An iot cell visitor management system

Abstract

The application provides a visitor management system for an Internet of Things community, comprising: a visitor terminal for visitor identity registration and access application; a proprietor terminal for the proprietor to receive access requests and perform remote authorization; and an access control execution unit arranged at a community entrance for collecting biological feature information of the visitor and verifying access rights; the application introduces a dynamic calculation formula of time deviation and credit score, realizes fine control of the access rights of the visitor, avoids security risks caused by static authorization, establishes a dynamic generation mechanism of a visitor 'black list' and 'white list', encourages the visitor to behave in a standard manner, uses homomorphic encryption technology to ensure the safety of biological feature data in the transmission and processing process, and uses an RSSI weighted centroid algorithm to realize effective monitoring of the trajectory of the visitor without increasing expensive positioning hardware.

Description

Technical Field

[0001] This invention relates to the fields of Internet of Things (IoT) and smart security technology, and in particular to an IoT-based community visitor management system. Background Technology

[0002] With the continuous advancement of smart city and smart community construction, community security management systems are becoming increasingly intelligent. Traditional visitor management methods mainly rely on manual registration or simple access control passwords, which suffer from problems such as low registration efficiency, difficulty in information traceability, and susceptibility to identity theft.

[0003] While existing IoT visitor systems have enabled remote reservations and QR code access, they still have the following major drawbacks: Existing systems typically employ a binary logic of "pass / deny". Once the owner authorizes, the visitor has full access rights for a fixed period of time, and cannot dynamically adjust permissions based on the visitor's lateness, early departure, or the real-time security situation of the community (such as when an emergency occurs in the community).

[0004] The lack of a credit accumulation mechanism for visitors' historical behavior means that the system cannot issue risk warnings or restrict permissions for visitors with a history of violations (such as littering, vandalism, or overstaying).

[0005] A large amount of visitors' biometric data (such as faces and fingerprints) is stored directly on cloud servers. Once the servers are attacked, privacy is easily leaked. To address this, an IoT-based community visitor management system is proposed. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide an Internet of Things (IoT) community visitor management system to solve or alleviate the technical problems existing in the prior art, and at least provide a beneficial alternative.

[0007] The technical solution of this invention is implemented as follows: an Internet of Things (IoT) community visitor management system, comprising: Visitor terminal, used for visitor registration and access requests; Owner terminal, used by owners to receive access requests and perform remote authorization; Access control units are installed at the entrances and exits of the community to collect visitors' biometric information and verify their access rights. An edge computing gateway is communicatively connected to the access control execution unit to receive collected information and perform local preprocessing and real-time permission determination. The cloud management platform communicates with the edge computing gateway and is used to store visitor data and issue security policies. The edge computing gateway has a built-in dynamic credibility assessment module. This module calculates the dynamic access credibility value of the visitor based on the visitor's appointment time deviation, historical credit score and real-time environmental risk coefficient, and uses this value to control the actions of the access control execution unit.

[0008] In some embodiments, the dynamic credibility assessment module calculates a dynamic access credibility value. The formula is: in, A score is assigned based on the visitor's identity. This represents the absolute deviation between the visitor's actual arrival time and the scheduled time. The maximum allowable time deviation threshold preset for the system. The visitor's historical visit credit score. The current risk factor of the community environment. , , The preset weighting coefficients, and .

[0009] In some embodiments, the historical access credit coefficient Dynamically updated using the following formula: in, The updated credit score. The credit rating before the update. For learning rate factor, Rate the actual behavior during this visit. This serves as the baseline score for expected behavior.

[0010] In some embodiments, the system further includes a distributed trajectory tracking unit, which comprises multiple Internet of Things beacon nodes located in the public area of ​​the community; Once a visitor enters the community through the access control unit, the visitor terminal or issued temporary electronic tag interacts with the beacon node, and the edge computing gateway calculates the visitor's location coordinates in real time. and compare the real-time location with the pre-planned path If the deviation exceeds a preset threshold, an anomaly warning will be triggered.

[0011] In some embodiments, the position coordinates The calculation employs a weighted centroid positioning algorithm based on Received Signal Strength Indication (RSSI), and the positioning coordinate calculation formula is as follows: in, The number of beacon nodes that detect visitor signals, For the first The coordinates of each beacon node. For the first The weights of each beacon node, and , For the first The signal strength received by each beacon node.

[0012] In some embodiments, the cloud management platform further includes a privacy protection module for desensitizing visitor biometric information; The desensitization process employs a homomorphic encryption algorithm, resulting in encrypted ciphertext. The calculation formula is: in, For generators, This is the original plaintext information. It is a random number. The key modulus; Edge computing gateways can match and verify encrypted data without decryption.

[0013] In some embodiments, the access control execution unit further includes a multimodal perception module for simultaneously collecting visitor facial images, voiceprint features, and body temperature data. The edge computing gateway performs feature fusion on the collected multidimensional data to construct a visitor feature vector. and compare it with the authorized feature vector issued by the cloud. Calculate Euclidean distance ,when When the identities are matched, among them This is the similarity threshold.

[0014] A visitor management method applied to the above system includes the following steps: S1. Visitors initiate access requests through visitor terminals, and owner terminals receive and confirm authorization, generating temporary authorization codes. S2. Visitors arrive at the access control unit and submit their identity information and biometric data; S3. The edge computing gateway calls the dynamic trustworthiness assessment module to calculate based on the formula. ; S4. If The access control unit opens the passage and activates the distributed trajectory tracking unit; S5. If a visitor leaves within the authorized time, the system will update. The gain is positive; if a visitor stays for too long or deviates from the path, the system reduces the gain. They then called the property management center.

[0015] In some embodiments, the system introduces a dynamic access confidence value. The concept is used to verify whether "your current passage is reasonable," and the formula is defined as follows: In this formula: Time penalty mechanism: The term is a linear decay factor; If the visitor is late An increase in this factor leads to a decrease in the factor itself. This means that even if a visitor is authorized, their credibility will decrease if they are too late, and they may even be refused or required to reconfirm, thus increasing the seriousness of management. Credit accumulation mechanism: This represents historical credit, and the system records a visitor's past behavior (such as whether they left on time or whether they violated any rules). If a visitor has violated rules multiple times in the past, their credit history will be recorded. It will become lower, leading to If the security level is lowered, the system can accordingly increase the security level for the individual or restrict their access to certain areas. Environmental risk perception: The cloud management platform issues alerts based on the current status of the community (such as whether there have been recent thefts, whether it is under epidemic control, etc.). When the environmental risk is high, The value decreases (or is used as a negative indicator), thereby dynamically tightening access control permissions; In addition, the system employs trajectory tracking technology based on RSSI weighted centroid localization, using the formula: in This formula uses signal strength to convert into weights. The stronger the signal of the beacon node, the greater its coordinate weight. Therefore, it can achieve accurate and low-cost positioning of visitors within the community without expensive high-precision positioning equipment, ensuring that visitor activities are within the authorized range. In terms of privacy protection, the system adopts homomorphic encryption technology, which enables the edge gateway to directly compare identity features in an encrypted state without decrypting the original biometric data, thus fundamentally eliminating the risk of biometric leakage.

[0016] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions: This invention achieves refined control over visitor access permissions by introducing a dynamic calculation formula for time deviation and credit score, avoiding the security risks associated with static authorization. It also establishes a dynamic generation mechanism for visitor "blacklists" and "whitelists" to encourage visitors to behave in a standardized manner. Furthermore, it employs homomorphic encryption technology to ensure the security of biometric data during transmission and processing. By utilizing the RSSI weighted centroid algorithm, it achieves effective monitoring of visitor trajectories without adding expensive positioning hardware.

[0017] The above overview is for illustrative purposes only and is not intended to be limiting in any way. Detailed Implementation

[0018] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention.

[0019] It is important to note that terms such as "first," "second," "symmetric," "array," "set in," and "set with" are used only to distinguish between descriptive and positional descriptions and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified with terms such as "first" or "symmetric" may explicitly or implicitly include one or more of that feature; similarly, when the quantity of certain features is not limited by words such as "two" or "three," it should be noted that such features also explicitly or implicitly include one or more features.

[0020] In this invention, unless otherwise explicitly specified and limited, terms such as “installation,” “connection,” and “fixation” should be interpreted broadly; for example, they can be fixed connections, detachable connections, or integral moldings; they can be mechanical connections, direct connections, welding, or indirect connections through an intermediate medium; they can be internal connections between two components or the interaction between two components.

[0021] This invention provides an IoT-based community visitor management system, comprising: Visitor terminal, used for visitor registration and access requests; Owner terminal, used by owners to receive access requests and perform remote authorization; Access control units are installed at the entrances and exits of the community to collect visitors' biometric information and verify their access rights. The edge computing gateway communicates with the access control execution unit to receive collected information and perform local preprocessing and real-time permission determination. The cloud management platform communicates and connects with the edge computing gateway to store visitor data and distribute security policies. The edge computing gateway has a built-in dynamic credibility assessment module. This module calculates the dynamic access credibility value of visitors based on visitor appointment time deviation, historical credit score and real-time environmental risk coefficient, and uses this value to control the actions of the access control execution unit.

[0022] In this embodiment, specifically, the dynamic credibility assessment module calculates the dynamic access credibility value. The formula is: in, A score is assigned based on the visitor's identity. This represents the absolute deviation between the visitor's actual arrival time and the scheduled time. The maximum allowable time deviation threshold preset for the system. The visitor's historical visit credit score. The current risk factor of the community environment. , , The preset weighting coefficients, and .

[0023] In this embodiment, specifically, the dynamic trust assessment module is embedded software and programmed into the high-performance processor (such as ARM Cortex-A series or FPGA) of the edge computing gateway. This module serves as the "brain" of the access control system, and its hardware interface connections include: Input interface: Connects to the GPIO interface of the access control controller to obtain the trigger signal of visitor card swiping / facial recognition in real time; connects to the cloud API through the network interface to obtain environmental risk data.

[0024] Storage unit: Connects to a local SQLite or Redis lightweight database to temporarily store visitors' historical credit data and blacklists, ensuring offline operation when the network is down.

[0025] The module's internal operating logic is divided into four levels: Data Acquisition Layer: Real-time monitoring of visitor IDs and appointment timestamps uploaded by the access control terminal. Current system time .

[0026] Parameter initialization layer: Reads weight coefficients from configuration file , , (Default can be set to) , , ), and the maximum permissible time deviation (e.g., 30 minutes).

[0027] Core Computation Layer: Executes core formulas Perform the calculation.

[0028] Decision output layer: The calculation results are... With the system's preset passage threshold (e.g., 0.75) is compared, and the output is "allow", "restrict access (only for specific areas)" or "reject and alarm" command.

[0029] The module maintains a "Visitor Credit Database Table" with the following fields: Visitor_ID, Last_Visit_Time, Violation_Count, R_hist.

[0030] When a visitor requests access, the module queries the database to obtain... .

[0031] If the visitor is a first-time visitor and has not made an appointment It will be reduced (e.g., from 1.0 to 0.6), and Assign an initial value of 0.5.

[0032] Calculation results A log record is generated in real time and uploaded to the cloud platform for big data analysis.

[0033] In this embodiment, specifically, the historical visit credit score... Dynamically updated using the following formula: in, The updated credit score. The credit rating before the update. For learning rate factor, Rate the actual behavior during this visit. This serves as the baseline score for expected behavior.

[0034] In this embodiment, specifically, the system also includes a distributed trajectory tracking unit, which includes multiple IoT beacon nodes set up in the public area of ​​the community; Once a visitor enters the community through the access control unit, the visitor terminal or issued temporary electronic tag interacts with the beacon node, and the edge computing gateway calculates the visitor's location coordinates in real time. and compare the real-time location with the pre-planned path If the deviation exceeds a preset threshold, an anomaly warning will be triggered.

[0035] In this embodiment, specifically, the position coordinates The calculation employs a weighted centroid positioning algorithm based on Received Signal Strength Indication (RSSI), and the positioning coordinate calculation formula is as follows: in, The number of beacon nodes that detect visitor signals, For the first The coordinates of each beacon node. For the first The weights of each beacon node, and , For the first The signal strength received by each beacon node.

[0036] In this embodiment, specifically, the cloud management platform also includes a privacy protection module for desensitizing the biometric information of visitors; The desensitization process uses a homomorphic encryption algorithm, and the encrypted ciphertext... The calculation formula is: in, For generators, This is the original plaintext information. It is a random number. The key modulus; Edge computing gateways can match and verify encrypted data without decryption.

[0037] In this embodiment, the access control execution unit further includes a multimodal perception module, used to simultaneously collect visitor facial images, voiceprint features, and body temperature data. The edge computing gateway performs feature fusion on the collected multidimensional data to construct a visitor feature vector. and compare it with the authorized feature vector issued by the cloud. Calculate Euclidean distance ,when When the identities are matched, among them This is the similarity threshold.

[0038] In this embodiment, the multimodal perception module is specifically deployed in the physical terminal device at the entrance of the community, aiming to improve the accuracy of identity recognition and anti-counterfeiting capabilities.

[0039] 1. Hardware Components Visible light camera: captures images of visitors' faces.

[0040] Microphone array: Collects visitor voice commands (such as "unlock", "visit xxx").

[0041] Infrared thermal imager: assists in imaging at night or in low light conditions, and detects body temperature.

[0042] ID card reader: Reads the encrypted information within the ID card chip.

[0043] 2. Work Process S21, Multi-dimensional Data Synchronous Acquisition When a visitor stands in front of the access control system, the PIR human body sensor triggers the system to start. The camera captures a facial image, the microphone array simultaneously records a 1-2 second audio clip, and the thermal imager detects the body surface temperature. At this point, the system obtains three types of raw data: image matrix... Audio waveforms Temperature values ; S22, Feature Extraction and Vectorization Visual features: Extracting facial feature vectors using lightweight convolutional neural networks (such as MobileNet). .

[0044] Voiceprint features: Extracting voiceprint feature vectors using Mel-frequency cepstral coefficients (MFCC). .

[0045] Physiological characteristics: body temperature If the temperature exceeds 37.3℃, the abnormal flag will be triggered directly.

[0046] S23, Feature Fusion The system concatenates and fuses visual features and voiceprint features to construct a comprehensive feature vector: This fused vector It contains both visual and auditory biological information, making it extremely difficult to be forged by single-modal forgery methods (such as photos or audio recordings).

[0047] S24: Matching Decision The edge gateway downloads the authorization feature template reserved by the visitor during the appointment from the cloud platform. The system calculates the Euclidean distance between the two. :

[0048] like (Preset threshold), if determined to be "the living person", output. .

[0049] like However, the visual distance is small while the voiceprint distance is large, leading to the judgment of "suspected recording attack" and output. And called the police.

[0050] 3. Cooperative defense mechanism The multimodal perception module works in conjunction with the dynamic reliability assessment module. For example, if the thermal imager detects an abnormal body temperature, although it does not affect identity recognition, it will force an adjustment to the environmental risk coefficient. By setting it to 0, visitor access is blocked through formula logic, thus achieving the intelligent integration of "identity authentication" and "health management".

[0051] In this embodiment, specifically, an access control unit is deployed at the entrance of the community, including a high-definition camera, an ID card reader, and an edge computing gateway. IoT beacon nodes (based on ZigBee or BLE5.0 protocol) are deployed on the main roads of the community and at the entrances of building units. The cloud management platform is deployed on a remote server.

[0052] According to the formula Define parameters and application scenarios: (Basic identity matching score): Application: When visitors use facial recognition or swipe their ID cards at access control terminals, the system calculates biometric similarity.

[0053] Values: Normalized to the [0,1] interval; if the face similarity is >95%, then... ; If the similarity is between 80% and 95%, ; If it is below 80%, it will be judged directly. Passage is refused.

[0054] Time penalty factor : Application: Used to solve the problem of visitors arriving late or too early.

[0055] calculate: .

[0056] If the visitor arrives on time The factor is 1, so no points are deducted.

[0057] like If a visitor is 15 minutes late, then , factor is The score for this item will be halved.

[0058] If a visitor is more than 30 minutes late, the factor becomes negative. The system will then use logic to set the number to 0 and display the message "Reservation has expired".

[0059] (Historical visit credit rating): Application: It embodies the system's "creative" learning mechanism.

[0060] Value: The initial value is 1.0. If the visitor's previous visit involved violations such as timeout or entering unauthorized areas, the system will adjust the value accordingly. The formula updates this value to be less than 1.0 (e.g., 0.7). Conversely, if the visitor behaves well, it can remain at 1.0 or gain a small advantage.

[0061] (Environmental risk coefficient): Application: Combined with the overall security situation of the community.

[0062] Value: Normally If the cloud sends a command indicating that there have been recent thefts in the community or that the community is under lockdown due to the pandemic, Automatically downgraded to 0.5 or lower, resulting in the final This significantly reduces access control permissions, thereby tightening access control.

[0063] Comprehensive judgment example: A visitor arrives on time (time factor = 1) and their identity is confirmed. Good credit () Community safety ).

[0064] calculate: .

[0065] result: Passage is permitted.

[0066] If the same visitor is 20 minutes late ( (Time factor = 0.33), and the community is under epidemic control ( ).

[0067] calculate: .

[0068] result: Refuse passage or require manual verification The system substitutes each parameter into the formula for calculation. ,like Below the system's set passage threshold The system will then notify the visitor that "the appointment has expired and needs to be reconfirmed." The visitor will need to reauthorize through the owner's terminal or contact the property management for manual processing.

[0069] Once inside, visitors carry a mobile phone with a dedicated app installed or a temporary electronic wristband, and the beacon node collects signals in real time.

[0070] Assume the coordinates of the three beacon nodes are as follows: , , The weights of the received RSSI intensity after conversion are as follows: , , .

[0071] According to the formula: System determines coordinates Has the visitor deviated from the preset route to the target building? If the visitor enters an unauthorized area (such as a green area or a non-target building), the system will automatically lower their priority level. value:

[0072] Here (Actual behavior score was lower than expected score), resulting in The decline will affect its future access rights.

[0073] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An Internet of Things (IoT) community visitor management system, characterized in that, include: Visitor terminal, used for visitor registration and access requests; Owner terminal, used by owners to receive access requests and perform remote authorization; Access control units are installed at the entrances and exits of the community to collect visitors' biometric information and verify their access rights. An edge computing gateway is communicatively connected to the access control execution unit to receive collected information and perform local preprocessing and real-time permission determination. The cloud management platform communicates with the edge computing gateway and is used to store visitor data and issue security policies. The edge computing gateway has a built-in dynamic credibility assessment module. This module calculates the dynamic access credibility value of the visitor based on the visitor's appointment time deviation, historical credit score and real-time environmental risk coefficient, and uses this value to control the actions of the access control execution unit.

2. The Internet of Things (IoT) community visitor management system according to claim 1, characterized in that, The dynamic credibility assessment module calculates the dynamic pass credibility value. The formula is: in, A score is assigned based on the visitor's identity. This represents the absolute deviation between the visitor's actual arrival time and the scheduled time. The maximum allowable time deviation threshold preset for the system. The visitor's historical visit credit score. The current risk factor of the community environment. , , The preset weighting coefficients, and .

3. The IoT-based community visitor management system according to claim 2, characterized in that, The historical visit credit rating Dynamically updated using the following formula: in, The updated credit score. The credit rating before the update. For learning rate factor, Rate the actual behavior during this visit. This serves as the baseline score for expected behavior.

4. The Internet of Things (IoT) community visitor management system according to claim 1, characterized in that, The system also includes a distributed trajectory tracking unit, which comprises multiple Internet of Things beacon nodes set up in the public area of ​​the community; Once a visitor enters the community through the access control unit, the visitor terminal or issued temporary electronic tag interacts with the beacon node, and the edge computing gateway calculates the visitor's location coordinates in real time. and compare the real-time location with the pre-planned path If the deviation exceeds a preset threshold, an anomaly warning will be triggered.

5. The Internet of Things (IoT) community visitor management system according to claim 4, characterized in that, The position coordinates The calculation employs a weighted centroid positioning algorithm based on Received Signal Strength Indication (RSSI), and the positioning coordinate calculation formula is as follows: in, The number of beacon nodes that detect visitor signals. For the first The coordinates of each beacon node. For the first The weights of each beacon node, and , For the first The signal strength received by each beacon node.

6. The Internet of Things (IoT) community visitor management system according to claim 1, characterized in that, The cloud management platform also includes a privacy protection module for desensitizing visitors' biometric information; The desensitization process employs a homomorphic encryption algorithm, resulting in encrypted ciphertext. The calculation formula is: in, For generators, This is the original plaintext information. It is a random number. The key modulus; Edge computing gateways can match and verify encrypted data without decryption.

7. The Internet of Things (IoT) community visitor management system according to claim 1, characterized in that, The access control execution unit also includes a multimodal perception module, used to simultaneously collect visitor facial images, voiceprint features, and body temperature data. The edge computing gateway performs feature fusion on the collected multidimensional data to construct a visitor feature vector. and compare it with the authorized feature vector issued by the cloud. Calculate Euclidean distance ,when When the identities are matched, among them This is the similarity threshold.

8. A visitor management method applied to the system according to any one of claims 1-7, characterized in that, Includes the following steps: S1. Visitors initiate access requests through visitor terminals, and owner terminals receive and confirm authorization, generating temporary authorization codes. S2. Visitors arrive at the access control unit and submit their identity information and biometric data; S3. The edge computing gateway calls the dynamic trustworthiness assessment module to calculate based on the formula. ; S4. If The access control unit opens the passage and activates the distributed trajectory tracking unit; S5. If a visitor leaves within the authorized time, the system will update. The gain is positive; if a visitor stays for too long or deviates from the path, the system reduces the gain. They then called the property management center.

Images