Key area electronic fence safety monitoring system and monitoring method based on communication tower group

Abstract

The invention discloses a key area electronic fence safety monitoring system and monitoring method based on a communication tower group, relates to the field of communication technology, Internet of Things and safety monitoring, and provides a key area electronic fence safety monitoring system based on a communication tower group, which is characterized by comprising a communication tower base station network, a communication tower base station network, a communication tower base station network and a communication tower base station network, a data acquisition module; a data processing and storage module; a data analysis and early warning module; and a user terminal module. The system can effectively improve the monitoring precision and response speed, reduces the construction and operation and maintenance cost, and is suitable for safety protection requirements in various complex environments.

Description

Technical Field

[0001] The present invention relates to the fields of communication technology, the Internet of Things, and security monitoring, and in particular to a key area electronic fence security monitoring system and a monitoring method based on a communication tower group. Background Art

[0002] With the development of society, the demand for security protection of important facilities and sensitive areas is increasing. Traditional physical fences have defects such as high cost, difficult maintenance, and easy intrusion, while the electronic fence system based on satellite navigation has limited positioning accuracy in urban environments with high-rise buildings. Therefore, it is particularly important to develop a new electronic fence system that utilizes widely distributed communication tower resources and combines modern communication and information technology. Summary of the invention

[0003] In response to the above-mentioned problems, the present invention aims to provide a key area electronic fence security monitoring system based on a communication tower group, which can effectively improve the monitoring accuracy and response speed, reduce the construction and operation and maintenance costs, and is suitable for security protection needs in various complex environments.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] A key area electronic fence security monitoring system based on a communication tower group, characterized by comprising:

[0006] Communication tower base station network: It is composed of multiple communication tower base stations, which serve as positioning beacons of the electronic fence system, used for signal transmission and reception, and can adjust signal characteristics as needed to support the needs of the positioning algorithm;

[0007] Data acquisition module: connected to the communication tower base station network by wired or wireless means, and used for environmental data collection, target recognition, and motion trajectory tracking of the communication tower base station network;

[0008] Data processing and storage module: used to process and store the data collected from the data acquisition module;

[0009] Data analysis and early warning module: used to perform real-time data flow analysis on the data processed by the data processing and storage module, identify abnormal behavior patterns, and trigger early warnings based on preset rules;

[0010] User terminal module: used to view the real-time monitoring screen transmitted from the data analysis and warning module to the user terminal, receive warning notifications, adjust electronic fence parameters, and review event records.

[0011] Furthermore, the communication tower base station network module includes:

[0012] Multi-base station collaborative positioning submodule: Calculate the specific location of the target by comparing the signal strength and phase difference between at least three communication tower base stations;

[0013] Time difference arrival positioning and arrival angle measurement submodule: used to measure the time difference of signals arriving at different base stations, combined with the preliminary position, to confirm the specific location of the target;

[0014] Signal enhancement and interference suppression submodule: used to automatically adjust the transmit power based on the received signal strength feedback and dynamically select the modulation and coding scheme according to the changes in channel conditions.

[0015] Furthermore, the data analysis and early warning module includes:

[0016] Abnormal behavior identification submodule: It is used to combine deep learning models to intelligently analyze personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern identification, and automatically distinguish between normal activities and potential threats;

[0017] Warning threshold adaptive adjustment submodule: Based on the abnormal detection results of the abnormal behavior recognition submodule, an adaptive algorithm is used to dynamically adjust the warning threshold;

[0018] Multi-channel alarm push submodule: used to ensure the instant communication of information in emergency situations.

[0019] The present application also discloses a key area electronic fence security monitoring method based on a communication tower group, which is characterized by comprising the following steps:

[0020] Step 1: Use the communication tower base station network as the positioning beacon of the electronic fence system for signal transmission and reception, and adjust the signal characteristics as needed to support the needs of the positioning algorithm;

[0021] Step 2: Connect to the communication network base station in step 1 by wired or wireless means to form an information collection network to collect environmental data, target identification, and motion trajectory tracking;

[0022] Step 3: Process and store the data collected in step 2 through the central processing unit and the data center;

[0023] Step 4: Analyze the data processed in step 3 in real-time data stream, identify abnormal behavior patterns, and set preset rules to trigger warnings;

[0024] Step 5: Transmit the warning information in step 4 to the user terminal.

[0025] Furthermore, step 1 includes:

[0026] Step 1-1: Utilize the signal strength comparison and phase difference between at least three communication tower base stations, perform triangulation or trilateral measurement by using signal strength comparison and phase difference, combine multi-base station information, and calculate the specific location of the target through mathematical models and algorithms;

[0027] Step 1-2: The specific position of the target calculated in step 1-1 is combined with the mathematical model to calculate the precise position, and the angle of arrival of the signal is measured to provide direction information and confirm the specific position of the target;

[0028] Step 1-3: Automatically adjust the transmit power based on the specific position in step 1-2 and the received signal strength feedback, and dynamically select the modulation and coding scheme according to the changes in channel conditions to optimize the robustness and efficiency of signal transmission and improve positioning accuracy.

[0029] Furthermore, step 4 includes:

[0030] Step 4-1: Combine the processed data in step 3 with the deep learning model to perform intelligent analysis on personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern recognition, and automatically distinguish between normal activities and potential threats;

[0031] Step 4-2: Based on the abnormal detection results in step 4-1, an adaptive algorithm is used to dynamically adjust the warning threshold;

[0032] Step 4-3: Based on the warning threshold set in step 4-2, the warning information reaching the warning threshold is transmitted to the user terminal.

[0033] The beneficial effects of the present invention are as follows: compared with the prior art, the present invention has the following improvements:

[0034] Improved security: Through the combination of the multi-base station collaborative positioning submodule and the time difference of arrival positioning (TDoA) and arrival angle measurement (AoA) submodules in the communication tower base station network module, the signal strength comparison and phase difference between at least three communication tower base stations are used for triangulation or trilateral measurement. Combined with the signal arrival time difference and angle measurement, the target position can be determined more accurately, and reliable positioning can be provided even in an environment with poor GPS signals, thereby improving the accuracy of the monitoring system. All-weather and no-dead-angle monitoring of key areas is achieved, significantly improving the level of security protection.

[0035] Reduce costs: Use existing communication tower resources as positioning beacons for the electronic fence system, eliminating the need to build new infrastructure, reducing construction costs, and also reducing subsequent operating and maintenance costs.

[0036] Flexibility and scalability: The system allows users to freely draw the boundaries of the electronic fence on the electronic map, set different warning levels and response rules, and can automatically or manually adjust the sensitivity and coverage of the electronic fence according to external factors such as time period, weather conditions, special events, etc., so that the system can be flexibly adjusted according to actual needs and easy to upgrade and expand functions.

[0037] Strong environmental adaptability: Whether it is a complex environment such as a city, suburbs or the wild, the system can adapt, expanding its application scope. Through intelligent algorithms and multimodal sensor networks, the system can maintain good performance in different environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flow chart of the security monitoring system of the present invention.

[0039] Figure 2 It is the working flow chart of the safety monitoring system of the present invention.

[0040] Figure 3 It is a work flow chart of the security monitoring method of the present invention. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0042] Example

[0043] See also Figure 1-Figure 3 The present application discloses a key area electronic fence security monitoring system based on a communication tower group, comprising:

[0044] Communication tower base station network: It is composed of multiple communication tower base stations, which serve as positioning beacons of the electronic fence system, used for signal transmission and reception, and can adjust signal characteristics as needed to support the needs of the positioning algorithm;

[0045] Specifically, the core of this system relies on the existing communication tower base station network. These base stations not only undertake daily wireless communication tasks, but also have a new role - as positioning beacons for the electronic fence system. Each base station is equipped with enhanced signal transmission and reception devices, which can adjust the signal characteristics as needed to support the needs of the positioning algorithm.

[0046] Data acquisition module: connected to the communication base station network module by wired or wireless means, and used to collect environmental data, target recognition, and motion trajectory tracking;

[0047] Among them, sensors for data collection include but are not limited to high-definition cameras, infrared thermal imagers, microwave radars, RFID readers, etc. These sensors are strategically deployed around or inside key areas to collect environmental data, target identification, motion trajectory tracking, etc. The sensor network is connected to the communication tower base station through wired or wireless means to form a dense information collection network.

[0048] Data processing and storage module: used to process and store data collected from the communication base station network module and the data acquisition module;

[0049] It should be noted that the CPU is responsible for processing a large amount of raw data collected from various base stations and sensors, performing positioning calculations, data analysis, and decision logic. The data center stores historical data and supports big data analysis and system optimization. The CPU and data center are usually located in a secure remote location to ensure the efficiency and security of data processing.

[0050] Data analysis and early warning module: used to analyze the real-time data stream of data processed by the data processing and storage module, identify abnormal behavior patterns, and preset rules for triggering early warnings;

[0051] Further explanation: the data analysis and warning module integrates machine learning and artificial intelligence algorithms to analyze real-time data streams and identify abnormal behavior patterns. For example, the decision tree is constructed through the isolation forest algorithm to isolate data points, and abnormal points are more easily isolated. When detecting illegal intrusions, the isolation forest learns normal behavior patterns. If new data is quickly isolated, it is determined to be abnormal behavior. The autoencoder algorithm is used to reconstruct data to identify anomalies. When detecting abnormal time activities, the autoencoder is trained to learn normal behavior. If the reconstruction error of new data is large, it is considered to be abnormal time activities. Through clustering algorithms such as K-Means or DBSCAN, the algorithm groups the data. When detecting abnormal time activities, if the data point is far away from the cluster center or in a low-density area, it is considered to be an abnormal time activity. And the warning is automatically triggered according to the preset rules. The warning information can be quickly conveyed to security managers through multiple channels.

[0052] User terminal module: used to view the real-time monitoring screen transmitted from the data analysis and warning module to the user terminal, receive warning notifications, adjust electronic fence parameters, and review event records.

[0053] More specifically, the communication tower base station network includes:

[0054] Multi-base station collaborative positioning submodule: Utilizes the signal strength comparison and phase difference between at least three communication tower base stations, performs triangulation or trilateral measurement by using signal strength comparison (RSSI) and phase difference (PDOA), combines multi-base station information, and calculates the specific location of the target through mathematical models and algorithms; this technology can provide more reliable positioning services in environments with poor GPS signals.

[0055] Specifically, the following mathematical models and algorithms are used:

[0056] Signal strength comparison (RSSI): By measuring the received signal strength indication (RSSI) of the signal at different base stations, and based on the known base station location and signal attenuation model, the distance between the target and the base station can be inferred. The relationship between signal strength and distance can be expressed by the following formula:

[0057] RSSI=RSSI_0-10n*log_10(d / d_0)

[0058] Among them, RSSI_0 is the RSSI value of the reference point, n is the path loss index (usually between 2 and 4), d is the distance from the target to the base station, and d_0 is the reference distance (usually 1 meter). By measuring the RSSI values ​​at multiple base stations, the distance from the target to each base station can be estimated.

[0059] Phase difference (PDOA): The direction of the target is determined by measuring the phase difference of the signal at different base stations. The phase difference can be used to calculate the position of the target through the angle of arrival (AOA) of the signal. The measurement of phase difference usually depends on the relative position between base stations and the signal wavelength, and can be calculated using the following formula:

[0060] Δφ=(2π / λ)*d_ant*sin(θ)

[0061] Among them, Δφ is the phase difference, λ is the signal wavelength, d_ant is the distance between the base station antennas, and θ is the signal arrival angle. By measuring the phase difference between multiple pairs of base stations, multiple equations about the arrival angle can be obtained, thereby solving the specific location of the target.

[0062] Triangulation or trilateration: Using the distance information obtained from RSSI and the angle information obtained from PDOA, a mathematical model of the target location can be established. For triangulation, the distance information of at least three base stations is required, while for trilateration, the angle information of three base stations is required. Combined with the location information of the base stations, a set of equations can be constructed to solve the location coordinates of the target.

[0063] For example, for triangulation, the target position (x,y) can be solved using the following set of equations:

[0064] sqrt((x-x_i)^2+(y-y_i)^2)=d_i

[0065] Among them, (x_i, y_i) is the position of base station i, and d_i is the distance from the target to base station i. For three base stations, three equations can be obtained, and the position of the target can be obtained by solving the system of simultaneous equations.

[0066] For trilateration, the following system of equations can be used:

[0067] sin(θ_i)=(Δφ_i*λ) / (2π*d_ant)

[0068] Among them, θ_i is the direction angle from the target to base station i. Similarly, for three base stations, three direction angle equations can be obtained to solve the target position.

[0069] Through the above steps and formulas, the signal strength comparison (RSSI) and phase difference (PDOA) information provided by the multi-base station cooperative positioning submodule can be used to calculate the specific location of the target. This technology can provide more reliable positioning services in environments with poor GPS signals.

[0070] Time difference of arrival (TDoA) and angle of arrival (AoA) submodules: used to measure the time difference between signals arriving at different base stations, combine the preliminary position, calculate the precise position through mathematical models, and measure the angle of arrival of the signal to provide direction information and confirm the specific location of the target;

[0071] Among them, TDoA determines the position by measuring the time difference between the arrival of the signal at different base stations, while AoA achieves positioning by analyzing the angle of arrival of the signal. The TDoA technology is used to measure the time difference between the arrival of the signal at different base stations, combined with the preliminary position estimate, and a more accurate position is calculated through mathematical models (such as hyperbolic positioning). The angle of arrival of the signal is measured by AoA, which can provide directional information to help confirm the specific location of the target. AoA can reduce uncertainty in positioning, especially when the multipath effect is severe. The combination of the two can further improve positioning accuracy, especially in complex urban environments. Specifically, the preliminary position is first estimated by TDoA, and then the angle of arrival of the signal is measured by AoA to correct the preliminary position estimate, so as to obtain a more accurate target position.

[0072] Specifically, the TDoA technology is used to measure the time difference between signals arriving at different base stations, including the following:

[0073] 1. Measure the time difference of the signal arriving at different base stations: First, it is necessary to measure the time difference of the signal from the target point to two or more base stations.

[0074] 2. Combined with preliminary position estimation: Based on the time difference, the hyperbolic positioning method is used to estimate the preliminary position of the target. The time difference between each pair of base stations corresponds to a hyperbola, and the target position is located at the intersection of all hyperbolas.

[0075] 3. Mathematical model to calculate the exact position: Through TDoA, the target position is calculated using the following formula:

[0076] Assume that the positions of base stations Bi and Bj are (xi,yi) and (xj,yj) respectively.

[0077] The time difference between the arrival of the signal at these two base stations is Δt ij .

[0078] The signal propagation speed is c (for electromagnetic waves, approximately equal to the speed of light).

[0079] The target position satisfies the following equation:

[0080]

[0081] Solving this system of equations can obtain the exact coordinates of the target location.

[0082] The signal arrival angle is measured by AoA, which includes the following:

[0083] Measuring the angle of arrival of signals: The angle of arrival of signals is measured through the antenna array of the base station. Each base station is equipped with equipment that can measure the angle of incidence of the signal.

[0084] Provides directional information: AoA measurements provide a direction vector, pointing in the direction of the target.

[0085] Confirming the specific position: Combining the preliminary position estimate with the AoA measurement can further narrow the target location and confirm the target's specific position. The AoA measurement result can be used to correct the TDoA estimated position and improve positioning accuracy.

[0086] Signal enhancement and interference suppression submodule: In order to improve positioning accuracy, the system will dynamically adjust the base station's transmission power and signal coding method to reduce the impact of multipath effects and external interference. The base station can automatically adjust the transmission power based on the received signal strength feedback. And according to the changes in channel conditions, the system can dynamically select the most suitable modulation and coding scheme to optimize the robustness and efficiency of signal transmission.

[0087] It should be noted that the specific steps of dynamic adjustment are as follows:

[0088] Automatically adjust transmit power: The base station can automatically adjust its transmit power based on the received signal strength feedback (RSSI). This means that the base station monitors the strength of the signal it receives and adjusts the strength of its own transmitted signal accordingly to maintain an ideal received signal level. This can prevent saturation caused by too strong a signal, or loss caused by too weak a signal.

[0089] Dynamic selection of modulation and coding schemes: The system dynamically selects the most suitable modulation and coding schemes based on changes in channel conditions. Modulation refers to the process of converting digital data into analog signals, while coding refers to encoding data before transmission to improve transmission reliability. Based on the quality of the current channel (such as noise level, interference level, etc.), the system can select the most suitable modulation method (such as QPSK, 16-QAM, 64-QAM, etc.) and coding rate (such as 1 / 2, 3 / 4, etc.) to optimize the robustness and efficiency of signal transmission.

[0090] Implementation of dynamic adjustment: Dynamic adjustment is mainly achieved through a closed-loop feedback mechanism. The base station continuously monitors the channel status and adjusts its transmission parameters based on the monitored information. This adjustment is continuous and adaptive, and changes with the changes in channel conditions, thereby ensuring the best performance of signal transmission.

[0091] The key to dynamic adjustment is to monitor channel conditions in real time and respond quickly based on the monitoring results. For example, when a base station detects that signal strength is weakening or there is interference, it may increase the transmit power or select a more robust modulation and coding scheme. Conversely, if channel conditions are good, the base station may reduce the transmit power to save energy and select a more efficient modulation and coding scheme. This dynamic adjustment ensures that high-quality signal transmission is always available in a changing environment.

[0092] It should also be noted that the data analysis and early warning module includes:

[0093] Abnormal behavior identification submodule: It is used to combine deep learning models to intelligently analyze personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern identification, and automatically distinguish between normal activities and potential threats;

[0094] Specifically, abnormal behavior recognition: Combined with deep learning models, intelligent analysis of personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern recognition is performed. Using a combination of convolutional neural networks (CNN) and long short-term memory networks (LSTM), CNN is used to extract features from images, and LSTM is used to process time series data and identify behavior patterns. Using spatiotemporal convolutional networks (STCN) or methods based on graph neural networks (GNN), the location data of vehicles at different time points are processed to predict and analyze driving paths. CNN can also be used for object detection and classification, combined with time series analysis, such as LSTM or GRU (gated recurrent unit), to estimate the movement speed of objects. Use 3D convolutional neural networks (3DCNN) to analyze video sequences and identify complex human movements and behaviors. Automatically distinguish normal activities from potential threats.

[0095] Improvements in abnormal behavior identification

[0096] Data enhancement: The generalization ability of the model can be improved through data enhancement techniques, such as rotation, scaling, cropping, flipping, etc., to enhance the robustness of the model.

[0097] Model architecture optimization: The performance of the model can be improved by optimizing the network architecture, such as introducing residual connections and attention mechanisms.

[0098] Multimodal fusion: In addition to image data, data from other modalities (such as sound, temperature, humidity, etc.) can also be integrated to improve recognition accuracy through multimodal learning.

[0099] Online learning: Through online learning, the model can continuously learn from new data to continuously optimize its performance.

[0100] CNN extracts image features

[0101] Data preprocessing: Convert the image to a fixed size and perform standardization or normalization to ensure the consistency of the input data.

[0102] Convolutional layer: Scans the image through a series of convolution kernels (filters) to extract local features. The convolution kernels automatically learn the edges, textures, and other important visual features in the image.

[0103] Activation function: ReLU (Rectified Linear Unit) is usually used as the activation function, which can help the network learn nonlinear mapping relationships.

[0104] Pooling layer: Reducing the size of the feature map through pooling operations (such as maximum pooling or average pooling) while retaining the most important information helps reduce the amount of computation and prevent overfitting.

[0105] Fully connected layer: Flatten the feature map output by the convolutional layer and pass it through a fully connected layer for classification or regression tasks. The fully connected layer can capture global features and map the features to the category space.

[0106] Loss function and optimization: Define a loss function (such as the cross entropy loss function) to measure the gap between the model prediction and the actual label, and update the network weights through an optimization algorithm (such as gradient descent) to minimize the loss.

[0107] LSTM processes time series data to identify behavioral patterns

[0108] Data preparation: Organize time series data, ensure that the data is arranged in chronological order, and perform necessary preprocessing such as normalization.

[0109] Input embedding: Mapping the input at each time step into a high-dimensional space to capture more information.

[0110] Forget gate, input gate, and output gate: The LSTM unit controls the flow of information through three gates (forget gate, input gate, and output gate). The forget gate determines which information is discarded, the input gate determines which information is updated, and the output gate determines which information will be passed to the next time step.

[0111] Cell state update: Based on the results of the forget gate and the input gate, the cell state is updated, which is the core of LSTM and stores important long-term dependency information.

[0112] Hidden state calculation: Calculate the output of the LSTM unit, the hidden state, which will be passed to the next time step and used for the final prediction.

[0113] Prediction and feedback: Make predictions based on the output of LSTM, compare the predicted results with the actual results, adjust model parameters through the feedback mechanism, and optimize the prediction performance.

[0114] Warning threshold adaptive adjustment submodule: Based on the abnormal detection results of the abnormal behavior recognition submodule, an adaptive algorithm is used to dynamically adjust the warning threshold;

[0115] The system collects data from the past period of time, including normal behavior patterns, abnormal event records, and the frequency and intensity of these events. Through statistical analysis, the initial warning threshold is determined. Data from sensor networks and communication tower base stations are collected and analyzed in real time, including personnel action patterns, vehicle driving paths, object movement speeds, environmental parameters, etc. Then based on the data and real-time anomaly detection results, the system uses adaptive algorithms (such as online learning algorithms, sliding window averages, exponentially weighted moving averages, etc.) to dynamically adjust the warning threshold. These data provide an instant view of the current environment and activities. Improve the accuracy and timeliness of warnings.

[0116] Specifically, online learning algorithms: Online learning algorithms allow the system to learn and update models as data is streamed in. Whenever a new data point arrives, the algorithm adjusts its model parameters based on the new data to better predict future data points. In the early warning threshold adjustment, this means that the system adjusts the threshold based on the latest behavior pattern data to reflect the current behavior trend. The specific calculation process depends on the selected learning algorithm, such as gradient descent or other online optimization techniques.

[0117] Sliding Window Average: Sliding Window Average is a simple and effective technique for smoothing time series data and identifying trends. In this method, the system maintains a fixed-size data window and updates the data within the window each time new data arrives. The warning threshold is determined based on the average value of the data within the window. As the window slides, the average value will also change accordingly, resulting in dynamic adjustment of the warning threshold. The calculation formula is:

[0118]

[0119] Where data i represents the i-th data point in the window, and N is the window size.

[0120] Exponentially Weighted Moving Average (EWMA): EWMA is a weighted averaging technique that gives more weight to recent data and less weight to older data. This allows for a quicker response to changes in data. Warning thresholds can be set based on the results of EWMA to quickly adapt to changes in behavior patterns. The calculation formula for EWMA is as follows:

[0121] EWMA t =α·data t +(1-α).EWMA t-1

[0122] Among them, α is a smoothing factor between 0 and 1, data t is the current data point,

[0123] EWMA t-1is the exponentially weighted moving average of the previous moment

[0124] Through the above method, the system can continuously evaluate data such as environmental parameters, personnel action patterns, vehicle driving paths, and object movement speeds, and determine the warning threshold based on the statistical characteristics of these data (such as mean, variance, etc.). When abnormal behavior is detected, the system will trigger an early warning. In addition, the system can adjust the threshold based on the detected abnormal behavior to better adapt to the changing environment and activity patterns. For example, if abnormal behavior is detected frequently in a certain period of time, the system may increase the warning threshold in that period of time to reduce false alarms. Conversely, in normal behavior patterns, the system may lower the threshold to capture potential abnormal situations.

[0125] Multi-channel alarm push submodule: ensure instant communication of information in emergency situations through mobile APP push, SMS, email, and direct voice calls.

[0126] It is also necessary to explain the setting and management of electronic fences in key areas based on communication tower clusters:

[0127] Flexible area demarcation: The user-friendly interface allows administrators to freely draw electronic fence boundaries on electronic maps and set different alert levels and response rules.

[0128] Dynamic adjustment strategy: Automatically or manually adjust the sensitivity and coverage of the electronic fence according to external factors such as time period, weather conditions, special events, etc. to achieve dynamic management. The system has a built-in rule engine and presets a series of time- and event-based adjustment rules. Based on the collected data and the instructions of the rule engine, the system automatically calculates and adjusts the sensitivity and coverage of the electronic fence through algorithms. The algorithm involves statistical analysis, machine learning model prediction, etc. to determine the most appropriate fence parameters.

[0129] Specifically, the specific steps for dynamically adjusting the sensitivity and coverage of the electronic fence include:

[0130] Collect data: The system collects data about time periods, weather conditions, special events, etc. This data can come from environmental monitoring devices, calendar events, or other external data sources.

[0131] Analyze data: Based on the collected data, the system analyzes the current environmental conditions, such as crowd density, weather conditions, etc., to determine whether the settings of the electronic fence need to be adjusted.

[0132] Adjustment rules engine: The system has a built-in rules engine with a series of preset time- and event-based adjustment rules. Based on the collected data and the instructions of the rules engine, the system automatically calculates and adjusts the sensitivity and coverage of the electronic fence through algorithms.

[0133] Calculating fence parameters: Algorithms involve statistical analysis, machine learning model predictions, etc. to determine the most appropriate fence parameters. For example, if a large event is detected during a specific time period, the fence coverage may be automatically expanded and the sensitivity may be increased to cope with the possible increase in traffic.

[0134] Implement adjustments: Based on the new parameters derived by the algorithm, the system automatically adjusts the boundaries of the geo-fence, alert levels, and other related settings to adapt to the current situation.

[0135] In this process, "dynamic" means that the system will automatically respond to changes in real-time data, while "automatic" means that no human intervention is required during the entire adjustment process, and the system can automatically update the parameters of the electronic fence. This ensures that the electronic fence can flexibly respond to different external conditions, thereby achieving more efficient monitoring and management.

[0136] Here is an overview of the calculations used by the algorithm to determine the most appropriate fence parameters:

[0137] Data Collection: The system collects a range of data, including but not limited to factors such as time period, weather conditions, special events, and historical data such as the frequency and intensity of past events.

[0138] Statistical analysis: Statistical analysis of the collected data is performed with the goal of finding regular patterns, such as the probability distribution of events occurring in different time periods, the impact of weather changes on activity patterns, etc. This step can help determine which parameters may be optimal under specific conditions.

[0139] Machine learning model prediction: Use machine learning models, such as regression analysis, classification algorithms, etc., to predict future situations based on historical data. The model will consider multiple factors, such as time, weather, etc., to predict possible behavior patterns in the future.

[0140] Rules Engine: The system has a built-in rules engine with a series of preset time and event-based adjustment rules. The rules engine decides whether to adjust the sensitivity and coverage of the electronic fence based on the currently collected data and the pre-set rules.

[0141] Parameter adjustment: Based on the above analysis and prediction results, the system uses algorithms to calculate the most appropriate fence parameters. This may involve multi-variable optimization problems, such as maximizing the effectiveness of monitoring while minimizing the false alarm rate. The system will automatically adjust the sensitivity and coverage of the electronic fence based on these calculation results.

[0142] Algorithm design: The algorithm may involve statistical analysis methods, such as regression analysis, principal component analysis, etc., to identify important factors affecting fence parameters; it may also include machine learning models, such as random forests, support vector machines, etc., to predict the optimal parameter configuration. The final parameter adjustment is to select a set of parameters that best suits the current situation by comparing multiple possible configurations.

[0143] Implementation adjustment: The system automatically adjusts the settings of the electronic fence based on the calculated optimal parameters, such as changing the boundary shape, adjusting the alert level, etc., to ensure that the electronic fence can adapt to changes in the current environment.

[0144] Through this process, the system can automatically optimize the parameter settings of the electronic fence under different conditions to achieve the best security protection effect.

[0145] Permission management: Set access rights for different users or groups to ensure that only authorized personnel can enter and exit designated areas, and the system can record all entry and exit records for easy audit tracking.

[0146] The present application also discloses a key area electronic fence security monitoring method based on a communication tower group, comprising the following steps:

[0147] Step 1: Use the communication tower base station network as the positioning beacon of the electronic fence system for signal transmission and reception, and adjust the signal characteristics as needed to support the needs of the positioning algorithm;

[0148] Step 2: Connect to the communication network base station in step 1 by wired or wireless means to form an information collection network to collect environmental data, target identification, and motion trajectory tracking;

[0149] Step 3: Process and store the data collected in step 2 through the central processing unit (CPU) and the data center;

[0150] Step 4: Analyze the data processed in step 3 in real-time data stream, identify abnormal behavior patterns, and set preset rules to trigger warnings;

[0151] Step 5: Transmit the warning information in step 4 to the user terminal.

[0152] Specifically, step 1 includes:

[0153] Step 1-1: Utilize the signal strength comparison and phase difference between at least three communication tower base stations, perform triangulation or trilateral measurement by using signal strength comparison (RSSI) and phase difference (PDOA), combine multi-base station information, and calculate the specific location of the target through mathematical models and algorithms;

[0154] Step 1-2: The specific position of the target calculated in step 1-1 is combined with the mathematical model to calculate the precise position, and the angle of arrival of the signal is measured to provide direction information and confirm the specific position of the target;

[0155] Step 1-3: Automatically adjust the transmit power based on the specific position in step 1-2 and the received signal strength feedback, and dynamically select the modulation and coding scheme according to the changes in channel conditions to optimize the robustness and efficiency of signal transmission and improve positioning accuracy.

[0156] Specifically, step 4 includes:

[0157] Step 4-1: Combine the processed data in step 3 with the deep learning model to perform intelligent analysis on personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern recognition, and automatically distinguish between normal activities and potential threats;

[0158] Step 4-2: Based on the abnormal detection results in step 4-1, an adaptive algorithm is used to dynamically adjust the warning threshold;

[0159] Step 4-3: Based on the warning threshold set in step 4-2, the warning reaching the warning threshold is pushed via mobile phone APP, SMS, email, and direct voice call to ensure the instant communication of information in emergency situations.

[0160] Its main operation process is: log in to the system, view real-time monitoring, respond to alarms, investigate events, adjust electronic fences, record processing, etc. It is characterized by including communication tower base stations, multimodal sensor networks, central processing units, data analysis and early warning modules and user terminals. The system uses communication tower base stations to achieve high-precision positioning, and realizes real-time monitoring and early warning of key areas by setting electronic fences and integrating intelligent analysis algorithms.

[0161] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A key area electronic fence security monitoring system based on a communication tower group, characterized in that: include: Communication tower base station network: It is composed of multiple communication tower base stations, which serve as positioning beacons of the electronic fence system, used for signal transmission and reception, and can adjust signal characteristics as needed to support the needs of the positioning algorithm; Data acquisition module: connected to the communication tower base station network by wired or wireless means, and used for environmental data collection, target recognition, and motion trajectory tracking of the communication tower base station network; Data processing and storage module: used to process and store the data collected from the data acquisition module; Data analysis and early warning module: used to perform real-time data flow analysis on the data processed by the data processing and storage module, identify abnormal behavior patterns, and trigger early warnings based on preset rules; User terminal module: used to view the real-time monitoring screen transmitted from the data analysis and warning module to the user terminal, receive warning notifications, adjust electronic fence parameters, and review event records.

2. According to claim 1, a key area electronic fence security monitoring system based on a communication tower group is characterized in that: The communication tower base station network module includes: Multi-base station collaborative positioning submodule: uses the signal strength comparison and phase difference between at least three communication tower base stations to calculate the specific location of the target; Time difference arrival positioning and arrival angle measurement submodule: used to measure the time difference of signals arriving at different base stations, combined with the preliminary position, to confirm the specific location of the target; Signal enhancement and interference suppression submodule: used to automatically adjust the transmit power based on the received signal strength feedback and dynamically select the modulation and coding scheme according to the changes in channel conditions.

3. According to claim 1, a key area electronic fence security monitoring system based on a communication tower group is characterized in that: The data analysis and early warning modules include: Abnormal behavior identification submodule: It is used to combine deep learning models to intelligently analyze personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern identification, and automatically distinguish between normal activities and potential threats; Warning threshold adaptive adjustment submodule: Based on the abnormal detection results of the abnormal behavior recognition submodule, an adaptive algorithm is used to dynamically adjust the warning threshold; Multi-channel alarm push submodule: used to ensure the instant communication of information in emergency situations.

4. A key area electronic fence security monitoring method based on a communication tower group according to any one of claims 1-3, characterized in that: The following steps are involved: Step 1: Use the communication tower base station network as the positioning beacon of the electronic fence system for signal transmission and reception, and adjust the signal characteristics as needed to support the needs of the positioning algorithm; Step 2: Connect to the communication network base station in step 1 by wired or wireless means to form an information collection network to collect environmental data, target identification, and motion trajectory tracking; Step 3: Process and store the data collected in step 2 through the central processing unit and the data center; Step 4: Analyze the data processed in step 3 in real-time data stream, identify abnormal behavior patterns, and set preset rules to trigger warnings; Step 5: Transmit the warning information in step 4 to the user terminal.

5. The key area electronic fence security monitoring method based on communication tower group according to claim 4 is characterized in that: Step 1 includes: Step 1-1: Utilize the signal strength comparison and phase difference between at least three communication tower base stations, perform triangulation or trilateral measurement by using signal strength comparison and phase difference, combine multi-base station information, and calculate the specific location of the target through mathematical models and algorithms; Step 1-2: The specific position of the target calculated in step 1-1 is combined with the mathematical model to calculate the precise position, and the angle of arrival of the signal is measured to provide direction information and confirm the specific position of the target; Step 1-3: Automatically adjust the transmit power based on the specific position in step 1-2 and the received signal strength feedback, and dynamically select the modulation and coding scheme according to the changes in channel conditions to optimize the robustness and efficiency of signal transmission and improve positioning accuracy.

6. The key area electronic fence security monitoring method based on communication tower group according to claim 4 is characterized in that: Step 4 includes: Step 4-1: Combine the processed data in step 3 with the deep learning model to perform intelligent analysis on personnel action patterns, vehicle driving paths, object movement speeds, and abnormal behavior pattern recognition, and automatically distinguish between normal activities and potential threats; Step 4-2: Based on the abnormal detection results in step 4-1, an adaptive algorithm is used to dynamically adjust the warning threshold; Step 4-3: Based on the warning threshold set in step 4-2, the warning information reaching the warning threshold is transmitted to the user terminal.

Images