An environment-sensing-based low-energy-consumption intelligent door and window safety alarm method and system

Abstract

The present application relates to the field of intelligent door and window alarm, and particularly relates to a low-energy-consumption intelligent door and window safety alarm method and system based on environment sensing. The low-energy-consumption intelligent door and window safety alarm system based on environment sensing comprises an association calculation module, an initial score calculation module, a monitoring alarm module and a monitoring frequency updating module. The present application significantly optimizes system energy efficiency through a double periodicity scoring mechanism and a monitoring frequency dynamic adjustment strategy. An initial score generated based on user characteristic parameters establishes a basic energy consumption baseline, and then, in combination with deviation analysis and time sequence correction of short-period environment monitoring data, a second importance score is generated to accurately quantify the risk value of each scene. The dynamic regulation mode enables the device to maintain an ultra-low power consumption state during a risk-free period. Compared with a traditional fixed frequency, the monitoring scheme can significantly reduce energy consumption, and is particularly suitable for long-term stable operation of a battery-powered intelligent window control device.

Description

Technical Field

[0001] The present invention relates to the field of intelligent door and window alarms, and in particular to a low-energy intelligent door and window safety alarm method and system based on environmental perception. Background Art

[0002] With the rapid development of smart home technology, door and window security systems, as an important part of home protection, have gradually been upgraded from traditional mechanical locks to intelligent devices with environmental perception capabilities. Early smart door and window systems mostly relied on single sensor detection, such as using vibration sensors to identify window breaking behavior, or using gas sensors to monitor gas leaks. Although such solutions are simple and easy to implement, they have significant false alarm and missed alarm problems. For example, the vibration of windows caused by wind in high-rise buildings can easily be misjudged as violent window breaking, while the aging window structure of users on lower floors may lead to an underestimated risk of leakage due to heavy rain. At the same time, gas leak monitoring relies solely on threshold triggering, without considering users' daily usage habits, and is prone to response lags or redundant alarms in actual scenarios. In addition, existing systems mostly use fixed monitoring frequencies, and sensors continue to operate at high power consumption, resulting in insufficient device endurance. This energy consumption contradiction is particularly prominent for wirelessly deployed door and window nodes.

[0003] Current research attempts to optimize alarm accuracy through multi-sensor fusion or the introduction of machine learning models. However, such solutions often require complex algorithm support, high requirements for edge computing resources, and are difficult to deploy on a large scale using low-cost hardware. More importantly, traditional methods lack the coordinated analysis of long-term user behavioral characteristics and dynamic changes in the environment. For example, the age of window installation affects structural stability, and the correlation between the average daily time away from home and the risk of gas leaks. The differences in these user characteristic parameters make it difficult for a unified alarm threshold to adapt to diverse scenarios, while a fixed monitoring frequency results in a waste of resources during low-risk periods.

[0004] To address the above problems, the present invention proposes a low-energy intelligent door and window security alarm method and system based on environmental perception. By quantifying the correlation between user characteristic parameters and alarm scenarios, a dynamic scoring model is constructed to achieve dual optimization of risk assessment and energy consumption regulation, providing a technical path that is both practical and economical for the field of smart home security. Summary of the Invention

[0005] The present invention significantly optimizes system energy efficiency through a dual periodic scoring mechanism and a dynamic adjustment strategy for monitoring frequency. A basic energy consumption baseline is established based on the initial score generated based on user characteristic parameters. Then, a second importance score is generated, combining the deviation analysis and timing correction of short-period environmental monitoring data, to accurately quantify the risk value of each scenario. This dynamic control mode enables the device to maintain an ultra-low power consumption state during risk-free periods. Compared with traditional fixed-frequency monitoring, this monitoring solution can significantly reduce energy consumption and is particularly suitable for the long-term stable operation of battery-powered smart window control devices.

[0006] A low-energy intelligent door and window security alarm method based on environmental perception, comprising:

[0007] The correlation between each user characteristic parameter and each alarm scenario is calculated. User characteristic parameters include floor height, window area, window installation time, average daily gas usage time, and average daily time away from home. Alarm scenarios include violent window breaking, window structure overload, heavy rain leakage, gas leakage, and dust pollution.

[0008] Set the initial score update cycle and calculate the initial importance score of each alarm scenario at the beginning of any initial score update cycle;

[0009] For any alarm scenario, collect the monitoring parameters corresponding to the alarm scenario and determine whether the collected monitoring parameters are all lower than the corresponding alarm trigger threshold. If so, no action is taken; if not, issue an alarm corresponding to the current alarm scenario and take corresponding measures.

[0010] Set a short-time update cycle. At the beginning of any short-time update cycle, for any alarm scenario, adjust the initial importance score of the alarm scenario based on the corresponding monitoring parameters of the alarm scenario collected in the previous short-time update cycle to obtain the first importance score of the alarm scenario; then further correct the first importance score based on the user status and day and night mode to obtain the second importance score of the alarm scenario; use the second importance score to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario, and apply it in the current short-time update cycle.

[0011] Preferably, for any alarm scenario, the monitoring parameters corresponding to the alarm scenario are collected, wherein the monitoring parameters corresponding to violent window breaking include glass vibration acceleration, glass breaking soundprint matching degree and window shape variable;

[0012] The monitoring parameters corresponding to window structure overload include window surface wind pressure and window curvature;

[0013] Monitoring parameters corresponding to rainstorm leakage include interlayer humidity and window sill water accumulation;

[0014] The monitoring parameters corresponding to gas leakage include methane concentration and carbon monoxide concentration;

[0015] The monitoring parameters corresponding to dust pollution include PM2.5 concentration and PM10 concentration.

[0016] Preferably, the correlation between each user characteristic parameter and each alarm scenario is calculated respectively, and the specific operations are as follows:

[0017] Get alarm event occurrence samples, each alarm event occurrence sample contains a user feature parameter of a user And the corresponding alarm scene code ,in, =1, 2, 3, 4, 5; to The corresponding values ​​are floor height, window area, window installation time, average daily gas usage time, and average daily time away from home; =1, 2, 3, 4, 5; to Corresponding to violent window breaking, window structure overload, rainstorm leakage, gas leakage and dust pollution, for any of the alarm scenarios, if the alarm scenario occurs in the alarm event sample, the corresponding alarm scenario code The value of is 1, otherwise it is 0;

[0018] Using the formula Calculate the correlation between floor height, window area, window installation time, average daily gas usage time, and average daily time away from home and each alarm scenario ,in, =1, 2, ..., ; for The average value of each user characteristic parameter of the alarm event samples; for The average value of each alarm scene code within a sample of alarm event occurrences.

[0019] Preferably, calculating an initial importance score for each alarm scenario;

[0020] The specific operations are as follows:

[0021] Set a standard threshold range for each user characteristic parameter and an initial score update cycle. At the beginning of any initial score update cycle, calculate the user's average daily gas usage time and average daily time away from home during the previous initial score update cycle.

[0022] Through the standard threshold range of each user characteristic parameter, the user's floor height, window area, window installation time, average daily gas usage time and average daily time away from home are linearly mapped to Get the linear mapping value of each user characteristic parameter within the range ;

[0023] Using the formula Calculate the initial importance score of each alarm scenario .

[0024] Preferably, the initial importance score of the alarm scenario is adjusted to obtain the first importance score of the alarm scenario. The specific operations are as follows:

[0025] At the beginning of any short-term update cycle, for any monitoring parameter, calculate the mean value of the monitoring parameter in the previous short-term update cycle and standard deviation , =1, 2, ..., 11; corresponding to glass vibration acceleration, glass breaking sound pattern matching, window shape, window surface wind pressure, window curvature, interlayer humidity, window sill water volume, methane concentration, carbon monoxide concentration, PM2.5 concentration and PM10 concentration, respectively, and the alarm trigger threshold based on the monitoring parameters , using the formula Calculate the first score of the current monitoring parameter ,in, is the amplification factor used to monitor the mean value of the parameter Exceeding the alarm trigger threshold When the value is half of the mean value, the deviation of the monitoring parameter is amplified; using the formula Calculate the second score of the current monitoring parameter ; Then use the formula Calculate the abnormal score of the current monitoring parameters ;

[0026] For any alarm scenario, the abnormal score of the monitoring parameter corresponding to the alarm scenario is calculated. The maximum value among them is used as the representative abnormality score of the current alarm scene. ;

[0027] Using the formula Calculate the first importance score .

[0028] Preferably, the first importance score is further modified according to the user status and the day and night mode to obtain the second importance score of the alarm scenario. The specific operation is as follows:

[0029] Acquisition-based Alarm event samples are generated. For any alarm scenario, the number of times the current alarm scenario occurs in the home state, away from home state, and sleeping state is counted. and the total number of occurrences , =1, 2, 3; corresponding to home state, away state and sleeping state respectively; at the same time, the number of times the current alarm scene occurs during the day and at night is counted respectively , =1, 2; corresponding to day and night respectively;

[0030] For any alarm scenario, determine the and The value of , then using the formula Calculate the second importance score .

[0031] Preferably, the second importance score is used to adjust the monitoring frequency of the monitoring parameter corresponding to the alarm scenario, and the specific operation is as follows:

[0032] For any monitoring parameter, set the benchmark monitoring frequency for that monitoring parameter , and the adjustable frequency range based on the monitoring parameter And the second importance score of the alarm scenario corresponding to the monitoring parameter , if the second importance score of the corresponding alarm scenario Less than or equal to 1, then use the formula Calculate the application monitoring frequency of the current monitoring parameters ; If the second importance score of the corresponding alarm scenario If it is greater than 1, then use the formula Calculate the application monitoring frequency of the current monitoring parameters .

[0033] A low-energy intelligent door and window security alarm system based on environmental perception, comprising:

[0034] The correlation calculation module is used to calculate the correlation between each user characteristic parameter and each alarm scenario;

[0035] The initial score calculation module is used to calculate the initial importance score of each alarm scenario at the beginning of any initial score update cycle;

[0036] The monitoring and alarm module is used to collect the monitoring parameters corresponding to any alarm scenario and determine whether the collected monitoring parameters are all lower than the corresponding alarm trigger threshold. If so, no action is taken; if not, an alarm corresponding to the current alarm scenario is issued and corresponding measures are taken;

[0037] The monitoring frequency update module includes a first scoring calculation unit, a second scoring calculation unit and a frequency calculation unit; the first scoring calculation unit is used to adjust the initial importance score of any alarm scenario at the beginning of any short-time update cycle based on the corresponding monitoring parameters of the alarm scenario collected in the previous short-time update cycle, and obtain the first importance score of the alarm scenario; the second scoring calculation unit is used to further correct the first importance score based on the user status and day and night mode to obtain the second importance score of the alarm scenario; the frequency calculation unit is used to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario based on the second importance score, and apply it in the current short-time update cycle.

[0038] The present invention has the following advantages:

[0039] 1. The present invention significantly optimizes system energy efficiency through a dual-periodic scoring mechanism and a dynamic adjustment strategy for monitoring frequency. A basic energy consumption baseline is established based on an initial score generated based on user characteristic parameters. Then, combined with deviation analysis and timing correction of short-period environmental monitoring data, a secondary importance score is generated to accurately quantify the risk value of each scenario. This dynamic control mode enables the device to maintain an ultra-low power consumption state during risk-free periods. Compared with traditional fixed-frequency monitoring, this monitoring solution can significantly reduce energy consumption and is particularly suitable for the long-term stable operation of battery-powered smart window control devices.

[0040] 2. The present invention breaks through the limitations of single physical quantity threshold judgment and enhances the accuracy of multi-scenario alarms through a three-level evaluation architecture consisting of user characteristic parameter correlation analysis, real-time environmental data fluctuation detection, and user behavior status correction. This process effectively distinguishes between real risks and false triggering events, and at the same time, by dynamically increasing the monitoring frequency of high-risk scenarios, ensures the timeliness and completeness of abnormal signal capture, thereby improving the reliability of alarm decisions from the source of data collection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a structural diagram of the low-energy intelligent door and window security alarm system based on environmental perception adopted in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0043] Example 1, a low-energy intelligent door and window security alarm method based on environmental perception, comprising:

[0044] The correlation between each user characteristic parameter and each alarm scenario is calculated separately, among which the user characteristic parameters include floor height, window area, window installation time, average daily gas usage time and average daily time away from home; the floor position of the user's residence affects the force of the external environment on the window (such as high-altitude wind pressure and theft risk); the size of the window is directly related to the wind pressure resistance and structural stability; the age of the window reflects the aging of the material and the degree of sealing degradation (such as aging of the rubber strip may cause leakage in heavy rain); the length of time the gas equipment is used in daily life indirectly reflects the safety of the gas pipeline or valve (long-term use may increase the risk of leakage); the day the user leaves the residence The average duration is closely related to the needs of home security (for example, the risk of gas leakage may be overlooked when no one is home for a long time); alarm scenarios include violent window breaking, window structure overload, rainstorm leakage, gas leakage and dust pollution; by analyzing the correlation between user characteristics and scenarios, the system can identify the differentiated risk needs of different users. For example, for users on high floors (with large floor height characteristic values), the system will pay more attention to window structure overload monitoring due to the high wind pressure; for households with frequent gas use (with long average daily gas usage time), the initial gas leakage score will be dynamically increased; at the same time, redundant monitoring of non-related scenarios is filtered based on the correlation degree to reduce the need for high-frequency sensor sampling;

[0045] Set the initial score update cycle. The duration of an initial score update cycle can be set to several weeks or months. At the beginning of any initial score update cycle, the initial importance score of each alarm scenario is calculated. Periodic updates of the initial score can promptly respond to long-term changes in user characteristics. The initial score provides a benchmark for subsequent dynamic monitoring frequency adjustments.

[0046] For any alarm scenario, collect the monitoring parameters corresponding to the alarm scenario and determine whether the collected monitoring parameters are all lower than the corresponding alarm trigger threshold. If so, no action is taken; if not, issue an alarm corresponding to the current alarm scenario and take corresponding measures.

[0047] Set a short-term update cycle. The duration of the short-term update cycle can be set to range from tens of minutes to several hours. At the beginning of any short-term update cycle, for any alarm scenario, based on the corresponding monitoring parameters of the alarm scenario collected in the previous short-term update cycle, adjust the initial importance score of the alarm scenario to obtain the first importance score of the alarm scenario; through short-term iterative score updates, quickly capture sudden risks and avoid response delays caused by long-term updates of traditional solutions. Subsequently, the first importance score is further corrected according to user status and day and night mode to obtain the second importance score of the alarm scenario; the second importance score is used to update the corresponding alarm scenario The monitoring frequency of monitoring parameters is adjusted and applied within the current short-term update cycle. For example, if the methane concentration in a user's home continues to rise in the previous cycle (does not reach the threshold but the trend is abnormal), the system will increase the first score of gas leakage at the beginning of the next short cycle. Combined with the current "user away from home" status, the second score is further increased, and the monitoring frequency is increased to ensure that risks can be predicted before the concentration exceeds the threshold. At the same time, the score is corrected by integrating user status and day and night patterns to make the alarm logic more in line with actual needs. This mechanism takes into account the reliability and energy efficiency of security scenarios through the closed-loop logic of "dynamic score correction-resource allocation on demand", and is the core technical support for the efficient self-adaptation of smart home systems.

[0048] For any alarm scenario, the corresponding monitoring parameters are collected. The monitoring parameters corresponding to violent window breaking include glass vibration acceleration, glass breaking sound pattern matching, and window shape variable.

[0049] The monitoring parameters corresponding to window structure overload include window surface wind pressure and window curvature;

[0050] Monitoring parameters corresponding to rainstorm leakage include interlayer humidity and window sill water accumulation;

[0051] The monitoring parameters corresponding to gas leakage include methane concentration and carbon monoxide concentration;

[0052] The monitoring parameters corresponding to dust pollution include PM2.5 concentration and PM10 concentration.

[0053] Calculate the correlation between each user characteristic parameter and each alarm scenario respectively. The specific operations are as follows:

[0054] Get alarm event occurrence samples, each alarm event occurrence sample contains a user feature parameter of a user And the corresponding alarm scene code ,in, =1, 2, 3, 4, 5; to The corresponding values ​​are floor height, window area, window installation time, average daily gas usage time, and average daily time away from home; =1, 2, 3, 4, 5; to Corresponding to violent window breaking, window structure overload, rainstorm leakage, gas leakage and dust pollution, for any of the alarm scenarios, if the alarm scenario occurs in the alarm event sample, the corresponding alarm scenario code The value of is 1, otherwise it is 0;

[0055] Using the formula Calculate the correlation between floor height, window area, window installation time, average daily gas usage time, and average daily time away from home and each alarm scenario ,in, =1, 2, ..., ; for The average value of each user characteristic parameter of the alarm event samples; for The average value of each alarm scene code within a sample of alarm event occurrences.

[0056] Calculate the initial importance score of each alarm scenario;

[0057] The specific operations are as follows:

[0058] Set a standard threshold range for each user characteristic parameter and an initial score update cycle. At the beginning of any initial score update cycle, calculate the user's average daily gas usage time and average daily time away from home during the previous initial score update cycle.

[0059] Through the standard threshold range of each user characteristic parameter, the user's floor height, window area, window installation time, average daily gas usage time and average daily time away from home are linearly mapped to Get the linear mapping value of each user characteristic parameter within the range ;

[0060] Using the formula Calculate the initial importance score of each alarm scenario .

[0061] Adjust the initial importance score of the alarm scenario to obtain the first importance score of the alarm scenario. The specific operations are as follows:

[0062] At the beginning of any short-term update cycle, for any monitoring parameter, calculate the mean value of the monitoring parameter in the previous short-term update cycle and standard deviation , =1, 2, ..., 11; corresponding to glass vibration acceleration, glass breaking sound pattern matching, window shape, window surface wind pressure, window curvature, interlayer humidity, window sill water volume, methane concentration, carbon monoxide concentration, PM2.5 concentration and PM10 concentration, respectively, and the alarm trigger threshold based on the monitoring parameters , using the formula Calculate the first score of the current monitoring parameter ,in, It is the amplification factor, which can be set between 1 and 1.5 to monitor the mean value of the parameter. Exceeding the alarm trigger threshold When the value is half of the mean value, the deviation of the monitoring parameter is amplified; using the formula Calculate the second score of the current monitoring parameter ; Then use the formula Calculate the abnormal score of the current monitoring parameters ;

[0063] For any alarm scenario, the abnormal score of the monitoring parameter corresponding to the alarm scenario is calculated. The maximum value among them is used as the representative abnormality score of the current alarm scene. ;

[0064] Using the formula Calculate the first importance score .

[0065] The first importance score is further modified based on the user status and day / night mode to obtain the second importance score of the alarm scenario. The specific operations are as follows:

[0066] Acquisition-based Alarm event samples are generated. For any alarm scenario, the number of times the current alarm scenario occurs in the home state, away from home state, and sleeping state is counted. and the total number of occurrences , =1, 2, 3; corresponding to home state, away state and sleeping state respectively; at the same time, the number of times the current alarm scene occurs during the day and at night is counted respectively , =1, 2; corresponding to day and night respectively;

[0067] For any alarm scenario, determine the and The value of , then using the formula Calculate the second importance score .

[0068] Use the second importance score to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario. The specific operations are as follows:

[0069] For any monitoring parameter, set the benchmark monitoring frequency for that monitoring parameter , and the adjustable frequency range based on the monitoring parameter And the second importance score of the alarm scenario corresponding to the monitoring parameter , if the second importance score of the corresponding alarm scenario Less than or equal to 1, then use the formula Calculate the application monitoring frequency of the current monitoring parameters ; If the second importance score of the corresponding alarm scenario If it is greater than 1, then use the formula Calculate the application monitoring frequency of the current monitoring parameters .

[0070] Example 2, a low-energy intelligent door and window security alarm system based on environmental perception, such as Figure 1 As shown, including:

[0071] The correlation calculation module is used to calculate the correlation between each user characteristic parameter and each alarm scenario. User characteristic parameters include floor height, window area, window installation time, average daily gas usage time, and average daily time away from home. Alarm scenarios include violent window breaking, window structure overload, heavy rain leakage, gas leakage, and dust pollution.

[0072] The initial score calculation module is used to calculate the initial importance score of each alarm scenario at the beginning of any initial score update cycle;

[0073] The monitoring and alarm module is used to collect the monitoring parameters corresponding to any alarm scenario and determine whether the collected monitoring parameters are all lower than the corresponding alarm trigger threshold. If so, no action is taken; if not, an alarm corresponding to the current alarm scenario is issued and corresponding measures are taken;

[0074] The monitoring frequency update module includes a first scoring calculation unit, a second scoring calculation unit and a frequency calculation unit; the first scoring calculation unit is used to adjust the initial importance score of any alarm scenario at the beginning of any short-time update cycle based on the corresponding monitoring parameters of the alarm scenario collected in the previous short-time update cycle, and obtain the first importance score of the alarm scenario; the second scoring calculation unit is used to further correct the first importance score based on the user status and day and night mode to obtain the second importance score of the alarm scenario; the frequency calculation unit is used to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario based on the second importance score, and apply it in the current short-time update cycle.

[0075] It should be understood that those skilled in the art may make improvements or modifications based on the above description, and all such improvements and modifications shall fall within the scope of protection of the appended claims. Any portion of this specification not described in detail is prior art known to those skilled in the art.

Claims

1. A low-energy intelligent door and window security alarm method based on environmental perception, characterized in that: include: The correlation between each user characteristic parameter and each alarm scenario is calculated. User characteristic parameters include floor height, window area, window installation time, average daily gas usage time, and average daily time away from home. Alarm scenarios include violent window breaking, window structure overload, heavy rain leakage, gas leakage, and dust pollution. Set the initial score update cycle and calculate the initial importance score of each alarm scenario at the beginning of any initial score update cycle; For any alarm scenario, collect the monitoring parameters corresponding to the alarm scenario and determine whether the collected monitoring parameters are all lower than the corresponding alarm trigger threshold. If so, no action is taken; if not, issue an alarm corresponding to the current alarm scenario and take corresponding measures. Set a short-term update cycle. At the beginning of any short-term update cycle, for any alarm scenario, adjust the initial importance score of the alarm scenario based on the corresponding monitoring parameters of the alarm scenario collected in the previous short-term update cycle to obtain the first importance score of the alarm scenario. Then, further modify the first importance score based on the user status and day / night mode to obtain the second importance score of the alarm scenario. Use the second importance score to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario and apply it in the current short-term update cycle. Calculate the initial importance score of each alarm scenario; The specific operations are as follows: Set a standard threshold range for each user characteristic parameter and an initial score update cycle. At the beginning of any initial score update cycle, calculate the user's average daily gas usage time and average daily time away from home during the previous initial score update cycle. Through the standard threshold range of each user characteristic parameter, the user's floor height, window area, window installation time, average daily gas usage time and average daily time away from home are linearly mapped to Get the linear mapping value of each user characteristic parameter within the range ; Using the formula Calculate the initial importance score of each alarm scenario ,in, That is, the correlation between each user characteristic parameter and each alarm scenario. =1, 2, 3, 4, 5; =1, 2, 3, 4, 5.

2. The low-energy intelligent door and window security alarm method based on environmental perception according to claim 1 is characterized in that: For any alarm scenario, the corresponding monitoring parameters are collected. The monitoring parameters corresponding to violent window breaking include glass vibration acceleration, glass breaking sound pattern matching, and window shape variable. The monitoring parameters corresponding to window structure overload include window surface wind pressure and window curvature; Monitoring parameters corresponding to rainstorm leakage include interlayer humidity and window sill water accumulation; The monitoring parameters corresponding to gas leakage include methane concentration and carbon monoxide concentration; The monitoring parameters corresponding to dust pollution include PM2.5 concentration and PM10 concentration.

3. The low-energy intelligent door and window security alarm method based on environmental perception according to claim 2 is characterized in that: Calculate the correlation between each user characteristic parameter and each alarm scenario respectively. The specific operations are as follows: Get alarm event occurrence samples, each alarm event occurrence sample contains a user feature parameter of a user And the corresponding alarm scene code ,in, =1, 2, 3, 4, 5; to The corresponding values ​​are floor height, window area, window installation time, average daily gas usage time, and average daily time away from home; =1, 2, 3, 4, 5; to Corresponding to violent window breaking, window structure overload, rainstorm leakage, gas leakage and dust pollution, for any of the alarm scenarios, if the alarm scenario occurs in the alarm event sample, the corresponding alarm scenario code The value of is 1, otherwise it is 0; Using the formula Calculate the correlation between floor height, window area, window installation time, average daily gas usage time, and average daily time away from home and each alarm scenario ,in, =1, 2, ..., ; for The average value of each user characteristic parameter of the alarm event samples; for The average value of each alarm scene code within a sample of alarm event occurrences.

4. The low-energy intelligent door and window security alarm method based on environmental perception according to claim 3 is characterized in that: Adjust the initial importance score of the alarm scenario to obtain the first importance score of the alarm scenario. The specific operations are as follows: At the beginning of any short-term update cycle, for any monitoring parameter, calculate the mean value of the monitoring parameter in the previous short-term update cycle and standard deviation , =1, 2, ..., 11; corresponding to glass vibration acceleration, glass breaking sound pattern matching, window shape, window surface wind pressure, window curvature, interlayer humidity, window sill water volume, methane concentration, carbon monoxide concentration, PM2.5 concentration and PM10 concentration, respectively, and the alarm trigger threshold based on the monitoring parameters , using the formula Calculate the first score of the current monitoring parameter ,in, is the amplification factor used to monitor the mean value of the parameter Exceeding the alarm trigger threshold When the value is half of the mean value, the deviation of the monitoring parameter is amplified; using the formula Calculate the second score of the current monitoring parameter ; Then use the formula Calculate the abnormal score of the current monitoring parameters ; For any alarm scenario, the abnormal score of the monitoring parameter corresponding to the alarm scenario is calculated. The maximum value among them is used as the representative abnormality score of the current alarm scene. ; Using the formula Calculate the first importance score .

5. The low-energy intelligent door and window security alarm method based on environmental perception according to claim 4 is characterized in that: The first importance score is further modified based on the user status and day / night mode to obtain the second importance score of the alarm scenario. The specific operations are as follows: Acquisition-based Alarm event samples are generated. For any alarm scenario, the number of times the current alarm scenario occurs in the home state, away from home state, and sleeping state is counted. and the total number of occurrences , =1, 2, 3; Corresponding to home state, away state and sleeping state respectively; at the same time, the number of times the current alarm scene occurs during the day and at night is counted respectively , =1, 2; corresponding to day and night respectively; For any alarm scenario, determine the and The value of , then using the formula Calculate the second importance score .

6. The low-energy intelligent door and window security alarm method based on environmental perception according to claim 5 is characterized in that: Use the second importance score to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario. The specific operations are as follows: For any monitoring parameter, set the benchmark monitoring frequency for that monitoring parameter , and the adjustable frequency range based on the monitoring parameter And the second importance score of the alarm scenario corresponding to the monitoring parameter , if the second importance score of the corresponding alarm scenario Less than or equal to 1, then use the formula Calculate the application monitoring frequency of the current monitoring parameters ; If the second importance score of the corresponding alarm scenario If it is greater than 1, then use the formula Calculate the application monitoring frequency of the current monitoring parameters .

7. A low-energy intelligent door and window security alarm system based on environmental perception, characterized in that: The system is applied to a low-energy intelligent door and window security alarm method based on environmental perception as described in any one of claims 1 to 6, comprising: The correlation calculation module is used to calculate the correlation between each user characteristic parameter and each alarm scenario; The initial score calculation module is used to calculate the initial importance score of each alarm scenario at the beginning of any initial score update cycle; The monitoring and alarm module is used to collect the monitoring parameters corresponding to any alarm scenario and determine whether the collected monitoring parameters are all lower than the corresponding alarm trigger threshold. If so, no action is taken; if not, an alarm corresponding to the current alarm scenario is issued and corresponding measures are taken; The monitoring frequency update module includes a first scoring calculation unit, a second scoring calculation unit and a frequency calculation unit; the first scoring calculation unit is used to adjust the initial importance score of any alarm scenario at the beginning of any short-time update cycle based on the corresponding monitoring parameters of the alarm scenario collected in the previous short-time update cycle, and obtain the first importance score of the alarm scenario; the second scoring calculation unit is used to further correct the first importance score based on the user status and day and night mode to obtain the second importance score of the alarm scenario; the frequency calculation unit is used to adjust the monitoring frequency of the monitoring parameters corresponding to the alarm scenario based on the second importance score, and apply it in the current short-time update cycle.

Images