Intelligent security information management method and device and storage medium

Abstract

The invention provides an intelligent security and protection information management method and device and a storage medium, and relates to the technical field of intelligent security and protection, and the method comprises the steps: collecting and detecting clear image data of a community key region, extracting a face region, cutting and storing the face region as an independent image, carrying out the feature extraction of an extracted face through a pre-trained deep learning model, and carrying out the feature extraction; the method comprises the following steps: acquiring feature vectors of a person, comparing the feature vectors with a registered database, judging the type of the person by calculating the Euclidean distance between the feature vectors, further judging whether the person is a temporary person after the person is identified as a registered person, and monitoring the residence time; and if the preset threshold value is exceeded, giving an alarm, and tracking the position of an unregistered person. According to the scheme, video streams are analyzed in real time, behaviors of registered personnel are monitored, if abnormal behaviors are found, an alarm is automatically given, related images are recorded, a self-learning mechanism is constructed, a database is updated in time through feedback of security personnel, and the scheme provides a more intelligent solution for community security management.

Description

Technical Field

[0001] The present invention relates to the field of intelligent security technology, and in particular to an intelligent security information management method, device and storage medium. Background Art

[0002] In modern society, security monitoring systems have become an important part of maintaining public safety and are widely used in communities, shopping malls, transportation hubs and other places. Traditional security monitoring systems usually rely on fixed cameras for recording and rely on manual inspections by security personnel to identify potential safety hazards. Although this method can monitor abnormal events to a certain extent, it has obvious shortcomings. First, manual inspections are not only inefficient, but also easily limited by the experience and judgment of security personnel, resulting in frequent omissions and false alarms. Secondly, traditional monitoring systems often have difficulty in accurately identifying dynamic scenes and complex behaviors, especially in the case of large personnel flow or poor lighting conditions, which affects image quality and recognition accuracy. In addition, traditional systems lack self-learning capabilities and cannot be dynamically adjusted according to the changing environment and user needs, resulting in lagging technology updates and difficulty in meeting growing security needs.

[0003] On the technical level, although some monitoring systems have begun to introduce basic image processing technology and simple behavior analysis algorithms, these technologies still have limitations. These algorithms usually rely on fixed rules and thresholds and cannot effectively handle diverse behavior patterns, resulting in an inability to adapt to complex security scenarios in practical applications. In addition, the existing feature extraction and comparison methods have low computational efficiency and poor real-time performance when dealing with high-dimensional feature spaces. Once the system encounters new behavior patterns or abnormal events, it often lacks the ability to respond quickly and cannot issue warnings in time. In summary, traditional security monitoring technology has deficiencies in intelligence, accuracy, real-time, and adaptability, and it is urgent to introduce more advanced technical means to improve the overall efficiency and reliability of security management.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent security information management method and system to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The intelligent security information management method includes the following specific steps:

[0008] Step 1: Collect clear image data of key areas in the community, perform face detection on the collected images, use deep neural networks to identify and extract face areas, apply detection algorithms to each frame of the image, obtain the coordinates of the face, and crop and store them as independent face images;

[0009] Step 2: Use the pre-trained deep learning model to extract features from the extracted face image and compare it with the stored registered database. By calculating the Euclidean distance between the extracted feature vector and the registered vector, the type of person is determined and divided into registered and unregistered categories;

[0010] Step 3: Classify the image information according to the recognition results. If it is recognized as a registered person type, further determine whether it is a temporary person and calculate its stay time. If it exceeds the set threshold, an alarm will be issued. At the same time, the location information of unregistered persons is obtained and tracked;

[0011] Step 4: Analyze the video stream in real time, monitor the bad behavior of the registered personnel, and use the behavior recognition algorithm to predict the behavior. If abnormal behavior is detected, the system will automatically issue an alarm and record the relevant image information for subsequent analysis;

[0012] Step 5: Build a self-learning mechanism where security personnel provide feedback on each alarm and update the database in a timely manner. At the same time, regularly retrain the model with new data to improve recognition accuracy and system adaptability.

[0013] Furthermore, the key areas include the gates of the community, garage entrances, and parks, squares, and children's playgrounds in the community;

[0014] Get images from the camera or video stream, and preprocess the images, including resizing and normalizing them, extract face images from the collected image information, and use the Caffe model provided by OpenCV to perform face detection;

[0015] For each frame To locate the face area, the expression is as follows:

[0016]

[0017] in, is the current frame image, is the coordinates of the detected face area, specifically the coordinates of the upper left corner and the lower right corner, It is a function call, which indicates the operation of face detection on the current frame image;

[0018] According to the detected Coordinates, draw a rectangular box on the original image to identify the face, cut out the face area from the original image according to these coordinates, and store it as an independent face image, denoted as .

[0019] Furthermore, the pre-trained deep learning model is used to extract facial features. The expression is as follows:

[0020]

[0021] in, is the extracted facial feature vector, which contains various attributes of the face. is the cropped face image, Indicates calling the pre-trained deep learning model Perform forward propagation to extract facial features; the various attributes of the face are: facial contour, eye position, nose shape, mouth features, and skin texture features;

[0022] The Euclidean distance between the extracted feature vector and the registered feature vector is calculated according to the following formula:

[0023]

[0024] in, It is the Euclidean distance value, which indicates the similarity of two facial features. The larger the value, the greater the difference between the two facial feature vectors and the lower the similarity. is the value of the registered face feature vector in the i-th dimension, is the value of the face feature vector extracted from the person to be identified in the i-th dimension, is the dimension of the feature vector;

[0025] like , then the person to be identified is determined to be a registered person type, otherwise the person to be identified is determined to be an unregistered person type.

[0026] Furthermore, if the person is identified as a registered person, the entry record is compared to determine whether the person is a temporary person. The expression is as follows:

[0027]

[0028] Indicates the judgment result, which includes and , Indicates that the person is a temporary staff member. Indicates that the person is a non-temporary employee. Indicates calling a function to check the given recognition Is it in the temporary personnel list? is an input parameter indicating the person with the minimum Euclidean distance value. ;

[0029] If the person is a temporary employee, obtain his / her stay time:

[0030]

[0031] in, is the dwell time, is the current time, The time for people to enter the community;

[0032] like If the preset temporary personnel stay time is exceeded, an alarm will be issued;

[0033] Unregistered persons are identified through image acquisition devices within the community and assigned a temporary , and at the same time obtain the location information of unregistered persons and track them. The expression is as follows:

[0034]

[0035] in, is a variable used to store the location information of unregistered persons. Is a function call, inside the function will be based on Query the current location of the unregistered person and return the corresponding location information;

[0036] Location information Send it to community security personnel and control the image acquisition equipment for real-time tracking.

[0037] Furthermore, the video stream is analyzed in real time to monitor the bad behavior of registered personnel, and behavior recognition algorithms are used to predict behavior. If abnormal behavior is detected, the system automatically issues an alarm and records relevant image information for subsequent analysis;

[0038] Use behavior recognition algorithms to analyze video streams and detect potential bad behaviors. The expression is as follows:

[0039]

[0040] in, is the predicted behavior category, For the processed video stream, is a function call that identifies Behavioral patterns in order to identify and classify human behavior;

[0041] If improper behavior is detected, the system will issue an alarm and record relevant image information.

[0042] Furthermore, a self-learning mechanism is constructed, and security personnel provide feedback on each alarm situation and update the database in a timely manner. The expression is as follows:

[0043]

[0044] in, Provide security personnel with feedback on alarm situations. This is a function that indicates updating the database;

[0045] The feedback information includes: alarm accuracy, security personnel confirm whether the alarm is true and provide relevant observations; behavior description, security personnel's specific description of the incident, the behavior and situation description of the personnel involved; suggestions and improvements, improvement suggestions put forward by security personnel to help the system better identify and judge similar incidents;

[0046] Regularly use newly collected data to retrain the model to improve recognition accuracy.

[0047] The present invention further provides an intelligent security information management device, which is used to execute the above-mentioned intelligent security information management method, including:

[0048] The image acquisition and detection module is used to collect clear image data of key areas in the community, perform face detection on the collected images, use deep neural networks to identify and extract face areas, obtain the coordinates of the face by applying the detection algorithm to each frame of the image, and crop and store it as an independent face image;

[0049] The feature extraction and comparison module is used to extract features from the extracted face images using a pre-trained deep learning model and compare them with the stored registered database. By calculating the Euclidean distance between the extracted feature vector and the registered vector, the type of person is determined and divided into registered and unregistered categories.

[0050] The recognition and alarm judgment module is used to classify the image information according to the recognition results. If it is recognized as a registered person type, it is further determined whether it is a temporary person and its stay time is calculated. If it exceeds the set threshold, an alarm is issued. At the same time, the location information of unregistered persons is obtained and tracked;

[0051] Behavior monitoring and prediction module, which is used to analyze video streams in real time, monitor the bad behavior of registered personnel, and use behavior recognition algorithms to predict behavior. If abnormal behavior is detected, the system automatically issues an alarm and records relevant image information for subsequent analysis;

[0052] The self-learning update mechanism module is used to build a self-learning mechanism. Security personnel provide feedback on each alarm situation and update the database in a timely manner. At the same time, new data is used to retrain the model regularly to improve recognition accuracy and system adaptability.

[0053] The present invention also includes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned intelligent security information management method can be implemented.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] The implementation of this intelligent security information management method not only improves the efficiency of rapid identification of personnel identities and significantly reduces the false alarm rate, but also enhances the monitoring ability of unregistered personnel, ensuring community safety. Through real-time behavior monitoring and abnormal behavior prediction, the system can issue alarms in a timely manner to reduce potential security risks. At the same time, the introduction of the self-learning mechanism enables the security system to be continuously improved and optimized based on feedback, improving the overall identification accuracy and system adaptability, thereby effectively improving the overall level of intelligent security. In general, this solution provides a more intelligent and dynamic solution for community security management, enhancing the work efficiency and responsiveness of security personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0057] Figure 2 It is a schematic diagram of the device module of the present invention. DETAILED DESCRIPTION

[0058] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0059] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0060] Example:

[0061] See also Figure 1 , the present invention provides a technical solution:

[0062] The intelligent security information management method includes the following specific steps:

[0063] Step 1: Collect clear image data of key areas in the community, perform face detection on the collected images, use deep neural networks to identify and extract face areas, apply detection algorithms to each frame of the image, obtain the coordinates of the face, and crop and store them as independent face images;

[0064] In this embodiment, the key areas include the gate of the community, the garage entrance, and the park, square, and children's playground of the community;

[0065] Get images from the camera or video stream, and preprocess the images, including resizing and normalizing them, extract face images from the collected image information, and use the Caffe model provided by OpenCV to perform face detection;

[0066] For each frame To locate the face area, the expression is as follows:

[0067]

[0068] in, is the current frame image, is the coordinates of the detected face area, specifically the coordinates of the upper left corner and the lower right corner, It is a function call, which indicates the operation of face detection on the current frame image;

[0069] According to the detected Coordinates, draw a rectangular box on the original image to identify the face, cut out the face area from the original image according to these coordinates, and store it as an independent face image, denoted as .

[0070] The main advantage of step 1 is that face detection and extraction through deep neural networks can significantly improve the accuracy and efficiency of face recognition. Compared with traditional rule-based methods, this step uses deep learning models to automatically adapt to different environments and lighting conditions, thereby maintaining stable recognition performance in complex scenes. By processing each frame of the image in real time, the face area can be quickly obtained and cropped for storage, ensuring higher quality of basic data for subsequent recognition and reducing the probability of missed detection and false detection.

[0071] In this patent solution, the use of step 1 can provide high-quality basic data for the overall system, ensuring the accuracy and effectiveness of subsequent steps. Accurate face detection and extraction lays a good foundation for the process of feature extraction and comparison, thereby improving the efficiency of the overall security system in personnel identification and classification. In addition, real-time processing capabilities enable the system to quickly respond to potential security threats, enhance the community's security protection capabilities, create favorable conditions for subsequent behavior monitoring and abnormal behavior detection, and improve the intelligence level of the entire security information management.

[0072] Step 2: Use the pre-trained deep learning model to extract features from the extracted face image and compare it with the stored registered database. By calculating the Euclidean distance between the extracted feature vector and the registered vector, the type of person is determined and divided into registered and unregistered categories;

[0073] In this embodiment, a pre-trained deep learning model is used to extract facial features, and the expression is as follows:

[0074]

[0075] in, is the extracted facial feature vector, which contains various attributes of the face. is the cropped face image, Indicates calling the pre-trained deep learning model Perform forward propagation to extract facial features; the various attributes of the face are: facial contour, eye position, nose shape, mouth features, and skin texture features;

[0076] The Euclidean distance between the extracted feature vector and the registered feature vector is calculated according to the following formula:

[0077]

[0078] in, It is the Euclidean distance value, which indicates the similarity of two facial features. The larger the value, the greater the difference between the two facial feature vectors and the lower the similarity. is the value of the registered face feature vector in the i-th dimension, is the value of the face feature vector extracted from the person to be identified in the i-th dimension, is the dimension of the feature vector;

[0079] like , then the person to be identified is determined to be a registered person type, otherwise the person to be identified is determined to be an unregistered person type.

[0080] In image recognition and face recognition, Euclidean distance is used to compare feature vectors to determine whether images belong to the same category. In multidimensional space, Euclidean distance can effectively measure the similarity between different points.

[0081] The main advantage of step 2 is that it uses a pre-trained deep learning model for facial feature extraction and database comparison, which significantly improves the accuracy and speed of face recognition. Compared with traditional manual feature extraction methods, deep learning models can automatically learn and extract more complex and high-dimensional features, thereby improving robustness to various facial changes, such as angle, lighting, expression, etc. In addition, by calculating the Euclidean distance between feature vectors for comparison, individual identity can be quickly and effectively determined, reducing the occurrence of misjudgment and missed judgment.

[0082] In this patent solution, the use of step 2 can provide fast and accurate personnel classification results for the overall security system, ensuring the effectiveness of subsequent processing. By accurately identifying registered and unregistered personnel, the system can quickly respond to potential security threats and take corresponding measures, such as issuing alarms and tracking unregistered personnel. This efficient identification mechanism not only improves the community's security protection capabilities, but also provides a reliable foundation for subsequent behavior monitoring and abnormal behavior detection, thereby promoting the intelligent and automated development of the entire security information management system.

[0083] Step 3: Classify the image information according to the recognition results. If it is recognized as a registered person type, further determine whether it is a temporary person and calculate its stay time. If it exceeds the set threshold, an alarm will be issued. At the same time, the location information of unregistered persons is obtained and tracked;

[0084] In this embodiment, if the type of person is identified as a registered person, whether the person is a temporary person is determined by comparing the storage records. The expression is as follows:

[0085]

[0086] Indicates the judgment result, which includes and , Indicates that the person is a temporary staff member. Indicates that the person is a non-temporary employee. Indicates calling a function to check the given recognition Is it in the temporary personnel list? is an input parameter indicating the person with the minimum Euclidean distance value. ;

[0087] If the person is a temporary employee, obtain his / her stay time:

[0088]

[0089] in, is the dwell time, is the current time, The time for people to enter the community;

[0090] like If the preset temporary personnel stay time is exceeded, an alarm will be issued;

[0091] Unregistered persons are identified through image acquisition devices within the community and assigned a temporary , and at the same time obtain the location information of unregistered persons and track them. The expression is as follows:

[0092]

[0093] in, is a variable used to store the location information of unregistered persons. Is a function call, inside the function will be based on Query the current location of the unregistered person and return the corresponding location information;

[0094] Location information Send it to community security personnel and control the image acquisition equipment for real-time tracking.

[0095] The main advantage of step 3 is that by monitoring and judging the stay time of registered personnel, the accuracy and response speed of community security management can be effectively improved. Compared with traditional security monitoring methods, relying solely on video recording or manual inspections cannot monitor the behavior and stay time of personnel in real time, which can easily lead to the omission of safety hazards. This step can quickly identify potential abnormal behaviors by automatically calculating the stay time and setting the threshold, significantly improving the intelligence level of the security system.

[0096] In this patent solution, the use of step 3 can effectively enhance the security system's ability to dynamically monitor personnel activities and ensure effective management of all personnel in the community, especially temporary personnel. By issuing alarms in a timely manner, the system can quickly respond to potential security threats and ensure community safety. At the same time, the tracking and processing of the location information of unregistered personnel improves the accuracy of security warnings, promotes the intelligent and automated development of the overall security information management method, and provides a solid foundation for subsequent behavior monitoring and anomaly detection, thereby improving the security protection capabilities of the entire community.

[0097] Step 4: Analyze the video stream in real time, monitor the bad behavior of the registered personnel, and use the behavior recognition algorithm to predict the behavior. If abnormal behavior is detected, the system will automatically issue an alarm and record the relevant image information for subsequent analysis;

[0098] In this embodiment, the video stream is analyzed in real time to monitor the bad behavior of registered personnel, and the behavior recognition algorithm is used to predict the behavior. If abnormal behavior is detected, the system automatically issues an alarm and records the relevant image information for subsequent analysis;

[0099] Use behavior recognition algorithms to analyze video streams and detect potential bad behaviors. The expression is as follows:

[0100]

[0101] in, is the predicted behavior category, For the processed video stream, is a function call that identifies Behavioral patterns in order to identify and classify human behavior;

[0102] If bad behavior is detected, the system will sound an alarm and record relevant image information; bad behavior includes: fighting or violence, destruction of public property, theft, harassment, alcohol or drug abuse, and abnormal wandering;

[0103] The logic behind detecting bad behavior is as follows: construct a behavior recognition model based on a convolutional neural network, obtain multiple video data, and label the video data with normal and bad behavior labels, train the model to obtain a trained behavior recognition model, and input the real-time video data into the model to obtain the behavior label of the person.

[0104] The main advantage of step 4 is that it analyzes the video stream in real time to monitor the bad behavior of registered personnel. This method can efficiently and quickly identify potential security threats. Compared with traditional security methods that rely on manual monitoring or reviewing videos after the fact, this step uses advanced behavior recognition algorithms to detect and predict abnormal behavior in real time, which helps to take timely measures to reduce the occurrence of security incidents. This automated monitoring method significantly improves the response speed and accuracy of the security system, ensuring a safe environment for the community.

[0105] In this patent solution, the use of step 4 can provide more comprehensive and proactive security protection for the overall security system. By real-time monitoring of the behavior of registered personnel, the system can not only promptly detect and alarm abnormal situations, but also record relevant image information to provide a basis for subsequent analysis. This intelligent behavior detection mechanism enhances the community's early warning ability for bad behavior, thereby improving residents' sense of security, while providing data support for community security management and promoting the continuous optimization and intelligent upgrade of the security system.

[0106] Step 5: Build a self-learning mechanism, where security personnel provide feedback on each alarm and update the database in a timely manner. At the same time, regularly use new data to retrain the model to improve recognition accuracy and system adaptability;

[0107] In this embodiment, a self-learning mechanism is constructed, and security personnel provide feedback on each alarm situation and update the database in a timely manner. The expression is as follows:

[0108]

[0109] in, Provide security personnel with feedback on alarm situations. This is a function that indicates updating the database;

[0110] The feedback information includes: alarm accuracy, security personnel confirm whether the alarm is true and provide relevant observations; behavior description, security personnel's specific description of the incident, the behavior and situation description of the personnel involved; suggestions and improvements, improvement suggestions put forward by security personnel to help the system better identify and judge similar incidents;

[0111] Regularly use newly collected data to retrain the model to improve recognition accuracy.

[0112] The main advantage of step 5 is to build a self-learning mechanism, so that the security system can continuously optimize and improve the recognition accuracy through the feedback of security personnel. Compared with the existing technology, traditional security systems often rely on static rules and fixed models, which are difficult to adapt to the ever-changing environment and needs. By collecting and analyzing the feedback information from security personnel, the system can dynamically update the database and model, enhance its adaptive ability, and thus more effectively deal with various complex security threats in practical applications.

[0113] In this patent solution, the adoption of step 5 can significantly improve the intelligence level and practicality of the overall security system. Through the continuous self-learning process, the system can effectively integrate historical data and user feedback, timely adjust the recognition algorithm and strategy, and thus improve the ability to predict and handle abnormal events. This feedback mechanism not only enhances the response speed and accuracy of the system, but also promotes the positive interaction between security personnel and technical systems, and ultimately achieves a comprehensive upgrade of community security management, providing residents with a safer and more reliable living environment.

[0114] See also Figure 2 , an intelligent security information management device, comprising:

[0115] The image acquisition and detection module is used to collect clear image data of key areas in the community, perform face detection on the collected images, use deep neural networks to identify and extract face areas, obtain the coordinates of the face by applying the detection algorithm to each frame of the image, and crop and store it as an independent face image;

[0116] The feature extraction and comparison module is used to extract features from the extracted face images using a pre-trained deep learning model and compare them with the stored registered database. By calculating the Euclidean distance between the extracted feature vector and the registered vector, the type of person is determined and divided into registered and unregistered categories.

[0117] The recognition and alarm judgment module is used to classify the image information according to the recognition results. If it is recognized as a registered person type, it is further determined whether it is a temporary person and its stay time is calculated. If it exceeds the set threshold, an alarm is issued. At the same time, the location information of unregistered persons is obtained and tracked;

[0118] Behavior monitoring and prediction module, which is used to analyze video streams in real time, monitor the bad behavior of registered personnel, and use behavior recognition algorithms to predict behavior. If abnormal behavior is detected, the system automatically issues an alarm and records relevant image information for subsequent analysis;

[0119] The self-learning update mechanism module is used to build a self-learning mechanism. Security personnel provide feedback on each alarm situation and update the database in a timely manner. At the same time, new data is used to retrain the model regularly to improve recognition accuracy and system adaptability.

[0120] The present invention also includes a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned intelligent security information management method can be implemented.

[0121] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0122] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An intelligent security information management method, characterized in that: The specific steps include: Step 1: Collect clear image data of key areas in the community, perform face detection on the collected images, use deep neural networks to identify and extract face areas, apply detection algorithms to each frame of the image, obtain the coordinates of the face, and crop and store them as independent face images; Step 2: Use the pre-trained deep learning model to extract features from the extracted face image and compare it with the stored registered database. By calculating the Euclidean distance between the extracted feature vector and the registered vector, the type of person is determined and divided into registered and unregistered categories; Step 3: Classify the image information according to the recognition results. If it is recognized as a registered person type, further determine whether it is a temporary person and calculate its stay time. If it exceeds the set threshold, an alarm will be issued. At the same time, the location information of unregistered persons is obtained and tracked; Step 4: Analyze the video stream in real time, monitor the bad behavior of the registered personnel, and use the behavior recognition algorithm to predict the behavior. If abnormal behavior is detected, the system will automatically issue an alarm and record the relevant image information for subsequent analysis; Step 5: Build a self-learning mechanism where security personnel provide feedback on each alarm and update the database in a timely manner. At the same time, regularly retrain the model with new data to improve recognition accuracy and system adaptability.

2. The intelligent security information management method according to claim 1, characterized in that: The key areas include the community's main gate, garage entrance, and the community's parks, squares, and children's playgrounds; Get images from the camera or video stream, and preprocess the images, including resizing and normalizing them, extract face images from the collected image information, and use the Caffe model provided by OpenCV to perform face detection; For each frame To locate the face area, the expression is as follows: in, is the current frame image, is the coordinates of the detected face area, specifically the coordinates of the upper left corner and the lower right corner, It is a function call, which indicates the operation of face detection on the current frame image; According to the detected Coordinates, draw a rectangular box on the original image to identify the face, cut out the face area from the original image according to these coordinates, and store it as an independent face image, denoted as .

3. The intelligent security information management method according to claim 1, characterized in that: Use the pre-trained deep learning model to extract facial features. The expression is as follows: in, is the extracted facial feature vector, which contains various attributes of the face. is the cropped face image, Indicates calling the pre-trained deep learning model Perform forward propagation to extract facial features; the various attributes of the face are: facial contour, eye position, nose shape, mouth features, and skin texture features; The Euclidean distance between the extracted feature vector and the registered feature vector is calculated according to the following formula: in, It is the Euclidean distance value, which indicates the similarity of two facial features. The larger the value, the greater the difference between the two facial feature vectors and the lower the similarity. is the value of the registered face feature vector in the i-th dimension, is the value of the face feature vector extracted from the person to be identified in the i-th dimension, is the dimension of the feature vector; like , then the person to be identified is determined to be a registered person type, otherwise the person to be identified is determined to be an unregistered person type.

4. The intelligent security information management method according to claim 1, characterized in that: If the person is identified as a registered person, the entry record is compared to determine whether the person is a temporary person. The expression is as follows: Indicates the judgment result, which includes and , Indicates that the person is a temporary staff member. Indicates that the person is a non-temporary employee. Indicates calling a function to check the given recognition Is it in the temporary personnel list? is an input parameter, indicating the person to be identified with the minimum Euclidean distance value. ; If the person is a temporary employee, obtain his / her stay time: in, is the dwell time, is the current time, The time for people to enter the community; like If the preset temporary personnel stay time is exceeded, an alarm will be issued; Unregistered persons are identified through image acquisition devices within the community and assigned a temporary , and at the same time obtain the location information of unregistered persons and track them. The expression is as follows: in, is a variable used to store the location information of unregistered persons. Is a function call, inside the function will be based on Query the current location of the unregistered person and return the corresponding location information; Location information Send it to community security personnel and control the image acquisition equipment for real-time tracking.

5. The intelligent security information management method according to claim 1, characterized in that: Real-time analysis of video streams, monitoring of bad behavior of registered personnel, and use of behavior recognition algorithms to predict behavior. If abnormal behavior is detected, the system automatically issues an alarm and records relevant image information for subsequent analysis; Use behavior recognition algorithms to analyze video streams and detect potential bad behaviors. The expression is as follows: in, is the predicted behavior category, For the processed video stream, is a function call that identifies Behavioral patterns in order to identify and classify human behavior; If improper behavior is detected, the system will issue an alarm and record relevant image information.

6. The intelligent security information management method according to claim 1, characterized in that: Build a self-learning mechanism, where security personnel provide feedback on each alarm and update the database in a timely manner. The expression is as follows: in, Provide security personnel with feedback on alarm situations. Is a function that indicates updating the database; The feedback information includes: alarm accuracy, security personnel confirm whether the alarm is true and provide relevant observations; behavior description, security personnel's specific description of the incident, the behavior and situation description of the personnel involved; suggestions and improvements, improvement suggestions put forward by security personnel to help the system better identify and judge similar incidents; Regularly use newly collected data to retrain the model to improve recognition accuracy.

7. The intelligent security information management device according to claim 1, characterized in that: The intelligent security information management device is used to execute an intelligent security information management method according to any one of claims 1 to 6, comprising: The image acquisition and detection module is used to collect clear image data of key areas in the community, perform face detection on the collected images, use deep neural networks to identify and extract face areas, obtain the coordinates of the face by applying the detection algorithm to each frame of the image, and crop and store it as an independent face image; The feature extraction and comparison module is used to extract features from the extracted face images using a pre-trained deep learning model and compare them with the stored registered database. By calculating the Euclidean distance between the extracted feature vector and the registered vector, the type of person is determined and divided into registered and unregistered categories. The recognition and alarm judgment module is used to classify the image information according to the recognition results. If it is recognized as a registered person type, it is further determined whether it is a temporary person and its stay time is calculated. If it exceeds the set threshold, an alarm is issued. At the same time, the location information of unregistered persons is obtained and tracked; Behavior monitoring and prediction module, which is used to analyze video streams in real time, monitor the bad behavior of registered personnel, and use behavior recognition algorithms to predict behavior. If abnormal behavior is detected, the system automatically issues an alarm and records relevant image information for subsequent analysis; The self-learning update mechanism module is used to build a self-learning mechanism. Security personnel provide feedback on each alarm situation and update the database in a timely manner. At the same time, new data is used to retrain the model regularly to improve recognition accuracy and system adaptability.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can implement an intelligent security information management method as described in any one of claims 1 to 6.

Images