Intelligent alarm method, device and equipment of multifunctional gateway and storage medium

Abstract

The invention relates to the technical field of gateway equipment data processing, and provides an intelligent alarm method, device and equipment of a multifunctional gateway and a storage medium, and the method comprises the steps: obtaining smoke concentration data and door magnetic state data of the intelligent gateway equipment to generate a corresponding alarm signal, carrying out the noise filtering and time window analysis of the alarm signal, and obtaining the smoke concentration data and the door magnetic state data of the intelligent gateway equipment. The alarm intensity index and the alarm duration index are obtained, the alarm intensity index and the alarm duration index are utilized to sort the alarm priorities, an alarm scheme is obtained, and a fire-fighting response instruction is generated based on the alarm scheme. Smoke concentration data and door magnetic state data are collected for real-time analysis and association processing, a fire-fighting response instruction is generated, the alarm accuracy and response efficiency are improved, potential safety hazards caused by false alarm and leakage alarm are reduced, and the problems that in practical application, a current alarm system is poor in adaptability in complex scenes, and fire-fighting performance is poor are solved. The processing of a plurality of alarm signals is not accurate enough, and false alarm or missing alarm occurs.

Description

Technical Field

[0001] The present application relates to the technical field of gateway device data processing, and in particular to an intelligent alarm method, apparatus, device and storage medium for a multifunctional gateway. Background Art

[0002] With the rapid development of smart cities and the Internet of Things (IoT) technologies, intelligent fire protection systems are becoming a critical component of modern buildings and public safety. Traditional fire alarm systems utilize a discrete device architecture, deploying firefighting equipment such as manual call points, audible and visual alarms, and smoke detectors independently. These systems rely on physical wiring and independent power supplies. While this architecture ensures functionality and reliability to a certain extent, it is becoming increasingly inefficient in the face of emerging smart fire protection requirements and struggles to meet the demands for rapid deployment and efficient operations and maintenance.

[0003] Among the relevant technical means, many intelligent fire protection gateway devices use independent wireless sensors and alarm modules, which are connected to the central control platform through wireless communication protocols. They have remote monitoring, data transmission and alarm functions, can monitor environmental changes on site in real time, and analyze data through the cloud platform to automatically trigger alarm signals. They can realize basic remote alarm and equipment status monitoring, and improve the real-time response capability and management efficiency of the fire protection system.

[0004] Regarding the above technical solution, although the existing technology uses wireless sensors and integrated communication technology to achieve remote monitoring and intelligent alarm to a certain extent, in actual applications, the current alarm system has poor adaptability in complex scenarios, and the processing of multiple alarm signals is not accurate enough, resulting in false alarms or missed alarms, leading to waste of resources and safety hazards. Summary of the Invention

[0005] In order to improve the current alarm system in actual applications, which has poor adaptability in complex scenarios, is not accurate enough in processing multiple alarm signals, and causes false alarms or missed alarms, this application provides an intelligent alarm method, device, equipment and storage medium for a multi-functional gateway.

[0006] The present invention provides an intelligent alarm method for a multifunctional gateway, which is applied to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor, including: obtaining smoke concentration data and door magnetic status data of the intelligent gateway device, performing real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and correlating the smoothed smoke concentration data with the door magnetic status data to obtain a potential fire risk data set; performing location identification and level evaluation on the potential fire risk data set to obtain location information and risk level, performing urgency analysis on the location information to obtain an urgency priority, and correcting the risk level using the urgency priority to obtain a corrected risk level; generating a corresponding alarm signal according to the corrected risk level, performing noise filtering and time window analysis on the alarm signal to obtain an alarm data set; extracting an alarm intensity index and an alarm duration index according to the alarm data set, and sorting the alarm priorities in the alarm data set using the alarm intensity index and the alarm duration index to obtain a priority sorting result; generating a corresponding alarm plan according to the priority sorting result, and generating a fire response instruction based on the alarm plan.

[0007] As a preferred solution, the steps of obtaining smoke concentration data and door magnetic status data of the intelligent gateway device, performing real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and correlating the smoothed smoke concentration data with the door magnetic status data to obtain a potential fire risk data set include: obtaining smoke concentration data and door magnetic status data of the intelligent gateway device, performing smoothing filtering on the smoke concentration data to obtain smoothed smoke concentration data, performing change rate extraction on the smoothed smoke concentration data to obtain change rate data; using the change rate data and the door magnetic status data to perform joint feature construction to obtain a risk feature group and an abnormal opening and closing event group, performing trend fitting on the risk feature group to obtain a concentration change model, using the concentration change model to perform data mapping on the abnormal opening and closing event group to obtain a gating trigger event group and a corresponding smoke abnormal event group; performing pattern matching analysis on the gating trigger event group and the corresponding smoke abnormal event group to obtain potential fire warning events, and generating a potential fire risk data set based on the potential fire warning events.

[0008] As a preferred solution, the steps of using the change rate data and the door magnetic state data to perform joint feature construction to obtain a risk feature group and an abnormal opening and closing event group, performing trend fitting on the risk feature group to obtain a concentration change model, and using the concentration change model to perform data mapping on the abnormal opening and closing event group to obtain a gate trigger event group and a corresponding smoke abnormal event group include: performing correlation analysis on the change rate data and the door magnetic state data to obtain a joint feature of the change rate and door magnetic opening and closing to construct a risk feature group, analyzing a pattern related to the risk feature group and fire risk to obtain a risk pattern set; performing trend analysis on the door magnetic state data based on the risk pattern set to obtain an opening and closing state trend, and generating an abnormal opening and closing event group based on the opening and closing state trend; performing trend fitting on the risk feature group to obtain a concentration change model, and using the concentration change model to perform mapping processing on the abnormal opening and closing event group to obtain each gate trigger event and the corresponding smoke concentration change event; and performing threshold screening on each gate trigger event and the smoke concentration change event to screen out gate trigger event groups and smoke abnormal event groups that meet a preset risk threshold.

[0009] As a preferred solution, the steps of performing location identification and level assessment on the potential fire risk data set to obtain location information and risk level, performing urgency analysis on the location information to obtain an urgency priority, and correcting the risk level using the urgency priority to obtain a corrected risk level include: tracing the intelligent gateway device based on the potential fire risk data set to obtain the traced intelligent gateway device, and obtaining the location information of the traced intelligent gateway device; inputting the potential fire risk data set into a preset risk level assessment table to obtain a corresponding risk level; The location information is parsed to obtain floor information and equipment location, an urgency analysis is performed on the floor information and the equipment location to obtain an urgency priority, and the risk level is corrected using the urgency priority to obtain a corrected risk level.

[0010] As a preferred solution, the steps of generating a corresponding alarm signal according to the corrected risk level, performing noise filtering and time window analysis on the alarm signal, and obtaining an alarm data set include: applying a timestamp algorithm to divide the time window of the corrected risk level to obtain an alarm signal, and generating a preliminary alarm pulse sequence and an alarm trigger identifier according to the alarm signal; performing time period smoothing processing on the preliminary alarm pulse sequence to obtain an alarm stability parameter, and using the alarm stability parameter to classify and aggregate the alarm trigger identifier to obtain an alarm continuity group and an alarm intermittent group; performing multi-band noise filtering on the alarm continuity group to obtain a main alarm signal, and performing time window segmentation processing on the main alarm signal to obtain an alarm peak sequence within a time period; matching and analyzing the alarm peak sequence with the alarm intermittent group to obtain a continuous alarm event group, performing comprehensive intensity estimation on the continuous alarm event group to obtain an alarm intensity index and time coverage, and generating an alarm data set based on the alarm intensity index and the time coverage.

[0011] As a preferred solution, the steps of extracting the alarm intensity index and the alarm duration index according to the alarm data set, sorting the alarm priorities in the alarm data set using the alarm intensity index and the alarm duration index, and obtaining priority sorting results include: extracting the alarm intensity index and the alarm duration index through the alarm data set, dividing the alarm intensity index into graded intervals to obtain intensity segmentation groups and abnormal intensity subgroups, statistically aggregating the alarm duration index to obtain duration distribution groups and instantaneous alarm subgroups; establishing an intensity-time cross-matrix using the intensity segmentation group and the duration distribution group, calculating the comprehensive risk value of each alarm signal according to the intensity-time cross-matrix, performing priority sorting according to the comprehensive risk value, and obtaining a preliminary alarm priority sorting result; cross-validating the abnormal intensity subgroup and the instantaneous alarm subgroup to obtain a high-risk alarm group, performing weighted processing on the high-risk alarm group to obtain a weighted priority sequence; and weighting the preliminary alarm priority sorting result using the weighted priority sequence to obtain a priority sorting result.

[0012] As a preferred solution, the steps of generating a corresponding alarm scheme according to the priority sorting result and generating a fire response instruction based on the alarm scheme include: extracting the highest priority alarm group and the second highest priority alarm group through the priority sorting result, performing response strategy selection processing on the highest priority alarm group to obtain a first response strategy group and a backup response strategy group; performing an impact area expansion analysis on the second highest priority alarm group to obtain an extended area group, performing response action mapping based on the first response strategy group and the extended area group to obtain a response action list and an execution priority table; performing resource availability matching on the response action list to obtain a resource allocation scheme, dynamically integrating the backup response strategy group and the resource allocation scheme to obtain a dynamic response switching table; generating an alarm scheme according to the execution priority table and the dynamic response switching table, and inputting a preset fire cloud platform based on the alarm scheme to generate a corresponding fire response instruction.

[0013] The present application also provides an intelligent alarm device for a multifunctional gateway, which is applied to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor, the intelligent alarm device comprising: an acquisition module, configured to acquire smoke concentration data and door magnetic status data of the intelligent gateway device, perform real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and perform correlation analysis on the smoothed smoke concentration data and the door magnetic status data to obtain a potential fire risk data set; a correction module, configured to perform location identification and level assessment on the potential fire risk data set to obtain location information and risk level, perform urgency analysis on the location information to obtain an urgency priority, and correct the risk level using the urgency priority to obtain a corrected risk level; an analysis module, configured to generate a corresponding alarm signal according to the corrected risk level, perform noise filtering and time window analysis on the alarm signal to obtain an alarm data set; a sorting module, configured to extract an alarm intensity index and an alarm duration index from the alarm data set, and use the alarm intensity index and the alarm duration index to sort the alarm priorities in the alarm data set to obtain a priority sorting result; and a generation module, configured to generate a corresponding alarm scheme according to the priority sorting result, and generate a fire response instruction based on the alarm scheme.

[0014] The present application also provides an electronic device including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the intelligent alarm method of the multi-functional gateway described in any one of the above is implemented.

[0015] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the intelligent alarm method for the multi-functional gateway as described in any one of the above.

[0016] Compared with the existing technology, the present application has the following beneficial effects: strong adaptability and low false alarm rate. Through the multifunctional intelligent gateway device, the smoke concentration data and door magnetic status data are integrated, and the potential fire risk is effectively identified and predicted through real-time analysis and correlation processing; through location identification, risk level assessment and correction of urgency priority, the urgency of the fire can be accurately assessed and an accurate alarm signal can be generated. Further noise filtering and time window analysis ensure the accuracy of the alarm signal, and priority sorting based on alarm intensity and duration indicators can effectively identify and respond to high-risk events; by generating a corresponding alarm plan and generating a fire response instruction based on the plan, it ensures that the fire protection system can respond quickly, reduce the losses caused by fire accidents, improve the accuracy and response efficiency of the alarm, and effectively reduce the safety hazards caused by false alarms and missed alarms. In actual applications, the current alarm system has poor adaptability in complex scenarios, and the processing of multiple alarm signals is not accurate enough, resulting in false alarms or missed alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] The structures, proportions, sizes, etc. depicted in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not intended to limit the conditions under which the present invention can be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportional relationships, or adjustments in size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and objectives that can be achieved by the present invention.

[0019] Figure 1 1 is a flow chart of an intelligent alarm method for a multifunctional gateway provided by an embodiment of the present invention; Figure 2 This is a schematic block diagram of the structure of an intelligent alarm device of a multifunctional gateway provided by an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the intelligent alarm device of the multifunctional gateway provided by an embodiment of the present invention; Figure 4It is a schematic block diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0020] Description of reference numerals: 10. Intelligent alarm device of multifunctional gateway; 11. Acquisition module; 12. Correction module; 13. Analysis module; 14. Sorting module; 15. Generation module; 20. Electronic device; 21. Memory; 22. Processor. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0023] It should also be understood that the terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should be further understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] The technical solution of the present invention will be further described below with reference to the accompanying drawings and through specific implementation methods.

[0026] Example 1: like Figure 1 As shown, the present application provides an intelligent alarm method for a multifunctional gateway, which is applied to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor, including steps S100 to S500.

[0027] Step S100: Obtain smoke concentration data and door magnetic status data from the smart gateway device, perform real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and perform correlation analysis on the smoothed smoke concentration data and the door magnetic status data to obtain a potential fire risk data set.

[0028] In this step, the intelligent gateway device uses its integrated wireless sensors to acquire smoke concentration data and door sensor status data. Specifically, smoke concentration data is collected in real time and processed using a filtering algorithm to generate smoothed data to reduce noise interference. Door sensor status data is acquired in real time by sensors detecting the door's open or closed state. Correlation analysis of these two data sources, combined with changes in the door sensor status and fluctuations in smoke concentration, can accurately predict potential fire risks.

[0029] For example, if a door magnetic sensor detects an abnormally opened door and the smoke concentration data fluctuates at the same time, it is judged as a potential fire risk and a corresponding risk data set is generated.

[0030] Step S200: perform location identification and level assessment on the potential fire risk data set to obtain location information and risk level, perform urgency analysis on the location information to obtain urgency priority, and use the urgency priority to correct the risk level to obtain a corrected risk level.

[0031] This step first analyzes the location-related information in the potential fire risk dataset to identify the location and obtain location information. Specifically, the intelligent gateway device uses its built-in positioning module (such as GPS and floor number) to determine the location of the fire. It then compares this location with a pre-set risk level assessment table to assess the severity and urgency of the current risk.

[0032] For example, if abnormal smoke concentrations and a door magnetic sensor are detected, the device will assess the risk level and calculate an urgency priority based on the floor, location, and surrounding conditions. If the urgency analysis result is high, the original risk level will be revised based on the priority to obtain a more accurate risk level.

[0033] Step S300: Generate a corresponding alarm signal according to the corrected risk level, perform noise filtering and time window analysis on the alarm signal, and obtain an alarm data set.

[0034] In this step, the intelligent gateway device generates a corresponding alarm signal based on the revised risk level. Specifically, the alarm signal undergoes real-time processing, including noise filtering and time window analysis. Noise filtering removes environmental interference and unnecessary alarm signals, while time window analysis processes the alarm signal in a sequential manner to ensure its effectiveness and timeliness.

[0035] For example, if multiple sensors trigger alarm signals simultaneously within a certain period of time, time window analysis can focus on the continuously occurring alarm signals to ensure the accuracy of the alarm signals.

[0036] Step S400: extracting an alarm intensity index and an alarm duration index according to the alarm data set, and using the alarm intensity index and the alarm duration index to sort the alarm priorities in the alarm data set to obtain a priority sorting result.

[0037] In this step, we analyze the intensity and duration metrics in the alarm dataset to further optimize the prioritization of alarm signals. Specifically, we use the intensity metric to assess the urgency of the alarm signal, while the duration metric assesses the duration of the alarm. These two metrics are combined to prioritize the alarm signals in the alarm dataset.

[0038] For example, when the intensity of an alarm signal is high and the duration is long, it is evaluated as a more urgent event and assigned a higher priority.

[0039] Step S500: Generate a corresponding alarm plan according to the priority sorting result, and generate a fire response instruction based on the alarm plan.

[0040] In this step, a specific alarm response plan is generated based on the previously generated priority ranking results. This plan allocates resources based on alarm priority and determines the order in which alarms should be responded to. Specifically, based on priority, the most urgent alarm signals are responded to first, followed by other signals as appropriate. Simultaneously, fire response instructions are generated based on the alarm plan to guide on-site firefighters in their response.

[0041] For example, if an alarm signal is assessed as the highest priority, on-site firefighters are immediately notified and instructed to take the most direct fire extinguishing or evacuation measures.

[0042] In this embodiment, smoke concentration data and door sensor status data are acquired through an intelligent gateway device and analyzed in real time to produce smoothed smoke concentration data. Subsequently, the smoothed smoke concentration data is correlated with the door sensor status data to produce a potential fire risk dataset. Next, the potential fire risk dataset is subjected to location identification and level assessment to obtain location information and risk level. The location information is then subjected to urgency analysis to determine the urgency priority. The risk level is then modified using this priority to obtain a corrected risk level. Based on the corrected risk level, a corresponding alarm signal is generated. The alarm signal is then subjected to noise filtering and time window analysis to produce an alarm dataset. Alarm intensity and duration indicators are then extracted from the alarm dataset and used to prioritize the alarms. Finally, an alarm plan is generated, and fire response instructions are generated based on this plan. Through smoothing and multi-level data analysis, interference factors can be removed and the urgency of the fire risk can be identified, thereby optimizing the alarm signal generation process. Combined with the priority sorting of alarm intensity and duration indicators, it can give priority to responding to the most urgent and high-risk alarm events among multiple alarm signals, which not only improves the accuracy and response efficiency of alarm signals, but also effectively reduces the safety hazards caused by false alarms and missed alarms, ensuring that the fire protection system can respond quickly and effectively. It is especially suitable for the intelligent transformation of old buildings and distributed fire monitoring systems, improving the current alarm system in actual applications. The adaptability of the system in complex scenarios is poor, the processing of multiple alarm signals is not accurate enough, and false alarms or missed alarms occur.

[0043] Example 2: In step S100, the smoke concentration data and door magnetic status data of the intelligent gateway device are obtained, the smoke concentration data is smoothed and filtered to obtain smoothed smoke concentration data, and the change rate of the smoothed smoke concentration data is extracted to obtain change rate data.

[0044] The intelligent gateway device's built-in sensors continuously acquire smoke concentration data and door sensor status data. Specifically, after smoke concentration data is collected, a smoothing filter algorithm (such as a sliding average or weighted filter) is first applied to remove short-term noise caused by device failures or external environmental interference, ensuring data smoothness and stability. Next, the smoke concentration data is analyzed for rate of change, calculating the rate of change to identify concentration trends.

[0045] For example, if the smoke concentration increases sharply in a short period of time, after smoothing, the concentration fluctuation is effectively reduced, and the rate of change extraction can capture the trend of concentration changes, facilitating subsequent judgment of the possibility of fire.

[0046] The change rate data and door magnetic status data are used to construct joint features to obtain the risk feature group and the abnormal opening and closing event group. The risk feature group is trend fitted to obtain the concentration change model. The concentration change model is used to perform data mapping on the abnormal opening and closing event group to obtain the gate trigger event group and the corresponding smoke abnormality event group.

[0047] By jointly analyzing change rate data and door sensor status data, a comprehensive risk signature group is constructed. The relationship between these two data sets is analyzed to extract characteristics that indicate fire risk. Specifically, by setting association rules or models (such as time series analysis models), potential correlations between changes in door sensor status and smoke concentration are identified to generate a risk signature group. Simultaneously, based on the risk signature group, trend analysis of door sensor status changes is performed to identify abnormal opening and closing event groups, which are then used to construct a concentration change model.

[0048] For example, if the door sensor status indicates that the door is abnormally opened and closed suddenly, and the rate of change of the smoke concentration also fluctuates greatly, the system will mark this event as high risk and perform further data mapping in the concentration change model to obtain the gate trigger event group and smoke anomaly event group related to this event.

[0049] The specific steps of using the change rate data and the door magnetic state data to jointly construct features to obtain the risk feature group and the abnormal opening and closing event group, performing trend fitting on the risk feature group to obtain the concentration change model, and using the concentration change model to perform data mapping on the abnormal opening and closing event group to obtain the gate trigger event group and the corresponding smoke abnormality event group include: Correlation analysis is performed on the change rate data and the door magnet status data to obtain the joint features of the change rate and door magnet opening and closing to construct a risk feature group. The patterns related to the risk feature group and fire risk are analyzed to obtain the risk pattern set.

[0050] Through correlation analysis methods, such as Pearson correlation coefficient calculation, we analyze whether there is a significant correlation between the change rate of smoke concentration and the change of door magnetic state, so as to construct a risk feature group.

[0051] For example, if the rate of change of smoke concentration fluctuates greatly in a short period of time, and the door magnetic state also changes frequently between on and off, then the correlation between the two data is high, indicating that the possibility of fire is high, thus providing a basis for constructing a risk feature group.

[0052] Based on the risk pattern set, the door magnetic state data is trend analyzed to obtain the opening and closing state trend, and an abnormal opening and closing event group is generated according to the opening and closing state trend.

[0053] By performing trend analysis based on door magnetic status data, we can observe the changing patterns of the door's opening and closing status over a period of time and identify trends in this state. Specifically, through time series analysis, we extract data such as the door magnetic switching frequency and duration to determine whether there are any abnormal opening and closing patterns, and then generate abnormal opening and closing event groups.

[0054] For example, if the door sensor status opens and closes frequently and irregularly within a specific time period, the system will treat these opening and closing states as abnormal opening and closing events and add them to the abnormal opening and closing event group. This information helps determine whether there is a potential fire risk.

[0055] The risk feature group is trend-fitted to obtain a concentration change model, which is then used to map the abnormal opening and closing event group to obtain each gate trigger event and the corresponding smoke concentration change event.

[0056] By performing trend fitting on the risk signature group, a concentration change model is generated to represent the changing trend of smoke concentration. Specifically, a fitting algorithm (such as linear regression or exponential smoothing) is used to model the changing trend of smoke concentration data and analyze the regularity of concentration changes. This concentration change model is then used to map the data of the abnormal opening and closing event group, determining the relationship between each gate trigger event and the corresponding smoke concentration change event.

[0057] For example, if the occurrence of an abnormal opening and closing event coincides with a significant change in smoke concentration in a short period of time, the system will mark the event as a gate trigger event, associate it with the smoke concentration change event, and generate specific fire warning data.

[0058] Threshold screening is performed on each gate trigger event and smoke concentration change event to screen out the gate trigger event group and smoke abnormality event group that meet the preset risk threshold.

[0059] By setting preset thresholds for each door control trigger event and smoke concentration change event, and filtering these events, we ensure that only high-risk events that meet the threshold requirements are further processed. Specifically, by setting smoke concentration thresholds and door sensor status change frequency thresholds, we filter out events that meet the conditions for processing.

[0060] For example, if the smoke concentration exceeds the set danger threshold and the duration of the abnormal door magnetic state exceeds the set value, this event meets the risk threshold and is considered a high-risk fire event, entering the subsequent fire warning processing process.

[0061] The gate trigger event group and the corresponding smoke abnormality event group are subjected to pattern matching analysis to obtain potential fire warning events, and a potential fire risk dataset is generated based on the potential fire warning events.

[0062] By performing pattern matching analysis on the gate trigger event group and the smoke anomaly event group, we determine whether there are highly correlated event combinations, thereby identifying potential fire warning events. Specifically, by setting matching rules (such as time matching and concentration matching), we combine qualified gate trigger events and smoke anomaly events to generate potential fire warning events.

[0063] For example, when the door magnetic sensor detects that the door is abnormally opened and the smoke concentration data increases abnormally at the same time, the system generates a potential fire warning event through pattern matching analysis and incorporates it into the potential fire risk dataset.

[0064] The relationship between smoke concentration data and door sensor status data is quantified through statistical correlation analysis (such as the Pearson correlation coefficient and mutual information). Specifically, by calculating the time difference between the changing trend of each data point and the change in the door sensor status, we can identify which smoke concentration fluctuations are highly correlated with the door's opening and closing status (abnormal opening and closing). This allows us to establish a correlation model between the two. When the changes in smoke concentration and door sensor status match a certain pattern (for example, a door suddenly opens in the presence of high smoke concentration), the correlation model identifies this pattern as a potential fire risk. Pattern recognition techniques, such as dynamic time warping (DTW), can be used to match continuous time series and identify dangerous patterns where smoke concentration and door sensor status co-occur.

[0065] Specifically, the system acquires time series data on smoke concentration and door sensor status, uses time windows to segment and analyze the changing trends of each data point over different time periods, and calculates the Pearson correlation coefficient within each time window to measure the relationship between smoke concentration and door sensor status. The system then uses thresholds or machine learning algorithms (such as classification trees or support vector machines) to determine when smoke concentration fluctuates abnormally and the door sensor status is abnormally open or closed, and flags this event as a potential fire risk.

[0066] For example, a potential fire risk dataset contains the following fields: timestamp, smoke concentration, door sensor status, correlation coefficient, and risk level. Each data record reflects the changes in smoke concentration and door sensor status. The correlation coefficient quantitatively describes the relationship between the two, and the risk level determines whether a fire risk is present based on a threshold.

[0067] In step S200, the smart gateway device is traced based on the potential fire risk data set to obtain the traced smart gateway device, and the location information of the traced smart gateway device is obtained.

[0068] By analyzing the event characteristics in the potential fire risk dataset, the system first traces the relevant smart gateway devices to determine their specific locations. Specifically, during the traceability process, the network node where the data originated is traced back, combined with sensor identification information and historical data, to accurately identify the relevant devices and extract their geographic location information from the device database.

[0069] For example, if the device receives data from a smoke concentration sensor and a door magnetic sensor, it can trace the data based on the timestamp and device ID and ultimately locate the specific device location, such as the floor or room number.

[0070] The potential fire risk data set is input into the preset risk level assessment table to obtain the corresponding risk level.

[0071] By comparing the potential fire risk dataset with a pre-set risk level assessment table, the system can perform a preliminary risk assessment for each event based on fire risk indicators in the data (such as smoke concentration and door sensor status). Specifically, the system assigns a preliminary risk level to each event based on the risk thresholds in the assessment table.

[0072] The location information is parsed to obtain floor information and equipment location, the floor information and equipment location are analyzed for urgency to obtain urgency priority, and the risk level is corrected using the urgency priority to obtain a corrected risk level.

[0073] By analyzing the acquired device location information, the system extracts floor information and device location information to further assess the risk level of the area. Specifically, by analyzing the floor information, the system can determine the area where the incident occurred. It then analyzes the urgency of the fire scenario based on regional characteristics (such as evacuation routes and floor heights), revising the initial risk level to determine the final risk level.

[0074] The location information of the smart gateway device is used to resolve the floor and room number. This step can be done by reading the device's GPS positioning information or combining it with the building's structural diagram to generate floor and room identification.

[0075] Based on the floor information and the characteristics of the fire scene, a weighted model can be used to perform emergency priority analysis: Floor height: Fires on high floors are more difficult to rescue and should be given a higher emergency priority.

[0076] Evacuation route: If the equipment is located in an area close to a fire evacuation route or exit, the urgency priority may be relatively low.

[0077] Regional flammability: Combined with environmental factors, such as the storage area of ​​flammable materials, the urgency of the area is further derived.

[0078] Each floor or area is assigned a weighted score based on the aforementioned factors (such as floor height, distance to evacuation routes, and flammability). This score, combined with the equipment location and fire risk level, derives the area's urgency priority. For example, a high-rise fire might have an urgency priority of 8, a flammable area a 9, and an area far from evacuation routes a 7.

[0079] For example, the data structure after urgency analysis is: area ID, floor number, urgency priority, and evaluation factors. The urgency priority is output through a weighted algorithm and ultimately serves as the basis for risk level correction.

[0080] Furthermore, pattern matching techniques and threshold screening can be used in matching and analyzing alarm datasets to quantify alarm intensity and duration. Time series matching algorithms (such as Dynamic Time Warping (DTW)) can be used to identify whether alarm signals are continuous or intermittent, thereby determining whether they represent a persistent fire hazard or a short-lived false alarm. Intensity estimation can be achieved by combining alarm intensity indicators (such as the rate of change of smoke concentration and door sensor switching frequency) with alarm duration (such as the time period exceeding the threshold) to produce an alarm intensity index. This index reflects the severity of the event. The proportion of alarm signal durations can be used to assess the impact of the alarm signal, ensuring that when multiple alarm signals occur simultaneously, those with a wide impact are prioritized.

[0081] For example, an alarm dataset may include fields such as timestamp, alarm intensity, alarm duration, alarm type, alarm priority, etc., with the alarm intensity index and time coverage being stored as additional fields.

[0082] The alarm intensity index can be calculated using a weighted average algorithm, taking into account concentration changes, time duration, and volatility. The comprehensive score can be used to prioritize alarm events based on the alarm intensity index and time coverage, selecting the most urgent events for response.

[0083] In step S300, a time stamp algorithm is applied to divide the corrected risk level into time windows to obtain an alarm signal, and a preliminary alarm pulse sequence and an alarm trigger identifier are generated according to the alarm signal.

[0084] By applying a timestamp algorithm, the system divides the corrected risk level data into time windows, ensuring that alarm signals are triggered at the precise moment. Specifically, by assigning a timestamp to each data collection point, the system can clearly determine the timing of data collection and divide the time windows based on this timing information, allowing subsequent alarm signals to be processed in chronological order and avoiding interference between multiple signals.

[0085] For example, when the smoke concentration changes at a high rate and the door magnetic state is abnormal within a certain period of time, the system will divide the data within this period into a time window based on the timestamp, generate the corresponding alarm signal pulse sequence, and identify the trigger time point of the signal.

[0086] The preliminary alarm pulse sequence is smoothed over a certain time period to obtain the alarm stability parameter. The alarm trigger identifiers are classified and aggregated using the alarm stability parameter to obtain the alarm continuous group and the alarm intermittent group.

[0087] By smoothing the initial alarm pulse sequence over time, the system reduces short-term fluctuations and unnecessary signal interference, ensuring alarm signal stability. Specifically, a smoothing filter algorithm (such as the weighted moving average) is employed to smooth each time point in the alarm pulse sequence, thereby generating alarm stability parameters. Based on these stability parameters, the system further categorizes alarm signals into persistent and intermittent groups.

[0088] For example, if the smoke concentration continues to increase over a period of time, the alarm signal during this period will be classified as the continuous alarm group; if the door magnetic state shows short and irregular changes, the system will classify the signal as the intermittent alarm group.

[0089] The alarm persistence group is subjected to multi-band noise filtering to obtain the main alarm signal, and the main alarm signal is subjected to time window segmentation processing to obtain the alarm peak sequence within the time period.

[0090] By applying multi-band noise filtering to the alarm persistence group, the system eliminates background noise from the signal and extracts the highly reliable primary alarm signal. Specifically, by setting up a multi-band noise filter, the signal is frequency-separated, filtering out low-frequency and high-frequency noise separately while retaining the valid alarm signal within the frequency band. Subsequently, the primary alarm signal is segmented into time windows to further analyze the alarm signal's changing trends over different time periods and generate a sequence of alarm peaks.

[0091] For example, if the smoke concentration continues to rise over a long period of time, the system will extract the main alarm signal after multi-band noise filtering, and divide these signals into time periods to generate an alarm peak sequence in each time period to ensure accurate judgment of the alarm signal.

[0092] The alarm peak sequence is matched and analyzed with the alarm discontinuity group to obtain the continuous alarm event group. The comprehensive intensity of the continuous alarm event group is estimated to obtain the alarm intensity index and time coverage. The alarm data set is generated based on the alarm intensity index and time coverage.

[0093] By matching and analyzing alarm peak sequences with alarm discontinuity groups, the system can identify alarm signals that meet the characteristics of continuous alarm events. Specifically, using time series analysis techniques, the system compares the alarm peak sequence with the signals in the discontinuity group to identify whether there are continuous alarm patterns, thus forming a continuous alarm event group. The system then performs a comprehensive intensity estimation on the continuous alarm event group, calculating the alarm intensity index and time coverage, and uses this as the basis to generate the final alarm data set.

[0094] For example, if the system triggers alarm signals multiple times within a certain time period and the alarm intensity gradually increases, the system will identify these signals as a continuous alarm event group, and calculate the alarm intensity index and coverage time based on the alarm intensity and time coverage to generate the corresponding alarm data set.

[0095] In step S400, the alarm intensity index and the alarm duration index are extracted from the alarm data set, the alarm intensity index is divided into graded intervals to obtain intensity segment groups and abnormal intensity subgroups, and the alarm duration index is statistically aggregated to obtain duration distribution groups and instantaneous alarm subgroups.

[0096] By extracting the intensity and duration metrics of each alarm signal from the alarm dataset, the system can comprehensively assess the severity of the alarm signal. Specifically, the system first analyzes the intensity of the alarm signal to generate an intensity index, which is used to classify the alarm signal into multiple levels (for example, low, medium, and high intensity). Then, by statistically analyzing the duration of the alarm signal, the system generates a duration index, which classifies the alarm signal into short-duration and long-duration alarm signals.

[0097] For example, when processing a group of alarm signals, the system finds that some alarm signals have greater intensity and longer duration. These signals will be classified as high-intensity alarm signals and included in the intensity segment group and duration distribution group, while those with lower intensity and shorter duration will be classified as instantaneous alarm subgroups.

[0098] The intensity segmentation group and duration distribution group are used to establish an intensity-time intersection matrix. The comprehensive risk value of each alarm signal is calculated based on the intensity-time intersection matrix. Priority is sorted according to the comprehensive risk value to obtain the preliminary ranking result of the alarm priority.

[0099] By cross-processing the intensity segment groups and duration distribution groups, the system generates an intensity-time cross-matrix. Combining the intensity and duration information of each alarm signal, the system calculates the overall risk value for each alarm signal. Specifically, the system uses this cross-matrix to analyze the relationship between intensity and duration, forming a comprehensive assessment of the alarm signals. This is then used to prioritize the alarms and produce a preliminary ranking of their priorities.

[0100] For example, if an alarm signal has a high intensity and a long duration, the signal will occupy a higher position in the cross matrix and be given a higher priority when sorting. However, some alarm signals with lower intensity and shorter duration will be given a lower priority.

[0101] Cross-validation is performed on the abnormal intensity subgroup and the instantaneous alarm subgroup to obtain a high-risk alarm group, which is then weighted to obtain a weighted priority sequence.

[0102] By cross-validating the anomaly intensity subgroups with the instantaneous alarm subgroups, the system can identify high-risk alarm signals that are underdetected. Specifically, the system uses an algorithm to detect the correlation between anomaly intensity and instantaneous alarms, determining which alarm signals are more risky. It then weights these signals, increasing their weight in the final priority ranking.

[0103] For example, if among the alarm signals, some instantaneous alarm signals suddenly appear and are accompanied by large intensity fluctuations, these signals will be marked as high-risk signals and given higher priorities during weighted processing to ensure that these high-risk events can be handled in a timely manner.

[0104] The weighted priority sequence is used to weight the preliminary alarm priority sorting results to obtain the priority sorting results.

[0105] By further optimizing the preliminary alarm priority ranking results through the weighted priority sequence, the system can generate the final alarm priority ranking. Specifically, based on the preliminary ranking results, the system adjusts the ranking of each alarm signal according to the weighted priority sequence to ensure that the most urgent alarm signals are processed first.

[0106] For example, when processing a group of alarm signals, some signals are weighted as high priority. Although they are ranked low in the initial sorting, they will be processed in advance after weighting, thus ensuring that the fire response can be carried out quickly.

[0107] In step S500, the highest priority alarm group and the second highest priority alarm group are extracted based on the priority sorting result, and a response strategy selection process is performed on the highest priority alarm group to obtain a first response strategy group and a backup response strategy group.

[0108] By analyzing the priority ranking results, the system extracts the highest and second-highest priority alarm groups, prioritizing the most urgent alarm events. Specifically, based on the alarm priority ranking, the system assigns high-priority alarm signals to the primary response strategy group and the second-highest priority alarm signals to the backup response strategy group for subsequent response actions.

[0109] For example, if the system detects a sharp increase in smoke concentration and an abnormal door sensor status, and the signal is assessed as high priority, the system will place it in the first response strategy group and prepare to respond immediately, while the second-highest priority alarm signal, such as a short smoke fluctuation, will enter the backup response strategy group and wait for subsequent processing.

[0110] An impact area expansion analysis is performed on the second-highest priority alarm group to obtain an extended area group. Response actions are mapped based on the first response strategy group and the extended area group to obtain a response action list and an execution priority table.

[0111] By performing an extended impact analysis on the next-highest priority alarm group, the system considers the impact range of the alarm signal and calculates the affected area. Specifically, based on the alarm signal's location and the likelihood of fire spread (e.g., smoke diffusion models and thermodynamic models), the system infers the affected area and generates an expanded area group.

[0112] For example, if the alarm signal originates from a relatively closed room, the system will use the smoke diffusion model to infer the fire spread trend in that area, analyze other rooms or floors that may be affected, and add these areas to the extended area group. Then, based on the first response strategy group and the extended area group, the system generates a response action list, outlining the specific emergency response measures to be implemented and creating an execution priority table so that subsequent personnel can carry out the actions according to priority.

[0113] The response action list is matched with resource availability to obtain a resource allocation plan, and the backup response strategy group and the resource allocation plan are dynamically integrated to obtain a dynamic response switching table.

[0114] By matching resource availability against the response action list, the system allocates resources based on available resources (such as firefighting equipment, personnel, and rescue equipment), ensuring that all high-priority tasks are supported. Specifically, resource allocation is dynamically adjusted based on available resources, such as the number of fire extinguishers, rescue personnel, and fire truck locations, to best meet emergency response needs.

[0115] For example, when responding to high-priority alarms, priority is given to deploying nearby firefighting resources, such as fire extinguishers and firefighters; for alarm events in the backup response strategy group, the system puts them on standby until existing resources release spare capacity.

[0116] An alarm plan is generated according to the execution priority table and the dynamic response switching table, and the corresponding fire response instructions are generated by the preset fire cloud platform based on the alarm plan input.

[0117] By executing a priority table and a dynamic response switching table, the system comprehensively considers factors such as the alarm signal's priority, resource availability, and impact range to generate a final alarm response plan. Specifically, the system receives the alarm plan through the firefighting cloud platform and converts the specific implementation measures in the plan into firefighting response instructions, guiding on-site firefighters in carrying out specific emergency operations.

[0118] For example, when the alarm plan determines that a certain floor is a fire-stricken area and people need to be evacuated immediately, the fire cloud platform will immediately generate a fire response command, instructing on-site personnel to start evacuating and start the fire extinguishing system to operate.

[0119] In this embodiment, smoke concentration data and door magnetic status data are obtained from the intelligent gateway device, and the smoke concentration data is smoothed, filtered, and the rate of change is extracted. Joint feature construction is performed in combination with the door magnetic status data to obtain risk feature groups and abnormal opening and closing event groups. A concentration change model is then formed through trend fitting to accurately identify potential fire risks. Furthermore, the location information of the intelligent gateway device is obtained through traceability, floor information and device location are analyzed, and urgency priority analysis is performed. The risk level is corrected based on the risk level assessment table to improve the accuracy of alarm risk assessment. Then, a timestamp algorithm is applied to divide the time window, generating an alarm pulse sequence and an alarm trigger identifier. Through smoothing, noise filtering, and time window segmentation, the alarm peak sequence is extracted, and an alarm data set is generated based on the alarm intensity and duration. Based on this, the alarm intensity index and alarm duration index are extracted, and an intensity-time intersection matrix is ​​constructed to complete preliminary priority sorting. The final priority sorting result is obtained through cross-validation and weighted processing of abnormal data. Finally, a response strategy is generated based on the priority sorting result, resource matching and dynamic integration are performed to form an alarm plan, and fire response instructions are generated through the fire cloud platform, achieving intelligent, precise, and efficient fire warning and response.

[0120] Example 3: like Figure 2 and Figure 3 As shown, the present application also provides an intelligent alarm device 10 for a multifunctional gateway, which is applied to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor. The intelligent alarm device includes an acquisition module 11, a correction module 12, an analysis module 13, a sorting module 14 and a generation module 15.

[0121] The acquisition module 11 is mainly used to obtain the smoke concentration data and door magnetic status data of the intelligent gateway device, perform real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and perform correlation analysis on the smoothed smoke concentration data and the door magnetic status data to obtain a potential fire risk data set.

[0122] The correction module 12 is mainly used to perform location identification and level assessment on the potential fire risk data set to obtain location information and risk level, perform urgency analysis on the location information to obtain urgency priority, and use the urgency priority to correct the risk level to obtain the corrected risk level.

[0123] The analysis module 13 is mainly used to generate a corresponding alarm signal according to the corrected risk level, perform noise filtering and time window analysis on the alarm signal, and obtain an alarm data set.

[0124] The sorting module 14 is mainly used to extract the alarm intensity index and the alarm duration index according to the alarm data set, and use the alarm intensity index and the alarm duration index to sort the alarm priorities in the alarm data set to obtain a priority sorting result.

[0125] The generation module 15 is mainly used to generate a corresponding alarm plan according to the priority sorting result, and generate a fire response instruction based on the alarm plan.

[0126] In this embodiment, by applying the intelligent alarm method of the multifunctional gateway to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor, the intelligent alarm device acquires smoke concentration data and door magnetic status data in real time through the acquisition module 11, and performs smoothing and filtering on the data to obtain smoothed smoke concentration data. Specifically, the acquisition module 11 performs real-time analysis on the smoke concentration data, generates a data set after filtering, and performs correlation analysis with the door magnetic status data to generate a potential fire risk data set. Then, the correction module 12 performs location identification and urgency analysis on the data set, corrects the risk level, and ensures the accuracy of the alarm signal. The analysis module 13 performs noise filtering and time window analysis on the alarm signal, and the sorting module 14 prioritizes the alarm according to the alarm intensity and duration indicators, and finally generates a corresponding alarm plan. The fire response instruction is output through the generation module 15 to realize automated response processing.

[0127] It should be noted that those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described device and each module can refer to the corresponding processes in the aforementioned embodiment 1 and will not be repeated here.

[0128] Example 4: like Figure 4 As shown, the present application also provides an electronic device 20, including a memory 21 and a processor 22, the memory 21 stores a computer program that can be run on the processor 22, and when the processor 22 executes the computer program, the intelligent alarm method of the multi-functional gateway of Example 1 is implemented.

[0129] In this embodiment, through the synergistic effect of memory 21 and processor 22 in electronic device 20, a computer program enables processor 22 to execute the intelligent alarm method for the multifunctional gateway described in Example 1. Specifically, memory 21 stores a computer program that enables processor 22 to execute. Under the control of processor 22, this program completes a series of intelligent alarm processes, including the acquisition, analysis, processing, sorting, and response generation of smoke concentration and door magnetic status data. In this way, the intelligent alarm method fully leverages the advantages of computer hardware and programs, providing rapid response and guaranteed accuracy, meeting the demand for efficient and intelligent fire alarm systems in the Internet of Things era.

[0130] Example 5: The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the processor executes the intelligent alarm method of the multifunctional gateway as in Example 1.

[0131] In this embodiment, a computer program stored on a computer-readable storage medium, when executed by a processor, implements the intelligent alarm method for the multifunctional gateway described in Example 1. Specifically, the computer program, stored on the storage medium, guides the processor through the real-time collection, smoothing, correlation analysis, and risk assessment of smoke concentration and door magnetic status data. It then performs steps such as alarm signal generation, noise filtering, and time window analysis. This program enables the processor to rapidly respond to fire alarms in various application environments, providing efficient and reliable alarm data processing and ensuring the accuracy and timeliness of the intelligent fire protection system.

[0132] The structures, proportions, sizes, etc. depicted in the drawings of this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology. They are not intended to limit the conditions under which the present invention can be implemented and therefore have no substantive technical significance. Any structural modifications, changes in proportional relationships, or adjustments in size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and objectives that can be achieved by the present invention.

[0133] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multifunctional gateway intelligent alarm method, applied to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor, characterized in that: include: Obtaining smoke concentration data and door magnetic status data of the intelligent gateway device, performing real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and performing correlation analysis on the smoothed smoke concentration data and the door magnetic status data to obtain a potential fire risk dataset; Performing location identification and level assessment on the potential fire risk dataset to obtain location information and risk level, performing urgency analysis on the location information to obtain an urgency priority, and revising the risk level using the urgency priority to obtain a revised risk level; generating a corresponding alarm signal according to the corrected risk level, performing noise filtering and time window analysis on the alarm signal to obtain an alarm data set; extracting an alarm intensity index and an alarm duration index according to the alarm data set, and sorting the alarm priorities in the alarm data set using the alarm intensity index and the alarm duration index to obtain a priority sorting result; A corresponding alarm plan is generated according to the priority sorting result, and a fire response instruction is generated based on the alarm plan.

2. The intelligent alarm method of the multifunctional gateway according to claim 1 is characterized in that: The steps of obtaining smoke concentration data and door magnetic status data of the intelligent gateway device, performing real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and performing correlation analysis on the smoothed smoke concentration data and the door magnetic status data to obtain a potential fire risk data set include: Obtaining smoke concentration data and door magnetic status data of the intelligent gateway device, performing smoothing filtering on the smoke concentration data to obtain smoothed smoke concentration data, and performing change rate extraction on the smoothed smoke concentration data to obtain change rate data; Using the change rate data and the door magnetic state data to perform joint feature construction, a risk feature group and an abnormal opening and closing event group are obtained. Trend fitting is performed on the risk feature group to obtain a concentration change model. The concentration change model is used to perform data mapping on the abnormal opening and closing event group to obtain a gate trigger event group and a corresponding smoke abnormality event group. A pattern matching analysis is performed on the gate trigger event group and the corresponding smoke abnormality event group to obtain potential fire warning events, and a potential fire risk data set is generated based on the potential fire warning events.

3. The intelligent alarm method of the multifunctional gateway according to claim 2, characterized in that: The steps of using the change rate data and the door magnetic state data to perform joint feature construction to obtain a risk feature group and an abnormal opening and closing event group, performing trend fitting on the risk feature group to obtain a concentration change model, and using the concentration change model to perform data mapping on the abnormal opening and closing event group to obtain a gate triggering event group and a corresponding smoke abnormality event group include: Performing a correlation analysis on the change rate data and the door magnetic state data to obtain a joint feature of the change rate and the door magnetic opening and closing to construct a risk feature group, analyzing a pattern related to the risk feature group and the fire risk to obtain a risk pattern set; Performing trend analysis on the door magnetic state data based on the risk pattern set to obtain an opening and closing state trend, and generating an abnormal opening and closing event group according to the opening and closing state trend; Performing trend fitting on the risk feature group to obtain a concentration change model, and using the concentration change model to perform mapping processing on the abnormal opening and closing event group to obtain each gate triggering event and the corresponding smoke concentration change event; Threshold screening is performed on each of the gated trigger events and the smoke concentration change event to screen out a gated trigger event group and a smoke abnormality event group that meet a preset risk threshold.

4. The intelligent alarm method of the multifunctional gateway according to claim 1, characterized in that: The steps of performing location identification and level assessment on the potential fire risk dataset to obtain location information and risk level, performing urgency analysis on the location information to obtain an urgency priority, and correcting the risk level using the urgency priority to obtain a corrected risk level include: Tracing the smart gateway device based on the potential fire risk dataset to obtain the traced smart gateway device, and obtaining location information of the traced smart gateway device; Inputting the potential fire risk data set into a preset risk level assessment table to obtain a corresponding risk level; The location information is parsed to obtain floor information and equipment location, an urgency analysis is performed on the floor information and the equipment location to obtain an urgency priority, and the risk level is corrected using the urgency priority to obtain a corrected risk level.

5. The intelligent alarm method of the multifunctional gateway according to claim 1, characterized in that: The step of generating a corresponding alarm signal according to the corrected risk level, performing noise filtering and time window analysis on the alarm signal to obtain an alarm data set includes: Applying a timestamp algorithm to divide the corrected risk level into time windows to obtain an alarm signal, and generating a preliminary alarm pulse sequence and an alarm trigger identifier based on the alarm signal; Performing time period smoothing processing on the preliminary alarm pulse sequence to obtain an alarm stability parameter, and using the alarm stability parameter to classify and aggregate the alarm trigger identifiers to obtain an alarm continuous group and an alarm intermittent group; Perform multi-band noise filtering on the alarm persistence group to obtain a main alarm signal, perform time window segmentation processing on the main alarm signal to obtain an alarm peak sequence within a time period; The alarm peak sequence is matched and analyzed with the alarm interruption group to obtain a continuous alarm event group, and a comprehensive intensity estimation is performed on the continuous alarm event group to obtain an alarm intensity index and a time coverage ratio, and an alarm data set is generated based on the alarm intensity index and the time coverage ratio.

6. The intelligent alarm method of the multifunctional gateway according to claim 1, characterized in that: The step of extracting an alarm intensity index and an alarm duration index based on the alarm data set, and sorting the alarm priorities in the alarm data set using the alarm intensity index and the alarm duration index to obtain a priority sorting result includes: Extracting an alarm intensity index and an alarm duration index from the alarm data set, dividing the alarm intensity index into hierarchical intervals to obtain intensity segment groups and abnormal intensity subgroups, and statistically aggregating the alarm duration index to obtain duration distribution groups and instantaneous alarm subgroups; An intensity-time intersection matrix is ​​established using the intensity segment group and the duration distribution group, a comprehensive risk value of each alarm signal is calculated based on the intensity-time intersection matrix, and priority is sorted based on the comprehensive risk value to obtain a preliminary ranking result of the alarm priority; Cross-validating the abnormal intensity subgroup and the instantaneous alarm subgroup to obtain a high-risk alarm group, and performing weighted processing on the high-risk alarm group to obtain a weighted priority sequence; The weighted priority sequence is used to weight the preliminary alarm priority sorting result to obtain a priority sorting result.

7. The intelligent alarm method of the multifunctional gateway according to claim 1, characterized in that: The step of generating a corresponding alarm plan according to the priority sorting result and generating a fire response instruction based on the alarm plan includes: Extract the highest priority alarm group and the second highest priority alarm group through the priority sorting result, perform response strategy selection processing on the highest priority alarm group to obtain the first response strategy group and the backup response strategy group; Performing an impact area expansion analysis on the second-highest priority alarm group to obtain an extended area group, and performing response action mapping based on the first response strategy group and the extended area group to obtain a response action list and an execution priority table; Performing resource availability matching on the response action list to obtain a resource allocation plan, and dynamically integrating the backup response strategy group with the resource allocation plan to obtain a dynamic response switching table; An alarm plan is generated according to the execution priority table and the dynamic response switching table, and a preset fire cloud platform is input based on the alarm plan to generate a corresponding fire response instruction.

8. A multifunctional gateway intelligent alarm device, applied to an intelligent gateway device integrated with a smoke sensor and a door magnetic sensor, characterized in that: The intelligent alarm device comprises: an acquisition module, configured to acquire smoke concentration data and door magnetic status data of the intelligent gateway device, perform real-time analysis on the smoke concentration data to obtain smoothed smoke concentration data, and perform correlation analysis on the smoothed smoke concentration data and the door magnetic status data to obtain a potential fire risk dataset; a correction module, configured to perform location identification and level assessment on the potential fire risk dataset to obtain location information and risk level, perform urgency analysis on the location information to obtain an urgency priority, and correct the risk level using the urgency priority to obtain a corrected risk level; An analysis module, configured to generate a corresponding alarm signal according to the corrected risk level, and perform noise filtering and time window analysis on the alarm signal to obtain an alarm data set; a sorting module, configured to extract an alarm intensity index and an alarm duration index according to the alarm data set, and sort the alarm priorities in the alarm data set using the alarm intensity index and the alarm duration index to obtain a priority sorting result; A generation module is used to generate a corresponding alarm plan according to the priority sorting result, and generate a fire response instruction based on the alarm plan.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the intelligent alarm method of the multifunctional gateway described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the processor is enabled to execute the intelligent alarm method of the multifunctional gateway according to any one of claims 1 to 7.

Images