An automatic alarm method and system based on security and fire protection integration

Abstract

The present invention discloses an automatic alarm method and system based on the integration of security and fire protection, which relates to the technical field of the integration of security and fire protection. The method comprises the following steps: collecting spatial position relationships within a monitoring range to generate position coordinate data; collecting visual image data, thermal data, audio data and smoke data within the monitoring range; the automatic alarm method and system based on the integration of security and fire protection obtain multimodal monitoring data by collecting visual image data, thermal data, audio input data and smoke data and combining corresponding data with the same position coordinates, so as to simultaneously judge the type of abnormality according to the characteristics of visual image data and / or thermal data and / or audio input data and / or smoke data with the same position coordinates, thereby improving the accuracy of judgment and reducing the probability of false alarms.

Description

Technical Field

[0001] The present invention relates to the technical field of security and fire protection integration, and in particular to an automatic alarm method and system based on security and fire protection integration. Background Art

[0002] Integrated security and fire protection systems are a crucial component of modern urban infrastructure. They provide comprehensive, multi-layered security and fire protection services through intelligent and information-based technologies. Publication No. CN119067613A discloses an integrated security and fire protection management platform and its data management method, relating to the field of integrated security and fire protection technology. The system includes: acquiring environmental information for each security point within a target area; extracting features from this environmental information to obtain target features corresponding to each security point within the target area; calculating a risk score for each security point based on preset feature weights, corresponding feature scores, and corresponding risk expansion adjustment coefficients for each feature within the target features; designating security points with risk scores above a preset risk determination threshold as risky security points, and determining their corresponding risk levels based on the risk scores; matching target handling strategies for these risky security points from a preset policy library based on their risk levels; and executing security control commands to manage and control the risky security points. The primary goal is to integrate security and fire protection management and improve the efficiency and accuracy of emergency response.

[0003] However, there is still the problem of how to improve the accuracy of judging security consumption issues, improve the accuracy of alarms and reduce the probability of false alarms. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic alarm method and system based on the integration of security and fire protection to solve the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solution: an automatic alarm method based on the integration of security and fire protection, comprising the following steps:

[0006] S1. Collect the spatial position relationship within the monitoring range to generate position coordinate data;

[0007] S2, collect visual image data, thermal data, audio data and smoke data within the monitoring range;

[0008] S3. Positionally annotating the visual image data, thermal data, audio data, and smoke data based on the position coordinate data to generate visual image and coordinate data, thermal data and coordinate data, audio data and coordinate data, and smoke data and coordinate data, respectively;

[0009] S4, performing search processing for the same position coordinate data based on the visual image and coordinate data, the thermal sensor and coordinate data, the audio and coordinate data, and the smoke sensor and coordinate data, and generating multimodal monitoring data and multimodal monitoring and coordinate data respectively;

[0010] S5. Performing combination processing of the same abnormality type features on the visual image abnormality type feature data, the thermal abnormality type feature data, the audio abnormality type feature data, and the smoke abnormality type feature data to generate abnormality type multimodal feature data;

[0011] S6. Performing multimodal monitoring data abnormality type identification processing on the multimodal monitoring data and the abnormality type multimodal feature data to generate multimodal abnormality type identification data;

[0012] S7. If the multimodal abnormality type identification data indicates no abnormality, the monitoring is terminated and the process returns to step S2. Otherwise, an abnormality type processing solution is analyzed and processed based on the multimodal abnormality type identification data and the abnormality type processing solution data to generate abnormality type processing solution return data.

[0013] S8. Collect and combine the multimodal monitoring and coordinate data, multimodal abnormality type identification data, and abnormality type processing solution return data to generate multimodal monitoring alarm management data, and notify the corresponding linkage department of the multimodal monitoring and coordinate data, multimodal abnormality type identification data, and abnormality type processing solution return data according to the multimodal monitoring alarm management data.

[0014] Furthermore, the S1 includes the following steps:

[0015] S1. The satellite positioning coordinate data of the building and the floor location data of each monitoring module in the building are collected through a satellite positioning system and a building engineering structural diagram to generate location coordinate data A. The satellite positioning coordinates can be longitude and latitude and / or road address information (such as the intersection of XX Road and XX Road, No. XX on XX Road, XX Community, XX Building, etc.). The floor location data can be XX location on the Xth floor of Building X, where XX location can be represented by an edited address number or a direction (such as the southwest corner of the west corridor, etc.).

[0016] Furthermore, the S2 includes the following steps:

[0017] S21. Collect visual image information within the monitoring range through visual sensors (such as surveillance cameras) to generate visual image data ;

[0018] S22, collect thermal information within the monitoring range through infrared sensors (such as infrared cameras) to generate thermal data ;

[0019] S23, collect audio information within the monitoring range through acoustic sensors (such as microphones) to generate audio data ;

[0020] S24, collect smoke information within the monitoring range through the smoke sensor and generate smoke data .

[0021] Furthermore, the S3 includes the following steps:

[0022] S3, the visual image data , thermal data , audio data and smoke sensor data Perform annotation processing on position coordinate data separately to generate visual images and coordinate data respectively , thermal and coordinate data , audio and coordinate data and smoke sensor and coordinate data ,in , , , , , , , Respectively , , , The corresponding position coordinate data.

[0023] Furthermore, the S4 includes the following steps:

[0024] S41, based on the hash table in the visual image and coordinate data , thermal and coordinate data , audio and coordinate data and smoke sensor and coordinate data Search for data with the same location coordinate data and generate a multi-modal monitoring and coordinate data set , , Represents the multimodal monitoring and coordinate data of the oth position , , , , Represents the visual image data of the oth position respectively , thermal data , audio data and smoke sensor data , if the visual image data corresponding to the oth position / Thermal data / Audio data / Smoke sensor data If it does not exist / / / is 0, represents the position coordinate data A of the o-th position, Indicates the maximum number of locations corresponding to multimodal monitoring data;

[0025] S42, multi-modal monitoring and coordinate data in Delete and generate multimodal monitoring data set , Represents the multimodal monitoring data of the oth position .

[0026] Furthermore, the S5 includes the following steps:

[0027] S51. Constructing a visual image abnormality type feature data set , thermal anomaly type feature data set , audio anomaly type feature data set and smoke sensor anomaly type feature data set , , Represents the visual image feature data corresponding to the p-th abnormal type, Indicates the thermal characteristic data corresponding to the p-th abnormal type, Indicates the audio feature data corresponding to the p-th abnormal type, Indicates the smoke sensor feature data corresponding to the p-th abnormal type, Indicates the maximum number of exception types, where if the pth exception type corresponds to / / / If it does not exist, return 0 at the corresponding position;

[0028] S52. Collecting visual image abnormality type feature data , Thermal anomaly type feature data set , audio anomaly type feature data set Combine to generate a multimodal feature data set of abnormal types , , Indicates the multimodal feature data of the abnormal type corresponding to the p-th abnormal type. Abnormal types include but are not limited to access control abnormalities (such as unregistered people or vehicles entering), illegal parking (vehicles parked illegally in designated areas), objects thrown from high places, vandalism, abnormal falls (such as people not getting up within a certain period of time after falling), elevator abnormalities, abnormal circuit temperature, smoke abnormalities, and fire alarms.

[0029] Furthermore, the S6 includes the following steps:

[0030] S61, the multimodal monitoring data set Multimodal monitoring data With the abnormal type multimodal feature data set E Perform feature matching. If the matching fails, multimodal monitoring data No abnormalities;

[0031] S62, if the match is successful, search for the modal abnormality type feature data set E that matches the Matched , generate multimodal anomaly type recognition data , including the following steps:

[0032] S621, initialize algorithm parameters, gray wolf population size N, maximum number of iterations T;

[0033] S622, initializing a gray wolf population in the search space E of the abnormal type multimodal feature data set, that is, randomly generating N gray wolves in the search space E, each gray wolf corresponding to a potential solution;

[0034] S623, calculate the fitness of each individual gray wolf in the gray wolf population, that is, calculate the fitness of each individual gray wolf at its location. and multimodal surveillance data Matching fitness, and select the gray wolf individual with the best fitness as the Alpha Wolf, that is, as the leader of the gray wolf group when hunting, select the gray wolf individuals with the second best fitness and the third best fitness as the Beta Wolf and Delta Wolf, respectively, to provide assistance when the gray wolf group hunts, and the remaining gray wolf individuals as Omega wolves, which follow the Alpha Wolf, Beta Wolf and Delta Wolf when the gray wolf group hunts;

[0035] S624. The gray wolf population follows the alpha, beta, and delta wolves in their hunting behavior. That is, the gray wolf individuals move based on the positions of the alpha, beta, and delta wolves. The position update formula for the gray wolf individuals performing hunting behavior is as follows:

[0036] ,

[0037] ,

[0038] ,

[0039] in, Indicates the position of the i-th gray wolf individual, when j=1,2,3 Denotes the positions of Alpha Wolf, Beta Wolf and Delta Wolf respectively, t represents the current iteration number, A is the control vector used to control the search range. When , it means expanding the search scope to perform a global search. When , it means narrowing the search range for local development, and C is a coefficient vector used to control the position update direction of the gray wolf. 、 is a random number in [0,1], a is a linearly decreasing parameter, usually decreasing from 2 to 0, used to balance exploration and development, ;

[0040] S625, determine whether the maximum number of iterations T is reached, if not, return to step S623, if so, output the position corresponding to the alpha wolf , generate multimodal anomaly type recognition data .

[0041] Furthermore, the step S7 includes the following steps:

[0042] S71, collecting the abnormal type multimodal feature data in each abnormal type multimodal feature data set E The processing scheme generates the abnormal type processing scheme data set , for Corresponding exception type processing solution data, , , express The solution for the Qth type of linkage department, Indicates the maximum number of departments that can be linked. These departments can include security guards, cleaners, elevator repairmen, plumbing repairmen, electricians, and the fire department. This allows security personnel to be notified when general security anomalies occur. In the event of a fire or other fire-related anomaly, both the fire department and security personnel are notified simultaneously. This allows security personnel to guide evacuation in advance, ensuring smooth access to consumer channels, and allowing firefighters to arrive in time for firefighting.

[0043] S72: If the multimodal monitoring data If there is no abnormality, return to step S2. If multimodal abnormality type identification data is generated , then based on the hash table, search for the exception type processing solution data set F that matches Corresponding , generate exception type processing solution to return data .

[0044] Furthermore, the step S8 includes the following steps:

[0045] S81, the multimodal monitoring and coordinate data , multimodal anomaly type recognition data and exception type handling scheme return data Collect, combine, and generate multimodal monitoring and alarm management data ;

[0046] S82. Return data based on the abnormality type processing solution in the multimodal monitoring alarm management data G. correspond in ,Will 、 and The corresponding processing plan is notified to the corresponding q-th linkage department.

[0047] An automatic alarm system based on the integration of security and fire protection is used to implement an automatic alarm method based on the integration of security and fire protection, including a data entry module, a sensor module, a data integration module, a data processing and analysis module, and an alarm notification module;

[0048] The data entry module is used to enter the collected floor location data, generate location coordinate data, collect and enter visual image abnormality type feature data, thermal abnormality type feature data, audio abnormality type feature data, smoke abnormality type feature data, abnormality type multimodal feature data and abnormality type processing solution data;

[0049] The sensor module includes a visual sensor, an infrared sensor, an acoustic sensor and a smoke sensor;

[0050] The data integration module is used to search and process the same position coordinate data based on the visual image and coordinate data, the thermal sensor and coordinate data, the audio and coordinate data, and the smoke sensor and coordinate data, and respectively generate multimodal monitoring data and multimodal monitoring and coordinate data; perform combination processing of the same abnormal type features on the visual image abnormal type feature data, the thermal sensor abnormal type feature data, the audio abnormal type feature data, and the smoke sensor abnormal type feature data, and generate abnormal type multimodal feature data;

[0051] The data processing and analysis module is used to perform multimodal monitoring data abnormality type identification processing on the multimodal monitoring data and abnormality type multimodal feature data to generate multimodal abnormality type identification data; perform abnormality type processing solution analysis processing based on the multimodal abnormality type identification data and abnormality type processing solution data to generate abnormality type processing solution return data; collect and combine the multimodal monitoring and coordinate data, multimodal abnormality type identification data and abnormality type processing solution return data to generate multimodal monitoring alarm management data;

[0052] The alarm notification module is used to notify the corresponding linkage department of the multimodal monitoring and coordinate data, the multimodal abnormality type identification data and the abnormality type processing solution return data according to the multimodal monitoring alarm management data.

[0053] 1. Compared with the existing technology, the present invention provides an automatic alarm method and system based on the integration of security and fire protection. By collecting visual image data, thermal data, audio input data and smoke data and combining the corresponding data with the same position coordinates, multimodal monitoring data is obtained, so that the type of abnormality can be judged based on the characteristics of visual image data and / or thermal data and / or audio data and / or smoke data with the same position coordinates at the same time, thereby improving the accuracy of judgment and reducing the probability of false alarms.

[0054] 2. Compared with the existing technology, the automatic alarm method and system based on the integration of security and fire protection provided by the present invention reduces the risk of falling into local optimal solutions during the search process by simulating the feature search of gray wolves and the multimodal feature data of abnormal types that best matches the collected multimodal monitoring data. The simultaneous comparison and matching of multiple features during the search further improves the accuracy of the search. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0056] Figure 1 A diagram of method steps provided by an embodiment of the present invention;

[0057] Figure 2 This is a system structure block diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0059] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0060] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0061] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0062] The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0063] See also Figure 1 , an automatic alarm method based on security and fire protection integration, comprising the following steps:

[0064] S1. Collecting the spatial position relationship within the monitoring range to generate position coordinate data includes the following steps:

[0065] S1. The satellite positioning coordinate data of the building and the floor location data of each monitoring module in the building are collected through a satellite positioning system and a building engineering structural diagram to generate location coordinate data A. The satellite positioning coordinates can be longitude and latitude and / or road address information (such as the intersection of XX Road and XX Road, No. XX on XX Road, XX Community, XX Building, etc.). The floor location data can be XX location on the Xth floor of Building X, where XX location can be represented by an edited address number or a direction (such as the southwest corner of the west corridor, etc.).

[0066] S2. Collecting visual image data, thermal data, audio data, and smoke data within the monitoring range includes the following steps:

[0067] S21. Collect visual image information within the monitoring range through visual sensors (such as surveillance cameras) to generate visual image data ;

[0068] S22, collect thermal information within the monitoring range through infrared sensors (such as infrared cameras) to generate thermal data ;

[0069] S23, collect audio information within the monitoring range through acoustic sensors (such as microphones) to generate audio data ;

[0070] S24, collect smoke information within the monitoring range through the smoke sensor and generate smoke data .

[0071] S3. Position-marking the visual image data, thermal data, audio data, and smoke data based on the position coordinate data to generate visual image and coordinate data, thermal data and coordinate data, audio data and coordinate data, and smoke data and coordinate data, including the following steps:

[0072] S3. Visual image data , thermal data , audio data and smoke sensor data Perform annotation processing on position coordinate data separately to generate visual images and coordinate data respectively , thermal and coordinate data , audio and coordinate data and smoke sensor and coordinate data ,in , , , , , , , Respectively , , , The corresponding position coordinate data.

[0073] S4, searching for the same position coordinate data based on the visual image and coordinate data, the thermal image and coordinate data, the audio image and coordinate data, and the smoke image and coordinate data, and generating multimodal monitoring data and multimodal monitoring and coordinate data, respectively, including the following steps:

[0074] S41, based on the hash table in visual image and coordinate data , thermal and coordinate data , audio and coordinate data and smoke sensor and coordinate data Search for data with the same location coordinate data and generate a multi-modal monitoring and coordinate data set , , Represents the multimodal monitoring and coordinate data of the oth position , , , , Represents the visual image data of the oth position respectively , thermal data , audio data and smoke sensor data , if the visual image data corresponding to the oth position / Thermal data / Audio data / Smoke sensor data If it does not exist / / / is 0, represents the position coordinate data A of the o-th position, Indicates the maximum number of locations corresponding to multimodal monitoring data;

[0075] S42, multi-modal monitoring and coordinate data in Delete and generate multimodal monitoring data set , Represents the multimodal monitoring data of the oth position .

[0076] S5. Combining the same abnormality type features of the visual image abnormality type feature data, the thermal abnormality type feature data, the audio abnormality type feature data, and the smoke abnormality type feature data to generate abnormality type multimodal feature data, including the following steps:

[0077] S51. Constructing a visual image abnormality type feature data set , thermal anomaly type feature data set , audio anomaly type feature data set and smoke sensor anomaly type feature data set , , Represents the visual image feature data corresponding to the p-th abnormal type, Indicates the thermal characteristic data corresponding to the p-th abnormal type, Indicates the audio feature data corresponding to the p-th abnormal type, Indicates the smoke sensor feature data corresponding to the p-th abnormal type, Indicates the maximum number of exception types, where if the pth exception type corresponds to / / / If it does not exist, return 0 at the corresponding position;

[0078] S52. Collecting visual image abnormality type feature data , thermal anomaly type feature data set , audio anomaly type feature data set Combine to generate a multimodal feature data set of abnormal types , , Indicates the multimodal feature data of the abnormal type corresponding to the p-th abnormal type. Abnormal types include but are not limited to access control abnormalities (such as unregistered people or vehicles entering), illegal parking (vehicles parked illegally in designated areas), objects thrown from high places, vandalism, abnormal falls (such as people not getting up within a certain period of time after falling), elevator abnormalities, abnormal circuit temperature, smoke abnormalities, and fire alarms.

[0079] S6. Performing multimodal monitoring data abnormality type identification processing on the multimodal monitoring data and the abnormality type multimodal feature data to generate multimodal abnormality type identification data, including the following steps:

[0080] S61. Multimodal monitoring data collection Multimodal monitoring data In the multimodal feature data set E of abnormal types Perform feature matching. If the matching fails, multimodal monitoring data No abnormalities;

[0081] S62. If the match is successful, search for the modal abnormality type feature data set E that matches the Matched , generate multimodal anomaly type recognition data , including the following steps:

[0082] S621, initialize algorithm parameters, gray wolf population size N, maximum number of iterations T;

[0083] S622, initializing a gray wolf population in the search space E of the abnormal type multimodal feature data set, that is, randomly generating N gray wolves in the search space E, each gray wolf corresponding to a potential solution;

[0084] S623, calculate the fitness of each individual gray wolf in the gray wolf population, that is, calculate the fitness of each individual gray wolf at its location. and multimodal surveillance data Matching fitness, and select the gray wolf individual with the best fitness as the Alpha Wolf, that is, as the leader of the gray wolf group when hunting, select the gray wolf individuals with the second best fitness and the third best fitness as the Beta Wolf and Delta Wolf, respectively, to provide assistance when the gray wolf group hunts, and the remaining gray wolf individuals as Omega wolves, which follow the Alpha Wolf, Beta Wolf and Delta Wolf when the gray wolf group hunts;

[0085] S624. The gray wolf population follows the alpha, beta, and delta wolves in their hunting behavior. That is, the gray wolf individuals move based on the positions of the alpha, beta, and delta wolves. The position update formula for the gray wolf individuals performing hunting behavior is as follows:

[0086] ,

[0087] ,

[0088] ,

[0089] in, Indicates the position of the i-th gray wolf individual, when j=1,2,3 Denotes the positions of Alpha Wolf, Beta Wolf and Delta Wolf respectively, t represents the current iteration number, A is the control vector used to control the search range. When , it means expanding the search scope to perform a global search. When , it means narrowing the search range for local development, and C is a coefficient vector used to control the position update direction of the gray wolf. 、 is a random number in [0,1], a is a linearly decreasing parameter, usually decreasing from 2 to 0, used to balance exploration and development, ;

[0090] S625, determine whether the maximum number of iterations T is reached, if not, return to step S623, if so, output the position corresponding to the alpha wolf , generate multimodal anomaly type recognition data .

[0091] S7. If the multimodal abnormality type identification data indicates no abnormality, the monitoring is terminated and the process returns to step S2. Otherwise, the abnormality type processing solution is analyzed and processed based on the multimodal abnormality type identification data and the abnormality type processing solution data to generate abnormality type processing solution return data, including the following steps:

[0092] S71. Collect the multimodal feature data of each abnormal type in the multimodal feature data set E. The processing scheme generates the abnormal type processing scheme data set , for Corresponding exception type processing solution data, , , express The solution for the Qth type of linkage department, Indicates the maximum number of departments that can be linked. These departments can include security guards, cleaners, elevator repairmen, plumbing repairmen, electricians, and the fire department. This allows security personnel to be notified when general security anomalies occur. In the event of a fire or other fire-related anomaly, both the fire department and security personnel are notified simultaneously. This allows security personnel to guide evacuation in advance, ensuring smooth access to consumer channels, and allowing firefighters to arrive in time for firefighting.

[0093] S72, if multimodal monitoring data If there is no abnormality, return to step S2. If multimodal abnormality type identification data is generated , then based on the hash table, search for the exception type processing solution data set F that matches Corresponding , generate exception type processing solution to return data .

[0094] S8. Collect and combine the multimodal monitoring and coordinate data, the multimodal anomaly type identification data, and the anomaly type processing solution return data to generate multimodal monitoring alarm management data. According to the multimodal monitoring alarm management data, the multimodal monitoring and coordinate data, the multimodal anomaly type identification data, and the anomaly type processing solution return data are notified to the corresponding linkage department, including the following steps:

[0095] S81, multi-modal monitoring and coordinate data , multimodal anomaly type recognition data and exception type handling scheme return data Collect, combine, and generate multimodal monitoring and alarm management data ;

[0096] S82. Return data based on the abnormality type processing solution in the multimodal monitoring alarm management data G. correspond in ,Will 、 and The corresponding processing plan is notified to the corresponding q-th linkage department.

[0097] See also Figure 2 , the present invention also provides an automatic alarm system based on the integration of security and fire protection, which is used to execute an automatic alarm method based on the integration of security and fire protection, including a data entry module, a sensor module, a data integration module, a data processing and analysis module, and an alarm notification module;

[0098] The data entry module is used to enter the collected floor location data, generate location coordinate data, collect and enter visual image abnormality type feature data, thermal abnormality type feature data, audio abnormality type feature data, smoke abnormality type feature data, abnormality type multimodal feature data and abnormality type processing plan data;

[0099] The sensor module includes visual sensor, infrared sensor, acoustic sensor and smoke sensor;

[0100] The data integration module is used to search and process the same position coordinate data based on the visual image and coordinate data, thermal sensor and coordinate data, audio and coordinate data, and smoke sensor and coordinate data, and generate multimodal monitoring data and multimodal monitoring and coordinate data respectively; and perform combination processing of the same abnormal type features on the visual image abnormal type feature data, thermal sensor abnormal type feature data, audio abnormal type feature data, and smoke sensor abnormal type feature data to generate abnormal type multimodal feature data;

[0101] The data processing and analysis module is used to perform multimodal monitoring data anomaly type identification processing on the multimodal monitoring data and the multimodal feature data of the anomaly type, and generate multimodal anomaly type identification data; perform an analysis and processing of the anomaly type processing solution based on the multimodal anomaly type identification data and the anomaly type processing solution data, and generate anomaly type processing solution return data; collect and combine the multimodal monitoring and coordinate data, the multimodal anomaly type identification data, and the anomaly type processing solution return data, and generate multimodal monitoring alarm management data;

[0102] The alarm notification module is used to notify the corresponding linkage department of the multimodal monitoring and coordinate data, multimodal abnormality type identification data and abnormality type processing solution return data based on the multimodal monitoring alarm management data.

[0103] The above only describes certain exemplary embodiments of the present invention by way of illustration. It is undeniable that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention.

Claims

1. An automatic alarm method based on the integration of security and fire protection, characterized by: The following steps are involved: S1. Collect the spatial position relationship within the monitoring range to generate position coordinate data; S2, collect visual image data, thermal data, audio data and smoke data within the monitoring range; S3. Positionally annotating the visual image data, thermal data, audio data, and smoke data based on the position coordinate data to generate visual image and coordinate data, thermal data and coordinate data, audio data and coordinate data, and smoke data and coordinate data, respectively; S4. Searching for identical position coordinate data based on the visual image and coordinate data, the thermal image and coordinate data, the audio image and coordinate data, and the smoke image and coordinate data to generate multimodal monitoring data and multimodal monitoring and coordinate data, respectively. The position coordinate data in the multimodal monitoring and coordinate data is deleted to generate a multimodal monitoring data set. S5. Perform combination processing of the same abnormality type features on the visual image abnormality type feature data, the thermal abnormality type feature data, the audio abnormality type feature data, and the smoke abnormality type feature data to generate abnormality type multimodal feature data and an abnormality type multimodal feature data set; S6. Performing multimodal monitoring data abnormality type identification processing on the multimodal monitoring data and the abnormality type multimodal feature data to generate multimodal abnormality type identification data, including the following steps: S61: performing feature matching on the multimodal monitoring data in the multimodal monitoring data set and the abnormal type multimodal feature data in the abnormal type multimodal feature data set; if the matching is unsuccessful, the multimodal monitoring data has no abnormality; S62: If the match is successful, searching the modal abnormality type feature data set for abnormality type multimodal feature data that matches the multimodal monitoring data to generate multimodal abnormality type identification data, including the following steps: S621, initialize algorithm parameters, gray wolf population size N, maximum number of iterations T; S622, initializing a gray wolf population in the search space of the abnormal type multimodal feature data set E; S623, calculating the fitness of each gray wolf individual in the gray wolf population, and selecting the gray wolf individual with the best fitness as the alpha wolf, selecting the gray wolf individuals with the second best fitness as the beta wolf and the delta wolf, respectively, and selecting the remaining gray wolf individuals as the omega wolves; S624. The gray wolf population follows the alpha wolf, beta wolf, and delta wolf to hunt. The position update formula of the gray wolf individuals performing hunting behavior is as follows: ， ， ， in, Indicates the position of the i-th gray wolf individual, when j=1,2,3 Represent the positions of Alpha Wolf, Beta Wolf and Delta Wolf respectively, t represents the current iteration number, A is the control vector, C is the coefficient vector, 、 is a random number in [0,1], and a is a linearly decreasing parameter; S625: Determine whether the maximum number of iterations T has been reached. If not, return to step S623. If so, output the multimodal feature data of the abnormal type corresponding to the alpha wolf position to generate multimodal abnormal type recognition data. ; S7. If the multimodal abnormality type identification data indicates no abnormality, the monitoring is terminated and the process returns to step S2. Otherwise, an abnormality type processing solution is analyzed and processed based on the multimodal abnormality type identification data and the abnormality type processing solution data to generate abnormality type processing solution return data. S8. Collect and combine the multimodal monitoring and coordinate data, multimodal abnormality type identification data, and abnormality type processing solution return data to generate multimodal monitoring alarm management data, and notify the corresponding linkage department of the multimodal monitoring and coordinate data, multimodal abnormality type identification data, and abnormality type processing solution return data according to the multimodal monitoring alarm management data.

2. The automatic alarm method based on the integration of security and fire protection according to claim 1, characterized in that: Said S1 comprises the following steps: S1. The satellite positioning coordinate data of the building and the floor position data of each monitoring module in the building are collected through a satellite positioning system and a building engineering structure diagram to generate position coordinate data A.

3. The automatic alarm method based on the integration of security and fire protection according to claim 2, characterized in that: The S2 comprises the following steps: S21. Collect visual image information within the monitoring range through visual sensors to generate visual image data ; S22, collect thermal information within the monitoring range through infrared sensors to generate thermal data ; S23, collect audio information within the monitoring range through acoustic sensors to generate audio data ; S24, collect smoke information within the monitoring range through the smoke sensor and generate smoke data .

4. The automatic alarm method based on the integration of security and fire protection according to claim 3 is characterized in that: The S3 includes the following steps: S3, the visual image data , thermal data , audio data and smoke sensor data Perform annotation processing on position coordinate data separately to generate visual images and coordinate data respectively , thermal and coordinate data , audio and coordinate data and smoke sensor and coordinate data .

5. The automatic alarm method based on the integration of security and fire protection according to claim 4 is characterized in that: The S4 comprises the following steps: S41, based on the hash table in the visual image and coordinate data , thermal and coordinate data , audio and coordinate data and smoke sensor and coordinate data Search for data with the same location coordinate data and generate a multi-modal monitoring and coordinate data set , , Represents the multimodal monitoring and coordinate data of the oth position , , , , Represents the visual image data of the oth position respectively , thermal data , audio data and smoke sensor data , represents the position coordinate data A of the o-th position, Indicates the maximum number of locations corresponding to multimodal monitoring data; S42, multi-modal monitoring and coordinate data in Delete and generate multimodal monitoring data set , Represents the multimodal monitoring data of the oth position .

6. The automatic alarm method based on the integration of security and fire protection according to claim 5, characterized in that: The S5 comprises the following steps: S51. Constructing a visual image abnormality type feature data set , thermal anomaly type feature data set , audio anomaly type feature data set and smoke sensor anomaly type feature data set , , Represents the visual image feature data corresponding to the p-th abnormal type, Indicates the thermal characteristic data corresponding to the p-th abnormal type, Indicates the audio feature data corresponding to the p-th abnormal type, Indicates the smoke sensor feature data corresponding to the p-th abnormal type, Indicates the maximum number of exception types; S52. Collecting visual image abnormality type feature data , Thermal anomaly type feature data set , audio anomaly type feature data set Combine to generate a multimodal feature data set of abnormal types , , Represents the multimodal feature data of the abnormal type corresponding to the p-th abnormal type.

7. The automatic alarm method based on the integration of security and fire protection according to claim 6, characterized in that: The S7 comprises the following steps: S71, collecting the abnormal type multimodal feature data in each abnormal type multimodal feature data set E The processing scheme generates the abnormal type processing scheme data set , for Corresponding exception type processing solution data, , , express The solution for the Qth type of linkage department, Indicates the maximum number of linkage departments; S72: If the multimodal monitoring data If there is no abnormality, return to step S2. If multimodal abnormality type identification data is generated , then based on the hash table, search for the exception type processing solution data set F that matches Corresponding , generate exception type processing solution to return data .

8. The automatic alarm method based on the integration of security and fire protection according to claim 7, characterized in that: The S8 comprises the following steps: S81, the multimodal monitoring and coordinate data , multimodal anomaly type recognition data and exception type handling scheme return data Collect, combine, and generate multimodal monitoring and alarm management data ; S82. Return data based on the abnormality type processing solution in the multimodal monitoring alarm management data G. correspond in ,Will 、 and The corresponding processing plan is notified to the corresponding q-th linkage department.

9. An automatic alarm system based on the integration of security and fire protection, used to execute the automatic alarm method based on the integration of security and fire protection according to any one of claims 1 to 8, characterized in that: Including data entry module, sensor module, data integration module, data processing and analysis module, and alarm notification module; The data entry module is used to enter the collected floor location data, generate location coordinate data, collect and enter visual image abnormality type feature data, thermal abnormality type feature data, audio abnormality type feature data, smoke abnormality type feature data, abnormality type multimodal feature data and abnormality type processing solution data; The sensor module includes a visual sensor, an infrared sensor, an acoustic sensor and a smoke sensor; The data integration module is used to search and process the same position coordinate data based on the visual image and coordinate data, the thermal sensor and coordinate data, the audio and coordinate data, and the smoke sensor and coordinate data, and respectively generate multimodal monitoring data and multimodal monitoring and coordinate data; perform combination processing of the same abnormal type features on the visual image abnormal type feature data, the thermal sensor abnormal type feature data, the audio abnormal type feature data, and the smoke sensor abnormal type feature data, and generate abnormal type multimodal feature data; The data processing and analysis module is used to perform multimodal monitoring data abnormality type identification processing on the multimodal monitoring data and the abnormality type multimodal feature data to generate multimodal abnormality type identification data; perform abnormality type processing solution analysis processing based on the multimodal abnormality type identification data and the abnormality type processing solution data to generate abnormality type processing solution return data; Collecting and combining the multimodal monitoring and coordinate data, the multimodal anomaly type identification data, and the anomaly type processing solution return data to generate multimodal monitoring alarm management data; The alarm notification module is used to notify the corresponding linkage department of the multimodal monitoring and coordinate data, the multimodal abnormality type identification data and the abnormality type processing solution return data according to the multimodal monitoring alarm management data.

Images