A door access control method and system based on ultra-high frequency RFID technology

Abstract

The application relates to the field of access control, in particular to an access control method and system based on super-high-frequency RFID technology, the method comprising the following steps: S1: according to the size, shape and personnel flow of an access control area, a multi-antenna array is arranged through distributed layout; S2: according to a Hyperledger Fabric blockchain platform, nodes are deployed at different positions through a distributed node architecture; S3: an artificial intelligence model is trained through data collected in an access control system, the trained artificial intelligence model performs real-time analysis and detection on the data in the access control system, and abnormal behaviors and events are identified; and S4: each data in the access control system is displayed on a management platform in a visual manner, and data analysis and optimized management are provided according to a permission management mechanism. The application can improve the safety of the access control system, improve the reliability of the access control system, enhance the intelligent level of the access control system, and improve the management efficiency of the access control system.

Description

Technical Field

[0001] This invention relates to the field of access control, and more particularly to an access control method and system based on ultra-high frequency RFID technology. Background Technology

[0002] With the continuous development of technology, access control systems are becoming increasingly important in various fields. Traditional access control systems mainly use keys, passwords, and cards for authentication, but these methods suffer from problems such as easy loss, vulnerability to hacking, and inconvenient management. The emergence of UHF RFID technology has brought new solutions to access control systems. UHF RFID has advantages such as long-distance identification, fast reading, and simultaneous identification of multiple tags, which can effectively improve the efficiency and security of access control systems. However, traditional UHF RFID technology also has some limitations, such as the possibility of data tampering, signal interference, and the inability to effectively detect abnormal behavior. Summary of the Invention

[0003] To address the aforementioned issues, this invention provides an access control method and system based on ultra-high frequency RFID technology, which can improve the security, reliability, intelligence, and management efficiency of the access control system.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] An access control method based on ultra-high frequency RFID technology includes the following steps:

[0006] S1: Based on the size, shape, and personnel flow of the access control area, a multi-antenna array is set up through a distributed layout;

[0007] S2: Based on the Hyperledger Fabric blockchain platform, nodes are deployed in different locations through a distributed node architecture;

[0008] S3: Train an artificial intelligence model by collecting data from the access control system. The trained artificial intelligence model performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events.

[0009] S4: Displays all data from the access control system in a visual manner on the management platform, and provides data analysis and optimization management based on the permission management mechanism.

[0010] Furthermore, the step of setting up a multi-antenna array through a distributed layout based on the size, shape, and personnel flow of the access control area includes the following steps:

[0011] S11: Determine the antenna for UHF RFID technology based on the antenna's gain, directivity, and frequency response. Based on the size, shape, and personnel flow of the access control area, set up a multi-antenna array in a distributed layout and connect the reader to the antenna via wireless connection.

[0012] S12: Preprocess the signals received by each antenna, measure and record the signal strength of the preprocessed signals, obtain the weight of each antenna through a signal weighting algorithm, and sum the signals by weighting.

[0013] S13: The operation of independent signal reception, signal comparison and selection and signal fusion is performed through spatial diversity algorithm. The fused signal obtained by spatial diversity algorithm and the weighted signal obtained by signal weighting algorithm are finally fused through decision fusion method.

[0014] Furthermore, the Hyperledger Fabric blockchain platform, through a distributed node architecture, deploys nodes in different locations, including the following steps:

[0015] S21: Based on the Hyperledger Fabric blockchain platform, deploy light nodes on access control devices, deploy full nodes on the central server, and connect edge smart boxes between the access control devices and the central server;

[0016] S22: By configuring access control management software parameters, it communicates with UHF RFID readers and light nodes; by configuring blockchain node management software parameters on the central server, it manages all nodes and communicates with edge smart boxes; by configuring data preprocessing and encryption software parameters on edge smart boxes, it preprocesses and encrypts access control data.

[0017] S23: When a user approaches the access control device using an access card or tag, the UHF RFID reader reads the user's identity information and sends the information to the access control management software on the access control device. The access control management software sends the user's identity information to the light node. The light node records the information in its local blockchain ledger and sends the information to the full node on the central server. The full node records the received information in the complete blockchain ledger and participates in the blockchain consensus process. The edge smart box encrypts and preprocesses the user's identity information and then sends the encrypted information to the full node on the central server. The full node records the encrypted information in the blockchain ledger.

[0018] S24: Once a user's identity information is recorded in the blockchain ledger, the access control software controls the opening and closing of the access control device based on the user's permission information. If the user has legitimate permissions, the access control device will unlock the door and allow the user to enter; if the user does not have legitimate permissions, the access control device will keep the door locked and refuse the user entry.

[0019] Furthermore, the full node records the received information in the complete blockchain ledger and participates in the blockchain consensus process, including verifying the transaction information received by the full node using a practical Byzantine fault-tolerant consensus algorithm and coordinating the consensus process through message passing between nodes; the edge smart box preprocesses the user's identity information, including preprocessing the raw data from the access control device using data compression and deduplication algorithms; the edge smart box encrypts the user's identity information, including encrypting it using Advanced Encryption Standard (AES) encryption algorithms.

[0020] Furthermore, the process of training an artificial intelligence model by collecting data from the access control system, and then using the trained model to perform real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events, includes the following steps:

[0021] S31: Based on the data collected from the access control system, preprocess the collected data, including cropping, scaling and grayscale conversion of image data, and segmentation and standardization of time series data.

[0022] S32: Divide the preprocessed data into training set, validation set and test set. Train the artificial intelligence model using the training set and optimize the model using the Adam optimization algorithm during the training process. Validate the model using the validation set and evaluate the trained artificial intelligence model using the test set. Optimize the model based on the evaluation results.

[0023] Furthermore, the artificial intelligence model includes the implementation of an artificial intelligence model through the fusion of convolutional neural networks and recurrent neural networks using a distributed architecture; the distributed architecture includes Apache Doris.

[0024] Furthermore, the convolutional neural network includes a convolutional neural network model constructed based on the ResNet architecture, convolutional layers, pooling layers, and fully connected layers. The convolutional neural network model is trained using preprocessed image data, and the model parameters are adjusted according to the stochastic gradient descent optimization algorithm. The trained convolutional neural network model is then applied to new access control system image data to extract the spatial feature representation of the image. The output of the convolutional neural network is a vector feature representing the image.

[0025] Furthermore, the recurrent neural network includes a recurrent neural network model constructed based on a long short-term memory network architecture, recurrent layers, and fully connected layers. The output of the convolutional neural network is fused with the time series data features using a weighted summation method to obtain the input vector of the recurrent neural network. The recurrent neural network model is trained using preprocessed time series data and the fused input vector. The model parameters are adjusted according to the backpropagation algorithm. The spatial features of the convolutional neural network output are analyzed and detected. The trained recurrent neural network model is applied to the time series data and convolutional neural network output of the new access control system to predict abnormal behaviors and events. The output of the recurrent neural network is a probability value or a classification result.

[0026] Furthermore, the data from the access control system is displayed visually on the management platform, and data analysis and optimization management are provided based on the access control mechanism, including the following steps:

[0027] S41: Data storage is performed using a combination of relational and non-relational databases. Relational databases are used to store structured data, while non-relational databases are used to store unstructured data. Data backup and recovery strategies are implemented.

[0028] S42: The visual management platform is presented through responsive design. The analysis results are displayed on the management platform through data visualization technology. The display formats include data charts, map displays and reports. Different interface layouts and display content are displayed according to user needs and permission levels.

[0029] S43: Assign different permissions to different user roles through a role-based access control model; use statistical analysis algorithms to calculate the average time for personnel to enter and exit and traffic indicators during peak hours; verify identity through multi-factor authentication, including password, Bluetooth, facial recognition and token; and highlight abnormal behavior detection results with different colors or icons.

[0030] S44: Analyze personnel behavior patterns through clustering algorithms and predict future personnel flow through prediction algorithms. Based on the analysis results, uncover hidden patterns and trends in the data and generate a report with optimization management suggestions.

[0031] An access control system based on UHF RFID technology includes a multi-antenna array module for communication connection, a blockchain module, an artificial intelligence algorithm module, and a visualization management module, wherein:

[0032] The multi-antenna array module is used to set up multiple antenna arrays in a distributed layout according to the size, shape and personnel flow of the access control area;

[0033] The blockchain module is used to deploy nodes in different locations through a distributed node architecture based on the Hyperledger Fabric blockchain platform;

[0034] The artificial intelligence algorithm module is used to train an artificial intelligence model by collecting data from the access control system. The trained artificial intelligence model performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events.

[0035] The visualization management module is used to display various data in the access control system on the management platform in a visual manner, and provides data analysis and optimization management based on the permission management mechanism.

[0036] The beneficial effects of this invention are as follows:

[0037] 1. By deploying a multi-antenna array in a distributed layout, the signal coverage area is expanded, signal blind spots are reduced, and the accuracy and reliability of tag reading are improved. Simultaneously, the coordinated operation of multiple antennas enhances signal strength, reduces the risk of interference, and prevents unauthorized personnel from entering the access control area through signal interference. The decentralized, immutable, and secure characteristics of blockchain ensure the authenticity and integrity of data. Any attempt to tamper with access control records will be immediately detected, effectively preventing malicious data alteration or forgery, improving the security of the access control system, and facilitating data exchange with vehicle management departments. Real-time analysis and detection of data in the access control system can identify abnormal behaviors and events.

[0038] 2. In signal processing and fusion, signal weighting and spatial diversity algorithms are employed to improve signal quality and stability. The signal weighting algorithm assigns different weights to different antennas based on their location and signal strength, allowing antennas with stronger signals and higher reliability to contribute more to the final fusion result. The spatial diversity algorithm utilizes the spatial diversity effect of multiple antennas to improve signal reception quality and reliability, reduce the probability of signal loss, and enhance the reliability of the access control system. On the Hyperledger Fabric blockchain platform, a distributed node architecture is adopted, deploying nodes in different locations, including light nodes on access control devices and full nodes on the central server. This distributed architecture improves the system's fault tolerance; even if one node fails, other nodes can still function normally, ensuring the stable operation of the access control system. Edge smart boxes connect the access control devices and the central server, preprocessing and encrypting data, improving data transmission efficiency and security. Simultaneously, edge smart boxes can monitor and analyze access control data in real time, promptly detecting anomalies and taking corresponding measures, further enhancing the reliability of the access control system.

[0039] 3. The artificial intelligence model obtained by fusing two complementary algorithms can fully leverage their respective advantages to improve the analysis and detection capabilities of access control system data. The fusion of convolutional neural networks and recurrent neural networks allows for better analysis and prediction of personnel behavior and events. The AI ​​algorithm can automatically learn and adapt to different access control scenarios, continuously improving its performance and accuracy, thus enhancing the intelligence level of the access control system. The visualization management platform displays various data from the access control system in an intuitive way, facilitating management and monitoring by administrators. Simultaneously, based on a permission management mechanism, the visualization management platform provides data analysis and optimization management functions for different users. Administrators can use the visualization management platform to understand the operational status of the access control system, personnel entry and exit, abnormal behavior detection results, etc., enabling timely decision-making and adjustments, thereby improving the intelligent management level of the access control system. Attached Figure Description

[0040] Figure 1 This is a flowchart of an access control method based on ultra-high frequency RFID technology.

[0041] Figure 2 This is a schematic diagram of an access control system based on ultra-high frequency RFID technology. Detailed Implementation

[0042] Please see Figure 1 and Figure 2 As shown, this invention relates to an access control method based on ultra-high frequency RFID technology, comprising the following steps:

[0043] S1: Based on the size, shape, and personnel flow of the access control area, a multi-antenna array is set up through a distributed layout;

[0044] S2: Based on the Hyperledger Fabric blockchain platform, nodes are deployed in different locations through a distributed node architecture;

[0045] S3: Train an artificial intelligence model by collecting data from the access control system. The trained artificial intelligence model performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events.

[0046] S4: Displays all data from the access control system in a visual manner on the management platform, and provides data analysis and optimization management based on the permission management mechanism.

[0047] Furthermore, the step of setting up a multi-antenna array through a distributed layout based on the size, shape, and personnel flow of the access control area includes the following steps:

[0048] S11: Determine the antenna for UHF RFID technology based on the antenna's gain, directivity, and frequency response. Based on the size, shape, and personnel flow of the access control area, set up a multi-antenna array in a distributed layout and connect the reader to the antenna via wireless connection.

[0049] S12: Preprocess the signals received by each antenna, measure and record the signal strength of the preprocessed signals, obtain the weight of each antenna through a signal weighting algorithm, and sum the signals by weighting.

[0050] S13: The operation of independent signal reception, signal comparison and selection and signal fusion is performed through spatial diversity algorithm. The fused signal obtained by spatial diversity algorithm and the weighted signal obtained by signal weighting algorithm are finally fused through decision fusion method.

[0051] Specifically, the advantages of a distributed layout of multi-antenna arrays include: by setting antennas in different locations, comprehensive coverage of the access control area can be achieved, reducing signal blind spots; the collaborative work of multiple antennas can increase signal reception strength, improving the accuracy and reliability of tag reading; multiple tags can be read simultaneously, increasing system capacity and processing power; and signal interference can be reduced, improving the system's anti-interference capability.

[0052] In step S11, according to the layout plan, antennas are installed at different locations within the access control area, ensuring that the distance and angle between antennas are reasonable to avoid signal interference and overlap. Based on the reader's reading distance, reading speed, and multi-tag processing capability, an UHF RFID reader is selected, and the reader is connected to each antenna to ensure stable and reliable signal transmission. The reader's parameters, such as frequency, power, and sensitivity, are configured to adapt to different application scenarios and environmental conditions.

[0053] In step S12, the signals received by each antenna are preprocessed, including filtering, amplification, and noise reduction, to improve signal quality and stability. The signal strength of the preprocessed signals is measured and recorded to prepare for the signal weighting algorithm. Following the implementation steps of the signal weighting algorithm, the weight of each antenna is calculated, and the signals are weighted and summed to obtain the weighted signal sum, which serves as one of the inputs for signal fusion.

[0054] In step S13, following the implementation steps of the spatial diversity algorithm, operations such as antenna layout and selection, independent signal reception, signal comparison and selection, and signal fusion are performed. The fused signal obtained from the spatial diversity algorithm and the weighted signal obtained from the signal weighting algorithm are further fused. The decision fusion involves selecting the signal obtained from either the signal weighting algorithm or the spatial diversity algorithm as the final fused signal based on certain decision rules. For example, if the signal obtained from the spatial diversity algorithm has better quality, that signal is selected; otherwise, the signal obtained from the signal weighting algorithm is selected. The fused signal is further processed and analyzed to extract tag information and make access control decisions.

[0055] By combining signal weighting and spatial diversity algorithms, more accurate and reliable signal processing and fusion are achieved in UHF RFID access control. The signal weighting algorithm assigns different weights based on factors such as antenna signal strength, distance, and reliability, allowing antennas with better signal quality to contribute more to the final result. The spatial diversity algorithm improves signal stability and anti-interference capabilities through independent reception and signal comparison and selection by multiple antennas. Combining these two algorithms fully leverages their advantages to enhance the performance of the access control system.

[0056] Furthermore, the Hyperledger Fabric blockchain platform, through a distributed node architecture, deploys nodes in different locations, including the following steps:

[0057] S21: Based on the Hyperledger Fabric blockchain platform, deploy light nodes on access control devices, deploy full nodes on the central server, and connect edge smart boxes between the access control devices and the central server;

[0058] S22: By configuring access control management software parameters, it communicates with UHF RFID readers and light nodes; by configuring blockchain node management software parameters on the central server, it manages all nodes and communicates with edge smart boxes; by configuring data preprocessing and encryption software parameters on edge smart boxes, it preprocesses and encrypts access control data.

[0059] S23: When a user approaches the access control device using an access card or tag, the UHF RFID reader reads the user's identity information and sends the information to the access control management software on the access control device. The access control management software sends the user's identity information to the light node. The light node records the information in its local blockchain ledger and sends the information to the full node on the central server. The full node records the received information in the complete blockchain ledger and participates in the blockchain consensus process. The edge smart box encrypts and preprocesses the user's identity information and then sends the encrypted information to the full node on the central server. The full node records the encrypted information in the blockchain ledger.

[0060] S24: Once a user's identity information is recorded in the blockchain ledger, the access control software controls the opening and closing of the access control device based on the user's permission information. If the user has legitimate permissions, the access control device will unlock the door and allow the user to enter; if the user does not have legitimate permissions, the access control device will keep the door locked and refuse the user entry.

[0061] Specifically, in step S21, an UHF RFID reader and controller are installed on the access control device to ensure that the reader can accurately read the information in the tags and the controller can control the opening and closing of the door lock. Light nodes are deployed on the access control device, and their parameters are configured to enable communication with the full nodes on the central server. Light nodes can be implemented using embedded devices or small servers. An edge smart box is connected between the access control device and the central server, and its parameters are configured to enable data preprocessing and encryption. The edge smart box can be implemented using dedicated hardware or software.

[0062] In step S22, the parameters of the blockchain network are configured, such as the number of nodes, consensus algorithm, and encryption method. This is done using the official documentation and tools of Hyperledger Fabric. The parameters of the access control management software are also configured to enable communication between the access control devices and UHF RFID readers and light nodes. This access control management software can be implemented using an existing access control management system or custom-developed software. The parameters of the blockchain node management software are configured to enable the central server to manage all nodes and communicate with the edge smart boxes. This blockchain node management software can be implemented using official tools of Hyperledger Fabric or third-party software. Finally, the parameters of the data preprocessing and encryption software are configured to enable the edge smart boxes to preprocess and encrypt access control data. This data preprocessing and encryption software is implemented using existing data processing and encryption software.

[0063] Step S24 also includes: the blockchain node management software on the central server can query and analyze the data in the blockchain ledger, enabling administrators to manage and monitor access control. Administrators can use the blockchain node management software to query user access control records, permission information, etc., and can also remotely control and manage access control devices. The edge smart box monitors and analyzes access control data in real time to promptly detect anomalies and take corresponding measures. For example, if the edge smart box detects abnormal access control records or data traffic, it can issue an alarm to notify the administrator for handling.

[0064] Furthermore, the full node records the received information in the complete blockchain ledger and participates in the blockchain consensus process, including verifying the transaction information received by the full node using a practical Byzantine fault-tolerant consensus algorithm and coordinating the consensus process through message passing between nodes; the edge smart box preprocesses the user's identity information, including preprocessing the raw data from the access control device using data compression and deduplication algorithms; the edge smart box encrypts the user's identity information, including encrypting it using Advanced Encryption Standard (AES) encryption algorithms.

[0065] Specifically, the Practical Byzantine Fault-Tolerant (PBT) consensus algorithm is a consensus algorithm applicable to distributed systems. It addresses issues such as node failures, malicious behavior, or erroneous information in distributed systems, offering high security and performance. In access control systems based on UHF RFID technology, the PBT ensures the stable operation of the blockchain network and data consistency. The PBT checks the transaction format, signature validity, and user identity. Only transactions that pass these verifications are further processed and participate in the consensus process. When a full node receives a new transaction, it broadcasts the transaction to other nodes and collects feedback. Other nodes respond to the transaction based on their ledger status and verification results. If more than two-thirds of the nodes agree to the transaction, it is considered valid and added to the blockchain ledger. The PBT ensures secure and reliable communication between nodes, preventing attacks and interference from malicious nodes. Even if some nodes fail or engage in malicious behavior, the algorithm guarantees the normal operation of the entire system and data consistency. In practical applications of access control, various network problems and node failures may be encountered. The PBFT consensus algorithm has a certain degree of fault tolerance, enabling the system to maintain stable operation even when some nodes fail.

[0066] Data compression and deduplication algorithms can reduce the storage space and transmission time of access control data, improving system performance. In access control based on UHF RFID technology, data compression and deduplication algorithms are used to preprocess the raw data from the access control device. The basic principle of data compression algorithms is to compress duplicate data in the access control data, reducing storage space; the basic principle of deduplication algorithms is to remove duplicate data, reducing transmission time. In applications, data compression and deduplication algorithms are optimized and adjusted according to system requirements and performance requirements, such as adjusting parameters like compression ratio, deduplication ratio, and algorithm complexity, to improve efficiency and performance.

[0067] The Advanced Encryption Standard (AES) is a widely used symmetric encryption algorithm with high security and performance. In access control systems based on UHF RFID technology, AES ensures fast and accurate encryption and decryption of access control data. Its basic principle is to divide plaintext data into several 128-bit blocks, encrypt each block using a key to obtain ciphertext data, and then decrypt the ciphertext data by dividing it into 128-bit blocks and decrypting each block using the same key to obtain the plaintext data. In applications, the AES is optimized and adjusted according to system requirements and performance specifications, such as adjusting key length, encryption mode, and padding methods, to improve the algorithm's security and performance.

[0068] Furthermore, the process of training an artificial intelligence model by collecting data from the access control system, and then using the trained model to perform real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events, includes the following steps:

[0069] S31: Based on the data collected from the access control system, preprocess the collected data, including cropping, scaling and grayscale conversion of image data, and segmentation and standardization of time series data.

[0070] S32: Divide the preprocessed data into training set, validation set and test set. Train the artificial intelligence model using the training set and optimize the model using the Adam optimization algorithm during the training process. Validate the model using the validation set and evaluate the trained artificial intelligence model using the test set. Optimize the model based on the evaluation results.

[0071] Specifically, in step S31, various data from the access control system are collected, including but not limited to personnel behavior data (such as passage time, dwell time, movement trajectory, etc.), environmental data (such as temperature, humidity, light intensity, etc.), and equipment status data (such as RFID reader signal strength, access control equipment operating status, etc.). The collected data is preprocessed to improve data quality and usability, including data cleaning (removing noise, outliers, etc.), denoising (using filtering techniques), and normalization (mapping data to a specific range). For image data, cropping, scaling, and grayscale conversion can be performed; for time series data, segmentation and standardization can be performed.

[0072] In step S2, the model is validated using a validation set. Based on the validation results, the model's structure and parameters are adjusted to improve its performance. The training and validation process is repeated until the model reaches the expected performance metrics. The trained AI model is evaluated using a test set, calculating metrics such as accuracy, recall, and F1 score to assess its performance and generalization ability. The model's performance and accuracy are further improved by adjusting its structure, parameters, and algorithm. The trained AI model is then deployed to the access control system for real-time data analysis and detection. When the model detects abnormal behavior or events, it promptly issues warnings to notify the administrator for handling.

[0073] Furthermore, the artificial intelligence model includes the implementation of an artificial intelligence model through the fusion of convolutional neural networks and recurrent neural networks using a distributed architecture; the distributed architecture includes Apache Doris.

[0074] Specifically, the distributed architecture is a distributed SQL data warehouse based on MPP (Massively Parallel Processing) architecture. Optimizations are made based on monitoring results, including adjusting job parallelism, memory allocation, and data partitioning to improve job efficiency and performance.

[0075] Furthermore, the convolutional neural network includes a convolutional neural network model constructed based on the ResNet architecture, convolutional layers, pooling layers, and fully connected layers. The convolutional neural network model is trained using preprocessed image data, and the model parameters are adjusted according to the stochastic gradient descent optimization algorithm. The trained convolutional neural network model is then applied to new access control system image data to extract the spatial feature representation of the image. The output of the convolutional neural network is a vector feature representing the image.

[0076] Specifically, adjusting the model's parameters is to enable the model to better extract the spatial features of image data.

[0077] Furthermore, the recurrent neural network includes a recurrent neural network model constructed based on a long short-term memory network architecture, recurrent layers, and fully connected layers. The output of the convolutional neural network is fused with the time series data features using a weighted summation method to obtain the input vector of the recurrent neural network. The recurrent neural network model is trained using preprocessed time series data and the fused input vector. The model parameters are adjusted according to the backpropagation algorithm. The spatial features of the convolutional neural network output are analyzed and detected. The trained recurrent neural network model is applied to the time series data and convolutional neural network output of the new access control system to predict abnormal behaviors and events. The output of the recurrent neural network is a probability value or a classification result.

[0078] Specifically, the time-series data of the access control system is preprocessed, including segmentation and standardization, to meet the input format of the recurrent neural network (RNN). The output of the convolutional neural network (CNN) is then used as the input of the RNN. The model parameters are adjusted to better extract the temporal features of the time-series data. In the above model tuning and optimization, hyperparameters of the CNN and RNN are adjusted, such as learning rate, batch size, and hidden layer size, to improve model performance and generalization ability. Different fusion methods are explored, such as different concatenation methods and weighted summation settings, to find the optimal fusion method and improve the model's accuracy and reliability. Model ensemble methods are used to combine multiple different CNN and RNN models to improve model performance and stability.

[0079] Furthermore, the data from the access control system is displayed visually on the management platform, and data analysis and optimization management are provided based on the access control mechanism, including the following steps:

[0080] S41: Data storage is performed using a combination of relational and non-relational databases. Relational databases are used to store structured data, while non-relational databases are used to store unstructured data. Data backup and recovery strategies are implemented.

[0081] S42: The visual management platform is presented through responsive design. The analysis results are displayed on the management platform through data visualization technology. The display formats include data charts, map displays and reports. Different interface layouts and display content are displayed according to user needs and permission levels.

[0082] S43: Assign different permissions to different user roles through a role-based access control model; use statistical analysis algorithms to calculate the average time for personnel to enter and exit and traffic indicators during peak hours; verify identity through multi-factor authentication, including password, Bluetooth, facial recognition and token; and highlight abnormal behavior detection results with different colors or icons.

[0083] S44: Analyze personnel behavior patterns through clustering algorithms and predict future personnel flow through prediction algorithms. Based on the analysis results, uncover hidden patterns and trends in the data and generate a report with optimization management suggestions.

[0084] Specifically, in step S41, the relational database is used to store structured data, such as personnel information and access control records; the non-relational database is used to store unstructured data, such as images and videos. The data backup and recovery strategy enables rapid data recovery in the event of system failure or data loss, ensuring the stable operation of the access control system.

[0085] In step S42, responsive design is a web design and development method that aims to enable web pages to automatically adjust their layout and display effects according to different device screen sizes and resolutions to provide a good user experience. By adopting responsive design, the visual management platform can adapt to different device screen sizes, such as computers, tablets, and mobile phones. It features a clean and clear interface layout, avoids information overload, and uses intuitive charts, graphs, and colors to display data.

[0086] In step S43, different permissions are assigned to different user roles. For example, administrators have the highest permissions and can perform operations such as system settings and data management; ordinary users can only view their own access control records and basic information. This allows for flexible management of user permissions, ensuring data security and confidentiality. Users with different roles can only access the functions and data they are authorized to, avoiding the risk of accidental operation and data leakage. Multi-factor authentication increases system security and prevents unauthorized user intrusion.

[0087] In step S44, data mining and machine learning algorithms are used to analyze personnel behavior patterns, providing in-depth analysis of access control data and offering various visualization chart types, such as bar charts, line charts, pie charts, or heatmaps, to meet different data display needs. Based on the data analysis results, an optimization management suggestion report is automatically generated, which may include problem analysis, solutions, implementation steps, etc. A feedback mechanism is established to allow users to evaluate and provide feedback on the optimization suggestions, so as to continuously improve the quality of the suggestions.

[0088] An access control system based on UHF RFID technology includes a multi-antenna array module for communication connection, a blockchain module, an artificial intelligence algorithm module, and a visualization management module, wherein:

[0089] The multi-antenna array module is used to set up multiple antenna arrays in a distributed layout according to the size, shape and personnel flow of the access control area;

[0090] The blockchain module is used to deploy nodes in different locations through a distributed node architecture based on the Hyperledger Fabric blockchain platform;

[0091] The artificial intelligence algorithm module is used to train an artificial intelligence model by collecting data from the access control system. The trained artificial intelligence model performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events.

[0092] The visualization management module is used to display various data in the access control system on the management platform in a visual manner, and provides data analysis and optimization management based on the permission management mechanism.

[0093] The above embodiments are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. An access control method based on ultra-high frequency RFID technology, characterized in that, Includes the following steps: S1: Based on the size, shape, and personnel flow of the access control area, a multi-antenna array is set up through a distributed layout; S2: Based on the Hyperledger Fabric blockchain platform, nodes are deployed in different locations through a distributed node architecture; S3: Train an artificial intelligence model by collecting data from the access control system. The trained artificial intelligence model performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events. S4: Displays all data from the access control system in a visual manner on the management platform, and provides data analysis and optimization management based on the access control mechanism; The method of setting up a multi-antenna array through a distributed layout based on the size, shape, and personnel flow of the access control area includes the following steps: S11: Determine the antenna for UHF RFID technology based on the antenna's gain, directivity, and frequency response. Based on the size, shape, and personnel flow of the access control area, set up a multi-antenna array in a distributed layout and connect the reader to the antenna via wireless connection. S12: Preprocess the signals received by each antenna, measure and record the signal strength of the preprocessed signals, obtain the weight of each antenna through a signal weighting algorithm, and sum the signals by weighting. S13: The operation of independent signal reception, signal comparison and selection and signal fusion is performed by spatial diversity algorithm. The fused signal obtained by spatial diversity algorithm and the weighted signal obtained by signal weighting algorithm are finally fused by decision fusion method. The fused signals are further processed and analyzed to extract tag information and make access control decisions.

2. The access control method based on UHF RFID technology according to claim 1, characterized in that, The method described above, based on the Hyperledger Fabric blockchain platform, involves deploying nodes in different locations using a distributed node architecture, and includes the following steps: S21: Based on the Hyperledger Fabric blockchain platform, deploy light nodes on access control devices, deploy full nodes on the central server, and connect edge smart boxes between the access control devices and the central server; S22: By configuring access control management software parameters, it communicates with UHF RFID readers and light nodes; by configuring blockchain node management software parameters on the central server, it manages all nodes and communicates with edge smart boxes; by configuring data preprocessing and encryption software parameters on edge smart boxes, it preprocesses and encrypts access control data. S23: When a user approaches the access control device using an access card or tag, the UHF RFID reader reads the user's identity information and sends the information to the access control management software on the access control device. The access control management software sends the user's identity information to the light node. The light node records the information in its local blockchain ledger and sends the information to the full node on the central server. The full node records the received information in the complete blockchain ledger and participates in the blockchain consensus process. The edge smart box encrypts and preprocesses the user's identity information and then sends the encrypted information to the full node on the central server. The full node records the encrypted information in the blockchain ledger. S24: Once a user's identity information is recorded in the blockchain ledger, the access control software controls the opening and closing of the access control device based on the user's permission information. If the user has legitimate permissions, the access control device will unlock the door and allow the user to enter; if the user does not have legitimate permissions, the access control device will keep the door locked and refuse the user entry.

3. The access control method based on ultra-high frequency RFID technology according to claim 2, characterized in that, The full node records the received information in the complete blockchain ledger and participates in the blockchain consensus process, including using a practical Byzantine fault-tolerant consensus algorithm to verify the transaction information received by the full node and coordinating the consensus process through message passing between nodes; the edge smart box preprocesses the user's identity information, including preprocessing the raw data from the access control device through data compression and deduplication algorithms; The edge smart box encrypts the user's identity information, including through encryption algorithms using Advanced Encryption Standard (AES).

4. The access control method based on UHF RFID technology according to claim 1, characterized in that, The process involves training an artificial intelligence model by collecting data from the access control system. The trained AI model then performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events. This includes the following steps: S31: Based on the data collected from the access control system, preprocess the collected data, including cropping, scaling and grayscale conversion of image data, and segmentation and standardization of time series data. S32: Divide the preprocessed data into training set, validation set and test set. Train the artificial intelligence model using the training set and optimize the model using the Adam optimization algorithm during the training process. Validate the model using the validation set and evaluate the trained artificial intelligence model using the test set. Optimize the model based on the evaluation results.

5. The access control method based on UHF RFID technology according to claim 4, characterized in that, The artificial intelligence model includes a distributed architecture that combines convolutional neural networks and recurrent neural networks to achieve the artificial intelligence model; the distributed architecture includes Apache Doris.

6. The access control method based on UHF RFID technology according to claim 5, characterized in that, The convolutional neural network includes a convolutional neural network model built according to the ResNet architecture, including convolutional layers, pooling layers, and fully connected layers. The convolutional neural network model is trained using preprocessed image data, and the model parameters are adjusted according to the stochastic gradient descent optimization algorithm. The trained convolutional neural network model is then applied to new access control system image data to extract the spatial feature representation of the image. The output of the convolutional neural network is a vector feature representing the image.

7. The access control method based on UHF RFID technology according to claim 6, characterized in that, The recurrent neural network (RNN) includes a model constructed based on a long short-term memory (LSTM) network architecture, recurrent layers, and fully connected layers. The output of a convolutional neural network (CNN) is fused with time-series data features using a weighted summation method to obtain the input vector of the RNN. The RNN model is trained using preprocessed time-series data and the fused input vector. Model parameters are adjusted using a backpropagation algorithm. The spatial features of the CNN output are analyzed and detected. The trained RNN model is then applied to new access control systems using time-series data and the CNN output to predict abnormal behaviors and events. The output of the RNN is a probability value or a classification result.

8. The access control method based on UHF RFID technology according to claim 1, characterized in that, The process of visually displaying various data from the access control system on a management platform, and providing data analysis and optimization management based on the access control mechanism, includes the following steps: S41: Data storage is performed using a combination of relational and non-relational databases. Relational databases are used to store structured data, while non-relational databases are used to store unstructured data. Data backup and recovery strategies are implemented. S42: The visual management platform is presented through responsive design. The analysis results are displayed on the management platform through data visualization technology. The display formats include data charts, map displays and reports. Different interface layouts and display content are displayed according to user needs and permission levels. S43: Assign different permissions to different user roles through a role-based access control model; use statistical analysis algorithms to calculate the average time for personnel to enter and exit and traffic indicators during peak hours; verify identity through multi-factor authentication, including password, Bluetooth, facial recognition and token; and highlight abnormal behavior detection results with different colors or icons. S44: Analyze personnel behavior patterns through clustering algorithms and predict future personnel flow through prediction algorithms. Based on the analysis results, uncover hidden patterns and trends in the data and generate a report with optimization management suggestions.

9. An access control system based on ultra-high frequency RFID technology, used to execute the access control method based on ultra-high frequency RFID technology as described in any one of claims 1-8, characterized in that, It includes a multi-antenna array module for communication connectivity, a blockchain module, an artificial intelligence algorithm module, and a visualization management module, among which: The multi-antenna array module is used to set up a multi-antenna array through a distributed layout according to the size, shape, and personnel flow of the access control area. The multi-antenna array module is used to perform the following steps: Based on the antenna's gain, directivity, and frequency response, the antenna for UHF RFID technology is determined. According to the size, shape, and personnel flow of the access control area, a multi-antenna array is set up in a distributed layout, and the reader is connected to the antenna via a wireless connection. The signals received by each antenna are preprocessed, the signal strength of the preprocessed signals is measured and recorded, the weight of each antenna is obtained through a signal weighting algorithm, and the signals are weighted and summed. The spatial diversity algorithm is used to perform independent signal reception, signal comparison and selection, and signal fusion. The fused signal obtained by the spatial diversity algorithm and the weighted signal obtained by the signal weighting algorithm are finally fused using the decision fusion method. The fused signals are further processed and analyzed to extract tag information and make access control decisions. The blockchain module is used to deploy nodes in different locations using a distributed node architecture based on the Hyperledger Fabric blockchain platform; The artificial intelligence algorithm module is used to train an artificial intelligence model by collecting data from the access control system. The trained artificial intelligence model performs real-time analysis and detection of the data in the access control system to identify abnormal behaviors and events. The visualization management module is used to display various data in the access control system on the management platform in a visual manner, and provides data analysis and optimization management based on the permission management mechanism.

Images