Smart park access control management method and system based on the Internet of Things

Abstract

The embodiment of the present application provides a smart park access control management method and system based on the Internet of Things, which collects the dynamic environmental parameters of the target area in the park and the identity authentication data of the target object in real time through the Internet of Things devices. First, the collected dynamic environmental parameters are matched with the preset security threshold range in real time to generate an environmental security assessment result. Then, the identity feature vector of the target object is extracted based on the identity authentication data, and multi-dimensional security verification is performed in combination with the environmental security assessment result. When the multi-dimensional security verification is passed, a dynamic access control strategy is intelligently generated based on the historical access records and current environmental parameters of the target object. Finally, the dynamic access control strategy is sent to the target access control terminal through the cloud server to realize intelligent control of the access rights and physical locking status of the access control terminal. The present invention improves the security management level of the smart park and ensures the intelligence and efficiency of access control management.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things technology, and more specifically, to a method and system for smart park access control management based on the Internet of Things. Background Art

[0002] As campuses continue to expand and demand for intelligent management grows, campus security management faces numerous challenges. Traditional access control systems rely solely on single authentication methods, such as simple card recognition or password verification. This approach presents numerous security vulnerabilities and is susceptible to fraudulent use or cracking. Furthermore, traditional access control systems lack comprehensive consideration of the surrounding environment and are unable to adjust access control policies based on dynamic environmental changes.

[0003] In modern campus environments, environmental factors such as temperature, humidity, and smoke concentration can have a significant impact on campus safety. For example, abnormal temperature fluctuations may indicate a fire hazard or equipment failure, while a sudden increase in smoke concentration is a direct sign of a fire. Traditional access control systems are unable to integrate these environmental factors into access control, and are unable to respond to environmental changes in a timely manner.

[0004] Furthermore, identity verification for target individuals requires greater precision and multi-dimensionality. Relying solely on single biometrics or electronic ID credentials is no longer sufficient due to the continuous advancement of forgery techniques. Multimodal biometrics and identity verification combined with blockchain technology can significantly improve the accuracy and security of identity verification.

[0005] Furthermore, with the development of IoT technology, a large number of IoT devices within the campus provide a rich source of data. However, integrating this data and implementing effective security management remains a pressing issue. Ensuring the normal operation of the access control system in unstable network communication situations, such as when the access control terminal is offline or experiencing communication delays, is also a crucial consideration. Finally, traditional access control systems lack the ability to effectively analyze and utilize historical data, making it impossible to identify potential security risks and provide early warnings. Summary of the Invention

[0006] In view of this, the purpose of this application is to provide a smart park access control management method and system based on the Internet of Things.

[0007] In conjunction with the first aspect of the present application, a method for managing access control in a smart park based on the Internet of Things is provided, which is applied to a smart park access control management system based on the Internet of Things. The method comprises:

[0008] The IoT devices deployed in the park collect dynamic environmental parameters of the target area and identity verification data of the target object;

[0009] Matching the dynamic environmental parameters with the preset safety threshold range in real time to generate an environmental safety assessment result;

[0010] Extracting the identity feature vector of the target object based on the identity authentication data, and performing multi-dimensional security verification in combination with the environmental security assessment results;

[0011] When the multi-dimensional security verification is passed, a dynamic access control strategy is generated based on the historical access records of the target object and the current environmental parameters;

[0012] The dynamic access control strategy is sent to the target access control terminal through the cloud server to control the access authority and physical locking status of the access control terminal.

[0013] In a possible implementation of the first aspect, collecting dynamic environmental parameters of the target area by using IoT devices deployed in the park includes:

[0014] Obtain real-time monitoring values of temperature, humidity, and smoke concentration through distributed environmental sensors;

[0015] Capture dynamic image data of the target area through a video acquisition device to extract the trajectory and density distribution characteristics of moving objects;

[0016] Voiceprint feature data is collected through sound sensors and compared with the preset abnormal voiceprint database to generate acoustic environment assessment indicators.

[0017] In a possible implementation of the first aspect, matching the dynamic environmental parameters with a preset safety threshold range in real time to generate an environmental safety assessment result includes:

[0018] performing time series analysis on the temperature monitoring values to detect abnormal temperature fluctuation patterns;

[0019] Spatial matching of the moving object trajectory with a preset campus electronic map to identify unauthorized area intrusion events;

[0020] The acoustic environment assessment index and the smoke concentration change rate are integrated to calculate the comprehensive environmental risk coefficient;

[0021] When the comprehensive environmental risk coefficient exceeds the dynamically adjusted threshold, an environmental safety alarm signal is triggered.

[0022] In a possible implementation of the first aspect, the step of collecting identity verification data includes:

[0023] An encrypted data packet of electronic identity credentials read by a near-field communication device;

[0024] Multimodal biometric features collected by biometric recognition devices, including 3D facial feature point cloud data and palm vein topology;

[0025] Real-time positioning information and historical access authorization records uploaded through mobile terminals.

[0026] In a possible implementation of the first aspect, extracting the identity feature vector of the target object based on the identity authentication data and performing multi-dimensional security verification in combination with the environmental security assessment result includes:

[0027] Performing blockchain node verification on the encrypted data packet of the electronic identity certificate to confirm the validity period and authority level of the identity certificate;

[0028] Performing a hierarchical comparison of the multimodal biometric features with pre-stored feature templates to generate a biometric matching matrix;

[0029] Calculating a spatial proximity parameter based on the real-time positioning information and the geographic coordinates of the access control terminal;

[0030] When the biometric matching matrix meets the dynamic verification threshold and the spatial proximity parameter is within an allowable range, an identity verification pass instruction is generated.

[0031] In a possible implementation of the first aspect, generating a dynamic access control strategy based on the historical passage record of the target object and current environmental parameters includes:

[0032] Analyze the time distribution characteristics and access frequency patterns in the historical access records to establish a behavior profile of the object;

[0033] Adjust the biometric sensitivity level of the access control terminal based on the visibility index and light intensity parameters in the current environmental parameters;

[0034] Dynamically assign access priority weights to access control terminals based on real-time crowd density data in each area of the park;

[0035] Generate dynamic authorization instruction sets that include time window restrictions, area access rights, and emergency escape routes.

[0036] In a possible implementation of the first aspect, the method further includes:

[0037] When it is detected that the access control terminal is offline or the communication delay exceeds the set threshold, the local decision-making mode of the edge computing node is started;

[0038] Executing an offline authentication algorithm through the edge computing node and caching the authentication result data;

[0039] Automatically synchronize cached data to the cloud server after communication is restored and update access control policy version information;

[0040] Adjust the encryption communication protocol level of the access control terminal according to the data synchronization status.

[0041] In a possible implementation of the first aspect, the method further includes:

[0042] Build a knowledge graph of access control events to associate and store historical verification records, device status data, and environmental parameter changes;

[0043] Analyze event association patterns in the knowledge graph through a deep learning model to predict potential security risks;

[0044] Automatically upgrade the verification security level of the access control terminal when abnormal access behavior patterns are detected;

[0045] Generate risk warning reports and push them to associated security management terminals.

[0046] In combination with the second aspect of the present application, a smart campus access control management system based on the Internet of Things is provided. The smart campus access control management system based on the Internet of Things includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the smart campus access control management system based on the Internet of Things implements the aforementioned smart campus access control management method based on the Internet of Things.

[0047] In combination with the third aspect of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the computer-executable instructions are executed, the aforementioned smart park access control management method based on the Internet of Things is implemented.

[0048] In combination with any of the above aspects, the dynamic environmental parameters of the target area in the park and the identity authentication data of the target object are collected in real time through the Internet of Things devices. First, the collected dynamic environmental parameters are matched with the preset security threshold range in real time to generate an environmental security assessment result. Next, the identity feature vector of the target object is extracted based on the identity authentication data, and multi-dimensional security verification is performed in combination with the environmental security assessment result. When the multi-dimensional security verification is passed, a dynamic access control strategy is intelligently generated based on the historical access records and current environmental parameters of the target object. Finally, the dynamic access control strategy is sent to the target access control terminal through the cloud server to realize intelligent control of the access rights and physical locking status of the access control terminal. The present invention improves the security management level of the smart park and ensures the intelligence and efficiency of access control management. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained by combining these drawings without paying any creative work.

[0050] Figure 1 A flowchart of the IoT-based smart campus access control management method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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 making creative efforts shall fall within the scope of protection of the present invention.

[0052] The terms "first," "second," and so on, in the specification and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed therein, or may optionally include other steps or elements inherent to such process, method, product, or end.

[0053] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0054] Figure 1 The flowchart of the method for access control management of a smart park based on the Internet of Things provided by an embodiment of the present application is shown. It should be understood that in other embodiments, the order of some steps of the method for access control management of a smart park based on the Internet of Things of this embodiment can be shared based on actual needs, or some steps can be omitted or maintained. The details of the method for access control management of a smart park based on the Internet of Things include:

[0055] Step S110: collecting dynamic environmental parameters of the target area and identity authentication data of the target object through the Internet of Things devices deployed in the park.

[0056] In this embodiment, environmental sensors are distributed across key locations within the industrial park to collect dynamic environmental parameters. For example, environmental sensors are installed within the industrial park's production workshops, on the corridors of each floor of the office building, around the industrial park's warehouses, and in the industrial park's public activity areas. These environmental sensors can accurately obtain real-time monitoring values for temperature, humidity, and smoke concentration. Taking the production workshop as an example, the operation of production equipment within the workshop may generate heat. Environmental sensors continuously monitor the temperature. During normal production hours, the temperature is likely to remain within a relatively stable range, such as between 20 and 25 degrees Celsius. Regarding humidity, due to factors such as the workshop's ventilation system, the humidity may be maintained at around 40% to 60%. If there is a malfunction in electrical equipment within the workshop or if flammable items catch fire and emit smoke, the smoke concentration sensor will immediately detect the increase in smoke concentration.

[0057] Video capture devices are also distributed throughout key areas of the park. These devices are installed at the park's entrances and exits, parking lots, and intersections within the park. These devices continuously capture dynamic image data of the target area. For example, at the park's entrances and exits, the video capture devices can clearly capture the entry and exit of people and vehicles, extracting the trajectory and density distribution characteristics of moving objects. When a vehicle enters the park, the video capture device tracks the vehicle's trajectory, from the moment it enters the park gate to the path it travels within the park. It can also calculate the density distribution of vehicles within a specific area, such as the parking density in the parking lot at different times.

[0058] Sound sensors also play a role within the campus. They have been installed in areas where critical equipment is located, such as computer rooms and power distribution rooms, as well as in some quiet office areas. These sensors collect voiceprint feature data and compare it with a pre-set abnormal voiceprint database to generate acoustic environment assessment indicators. For example, in a computer room, if the equipment is operating normally, the sound sensors will detect the sound characteristics of normal operation, which matches the pre-set normal voiceprint data. However, any abnormal sounds, such as vibrations from loose equipment components or sounds from unauthorized intruders, are detected immediately by the sound sensors. By comparing the data with the abnormal voiceprint database, the sensors generate corresponding acoustic environment assessment indicators, alerting users to potential security risks.

[0059] The campus has implemented various methods for collecting identity verification data from target users. Near-field communication (NFC) devices are installed at each access control entrance. When an employee or visitor approaches an access control station using a card or mobile device carrying an electronic ID, the NFC device reads the encrypted data packet containing the electronic ID. For example, an employee's work ID card has a built-in encrypted ID chip. When held near an access control card reader, the card reader can read the encrypted data packet containing the employee's identity information, department, and permission level.

[0060] Biometric devices are also widely used. Devices capable of collecting multimodal biometrics have been installed at access control points in key office areas and finance offices. These devices collect 3D facial feature point cloud data and palm vein topology. When an employee enters these areas, they stand before the biometric device, which accurately captures the employee's 3D facial feature point cloud data, including the three-dimensional structural features of key facial areas. It also collects the palm vein topology, such as the direction of vein branches and intersections, as a key basis for identity verification.

[0061] The park also utilizes information uploaded by employees and visitors using their mobile devices. For example, the park's security management system requires employees to enable the location function on their mobile devices while on campus. The mobile devices then upload their real-time location information. The system also records employees' access authorization history, including information about areas they have entered and how long they have stayed in each area. This information is then used as part of the authentication data.

[0062] Step S120 , matching the dynamic environmental parameters with a preset safety threshold range in real time to generate an environmental safety assessment result.

[0063] Continuing with the previous example of the enterprise park, time series analysis of temperature monitoring values is a key assessment step. The greenhouse area of the park houses temperature-sensitive plants. Normally, daytime temperatures should be between 15-25 degrees Celsius and nighttime temperatures between 10-15 degrees Celsius. Environmental sensors continuously collect temperature data, generating a time series. If the temperature suddenly rises from 20 to 30 degrees Celsius within a short period of time, such as within an hour, this constitutes an abnormal temperature fluctuation pattern. This abnormal fluctuation could be caused by a malfunction in the greenhouse's temperature control system or external environmental factors. The system would then determine that this situation poses a threat to plant growth, thereby impacting the environmental safety of the park's greenhouse area.

[0064] Spatial matching of moving object trajectories with pre-set electronic campus maps also plays a key role in security assessments. In the campus' warehouse area, pre-set electronic campus maps clearly delineate the boundaries of various storage areas and the storage zones for different items. A video capture device captures the trajectory of a moving object. If this trajectory indicates that the object has entered a high-value item storage area through an unauthorized passage, this identifies an unauthorized intrusion. For example, if an unauthorized individual attempts to bypass the normal warehouse entrance and enter an area storing valuable raw materials through an unsecured passage on the side of the warehouse, the system can promptly detect this unusual intrusion by matching the moving object's trajectory with the electronic map.

[0065] Combining acoustic environment assessment indicators with the rate of change of smoke concentration to calculate a comprehensive environmental risk factor is also a key tool in environmental safety assessments. In the campus's power distribution room, smoke concentrations are normally very low, and the acoustic environment is dominated by the hum of normal equipment operation. If smoke concentrations suddenly increase, and the sound sensor detects unusual sparking sounds, this indicates a potential risk of fire caused by electrical equipment failure. The system calculates a comprehensive environmental risk factor based on the rate of change of smoke concentration and acoustic environment assessment indicators. When this factor exceeds a dynamically adjusted threshold—for example, if the set threshold is 0.8 and the calculated factor is 0.9—an environmental safety alarm is triggered. This alarm is sent to the campus's security monitoring center, notifying relevant personnel for prompt inspection and action.

[0066] Step S130: extracting the identity feature vector of the target object based on the identity authentication data, and performing multi-dimensional security verification in combination with the environmental security assessment result.

[0067] For example, when an employee attempts to enter the advanced R&D area within the park, their electronic identity credentials are first verified against a blockchain node. Assuming the park's identity verification system is built on blockchain technology, the employee's electronic identity credentials are stored on the blockchain nodes. The system then verifies the credential's validity period. For example, an employee's work ID is valid for one year, starting from the date of issuance. It also verifies the access level. This R&D area is classified as highly confidential, and only R&D personnel with high-level permissions are allowed access. If the employee's credential is valid and meets the required access level, this is a key aspect of multi-dimensional security verification.

[0068] For biometric verification, an employee's multimodal biometrics are compared against pre-stored feature templates in a layered manner. For example, for an employee entering the advanced R&D area, the employee stands in front of a biometric recognition device. The 3D facial feature point cloud data and palm vein topology captured by the device are compared against the pre-stored feature template for the employee. First, the overall structure is compared, followed by a detailed layered comparison of key feature points to generate a biometric matching matrix. If each matching indicator in this matrix meets the dynamic verification threshold, for example, a facial feature matching of over 95% and a palm vein feature matching of over 90%, the biometric matching meets the requirements.

[0069] At the same time, the spatial proximity parameter is calculated based on the real-time location information uploaded by the employee's mobile terminal and the geographic coordinates of the access control terminal. If the employee is near the access control, the distance is within the set allowable range (for example, within 5 meters), and the biometric matching matrix meets the dynamic verification threshold and the spatial proximity parameter is within the allowable range, the system will generate an authentication pass instruction. In addition, combined with the previous environmental safety assessment results, if the current environmental safety assessment results show that the environment around the R&D area is normal, without abnormal temperature fluctuations, unauthorized intrusion, or fire risks, then the multi-dimensional security verification will be successfully passed.

[0070] Step S140: When the multi-dimensional security verification is passed, a dynamic access control strategy is generated according to the historical passage records of the target object and the current environmental parameters.

[0071] For employees who frequently visit the campus, the system analyzes the time distribution and access frequency patterns in their historical visit records to create a behavioral profile. For example, a marketing employee's visit history shows that they frequently visit the office building between 9:00 AM and 6:00 PM on weekdays, occasionally attend meetings in the conference room around 2:00 PM, and visit the campus's exhibition center once or twice a week. Based on this information, the system creates a behavioral profile for this employee.

[0072] The biometric sensitivity level of the access control terminal is adjusted based on the visibility and light intensity parameters in the current environmental parameters. In the outdoor access control areas of the campus, if visibility is low and light intensity is weak in the early morning or evening, the system will appropriately reduce the sensitivity level of the biometric device. For example, if the original facial feature matching requirement is above 95%, in such low visibility and low light intensity conditions, it may be sufficient to adjust it to above 90% to ensure that employees can pass through the access control normally while also ensuring a certain level of security.

[0073] Based on real-time traffic density data for each area within the campus, access control terminals are dynamically assigned access priority weights. In the campus cafeteria area, where traffic is high during lunchtime, when employees travel from other areas to the cafeteria, access control terminals near the cafeteria assign higher access priority weights based on traffic density data. This ensures that employees can pass through the access control points quickly and avoids congestion at the gates.

[0074] Finally, a dynamic authorization set is generated, including time window restrictions, area access rights, and emergency escape routes. For example, a new employee might be restricted to the office and training areas during their probationary period, and only be allowed to enter the campus between 9:00 AM and 5:00 PM on weekdays. Furthermore, each area's access authorization also includes information about the area's emergency escape route. In the event of an emergency, employees can quickly evacuate by following the escape route specified in the authorization.

[0075] In step S150, the dynamic access control policy is sent to the target access control terminal via the cloud server to control the access authority and physical locking status of the access control terminal.

[0076] In the enterprise campus management system, once dynamic access control policies are generated, the cloud server distributes them to the target access control terminals. For example, for the access control of the advanced R&D area mentioned earlier, the cloud server sends a dynamic access control policy containing time window restrictions, area access permissions, and other information to the access control terminal. If the employee's identity verification passes, and the current environmental parameters and historical access records meet the requirements, the cloud server sends a command to the access control terminal, allowing the employee to pass. At this point, the physical lock on the access control terminal is released, allowing the employee to enter the R&D area normally.

[0077] For example, in the park's visitor management, if a visitor passes multi-dimensional security verification, the cloud server will send a dynamic access control policy to the corresponding access control terminal based on the visitor's access area and time restrictions. If a visitor is authorized to visit the park's exhibition center between 10:00 and 11:00 a.m., when the time arrives at 10:00, the cloud server will send a command to the exhibition center's access control terminal to allow the visitor to pass. At the same time, at 11:00, according to policy requirements, the access control terminal may restrict the visitor's continued passage or require re-verification, and adjust the physical locking status as appropriate to ensure the park's security management is carried out in an orderly manner.

[0078] Based on the above steps, the dynamic environmental parameters of the target area in the park and the identity authentication data of the target object are collected in real time through the Internet of Things devices. First, the collected dynamic environmental parameters are matched with the preset security threshold range in real time to generate an environmental security assessment result. Next, the identity feature vector of the target object is extracted based on the identity authentication data, and multi-dimensional security verification is performed in combination with the environmental security assessment result. When the multi-dimensional security verification is passed, a dynamic access control strategy is intelligently generated based on the historical access records and current environmental parameters of the target object. Finally, the dynamic access control strategy is sent to the target access control terminal through the cloud server to achieve intelligent control of the access rights and physical locking status of the access control terminal. The present invention improves the security management level of the smart park and ensures the intelligence and efficiency of access control management.

[0079] In a possible implementation, collecting dynamic environmental parameters of the target area by using IoT devices deployed in the park includes:

[0080] Real-time monitoring values of temperature, humidity and smoke concentration are obtained through distributed environmental sensors.

[0081] The dynamic image data of the target area is captured by the video acquisition device to extract the trajectory and density distribution characteristics of the moving object.

[0082] Voiceprint feature data is collected through sound sensors and compared with the preset abnormal voiceprint database to generate acoustic environment assessment indicators.

[0083] In this embodiment, distributed environmental sensors are first used to obtain real-time monitoring values for temperature, humidity, and smoke concentration. Within the park's layout, environmental sensors are widely installed in various areas. For example, within the park's production workshops, numerous production equipment continuously operates, generating heat dissipation and humidity fluctuations. Environmental sensors can accurately capture real-time temperature and humidity conditions. In workshops producing precision electronic equipment, the temperature must be strictly controlled between 20-22 degrees Celsius and the humidity maintained at 40%-50% to ensure the normal operation of production equipment and product quality. Furthermore, in the park's storage warehouses, particularly those storing flammable items, smoke concentration sensors constantly monitor the ambient smoke concentration. Any smoke formation, even the slightest change in concentration, can be detected by the sensors. For example, if a piece of goods in the warehouse begins to smoke due to moisture or other reasons, the smoke concentration sensors can quickly detect this, providing a basis for subsequent safety measures.

[0084] Secondly, video capture devices capture dynamic image data of the target area, extracting the trajectories and density distribution characteristics of moving objects. Video capture devices play a crucial role in key traffic arteries within the park, such as main roads and parking lot entrances and exits. For example, on the park's main roads, the devices continuously collect image data 24 hours a day. During the morning rush hour, when the volume of vehicles and people is high, the devices can accurately track the movement of each vehicle and pedestrian. Analysis of these trajectories can reveal traffic flow patterns and the formation of congestion points. For example, if a certain intersection exhibits excessive vehicle density during a specific time period, potentially leading to congestion, this information can provide a basis for decision-making regarding traffic management within the park. In the park's parking lots, video capture devices can calculate the parking density of different areas. When a particular area approaches saturation, incoming vehicles can be redirected to other areas with available spaces.

[0085] Furthermore, sound sensors collect voiceprint feature data and compare it with a pre-set abnormal voiceprint database to generate acoustic environment assessment indicators. Sound sensors are installed near key equipment in the equipment room area of the campus. Under normal circumstances, equipment operation produces sounds of specific frequencies and intensities. The sound sensors collect these normal voiceprint feature data and store them as normal baseline data. However, if a device malfunctions, such as a worn motor bearing or loose fan blades, the sound produced by the equipment will change. After collecting the voiceprint feature data of these abnormal sounds, the sound sensors compare it with a pre-set abnormal voiceprint database. A successful match indicates that the equipment may pose a safety hazard. For example, the database stores the high-frequency, harsh soundprint characteristics emitted by an overloaded motor. When the sound sensors collect similar soundprints, corresponding acoustic environment assessment indicators are generated, indicating that the equipment in the area may be at risk of failure and requires timely inspection and maintenance.

[0086] In a possible implementation, matching the dynamic environmental parameters with a preset safety threshold range in real time to generate an environmental safety assessment result includes:

[0087] A time series analysis is performed on the temperature monitoring values to detect abnormal temperature fluctuation patterns.

[0088] The trajectory of the moving object is spatially matched with a preset electronic map of the park to identify unauthorized area intrusion events.

[0089] The acoustic environment assessment index and the smoke concentration change rate are integrated to calculate the comprehensive environmental risk coefficient.

[0090] When the comprehensive environmental risk coefficient exceeds the dynamically adjusted threshold, an environmental safety alarm signal is triggered.

[0091] In the park's security management system, real-time matching of the collected dynamic environmental parameters with the preset safety threshold range is a crucial link.

[0092] Time series analysis of monitored temperature values can be used to detect abnormal temperature fluctuation patterns. For example, the greenhouse planting area of the park houses a variety of valuable flowers and rare plants. Different plants have different growth requirements and are highly sensitive to temperature fluctuations. Normally, daytime temperatures should be between 18 and 25 degrees Celsius. Environmental sensors continuously collect temperature data, generating a time series. If the temperature suddenly drops from 22 to 15 degrees Celsius over a period of time, such as several consecutive hours, this constitutes an abnormal temperature fluctuation pattern. This fluctuation could be due to a malfunction in the greenhouse's temperature control system or inclement weather affecting the greenhouse's insulation. By detecting this abnormal temperature fluctuation pattern, the system can promptly identify the risk of plant frost damage in the greenhouse planting area and take appropriate measures, such as activating backup heating equipment or checking the greenhouse's sealing.

[0093] The system spatially matches the trajectories of moving objects against a pre-set electronic map of the campus to identify unauthorized intrusions. Access to the confidential R&D area of the campus is strictly restricted. The pre-set electronic map clearly identifies the boundaries of the R&D area and its various functional divisions. Video capture devices continuously monitor dynamic image data surrounding the R&D area and extract the trajectories of moving objects. If an unauthorized person or vehicle approaches the R&D area and their movement trajectory indicates that they have entered the R&D boundary, the system identifies this as an unauthorized intrusion. For example, if an outsider attempts to break through security and enter the R&D area to steal confidential information, once their movement trajectory is captured and spatially matched against the electronic map, the system will immediately issue an alarm, notifying campus security personnel to intercept and handle the situation.

[0094] The system combines acoustic environment assessment indicators with the smoke concentration change rate to calculate a comprehensive environmental risk factor. In the campus's office buildings, especially on floors with a concentration of electrical equipment, such as computer rooms and distribution rooms, during normal operation, the acoustic environment is dominated by the hum of normal equipment operation, and smoke concentrations are extremely low. If, at a certain moment, the sound sensor detects an abnormal electrical discharge, the acoustic environment assessment indicator indicates an abnormality, and the smoke concentration sensor simultaneously detects a slight upward trend in smoke concentration, the system combines these two parameters to calculate a comprehensive environmental risk factor. Assuming the abnormality level of the acoustic environment assessment indicator is 0.3 (based on predefined assessment criteria) and the smoke concentration change rate is 0.2 (also based on predefined criteria), a specific calculation formula (such as weighted summation) yields a comprehensive environmental risk factor of 0.5. When this comprehensive environmental risk factor exceeds a dynamically adjusted threshold (for example, set to 0.4), an environmental safety alarm is triggered. This alarm is sent to the campus's security monitoring center, prompting personnel to inspect the equipment and environment within the office building to eliminate potential fire or electrical failure risks.

[0095] In a possible implementation, the step of collecting identity verification data includes:

[0096] The electronic identity credential is read via the NFC device to encrypt the data packet.

[0097] Multimodal biometric features collected by biometric recognition devices include three-dimensional facial feature point cloud data and palm vein topology.

[0098] Real-time positioning information and historical access authorization records uploaded through mobile terminals.

[0099] An encrypted data packet of electronic identity credentials is read by a near-field communication device. Near-field communication devices are installed at each access control entrance to the campus. Employees and visitors enter the campus using a card or mobile device with an electronic identity credential. For example, an employee's work ID card contains an encrypted chip containing their identity information. When an employee holds their ID card against the access control's near-field communication reader, the reader reads the encrypted data packet. This encrypted data packet contains important identity information such as the employee's name, department, position, and authority level. This information is encrypted to ensure security during transmission and reading, preventing identity theft or tampering.

[0100] Multimodal biometric features collected by biometric devices include 3D facial feature point cloud data and palm vein topology. Biometric devices have been installed at key entrances within the campus, such as access control points for important office areas and the finance office. When employees need to enter these areas, they step before the biometric device. The biometric device first collects the employee's 3D facial feature point cloud data. This process accurately captures the three-dimensional structural features of key facial features, such as the 3D coordinates and shape characteristics of the eyes, nose, and mouth, forming a complete facial feature point cloud. The device also collects the employee's palm vein topology, including unique structural features such as the branching patterns and intersections of the palm veins. For example, only authorized finance personnel are allowed access to the finance office. When a finance employee steps before the biometric device, the facial feature point cloud data and palm vein topology collected by the device serve as crucial verification for their identity.

[0101] Real-time location information and historical access authorization records uploaded by mobile terminals. The park requires employees to enable the positioning function of their mobile terminals while on campus. Mobile terminals will regularly upload their real-time location information to the park's security management system. For example, when an employee moves within the park, from the office building to the campus cafeteria, the mobile terminal will send real-time location information to the system. The system also records the employee's historical access authorization records. These records include information such as the areas the employee has entered, the length of time spent in each area, and entry and exit timestamps. For example, for a sales employee who frequently travels between different areas of the park for business negotiations, the system will record detailed information on each entry into areas such as the customer reception area and conference room. This information, combined with real-time location information, provides data support for employee identity verification and security management.

[0102] In a possible implementation, extracting the identity feature vector of the target object based on the identity authentication data and performing multi-dimensional security verification in combination with the environmental security assessment result includes:

[0103] The encrypted data packet of the electronic identity certificate is verified by the blockchain node to confirm the validity period and authority level of the identity certificate.

[0104] The multimodal biometric features are compared with pre-stored feature templates in a hierarchical manner to generate a biometric matching matrix.

[0105] A spatial proximity parameter is calculated based on the real-time positioning information and the geographic coordinates of the access control terminal.

[0106] When the biometric matching matrix meets the dynamic verification threshold and the spatial proximity parameter is within an allowable range, an identity verification pass instruction is generated.

[0107] Blockchain node verification is performed on the encrypted data packet of the electronic identity credential to confirm the credential's validity period and permission level. Assume that a campus utilizes a blockchain-based authentication system. The electronic identity credential information of employees and visitors is stored on blockchain nodes. When an employee attempts to enter a specific area of the campus, the system verifies the encrypted data packet of their electronic identity credential on the blockchain node. For example, in the campus's R&D laboratory, only R&D personnel with advanced permissions are allowed access. The system first verifies whether the employee's identity credential is within its validity period. For example, an employee's work ID is valid for three years from the date of issuance. If the credential is within its validity period, the system then verifies the permission level. If the employee's permission level is advanced R&D and matches the R&D laboratory's access permissions, the verification passes. This blockchain node verification method ensures the authenticity and immutability of the identity credential, enhancing authentication security.

[0108] Multimodal biometric features are compared against pre-stored feature templates in a hierarchical manner to generate a biometric match matrix. For example, when a senior executive's office access control system is used in a campus, the executive steps into the biometric recognition system. The 3D facial feature point cloud data and palm vein topology captured by the biometric recognition system are then compared against the pre-stored feature template for the executive. Initially, a preliminary comparison of the overall structure is performed, such as the facial outline and the general direction of the palm veins. Then, a more detailed hierarchical comparison is performed, such as comparing the detailed features around the eyes and the micro-branching structure of the palm veins within the facial feature point cloud data. During this process, the system generates a biometric match matrix. This matrix contains the match values for each level of facial and palm vein features. For example, the overall structural match of the facial features is 90%, the detailed features around the eyes are 85%, the overall direction of the palm veins is 92%, and the micro-branching structure is 88%. If all matching indicators in the biometric matching matrix meet the dynamic verification threshold (for example, the set overall matching threshold is above 80%), the verification of biometric matching is passed.

[0109] The spatial proximity parameter is calculated based on real-time location information and the geographic coordinates of the access control terminal. Within the campus, when an employee approaches an access control terminal, the system calculates the spatial proximity parameter based on the real-time location information uploaded by the employee's mobile device and the access control terminal's geographic coordinates. For example, at the access control of the employee dormitory area, an employee walks from the dormitory to the access control terminal to exit. The employee's mobile device transmits its real-time location information, and the system calculates the distance between the employee and the access control terminal to be 3 meters (assuming this distance is the spatial proximity parameter). If the set allowable range is within 5 meters and the biometric matching matrix meets the dynamic verification threshold, the spatial proximity verification passes. When all these verification conditions are met, the system generates an authentication pass instruction, allowing the employee to pass through the access control. This process also incorporates the results of a previous environmental safety assessment. If the environmental safety assessment indicates anomalies in the area surrounding the access control terminal, such as high smoke concentration or the presence of unauthorized objects, the system may implement additional security measures, such as issuing a warning or temporarily restricting access to the access control terminal, to ensure overall campus security, even if authentication passes.

[0110] In one possible implementation, generating a dynamic access control strategy based on the target object's historical passage records and current environmental parameters includes:

[0111] Analyze the time distribution characteristics and access frequency patterns in the historical access records to establish a behavior profile of the object.

[0112] Adjust the biometric sensitivity level of the access control terminal based on the visibility index and light intensity parameters in the current environmental parameters.

[0113] Based on the real-time crowd density data of each area in the park, the access priority weights of the access control terminals are dynamically allocated.

[0114] Generate dynamic authorization instruction sets that include time window restrictions, area access rights, and emergency escape routes.

[0115] For example, a senior engineer within the campus will undergo a detailed analysis of his access history. Based on his time distribution, he typically spends time within the campus between 8:30 AM and 5:30 PM on weekdays, and eats in the cafeteria between 12 PM and 1 PM. His visit frequency patterns reveal that he conducts experiments in the lab three times a week, attends project meetings in the conference room twice a week, and enters and exits his office floor multiple times daily. Based on this information, the system constructs a behavioral profile for the engineer. This profile not only reflects his daily work activities but also provides an important basis for developing access control policies. For example, if he attempts to enter the lab outside of working hours, such as at 8 PM, this does not align with his typical behavior profile. The system may conduct stricter scrutiny of his entry request or even deny it outright unless he provides a reasonable explanation and additional authorization.

[0116] The access control terminal's biometric sensitivity level is adjusted based on the current environmental parameters, such as visibility and light intensity. In outdoor access control areas within a campus, such as the campus gate and access control points connecting the campus to the outside world, these parameters significantly impact the accuracy of biometric recognition. In the early morning or evening, visibility is low and light intensity is weak. For example, on a winter morning, fog is heavy, visibility may be only a few dozen meters, and light intensity is also low. In these conditions, the access control terminal's biometric recognition function may be affected. To ensure that employees can pass through the access control system, the system adjusts the biometric sensitivity level based on the current visibility and light intensity parameters. The original facial feature match requirement is set to at least 95%. In such low visibility and light conditions, the system may adjust the match requirement to at least 90%. This prevents employees from being unable to pass through the access control system due to environmental factors and also ensures access control security to a certain extent.

[0117] Based on real-time traffic density data for various areas within the campus, access control terminals are dynamically assigned access priority weights. Public areas within the campus, such as the cafeteria and gymnasium, experience significant variations in traffic density at different times of day. For example, lunchtime is peak traffic for the cafeteria, with many employees frequenting the cafeteria for meals. During this time, access control terminals near the cafeteria assign higher access priority weights to employees heading to the cafeteria based on real-time traffic density data from various areas within the campus. If other people are en route to the cafeteria from other areas within the campus, their access verification requests will be prioritized when they arrive at the cafeteria gate, ensuring they pass through quickly and avoiding congestion. Employees heading to the cafeteria during off-peak hours have lower access priority weights, and access verification proceeds according to the normal process.

[0118] Generate dynamic authorization instructions that include time window restrictions, area access rights, and emergency escape routes. For new employees within the campus, the system generates a specific dynamic authorization instruction set. Regarding time window restrictions, new employees may only be allowed to enter the campus between 9:00 AM and 6:00 PM on weekdays, based on their onboarding and work schedule. Regarding area access rights, new employees may initially be granted access only to office and training areas. As their work hours increase and their work needs change, their area access rights will be gradually expanded. Furthermore, the access authorization instructions for each area also include information about the area's emergency escape routes. For example, the access authorization instructions for the office building clearly indicate which staircase or passageway to evacuate to a safe area in the event of an emergency, such as a fire. This dynamic authorization instruction set not only ensures the normal movement of new employees within the campus but also protects their safety in emergencies.

[0119] In one possible implementation, the method further includes:

[0120] When it is detected that the access control terminal is offline or the communication delay exceeds the set threshold, the local decision-making mode of the edge computing node is started.

[0121] The offline authentication algorithm is executed by the edge computing node, and the verification result data is cached.

[0122] After communication is restored, cached data is automatically synchronized to the cloud server and the access control policy version information is updated.

[0123] Adjust the encryption communication protocol level of the access control terminal according to the data synchronization status.

[0124] In the access control management system of the campus, the normal communication of the access control terminal is crucial to security management. However, sometimes the access control terminal may go offline or the communication delay may exceed the set threshold.

[0125] For example, an access control terminal in a remote area of the campus might lose communication with the cloud server due to a network failure or external interference, or experience a communication delay exceeding a set threshold (for example, a 5-second delay threshold). In this case, the system automatically activates the local decision-making mode of the edge computing node. The edge computing node is located near the access control terminal and stores some of the necessary authentication data and algorithms. Once in local decision-making mode, the edge computing node executes the offline authentication algorithm. Suppose an employee attempts to enter the campus using this offline access control terminal. The edge computing node reads the encrypted data packet of the employee's electronic identity credential from their near-field communication device and performs local verification. Simultaneously, the biometric recognition device collects the employee's multimodal biometric features, which the edge computing node then compares in layers against pre-stored feature templates stored locally. If the employee's authentication is successful, the edge computing node caches the verification result data. This cached data is crucial once communication is restored.

[0126] When communication between the access control terminal and the cloud server is restored, the verification result data previously cached in the edge computing node will be automatically synchronized to the cloud server. For example, after the access control terminal is offline and communication is restored, the edge computing node will send the cached employee identity verification result data to the cloud server. After receiving this data, the cloud server will update the access control policy version information based on this data, the current campus security policy, and other relevant factors. If there are new security regulations or access control policy adjustments during the offline period, the cloud server will send the updated access control policy version information to the access control terminal. For example, due to the increased security level of a certain area in the campus, the cloud server will adjust the access permission requirements of the access control terminal and send the new access control policy version information to the access control terminal so that the access control terminal can perform access control management according to the new policy.

[0127] When data synchronization between the access control terminal and the cloud server is working well—for example, data is completely and accurately synchronized without data loss or errors—the access control terminal's encryption protocol level may remain at the default level, such as medium. This level ensures data transmission security while maintaining good communication efficiency. However, if problems occur during data synchronization, such as partial data loss or data transmission errors, the system will deem the synchronization status poor. In this case, to ensure the security of subsequent data transmission, the access control terminal's encryption protocol level will be increased, for example, from medium to high. High encryption uses more complex encryption algorithms and longer encryption keys, providing higher data security, but may reduce communication efficiency. This approach of adjusting the encryption protocol level based on data synchronization status strikes a balance between ensuring data security and maintaining the normal operation of the access control management system.

[0128] In one possible implementation, the method further includes:

[0129] Build a knowledge graph of access control events and associate and store historical verification records, device status data, and environmental parameter changes.

[0130] The event association patterns in the knowledge graph are analyzed through a deep learning model to predict potential security risks.

[0131] When abnormal access behavior patterns are detected, the verification security level of the access control terminal is automatically upgraded.

[0132] Generate risk warning reports and push them to associated security management terminals.

[0133] In the above embodiments, the IoT-based smart campus access control management system for executing the above method embodiments has at least one processor, a control module (chip set) coupled to at least one of the (at least one) processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one loading / output device coupled to the control module, and a network interface coupled to the control module.

[0134] The processor may include at least one single-core or multi-core processor, and the processor may include any combination of general-purpose processors or dedicated processors (such as graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the smart campus access control management system based on the Internet of Things can be used as the gateway or other electronic device described in the embodiments of this application.

[0135] For some alternative embodiments, the IoT-based smart campus access control management system may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor integrated with the at least one computer-readable medium and configured to execute instructions to implement a module to perform the actions described in this disclosure.

[0136] For one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) and / or any suitable device or component in communication with the control module.

[0137] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0138] The memory can be used, for example, to load and store data and / or instructions for an IoT-based smart campus access control management system. For one embodiment, the memory can include any suitable volatile memory, such as a suitable DRAM.

[0139] For one embodiment, the control module may include at least one load / output controller to provide an interface to the NVM / storage device and the (at least one) load / output device.

[0140] For example, NVM / storage devices may be used to store data and / or instructions. The NVM / storage devices may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one compact disc (CD) drive, and / or at least one digital versatile disc (DVD) drive).

[0141] The NVM / storage device may include storage resources that are physically part of the device on which the IoT-based smart campus access control management system is installed, or it may be accessible to the device without being part of the device. For example, the NVM / storage device may be accessed via (at least one) load / output device over a network.

[0142] The (at least one) load-in / output device may provide an interface for the smart campus access control management system based on the Internet of Things to communicate with any other appropriate device, and the load-in / output device may include a communication component, a pinyin component, a sensor component, etc. The network interface may provide an interface for the smart campus access control management system based on the Internet of Things to communicate based on at least one network, and the smart campus access control management system based on the Internet of Things may wirelessly communicate with at least one component of a wireless network based on any of the at least one wireless network priors and / or protocols, for example, access a wireless network based on a communication prior.

[0143] For one embodiment, at least one of the (at least one) processors may be loaded together with the logic of at least one controller of a control module (e.g., a memory controller module). For one embodiment, at least one of the (at least one) processors may be loaded together with the logic of at least one controller of a control module to form a system-level load. For one embodiment, at least one of the (at least one) processors may be fused on the same die with the logic of at least one controller of a control module. For one embodiment, at least one of the (at least one) processors may be fused on the same die with the logic of at least one controller of a control module to form a system-on-chip (SoC).

[0144] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0145] An embodiment of the present invention discloses a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the smart campus access control management method based on the Internet of Things described in the aforementioned embodiment.

[0146] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the smart campus access control management method based on the Internet of Things described in the aforementioned embodiment.

[0147] The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple modules. Some or all of the modules may be selected based on actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement the present invention without inventive effort.

[0148] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, the storage medium including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electronically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of storing or storing data.

[0149] Finally, it should be noted that what is disclosed above is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A smart park access control management method based on the Internet of Things, characterized in that: The method comprises: The IoT devices deployed in the park collect dynamic environmental parameters of the target area and identity verification data of the target object; Matching the dynamic environmental parameters with the preset safety threshold range in real time to generate an environmental safety assessment result; Extracting the identity feature vector of the target object based on the identity authentication data, and performing multi-dimensional security verification in combination with the environmental security assessment results; When the multi-dimensional security verification is passed, a dynamic access control strategy is generated based on the historical access records of the target object and the current environmental parameters; The dynamic access control strategy is sent to the target access control terminal through the cloud server to control the access authority and physical locking status of the access control terminal.

2. The method for managing access control of a smart park based on the Internet of Things according to claim 1, characterized in that: The dynamic environmental parameters of the target area are collected by IoT devices deployed in the park, including: Obtain real-time monitoring values of temperature, humidity, and smoke concentration through distributed environmental sensors; Capture dynamic image data of the target area through a video acquisition device to extract the trajectory and density distribution characteristics of moving objects; Voiceprint feature data is collected through sound sensors and compared with the preset abnormal voiceprint database to generate acoustic environment assessment indicators.

3. The method for managing access control of a smart park based on the Internet of Things according to claim 2, characterized in that: The step of matching the dynamic environmental parameters with a preset safety threshold range in real time to generate an environmental safety assessment result includes: performing time series analysis on the temperature monitoring values to detect abnormal temperature fluctuation patterns; Spatial matching of the moving object trajectory with a preset campus electronic map to identify unauthorized area intrusion events; The acoustic environment assessment index and the smoke concentration change rate are integrated to calculate the comprehensive environmental risk coefficient; When the comprehensive environmental risk coefficient exceeds the dynamically adjusted threshold, an environmental safety alarm signal is triggered.

4. The method for managing access control of a smart park based on the Internet of Things according to claim 1, characterized in that: The steps of collecting identity verification data include: An encrypted data packet of electronic identity credentials read by a near-field communication device; Multimodal biometric features collected by biometric recognition devices, including 3D facial feature point cloud data and palm vein topology; Real-time positioning information and historical access authorization records uploaded through mobile terminals.

5. The method for managing access control of a smart park based on the Internet of Things according to claim 4 is characterized in that: Extracting the identity feature vector of the target object based on the identity authentication data and performing multi-dimensional security verification in combination with the environmental security assessment result includes: Performing blockchain node verification on the encrypted data packet of the electronic identity certificate to confirm the validity period and authority level of the identity certificate; Performing a hierarchical comparison of the multimodal biometric features with pre-stored feature templates to generate a biometric matching matrix; Calculating a spatial proximity parameter based on the real-time positioning information and the geographic coordinates of the access control terminal; When the biometric matching matrix meets the dynamic verification threshold and the spatial proximity parameter is within an allowable range, an identity verification pass instruction is generated.

6. The method for managing access control of a smart park based on the Internet of Things according to claim 1, characterized in that: Generating a dynamic access control strategy based on the target object's historical access records and current environmental parameters includes: Analyze the time distribution characteristics and access frequency patterns in the historical access records to establish a behavior profile of the object; Adjust the biometric sensitivity level of the access control terminal based on the visibility index and light intensity parameters in the current environmental parameters; Dynamically assign access priority weights to access control terminals based on real-time crowd density data in each area of the park; Generate dynamic authorization instruction sets that include time window restrictions, area access rights, and emergency escape routes.

7. The method for access control management of a smart park based on the Internet of Things according to claim 1, characterized in that: The method further comprises: When it is detected that the access control terminal is offline or the communication delay exceeds the set threshold, the local decision-making mode of the edge computing node is started; Executing an offline authentication algorithm through the edge computing node and caching the authentication result data; Automatically synchronize cached data to the cloud server after communication is restored and update access control policy version information; Adjust the encryption communication protocol level of the access control terminal according to the data synchronization status.

8. The method for managing access control of a smart park based on the Internet of Things according to claim 1, characterized in that: The method further comprises: Build a knowledge graph of access control events to associate and store historical verification records, device status data, and environmental parameter changes; Analyze event association patterns in the knowledge graph through a deep learning model to predict potential security risks; Automatically upgrade the verification security level of the access control terminal when abnormal access behavior patterns are detected; Generate risk warning reports and push them to associated security management terminals.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores machine-executable instructions, which, when executed by a computer, implement the smart park access control management method based on the Internet of Things as described in any one of claims 1 to 8.

10. A smart park access control management system based on the Internet of Things, characterized by: It includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the smart park access control management method based on the Internet of Things as described in any one of claims 1 to 8 is implemented.

Images