Monitoring and early warning system and method based on intelligent door lock

Abstract

The invention relates to the technical field of Internet of Things, and particularly discloses a monitoring and early warning system and method based on an intelligent door lock, the system is in communication connection with a house renting platform and obtains renting information from the house renting platform, and the system comprises a management platform used for issuing an identity authentication request according to the renting information, acquiring identity authentication information, comparing the identity authentication information with data in the information verification system, and issuing a virtual key to the corresponding intelligent door lock after identity authentication is passed; the intelligent door locks are mounted on doors of the rental houses, have communication capability and are used for receiving the virtual keys and uploading unlocking / locking records to the management platform and the data center; the data center is in communication connection with the multiple intelligent door locks and the management platform and used for obtaining information uploaded by the intelligent door locks, analyzing the information uploaded by the intelligent door locks according to the lease information corresponding to the intelligent door locks, recognizing abnormal information and sending early warning signals to the management platform and the corresponding intelligent door locks.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a monitoring and early warning system and method based on a smart door lock. Background Art

[0002] With the rapid development of Internet of Things technology and the popularization of smart home concepts, smart door locks, as an important part of smart homes, are gradually replacing traditional mechanical locks and becoming the first choice for modern family security protection. Smart door locks not only have the anti-theft functions of traditional locks, but also incorporate modern technological elements such as face recognition, fingerprint recognition, password input, remote control, etc., which greatly improves the convenience and safety of users. However, with the continuous expansion of the smart door lock market, some new security challenges and regulatory issues have gradually emerged.

[0003] First, the popularity of smart door locks has made the means of illegal intrusion more covert and complex. Traditional violent intrusion methods such as picking locks and doors are gradually replaced by new methods such as technical cracking and illegal key copying. Some criminals use technical means to crack the encryption system of smart door locks, or illegally enter homes by copying legal key information, posing a serious threat to users' property safety and personal privacy.

[0004] Secondly, although the remote control function of smart door locks is convenient for users, it also brings new security risks. Some smart door lock systems lack effective identity authentication mechanisms, allowing unauthorized third parties to remotely control door locks and conduct illegal intrusions. In addition, if some smart door lock systems do not adopt sufficient security measures when transmitting data with cloud servers, user information may be stolen or tampered with.

[0005] Furthermore, with the development of the Internet, the online housing market has grown rapidly, providing tenants with more convenient and diverse accommodation options, and the application of smart door locks in the rental market has become more and more widespread. Although most rental platforms require tenants to verify their identities, there are many loopholes in actual operations, such as submission of false information, manual review omissions, etc., which result in individuals who have not been legally verified to easily obtain admission. Due to the lack of effective supervision mechanisms and technical means, not only will the landlord face the risk of property loss, but some lawless elements may also use the convenience of smart door locks to conduct illegal operations, posing challenges to social order and public safety. The lack of an effective real-time monitoring mechanism makes it difficult for regulators to promptly detect and stop such illegal activities.

[0006] In response to the above problems, the market urgently needs a real-time monitoring and early warning system to conduct all-round monitoring and early warning of smart door locks of rental houses. Summary of the invention

[0007] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art, thereby providing a monitoring and early warning system and method based on smart door locks, which can analyze the information uploaded by the smart door locks according to the rental information corresponding to the smart door locks, identify abnormal information through machine learning algorithms, and promptly discover and warn of potential illegal intrusions and illegal business activities, so as to achieve all-round monitoring and early warning of smart door locks.

[0008] In order to achieve the above object, the technical solution adopted by the present invention is as follows: This specification provides a monitoring and early warning system based on smart door locks, which is connected to a house rental platform and obtains rental information from the house rental platform. The system includes multiple smart door locks, a management platform, and a data center, wherein: The management platform is used to issue an identity authentication request based on the rental information, obtain the identity authentication information and compare it with the data in the information verification system to ensure the authenticity of the information, and issue a virtual key to the corresponding smart door lock after the identity authentication is passed; Smart door locks are installed on the doors of each rental house and have communication capabilities. They are used to receive virtual keys and upload the opening / closing records to the management platform and data center. The opening / closing records include the opening / closing time and the duration of each opening. The data center is connected to multiple smart door locks and a management platform for communication, and is used to obtain information uploaded by each smart door lock, analyze the information uploaded by the smart door lock according to the rental information corresponding to the smart door lock, identify abnormal information and send early warning signals to the management platform and the corresponding smart door lock.

[0009] Furthermore, the system further comprises a plurality of user terminals, and each user terminal is communicatively connected to at least one smart door lock; The user terminal includes an identity authentication module, which is used to perform identity authentication according to an identity authentication request issued by a management platform to control the smart door lock; The user terminal also includes an information receiving module for receiving an early warning signal sent by a data center.

[0010] Furthermore, when the user terminal performs identity authentication, the distance between the user terminal and the smart door lock is less than a preset distance.

[0011] Furthermore, the identity authentication module uses OCR text recognition technology and liveness authentication technology to perform identity authentication.

[0012] Furthermore, the user end also includes a smart door lock control module, which is used to send an unlocking instruction to the smart door lock to achieve remote unlocking.

[0013] Furthermore, the smart door lock is also used to receive the unlocking instruction sent by the user terminal, and upload the unlocking instruction to the management platform and the data center.

[0014] Furthermore, the data center includes an information acquisition module and an information analysis module; An information acquisition module is used to acquire information uploaded by each smart door lock and the leasing information corresponding to each smart door lock, wherein the leasing information includes but is not limited to the leasing house information, the number of leasing personnel, the leasing personnel information, and the leasing start and end time; The information analysis module uses an analysis model built and trained by a machine learning algorithm to analyze the acquired information, identify abnormal information and send early warning signals to the management platform and the corresponding smart door lock. The abnormal information includes but is not limited to unauthorized unlocking, frequent unlocking, unlocking without an order, and unlocking for a long time.

[0015] Furthermore, a time interval for optimizing and updating the analysis model is preset, and the PPO reinforcement learning algorithm is used to optimize and update the analysis model using the information acquired within the time interval and historical information.

[0016] Furthermore, the management platform is also connected to the management system of the relevant management department for communication. The management platform verifies the abnormal information and sends the rental information corresponding to the smart door locks with serious violations after verification to the management system of the relevant management department.

[0017] This specification also provides a monitoring and early warning method based on a smart door lock. According to the above-mentioned monitoring and early warning system based on a smart door lock, it includes: An identity authentication request is issued based on the rental information, and the identity authentication information is obtained and compared with the data in the information verification system to ensure the authenticity of the information. After the identity authentication is passed, a virtual key is issued to the corresponding smart door lock; The smart door lock uploads the lock opening / closing record, which includes the lock opening / closing time and the duration of each opening; Obtain the information uploaded by each smart door lock, analyze the information uploaded by the smart door lock according to the rental information corresponding to the smart door lock, identify abnormal information and send early warning signals.

[0018] Due to the adoption of the above technical solution, the present invention has the following beneficial effects: 1. Obtain rental information from the rental platform and then conduct identity authentication, and compare the identity authentication information with the data in the information verification system to confirm the accuracy of the information, effectively preventing individuals who have not been legally verified from obtaining check-in rights, thereby reducing the landlord's risk of property loss and the possibility of criminals engaging in illegal activities.

[0019] 2. The system analyzes the information uploaded by the smart door lock based on the rental information. The system can automatically detect and identify abnormal information, identify potential risks of illegal operations, and send early warning signals to the management platform, smart door locks, and user terminals, effectively reducing the pressure of manual supervision and improving the efficiency and accuracy of supervision.

[0020] 3. The management platform is also connected to the management systems of relevant management departments. After checking the abnormal information, any serious violations will be directly fed back to the relevant management departments, so that the relevant management departments can discover the violations in time and stop them. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments will be briefly introduced below. Obviously, the drawings in the following description only relate to some embodiments of the present invention, but are not intended to limit the present invention.

[0022] Figure 1 It is a structural diagram of the monitoring and early warning system based on the smart door lock; Figure 2 It is a flow chart of the monitoring and early warning method based on smart door locks. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. The components of the embodiments of the present invention described and shown in the accompanying drawings can be arranged and designed in various configurations. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0025] Unless otherwise defined, the technical terms or scientific terms used in this patent document shall have the usual meanings understood by persons with ordinary skills in the field to which the invention belongs. The words "first", "second" and similar words used in the patent specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one", "one" or "the" do not indicate a quantity limitation, but indicate the existence of at least one. Words such as "include" or "comprise" mean that the elements or objects appearing before "include" or "comprise" include the elements or objects listed after "include" or "comprise" and their equivalents, and do not exclude other elements or objects. "Center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0026] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the features of the following embodiments can be combined with each other.

[0028] Embodiment 1: See also Figure 1 This embodiment provides a monitoring and early warning system based on smart door locks, which is connected to a housing rental platform and obtains rental information from the housing rental platform. The system includes multiple smart door locks, multiple user terminals, a management platform, and a data center, wherein: The management platform is used to issue an identity authentication request based on the rental information, obtain the identity authentication information and compare it with the data in the information verification system to ensure the authenticity of the information, and issue a virtual key to the corresponding smart door lock after the identity authentication is passed.

[0029] The user terminal includes a user terminal, and each user terminal is communicatively connected to at least one smart door lock. The user terminal includes an identity authentication module, and the identity authentication module is used to perform identity authentication according to the identity authentication request issued by the management platform to control the smart door lock; the user terminal also includes an information receiving module, which is used to receive the early warning signal sent by the data center; the user terminal also includes a smart door lock control module, which is used to issue an unlocking instruction to the smart door lock to realize remote unlocking.

[0030] Smart door locks are installed on the doors of each rental house and have communication capabilities, and are used to receive virtual keys, receive unlocking instructions issued by the user end, and upload unlocking / locking records and unlocking instructions to the management platform and data center. The unlocking / locking records include the unlocking / locking time and the duration of each unlocking. The data center is connected to multiple smart door locks and a management platform for communication, and is used to obtain information uploaded by each smart door lock, analyze the information uploaded by the smart door lock according to the rental information corresponding to the smart door lock, identify abnormal information and send early warning signals to the management platform and the corresponding smart door lock.

[0031] The management platform can synchronize all rental information of the housing rental platform and issue identity authentication requests based on the rental information. Users perform identity authentication through the identity authentication module on the user side. During the identity authentication, the distance between the user side and the smart door lock should be less than the preset distance.

[0032] Specifically, through high-precision distance sensing methods, the spatial position of the user end is compared with the real-time position of the smart door lock, and identity authentication can only be triggered when the user is physically close to the target door lock. This method not only improves the security of identity authentication and avoids unauthorized operations at a distance, but also can collect 3D point cloud data between the user end and the door lock. Using this data, the depth and shape information in the point cloud can be combined with machine learning algorithms to accurately classify the type and structure of goods approaching the door lock, and quickly identify the appearance characteristics and classification attributes of the goods, thereby further enhancing the security and accuracy of the authentication process.

[0033] The identity authentication module uses OCR text recognition technology and liveness authentication technology for identity authentication.

[0034] OCR text recognition technology: OCR (Optical Character Recognition) text recognition technology is a technology that can convert text in an image into editable and searchable digital text. During the identity authentication process, OCR technology can automatically recognize and enter text information in identity documents uploaded by users (such as ID cards, passports, etc.), thereby improving the efficiency and accuracy of identity authentication. Through OCR technology, the identity information submitted by users can be quickly read and verified, reducing the errors and tediousness of manual input.

[0035] Liveness authentication technology: Liveness authentication technology is a technology used to ensure the authenticity and liveness of the identity authentication process. It usually involves real-time detection and analysis of the user's biometrics to verify whether the user is indeed operating in person. During the identity authentication process, by requiring the user to perform liveness authentication (such as blinking, smiling, nodding, etc.) to ensure that it is the user who is authenticating and that the identity information is authentic and valid, it can further improve security and credibility.

[0036] After identity authentication on the user side, the management platform will obtain the identity authentication information and compare the identity authentication information with the data in the information verification system to ensure the authenticity of the information, and then issue a virtual key so that the user can directly unlock the door through the information obtained during identity authentication, such as fingerprints, portrait information, etc.

[0037] It should be noted that this information verification system is developed and provided by a third-party professional organization. It is an existing and mature information verification tool. The system has undergone strict security and legality reviews to ensure that it operates in compliance with the legal framework. Users can purchase the system through legal and formal channels and obtain its legal right to use it. Once the right to use is obtained, users can use the system to query the identity information of relevant personnel and compare it with existing information to verify the authenticity and accuracy of the information. This process is both efficient and convenient, providing strong support for users' information verification work.

[0038] After the key is issued, the user end will receive the key issuance information. The user can also set the unlocking method on the user end according to the unlocking method of the door lock and personal usage habits.

[0039] The data center includes an information acquisition module, a feature extraction module, and an information analysis module; An information acquisition module is used to acquire information uploaded by each smart door lock and the leasing information corresponding to each smart door lock, wherein the leasing information includes but is not limited to the leasing house information, the number of leasing personnel, the leasing personnel information, and the leasing start and end time; The feature extraction module pre-processes the acquired data, such as cleaning, deduplication, formatting, etc., and extracts key features from the pre-processed information, including the number of door lock openings per day, the time distribution of door lock openings per day, the average duration of door lock openings, and the way door locks are opened, and the extracted key features are used as inputs to the analysis model; The information analysis module analyzes the information using an analysis model built and trained by a machine learning algorithm, identifies abnormal information and sends early warning signals to the management platform and the corresponding smart door lock. The abnormal information includes but is not limited to unauthorized unlocking, frequent unlocking, unlocking without an order, and unlocking for a long time.

[0040] It should be noted that the analysis model is built based on machine learning, using a time-series convolutional neural network combined with an attention mechanism to identify abnormal behavior in the time-series data of smart door locks. The main input features of the analysis model include unlocking time, unlocking duration, unlocking method, unlocking frequency, and matching with rental information. These features are pre-processed to form a multi-modal input tensor for analysis model training and anomaly detection.

[0041] Specifically, the input data is first normalized to map the feature values ​​to the range of [0, 1] to avoid interference from dimensional differences. Subsequently, the time series features are constructed, and the unlocking records are organized into input tensors in chronological order using the sliding window technique.

[0042] Specifically, the analysis model includes an input layer, a temporal convolution layer, an attention mechanism layer, and an output layer.

[0043] The time series convolution layer is used to capture abnormal patterns in time series data, with a convolution kernel size of 3 and a step size of 1. The attention mechanism enhances the model's focus on key features, such as unlocking at night or unlocking at high frequencies. Finally, the output layer generates an anomaly score, which is normalized to the interval [0,1].

[0044] The analysis model uses a binary cross entropy loss function, the optimizer uses Adam, and the learning rate is set to 0.001. The training data includes labeled normal and abnormal behavior data, and the abnormal behavior data can be generated through simulation or historical records. The model also regularly applies the PPO (Proximal Policy Optimization) reinforcement learning algorithm to optimize parameters using the latest user behavior data.

[0045] The analysis model processes the input data and calculates the anomaly score to identify potential abnormal behaviors. The expression is: ; in, For the abnormality score, represents the total number of features, represents the index of the feature, Indicates Feature weight value, Represents eigenvalue The nonlinear mapping value of If abnormal score , it is unauthorized unlocking, indicating that the identity information does not match; If abnormal score , it is frequent unlocking, which means the number of unlocking times exceeds 5 times within 1 hour; If abnormal score , it means the door has not been locked for a long time, which means the door has not been locked for more than 5 minutes; It should also be noted that the analysis model has the ability to be dynamically updated. Through the feedback of the actual processing results of the management platform, the training data set is continuously expanded and the model performance is optimized. The reinforcement learning algorithm is used to adjust the model parameters to adapt to the diverse and changing user behavior scenarios. It can effectively identify abnormal behaviors such as unauthorized unlocking and frequent unlocking, and improve the security and intelligence level of the smart door lock system.

[0046] The training of the analysis model includes the following steps: Select a suitable machine learning algorithm and build an initial model based on historical data; train the model using methods such as cross-validation to evaluate the performance and stability of the initial model; adjust algorithm parameters such as learning rate, number of iterations, etc. based on the training results to improve the accuracy of the model.

[0047] It should be noted that historical data comes from the operation log records during the actual operation of the smart door lock, including unlocking record data, rental information data, abnormal behavior data and user feedback data: Among them, unlocking record data: the timestamp of the unlocking event, the unlocking method (such as fingerprint, password, virtual key), the unlocking duration, etc., covering a variety of scenarios (such as short-term rental, long-term rental, unauthorized attempts, etc.); rental information data: rental order information obtained from the house rental platform, including the start and end time of the rental, the identity information of the tenant, the rental house number, etc.; abnormal behavior data: abnormal unlocking behavior manually marked by historical events, such as unlocking outside the rental period, frequent unlocking, unlocking without orders, etc.; user-side feedback data: including records of abnormal operations actively fed back by tenants and manual review results after early warning.

[0048] Specifically, when constructing the initial model, based on the historical data of the smart door lock, including unlocking record data, rental information data, abnormal behavior data and user feedback data, the initial model expression is defined as follows: Let the input feature vector The expression is: ; =1,2,…,n; Among them, each Indicates the normalized key feature values, such as unlocking time, unlocking method, lease start and end time, etc. Specifically, unlocking record data: unlocking time, unlocking method, duration, etc.; rental information data: lease start and end time, leased house number, etc.; abnormal behavior data: such as unlocking outside the lease period, frequent unlocking, etc.; user-side feedback data: abnormal operation records and manual review results.

[0049] Furthermore, for the input feature vector Each key feature value in Remove duplicate and invalid data, use interpolation method to handle missing values, and use Z-Score method to eliminate outliers; Extract features such as unlocking time, method, duration, and integrate multimodal data through Bayesian fusion; The recursive feature elimination (RFE) method is used to retain the most relevant features and form a comprehensive feature set; Initial model output Indicates whether it is an abnormal behavior, which is defined as a binary classification problem, and the expression is: ; in, represents the decision boundary function calculated by the kernel function, which is used to measure the similarity between input features. are model parameters, is the input feature vector, which represents the feature set extracted from historical data; if the support vector machine (SVM) is taken as an example, the expression of the initial model is: ; in, represents the number of support vectors, represents the Lagrange multiplier, represents the label of the training sample, Indicates the position offset of the classification boundary; It should be noted that through Functions can divide function values ​​into two categories as follows: like , represents the positive class; like , represents the negative class; Taking the temporal convolutional neural network (TCN) as an example, the expression of the initial model is: ; in, represents an activation function (such as Sigmoid), represents the output layer weight matrix, represents the output layer bias vector, Represents a time series feature extraction module that includes multi-layer convolution operations; the initial model training adopts the following steps: divide the historical data into a training set (70%), a validation set (15%), and a test set (15%), ensuring that the data segmentation follows the time order in the time series scenario; use K-fold cross validation (such as 5 folds) to evaluate the performance of the model, and record the accuracy, recall, F1 score, and AUC indicators of each fold; For classification problems, the objective function is the cross entropy loss, expressed as: ; in, is the loss function, which indicates the degree of mismatch between the model prediction and the true label. is the averaging factor used to normalize the sum of squared errors of all samples, represents the total number of samples in the training set, Indicates The true label of the sample, The index variable representing the sample, The predicted samples belong to the positive class ( ) probability; For regression problems, the objective function is the mean square error (MSE), which is expressed as: ;in, represents the objective function (loss function), that is, the number of data points in the training set, Indicates The true value of the data point, Indicates The predicted value of the data point, is the square error, which is used to amplify larger errors while eliminating the mutual cancellation of positive and negative errors; It should be noted that the model is evaluated on the test set, a confusion matrix is ​​generated, the AUC value and F1 score are calculated, L2 regularization is used, the amount of data is increased or an integrated learning method is introduced, and a grid search or Bayesian optimization method is used to search for the best hyperparameter combination.

[0050] The analysis model is used to analyze the unlocking method, unlocking time, unlocking frequency and other information uploaded by the smart door lock to determine whether there is illegal operation in the unreserved room. For example, there is no tenant in the room, but multiple unlocking operations are detected; or there is a rental order, but the management platform issues a virtual key without the tenant's identity verification.

[0051] The data center automatically screens out suspected cases of illegal operations. The characteristics of illegal operations include but are not limited to: serious discrepancies between unlocking records and order information, frequent abnormal unlocking behaviors, and the system cannot automatically determine their legality. These cases need to be further checked and confirmed by the manual review team to ensure the accuracy and fairness of the judgment. The manual review will take into account various factors, including but not limited to the tenant's behavior patterns and historical records, to determine whether there is real illegal operation.

[0052] After receiving the early warning sent by the data center, the management platform will have a manual team verify the abnormal information and generate processing results for the abnormal information. The processing results include confirmed cases of illegal operations, cases of false alarms, etc. The leasing information corresponding to the smart door locks that have serious violations after verification will be sent to the management system of the relevant management department through API interfaces, etc., in order to deal with the illegal operations.

[0053] At certain time intervals (such as one week), the PPO reinforcement learning algorithm is used to optimize and update the analysis model based on the information uploaded by the smart door locks obtained within the time interval, the rental information corresponding to the smart door locks, the identified abnormal information, the processing results of the abnormal information and the historical information.

[0054] Specifically, at a certain time interval (such as one week), based on the information uploaded by the smart door locks obtained within the time interval, including lock opening and closing records, abnormal event types and frequencies, rental information (such as rental personnel information, rental period, etc.), and abnormal event processing results, combined with historical data, an optimized data set is constructed. During the optimization process, the data is normalized and organized into a multi-dimensional tensor of time series as the input of the reinforcement learning environment.

[0055] Specifically, the normalized expression is: ; in, represents the original eigenvalue, represents the maximum value of the feature, represents the minimum value of the feature, represents the normalized eigenvalue; Specifically, the expression for organizing data into a three-dimensional tensor by time interval is: ; in, represents the qth time step, the uth event, and the Features, represents the feature values ​​extracted from the data; Through the PPO (Proximal Policy Optimization) algorithm, the agent selects actions based on the current state. The actions include adjusting the parameters of the analysis model (such as anomaly recognition threshold, feature weight, etc.) to maximize the cumulative reward. The design of the reward function revolves around the core goals of improving the accuracy of anomaly detection, reducing false alarm rate, and improving the timeliness of warning. The PPO algorithm uses a truncated probability ratio for policy updates to ensure the stability of policy optimization. During the optimization process, the performance indicators of the analysis model (such as accuracy, F1 score) are evaluated in real time through multiple rounds of training, and the learning rate and exploration range are adjusted dynamically. After the optimization is completed, the analysis model with the best performance is applied to subsequent data analysis and anomaly detection tasks to achieve continuous optimization and efficient application of the model.

[0056] The data center will collect abnormal information processing results and feedback from multiple parties such as the manual review team and relevant management departments. The analysis model will regularly review and adjust algorithm parameters and improve detection strategies based on this information and historical information to improve the accuracy of identifying illegal business operations and the efficiency of detection, forming a closed-loop management mechanism. This optimization process helps the system to continuously adapt to new security threats and market demands, and provide more efficient and accurate monitoring and early warning services.

[0057] The above system obtains rental information from the rental platform and then performs identity authentication. The identity authentication information is compared with the data in the information verification system to confirm the accuracy of the information, effectively preventing individuals who have not been legally verified from obtaining check-in rights, thereby reducing the landlord's risk of property loss and the possibility of criminals engaging in illegal activities.

[0058] Suppose a long-term rental apartment platform discovers the following situation through its monitoring and early warning system: There is no booking record for a room on the rental platform, but the smart door lock device shows that the room was opened frequently within a certain period of time.

[0059] By comparing the door lock logs and tenant identity information, the system found that these opening records did not match the identity information of multiple different tenants.

[0060] The manual review team further investigated and found that the room was actually used for illegal short-term rental operations and had not gone through the formal booking process of the long-term rental apartment platform.

[0061] Based on the above situation, the system can determine that the room has illegal business operations and promptly inform relevant departments through API interfaces for investigation and punishment. This example shows how the system can effectively identify and warn of illegal business operations through real-time monitoring and data analysis.

[0062] The system analyzes the information uploaded by the smart door locks based on the rental information. The system can automatically detect and identify abnormal information, identify potential risks of illegal operations, and send early warning signals to the management platform, smart door locks, and user terminals, effectively reducing the pressure of manual supervision and improving the efficiency and accuracy of supervision.

[0063] The system is also connected to the management systems of relevant management departments. After checking the abnormal information, any serious violations will be directly fed back to the relevant management departments, so that the relevant management departments can discover the violations in time and stop them.

[0064] Furthermore, the information transmission between the system and each module adopts a custom protocol to ensure the security of data transmission. During the data collection and processing, the system strictly abides by relevant laws and regulations to ensure the security of user privacy and desensitizes sensitive information, such as replacing ID card numbers, mobile phone numbers, etc. with unique identifiers.

[0065] Furthermore, the system also has expandable interfaces so that more types of smart door locks or security devices can be integrated in the future to ensure the compatibility of subsequent new smart door locks with existing systems.

[0066] It should be emphasized that the process of obtaining user identity information, biometric information and other related information involved in this application is carried out under the premise of fully respecting the user's wishes and privacy. We always adhere to the principles of legality, legitimacy and necessity to ensure that all information is obtained with the user's explicit consent and authorization. When obtaining this information, we will clearly and explicitly inform the user of the purpose, scope and method of use of the information, and ensure the security and confidentiality of the information to fully protect the user's legitimate rights and interests and privacy security.

[0067] Embodiment 2: See also Figure 2 This embodiment provides a monitoring and early warning method based on a smart door lock. According to the monitoring and early warning system based on a smart door lock described in Embodiment 1, it includes: An identity authentication request is issued based on the rental information, and the identity authentication information is obtained and compared with the data in the information verification system to ensure the authenticity of the information. After the identity authentication is passed, a virtual key is issued to the corresponding smart door lock; The smart door lock uploads the lock opening / closing record and unlocking instruction, wherein the lock opening / closing record includes the lock opening / closing time and the duration of each opening; The information uploaded by each smart door lock is obtained, and the information uploaded by the smart door lock is analyzed according to the rental information corresponding to the smart door lock, abnormal information is identified and an early warning signal is sent. The abnormal information includes but is not limited to unauthorized unlocking, frequent unlocking, unlocking without an order, and unlocking for a long time.

[0068] The user authenticates through the user terminal, and the distance between the user terminal and the smart door lock should be within the preset range during the authentication. The user terminal is an easy-to-use mobile application that allows users to complete operations such as filling in personal information, liveness authentication, smart door lock binding, and smart door lock unlocking settings. If necessary, such as when workers need to come to the house for maintenance during work hours, users can remotely open the smart door lock through the user terminal.

[0069] It should be noted that the above information is obtained with the user's consent and is used for legal purposes.

[0070] The system analyzes the information uploaded by the smart door lock to determine whether there is any abnormal information or illegal operation. For example, there is no tenant in the room, but multiple unlocking operations are detected; or there is a rental order, but the management platform issues a virtual key without the tenant's identity verification.

[0071] The system will automatically screen out suspected illegal business cases. The characteristics of illegal business cases include but are not limited to: serious discrepancies between unlocking records and rental information, frequent abnormal unlocking behaviors, and the system cannot automatically determine their legality. These cases need to be further checked and confirmed by the manual review team to ensure the accuracy and fairness of the judgment. The manual inspection will comprehensively consider various factors, including but not limited to the tenant's behavior patterns, historical records, etc., to determine whether there is real illegal business behavior, and send the rental information corresponding to the smart door locks with serious violations after verification to the management system of the relevant management department.

[0072] It should also be noted that the acquisition of user identity, biometric information and other information mentioned in this application has been approved by the user.

[0073] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A monitoring and early warning system based on smart door locks, which is connected to a housing rental platform and obtains rental information from the housing rental platform, characterized in that: The system includes multiple smart door locks, management platforms, and data centers, including: The management platform is used to issue an identity authentication request based on the rental information, obtain the identity authentication information and compare it with the data in the information verification system to ensure the authenticity of the information, and issue a virtual key to the corresponding smart door lock after the identity authentication is passed; Smart door locks are installed on the doors of each rental house and have communication capabilities. They are used to receive virtual keys and upload the opening / closing records to the management platform and data center. The opening / closing records include the opening / closing time and the duration of each opening. The data center is connected to multiple smart door locks and a management platform for communication, and is used to obtain information uploaded by each smart door lock, analyze the information uploaded by the smart door lock according to the rental information corresponding to the smart door lock, identify abnormal information and send early warning signals to the management platform and the corresponding smart door lock.

2. According to claim 1, a monitoring and early warning system based on smart door locks is characterized in that: The system further comprises a plurality of user terminals, and each user terminal is communicatively connected with at least one smart door lock; The user terminal includes an identity authentication module, which is used to perform identity authentication according to an identity authentication request issued by a management platform to control the smart door lock; The user terminal also includes an information receiving module for receiving an early warning signal sent by a data center.

3. According to claim 2, a monitoring and early warning system based on smart door locks is characterized in that: When the user terminal performs identity authentication, the distance between the user terminal and the smart door lock is less than a preset distance.

4. A monitoring and early warning system based on smart door locks according to claim 2 or 3, characterized in that: The identity authentication module uses OCR text recognition technology and liveness authentication technology to perform identity authentication.

5. According to claim 2, a monitoring and early warning system based on smart door locks is characterized in that: The user end also includes a smart door lock control module, which is used to send an unlocking instruction to the smart door lock to achieve remote unlocking.

6. A monitoring and early warning system based on smart door locks according to claim 5, characterized in that: The smart door lock is also used to receive the unlocking instruction sent by the user end, and upload the unlocking instruction to the management platform and the data center.

7. A monitoring and early warning system based on smart door locks according to claim 6, characterized in that: The data center includes an information acquisition module and an information analysis module; An information acquisition module is used to acquire information uploaded by each smart door lock and the leasing information corresponding to each smart door lock, wherein the leasing information includes but is not limited to the leasing house information, the number of leasing personnel, the leasing personnel information, and the leasing start and end time; The information analysis module uses an analysis model built and trained by a machine learning algorithm to analyze the acquired information, identify abnormal information and send early warning signals to the management platform and the corresponding smart door lock. The abnormal information includes but is not limited to unauthorized unlocking, frequent unlocking, unlocking without an order, and unlocking for a long time.

8. The monitoring and early warning system based on smart door lock according to claim 7 is characterized in that: The time interval for optimizing and updating the analysis model is preset, and the PPO reinforcement learning algorithm is used to optimize and update the analysis model using the information obtained within the time interval and historical information.

9. A monitoring and early warning system based on smart door locks according to claim 1 or 7, characterized in that: The management platform is also connected to the management system of the relevant management department for communication. The management platform verifies the abnormal information and sends the rental information corresponding to the smart door locks with serious violations after verification to the management system of the relevant management department.

10. A monitoring and early warning method based on a smart door lock, according to a monitoring and early warning system based on a smart door lock according to any one of claims 1 to 9, characterized in that: include: An identity authentication request is issued based on the rental information, and the identity authentication information is obtained and compared with the data in the information verification system to ensure the authenticity of the information. After the identity authentication is passed, a virtual key is issued to the corresponding smart door lock; The smart door lock uploads the lock opening / closing record, which includes the lock opening / closing time and the duration of each opening; Obtain the information uploaded by each smart door lock, analyze the information uploaded by the smart door lock according to the rental information corresponding to the smart door lock, identify abnormal information and send early warning signals.

Images