Environment-friendly access control management system based on Internet of Things

Abstract

The invention relates to the technical field of access control management, and discloses an environment-friendly access control management system based on Internet of Things, which comprises a data acquisition module, a data processing module, an environment-friendly grade evaluation module, an access control module, a user interaction module and a system optimization module. The data acquisition module collects original data by using various sensors, the processing module optimizes the data, and the environmental protection grade evaluation module evaluates the environmental protection condition by integrating multiple factors. The entrance guard control module controls entrance guard according to the evaluation result, and the system optimization module optimizes a strategy by using reinforcement learning. The system has obvious advantages, can comprehensively and accurately collect data, and provides support for decision making; the environmental protection grade is scientifically evaluated to prevent pollution diffusion; an access control strategy is intelligently optimized, and environmental protection and passing efficiency are balanced; the emergency response and linkage capability is achieved, and safety is guaranteed; convenient interaction experience is provided, and management is convenient; time sequence analysis dynamic evaluation is introduced, so that decision making is more scientific, and the defects of a traditional access control management system in the aspect of environmental protection are effectively overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of access control management, and in particular to an environmentally friendly access control management system based on the Internet of Things. Background Art

[0002] In today's society, environmental awareness is increasing, and environmental management requirements for various places are becoming more stringent. As a key control node for the entry and exit of people and vehicles, the integration of access control management system and environmental protection needs has become crucial. The traditional access control management system has relatively single functions, mainly focusing on the identification and access control of people and vehicles, and has many deficiencies in environmental management.

[0003] Lack of environmental data monitoring: It is impossible to conduct real-time and comprehensive monitoring of environmental parameters such as air quality and noise level in the access control area. This makes it difficult for the management to grasp the environmental conditions of the area, to discover potential environmental pollution problems in a timely manner, and to provide accurate data support for subsequent environmental protection decisions.

[0004] The environmental assessment system is imperfect: There is a lack of scientific and reasonable environmental assessment methods, which cannot comprehensively consider the impact of multiple factors on the environment, such as air quality, noise level, density of people and vehicles, etc. It is impossible to accurately assess the environmental protection level of the access control area, and it is difficult to formulate targeted environmental management measures.

[0005] Access control is out of touch with environmental protection: The decision to open or close the access control is usually based only on the access rights of people and vehicles, and is not related to environmental conditions. When the environmental quality is poor, it is not possible to restrict the entry of people and vehicles in time, which may lead to further spread of pollution; when the environmental quality is good, it is also impossible to improve the access efficiency by reasonably adjusting the access control strategy, making it difficult to balance the relationship between environmental protection and access.

[0006] Lack of dynamic optimization mechanism: Traditional systems find it difficult to dynamically adjust and optimize access control strategies based on changes in actual conditions. As time goes by, environmental conditions and the traffic needs of people and vehicles continue to change, and fixed access control strategies cannot adapt to these changes, resulting in inefficient access control management and failure to meet the growing environmental protection and management needs.

[0007] Insufficient emergency response capabilities: When faced with emergencies, such as fires and environmental pollution accidents, traditional access control systems lack effective emergency response mechanisms. They cannot be linked with fire protection, security and other systems, and cannot quickly achieve personnel evacuation and special vehicle access. There are major safety hazards, making it difficult to ensure the safety of personnel and the normal operation of the site. Summary of the invention

[0008] The purpose of the present invention is to provide an environmentally friendly access control management system based on the Internet of Things to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solution: an environmental access control management system based on the Internet of Things, the system comprising:

[0010] It includes data acquisition module, data processing module, environmental protection grade assessment module, access control module, user interaction module and system optimization module;

[0011] The data acquisition module is used to collect the original data set required for access control management, specifically by using a variety of sensors deployed in the access control area, including air quality sensors, noise sensors, pedestrian flow sensors and vehicle flow sensors, to collect real-time data, and send the original data to the data processing module;

[0012] The data processing module is used to optimize the original data, specifically to perform data cleaning, feature extraction and data standardization on the original data to obtain optimized access control management data, and send the optimized access control management data to the environmental protection level assessment module and the access control module;

[0013] The environmental protection level assessment module is used to assess the environmental protection status of the access control area, specifically, based on the optimized access control management data, a comprehensive evaluation algorithm is used to conduct a comprehensive assessment of the air quality, noise level, pedestrian density and vehicle density to obtain an environmental protection level assessment result, and the environmental protection level assessment result is sent to the access control module;

[0014] The comprehensive evaluation algorithm specifically includes constructing an evaluation index set, constructing a comment set, determining index weights, constructing a relationship matrix, and performing a comprehensive evaluation;

[0015] The reinforcement learning module is used to continuously optimize the system, specifically, according to user feedback and historical data, using an optimization algorithm based on reinforcement learning to adjust the access control strategy to improve the efficiency and environmental protection effect of access control management, and send the optimized strategy to the access control module;

[0016] The access control module is used to control the opening and closing of the access control according to the environmental protection level assessment result, specifically to set the environmental protection level threshold. When the environmental protection level assessment result is lower than the threshold, the access control is activated to restrict entry; when the environmental protection level assessment result is higher than or equal to the threshold, the access control is allowed to open.

[0017] Preferably, when the environmental protection level assessment module assesses the environmental protection status of the access control area, the specific implementation steps include:

[0018] Construct an evaluation index set: Let the evaluation index set be U = {u 1 ,u 2 ,u 3 ,u4}, where u 1 Represents the air quality, u 2 represents the noise level, u 3 represents the crowd density, u 4 represents the traffic density;

[0019] Construct a comment set: Let the comment set be U = {v 1 ,v 2 ,v 3 ,v 4 ,v 5}, representing "excellent", "good", "average", "poor", and "bad" respectively;

[0020] Determine the index weight: Use the hierarchical analysis method to determine the weight vector W of each evaluation index = {w 1 ,w 2 ,w 3 ,w 4}, where w i Indicates the index u i The weight of

[0021] Construct the relationship matrix: For each evaluation index u i , based on the optimized access control management data, construct the relationship matrix R i =[r ij ], where r ij Indicates the index u i Belong to comments v j the extent of;

[0022] Comprehensive evaluation: The comprehensive evaluation model B = W·R is used for comprehensive evaluation, where R is the total relationship matrix. 1 , R 2 , R 3 , R 4 By row splicing, B = {b 1 ,b 2 ,b 3 ,b 4 ,b 5} is the evaluation result vector, which indicates the degree to which the environmental protection status of the access control area belongs to each comment level; the final environmental protection level evaluation result is determined according to the maximum degree of membership principle.

[0023] Preferably, when constructing the evaluation index set, the personnel activity type factor is further considered for the crowd density index: the personnel activities are divided into three types: stationary, slow and fast, and different weight coefficients w are assigned to each type. s 、w m 、w fBy analyzing the data collected by the human flow sensor and combining it with the information on the types of human activities obtained by the human activity detection device, a comprehensive index of human flow density is obtained by weighted calculation. The calculation formula is where n s 、n m 、n f Respectively represent the number of people who are stationary, moving slowly, and moving quickly per unit time.

[0024] Preferably, when conducting a comprehensive evaluation, based on the comprehensive evaluation model B=W·R, time series analysis is introduced to dynamically correct the evaluation results, and the historical environmental protection grade evaluation result data is used to establish a time series prediction model using an autoregressive moving average model.

[0025] Preferably, when the reinforcement learning module continuously optimizes the system, the specific implementation steps include:

[0026] Collect user feedback data, historical access control records, and corresponding environmental rating assessment results to form a state-action-reward sequence data set;

[0027] The environmental protection level assessment results, current time, pedestrian density, vehicle density, etc. are used as state features to construct the state space S;

[0028] Define the adjustment actions of the access control strategy, including adjusting the environmental protection level threshold and changing the access control response strategy, to form an action space A;

[0029] The reward function R(s,a) is designed based on factors such as the improvement of access control management efficiency, the degree of improvement of environmental protection effects and user satisfaction, where s∈S, a∈A;

[0030] Use Q-learning algorithm to learn strategies and update Q value table; and select the optimal action strategy according to the learned Q value table;

[0031] The optimized access control strategy is sent to the access control module for implementation, and data is continuously collected for the next round of learning iteration to form a closed-loop optimization.

[0032] Preferably, the reinforcement learning module introduces a penalty mechanism when designing the reward function R(s,a). When the access control strategy adjustment causes the environmental protection level to continue to decline over a period of time or the access control management efficiency is significantly reduced, a corresponding negative reward is given to encourage the system to converge to a better access control strategy faster.

[0033] Preferably, the access control module has multiple emergency response modes. When an emergency occurs, it automatically switches to the emergency release mode and forces the access to be opened. At the same time, the access control module is linked with the fire protection and security systems, receives alarm signals from these systems, and sets warning signs and voice prompts around the access control area. During the period of access restriction, for special vehicles, the access control can be quickly opened after manual remote authorization through license plate recognition and emergency call buttons.

[0034] Preferably, it also includes a user interaction module for interacting with users, displaying environmental protection level assessment results and access control status, and providing a user operation interface to allow users to query historical data and set access control parameters.

[0035] Preferably, the present invention further includes an electronic device, comprising:

[0036] processor;

[0037] a memory for storing processor-executable instructions;

[0038] Wherein, the processor is configured to call the instructions stored in the memory to implement the above-mentioned environmental protection access control management system.

[0039] Preferably, the present invention further includes a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions, when executed by a processor, implement the above-mentioned environmental access control management system.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The data acquisition module of the system collects the raw data required for access control management in real time by deploying multiple sensors such as air quality, noise, human flow, and vehicle flow. Taking a textile factory as an example, it can not only monitor the performance parameters of the loom, but also obtain the environmental parameters and configuration parameters of the workshop, comprehensively reflect the actual operating status of the loom, avoid decision-making errors caused by one-sided data, and provide a solid data foundation for subsequent analysis, prediction and decision-making.

[0042] The environmental protection level assessment module adopts a comprehensive evaluation algorithm to construct an evaluation index set and comment set, determine the index weight, construct a relationship matrix and conduct a comprehensive evaluation. Taking into account factors such as air quality, noise level, pedestrian density and vehicle density, a scientific environmental protection level assessment result is obtained to provide a reliable basis for access control. For example, when the air quality sensor detects that harmful gases exceed the standard, combined with the pedestrian and vehicle density data, the environmental protection level is assessed to be low, which can effectively prevent the spread of pollution and ensure the quality of the internal production environment of the factory.

[0043] The reinforcement learning module uses a reinforcement learning-based optimization algorithm to adjust the access control strategy based on user feedback and historical data. By constructing state space and action space, designing reward functions, and using the Q-learning algorithm for strategy learning, closed-loop optimization is achieved. Over time, the system can better balance environmental protection requirements and the efficiency of personnel and vehicle traffic. For example, by adjusting the environmental protection level threshold, while ensuring environmental protection effects, it reduces the impact on normal production activities and improves the overall efficiency and environmental protection effects of access control management.

[0044] The access control module has multiple emergency response modes and is linked to the fire protection and security systems. In case of an emergency (such as a fire), it automatically switches to the emergency release mode, forcibly opens the access control, and sets up warning signs and voice prompts around the access control area to guide personnel to evacuate safely. During the access control restricted access period, special vehicles can pass quickly after manual remote authorization through license plate recognition and emergency call buttons. These measures ensure the safety of personnel and normal operation order of the factory under special circumstances, and enhance the safety and reliability of the system.

[0045] The user interaction module facilitates user interaction with the system, displays environmental rating assessment results and access control status, and provides an operation interface for users to query historical data and set access control parameters. Factory managers can use this module to keep abreast of the environmental status of access control areas, adjust access control strategies according to actual needs, and achieve humanized management.

[0046] In the comprehensive assessment, time series analysis is introduced to dynamically revise the assessment results. The historical environmental protection level assessment result data is used to establish a time series prediction model using the autoregressive moving average model. Combined with the current actual assessment results and prediction results, it can more timely and accurately reflect the changing trend of the environmental protection status of the access control area, providing a more scientific basis for access control decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a working principle diagram of the environmentally friendly access control management system of the present invention;

[0048] Figure 2 A step-by-step diagram for environmental status assessment;

[0049] Figure 3 Diagram of the steps to continuously optimize the system for the reinforcement learning module. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1-3 The present invention provides a technical solution: an environmental access control management system based on the Internet of Things, the system comprising:

[0052] The data acquisition module deploys air quality sensors, noise sensors, human flow sensors, and vehicle flow sensors in the access control area. For example, at the access control of an industrial park, the air quality sensor collects the concentration of pollutants such as PM2.5, PM10, and sulfur dioxide in the air in real time; the noise sensor monitors the decibel value of environmental noise; the human flow sensor uses infrared sensing technology to count the number of people entering and leaving per unit time; the vehicle flow sensor uses geomagnetic induction or video monitoring to obtain the number of vehicles passing through, and transmits these raw data to the data processing module.

[0053] After receiving the raw data, the data processing module performs data cleaning to remove abnormal values ​​caused by sensor failure or interference, such as the occasional extremely high concentration values ​​of the air quality sensor. Then feature extraction is performed to extract the traffic flow characteristics of peak and valley periods from the traffic flow data. Finally, through data standardization, data of different types and magnitudes are unified in scale for subsequent analysis and calculation. The processed optimized data is sent to the environmental protection level assessment module and the access control module.

[0054] The environmental protection grade assessment module uses a comprehensive evaluation algorithm to evaluate the environmental protection status of the access control area based on the optimized data. The algorithm includes steps such as constructing an evaluation index set, a comment set, determining the index weights, constructing a relationship matrix, and comprehensive evaluation. For example, in the access control area of ​​a large shopping mall, the environmental protection status of the area is judged to be "good", "medium", etc. by combining the collected data with the weights of each index, and the evaluation results are transmitted to the access control module.

[0055] The access control module controls access control according to the environmental protection level assessment results. The environmental protection level threshold is pre-set. When the assessment result is lower than the threshold, the access control is activated to restrict access; when it is higher than or equal to the threshold, the access control is allowed to open. For example, when the air quality is poor and the density of people and vehicles is too large, resulting in the environmental protection level assessment result being lower than the set threshold, the access control system automatically restricts the entry of people and vehicles until the environmental protection situation improves.

[0056] The reinforcement learning module uses a reinforcement learning-based optimization algorithm to adjust the access control strategy based on user feedback and historical data. It collects user feedback on access control management, such as long waiting time, and combines historical access control records and environmental protection level assessment results to build a state-action-reward sequence data set to continuously optimize access control strategies and improve management efficiency and environmental protection effects.

[0057] The user interaction module is responsible for interacting with users, displaying environmental protection level assessment results and access control status, and providing an operation interface for users to query historical data and set access control parameters. For example, at the school access control, users can view the current environmental protection level on the display screen and query the changes in environmental protection data over the past week.

[0058] Taking the access control area of ​​a textile factory as an example, the present invention is further described in combination with Examples 1 to 5:

[0059] Embodiment 1:

[0060] This embodiment describes in detail the specific implementation steps of the environmental protection level assessment module when assessing the environmental protection status of the access control area, specifically including:

[0061] Construct an evaluation index set: Let the evaluation index set be U = {u 1 ,u 2 ,u 3 ,u 4}, where u 1 stands for air quality. In this textile factory, the air quality mainly monitors the content of formaldehyde, dust and volatile organic compounds (VOCs). 2 Represents the noise level. The operation of the machines in the factory will generate noise, and its decibel value is monitored by the noise sensor. 3 Represents the density of human traffic, which is determined by counting the number of people entering and leaving per unit time using infrared sensing devices installed on both sides of the access control. 4 Represents the traffic density, which is measured by the number of vehicles passing through the access control system detected by the ground sensor coil.

[0062] Construct a comment set: Let the comment set be V = {v 1 ,v 2 ,v 3 ,v 4 ,v 5}, representing "excellent", "good", "medium", "poor" and "bad" respectively. For air quality, if the formaldehyde content is lower than 50% of the national standard value, the dust and VOCs content is extremely low, and there is no obvious odor, it will be rated as "excellent"; if the formaldehyde content is between 50%-80% of the national standard limit, the dust and VOCs content is low, and there is no obvious unpleasant odor, it will be rated as "good"; and so on, clear evaluation standards for each level will be formulated.

[0063] Determine the index weight: Use the hierarchical analysis method to determine the weight vector W of each evaluation index = {w 1 ,w 2 ,w 3 ,w 4 Invite factory environmental experts, equipment management personnel, etc. to form a judging panel to compare the relative importance of each indicator and construct a judgment matrix. By calculating the eigenvector and maximum eigenvalue of the judgment matrix, the weight of each indicator is obtained. Assume that after calculation, the air quality u 1 The weight w 1 =0.4, noise level u 2 The weight w 2 =0.2, crowd density u 3 The weight w 3 =0.2, traffic density u 4 The weight w 4 =0.2, and satisfies

[0064] Construct the relationship matrix: For each evaluation index u i , construct the relationship matrix R based on the optimized access control management data i =[r ij ] Based on air quality u 1 For example, if the monitoring data shows that the formaldehyde content is within the "good" standard range, and the dust and VOCs content also meet the "good" requirements, then r 12 =1 (indicates that the air quality is "good" and the degree of evaluation is 1), r 11 =r 13 =r 14 =r 15 = 0. The relationship matrix of other indicators is constructed in the same way.

[0065] Comprehensive evaluation: The comprehensive evaluation model B = W·R is used for comprehensive evaluation, where R is the total relationship matrix. 1 ,R 2 ,R 3 ,R 4 By row splicing, B = {b 1 ,b 2 ,b 3 ,b 4 ,b 5} is the evaluation result vector, which indicates the degree to which the environmental protection status of the access control area belongs to each evaluation level. The final environmental protection level evaluation result is determined according to the maximum degree of membership principle. Assuming that B = {0.1, 0.3, 0.4, 0.1, 0.1} is calculated, the environmental protection level of the access control area is "medium", because b 3 =0.4 is the largest, indicating that the environmental protection status belongs to the "medium" evaluation level to the highest extent.

[0066] Embodiment 2:

[0067] This embodiment mainly describes a specific calculation method for considering the personnel activity type factor for the crowd density index when constructing an evaluation index set.

[0068] The personnel activities are divided into three types: stationary, slow and fast, and different weight coefficients w are assigned to each type. s 、w m 、w f At the entrance of the workshop, high-definition cameras and human behavior analysis software are installed to detect the type of human activity. After analysis and actual testing, the static state weight coefficient w is determined. s =0.2, slow-moving state weight coefficient w m =0.3, fast state weight coefficient w f =0.5.

[0069] By analyzing the data collected by the human flow sensor and combining it with the information on the types of human activities obtained by the human activity detection device, a comprehensive index of human flow density is obtained by weighted calculation. For example, in a certain period of time, the total number of people detected by the human flow sensor per unit time is 100, of which the number of people in a stationary state is n s = 20 people, the number of people in slow-moving state n m = 30 people, the number of people in fast-moving state n f =50 people. According to the calculation formula

[0070]

[0071] Available (People / unit time). The comprehensive index of human density calculated in this way can more accurately reflect the actual impact of human activities on the environment of the access control area, and provide more accurate data support for environmental protection level assessment.

[0072] Embodiment 3:

[0073] This embodiment describes the specific process of dynamically revising the evaluation results by introducing time series analysis when conducting a comprehensive evaluation, taking the environmental protection level evaluation data of the access control area of ​​a textile factory within one week as an example.

[0074] Using historical environmental protection level assessment result data, the autoregressive moving average model (ARIMA) is used to establish a time series prediction model. The daily environmental protection level assessment result data of the access control area in the past month are collected and the data is tested for stability. If the data is not stable, it is stabilized by differential operation. It is assumed that after testing and processing, it is determined that the data is suitable for the ARIMA (p, d, q) model, where p is the autoregressive order, d is the differential order, and q is the moving average order. Through trial calculation and model comparison, the model parameters are determined to be ARIMA (2, 1, 1).

[0075] In the comprehensive evaluation model B = W·R, we get the current evaluation result vector B t Then, the established time series prediction model is used to predict the environmental protection level evaluation result vector of the next time period. Prediction. Combined with the current actual evaluation results B t And the prediction results are predicted Dynamically correct the current assessment results. For example, if the current assessment results show that the environmental protection level is "medium", but the time series prediction model shows that the environmental protection level has a downward trend in the next time period, and the prediction result is close to "poor", then the current "medium" assessment result will be appropriately adjusted, and certain warnings will be given to remind managers to pay attention to possible environmental changes. Through this dynamic correction method, the changing trend of the environmental protection status of the access control area can be reflected more timely and accurately, providing a more scientific basis for access control decisions.

[0076] Embodiment 4:

[0077] This embodiment describes in detail the specific implementation steps of the reinforcement learning module when continuously optimizing the system, including:

[0078] Collect user feedback data, historical access control records and corresponding environmental protection level assessment results to form a state-action-reward sequence data set. In this textile factory, an online questionnaire is set up to collect employees' feedback on access control management, such as whether the access control opening speed is appropriate, whether the access is inconvenient due to environmental protection restrictions, etc.; at the same time, historical access control records are recorded, including the time of each access control opening and closing, environmental protection level assessment results and other information. These data are organized into a state-action-reward sequence. For example, at a certain moment, the environmental protection level is "good", the pedestrian density is 50 people / hour, and the vehicle density is 20 vehicles / hour. At this time, the access control is opened normally (action), and the environmental protection level remains stable for a period of time and the employee feedback is good (reward).

[0079] The environmental protection level assessment results, current time, pedestrian density, vehicle density, etc. are used as state features to construct the state space S. Assume that the environmental protection level assessment results are divided into five levels: "excellent", "good", "medium", "poor", and "bad", represented by 1-5 respectively; the current time is in hours; the pedestrian density ranges from 0 to 100 people / hour; and the vehicle density ranges from 0 to 50 vehicles / hour. Then a state s can be represented as (3, 14, 40, 15), indicating that the environmental protection level is "medium", the current time is 2 pm, the pedestrian density is 40 people / hour, and the vehicle density is 15 vehicles / hour. Define the adjustment actions of the access control strategy, including adjusting the environmental protection level threshold and changing the access control response strategy, to form the action space A. The action of adjusting the environmental protection level threshold can be to increase or decrease 5 minutes, 10 minutes, etc. based on the current threshold; the action of changing the access control response strategy includes adjusting the access control opening delay time from 5 seconds to 3 seconds, or increasing the priority of special vehicles to pass quickly, etc.

[0080] The reward function R(s,a) is designed based on factors such as the improvement of access control management efficiency, the degree of improvement of environmental protection effects, and user satisfaction, where s∈S, a∈A. For example, after adjusting the environmental protection level threshold, if the environmental protection level is improved within a period of time, and the access control management efficiency is not affected, and the user satisfaction is high, a positive reward is given, such as R(s,a)=10; if the adjustment action causes the environmental protection level to continue to decline within a period of time or the access control management efficiency is significantly reduced, a negative reward is given, such as R(s,a)=-10.

[0081] Use the Q-learning algorithm to learn the strategy and update the Q value table. Initialize the Q value table, and the Q value of each state-action pair is initialized to 0. In each iteration, select an action a according to the current state s, and execute the action to obtain the new state s ′ And reward r, according to the Q value update formula

[0082]

[0083] Update the Q value, where α is the learning rate (the value range is 0-1, assuming it is 0.1 here), and γ is the discount factor (the value range is 0-1, assuming it is 0.9 here). Repeat this process continuously. As the number of iterations increases, the Q value table gradually converges. According to the learned Q value table, select the optimal action strategy, send the optimized access control strategy to the access control module for implementation, and continue to collect data for the next round of learning iterations to form a closed-loop optimization. After multiple iterative optimizations, the access control strategy is more reasonable and can better balance environmental protection requirements and the efficiency of personnel and vehicle traffic.

[0084] Embodiment 5:

[0085] This embodiment illustrates the various emergency response modes that the access control module has and the handling methods in special circumstances. When an emergency (such as a fire) occurs, the access control module automatically switches to the emergency release mode and forces the access control to be opened. In this textile factory, the fire alarm system is linked to the access control module. Once the fire alarm system sends an alarm signal, the access control module immediately receives the signal, triggers the emergency release mode, and all access controls are quickly opened to ensure that personnel can evacuate quickly. At the same time, the access control module is linked to the fire protection and security systems, receives alarm signals from these systems, and sets warning signs and voice prompts around the access control area. For example, the display screen above the access control displays the text message "Fire alarm, please do not stay, evacuate quickly", and plays the voice prompt "Please follow the evacuation signs and evacuate in an orderly manner" to guide personnel to evacuate safely.

[0086] During the period of restricted access, for special vehicles (such as fire trucks and emergency vehicles), the access control can be quickly opened after manual remote authorization through license plate recognition and emergency call buttons. Install a high-definition license plate recognition camera at the factory access control. When the fire truck approaches, the license plate recognition system automatically recognizes the license plate number and transmits the information to the access control module. At the same time, the personnel on the vehicle press the emergency call button to contact the duty personnel in the factory security room. After the duty personnel confirms the situation, they authorize the access control through the remote operation interface to ensure that special vehicles can enter the factory in time to perform tasks. Through these emergency response and special situation handling mechanisms, the security and reliability of the access control management system are improved, and the normal operation of the factory and the safety of personnel and property are guaranteed.

[0087] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0088] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An environmentally friendly access control management system based on the Internet of Things, characterized by: It includes data acquisition module, data processing module, environmental protection grade assessment module, access control module, user interaction module and system optimization module; The data acquisition module is used to collect the original data set required for access control management, specifically by using a variety of sensors deployed in the access control area, including air quality sensors, noise sensors, pedestrian flow sensors and vehicle flow sensors, to collect real-time data, and send the original data to the data processing module; The data processing module is used to optimize the original data, specifically to perform data cleaning, feature extraction and data standardization on the original data to obtain optimized access control management data, and send the optimized access control management data to the environmental protection level assessment module and the access control module; The environmental protection level assessment module is used to assess the environmental protection status of the access control area, specifically, based on the optimized access control management data, a comprehensive evaluation algorithm is used to conduct a comprehensive assessment of the air quality, noise level, pedestrian density and vehicle density to obtain an environmental protection level assessment result, and the environmental protection level assessment result is sent to the access control module; The comprehensive evaluation algorithm specifically includes constructing an evaluation index set, constructing a comment set, determining index weights, constructing a relationship matrix, and performing a comprehensive evaluation; The reinforcement learning module is used to continuously optimize the system, specifically, according to user feedback and historical data, using an optimization algorithm based on reinforcement learning to adjust the access control strategy to improve the efficiency and environmental protection effect of access control management, and send the optimized strategy to the access control module; The access control module is used to control the opening and closing of the access control according to the environmental protection level assessment result, specifically to set the environmental protection level threshold. When the environmental protection level assessment result is lower than the threshold, the access control is activated to restrict entry; when the environmental protection level assessment result is higher than or equal to the threshold, the access control is allowed to open.

2. According to the Internet of Things-based environmental access control management system of claim 1, it is characterized in that: The environmental protection level assessment module, when assessing the environmental protection status of the access control area, specifically implements the following steps: Constructing the evaluation index set: Let the evaluation index set be U = {u1,u2,u3,u4}, where u1 represents air quality, u2 represents noise level, u3 represents pedestrian density, and u4 represents vehicle density; Construct a review set: Let the review set be U = {v1, v2, v3, v4, v5}, which represent "excellent", "good", "average", "poor", and "bad" respectively; Determine the indicator weight: Use the hierarchical analysis method to determine the weight vector W = {w1, w2, w3, w4} of each evaluation indicator, where w i Indicates the index u i The weight of Construct the relationship matrix: For each evaluation index u i , based on the optimized access control management data, construct the relationship matrix R i =[r ij ], where r ij Indicates the index u i Belong to comments v j the extent of; Comprehensive evaluation: The comprehensive evaluation model B = W·R is used for comprehensive evaluation, where R is the total relationship matrix, which is composed of R1, R2, R3, and R4 spliced ​​in rows, and B = {b1, b2, b3, b4, b5} is the evaluation result vector, which indicates the degree to which the environmental protection status of the access control area belongs to each comment level; the final environmental protection level evaluation result is determined according to the principle of maximum membership.

3. According to the Internet of Things-based environmental access control management system of claim 2, it is characterized in that: When constructing the evaluation index set, the personnel activity type factor is further considered for the crowd density index: the personnel activities are divided into three types: static, slow and fast, and different weight coefficients w are assigned to each type. s 、w m 、w f By analyzing the data collected by the human flow sensor and combining it with the information on the types of human activities obtained by the human activity detection device, a comprehensive index of human flow density is obtained by weighted calculation. The calculation formula is where n s 、n m 、n f Respectively represent the number of people who are stationary, moving slowly, and moving quickly per unit time.

4. The environmental protection access control management system based on the Internet of Things according to claim 2 is characterized in that: When conducting comprehensive evaluation, on the basis of the comprehensive evaluation model B=W·R, time series analysis is introduced to dynamically correct the evaluation results. The historical environmental protection grade evaluation result data is used to establish a time series prediction model using the autoregressive moving average model.

5. The environmental protection access control management system based on the Internet of Things according to claim 1 is characterized in that: The reinforcement learning module, when continuously optimizing the system, specifically implements the following steps: Collect user feedback data, historical access control records, and corresponding environmental rating assessment results to form a state-action-reward sequence data set; The environmental protection level assessment results, current time, pedestrian density, vehicle density, etc. are used as state features to construct the state space S; Define the adjustment actions of the access control strategy, including adjusting the environmental protection level threshold and changing the access control response strategy, to form an action space A; The reward function R(s,a) is designed based on factors such as the improvement of access control management efficiency, the degree of improvement of environmental protection effects and user satisfaction, where s∈S, a∈A; Use Q-learning algorithm to learn strategies and update Q value table; and select the optimal action strategy according to the learned Q value table; The optimized access control strategy is sent to the access control module for implementation, and data is continuously collected for the next round of learning iteration to form a closed-loop optimization.

6. The environmental protection access control management system based on Internet of Things according to claim 5 is characterized in that: The reinforcement learning module introduces a penalty mechanism when designing the reward function R(s,a). When the access control strategy adjustment causes the environmental protection level to continue to decline over a period of time or the access control management efficiency is significantly reduced, a corresponding negative reward is given to encourage the system to converge to a better access control strategy faster.

7. The environmental access control management system based on the Internet of Things according to claim 1 is characterized in that: The access control module has multiple emergency response modes. When an emergency occurs, it automatically switches to the emergency release mode and forces the access to be opened. At the same time, the access control module is linked with the fire protection and security systems, receives alarm signals from these systems, and sets up warning signs and voice prompts around the access control area. During the period of access restriction, for special vehicles, the access control can be quickly opened after manual remote authorization through license plate recognition and emergency call buttons.

8. The environmental protection access control management system based on Internet of Things according to claim 1 is characterized in that: It also includes a user interaction module for interacting with users, displaying environmental protection level assessment results and access control status, and providing a user operation interface for users to query historical data and set access control parameters.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to implement the system described in any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the system according to any one of claims 1 to 8 is implemented.

Images