Building-level low-cost alarm method and system for multi-source signal identification

Abstract

The invention provides a building-level low-cost alarm method and a building-level low-cost alarm system for multi-source signal identification. The method comprises the steps of monitoring a target building, collecting monitoring state data of a preset monitoring point and scene feature data of an area where the preset monitoring point is located in real time, and performing processing according to the scene feature data in combination with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set, performing corresponding comparison processing according to the monitoring state data and the corrected recognition boundary threshold set to obtain a state deviation rate set, further performing fusion processing to obtain a comprehensive deviation degree, determining an alarm level according to the comprehensive deviation degree, and matching a corresponding alarm response mechanism, thereby realizing the building-level low-cost alarm technology for multi-source signal recognition.

Description

A low-cost building-level alarm method and system for multi-source signal recognition Technical Field

[0001] This application relates to the field of security protection technology, and more specifically, to a low-cost building-level alarm method and system for multi-source signal recognition. Background Technology

[0002] With the acceleration of urbanization, the demand for building security monitoring is increasing, especially in residential buildings and small office buildings, where there is an urgent need for low-cost and high-efficiency alarm solutions. Existing building alarm technologies have many obvious limitations: some rely on a single monitoring signal, which is easily affected by environmental interference, leading to false alarms and missed alarms; some use multi-source data, but do not dynamically adjust the recognition threshold according to scene characteristics, resulting in insufficient adaptability.

[0003] Meanwhile, traditional alarm systems are often complex in hardware and have high deployment costs, making them difficult to popularize in small and medium-sized buildings. In addition, existing solutions mostly process monitoring data in a single dimension, resulting in low accuracy in alarm level determination and a lack of targeted alarm response mechanisms. These problems restrict the large-scale application of building security monitoring. Therefore, there is an urgent need for a multi-source signal alarm technology that combines low cost, high adaptability and accurate identification to meet the actual needs of building-level security protection. Summary of the Invention

[0004] The purpose of this application is to provide a low-cost building-level alarm method and system for multi-source signal recognition. This method monitors the target building and collects real-time monitoring status data from preset monitoring points, as well as scene feature data of the surrounding area. The scene feature data is then processed in conjunction with a preset set of recognition boundary thresholds to obtain a corrected set of thresholds. The monitoring status data is then compared with the corrected thresholds to obtain a set of deviation rates. Further fusion processing is performed to obtain a comprehensive deviation. The alarm level is determined based on the comprehensive deviation, and a corresponding alarm response mechanism is matched, thus achieving low-cost building-level alarm technology based on multi-source signal recognition.

[0005] This application also provides a low-cost building-level alarm method for multi-source signal recognition, comprising the following steps: monitoring the target building and collecting real-time monitoring status data of preset monitoring points and scene feature data of the area; processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set; comparing the monitoring status data with the corrected recognition boundary threshold set to obtain a status deviation rate set, further performing fusion processing to obtain a comprehensive deviation degree; determining the alarm level based on the comprehensive deviation degree and matching a corresponding alarm response mechanism.

[0006] Optionally, in the low-cost building-level alarm method for multi-source signal recognition described in this application, the monitoring of the target building and the real-time collection of monitoring status data of preset monitoring points and scene feature data of the area include: monitoring the target building and collecting monitoring status data of preset monitoring points in real time, including vibration, sound and infrared radiation intensity; and simultaneously acquiring scene feature data of the area where the preset monitoring points are located, including area type, time period and building floor.

[0007] Optionally, in the building-level low-cost alarm method for multi-source signal recognition described in this application, the step of processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set includes: obtaining a preset recognition boundary threshold set, including a preset vibration amplitude boundary threshold, a preset sound loudness boundary threshold, and a preset infrared radiation intensity boundary threshold; processing the preset recognition boundary threshold set in conjunction with the area type, time period, and building floor using a preset recognition boundary adjustment model to obtain a corrected recognition boundary threshold set; the corrected recognition boundary threshold set includes a corrected vibration amplitude boundary threshold, a corrected sound loudness boundary threshold, and a corrected infrared radiation intensity boundary threshold.

[0008] Optionally, in the building-level low-cost alarm method for multi-source signal recognition described in this application, the step of comparing the monitoring status data with the corrected identification boundary threshold set to obtain a status deviation rate set, and further performing fusion processing to obtain a comprehensive deviation degree, includes: comparing the vibration, sound, and infrared radiation intensity with the three thresholds of the corrected identification boundary threshold set to obtain a status deviation rate set; the status deviation rate set includes vibration deviation rate, sound deviation rate, and infrared deviation rate; and processing the vibration deviation rate, sound deviation rate, and infrared deviation rate using a preset fusion rule algorithm to obtain a comprehensive deviation degree.

[0009] Optionally, in the building-level low-cost alarm method for multi-source signal identification described in this application, the step of determining the alarm level based on the comprehensive deviation and matching the corresponding alarm response mechanism includes: comparing the comprehensive deviation with a preset comprehensive deviation threshold to obtain a first threshold comparison result; determining the alarm level based on the first threshold comparison result; the alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm; and matching the corresponding alarm response mechanism based on the alarm level.

[0010] Optionally, the building-level low-cost alarm method for multi-source signal recognition described in this application further includes: monitoring the target building and extracting alarm statistics within a preset time period, including alarm accuracy, alarm response delay, and alarm maintenance cost; processing the alarm accuracy, alarm response delay, and alarm maintenance cost through a preset alarm qualification assessment model to obtain an alarm qualification degree; comparing the alarm qualification degree with a preset alarm qualification degree threshold to obtain a second threshold comparison result; and determining whether the alarm system of the target building meets the requirements based on the second threshold comparison result.

[0011] Secondly, this application provides a low-cost building-level alarm system based on multi-source signal recognition. The system includes a memory and a processor. The memory contains a program for a low-cost building-level alarm method based on multi-source signal recognition. When executed by the processor, the program implements the following steps: monitoring the target building and collecting real-time monitoring status data of preset monitoring points and scene feature data of the area; processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set; comparing the monitoring status data with the corrected recognition boundary threshold set to obtain a status deviation rate set, further performing fusion processing to obtain a comprehensive deviation degree; determining the alarm level based on the comprehensive deviation degree and matching a corresponding alarm response mechanism.

[0012] Optionally, in the low-cost building-level alarm system for multi-source signal recognition described in this application, the monitoring of the target building and the real-time acquisition of monitoring status data of preset monitoring points and scene feature data of the area include: monitoring the target building and the real-time acquisition of monitoring status data of preset monitoring points, including vibration, sound and infrared radiation intensity; and synchronously acquiring scene feature data of the area where the preset monitoring points are located, including area type, time period and building floor.

[0013] Optionally, in the low-cost building-level alarm system for multi-source signal recognition described in this application, the step of processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set includes: obtaining a preset recognition boundary threshold set, including a preset vibration amplitude boundary threshold, a preset sound loudness boundary threshold, and a preset infrared radiation intensity boundary threshold; processing the preset recognition boundary threshold set in conjunction with the area type, time period, and building floor using a preset recognition boundary adjustment model to obtain a corrected recognition boundary threshold set; the corrected recognition boundary threshold set includes a corrected vibration amplitude boundary threshold, a corrected sound loudness boundary threshold, and a corrected infrared radiation intensity boundary threshold.

[0014] Optionally, in the building-level low-cost alarm system for multi-source signal recognition described in this application, the step of comparing the monitoring status data with the corrected identification boundary threshold set to obtain a status deviation rate set, and further performing fusion processing to obtain a comprehensive deviation degree, includes: comparing the vibration, sound, and infrared radiation intensity with the three thresholds of the corrected identification boundary threshold set to obtain a status deviation rate set; the status deviation rate set includes vibration deviation rate, sound deviation rate, and infrared deviation rate; and processing the vibration deviation rate, sound deviation rate, and infrared deviation rate using a preset fusion rule algorithm to obtain a comprehensive deviation degree.

[0015] As can be seen from the above, the multi-source signal recognition building-level low-cost alarm method and system provided in this application monitors the target building and collects the monitoring status data of preset monitoring points and the scene feature data of the area in real time. Based on the scene feature data, it is processed in combination with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set. Based on the monitoring status data and the corrected recognition boundary threshold set, a status deviation rate set is obtained. Further fusion processing is performed to obtain a comprehensive deviation degree. Based on the comprehensive deviation degree, the alarm level is determined and a corresponding alarm response mechanism is matched, thereby realizing the technology of multi-source signal recognition building-level low-cost alarm.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 is a flowchart of a building-level low-cost alarm method for multi-source signal recognition provided in an embodiment of this application; Figure 2 is a flowchart of obtaining the corrected identification boundary threshold set in the building-level low-cost alarm method for multi-source signal recognition provided in an embodiment of this application; Figure 3 is a flowchart of obtaining the comprehensive deviation in the building-level low-cost alarm method for multi-source signal recognition provided in an embodiment of this application; Figure 4 is a flowchart of matching the corresponding alarm response mechanism in the building-level low-cost alarm method for multi-source signal recognition provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0020] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0021] Please refer to Figure 1, which is a flowchart of a low-cost building-level alarm method for multi-source signal recognition in some embodiments of this application. This low-cost building-level alarm method for multi-source signal recognition is used in terminal devices, such as computers and mobile terminals. The method includes the following steps: S11, monitoring the target building and collecting real-time monitoring status data of preset monitoring points and scene feature data of the area; S12, processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set; S13, comparing the monitoring status data with the corrected recognition boundary threshold set to obtain a status deviation rate set, and further performing fusion processing to obtain a comprehensive deviation degree; S14, determining the alarm level based on the comprehensive deviation degree and matching the corresponding alarm response mechanism.

[0022] It is worth noting that existing low-cost building-level alarm systems suffer from problems such as single-dimensional monitoring data, fixed identification thresholds, lack of data fusion in processing, and ambiguous alarm level classifications. To better address these issues, the system first monitors the target building and collects real-time monitoring status data from preset monitoring points, including vibration, sound, and infrared radiation intensity, as well as scene characteristic data of the area, including area type, time period, and building floor. Next, based on the area type, time period, and building floor, a preset set of identification boundary thresholds is processed to obtain a corrected set of identification boundary thresholds, including corrected vibration amplitude boundary thresholds, corrected sound loudness boundary thresholds, and corrected infrared radiation intensity boundary thresholds. Then, the monitoring status data is compared with the corrected set of identification boundary thresholds to obtain a set of status deviation rates, including vibration deviation rate, sound deviation rate, and infrared deviation rate. This is further fused to obtain a comprehensive deviation degree. The alarm level is determined based on the comprehensive deviation degree, including Level 1, Level 2, and Level 3 alarms, and a corresponding alarm response mechanism is matched, thereby achieving a low-cost building-level alarm technology with multi-source signal identification.

[0023] According to an embodiment of the present invention, the monitoring of the target building and the real-time collection of monitoring status data of preset monitoring points and scene feature data of the area include: monitoring the target building and collecting monitoring status data of preset monitoring points in real time, including vibration, sound and infrared radiation intensity; and simultaneously acquiring scene feature data of the area where the preset monitoring points are located, including area type, time period and building floor.

[0024] It is worth noting that the target building is monitored in its entirety. For pre-set monitoring points (such as building entrances and exits, key corners of corridors, equipment rooms, and other key areas), a low-cost sensor array is deployed to collect monitoring status data in real time. The core data includes vibration signals (capturing abnormal physical disturbances such as broken doors and windows, wall impacts, etc.), sound signals (identifying abnormal audio such as cries for help, glass breaking sounds, etc.), and infrared radiation intensity (detecting infrared features such as human activity and abnormal heat sources). At the same time, scene feature data of the area where each pre-set monitoring point is located is acquired simultaneously. The area type covers functional areas such as residential areas, equipment rooms, and public passages. The time period parameters include time dimensions such as weekdays / holidays and daytime / nighttime. The building floor information distinguishes between low, middle, and high floors.

[0025] Please refer to Figure 2, which is a flowchart illustrating the process of obtaining a corrected identification boundary threshold set in a low-cost building-level alarm method for multi-source signal identification in some embodiments of this application. According to an embodiment of the present invention, the step of processing the scene feature data in conjunction with a preset identification boundary threshold set to obtain a corrected identification boundary threshold set includes: S21, obtaining a preset identification boundary threshold set, including a preset vibration amplitude boundary threshold, a preset sound loudness boundary threshold, and a preset infrared radiation intensity boundary threshold; S22, processing the preset identification boundary threshold set in conjunction with the area type, time period, and building floor using a preset identification boundary adjustment model to obtain a corrected identification boundary threshold set; S23, the corrected identification boundary threshold set includes a corrected vibration amplitude boundary threshold, a corrected sound loudness boundary threshold, and a corrected infrared radiation intensity boundary threshold.

[0026] It is worth noting that, to achieve scenario adaptability for alarm recognition, a preset set of recognition boundary thresholds is first retrieved. This threshold set is based on safety monitoring data in typical scenarios and includes preset vibration amplitude boundary thresholds (baseline vibration safety thresholds), preset sound loudness boundary thresholds (upper limits of typical environmental noise), and preset infrared radiation intensity boundary thresholds (standard range of infrared radiation for normal human bodies or the environment). This provides a basic reference for dynamic threshold correction. Subsequently, scenario feature data such as area type, time period, and building floor are input into the preset recognition boundary adjustment model along with the preset recognition boundary threshold set. This model has built-in weight coefficients corresponding to different scenarios (e.g., the vibration threshold weight for equipment rooms is higher than that for residential areas, the sound threshold weight for nighttime is lower than that for daytime, and the infrared monitoring sensitivity weight for high-rise buildings is higher than that for low-rise buildings). Through multi-dimensional data fusion calculation, the original thresholds are modified according to the scenario. Finally, a modified set of recognition boundary thresholds is generated, whose dimensions are consistent with the preset threshold set. Specifically, it includes modified vibration amplitude boundary thresholds, modified sound loudness boundary thresholds, and modified infrared radiation intensity boundary thresholds. This ensures that the recognition standards fit the actual scenario of the monitoring point, effectively reducing the risk of false alarms and missed alarms in different scenarios and improving the accuracy of alarm recognition.

[0027] Please refer to Figure 3, which is a flowchart illustrating the process of obtaining the comprehensive deviation degree in a building-level low-cost alarm method for multi-source signal identification in some embodiments of this application. According to an embodiment of the present invention, the step of comparing the monitored state data with the corrected identification boundary threshold set to obtain a state deviation rate set, and then further performing fusion processing to obtain the comprehensive deviation degree, includes: S31, comparing the vibration, sound, and infrared radiation intensity with the three thresholds of the corrected identification boundary threshold set to obtain a state deviation rate set; S32, the state deviation rate set includes vibration deviation rate, sound deviation rate, and infrared deviation rate; S33, processing the vibration deviation rate, sound deviation rate, and infrared deviation rate using a preset fusion rule algorithm to obtain the comprehensive deviation degree.

[0028] It is worth noting that in the alarm status determination stage, a precise comparative analysis is conducted based on multi-source monitoring data and scenario-based correction thresholds. First, the three monitoring data points of vibration amplitude, sound loudness, and infrared radiation intensity collected in real time are compared one-to-one with the corresponding correction thresholds for vibration amplitude, sound loudness, and infrared radiation intensity in the correction threshold set. By calculating the proportion of each monitoring data point exceeding the corresponding correction threshold, a status deviation rate set is generated, which specifically includes vibration deviation rate, sound deviation rate, and infrared deviation rate. Subsequently, a preset fusion rule algorithm is called to comprehensively process the three deviation rates. This algorithm has built-in weight coefficients for each deviation rate (which can be preset according to the building's safety requirements; for example, the weight of vibration deviation rate is higher than that of sound deviation rate, highlighting the priority of severe anomalies such as demolition). Through weighted summation, normalization, and other calculation logic, the multi-dimensional individual deviation rates are integrated into a unified quantitative indicator, namely, the comprehensive deviation degree.

[0029] Please refer to Figure 4, which is a flowchart of the matching alarm response mechanism for a building-level low-cost alarm method for multi-source signal identification in some embodiments of this application. According to an embodiment of the present invention, determining the alarm level based on the comprehensive deviation and matching the corresponding alarm response mechanism includes: S41, comparing the comprehensive deviation with a preset comprehensive deviation threshold to obtain a first threshold comparison result; S42, determining the alarm level based on the first threshold comparison result; S43, the alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm; S44, matching the corresponding alarm response mechanism based on the alarm level.

[0030] It is worth noting that in the risk level determination and response execution phase, alarm classification and precise handling are achieved through quantitative threshold comparison. First, the obtained comprehensive deviation is compared in real time with a preset comprehensive deviation threshold, which is divided into multiple intervals based on the building's security protection needs (such as low-risk threshold interval, medium-risk threshold interval, and high-risk threshold interval). The comparison generates a first threshold comparison result, clarifying the risk interval of the comprehensive deviation. Subsequently, the corresponding alarm level is determined based on the first threshold comparison result: if the comprehensive deviation is in the low-risk threshold interval, it is determined as a Level 1 alarm (mild anomaly); if it is in the medium-risk threshold interval, it is determined as a Level 2 alarm (moderate anomaly); if it is in the high-risk threshold interval, it is determined as a Level 3 alarm (severe anomaly). Finally, according to the preset alarm response mechanism mapping rules, differentiated handling plans are matched for different alarm levels: Level 1 alarms can take mild responses such as background recording and SMS reminders to property management; Level 2 alarms activate on-site audible and visual alarms and remote video verification; Level 3 alarms trigger emergency alarms, linkage with the public security system, and notification of security personnel for on-site handling, among other severe responses.

[0031] According to an embodiment of the present invention, the method further includes: monitoring the target building and extracting alarm statistics within a preset time period, including alarm accuracy, alarm response delay, and alarm maintenance cost; processing the alarm accuracy, alarm response delay, and alarm maintenance cost through a preset alarm qualification assessment model to obtain an alarm qualification degree; comparing the alarm qualification degree with a preset alarm qualification degree threshold to obtain a second threshold comparison result; and determining whether the alarm system of the target building meets the requirements based on the second threshold comparison result.

[0032] It is particularly important to note that, to ensure the continuous and reliable operation of the building alarm system, a closed-loop evaluation mechanism needs to be established to dynamically verify the system performance. First, monitor the alarm operation status of the target building and extract core alarm statistics within a preset time period (e.g., 1 month, 3 months): alarm accuracy (the ratio of effective alarms to total alarms, reflecting identification accuracy), alarm response delay (the time taken from triggering an alarm to initiating the response mechanism, reflecting timeliness), and alarm maintenance cost (equipment maintenance, data transmission, and other related costs, aligning with low-cost design requirements). Then, input these three statistics into a preset alarm qualification assessment model. The model has built-in weighting coefficients for each indicator (e.g., alarm accuracy has the highest weight, balancing response efficiency and cost control). Through weighted calculation and standardization, a quantified alarm qualification score is output. Finally, compare the alarm qualification score with a preset alarm qualification threshold to obtain a second threshold comparison result: if the qualification score is higher than the threshold, the system meets the standards in accuracy, timeliness, and cost control, and is deemed compliant; if it is lower than the threshold, it is deemed non-compliant, requiring targeted optimization of threshold parameters, adjustment of the response mechanism, or equipment maintenance.

[0033] Secondly, the present invention also discloses a low-cost building-level alarm system for multi-source signal recognition, including a memory and a processor. The memory includes a low-cost building-level alarm method program for multi-source signal recognition. When the processor executes the low-cost building-level alarm method program for multi-source signal recognition, it performs the following steps: monitoring the target building and collecting monitoring status data of preset monitoring points and scene feature data of the area in real time; processing the scene feature data in combination with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set; comparing the monitoring status data with the corrected recognition boundary threshold set to obtain a status deviation rate set, and further performing fusion processing to obtain a comprehensive deviation degree; determining the alarm level based on the comprehensive deviation degree and matching the corresponding alarm response mechanism.

[0034] It is worth noting that existing low-cost building-level alarm systems suffer from problems such as single-dimensional monitoring data, fixed identification thresholds, lack of data fusion in processing, and ambiguous alarm level classifications. To better address these issues, the system first monitors the target building and collects real-time monitoring status data from preset monitoring points, including vibration, sound, and infrared radiation intensity, as well as scene characteristic data of the area, including area type, time period, and building floor. Next, based on the area type, time period, and building floor, a preset set of identification boundary thresholds is processed to obtain a corrected set of identification boundary thresholds, including corrected vibration amplitude boundary thresholds, corrected sound loudness boundary thresholds, and corrected infrared radiation intensity boundary thresholds. Then, the monitoring status data is compared with the corrected set of identification boundary thresholds to obtain a set of status deviation rates, including vibration deviation rate, sound deviation rate, and infrared deviation rate. This is further fused to obtain a comprehensive deviation degree. The alarm level is determined based on the comprehensive deviation degree, including Level 1, Level 2, and Level 3 alarms, and a corresponding alarm response mechanism is matched, thereby achieving a low-cost building-level alarm technology with multi-source signal identification.

[0035] According to an embodiment of the present invention, the monitoring of the target building and the real-time collection of monitoring status data of preset monitoring points and scene feature data of the area include: monitoring the target building and collecting monitoring status data of preset monitoring points in real time, including vibration, sound and infrared radiation intensity; and simultaneously acquiring scene feature data of the area where the preset monitoring points are located, including area type, time period and building floor.

[0036] It is worth noting that the target building is monitored in its entirety. For pre-set monitoring points (such as building entrances and exits, key corners of corridors, equipment rooms, and other key areas), a low-cost sensor array is deployed to collect monitoring status data in real time. The core data includes vibration signals (capturing abnormal physical disturbances such as broken doors and windows, wall impacts, etc.), sound signals (identifying abnormal audio such as cries for help, glass breaking sounds, etc.), and infrared radiation intensity (detecting infrared features such as human activity and abnormal heat sources). At the same time, scene feature data of the area where each pre-set monitoring point is located is acquired simultaneously. The area type covers functional areas such as residential areas, equipment rooms, and public passages. The time period parameters include time dimensions such as weekdays / holidays and daytime / nighttime. The building floor information distinguishes between low, middle, and high floors.

[0037] According to an embodiment of the present invention, the step of processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set includes: obtaining a preset recognition boundary threshold set, including a preset vibration amplitude boundary threshold, a preset sound loudness boundary threshold, and a preset infrared radiation intensity boundary threshold; processing the preset recognition boundary threshold set in conjunction with the area type, time period, and building floor using a preset recognition boundary adjustment model to obtain a corrected recognition boundary threshold set; the corrected recognition boundary threshold set includes a corrected vibration amplitude boundary threshold, a corrected sound loudness boundary threshold, and a corrected infrared radiation intensity boundary threshold.

[0038] It is worth noting that, to achieve scenario adaptability for alarm recognition, a preset set of recognition boundary thresholds is first retrieved. This threshold set is based on safety monitoring data in typical scenarios and includes preset vibration amplitude boundary thresholds (baseline vibration safety thresholds), preset sound loudness boundary thresholds (upper limits of typical environmental noise), and preset infrared radiation intensity boundary thresholds (standard range of infrared radiation for normal human bodies or the environment). This provides a basic reference for dynamic threshold correction. Subsequently, scenario feature data such as area type, time period, and building floor are input into the preset recognition boundary adjustment model along with the preset recognition boundary threshold set. This model has built-in weight coefficients corresponding to different scenarios (e.g., the vibration threshold weight for equipment rooms is higher than that for residential areas, the sound threshold weight for nighttime is lower than that for daytime, and the infrared monitoring sensitivity weight for high-rise buildings is higher than that for low-rise buildings). Through multi-dimensional data fusion calculation, the original thresholds are modified according to the scenario. Finally, a modified set of recognition boundary thresholds is generated, whose dimensions are consistent with the preset threshold set. Specifically, it includes modified vibration amplitude boundary thresholds, modified sound loudness boundary thresholds, and modified infrared radiation intensity boundary thresholds. This ensures that the recognition standards fit the actual scenario of the monitoring point, effectively reducing the risk of false alarms and missed alarms in different scenarios and improving the accuracy of alarm recognition.

[0039] According to an embodiment of the present invention, the step of comparing the monitored state data with the corrected identification boundary threshold set to obtain a state deviation rate set, and further performing fusion processing to obtain a comprehensive deviation degree, includes: comparing the vibration, sound, and infrared radiation intensity with three thresholds of the corrected identification boundary threshold set to obtain a state deviation rate set; the state deviation rate set includes vibration deviation rate, sound deviation rate, and infrared deviation rate; and processing the vibration deviation rate, sound deviation rate, and infrared deviation rate using a preset fusion rule algorithm to obtain a comprehensive deviation degree.

[0040] It is worth noting that in the alarm status determination stage, a precise comparative analysis is conducted based on multi-source monitoring data and scenario-based correction thresholds. First, the three monitoring data points of vibration amplitude, sound loudness, and infrared radiation intensity collected in real time are compared one-to-one with the corresponding correction thresholds for vibration amplitude, sound loudness, and infrared radiation intensity in the correction threshold set. By calculating the proportion of each monitoring data point exceeding the corresponding correction threshold, a status deviation rate set is generated, which specifically includes vibration deviation rate, sound deviation rate, and infrared deviation rate. Subsequently, a preset fusion rule algorithm is called to comprehensively process the three deviation rates. This algorithm has built-in weight coefficients for each deviation rate (which can be preset according to the building's safety requirements; for example, the weight of vibration deviation rate is higher than that of sound deviation rate, highlighting the priority of severe anomalies such as demolition). Through weighted summation, normalization, and other calculation logic, the multi-dimensional individual deviation rates are integrated into a unified quantitative indicator, namely, the comprehensive deviation degree.

[0041] According to an embodiment of the present invention, determining the alarm level based on the comprehensive deviation and matching the corresponding alarm response mechanism includes: comparing the comprehensive deviation with a preset comprehensive deviation threshold to obtain a first threshold comparison result; determining the alarm level based on the first threshold comparison result; the alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm; and matching the corresponding alarm response mechanism based on the alarm level.

[0042] It is worth noting that in the risk level determination and response execution phase, alarm classification and precise handling are achieved through quantitative threshold comparison. First, the obtained comprehensive deviation is compared in real time with a preset comprehensive deviation threshold, which is divided into multiple intervals based on the building's security protection needs (such as low-risk threshold interval, medium-risk threshold interval, and high-risk threshold interval). The comparison generates a first threshold comparison result, clarifying the risk interval of the comprehensive deviation. Subsequently, the corresponding alarm level is determined based on the first threshold comparison result: if the comprehensive deviation is in the low-risk threshold interval, it is determined as a Level 1 alarm (mild anomaly); if it is in the medium-risk threshold interval, it is determined as a Level 2 alarm (moderate anomaly); if it is in the high-risk threshold interval, it is determined as a Level 3 alarm (severe anomaly). Finally, according to the preset alarm response mechanism mapping rules, differentiated handling plans are matched for different alarm levels: Level 1 alarms can take mild responses such as background recording and SMS reminders to property management; Level 2 alarms activate on-site audible and visual alarms and remote video verification; Level 3 alarms trigger emergency alarms, linkage with the public security system, and notification of security personnel for on-site handling, among other severe responses.

[0043] According to an embodiment of the present invention, the method further includes: monitoring the target building and extracting alarm statistics within a preset time period, including alarm accuracy, alarm response delay, and alarm maintenance cost; processing the alarm accuracy, alarm response delay, and alarm maintenance cost through a preset alarm qualification assessment model to obtain an alarm qualification degree; comparing the alarm qualification degree with a preset alarm qualification degree threshold to obtain a second threshold comparison result; and determining whether the alarm system of the target building meets the requirements based on the second threshold comparison result.

[0044] It is particularly important to note that, to ensure the continuous and reliable operation of the building alarm system, a closed-loop evaluation mechanism needs to be established to dynamically verify the system performance. First, monitor the alarm operation status of the target building and extract core alarm statistics within a preset time period (e.g., 1 month, 3 months): alarm accuracy (the ratio of effective alarms to total alarms, reflecting identification accuracy), alarm response delay (the time taken from triggering an alarm to initiating the response mechanism, reflecting timeliness), and alarm maintenance cost (equipment maintenance, data transmission, and other related costs, aligning with low-cost design requirements). Then, input these three statistics into a preset alarm qualification assessment model. The model has built-in weighting coefficients for each indicator (e.g., alarm accuracy has the highest weight, balancing response efficiency and cost control). Through weighted calculation and standardization, a quantified alarm qualification score is output. Finally, compare the alarm qualification score with a preset alarm qualification threshold to obtain a second threshold comparison result: if the qualification score is higher than the threshold, the system meets the standards in accuracy, timeliness, and cost control, and is deemed compliant; if it is lower than the threshold, it is deemed non-compliant, requiring targeted optimization of threshold parameters, adjustment of the response mechanism, or equipment maintenance.

[0045] This invention discloses a low-cost building-level alarm method and system for multi-source signal recognition. It monitors the target building and collects real-time monitoring status data from preset monitoring points, as well as scene feature data of the surrounding area. The scene feature data is processed in conjunction with a preset set of recognition boundary thresholds to obtain a corrected set of recognition boundary thresholds. The monitoring status data is then compared with the corrected set of recognition boundary thresholds to obtain a set of status deviation rates. Further fusion processing is performed to obtain a comprehensive deviation. The alarm level is determined based on the comprehensive deviation, and a corresponding alarm response mechanism is matched, thereby achieving low-cost building-level alarm technology based on multi-source signal recognition.

[0046] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0047] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0048] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0049] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0050] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A low-cost building-level alarm method based on multi-source signal recognition, characterized in that, Includes the following steps: Monitor the target building and collect real-time monitoring status data of preset monitoring points as well as scene feature data of the area; The scene feature data is processed in conjunction with a preset set of identification boundary thresholds to obtain a corrected set of identification boundary thresholds. The monitoring status data is compared with the corrected set of identification boundary thresholds to obtain a set of status deviation rates. This set is then further fused to obtain a comprehensive deviation. The alarm level is determined based on the comprehensive deviation, and a corresponding alarm response mechanism is matched.

2. The low-cost building-level alarm method for multi-source signal recognition according to claim 1, characterized in that, The monitoring of the target building and the real-time collection of monitoring status data from preset monitoring points, as well as scene feature data of the area, include: monitoring the target building and collecting monitoring status data from preset monitoring points, including vibration, sound, and infrared radiation intensity; and simultaneously acquiring scene feature data of the area where the preset monitoring points are located, including area type, time period, and building floor.

3. The low-cost building-level alarm method for multi-source signal recognition according to claim 2, characterized in that, The step of processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set includes: obtaining a preset recognition boundary threshold set, including a preset vibration amplitude boundary threshold, a preset sound loudness boundary threshold, and a preset infrared radiation intensity boundary threshold; processing the preset recognition boundary threshold set in conjunction with the area type, time period, and building floor using a preset recognition boundary adjustment model to obtain a corrected recognition boundary threshold set; the corrected recognition boundary threshold set includes a corrected vibration amplitude boundary threshold, a corrected sound loudness boundary threshold, and a corrected infrared radiation intensity boundary threshold.

4. The low-cost building-level alarm method for multi-source signal identification according to claim 1, characterized in that, The step of comparing the monitored state data with the corrected identification boundary threshold set to obtain a state deviation rate set, and then performing further fusion processing to obtain a comprehensive deviation degree, includes: comparing the vibration, sound, and infrared radiation intensity with the three thresholds of the corrected identification boundary threshold set to obtain a state deviation rate set; the state deviation rate set includes vibration deviation rate, sound deviation rate, and infrared deviation rate; and processing the vibration deviation rate, sound deviation rate, and infrared deviation rate using a preset fusion rule algorithm to obtain a comprehensive deviation degree.

5. The low-cost building-level alarm method for multi-source signal recognition according to claim 4, characterized in that, The step of determining the alarm level based on the comprehensive deviation and matching the corresponding alarm response mechanism includes: comparing the comprehensive deviation with a preset comprehensive deviation threshold to obtain a first threshold comparison result; determining the alarm level based on the first threshold comparison result; the alarm level includes a level 1 alarm, a level 2 alarm, and a level 3 alarm; and matching the corresponding alarm response mechanism based on the alarm level.

6. The low-cost building-level alarm method for multi-source signal identification according to claim 1, characterized in that, Also includes: The system monitors the target building and extracts alarm statistics within a preset time period, including alarm accuracy, alarm response delay, and alarm maintenance cost. Based on the alarm accuracy, alarm response delay, and alarm maintenance cost, it processes these statistics using a preset alarm qualification assessment model to obtain an alarm qualification level. The alarm qualification level is then compared with a preset alarm qualification threshold to obtain a second threshold comparison result. Based on the second threshold comparison result, it is determined whether the alarm system of the target building meets the requirements.

7. A low-cost building-level alarm system with multi-source signal recognition, characterized in that, The system includes a memory and a processor. The memory contains a program for a low-cost building-level alarm method based on multi-source signal recognition. When the program is executed by the processor, the following steps are implemented: monitoring the target building and collecting real-time monitoring status data of preset monitoring points and scene feature data of the area; processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set; comparing the monitoring status data with the corrected recognition boundary threshold set to obtain a status deviation rate set, further performing fusion processing to obtain a comprehensive deviation degree; determining the alarm level based on the comprehensive deviation degree and matching the corresponding alarm response mechanism.

8. The low-cost building-level alarm system for multi-source signal recognition according to claim 7, characterized in that, The monitoring of the target building and the real-time collection of monitoring status data from preset monitoring points, as well as scene feature data of the area, include: monitoring the target building and collecting monitoring status data from preset monitoring points, including vibration, sound, and infrared radiation intensity; and simultaneously acquiring scene feature data of the area where the preset monitoring points are located, including area type, time period, and building floor.

9. The low-cost building-level alarm system for multi-source signal recognition according to claim 8, characterized in that, The step of processing the scene feature data in conjunction with a preset recognition boundary threshold set to obtain a corrected recognition boundary threshold set includes: obtaining a preset recognition boundary threshold set, including a preset vibration amplitude boundary threshold, a preset sound loudness boundary threshold, and a preset infrared radiation intensity boundary threshold; processing the preset recognition boundary threshold set in conjunction with the area type, time period, and building floor using a preset recognition boundary adjustment model to obtain a corrected recognition boundary threshold set; the corrected recognition boundary threshold set includes a corrected vibration amplitude boundary threshold, a corrected sound loudness boundary threshold, and a corrected infrared radiation intensity boundary threshold.

10. The low-cost building-level alarm system for multi-source signal recognition according to claim 7, characterized in that, The step of comparing the monitored state data with the corrected identification boundary threshold set to obtain a state deviation rate set, and then performing further fusion processing to obtain a comprehensive deviation degree, includes: comparing the vibration, sound, and infrared radiation intensity with the three thresholds of the corrected identification boundary threshold set to obtain a state deviation rate set; the state deviation rate set includes vibration deviation rate, sound deviation rate, and infrared deviation rate; and processing the vibration deviation rate, sound deviation rate, and infrared deviation rate using a preset fusion rule algorithm to obtain a comprehensive deviation degree.

Images