation unit calculates the generalized distance between the state feature vector and the standard safety feature vector and uses this distance as the risk deviation. The standard safety feature vector is the cluster center of the historical state feature vectors of each monitoring point in the fire monitoring area under the condition of no fire hazard. Using this cluster center as a reference benchmark makes the risk deviation a statistically reasonable reference system. When the environmental ground state slowly drifts due to seasonal changes or day-night alternation, the standard safety feature vector can be adaptively adjusted by periodically updating the cluster center, effectively solving the problem of false alarms and missed alarms caused by dynamic environmental changes in the traditional fixed threshold method.

[0026] Example 3 The main difference between this embodiment and Embodiment 1 is that, please refer to... Figure 1 As shown, the risk identification module includes spatial association units and evolution determination units; The spatial correlation unit establishes spatial topological correlations between monitoring points based on their physical locations and the layout of fire protection facilities. It then performs spatial interpolation on the risk deviation of each monitoring point according to the spatial topological correlations to form a global risk distribution map. The evolution determination unit calculates the spatial gradient change and temporal rate of change of risk intensity based on the global risk distribution map at the current time and the previous time, and determines the risk evolution trend based on the spatial gradient change and temporal rate of change. Risk evolution trends include the direction of risk spread, the rate of risk spread, and the areas where risks accumulate; The evolution determination unit determines the direction of risk spread based on the spatial gradient change, the rate of risk spread based on the time change rate, and the risk clustering area based on the spatial clustering degree of monitoring points whose risk deviation exceeds the preset threshold. The response scheduling module includes a policy generation unit and a priority management unit; The strategy generation unit generates differentiated response strategies for different risk levels based on the direction of risk spread, the rate of risk spread, and the area of ​​risk clustering. The differentiated response strategies include warning type, warning scope, and emergency measure type. The priority management unit calculates the overall urgency of response for each monitoring point based on the risk deviation of each monitoring point, as well as the personnel density level and material importance level of the area where the monitoring point is located, and determines the response priority based on the overall urgency of response. When calculating the overall response urgency, the priority management unit uses the risk deviation as the basic urgency indicator and uses personnel density level and material importance level to weight and correct the basic urgency indicator to obtain the overall response urgency. The response scheduling module also includes a resource adaptation unit; The resource adaptation unit obtains the resource status information of available fire protection facilities within the fire monitoring area, and matches the target fire protection facility from the available fire protection facilities according to the differentiated response strategy and response priority, and generates control instructions for the target fire protection facility.

[0027] By establishing spatial topological relationships between monitoring points through spatial correlation units and interpolating discrete risk deviations into a global risk distribution map, the system gains the ability to grasp the overall risk situation. Then, through evolutionary judgment units, spatial gradient changes and temporal rates of change are calculated to determine the direction, rate, and clustering area of ​​risk spread, enabling proactive perception and tracking of the dynamic evolution of the fire. The spatial correlation units construct spatial topological relationships between monitoring points by incorporating the physical coordinates of each monitoring point and the layout information of fire protection facilities into a unified spatial reference framework. The risk deviations of each monitoring point are then spatially interpolated according to this relationship to form a global risk distribution map, allowing managers and system decision-makers to fully grasp the overall risk situation of the entire fire monitoring area. The evolutionary judgment unit calculates the spatial gradient changes and temporal rates of change of risk intensity based on the current and previous global risk distribution maps. The spatial gradient changes reflect the risk intensity in spatial location. The rate and direction of change in the data, and the time rate of change, reflect the speed and trend of change in risk intensity at each location over time. Combining these two factors allows the system to determine the direction, rate, and area of ​​risk spread, enabling it to accurately assess the current state and trajectory of a fire. The strategy generation unit generates differentiated response strategies for different risk levels based on risk evolution trends. The priority management unit uses risk deviation as a basis and incorporates personnel density and material importance levels for weighted correction to obtain a comprehensive response urgency. This comprehensive response urgency reflects three core dimensions: life safety protection needs, property protection needs, and risk urgency. This effectively solves the resource scheduling conflict between high-risk, low-value areas and low-risk, high-value areas in traditional methods. The resource adaptation unit obtains the resource status information of available fire-fighting facilities and generates control commands based on differentiated response strategies and response priorities, matching target fire-fighting facilities. This ensures that fire-fighting resource scheduling has high accuracy and adaptability.

[0028] Example 4 The main difference between this embodiment and Embodiment 1 is that, please refer to... Figure 2 As shown, the implementation method of the intelligent fire monitoring and early warning system includes the following steps: S1: Collect environmental status data from multiple monitoring points within the fire monitoring area through the sensor detection module, and generate the status time sequence of the corresponding monitoring points; S2: The feature mapping module maps the state time sequence of each monitoring point to a state feature vector in a high-dimensional feature space, and compares the state feature vector with the preset standard safety feature vector to calculate the risk deviation of each monitoring point. S3: The risk identification module constructs a global risk distribution map of the fire monitoring area based on the risk deviation of each monitoring point and the spatial topological relationship between the monitoring points, and determines the risk evolution trend based on the global risk distribution map. S4: The response scheduling module generates differentiated response strategies for different monitoring points based on the risk evolution trend, and performs hierarchical control of fire protection facilities according to response priority; In step S3, the spatial gradient change and time change rate of risk intensity are calculated based on the global risk distribution map at the current time and the previous time. The direction of risk spread is determined based on the spatial gradient change, the rate of risk spread is determined based on the time change, and the risk clustering area is determined based on the spatial clustering degree of monitoring points whose risk deviation exceeds the preset threshold.

[0029] In the risk identification step, the spread direction is determined by calculating the spatial gradient change, the spread rate is determined by the time change rate, and the clustering area is determined by the spatial clustering degree of monitoring points whose risk deviation exceeds the threshold. Then, differentiated response strategies are generated and fire protection facilities are controlled in a graded manner according to response priority. Step S1 provides the original data foundation for the entire early warning process, ensuring that subsequent steps have sufficient and high-quality data sources. Step S2 realizes the effective transformation from data to information, enabling the system to uniformly measure and horizontally compare the risk level of each monitoring point in a standardized manner. Step S3 enables the system to grasp the risk situation and its evolution law of the fire monitoring area from a holistic perspective, realizing a qualitative change from local perception to global cognition. The judgment results of the three dimensions of risk spread direction, spread rate, and clustering area complement each other and together constitute a complete description of the dynamic evolution process of the fire. Step S4 transforms the risk identification results into specific and executable control actions, realizing a closed loop of the entire process from cognition to decision-making to execution. This enables the system to effectively curb the further spread of the fire in the early stage of fire spread, buy valuable time for firefighters to arrive at the scene and for trapped personnel to evacuate safely, and comprehensively improve the intelligence level and emergency response efficiency of the fire monitoring and early warning system.

[0030] In the description of this invention, it should be understood that the terms "first" and "second" 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. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0031] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0032] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first and second features are in direct contact, or that they are in indirect contact through an intermediate medium. Furthermore, "above," "over," or "on top" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," or "beneath" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0033] In the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0034] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make modifications, alterations, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An intelligent fire monitoring and early warning system based on the Internet of Things, characterized in that, include: The server, and a sensor detection module, a feature mapping module, a risk identification module and a response scheduling module that are respectively connected to the server in communication; The sensing and detection module collects environmental status data from multiple monitoring points within the fire monitoring area and generates a time sequence of the status of the corresponding monitoring points. The feature mapping module maps the state time sequence of each monitoring point to a state feature vector in a high-dimensional feature space, and compares the state feature vector with a preset standard safety feature vector to calculate the risk deviation of each monitoring point. The risk identification module constructs a global risk distribution map of the fire monitoring area based on the risk deviation of each monitoring point and the spatial topological relationship between the monitoring points, and determines the risk evolution trend based on the global risk distribution map. The response scheduling module generates differentiated response strategies for different monitoring points based on the risk evolution trend, and performs hierarchical control of fire protection facilities according to response priority.

2. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 1, characterized in that, The feature mapping module includes a temporal alignment unit, a feature extraction unit, and a deviation calculation unit; The timing alignment unit performs time base unification processing on the state timing sequences of different monitoring points; The feature extraction unit extracts the feature components of each monitoring point in the time domain and frequency domain according to the state time sequence after the time base is unified, and combines the feature components into the state feature vector. The deviation calculation unit calculates the generalized distance between the state feature vector and the standard safety feature vector, and uses the generalized distance as the risk deviation.

3. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 2, characterized in that, The standard safety feature vector is the cluster center of the historical state feature vectors of each monitoring point in the fire monitoring area under the condition of no fire hazard.

4. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 1, characterized in that, The risk identification module includes a spatial association unit and an evolution determination unit; The spatial association unit establishes a spatial topological association relationship between monitoring points based on the physical location of the monitoring points and the layout of fire protection facilities, and performs spatial interpolation on the risk deviation of each monitoring point according to the spatial topological association relationship to form the global risk distribution map. The evolution determination unit calculates the spatial gradient change and time rate of change of risk intensity based on the global risk distribution map at the current time and the previous time, and determines the risk evolution trend based on the spatial gradient change and the time rate of change.

5. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 4, characterized in that, The risk evolution trend includes the direction of risk spread, the rate of risk spread, and the area of ​​risk concentration; The evolution determination unit determines the risk spread direction based on the spatial gradient change, determines the risk spread rate based on the time change rate, and determines the risk clustering area based on the spatial clustering degree of monitoring points where the risk deviation exceeds a preset threshold.

6. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 5, characterized in that, The response scheduling module includes a policy generation unit and a priority management unit; The strategy generation unit generates differentiated response strategies for different risk levels based on the risk spread direction, the risk spread rate, and the risk clustering area. The differentiated response strategies include warning type, warning range, and emergency measure type. The priority management unit calculates the overall urgency of response for each monitoring point based on the risk deviation of each monitoring point, as well as the personnel density level and material importance level of the area where the monitoring point is located, and determines the response priority based on the overall urgency of response.

7. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 6, characterized in that, When calculating the overall response urgency, the priority management unit uses the risk deviation as the basic urgency indicator and applies the personnel density level and the material importance level to weight and correct the basic urgency indicator to obtain the overall response urgency.

8. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 6, characterized in that, The response scheduling module also includes a resource adaptation unit; The resource adaptation unit acquires the resource status information of available fire protection facilities within the fire monitoring area, and matches the target fire protection facility from the available fire protection facilities according to the differentiated response strategy and the response priority, and generates control instructions for the target fire protection facility.

9. A method for implementing intelligent fire monitoring and early warning based on the Internet of Things, executed in the system described in any one of claims 1-8, comprising the following steps: S1: Collect environmental status data from multiple monitoring points within the fire monitoring area through the sensor detection module, and generate the status time sequence of the corresponding monitoring points; S2: The state time sequence of each monitoring point is mapped to a state feature vector in a high-dimensional feature space through the feature mapping module, and the state feature vector is compared with the preset standard safety feature vector to calculate the risk deviation of each monitoring point; S3: Based on the risk deviation of each monitoring point and the spatial topological relationship between the monitoring points, the risk identification module constructs a global risk distribution map of the fire monitoring area and determines the risk evolution trend based on the global risk distribution map. S4: The response scheduling module generates differentiated response strategies for different monitoring points based on the risk evolution trend, and performs hierarchical control of fire protection facilities according to response priority.

10. The intelligent fire monitoring and early warning system based on the Internet of Things according to claim 9, characterized in that, In step S3, the spatial gradient change and time change rate of risk intensity are calculated based on the global risk distribution map at the current time and the previous time. The direction of risk spread is determined based on the spatial gradient change, the rate of risk spread is determined based on the time change, and the risk clustering area is determined based on the spatial clustering degree of monitoring points whose risk deviation exceeds a preset threshold.

Images