Intelligent door lock password peep prevention method and system, electronic device and storage medium

Abstract

The invention relates to an intelligent door lock password peep-proof method and system, an electronic device and a storage medium, input behavior information is generated by acquiring an input password character string, and the input behavior information is added to an information base; checking whether the length of the password character string is within a preset length range or not; extracting a core password in the password character string within a preset length range; matching the extracted core password with a preset effective password; extracting input behavior characteristics in the input behavior information, analyzing the input behavior characteristics by utilizing a preset behavior analysis algorithm, and judging whether the input behavior is abnormal or not; the information base is inquired, after it is determined that at least password error information and abnormal behavior information exist, the password verification strategy is updated through the preset security strategy model, the new password is generated according to the updated password verification strategy, and an administrator is notified through encrypted communication, so that the problems that in the related technology, the password is prone to being peeped and the cracking difficulty is low are solved; the difficulty of peeping and cracking the password can be increased.

Description

Technical Field

[0001] The present application relates to the field of door lock technology, and in particular to a method, system, electronic device and storage medium for preventing password peeping of smart door locks. Background Art

[0002] With the popularity of smart homes, smart door locks, as the first line of defense for home security, have received widespread attention for their safety and convenience. Traditional door locks rely on physical keys to unlock, while smart door locks provide unlocking functions through passwords, fingerprints, facial recognition, mobile phone applications, and other methods, greatly improving the convenience of use. However, these convenient unlocking methods also bring new security challenges.

[0003] Password input security issues: In public places or areas covered by surveillance equipment, traditional password input methods are easily peeped at. Someone with ulterior motives may infer the password combination by observing the user's password input action, thereby threatening the security of the door lock.

[0004] Limitations of biometric technology: Although biometric technologies such as fingerprint and facial recognition provide a convenient way to unlock without having to remember passwords, these technologies may be affected by environmental factors, such as wet fingers or face occlusion, resulting in reduced recognition accuracy. In addition, the storage and transmission of biometric data also poses the risk of being intercepted and abused.

[0005] Vulnerability of static passwords: Many smart door locks use static passwords as a means of unlocking. Once the password is cracked, the security of the door lock will be threatened. Moreover, users tend to use passwords that are easy to remember, which are often less secure and easy to crack.

[0006] Networking risks of smart door locks: In order to achieve remote control and monitoring, smart door locks may need to be connected to the Internet. This increases the risk of door locks being hacked, and hackers may gain control of the door locks through network attacks.

[0007] Security of user habits: Users may develop certain habits when entering passwords, such as always using the same finger sequence to enter passwords. These habits may be observed and exploited by interested parties.

[0008] Access control in emergencies: In an emergency, such as a fire or medical emergency, quick access to a residence is required. Smart door locks need to be able to allow emergency services to enter quickly while maintaining security.

[0009] Therefore, it is of great practical significance to develop a smart door lock password anti-peeping method and system that can increase the difficulty of password being peeped and cracked. Summary of the invention

[0010] The embodiments of the present application provide a method, system, electronic device and storage medium for preventing a smart door lock password from being peeped at, so as to at least solve the problem that passwords in the related art are easily peeped at and difficult to crack.

[0011] In a first aspect, an embodiment of the present application provides a method for preventing a smart door lock from being peeped by a password, which includes: obtaining an input password string to generate input behavior information, and adding the input behavior information to an information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature; checking whether the length of the password string is within a preset length range, and if it is not within the preset length range, prompting re-entry; extracting the core password from the password string within the preset length range; matching the extracted core password with a preset valid password, and if the match fails, prompting a password error, and generating password error information and adding it to the information library; extracting the input behavior features in the input behavior information, and analyzing the input behavior using a preset behavior analysis algorithm Features, determine whether the input behavior is abnormal. If the input behavior is determined to be abnormal, notify the administrator through the preset communication channel, and generate abnormal behavior information to add to the information base, wherein the preset behavior analysis algorithm is the K-means clustering algorithm or the DBSCAN clustering algorithm; query the information base, and after determining that at least there is password error information and abnormal behavior information, use the preset security policy model to update the password verification policy, generate a new password according to the updated password verification policy, and notify the administrator through encrypted communication, wherein the preset security policy model is a neural network trained based on the long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least the corresponding information base, and the preset data set at least includes a historical information base composed of the information base.

[0012] In some of the embodiments, after matching the extracted core password with the preset valid password, if the match fails, a password error prompt is given, and password error information is generated and added to the database, it also includes: obtaining the input secondary verification information and adding it to the information library, wherein the secondary verification information includes at least one verification feature; extracting the verification feature of the secondary verification information, matching the verification feature with the preset valid verification feature, if the match fails, a password error prompt is given, and password error information is generated and added to the information library, wherein the verification feature includes at least one of password verification data, face verification data, fingerprint verification data, palm vein verification data, dynamic verification code data, and voiceprint verification data.

[0013] In some embodiments, the input behavior feature includes at least one of a password input speed and an input mode.

[0014] In some of the embodiments, a preset behavior analysis algorithm analyzes input behavior characteristics, including: recording the time interval between each key press by the user; predicting the time interval range of normal input using a long short-term memory network (LSTM) model; and comparing the actual recorded time interval with the predicted time interval range to identify whether the input behavior is abnormal.

[0015] In some of the embodiments, a preset behavior analysis algorithm analyzes input behavior characteristics, including: analyzing the user's commonly used input patterns, wherein the input pattern at least includes the order of commonly used fingers; using a hidden Markov model (HMM) to identify inconsistent input patterns; and comparing the identified input pattern with the user's historical input pattern to identify whether the input behavior is abnormal.

[0016] In some embodiments, the password verification policy includes at least one of the policies of changing the number of password verification times, changing the password verification type, changing redundant passwords, changing valid passwords, and changing the effective length of passwords.

[0017] In a second aspect, an embodiment of the present application provides a smart door lock password anti-peeping system, including: a password acquisition module, used to acquire an input password string to generate input behavior information, and the input behavior information is added to an information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature; a password length verification module, coupled with the password acquisition module, used to check whether the length of the password string is within a preset length range, and if it is not within the preset length range, prompting re-entry; a password extraction module, coupled with the password length verification module, used to extract the core password from the password string within the preset length range; a valid password verification module, coupled with the password extraction module, used to match the extracted core password with a preset valid password, and if the match fails, prompting a password error, and generating password error information and adding it to the information library; an input behavior verification module, coupled with the password acquisition module, used to extract input behavior information The input behavior features in the input are analyzed by a preset behavior analysis algorithm to determine whether the input behavior is abnormal. If the input behavior is determined to be abnormal, the administrator is notified through a preset communication channel, and abnormal behavior information is generated and added to the information base, wherein the preset behavior analysis algorithm is a K-means clustering algorithm or a DBSCAN clustering algorithm; a password verification policy update module is coupled with the valid password verification module and the input behavior verification module, and is used to query the information base, and after determining that at least there is password error information and abnormal behavior information, the password verification policy is updated by using a preset security policy model, a new password is generated according to the updated password verification policy, and the administrator is notified through encrypted communication, wherein the preset security policy model is a neural network trained based on a long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least the corresponding information base, and the preset data set at least includes a historical information base composed of an information base.

[0018] In some embodiments, it also includes: a secondary verification module, coupled with the valid password verification module, for obtaining input secondary verification information and adding it to an information library, wherein the secondary verification information includes at least one verification feature; extracting the verification feature of the secondary verification information, and matching the verification feature with a preset valid verification feature. If the match fails, a password error is prompted, and a password error message is generated and added to the information library, wherein the verification feature includes at least one of password verification data, face verification data, fingerprint verification data, palm vein verification data, dynamic verification code data, and voiceprint verification data.

[0019] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps of the smart door lock password anti-peeping method as described in the first aspect above.

[0020] In a third aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the smart door lock password anti-peeping method as described in the first aspect above are implemented.

[0021] Compared with the related art, the smart door lock password anti-peeping method, system, electronic device and storage medium provided by the embodiments of the present application adopt the method of obtaining an input password string to generate input behavior information, and the input behavior information is added to the information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature; check whether the length of the password string is within a preset length range, and if it is not within the preset length range, prompt to re-enter; extract the core password in the password string within the preset length range; match the extracted core password with the preset valid password, if the match fails, prompt that the password is wrong, and generate a password error message and add it to the information library; extract the input behavior features in the input behavior information, use the preset behavior analysis algorithm to analyze the input behavior features, and judge whether the input behavior is abnormal, such as If the input behavior is judged to be abnormal, the administrator is notified through the preset communication channel, and abnormal behavior information is generated and added to the information library, wherein the preset behavior analysis algorithm is the K-means clustering algorithm or the DBSCAN clustering algorithm; the information library is queried, and after determining that at least password error information and abnormal behavior information exist, the password verification policy is updated using the preset security policy model, a new password is generated according to the updated password verification policy, and the administrator is notified through encrypted communication, wherein the preset security policy model is a neural network trained based on the long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least the corresponding information library, and the preset data set at least includes a historical information library composed of the information library, which solves the problem of easy peeping and low cracking difficulty of passwords in related technologies, and can increase the difficulty of peeping and cracking passwords.

[0022] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 It is a hardware structure block diagram of a terminal of the smart door lock password anti-peeping method of an embodiment of the present application;

[0025] Figure 2is a flow chart of a method for preventing a smart door lock from being peeped according to an embodiment of the present application;

[0026] Figure 3 It is a structural block diagram of the smart door lock password anti-peeping system according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0028] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0029] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The "multiple links" involved in this application refer to links greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects, and do not represent a specific ordering of objects.

[0030] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 1 is a hardware structure block diagram of a terminal of the smart door lock password anti-peeping method of the embodiment of the present application. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the smart door lock password anti-peeping method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0032] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by the communication provider of the terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0033] This embodiment provides a method for preventing a smart door lock password from being peeped running on the above terminal. Figure 2 Flow chart of the method for preventing peeping of smart door lock password according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0034] Step S201, obtaining an input password string to generate input behavior information, and adding the input behavior information to an information base, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature.

[0035] In this embodiment, the core password of the present invention generally refers to the main password set by the user, which may contain a combination of letters, numbers, and special characters to ensure the complexity of the password and make it difficult to guess. These features may include, but are not limited to: key speed, the input speed of each character when the user enters the password. Key interval, the pause time between the user entering different characters. Error rate, the frequency and type of errors made by the user when entering the password. Mouse movement, if the password input is completed by clicking the virtual keyboard, the movement path and speed of the mouse are also a feature. Pressure pattern, on a device that supports pressure sensing, the amount of pressure applied by the user when pressing the key is also a feature. The information library is used to store the user's input behavior information and can be used for: user verification, verifying the user's identity by comparing the real-time input behavior with the behavior characteristics stored in the information library. Anomaly detection, if the input behavior is detected to be significantly different from the user's historical behavior, it may indicate that the account has been stolen. User behavior analysis, analyzing the user's behavior pattern to improve the user experience or enhance security. To implement this system, it is necessary to: high-precision sensors for capturing the user's input behavior. Data analysis algorithms for extracting behavior characteristics from the collected data. Machine learning models for learning and identifying user behavior patterns. Privacy and security, when processing user input behavior information, it is necessary to ensure compliance with relevant data protection regulations and protect user privacy. This technology can be applied to a variety of scenarios, including but not limited to: banking and financial services, for identity authentication of online transactions; enterprise security, for security verification of employees accessing internal systems; personal devices, for unlocking mobile phones, computers and other devices. This technical solution obtains the password string entered by the user and generates input behavior information, where the password string contains at least one core password, and the input behavior information includes at least one input behavior feature, such as input speed, key strength and time interval, etc. This information is added to the information library, so that the smart door lock system not only pays attention to the password content itself, but also pays attention to the user's password input behavior pattern, thereby effectively preventing the password from being peeped, real-time monitoring and analysis of user behavior patterns to identify abnormal behavior, adaptively adjusting security policies to improve security protection efficiency, reduce false alarms, and make accurate security decisions based on actual data to deal with diverse security threats, thereby playing a vital role in the entire technical solution, enhancing password security, improving user experience, and providing an innovative security protection mechanism for smart door lock systems.

[0036] Step S202, checking whether the length of the password string is within a preset length range, if not, prompting to re-enter the password.

[0037] In this embodiment, the system of the present invention checks whether the input length is within the allowed range (such as a minimum of 6 digits and a maximum of 12 digits). If not, the user is prompted to re-enter. As a key step in the smart door lock system, this technical solution ensures that the length of the password string meets the security standards. By checking whether the length of the password entered by the user is within the preset range, it not only improves the complexity and difficulty of guessing the password, thereby enhancing the security of the door lock, but also requires the consistency of the password length. It helps the system to more accurately identify and verify the behavior pattern of the user input. When it is detected that the password length does not meet the requirements, the user is prompted to re-enter, further ensuring that only password attempts that meet the established security policies can be accepted, effectively preventing the security risks that may be caused by too short passwords, and also avoiding unnecessary interference in the analysis of user input behavior caused by too long passwords, ensuring the system's accurate monitoring and timely response to user behavior, thereby playing a fundamental security role in the entire technical solution.

[0038] Step S203, extracting the core password from the password character string within a preset length range; matching the extracted core password with the preset valid password, if the match fails, prompting a password error, and generating password error information to be added to the information library.

[0039] In this embodiment, the technical solution of the present invention plays a core role in the smart door lock system. It first ensures that the password string entered by the user meets the preset security length requirement, and then accurately extracts the core password part from the password that meets the length requirement. This is the key to the verification process, because the core password is the only credential for unlocking the door lock; then, the system matches and verifies the extracted core password with the pre-set valid password. If the match fails, it indicates that the core password entered by the user is wrong. At this time, the system will not only prompt the user with a password error message, but also record the password error event as input behavior information and add it to the information library. Such an operation not only reminds the user to re-enter the correct password, but also provides data support for the system's learning and adaptation, so that the system can optimize its security strategy and improve its ability to identify abnormal behaviors by analyzing multiple input behaviors, including correct and incorrect attempts, thereby ensuring the safety of the door lock while also improving the user experience and the overall intelligence level of the system.

[0040] Step S204, extracting input behavior features from the input behavior information, analyzing the input behavior features using a preset behavior analysis algorithm, and determining whether the input behavior is abnormal. If the input behavior is determined to be abnormal, notifying the administrator through a preset communication channel, and generating abnormal behavior information to be added to the information library, wherein the preset behavior analysis algorithm is a K-means clustering algorithm or a DBSCAN clustering algorithm.

[0041] In this embodiment, the technical solution of the present invention plays a vital role in the smart door lock system. It extracts the behavioral characteristics of the user when entering the password, such as input speed, key sequence and time interval, and uses a preset behavioral analysis algorithm, such as K-means clustering algorithm or DBSCAN clustering algorithm, to conduct in-depth analysis of these input behavior characteristics to identify and judge whether the user's input behavior conforms to the normal mode; when the system finds through algorithm analysis that the input behavior deviates significantly from the normal mode, that is, it is judged to be abnormal behavior, it will automatically trigger the alarm mechanism, and notify the administrator in time through preset communication channels, such as SMS, email or application push, and record and add the detailed information of the abnormal behavior to the information library, so as to provide data support for subsequent security audits and behavior pattern analysis. Such operations not only enhance the active defense capability of the door lock system, but also improve the system's recognition accuracy and response efficiency to potential threats through continuous learning and adaptive adjustment, thereby ensuring the security and reliability of the smart door lock system.

[0042] The general steps of using the K-means clustering algorithm to analyze the door lock password input behavior are as follows: Data collection: Collect the user's password input behavior data on the door lock, including input time, input speed, key sequence, input duration, number of input errors, etc. Data preprocessing: Clean the data and remove invalid or abnormal values ​​(such as records caused by equipment failure). Missing value processing, fill or delete the missing data. Standardize or normalize the data to make the dimensions of different features consistent for easy algorithm processing. Feature selection: Determine which features are most helpful in distinguishing normal and abnormal behaviors, which may require a combination of domain knowledge and exploratory data analysis. The selected features should be able to reflect the user's behavior pattern, such as fast and continuous input may indicate familiarity, while slow and hesitant input may indicate attempt or forgetfulness. Determine the K value: Determine the number of clusters (K value), which is a key parameter of the K-means algorithm. The optimal K value can be estimated by methods such as the elbow rule and silhouette coefficient. Initialize the center point: Randomly select K data points as the initial cluster center, or use the K-means++ algorithm to select the initial center point to improve the clustering effect. Run K-means algorithm: Run K-means algorithm on the dataset using the selected K value and initial center point. The algorithm will assign data points to the nearest cluster center based on the distance in the feature space and continuously update the location of the cluster center. Result analysis: Analyze the clustering results, each cluster represents a password input behavior pattern. For each cluster, further analyze its behavioral characteristics, such as input error rate, input speed, etc. Evaluate clustering effect: Use internal evaluation indicators (such as Within-Cluster Sum of Squares, WCSS) to evaluate the quality of clustering. It may be necessary to run the algorithm multiple times, each time using a different initial center point to ensure that the best clustering result is found. Noise point analysis: Check data points that are assigned to the edge of the cluster or far from the cluster center, which may be an indication of abnormal behavior. Model verification: Validate the model using known normal behavior and abnormal behavior data. Evaluate the model's accuracy, recall rate, and F1 score. Model adjustment: Adjust the K value or feature selection based on the verification results. Multiple iterations may be required to optimize model performance. Deployment and monitoring: Deploy the trained model to the actual door lock system. Continuously monitor the performance of the model and make adjustments based on new data and feedback. Security measures integration: Combine the analysis results of the K-means clustering algorithm with other security measures (such as password complexity checks, attempt limits, etc.) to improve overall security. User feedback loop: Allow users to report false positives or false negatives so that the model can be continuously improved. Regularly update the user behavior model to adapt to changes in user behavior. Through these concrete steps, the K-means clustering algorithm can help identify and prevent unusual door lock password input behaviors, thereby improving the security of the door lock system.

[0043] The general steps of using the DBSCAN algorithm to analyze the door lock password input behavior are as follows: Data collection: Collect the user's password input behavior data on the door lock, including but not limited to input time, input speed, key sequence, input duration, number of input errors, etc. Data preprocessing: Clean the data and remove invalid or outliers (such as records caused by equipment failure). Standardize or normalize the data to make the dimensions of different features consistent for easy algorithm processing. Feature selection: Determine which features are most helpful in distinguishing normal and abnormal behaviors, which may require a combination of domain knowledge and exploratory data analysis. The selected features should be able to reflect the user's behavior patterns, such as fast and continuous input may indicate familiarity, while slow and hesitant input may indicate attempts or forgetfulness. Select DBSCAN parameters: Determine eps (neighborhood radius): This is the range of the neighborhood used to define the point in the algorithm, which needs to be selected based on the density distribution of the data. Determine minPts (minimum number of points): This is the minimum number of samples required to form a cluster, which usually depends on the size of the data set and the expected density of the cluster. Run the DBSCAN algorithm: Run the DBSCAN algorithm on the data set using the selected parameters. The algorithm will cluster the data points according to their density and mark the points in the low-density area as noise. Result analysis: Analyze the clustering results to identify clusters of normal usage patterns and possible abnormal behavior clusters. For each cluster, further analyze its behavioral characteristics, such as input error rate, input speed, etc. Noise point analysis: Check the data points marked as noise, which may be abnormal behaviors and require further manual review or additional analysis. Model validation: Validate the model using known normal behavior and abnormal behavior data. Evaluate the model's accuracy, recall rate, and F1 score. Model adjustment: Adjust DBSCAN parameters or feature selection based on the validation results. Multiple iterations may be required to optimize model performance. Deployment and monitoring: Deploy the trained model to the actual door lock system. Continuously monitor the performance of the model and adjust it based on new data and feedback. Security measures integration: Combine the analysis results of the DBSCAN algorithm with other security measures (such as password complexity checks, attempt limit, etc.) to improve overall security. User feedback loop: Allow users to feedback false positives or false negatives so that the model can be continuously improved. Update the user behavior model regularly to adapt to changes in user behavior. Through these specific steps, the DBSCAN algorithm can help identify and prevent unusual door lock password input behaviors, thereby improving the security of the door lock system.

[0044] Step S205, query the information database, and after determining that at least password error information and abnormal behavior information exist, use the preset security policy model to update the password verification policy, generate a new password according to the updated password verification policy, and notify the administrator through encrypted communication, wherein the preset security policy model is a neural network trained based on the long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least the corresponding information database, and the preset data set at least includes a historical information database composed of the information database.

[0045] In this embodiment, the technical solution of the present invention plays a role in dynamic security regulation in the smart door lock system. By regularly querying the information library to detect whether there is password error information and abnormal behavior information, once these security warning signals are found, the system will activate the preset security policy model, which is a neural network based on the long short-term memory network (LSTM). It uses a preset data set including a historical information library for training, and can dynamically update the password verification strategy according to the collected behavior data; Subsequently, the system will generate a new password according to this updated strategy, and securely notify the administrator through an encrypted communication method to ensure the security of the password update process, thereby ensuring the security of the door lock while also improving the system's adaptability to emerging threats and overall security, so that the smart door lock system can continue to evolve and effectively resist various security threats. In the smart door lock system, the specific process of using the long short-term memory network (LSTM) to train the security policy model involves multiple steps, including data collection, data preprocessing, model design, training, verification and deployment. The following is a detailed description of this process: Data collection: Collect data, collect historical data from the information library, including normal and abnormal password input behavior information, such as input speed, key sequence, time interval, number of password errors, etc. Label assignment: assign labels to data, normal behavior is marked as "normal", and abnormal behavior is marked as "abnormal". Data preprocessing: data cleaning, remove invalid or incomplete data records to ensure data quality. Feature selection: select the most useful features for model prediction, such as input speed, error rate, etc. Data standardization: standardize the data to make model training more efficient. Data segmentation: divide the data into training set, validation set and test set, usually with a ratio of 70% training set, 15% validation set, and 15% test set. Model design: select model structure, design LSTM model architecture, determine the number of network layers, the number of units in each layer, etc. Define loss function, select a suitable loss function, such as cross entropy loss, for classification problems. Optimizer selection: select a suitable optimizer, such as Adam or SGD, to update the network weights. Model training: training process, use the training data set to train the model, calculate the prediction results through forward propagation, and adjust the model weights through backpropagation. Hyperparameter tuning: adjust hyperparameters such as learning rate and batch size to improve model performance. Early stopping method: Use the validation set to monitor the model performance. If the performance is no longer improving, stop training early to avoid overfitting. Model validation: Performance evaluation: Use the validation set to evaluate the model's accuracy, recall, F1 score and other indicators. Error analysis: Analyze the cases where the model predicts errors and understand the model's weaknesses. Model deployment: Deploy the model and deploy the trained model to the smart door lock system. Real-time prediction: The model analyzes the input behavior information in real time, determines whether the behavior is abnormal, and updates the password verification strategy based on the analysis results.Continuous learning: Feedback loop, the system continuously collects new input behavior data and regularly retrains the model to adapt to emerging security threats and changes in user behavior. Through this training process, the LSTM model of the smart door lock system can accurately identify and predict abnormal patterns of password input behavior, thereby dynamically adjusting security policies and improving the security and responsiveness of the system.

[0046] Through the above steps S201 to S205, the smart door lock password anti-peeping method, system, electronic device and storage medium, adopt the method of obtaining the input password string to generate input behavior information, and the input behavior information is added to the information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature; check whether the length of the password string is within the preset length range, if not, prompt to re-enter; extract the core password in the password string within the preset length range; match the extracted core password with the preset valid password, if the match fails, prompt the password error, and generate password error information and add it to the information library; extract the input behavior feature in the input behavior information, use the preset behavior analysis algorithm to analyze the input behavior feature, and judge whether the input behavior is abnormal, If the input behavior is judged to be abnormal, the administrator is notified through the preset communication channel, and abnormal behavior information is generated and added to the information library, wherein the preset behavior analysis algorithm is a K-means clustering algorithm or a DBSCAN clustering algorithm; the information library is queried, and after determining that at least password error information and abnormal behavior information exist, the password verification policy is updated using the preset security policy model, a new password is generated according to the updated password verification policy, and the administrator is notified through encrypted communication, wherein the preset security policy model is a neural network trained based on a long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least the corresponding information library, and the preset data set at least includes a historical information library composed of the information library, which solves the problem of easy peeping and low cracking difficulty of passwords in related technologies, and can increase the difficulty of peeping and cracking passwords.

[0047] In some of the embodiments, after matching the extracted core password with the preset valid password, if the match fails, a password error prompt is given, and password error information is generated and added to the database, it also includes: obtaining the input secondary verification information and adding it to the information library, wherein the secondary verification information includes at least one verification feature; extracting the verification feature of the secondary verification information, matching the verification feature with the preset valid verification feature, if the match fails, a password error prompt is given, and password error information is generated and added to the information library, wherein the verification feature includes at least one of password verification data, face verification data, fingerprint verification data, palm vein verification data, dynamic verification code data, and voiceprint verification data.

[0048] In this embodiment, the technical solution of the present invention plays a role in enhancing security and error handling in the smart door lock system. When the core password fails to match, the system will not immediately deny access, but instead start a secondary verification process by obtaining additional verification feature information such as passwords, faces, fingerprints, palm veins, dynamic verification codes or voiceprints, and adding them to the information library. Then, the preset valid verification features are used to match the obtained verification features. This step adds a level of security to ensure that even if the password is cracked or guessed, the attacker still needs to pass secondary verification to obtain access rights. If the secondary verification also fails, the system will prompt that the password is wrong and record the information of this verification failure in the information library for future security analysis and behavior pattern learning. At the same time, this information can also be used by the system to automatically adjust security policies, improve the ability to identify and respond to abnormal behaviors, and ensure that only authorized users can access the door lock, thereby providing a more comprehensive and proactive security protection measure in the entire technical solution.

[0049] In some embodiments, the input behavior feature includes at least one of a password input speed and an input mode.

[0050] In this embodiment, the technical solution of the present invention provides a behavioral biometric security layer for the smart door lock system by capturing and analyzing the user's behavioral characteristics such as password input speed and input mode, wherein the input speed refers to the time interval between the user's key presses, and the input mode may involve the user's unique key sequence or rhythm; these characteristics are used as key data to distinguish user identities and detect abnormal behaviors. By continuously collecting and analyzing these behavioral characteristics, the system can establish a unique input profile for each user. When input behavior that is significantly inconsistent with the archived behavioral characteristics is detected, the system will mark it as a potential abnormal behavior and take corresponding security measures, such as triggering an alarm or requiring additional identity authentication, thereby enhancing the security of the system, so that the smart door lock can not only defend against traditional password cracking attacks, but also effectively respond to more covert behavioral pattern imitation attacks, ensuring that only legitimate users can successfully unlock the door by password input, thereby improving the security performance and user experience of the entire system.

[0051] In some of the embodiments, a preset behavior analysis algorithm analyzes input behavior characteristics, including: recording the time interval between each key press by the user; predicting the time interval range of normal input using a long short-term memory network (LSTM) model; and comparing the actual recorded time interval with the predicted time interval range to identify whether the input behavior is abnormal.

[0052] In this embodiment, the technical solution of the present invention plays a core security monitoring role in the smart door lock system. The user's password input behavior is carefully monitored and analyzed through a preset behavior analysis algorithm. The specific operation includes recording the time interval between each key press of the user, and then using the long short-term memory network (LSTM) model to predict the time interval range of normal user input based on historical data. By comparing the actual recorded time interval with this predicted range, the system can identify whether there is abnormal input behavior, such as input speed that is too fast or too slow, which may indicate that it is not the user himself or an attempt to crack, thereby triggering security warnings or further verification measures in time. Such dynamic monitoring and analysis not only improves the door lock's ability to respond to potential threats, but also enhances the system's understanding and adaptability to user behavior through continuous learning of the machine learning model, ensuring that the smart door lock can maintain a high level of security protection in the face of ever-changing security threats.

[0053] In some of the embodiments, a preset behavior analysis algorithm analyzes input behavior characteristics, including: analyzing the user's commonly used input patterns, wherein the input pattern at least includes the order of commonly used fingers; using a hidden Markov model (HMM) to identify inconsistent input patterns; and comparing the identified input pattern with the user's historical input pattern to identify whether the input behavior is abnormal.

[0054] In this embodiment, the role of the technical solution of the present invention in the smart door lock system is to enhance the recognition and monitoring of user behavior patterns. The user's input pattern, especially the order of commonly used fingers, is analyzed in detail through a preset behavior analysis algorithm, and then a statistical model such as a hidden Markov model (HMM) is used to learn and identify the pattern of user input, thereby establishing a benchmark for normal behavior; when the user enters a password, the system will capture and analyze its input pattern in real time, and compare the real-time analysis results with the user's historical input pattern. If it is found that the input pattern is significantly different from the historical data, such as using a different finger sequence or input rhythm, the system will mark it as abnormal behavior, which may mean that the door lock is suffering from unauthorized access attempts; in this way, the system can not only provide real-time security monitoring, but also adapt to the user's personalized behavior and improve the accuracy of detecting potential threats, thereby playing a role of active defense and precise identification in the entire security solution, ensuring the safety and reliability of the smart door lock system.

[0055] In some embodiments, the password verification policy includes at least one of the policies of changing the number of password verification times, changing the password verification type, changing redundant passwords, changing valid passwords, and changing the effective length of passwords.

[0056] In this embodiment, the role of this technical solution in the smart door lock system is to provide flexible password security policy management to adapt to different security needs and respond to various security threats. The specific operations include dynamically adjusting various aspects of password verification based on the system's analysis results of user behavior and changes in the security environment, such as increasing or decreasing the number of password verifications to improve security or improve user experience, changing the password verification type to introduce multi-factor authentication to enhance protection, adjusting redundant password policies to allow users to freely add numbers around the core password to prevent peeping, updating valid passwords to reduce the risk of password cracking, and changing the effective length of passwords to increase the complexity and difficulty of guessing of passwords; through the implementation of these strategies, the system can control access rights more accurately, while responding quickly to user behavior and security threats, ensuring that the security of the door lock is always in the best state.

[0057] This embodiment also provides a smart door lock password anti-peeping system, which is used to implement the above embodiments and preferred embodiments, and will not be repeated here. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0058] Figure 3 is a structural block diagram of the smart door lock password anti-peeping system according to an embodiment of the present application, such as Figure 3 As shown, the device includes a password acquisition module 31, a password length verification module 32, a password extraction module 33, a valid password verification module 34, an input behavior verification module 35 and a password verification strategy update module 36, wherein:

[0059] A password acquisition module 31 is used to acquire an input password string to generate input behavior information, and the input behavior information is added to the information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature;

[0060] The password length verification module 32 is coupled to the password acquisition module 31 and is used to check whether the length of the password string is within a preset length range. If it is not within the preset length range, it prompts the user to re-enter the password and generates a password error message to be added to the information library.

[0061] A password extraction module 33, coupled to the password length verification module 32, is used to extract the core password from the password character string within a preset length range;

[0062] The effective password verification module 34 is coupled to the password extraction module 33 and is used to match the extracted core password with the preset effective password. If the match fails, it prompts that the password is wrong and generates password error information to be added to the information library;

[0063] The input behavior verification module 35 is coupled with the password acquisition module 31, and is used to extract input behavior features from the input behavior information, analyze the input behavior features using a preset behavior analysis algorithm, and determine whether the input behavior is abnormal. If the input behavior is determined to be abnormal, the administrator is notified through a preset communication channel, and abnormal behavior information is generated and added to the information library, wherein the preset behavior analysis algorithm is a K-means clustering algorithm or a DBSCAN clustering algorithm;

[0064] The password verification policy update module 36 is coupled with the valid password verification module 34 and the input behavior verification module 35, and is used to query the information base, and after determining that at least password error information and abnormal behavior information exist, update the password verification policy using the preset security policy model, generate a new password according to the updated password verification policy, and notify the administrator through encrypted communication, wherein the preset security policy model is a neural network trained based on the long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least the corresponding information base, and the preset data set at least includes a historical information base composed of the information base.

[0065] In some embodiments, it also includes: a secondary verification module 37, coupled with the valid password verification module 34, for obtaining the input secondary verification information and adding it to the information library, wherein the secondary verification information includes at least one verification feature; extracting the verification feature of the secondary verification information, and matching the verification feature with the preset valid verification feature. If the match fails, it prompts that the password is wrong, and generates password error information and adds it to the information library, wherein the verification feature includes at least one of password verification data, face verification data, fingerprint verification data, palm vein verification data, dynamic verification code data, and voiceprint verification data.

[0066] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0067] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0068] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0069] In addition, in combination with the material distribution method for a mixed-flow assembly workshop in the above embodiment, the present application embodiment can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any of the material distribution methods for a mixed-flow assembly workshop in the above embodiment is implemented.

[0070] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0071] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for preventing peeping of smart door lock password, characterized in that: include: Obtaining an input password string to generate input behavior information, and adding the input behavior information to an information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature; Check whether the length of the password string is within a preset length range, and if not, prompt the user to re-enter the password; Extract the core password from the password string within a preset length range; Match the extracted core password with the preset valid password. If the match fails, a password error message will be prompted and a password error message will be generated and added to the information database. Extract input behavior features from the input behavior information, analyze the input behavior features using a preset behavior analysis algorithm, determine whether the input behavior is abnormal, and if the input behavior is determined to be abnormal, notify the administrator through a preset communication channel, and generate abnormal behavior information and add it to the information library, wherein the preset behavior analysis algorithm is a K-means clustering algorithm or a DBSCAN clustering algorithm; The information base is queried, and after determining that at least password error information and abnormal behavior information exist, the password verification policy is updated using a preset security policy model, a new password is generated according to the updated password verification policy, and an administrator is notified through encrypted communication, wherein the preset security policy model is a neural network trained based on a long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least a corresponding information base, and the preset data set at least includes a historical information base constituted by the information base.

2. The method according to claim 1, characterized in that: After matching the extracted core password with the preset valid password, if the match fails, a password error message is prompted, and a password error message is generated and added to the database, it also includes: Obtaining input secondary verification information and adding it to the information library, wherein the secondary verification information includes at least one verification feature; Extract the verification feature of the secondary verification information, and use the preset valid verification feature to match the verification feature. If the match fails, it will prompt that the password is wrong, and generate password error information to add to the information library, wherein the verification feature at least includes one of password verification data, face verification data, fingerprint verification data, palm vein verification data, dynamic verification code data, and voiceprint verification data.

3. The method according to claim 1, characterized in that The input behavior feature includes at least one of a password input speed and an input mode.

4. The method according to claim 3, characterized in that The preset behavior analysis algorithm analyzes input behavior characteristics, including: Record the time interval between each key press by the user; Use the long short-term memory network (LSTM) model to predict the time interval range of normal input; The actual recorded time intervals are compared with the predicted time interval range to identify whether the input behavior is abnormal.

5. The method according to claim 3, characterized in that: The preset behavior analysis algorithm analyzes input behavior characteristics, including: Analyzing a user's commonly used input mode, wherein the input mode at least includes a sequence of commonly used fingers; Use Hidden Markov Models (HMMs) to identify inconsistent input patterns; The recognized input pattern is compared with the user's historical input pattern to identify whether the input behavior is abnormal.

6. The method according to claim 1, characterized in that The password verification strategy at least includes one of the strategies of changing the number of password verification times, changing the password verification type, changing redundant passwords, changing valid passwords, and changing the effective length of passwords.

7. An intelligent door lock password anti-peeping system, characterized in that: include: A password acquisition module, used to acquire an input password string to generate input behavior information, and the input behavior information is added to the information library, wherein the password string includes at least one core password, and the input behavior information includes at least one input behavior feature; A password length verification module, coupled to the password acquisition module, is used to check whether the length of the password string is within a preset length range, and if not, prompts the user to re-enter the password; A password extraction module, coupled to the password length verification module, is used to extract the core password from the password character string within a preset length range; A valid password verification module, coupled with the password extraction module, is used to match the extracted core password with a preset valid password. If the match fails, a password error message is prompted and a password error message is generated and added to the information library; An input behavior verification module, coupled with the secret acquisition module, is used to extract input behavior features from the input behavior information, analyze the input behavior features using a preset behavior analysis algorithm, and determine whether the input behavior is abnormal. If the input behavior is determined to be abnormal, the administrator is notified through a preset communication channel, and abnormal behavior information is generated and added to the information library, wherein the preset behavior analysis algorithm is a K-means clustering algorithm or a DBSCAN clustering algorithm; The password verification policy update module is coupled with the valid password verification module and the input behavior verification module, and is used to query the information base, and after determining that at least password error information and abnormal behavior information exist, update the password verification policy using a preset security policy model, generate a new password according to the updated password verification policy, and notify the administrator through encrypted communication, wherein the preset security policy model is a neural network trained based on a long short-term memory network LSTM and a preset data set, and is trained to output an updated password verification policy based on at least a corresponding information base, and the preset data set at least includes a historical information base composed of the information base.

8. The system according to claim 7, characterized in that include: A secondary verification module, coupled to the valid password verification module, is used to obtain input secondary verification information and add it to the information library, wherein the secondary verification information includes at least one verification feature; Extract the verification feature of the secondary verification information, and use the preset valid verification feature to match the verification feature. If the match fails, it will prompt that the password is wrong, and generate password error information to add to the information library, wherein the verification feature at least includes one of password verification data, face verification data, fingerprint verification data, palm vein verification data, dynamic verification code data, and voiceprint verification data.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps of the smart door lock password anti-peeping method according to any one of claims 1 to 6.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart door lock password anti-peeping method described in any one of claims 1 to 6 are implemented.

Images