Intelligent lock anti-cracking method and system based on multi-band signal analysis

Abstract

The invention relates to the technical field of intelligent locks, in particular to an intelligent lock anti-cracking method and system based on multi-band signal analysis. The method comprises the following steps: continuously collecting electromagnetic signals in an environment through a multi-band receiver of the intelligent lock; performing spectral analysis on the acquired multi-band signals to generate a spectrogram; constructing a multi-dimensional spectrum matrix by using the spectrogram; performing time sequence analysis on the multi-dimensional spectrum matrix, and extracting spectrum change characteristics; judging whether a potential cracking threat exists or not based on the extracted spectrum change characteristics; if potential cracking threats are detected, a protection mechanism of the intelligent lock is triggered. According to the invention, through omnibearing signal analysis and a dynamic protection strategy, the capability of the intelligent lock for resisting complex cracking behaviors is improved, and the actual requirements of the intelligent lock field for high safety and high stability are met.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent locks, and specifically to an intelligent lock anti-cracking method and system based on multi-band signal analysis. Background Art

[0002] With the continuous development of smart home technology, intelligent locks, as key devices for home security, are favored by more and more users. However, with the progress of technology, cracking methods for intelligent locks emerge in an endless stream, posing a serious threat to users' property safety. Currently, most intelligent locks on the market rely on single-band signal transmission and reception. Although this method can meet general communication requirements, its protection ability is relatively weak in the face of diverse and increasingly complex cracking methods. Especially for complex cracking methods such as multi-band and synchronous interference used by advanced attackers, existing intelligent locks lack effective protection mechanisms. Therefore, how to enhance the intelligent lock's ability to identify and protect against multi-band signal interference and cracking behavior through effective technical means has become an urgent technical problem in the current intelligent lock technology field. Summary of the Invention

[0003] The present invention provides an intelligent lock anti-cracking method and system based on multi-band signal analysis to enhance the intelligent lock's ability to identify and protect against multi-band signal interference and cracking behavior.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: On the one hand, an intelligent lock anti-cracking method based on multi-band signal analysis is provided. The method includes the following steps: Continuously collect electromagnetic signals in the environment through the multi-band receiver of the intelligent lock; Perform spectral analysis on the collected multi-band signals to generate a spectrogram; Construct a multi-dimensional spectral matrix using the spectrogram; Perform time series analysis on the multi-dimensional spectral matrix to extract spectral change features; Based on the extracted spectral change features, determine whether there is a potential cracking threat; If a potential cracking threat is detected, trigger the protection mechanism of the intelligent lock; The formula for extracting spectral change features is: , where V is the spectral change value, N is the length of the time series, M is the number of frequency bands, S i,j is the signal intensity of the jth frequency band at the ith time point, w j is the weight coefficient of the jth frequency band.

[0005] On the other hand, an intelligent lock anti-cracking system based on multi-band signal analysis is provided. The system includes: A multi - band signal receiving module, used to collect electromagnetic signals in the environment; A spectrum analysis module, used to perform spectrum analysis on the collected electromagnetic signals and generate a spectrogram; A matrix construction module, used to construct a multi - dimensional spectrum matrix according to the spectrogram; A feature extraction module, used to perform time - series analysis on the multi - dimensional spectrum matrix and extract spectrum change features; A threat judgment module, used to judge whether there is a potential cracking threat based on the extracted spectrum change features; A protection control module, used to trigger corresponding protection mechanisms when a potential cracking threat is detected.

[0006] The beneficial effects of the present invention are as follows: By adopting multi - band signal receiving and analysis technology, the present invention can conduct detailed analysis and monitoring of environmental electromagnetic signals from multiple dimensions. By constructing a multi - dimensional spectrum matrix and performing time - series analysis, the present invention can accurately extract spectrum change features and judge potential cracking threats based on these features. Through comprehensive signal analysis and dynamic protection strategies, the ability of the intelligent lock to resist complex cracking behaviors is improved, meeting the actual requirements of the intelligent lock field for high security and high stability.

[0007] In addition, the present invention also designs a protection mechanism, which can immediately trigger corresponding protection measures when a potential threat is detected, thereby further enhancing the security of the intelligent lock. Brief Description of the Drawings

[0008] Figure 1 It is a flowchart of the intelligent lock anti - cracking method in an embodiment of the present invention; Figure 2 It is a multi - band signal spectrum analysis diagram in an embodiment of the present invention; Figure 3 It is a multi - dimensional spectrum matrix diagram in an embodiment of the present invention; Figure 4 It is a spectrum change feature diagram in an embodiment of the present invention; Figure 5 It is a supplementary process of the intelligent lock anti - cracking method in an embodiment of the present invention Figure 1 ; Figure 6 It is a flowchart of judging cracking attempt features in an embodiment of the present invention; Figure 7 It is a supplementary process of the intelligent lock anti - cracking method in an embodiment of the present invention Figure 2 ; Figure 8 It is an architecture diagram of the intelligent lock anti - cracking system in an embodiment of the present invention; In the drawings, the list of components represented by each reference numeral is as follows: 100, Multi-band signal receiving module; 200, Spectrum analysis module; 300, Matrix construction module; 400, Feature extraction module; 500, Threat judgment module; 600, Protection control module; 700, Band correlation analysis module; 800, Dynamic frequency adjustment unit; 900, Adaptive learning module. Detailed implementation

[0009] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention.

[0010] The present invention provides the following preferred embodiments: Embodiment 1 To solve the problem that the intelligent lock is vulnerable to cracking attacks in a complex electromagnetic environment, this embodiment proposes an anti-cracking method based on multi-band signal analysis.

[0011] As Figure 1 shown, the anti-cracking method of the intelligent lock includes the following steps: S101. Continuously collect electromagnetic signals in the environment through the multi-band receiver of the intelligent lock.

[0012] S102. Perform spectrum analysis on the collected multi-band signals to generate a spectrogram, as Figure 2 shown.

[0013] S103. Use the spectrogram to construct a multi-dimensional spectrum matrix, as Figure 3 shown.

[0014] S104. Perform time series analysis on the multi-dimensional spectrum matrix to extract spectrum change features, as Figure 4 shown.

[0015] S105. Based on the extracted spectrum change features, determine whether there is a potential cracking threat.

[0016] S106. If a potential cracking threat is detected, trigger the protection mechanism of the intelligent lock.

[0017] S107. The formula for extracting spectrum change features is:

[0018] where V is the spectrum change value, N is the length of the time series, M is the number of frequency bands, S i,j is the signal strength of the j-th frequency band at the i-th time point, and w j is the weight coefficient of the j-th frequency band.

[0019] Specifically, in this embodiment, the intelligent lock is equipped with a multi-band receiver that can continuously collect electromagnetic signals in the environment. These signals cover a wide frequency band from ultra-low frequency to ultra-high frequency, enabling a comprehensive perception of the electromagnetic activities in the surrounding environment. The collected signals are first input into the spectrum analysis module to generate corresponding spectrograms. This process converts the time-domain signals into frequency-domain signals through Fourier transform of the signals, and the generation of spectrograms depends on the fine processing of the frequency-domain data to reflect the energy distribution of each frequency band at different time points.

[0020] Furthermore, using the generated spectrograms, this embodiment constructs a multi-dimensional spectrum matrix. Based on the spectrograms, the multi-dimensional spectrum matrix combines time series information to construct a multi-dimensional data structure, enabling the clear presentation of the changes of signals in different frequency bands over time. This matrix structure can effectively capture the tiny fluctuations of signals on the time axis, thus providing an accurate data basis for subsequent time series analysis. Each dimension in the matrix corresponds to a specific frequency band, and each matrix element represents the signal intensity of that frequency band at a certain time point. The construction process of the matrix not only considers the continuity of the time dimension but also performs weighted processing on the signal characteristics of different frequency bands to ensure that the contribution rates of signals in each frequency band to the overall analysis are balanced.

[0021] Furthermore, after the construction of the multi-dimensional spectrum matrix is completed, this embodiment conducts time series analysis on the matrix to extract spectrum change characteristics. In this step, time series analysis mainly identifies the significant changes by observing the change patterns of signal intensities in the matrix over time. It should be understood that the spectrum change characteristics not only reflect the intensity level of the signal at a certain moment but also include its dynamic changes on the time axis. By comparing the signal intensities at different time points, this embodiment can calculate the fluctuations of each frequency band in the time series and extract the spectrum change value V described in the formula. It can be understood that the calculation of the spectrum change value V takes into account multiple factors, including the time series length N, the number of frequency bands M, and the intensities S of signals in different frequency bands at each time point. i,j Through the comprehensive analysis of these parameters, characteristic values that can accurately reflect the dynamic changes of the signals are generated.

[0022] Furthermore, based on the extracted spectrum change characteristics, this embodiment further determines whether there is a potential cracking threat. This determination process relies on a preset normal signal behavior pattern and evaluates whether the current signal deviates from the normal range by comparing the current spectrum change characteristics with historical data. It should be understood that this embodiment performs weighted processing on the signal intensities of different frequency bands to more accurately reflect the impact of spectrum change characteristics on threat assessment. When calculating the weight coefficient w jWhen considering the characteristics of different frequency bands and their typical performance in normal usage scenarios, the spectral change characteristics can more comprehensively characterize the abnormal behavior of signals, providing a reliable basis for detecting cracking threats.

[0023] If a potential cracking threat is detected, this embodiment will immediately trigger the protection mechanism of the smart lock. The triggering of the protection mechanism is based on the threshold judgment of the spectral change value V. The dynamically adjusted threshold can adapt to signal fluctuations under different environmental and time conditions. The calculation formula of the threshold takes into account the historical average value μ of the spectral change value V and the standard deviation σ V and is dynamically adjusted in combination with the time interval Δt between the current time and the last threat detection time. It can be understood that this dynamic adjustment mechanism ensures that the smart lock can respond flexibly when facing threats of different intensities, avoiding both over-sensitivity and missed threat reports.

[0024] Through this embodiment, the smart lock can accurately identify and protect against potential cracking threats in a complex electromagnetic environment. The core lies in collecting and analyzing multi-band signals, combining multi-dimensional spectral matrices and time series analysis, extracting spectral change characteristics, and making threat judgments based on these characteristics. This embodiment not only optimizes the depth and breadth of spectral analysis but also improves the system's adaptability to different environmental conditions through the introduction of a dynamic threshold. Ultimately, this embodiment realizes the active protection ability of the smart lock, significantly enhancing its security and reliability in various complex environments.

[0025] Embodiment 2 To solve the problem that existing smart locks cannot effectively identify and respond to potential cracking threats in a complex electromagnetic signal environment, this embodiment further refines the mechanism of dynamic threshold judgment. In this embodiment, by dynamically analyzing the historical data of the spectral change value, the threshold T is adjusted in real time to adapt to signal fluctuations under different environmental and time conditions. This dynamic threshold judgment mechanism ensures the accurate detection of abnormal signals and can flexibly respond to changes in the external environment, improving the accuracy of threat identification and the protection ability of the smart lock.

[0026] In this embodiment, the calculation formula of the dynamic threshold T is:

[0027] where T is the dynamic threshold, μ V is the historical average value of the spectral change value, σ Vis the historical standard deviation of the spectral change value, k is an adjustable coefficient, Δt is the interval between the current time and the last threat detection time, and τ is the time decay constant. It should be understood that the calculation of the dynamic threshold not only depends on the current signal change, but also comprehensively considers the influence of historical data and time factors. Through this calculation method, the system can adaptively adjust the sensitivity to signal fluctuations, so that in a complex electromagnetic environment, it can avoid false alarms for small-amplitude environmental changes and can also timely detect potential cracking threats brought by abnormal fluctuations.

[0028] Furthermore, in the process of setting the dynamic threshold, this embodiment has carefully optimized the adjustable coefficient k. The magnitude of the k value directly determines the response sensitivity of the system to spectral changes. In practical applications, the k value can be dynamically adjusted according to different scenario requirements. For example, in some scenarios with relatively stable electromagnetic environments, the k value can be set to a lower value to avoid the system being too sensitive; while in some scenarios with frequent electromagnetic interference, the k value can be appropriately increased to ensure that the system can respond in a timely manner to large-amplitude signal fluctuations. Therefore, the setting of the k value has high flexibility in different environments, ensuring the adaptability of the system to external environmental changes.

[0029] Furthermore, the time decay constant τ in the formula further refines the system's weight control of time factors. It should be understood that the introduction of τ enables the system to dynamically adjust the dependence on historical data according to the time interval Δt. When Δt is small, the system relies more on recent data for judgment to ensure the real-time response ability to current environmental changes; while when Δt is large, the system will gradually reduce the dependence on historical data and enhance the response strength to the current signal. This time decay mechanism enables the system to better balance the relationship between historical signal characteristics and current signal changes, improving the accuracy and reliability of threat detection.

[0030] The benefit of this embodiment is that by adopting the calculation formula of the dynamic threshold, the intelligent lock system can adaptively adjust the signal determination standard under different environmental and time conditions. This mechanism not only considers the historical statistical characteristics of the spectral change value, but also comprehensively considers the dynamic changes of time factors, effectively avoiding the limitations of the traditional fixed threshold method in threat detection in a complex electromagnetic environment. Through this embodiment, the intelligent lock can more accurately judge potential cracking threats and immediately trigger corresponding protection mechanisms, providing users with more stable and reliable security protection capabilities.

[0031] In addition, there is a tight logical connection between the various parameters in the dynamic threshold calculation. μ V As the historical average, it reflects the overall signal fluctuation trend of the system over a long period of time, while σ VIt represents the degree of discreteness of signal fluctuations. These two parameters together constitute the basic characteristics of signal changes in the current environment. By dynamically monitoring these two parameters, the system can accurately identify abnormal signal changes. At the same time, Δt and τ determine how to balance the relationship between historical data and current data when the system makes signal judgments. This time decay mechanism enables the system to flexibly adjust the dependence on historical data under different time conditions, ensuring the timeliness of threat detection. Through this embodiment, the intelligent lock system has achieved a leap from a single static threshold judgment to a dynamic adaptive judgment, significantly improving the flexibility and threat response ability of the system.

[0032] Embodiment III To solve the problem that the information of each frequency band in multi-band signal analysis is not fully utilized, this embodiment further optimizes the signal processing method and introduces the correlation analysis between frequency bands. By calculating the correlation coefficients between different frequency bands, this embodiment can capture signal characteristics more comprehensively, improving the adaptability of the intelligent lock to complex electromagnetic environments and the recognition accuracy of cracking threats.

[0033] Specifically, the intelligent lock anti-cracking method further includes performing correlation analysis on multi-band signals, calculating the correlation coefficients between frequency bands according to the correlation analysis, and the calculation formula of the correlation coefficient is:

[0034] where R ij is the correlation coefficient between the i-th frequency band and the j-th frequency band, S i,t and S j,t are the signal intensities of the i-th and j-th frequency bands at time t respectively, and are their respective averages.

[0035] In this embodiment, the correlation analysis of multi-band signals is performed after spectrum analysis and multi-dimensional spectrum matrix construction. This step aims to deeply explore the internal relationship between signals of different frequency bands, providing more dimensional information support for subsequent threat judgments.

[0036] where R ij is the correlation coefficient between the i-th frequency band and the j-th frequency band, S i,t and S j,t respectively represent the signal intensities of the i-th and j-th frequency bands at time t, and are their respective averages. It should be understood that this calculation method not only considers the absolute value of the signal intensity but also eliminates the influence of baseline deviation by subtracting the average value, making the correlation analysis more accurate.

[0037] Furthermore, the calculation process of the correlation coefficient involves the processing of time series data. In practical applications, the system will select an appropriate time window for correlation analysis. The selection of the time window needs to balance real-time performance. A shorter time window can provide a faster response speed, while a longer time window can provide a more stable correlation estimate. It can be understood that the length of the time window can be dynamically adjusted according to the actual application scenario to adapt to different environmental change speeds.

[0038] Furthermore, the calculation results of the correlation coefficient form a correlation matrix, and each element R in the matrix ij represents the degree of correlation between two different frequency bands. This correlation matrix provides rich information and can be used to identify abnormal associations between frequency bands. Under normal circumstances, there may be stable correlations between certain frequency bands, and when a cracking attempt occurs, this correlation may change significantly. Therefore, by monitoring the changes in the correlation coefficient, the system can more sensitively detect potential cracking behaviors.

[0039] Furthermore, this embodiment also considers the application of the correlation coefficient in threat judgment. By setting a threshold range for the correlation coefficient, the system can identify abnormal frequency band associations. For example, if two frequency bands that were originally highly correlated suddenly become uncorrelated, or if two frequency bands that were originally uncorrelated suddenly show a high degree of correlation, this may be a signal of a cracking attempt. It should be understood that this correlation-based judgment method provides a supplementary dimension, which, combined with the judgment method based on the signal strength of a single frequency band, can significantly improve the detection accuracy of the system.

[0040] Furthermore, the results of the correlation analysis can also be used to optimize the extraction of spectral change features. By introducing the correlation coefficient as a weighting factor into the calculation of the spectral change value, the system can more strongly emphasize the changes in highly correlated frequency bands, thereby improving the sensitivity to coordinated attacks. This weighted processing method enables the system to better adapt to complex electromagnetic environments and improve the ability to identify multi-frequency band coordinated cracking attempts.

[0041] The benefit of this embodiment is that by introducing the correlation analysis between frequency bands, the intelligent lock system obtains deeper signal feature information. This not only enhances the system's understanding ability of complex electromagnetic environments but also improves the recognition accuracy of potential cracking threats. The correlation analysis provides a new dimension for the system to evaluate signal anomalies, enabling the protection mechanism to be more comprehensive and accurate. Through this embodiment, the intelligent lock can better cope with advanced cracking means such as multi-frequency band coordinated attacks and provide more reliable and comprehensive security protection for users.

[0042] Embodiment 4 To address the problem that traditional smart locks are vulnerable to attacks at a single frequency, this embodiment further refines the protection mechanism. By introducing dynamic frequency hopping technology, the anti-cracking ability of the smart lock is improved. Dynamic frequency hopping is an effective means of disrupting attackers by continuously changing the operating frequency. In this embodiment, the generation formula of the hopping sequence is:

[0043] where \(f_n\) is the frequency index after the \(n\)th hop, \(f_0\) is the initial frequency index, \(a\) and \(b\) are adjustable parameters, and \(M\) is the number of available frequencies.

[0044] Furthermore, in the dynamic frequency hopping mechanism of this embodiment, an initial frequency index \(f_0\) is first set as the operating frequency of the system at the start stage. The number of available frequencies \(M\) is pre-planned according to the spectrum resource situation in the environment where the smart lock is located to ensure that the system can use enough frequencies for hopping, thereby increasing the cracking difficulty. Each frequency hop is calculated based on the formula, and the core lies in the configuration of the parameters \(a\) and \(b\), which determine the complexity and unpredictability of the hopping sequence.

[0045] Furthermore, the selection of the parameters \(a\) and \(b\) needs to consider various factors. The setting of the \(a\) value mainly affects the step size of the frequency hop. For different application scenarios, it can be adjusted according to the characteristics of the interference source and the configuration of the spectrum resources. A larger \(a\) value will cause the frequency index to change faster, effectively disrupting the attacker; while a smaller \(a\) value can perform more detailed hopping within the limited spectrum resources, improving the frequency utilization rate. On the other hand, the setting of the \(b\) value provides additional randomness, making the hopping sequence more difficult to predict. It can be understood that the combination of \(a\) and \(b\) makes the frequency hopping sequence highly complex, thus increasing the cracking difficulty.

[0046] Furthermore, in practical applications, this embodiment recommends adjusting the values of \(a\) and \(b\) according to the dynamic changes in the spectrum environment. The system can dynamically adjust these two parameters through real-time monitoring of the surrounding electromagnetic environment, thereby flexibly coping with various interferences and threats in the environment. For example, when it is detected that the interference signal on a specific frequency band increases, the \(a\) value can be appropriately increased to quickly jump out of the interfered frequency band, or the \(b\) value can be adjusted to change the pattern of the hopping sequence to avoid the interference area.

[0047] It should be understood that dynamic frequency hopping not only effectively blocks the long-term cracking of a single frequency by external attackers, but also reduces the effectiveness of the attacker's continuous monitoring and analysis of the spectrum by frequently switching the operating frequency. This protection mechanism exhibits extremely high anti-interference ability in the face of attack means such as high-frequency signal sweeping, interference, and capturing. Through frequency hopping, the concealment of signal transmission is improved, making it difficult for attackers to capture and decode the effective signal.

[0048] The benefits of this embodiment are that by introducing the dynamic frequency hopping technology, the intelligent lock system realizes the dynamic scheduling of multi-band signals in time. Its protection mechanism not only considers the efficient utilization of frequency resources, but also synthesizes the highly complex hopping sequences brought by different parameter combinations, increasing the difficulty of system cracking. In addition, the implementation of dynamic frequency hopping depends on a high-precision frequency control module. In this embodiment, a frequency synthesizer based on digital signal processing (DSP) technology is recommended to ensure the fast response and high stability of frequency hopping. This frequency can complete frequency switching in an extremely short time, ensuring the continuity of the signal and preventing signal interruption during the consistent frequency hopping process.

[0049] It can be understood that the calculation and execution of the frequency hopping sequence need to be closely coordinated with the control logic of the intelligent lock. In this embodiment, the system sends the calculated frequency index to the frequency control module through a preset hopping sequence generation algorithm to complete the frequency switching, and the whole process can be completed within a few microseconds to ensure the real-time performance and reliability of the system.

[0050] Embodiment Five To solve the potential signal anomaly detection problem in the multi-band signal analysis of the intelligent lock, this embodiment further refines the anti-cracking method and adopts a signal anomaly pattern recognition mechanism based on anomaly scores. Through this mechanism, the system can effectively distinguish normal signal fluctuations from potential cracking attack behaviors, thereby providing a more accurate protection response. The calculation formula for the anomaly score is:

[0051] where S anom represents the anomaly score, S j is the current signal strength, μ j and σ j are the historical average value and standard deviation of this frequency band respectively, and k is an adjustable coefficient. Through this formula, the system can quickly determine whether there is an abnormal fluctuation in the current signal based on real-time monitoring.

[0052] Furthermore, the signal anomaly detection mechanism of this embodiment is based on statistical principles, and a standard behavior model for each frequency band is constructed through historical data. The system continuously monitors the signal strength of each frequency band and calculates the average value μ j and standard deviation σ j of this frequency band according to historical data. The average value μ j represents the typical signal strength of this frequency band, and the standard deviation σ j reflects the range of signal fluctuations. It should be understood that this dynamic update based on historical data enables the system to adapt to different signal fluctuation situations in different environments, thereby reducing the false alarm rate and improving the protection accuracy.

[0053] Furthermore, the setting of the k value directly affects the sensitivity of the anomaly score. A smaller k value makes the system more sensitive to signal fluctuations, resulting in a higher anomaly score even under small anomaly fluctuations, which is suitable for high-sensitivity scenarios. On the contrary, a larger k value can reduce the sensitivity and is applicable to a relatively stable signal environment to prevent over-response to normal signal fluctuations. It can be understood that the choice of the k value needs to be flexibly adjusted according to the actual application scenario to ensure that the system can maintain the best sensitivity in different signal environments.

[0054] Furthermore, the anomaly score S anom is used to evaluate the current signal state. If S anom exceeds a certain preset threshold, it indicates that the current signal exhibits obvious abnormal characteristics, which may mean the existence of a cracking attempt or other malicious interference behaviors. At this time, the system will trigger corresponding protection measures according to the magnitude and duration of the anomaly score. For example, when the anomaly score is large and the duration is long, the system can immediately perform a locking operation and send an alarm to the user to alert them of the possible cracking threat.

[0055] Furthermore, the anomaly score recognition mechanism of this embodiment also has an adaptive ability. By dynamically updating the historical signal data, the system can automatically adjust the values of μ j and σ j to ensure efficient anomaly detection ability under different environmental conditions. For example, when the smart lock is in an environment with strong electromagnetic interference, the signal fluctuation range may increase, and the system will correspondingly adjust the value of σ j to reduce the sensitivity of anomaly detection to avoid false alarms. In an environment with less interference, the value of σ j will be correspondingly reduced to improve the detection accuracy.

[0056] Furthermore, the anomaly score mechanism can be combined with the aforementioned dynamic frequency hopping mechanism. When the system detects that the anomaly score S anom of a certain frequency band exceeds the threshold, in addition to triggering an alarm or a locking operation, the system can also accelerate the frequency hopping process to further enhance the protection effect. At this time, the rate and randomness of frequency hopping will be significantly improved, making it more difficult for attackers to predict and capture effective signals. This collaborative mechanism greatly improves the overall protection level of the smart lock.

[0057] It is understandable that the implementation of the anomaly scoring mechanism relies on efficient data processing capabilities and real-time signal monitoring modules. By combining anomaly score calculation with dynamic frequency hopping, the smart lock can effectively cope with complex attack methods, such as advanced attack behaviors like multi-band signal disruption and joint cracking. In addition, the system can also perform frequency band priority management based on the anomaly scores of different frequency bands, accelerating the hopping rate on the abnormal frequency band or temporarily blocking the frequency band to ensure the stability and security of communication.

[0058] Through the signal anomaly detection mechanism of this embodiment, the smart lock has achieved a more accurate anti-cracking ability, capable of accurately identifying potential threats in a complex electromagnetic environment and responding in a timely manner. This mechanism not only improves the security of the system but also enhances the adaptive ability of the system in a dynamically changing environment.

[0059] Embodiment Six To solve the anti-cracking problem of smart locks for multi-band signal analysis in a complex electromagnetic environment, this embodiment further refines the signal anomaly detection mechanism, especially optimizing it for the long-term changes in environmental signals, and proposes a multi-band signal comparison and analysis method based on an environmental baseline signal model. By establishing a dynamically updated environmental baseline signal model, the system can adapt to changes in environmental electrical signals at different time periods and under different weather conditions, and accurately identify abnormal signals through the analysis of real-time signals to prevent cracking attacks.

[0060] As Figure 5 shown, the smart lock anti-cracking method further includes the following steps: S601. Establish an environmental baseline signal model, which contains the normal environmental electrical signal characteristics at different time periods and under different weather conditions.

[0061] S602. Compare the multi-band signals with the environmental baseline signal model in real time to identify abnormal signals.

[0062] S603. Perform clustering analysis on the abnormal signals to classify the abnormal signals with similar characteristics.

[0063] S604. Perform pattern recognition on the classified abnormal signals to determine whether the abnormal signals conform to the characteristics of cracking attempts.

[0064] S605. For abnormal signals that do not conform to the characteristics of cracking attempts, start the learning mechanism, record the characteristics of the abnormal signals, and perform continuous monitoring.

[0065] S606. Regularly update the environmental baseline signal model to adapt to the long-term changes in the environment.

[0066] Specifically, in this embodiment, an environmental baseline signal model is first established, which is based on the characteristics of normal environmental electrical signals collected under different time periods and different weather conditions. The system regularly collects and stores signal data in different environments, and calculates the normal signal ranges and characteristics of each frequency band through statistical methods. These characteristics include parameters such as the average value and standard deviation of the signal, corresponding to different time periods and different weather conditions respectively. It should be understood that this environmental baseline signal model is dynamic and will be continuously updated according to changes in environmental conditions to ensure adaptability to external signal changes during long-term operation.

[0067] Furthermore, during operation, the system compares the multi-band signals collected in real time with the environmental baseline signal model. Through this real-time comparison, the system can quickly identify abnormal signals that do not match the baseline signal characteristics. If parameters such as the frequency band intensity and fluctuation amplitude of the real-time signal deviate significantly from the normal range in the baseline model, it may indicate the presence of an abnormal signal. It can be understood that this real-time comparison can significantly improve the detection accuracy of the system for signal abnormalities and effectively reduce false alarm phenomena.

[0068] Furthermore, for the clustering analysis of abnormal signals. After identifying the abnormal signals, the system further performs clustering analysis on the abnormal signals with similar characteristics. The goal of clustering analysis is to classify abnormal signals with similar properties into a group for further pattern recognition. This process is based on factors such as the frequency band characteristics, intensity fluctuations, and time distribution of the signals, and automatically identifies similar signal patterns through clustering algorithms and classifies them. It should be understood that clustering analysis not only improves the system's processing ability for complex signal environments, but also provides a more accurate data basis for subsequent identification of cracking attempts.

[0069] Furthermore, the system performs pattern recognition on the classified abnormal signals to determine whether these abnormal signals conform to the characteristics of cracking attempts. The process of pattern recognition relies on the pattern library of historical attack behaviors and the anti-cracking logic built into the intelligent lock system. By analyzing the frequency changes, time distribution, and intensity fluctuations of the abnormal signals, the system can determine whether these signals match known cracking attempts. If the system identifies that the abnormal signals conform to the characteristics of cracking attempts, it will immediately trigger corresponding protection measures, such as locking the intelligent lock, triggering an alarm, or accelerating frequency hopping.

[0070] Furthermore, if the classified abnormal signals do not conform to the characteristics of cracking attempts, the system activates the learning mechanism. Through the learning mechanism, the system records the characteristics of these abnormal signals and continuously monitors their subsequent performance. It can be understood that the learning mechanism endows the intelligent lock with the ability of self-learning and optimization, enabling it to continuously improve its protection strategy during long-term use. For abnormal signals that have not been clearly classified, the system will keep monitoring them. Once the characteristics of the signal reappear or change, the system will re-evaluate them to further improve the accuracy and flexibility of protection.

[0071] Furthermore, this embodiment also regularly updates the environmental baseline signal model to adapt to long-term environmental changes. With the changes in seasons, climate fluctuations, and electromagnetic interference in the environment, the system automatically adjusts the parameters of the baseline model to ensure that the baseline model can accurately reflect the current environmental electrical signal characteristics. It can be understood that this dynamic update mechanism can effectively improve the adaptability of the system during long-term operation and ensure the accuracy of the environmental baseline model.

[0072] Through this embodiment, the intelligent lock system not only realizes the real-time analysis and abnormal detection of multi-band signals, but also enhances the adaptability to complex signal environments through the environmental baseline signal model and clustering analysis technology. The pattern recognition and learning mechanism further ensure that the system can make accurate judgments when facing potential cracking threats and continuously optimize the protection strategy when new abnormal signals are identified. The benefits of this embodiment are that through the dynamically updated baseline signal model and flexible protection mechanism, the intelligent lock can maintain a high level of security for a long time, adapt to the changing electromagnetic environment and respond to potential cracking threats in a timely manner.

[0073] Embodiment Seven To solve the protection problem of intelligent locks in the face of complex cracking attempts, this embodiment further refines the analysis and judgment method of abnormal signals. Especially for characteristics such as possible periodic signal emission, multi-band scanning behavior, and concentrated emission of high-energy signals, a multi-level signal analysis mechanism is proposed. Through the multi-dimensional analysis of abnormal signals, this mechanism can accurately identify and judge whether the signal has the characteristics of a cracking attempt, so as to take protective measures in a timely manner.

[0074] As Figure 6 shown, the steps to determine whether an abnormal signal conforms to the characteristics of a cracking attempt include: S701. Analyze the time pattern of the abnormal signal to determine whether there is periodic signal emission.

[0075] S702. Detect the frequency scanning behavior of the abnormal signal to identify whether there is rapid or systematic scanning of multiple frequency bands.

[0076] S703. Evaluate the energy distribution of the abnormal signal to determine whether there is concentrated high-energy signal emission.

[0077] S704. Analyze the modulation characteristics of the abnormal signal to identify whether common digital or analog modulation methods are used.

[0078] S705. Detect whether there is interference or blocking in the normal communication frequency band of the smart lock.

[0079] S706. Determine whether the abnormal signal has the characteristics of imitating the legal communication signal of the smart lock.

[0080] S707. Analyze the complexity of the abnormal signal, evaluate whether it comes from a cracking device, detect whether there is a cooperative pattern of multi-source signals, and determine whether it is an attempt of multi-cracking device collaborative cracking.

[0081] Specifically, after receiving the abnormal signal, this embodiment first analyzes its time pattern. The analysis of the time pattern aims to identify whether the signal has the characteristic of periodic emission. Periodic signals often indicate that the attacker is trying to repeatedly test or capture the communication data of the smart lock for password speculation or other forms of attacks. By statistically analyzing the distribution characteristics of the abnormal signal on the time axis, the system can determine whether it conforms to the pattern of periodic emission. Once a periodic signal emission is detected, the system will immediately raise the alert level and trigger further frequency scanning and energy distribution analysis.

[0082] Furthermore, in the frequency scanning behavior detection, the system monitors whether the abnormal signal involves rapid or systematic scanning of multiple frequency bands. This behavior usually indicates that the attacker is trying to locate the communication frequency band of the smart lock for subsequent attack operations. It should be understood that frequency scanning is usually accompanied by changes in signal strength. Therefore, the system not only monitors the scanning behavior but also comprehensively evaluates it in combination with changes in energy distribution. If it is found that the abnormal signal quickly switches or shows systematic scanning characteristics on multiple frequency bands, the system will determine that it has a high cracking risk and may immediately take countermeasures such as frequency hopping.

[0083] Furthermore, this embodiment also evaluates the energy distribution of the abnormal signal to determine whether there is concentrated high-energy signal emission. Concentrated high-energy signals usually indicate that the attacker is trying to interfere with or block the normal communication of the smart lock by means of power coverage for brute-force cracking or interrupting legal communication. The system can identify such attack behaviors by analyzing the energy distribution characteristics of the signal on each frequency band and adjust the protection strategy of the smart lock accordingly, such as temporarily shielding the interfered frequency band or increasing the transmission power of the legal signal to ensure communication stability.

[0084] Furthermore, the system will also analyze the modulation characteristics of the abnormal signal to identify whether it uses common digital or analog modulation methods. Attackers usually use standard modulation techniques to simulate or replay legitimate communication signals, thus misleading the protection system of the smart lock. By analyzing the modulation mode of the signal, the system can determine whether the signal matches the modulation characteristics of the legitimate signal of the smart lock. If it is found that the modulation method matches and other characteristics also indicate abnormalities, the system will further increase the alert level and may trigger protection measures such as locking or alarming.

[0085] Furthermore, this embodiment also detects whether the abnormal signal interferes with or blocks the normal communication frequency band of the smart lock. Attackers may block the legitimate frequency band by sending interference signals, making the smart lock unable to communicate normally. By real-time monitoring the signal strength and quality of each frequency band, the system can identify whether there is interference behavior and adjust the communication strategy accordingly, such as switching to an alternative frequency band or temporarily increasing the transmission power to ensure the continuity of communication.

[0086] Furthermore, when determining whether the abnormal signal has the characteristics of imitating the legitimate communication signal of the smart lock, the system will judge whether it matches the legitimate signal by analyzing the characteristic parameters of the signal, such as signal waveform, modulation method, frequency stability, etc. Imitation attacks usually involve the precise replication of legitimate signals. Through strict feature comparison, the system can distinguish between legitimate and illegal signals, thus preventing the success of imitation attacks.

[0087] Furthermore, this embodiment also introduces complexity analysis to evaluate whether the abnormal signal comes from a cracking device. The system will judge whether the signal may come from a highly collaborative cracking device group by analyzing the source characteristics, waveform complexity, and modulation method of the signal. Especially in the face of a coordinated attack of multi-source signals, the system can identify the coordinated pattern of the signals, judge whether there is a joint attack attempt by multiple cracking devices, and make a protection response in a timely manner.

[0088] Through this embodiment, the smart lock system can comprehensively analyze the abnormal signal from multiple dimensions such as time pattern, frequency scanning, energy distribution, modulation characteristics, communication interference, signal imitation, and signal complexity. The multi-level signal analysis mechanism of this embodiment improves the system's ability to identify cracking attempts and can maintain a high level of security in a complex signal environment.

[0089] Embodiment Eight To solve the problem of abnormal recognition of smart locks in the face of complex user behavior patterns, this embodiment further refines the anti-cracking method based on user behavior analysis. By recording the user's unlocking behavior, including the authentication time point, duration, and authentication method used for successful unlocking, a user behavior model is established, thereby improving the accuracy and response ability of the smart lock in detecting abnormal behaviors.

[0090] As shown Figure 7 below, the anti-cracking method further includes the following steps: S801. Record the authentication time point, duration, and authentication method used for successful unlocking.

[0091] S802. Analyze the user's unlocking time pattern and establish a user behavior model.

[0092] S803. Record the user's geographical location information and associate the geographical location information with the unlocking behavior.

[0093] S804. Detect abnormal unlocking attempts, including frequent failed attempts or unconventional authentication time points, durations, and authentication methods.

[0094] S805. Analyze the user behavior pattern in combination with environmental factors.

[0095] S806. When an operation significantly deviating from the normal user behavior pattern is detected, raise the vigilance level and require additional identity verification.

[0096] S807. Allow the user to set behavior rules, where the behavior rules include prohibiting unlocking during a set time period or requiring dual authentication.

[0097] Specifically, in this embodiment, a user behavior pattern analysis module is integrated into the intelligent lock system. This module first establishes a detailed unlocking behavior database by recording the time point, duration, and authentication method used for each successful unlocking by the user, such as fingerprint, password, mobile phone NFC, etc. It should be understood that the collection of these data is long-term, and the system continuously records the unlocking behavior according to different time periods and geographical locations to ensure a comprehensive understanding of the user's daily unlocking habits.

[0098] Furthermore, based on these data, the system establishes the user's unlocking time pattern through algorithms. For example, the system can identify when and where the user usually uses the intelligent lock for unlocking operations, and summarize the frequency, duration, and authentication method of these unlocking operations into typical behavior patterns. This user behavior model will be continuously improved over time, enabling the system to distinguish normal behavior from potential abnormal behavior.

[0099] Furthermore, this embodiment particularly introduces the correlation analysis of geographical location information. The intelligent lock system can record the geographical location at each unlocking and correlate it with the user's unlocking behavior. The introduction of geographical location information enables the system to identify the unlocking frequency and patterns of the user at specific locations. For example, if the intelligent lock detects that the user's geographical location is far away, it raises the vigilance level; conversely, if the user's geographical location is close, it lowers the vigilance level. It can be understood that the combination of geographical location information and behavior patterns helps the system to more accurately identify potential risky operations.

[0100] Furthermore, the system will automatically detect and mark abnormal unlocking attempts, especially frequent failed unlocking operations or unlocking operations at unconventional time points. For example, if the intelligent lock receives multiple unlocking requests during a period when the user usually does not use it and these requests fail multiple times, the system will determine that this behavior may be a cracking attempt and take corresponding protective measures in a timely manner. In addition, the system can also analyze in combination with the methods used for each authentication, such as fingerprint authentication, password input, etc., to identify whether there are uncommon combinations of authentication methods or abnormal authentication durations.

[0101] Furthermore, this embodiment also combines environmental factors, such as public holidays or special events, for more refined analysis of user behavior patterns. The system can automatically identify public holidays or other special events and dynamically adjust the expected patterns of user behavior according to the particularity of these time periods. For example, during holidays, users may not use the intelligent lock frequently, and the system will correspondingly adjust the sensitivity to abnormal behavior. This mechanism ensures that the intelligent lock can still maintain vigilance against potential abnormal behavior in special environments.

[0102] Furthermore, when the system detects an operation that significantly deviates from the user's normal behavior pattern, it will automatically raise the vigilance level and require additional identity verification. The additional verification methods may include security measures such as mobile phone verification codes and two-factor authentication to ensure the true identity of the user. In extreme cases, the system can trigger the locking function to temporarily disable the unlocking operation of the intelligent lock until the user completes the additional identity verification.

[0103] In addition, this embodiment allows users to set personalized behavior rules. For example, users can set that unlocking operations are prohibited during certain specific time periods, or require two-factor authentication during specific time periods, such as only fingerprint authentication during the day on weekdays, while both fingerprint and password two-factor authentication are required at night. This flexible rule setting further enhances the security and user experience of the intelligent lock. Users can define specific behavior rules according to their own living habits and security needs to maximize the protection efficiency of the lock in actual applications.

[0104] Through this embodiment, the intelligent lock system can comprehensively identify potential abnormal operations based on various data such as user behavior patterns, geographical locations, and environmental factors in a complex and changeable environment. At the same time, through behavior rule setting and additional identity verification, the system can ensure effective protection even in special situations. The intelligent lock can not only adapt intelligently to the daily usage habits of users but also flexibly respond to abnormal behaviors, enhancing overall security. The benefit of this embodiment is that by combining user behavior patterns, geographical locations, and environmental factors, the intelligent lock can maintain a high level of security in a changeable usage environment, reduce false alarms, and effectively respond to complex cracking attempts.

[0105] Embodiment Nine To address the detection and protection problems of potential cracking threats in the existing intelligent lock system in the face of a complex electromagnetic environment, this embodiment proposes an intelligent lock anti-cracking system based on multi-band signal analysis. As Figure 8 shown, by integrating a multi-band signal receiving module 100, a spectrum analysis module 200, a matrix construction module 300, a feature extraction module 400, a threat judgment module 500, and a protection control module 600, the system can detect potential cracking threats in real time and take protective measures promptly when necessary.

[0106] Specifically, this embodiment introduces a multi-band signal receiving module 100 for collecting electromagnetic signals in the environment where the intelligent lock is located. This module can collect various electromagnetic signals including environmental noise, device communication signals, and potential attack signals through receivers of multiple frequency bands, such as broadband antennas or multi-band receiving chips. It should be understood that signals of different frequency bands often have different characteristics, and attackers may use specific frequency bands for cracking operations. Therefore, the multi-band signal receiving module 100 needs to have the capabilities of high sensitivity and wide-band coverage to ensure that it can capture electromagnetic signals in a wide range.

[0107] Furthermore, the collected electromagnetic signals will be transmitted to the spectrum analysis module 200, which is responsible for performing spectrum analysis on these signals and generating spectrograms. The spectrum analysis module 200 converts the received time-domain signals into frequency-domain signals through algorithms such as Fourier transform to generate spectrograms. These spectrograms can reflect the signal intensity distribution of each frequency band in the environment. It can be understood that the results of spectrum analysis directly affect subsequent feature extraction and threat judgment. Therefore, the spectrum analysis module 200 needs to have high computational accuracy and real-time processing capabilities.

[0108] Furthermore, this embodiment also includes a matrix construction module 300, which constructs a multi-dimensional spectrum matrix based on the generated spectrogram. This matrix not only records the signal strength of each frequency band, but also can construct a more complex multi-dimensional matrix structure by introducing parameters such as the time dimension and signal fluctuations. Through this matrix representation, the system can more intuitively analyze the changes of signals in the time and frequency dimensions, and provide a basis for subsequent time series analysis and feature extraction. It should be understood that the construction of the multi-dimensional spectrum matrix can capture subtle signal changes. Especially in the face of a complex electromagnetic environment, the matrix can help identify signals that are slightly abnormal in frequency or intensity but pose potential threats.

[0109] Furthermore, the feature extraction module 400 performs time series analysis on the constructed multi-dimensional spectrum matrix and extracts the spectrum change features therein. Time series analysis can capture the fluctuation trends and change patterns of signals at different time periods, and these changes are often clues for identifying cracking attempts. For example, an attacker may try to avoid the monitoring mechanism of the smart lock by frequently changing the signal frequency or power. The feature extraction module 400 can provide important basis for subsequent threat judgment by identifying such abnormal spectrum changes.

[0110] Furthermore, in the threat judgment link, this embodiment introduces a threat judgment module 500 to judge whether there is a potential cracking threat based on the extracted spectrum change features. This module identifies potential attack behaviors by comparing abnormal signal features with known cracking patterns, such as frequency scanning, periodic signals, concentrated high-energy signals, etc. It should be understood that the core of the threat judgment module 500 lies in its ability to dynamically adapt to new attack methods, and the built-in threat feature library of the system will be updated continuously over time to ensure that it can cope with evolving cracking technologies.

[0111] Furthermore, when the threat judgment module 500 identifies a potential cracking threat, the protection control module 600 will immediately trigger corresponding protection mechanisms. For example, the system can take measures such as frequency hopping, signal interference, alarm or directly locking the smart lock to prevent the attacker from further cracking the smart lock. The protection control module 600 ensures that the protection measures can be executed quickly and effectively by communicating with the core control unit of the smart lock in real time. It can be understood that the response speed and reliability of the protection control module 600 directly determine the protection effect of the system, so this module needs to have efficient communication capabilities and real-time decision-making capabilities.

[0112] The benefits of this embodiment are that by integrating multiple modules such as multi-band signal reception, spectrum analysis, matrix construction, feature extraction, threat judgment, and protection control, the system can analyze the signal changes in the electromagnetic environment in real time from multiple dimensions and take effective protection measures in a timely manner when detecting potential threats. In particular, through the construction of a multi-dimensional spectrum matrix and time series analysis, the system can accurately identify complex cracking attempts and dynamically adjust the protection strategy according to the actual situation, thereby effectively improving the anti-cracking ability of the intelligent lock.

[0113] Embodiment Ten To address the deficiencies of existing intelligent lock anti-cracking systems in terms of frequency band weight adjustment, dynamic frequency adaptation, and adaptive learning, this embodiment further optimizes the signal analysis and protection mechanisms of the anti-cracking system, such as Figure 8 As shown, this embodiment introduces a frequency band correlation analysis, dynamic frequency adjustment, and adaptive learning module 900 to cope with complex cracking attempts and continuously improve the protection performance of the system.

[0114] Specifically, the frequency band correlation analysis module 700 is used to calculate the correlation coefficients between signals in different frequency bands. Through frequency band correlation analysis, the system can identify the signal dependence relationships between different frequency bands. For example, in some cracking attempts, an attacker may transmit signals simultaneously on multiple frequency bands and use the correlation between the frequency bands for a joint attack. The frequency band correlation analysis module 700 can identify these hidden correlated signals by calculating the correlation coefficients between each frequency band. According to the magnitude of the correlation coefficients, the system can dynamically adjust the weights of different frequency bands so that in the protection strategy, the frequency bands with higher weights can obtain higher monitoring priorities and resource allocations. It should be understood that this dynamic weight adjustment can effectively enhance the system's protection ability against multi-band joint attacks.

[0115] Furthermore, to enhance the system's adaptability in the face of dynamic threats, this embodiment introduces a dynamic frequency adjustment unit 800, which is integrated into the protection control module 600. The main function of the dynamic frequency adjustment unit 800 is to dynamically adjust the signal reception frequency band according to the threat situation detected in real time. Specifically, when the system detects a high cracking risk on a specific frequency band, the dynamic frequency adjustment unit 800 can automatically reduce the signal reception frequency of that frequency band or temporarily block that frequency band to prevent the system from being continuously attacked. In addition, this unit can also automatically adjust the reception frequencies of other frequency bands according to the characteristics of the attack behavior, such as the modulation method and frequency switching mode of the attack signal, so as to effectively avoid cracking behaviors. It should be understood that this dynamic frequency adjustment mechanism can not only enhance the protection flexibility of the system but also ensure the system's adaptability in the face of a complex electromagnetic environment.

[0116] Furthermore, this embodiment particularly introduces an adaptive learning module 900, which is used to dynamically adjust system parameters according to historical data. Through the analysis of historical data, the adaptive learning module 900 can continuously optimize the working parameters of the system to adapt to the changing electromagnetic environment and the evolving cracking technologies. This module adopts an adaptive learning rate adjustment algorithm, and its learning rate calculation formula is:

[0117] where η(t) is the learning rate of the system at time t, η0 is the initial learning rate, and β and γ are adjustable parameters that control the rate of decrease of the learning rate. Through this learning rate adjustment formula, the system can dynamically adjust the learning speed according to the actual situation, ensuring that the system can quickly learn and adjust the protection strategy when facing new types of attacks, and gradually reduce the learning rate in a relatively stable environment to maintain the stability and efficiency of the system. It can be understood that this adaptive learning mechanism can ensure that the system still has high flexibility and response ability after long-term operation.

[0118] Furthermore, the adaptive learning module 900 can not only optimize the core parameters of the threat judgment module 500 and the protection control module 600, but also dynamically adjust the weight of the frequency band correlation analysis and the response strategy of the dynamic frequency adjustment unit 800 according to different types of cracking behaviors. For example, when the system faces frequent signal interference attacks, the adaptive learning module 900 can continuously accumulate the characteristic data of the interference signals and adjust the signal reception sensitivity and frequency hopping strategy, thereby enhancing the system's resistance to interference attacks. Through this dynamic adaptive adjustment, the system can gradually enhance its ability to resist new cracking attempts.

[0119] It should be understood that the learning rate adjustment and parameter optimization processes of the adaptive learning module 900 are both automatically performed without user intervention. This not only improves the system's autonomous learning ability but also ensures that the system can maintain the best protection state in different environments. At the same time, the design of the adaptive learning module 900 can also be adjusted according to the security requirements and usage habits set by the user for personalization, further enhancing the system's adaptability.

[0120] The advantage of this embodiment is that the intelligent lock anti-cracking system can achieve precise analysis and dynamic response of multi-band signals in a complex electromagnetic environment. By introducing the frequency band correlation analysis module 700, the dynamic frequency adjustment unit 800, and the adaptive learning module 900, the system can effectively cope with multi-band joint cracking attempts and maintain high protection performance after long-term operation.

Claims

1. An anti-cracking method for intelligent locks based on multi-band signal analysis, characterized in that, The method includes the following steps: Continuously collect electromagnetic signals in the environment through the multi-band receiver of the smart lock; Perform spectral analysis on the collected multi-band signals to generate a spectrogram; Construct a multi-dimensional spectral matrix using the spectrogram; Perform time series analysis on the multi-dimensional spectral matrix to extract spectral change features; Based on the extracted spectral change features, determine whether there is a potential cracking threat; If a potential cracking threat is detected, trigger the protection mechanism of the smart lock; The formula for extracting the spectral change features is: , where V is the spectrum change value, N is the length of the time series, M is the number of frequency bands, and S i,j is the signal intensity of the j-th frequency band at the i-th time point, and w j is the weight coefficient of the j-th frequency band.

2. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 1, wherein, Determine whether there is a potential cracking threat through a dynamic threshold, and the calculation formula for the dynamic threshold is: , where T is the dynamic threshold, μ V is the historical average value of the spectrum change value, σ V is the historical standard deviation of the spectrum change value, k is an adjustable coefficient, Δt is the interval between the current time and the last threat detection time, and τ is the time decay constant.

3. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 2, wherein The method further includes performing correlation analysis on the multi-band signals, calculating the correlation coefficient between frequency bands according to the correlation analysis, and the calculation formula for the correlation coefficient is: , where R ij is the correlation coefficient between the i-th frequency band and the j-th frequency band, S i,t and S j,t are the signal intensities of the i-th and j-th frequency bands at time t, respectively, and are their respective average values.

4. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 1, wherein The protection mechanism includes dynamic frequency hopping, and the sequence generation formula for the dynamic frequency hopping is: , where f n is the frequency index after the nth jump, f0 is the initial frequency index, a and b are adjustable parameters, and M is the number of available frequencies.

5. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 1, characterized in that, The method further includes identifying signal anomaly patterns using an anomaly score, and the calculation method for the anomaly score is: , where S anom is the anomaly score, S j is the current signal strength of the j-th frequency band, μ j and σ j are the historical average and standard deviation of this frequency band respectively, and k is an adjustable coefficient.

6. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 1, wherein The method further includes the following steps: Establish an environmental baseline signal model, which contains the normal environmental electrical signal characteristics under different time periods and different weather conditions; Compare the multi-band signals with the environmental baseline signal model in real time to identify abnormal signals; Perform cluster analysis on the abnormal signals to classify the abnormal signals with similar characteristics; Perform pattern recognition on the classified abnormal signals to determine whether the abnormal signals conform to the cracking attempt characteristics; For the abnormal signals that do not conform to the cracking attempt characteristics, start a learning mechanism, record the characteristics of the abnormal signals, and perform continuous monitoring; Regularly update the environmental baseline signal model to adapt to the long-term changes in the environment.

7. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 6, characterized in that The step of determining whether the abnormal signals conform to the cracking attempt characteristics includes: Analyze the time pattern of the abnormal signals to determine whether there is periodic signal emission; Detect the frequency scanning behavior of the abnormal signals to identify whether there is rapid or systematic scanning of multiple frequency bands; Evaluate the energy distribution of the abnormal signals to determine whether there is concentrated high-energy signal emission; Analyze the modulation characteristics of the abnormal signals to identify whether common digital or analog modulation methods are used; Detect whether there is interference or blocking of the normal communication frequency band of the smart lock; Determine whether the abnormal signals have the characteristics of imitating the legal communication signals of the smart lock; Analyze the complexity of the abnormal signals, evaluate whether they come from cracking devices, detect whether there is a cooperative pattern of multi-source signals, and determine whether it is an attempt of multi-cracking device cooperative cracking.

8. The intelligent lock anti-cracking method based on multi-band signal analysis according to claim 1, characterized in that, The method further includes the following steps: Record the authentication time point, duration, and authentication method used for successful unlocking; Analyze the user's unlocking time pattern and establish a user behavior model; Record the user's geographical location information and associate the geographical location information with the unlocking behavior; Detect abnormal unlocking attempts, including frequent failed attempts or unconventional authentication time points, durations, and authentication methods; Analyze the user behavior pattern in combination with environmental factors; When an operation that significantly deviates from the normal user behavior pattern is detected, raise the vigilance level and require additional authentication; Allow users to set behavior rules, which include prohibiting unlocking during a set time period or requiring dual authentication.

9. An intelligent lock anti-cracking system based on multi-band signal analysis, characterized in that, The system includes: A multi-band signal receiving module for collecting electromagnetic signals in the environment; A spectrum analysis module for performing spectrum analysis on the collected electromagnetic signals and generating a spectrogram; A matrix construction module for constructing a multi-dimensional spectrum matrix based on the spectrogram; A feature extraction module for performing time series analysis on the multi-dimensional spectrum matrix to extract spectrum change features; A threat judgment module for judging whether there is a potential cracking threat based on the extracted spectrum change features; A protection control module for triggering corresponding protection mechanisms when a potential cracking threat is detected.

10. The intelligent lock anti-cracking system based on multi-band signal analysis according to claim 9, wherein The system further includes A frequency band correlation analysis module for calculating the correlation coefficient between signals of different frequency bands and adjusting the weights of each frequency band according to the correlation coefficient; A dynamic frequency adjustment unit integrated in the protection control module for dynamically adjusting the signal receiving frequency band according to the detected threat situation; And an adaptive learning module for dynamically adjusting system parameters according to historical data. The learning rate calculation formula of the adaptive learning module is: , where η(t) is the learning rate at time t, η0 is the initial learning rate, and β and γ are adjustable parameters.

Images