Anti-theft method and anti-theft system of electronic equipment

Abstract

The invention provides an anti-theft method and anti-theft system for electronic equipment, and relates to the technical field of equipment theft prevention, and the method comprises the steps: carrying out the magnetic field detection of target electronic equipment through an electromagnetic heterogeneous detection region, and obtaining the dynamic field intensity data of the periphery of the target electronic equipment; performing layered marking on the operation state of the target electronic equipment to obtain a distributed operation identifier of the target electronic equipment during operation control, and determining an elastic alarm gradient of the target electronic equipment during activation of spatial alarm isolation according to the distributed operation identifier and the dynamic field intensity data; performing cooperative verification on the environment entropy state feature to obtain a cooperative confidence path of the target electronic equipment on each environment node, and determining an interaction verification label of the target electronic equipment in the operation environment according to the cooperative confidence path; and performing anti-theft alarm authentication on the target electronic equipment according to the elastic alarm gradient and the interactive verification tag. According to the invention, real-time magnetic field detection alarm can be carried out on the electronic equipment in a complex dynamic environment, so that the anti-theft effectiveness of the electronic equipment is improved.

Description

Technical Field

[0001] This application relates to the technical field of device anti-theft, and more specifically, to an anti-theft method and anti-theft system for electronic devices. Background Art

[0002] Device anti-theft refers to the adoption of a series of technical means and measures aimed at preventing electronic devices from being illegally stolen, tampered with, or accessed without authorization. With the popularization of smart devices and the increasing demand for information security in daily life, the anti-theft of electronic devices has become increasingly important. Device anti-theft methods generally include multiple aspects such as hardware protection, software protection, and environmental monitoring. Hardware protection generally involves physical locking, encrypted storage, and identity authentication, etc., to ensure that the device cannot be easily used or accessed even if it is stolen. Software protection relies on the secure design of the operating system and applications, and adopts technologies such as password protection, behavior analysis, and permission management to limit the usage scope of the device and prevent illegal operations. Environmental monitoring technology uses sensors, positioning systems, magnetic field induction, etc. to monitor the environment around the device in real time. Once abnormal behavior is detected or the device is illegally moved, the system can immediately trigger the alarm or locking function and take timely measures to prevent theft incidents from occurring.

[0003] However, existing anti-theft methods for electronic devices usually rely on simple physical protection and basic identity authentication, are vulnerable to cracking and bypassing, and cannot effectively cope with complex and changing security threats, resulting in the difficulty of accurately identifying the security status of the device when encountering potential risks, making traditional anti-theft methods unable to flexibly adapt to different threat environments, thus unable to monitor the state changes of the device in real time and resulting in insufficient anti-theft effects. Therefore, how to perform real-time magnetic field detection and alarm on electronic devices in a complex dynamic environment to improve the effectiveness of electronic device anti-theft is a problem faced by the industry. Summary of the Invention

[0004] This application provides an anti-theft method and anti-theft system for electronic devices, which can perform real-time magnetic field detection and alarm on electronic devices in a complex dynamic environment to improve the effectiveness of electronic device anti-theft.

[0005] In a first aspect, this application provides an anti-theft method for an electronic device, and the anti-theft method includes the following steps:

[0006] Construct an electromagnetic heterogeneous detection area through an integrated fiber Bragg grating sensing array, and perform magnetic field detection on the target electronic device by the electromagnetic heterogeneous detection area to obtain dynamic field strength data around the target electronic device;

[0007] Use the key in the fiber - optic broadband operation service to hierarchically label the operating state of the target electronic device, obtaining the distributed operation identifier of the target electronic device during operation control. Determine the elastic alarm gradient of the target electronic device when activating space alarm isolation according to the distributed operation identifier and the dynamic field - strength data;

[0008] Collect the environmental entropy - state characteristics of the target electronic device in the operating environment, perform collaborative verification on the environmental entropy - state characteristics, obtain the collaborative confidence path of the target electronic device on each environmental node, and then determine the interactive verification label of the target electronic device in the operating environment from the collaborative confidence path;

[0009] Authenticate the anti - theft alarm of the target electronic device based on the elastic alarm gradient and the interactive verification label.

[0010] In this embodiment, the process of the electromagnetic heterogeneous detection area detecting the magnetic field of the target electronic device to obtain the dynamic field - strength data around the target electronic device specifically includes:

[0011] Circularly arrange multimodal magnetic field sensors around the target electronic device to construct a heterogeneous detection network;

[0012] Extract the characteristics of the electromagnetic heterogeneous detection area through the heterogeneous detection network to obtain the dynamic field - strength data around the target electronic device.

[0013] In this embodiment, the dynamic field - strength data refers to the distribution data of the magnetic field around the target electronic device changing with time.

[0014] In this embodiment, the process of using the key in the fiber - optic broadband operation service to hierarchically label the operating state of the target electronic device and obtain the distributed operation identifier of the target electronic device during operation control specifically includes:

[0015] Based on the dynamic key distribution protocol in the fiber - optic broadband network, establish an associated mapping relationship between the operating state of the target electronic device and the key;

[0016] Extract the behavior feature vector of the target electronic device synchronized with the key period according to the associated mapping relationship;

[0017] Construct a hierarchical labeling evidence deposit through the behavior feature vector;

[0018] Determine the distributed operation identifier of the target electronic device during operation control from the hierarchical labeling evidence deposit.

[0019] In this embodiment, the process of determining the elastic alarm gradient of the target electronic device when activating space alarm isolation according to the distributed operation identifier and the dynamic field - strength data specifically includes:

[0020] Determine the alarm correlation tensor of the target electronic device when activating spatial alarm isolation according to the distribution operation identifier;

[0021] Determine the dynamic risk characteristics when the target electronic device has a running deviation;

[0022] Determine the elastic alarm gradient of the target electronic device when activating spatial alarm isolation from the alarm correlation tensor and the dynamic risk characteristics.

[0023] In this embodiment, collecting the environmental entropy state characteristics of the target electronic device in the operating environment specifically includes:

[0024] Collect the environmental parameters of the target electronic device through a multi-source sensor array;

[0025] Perform a joint time-frequency domain analysis on the environmental parameters to obtain the dynamic fusion information of the target electronic device in the operating environment;

[0026] Determine the environmental entropy state characteristics of the target electronic device in the operating environment according to the dynamic fusion information.

[0027] In this embodiment, the environmental entropy state characteristic refers to the degree of uncertainty in the operating environment of the target electronic device.

[0028] In this embodiment, determining the interactive verification label of the target electronic device in the operating environment from the collaborative confidence path specifically includes:

[0029] Determine the path credibility parameters between the target electronic device and each environmental node according to the collaborative confidence path;

[0030] Bind the credibility parameter to the device operating state characteristic to generate an interactive verification primitive label with a time limit constraint;

[0031] Determine the interactive verification label of the target electronic device in the operating environment according to the interactive verification primitive label.

[0032] In this embodiment, authenticating the anti-theft alarm of the target electronic device based on the elastic alarm gradient and the interactive verification label specifically includes:

[0033] Generate the device security situation value of the target electronic device according to the elastic alarm gradient and the interactive verification label;

[0034] Match the device security situation value with a preset prevention and control strategy library to trigger a gradient authentication challenge mechanism;

[0035] Execute a hierarchical anti-theft strategy according to the response result of the gradient authentication challenge mechanism and the device spatial coordinates.

[0036] In a second aspect, the present application provides an anti-theft system for an electronic device, which is used to execute an anti-theft method for an electronic device. The anti-theft system includes:

[0037] A magnetic field detection module, configured to construct an electromagnetic heterogeneous detection area through an integrated fiber Bragg grating sensing array, perform magnetic field detection on a target electronic device by the electromagnetic heterogeneous detection area, and obtain dynamic field strength data around the target electronic device;

[0038] An operation identification module, configured to hierarchically label the operation state of the target electronic device by using a key in the fiber broadband operation service, obtain a distributed operation identification of the target electronic device during operation control, and determine an elastic alarm gradient of the target electronic device when activating space alarm isolation according to the distributed operation identification and the dynamic field strength data;

[0039] A collaborative verification module, configured to collect environmental entropy state characteristics of the target electronic device in the operating environment, perform collaborative verification on the environmental entropy state characteristics, obtain a collaborative confidence path of the target electronic device at each environmental node, and further determine an interactive verification label of the target electronic device in the operating environment from the collaborative confidence path;

[0040] An alarm authentication module, configured to perform anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interactive verification label.

[0041] The technical solution provided by the embodiments disclosed in the present application has the following beneficial effects:

[0042] Construct an electromagnetic heterogeneous detection area through an integrated fiber Bragg grating sensing array, perform magnetic field detection on a target electronic device by the electromagnetic heterogeneous detection area, and obtain dynamic field strength data around the target electronic device; hierarchically label the operation state of the target electronic device by using a key in the fiber broadband operation service, obtain a distributed operation identification of the target electronic device during operation control, and determine an elastic alarm gradient of the target electronic device when activating space alarm isolation according to the distributed operation identification and the dynamic field strength data; collect environmental entropy state characteristics of the target electronic device in the operating environment, perform collaborative verification on the environmental entropy state characteristics, obtain a collaborative confidence path of the target electronic device at each environmental node, and further determine an interactive verification label of the target electronic device in the operating environment from the collaborative confidence path; perform anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interactive verification label.

[0043] It can be seen that in the present application, the authentication accuracy of anti-theft for electronic devices can be improved; among them, through real-time magnetic field detection and acquisition of dynamic field strength data, the change of the operating environment of the device can be accurately monitored, potential security threats can be discovered in time, and the response ability and adaptability of the device anti-theft system can be enhanced; by combining the operating state of the device with hierarchical marking of keys, more refined security control is achieved, and the security state of the device is evaluated in real time through an elastic alarm gradient, providing a flexible protection response to adapt to the dynamically changing environmental risks; through the collection and collaborative verification of environmental entropy state characteristics, the interaction behavior between the device and the surrounding environment can be deeply analyzed, the risks of the device at different environmental nodes can be accurately identified, the legality of the device behavior can be ensured, and the accuracy of anti-theft authentication can be improved; combining the elastic alarm gradient and interactive verification tags for anti-theft alarm authentication makes the anti-theft authentication of the device more comprehensive and accurate, can respond to potential security threats in real time and execute appropriate protection measures, and improves the security and real-time performance of the overall anti-theft system.

[0044] In summary, the technical solution adopted in the present application can perform real-time magnetic field detection and alarm on electronic devices in a complex dynamic environment to improve the effectiveness of anti-theft for electronic devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 is a flowchart of the anti-theft method for an electronic device provided by the present application;

[0047] Figure 2 is a schematic flowchart of determining the distributed operation identifier provided by the present application;

[0048] Figure 3 is a schematic flowchart of determining the collaborative confidence path provided by the present application;

[0049] Figure 4 is a module structure diagram of the anti-theft system for an electronic device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0051] The embodiments of the present application provide an anti-theft method and an anti-theft system for an electronic device. The core is to construct an electromagnetic heterogeneous detection area by integrating a fiber Bragg grating sensing array, and the electromagnetic heterogeneous detection area performs magnetic field detection on the target electronic device to obtain dynamic field strength data around the target electronic device; use the key in the fiber broadband operation service to hierarchically mark the operating state of the target electronic device to obtain the distributed operation identifier of the target electronic device during operation control, and determine the elastic alarm gradient of the target electronic device when activating the space alarm isolation according to the distributed operation identifier and the dynamic field strength data; collect the environmental entropy state characteristics of the target electronic device in the operating environment, perform collaborative verification on the environmental entropy state characteristics to obtain the collaborative confidence path of the target electronic device at each environmental node, and then determine the interactive verification label of the target electronic device in the operating environment according to the collaborative confidence path; perform anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interactive verification label.

[0052] Embodiment 1. To better understand the above technical solutions, the above technical solutions will be described in detail below with reference to the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 As shown, this figure is an exemplary flowchart of the anti-theft method for an electronic device according to the present embodiment of the present application. The anti-theft method includes the following steps:

[0053] In step S1, an electromagnetic heterogeneous detection area is constructed by integrating a fiber Bragg grating sensing array, and the electromagnetic heterogeneous detection area performs magnetic field detection on the target electronic device to obtain dynamic field strength data around the target electronic device.

[0054] In specific implementation, the electromagnetic heterogeneous detection area can be constructed by integrating a fiber Bragg grating sensing array in the following way: First, lay multi-channel optical fibers in the detection area and periodically write fiber Bragg gratings on the optical fibers. When an external magnetic field acts on the optical fiber, it will cause minute mechanical stress or temperature changes, thereby leading to the drift of the fiber Bragg wavelength. The wavelength change information is obtained in real time by using spectral demodulation or optical interference demodulation, and the corresponding magnetic field intensity distribution is calculated by using a neural network or an optimized regression model. In addition, to improve the detection accuracy and anti-interference ability, multi-point layout and distributed demodulation can be adopted, and the Fourier transform is combined to distinguish the characteristic signals of the target device. The electromagnetic detection area after distinguishing the characteristic signals of the target device is used as the electromagnetic heterogeneous detection area. In other embodiments, other methods can also be used to determine the electromagnetic heterogeneous detection area, which is not limited here.

[0055] It should be noted that in this application, integrating a fiber Bragg grating sensing array means arranging multiple fiber Bragg grating sensors in the optical fiber to achieve distributed high-precision detection and dynamic monitoring of the spatial electromagnetic field; the electromagnetic heterogeneous detection area refers to an area that senses electromagnetic signals of different frequencies and intensities and realizes spatial distributed electromagnetic field monitoring.

[0056] In this embodiment, the magnetic field detection of the target electronic device by the electromagnetic heterogeneous detection area to obtain the dynamic field strength data around the target electronic device can be achieved by the following steps:

[0057] Arrange multi-modal magnetic field sensors in a ring around the target electronic device to construct a heterogeneous detection network;

[0058] Extract features from the electromagnetic heterogeneous detection area through the heterogeneous detection network to obtain the dynamic field strength data around the target electronic device.

[0059] In specific implementation, first, a Hall effect sensor is used to detect DC and low-frequency magnetic field signals for perceiving the constant magnetic field characteristics of the target electronic device. In combination with a fiber Bragg grating magnetic field sensor, the spectral shift generated by the fiber grating under the action of an external magnetic field is utilized to achieve remote and high-precision perception of the electromagnetic environment. Then, magnetic field sensors are arranged in an equidistant circular distribution around the target electronic device to form an all-round and non-blind-zone coverage, so as to improve the spatial detection accuracy. A multi-layer layout method is adopted, that is, sensor arrays are set both in the horizontal plane and the vertical plane, enabling the detection network to perceive magnetic field changes in three dimensions and enhancing the monitoring ability for complex devices. Then, a distributed data acquisition architecture is adopted to transmit the signals of various sensors to the data processing center through a low-latency wireless communication protocol, thus obtaining a heterogeneous detection network. Next, the Kalman filtering algorithm is used to remove the noise in the sensor signals and improve the data stability. The magnetic field signals are decomposed by wavelet transform at multiple scales to extract the characteristic information in different frequency bands, calculate the time series characteristics, including mean, variance, peak value, slope, etc., analyze the magnetic field change trend, use Fourier transform to extract the frequency domain characteristics of the magnetic field signals, analyze the operating state of the target electronic device, and use the interpolation algorithm to reconstruct the spatial magnetic field data to generate a dynamic magnetic field distribution map around the target electronic device, and read the dynamic field strength data from the dynamic magnetic field distribution map.

[0060] It should be noted that in this application, the multi-modal magnetic field sensor refers to a sensor capable of perceiving magnetic field signals in different frequency bands and of different types, including Hall sensors, fluxgate sensors, and fiber Bragg grating magnetic field sensors; the heterogeneous detection network refers to a distributed detection system composed of different types of magnetic field sensors; the dynamic field strength data refers to the distribution data of the magnetic field around the target electronic device changing with time.

[0061] In step S2, a key in the fiber broadband operation service is used to hierarchically mark the operating state of the target electronic device to obtain the distributed operation identifier of the target electronic device during operation control. According to the distributed operation identifier and the dynamic field strength data, the elastic alarm gradient of the target electronic device when activating spatial alarm isolation is determined.

[0062] Preferably, in this embodiment, a key in the fiber broadband operation service is used to hierarchically mark the operating state of the target electronic device to obtain the distributed operation identifier of the target electronic device during operation control. Refer to Figure 2 As shown, this figure is a schematic flowchart of determining the distributed operation identifier in some embodiments of this application. The determination of the distributed operation identifier in this embodiment can be implemented by the following steps:

[0063] In step S21, based on the dynamic key distribution protocol in the fiber broadband network, an association mapping relationship between the operating state of the target electronic device and the key is established;

[0064] In step S22, extract the behavioral feature vector of the target electronic device synchronized with the key period according to the association mapping relationship;

[0065] In step S23, construct a hierarchical labeled evidence deposit through the behavioral feature vector;

[0066] In step S24, determine the distributed operation identifier of the target electronic device during operation control from the hierarchical labeled evidence deposit.

[0067] In specific implementation, first, in the fiber optic broadband network, adopt quantum key distribution (QKD) or a dynamic key protocol based on Diffie-Hellman key exchange to ensure that the key remains dynamically changing within different time windows. The server regularly distributes encryption keys to the target electronic device, and each key period (such as millisecond level, second level) uniquely corresponds to a key; during the operation of the target electronic device, specific characteristics are generated in its electromagnetic signal, power consumption mode, data transmission rate, etc. Adopt time series analysis method to analyze the device operation state and generate corresponding state labels. The server binds the operation state label within each key period with the current key to obtain the association mapping relationship between the operation state of the target electronic device and the key; then, collect multi-dimensional data during device operation, including CPU usage rate, power consumption curve, electromagnetic radiation signal, network traffic, device log, etc., and adopt Gaussian mixture model or principal component analysis for data dimensionality reduction to extract core feature parameters. Adopt the time series sliding window mechanism to extract eigenvalue within each key period to form a time series behavior vector. Then, according to the device operation mode, divide the feature vector into different levels, such as idle mode, normal operation mode, abnormal operation mode, attack mode, etc. Adopt the K-means clustering model for classification, and adopt the hash encryption algorithm to encrypt the feature vector to ensure data integrity. Then, combined with blockchain technology, store the device state of each key period in an immutable distributed ledger to form a traceable evidence deposit, that is, a hierarchical labeled evidence deposit. Finally, combined with Bayesian network and decision tree classifier, calculate the probability distribution of the current operation state of the device according to the historical evidence deposit data, and then adopt a time series database to store the operation identifiers of different time periods to support real-time query and analysis. According to the operation mode of the device, generate corresponding operation state labels, such as "normal operation", "high load operation", "potential anomaly", "malicious attack". Adopt digital signature technology to encrypt the operation identifier, and use the encrypted operation identifier as the distributed operation identifier.

[0068] It should be noted that in this application, the key representation in the fiber - optic broadband operation service; the association mapping relationship represents the one - to - one correspondence between the operation status data of the target electronic device and the key cycle; the behavior feature vector represents the operation status features of the target electronic device within a specific time window; the hierarchical marking evidence storage represents the feature marking information of the target electronic device; the distributed operation identifier represents the element information of the target electronic device during operation status recognition.

[0069] In this embodiment, determining the elastic alarm gradient of the target electronic device when activating the space alarm isolation according to the distributed operation identifier and the dynamic field strength data can be achieved by the following steps:

[0070] Determine the alarm - related tensor of the target electronic device when activating the space alarm isolation according to the distributed operation identifier;

[0071] Determine the dynamic risk characteristics when the target electronic device has an operation deviation;

[0072] Determine the elastic alarm gradient of the target electronic device when activating the space alarm isolation from the alarm - related tensor and the dynamic risk characteristics.

[0073] Specifically, when implementing, first, based on the distributed operation identifier of the target electronic device, such as "normal operation", "abnormal fluctuation", "fault warning", establish a state - alarm relationship matrix, use the hierarchical clustering algorithm to classify devices in different states, determine the similarity between each state, use the third - order tensor decomposition method to model the device state, alarm event, and time series as a tensor structure, and the tensor elements in the tensor structure represent the alarm level of the device at a specific time point and within a specific space range, ensuring that the alarm event has time consistency and space continuity. Combine the Bayesian network to calculate the alarm probability between different device states to form an alarm impact weight matrix, and use the alarm impact weight matrix as the alarm - related tensor. Then, use time - series anomaly detection to monitor the device state change, judge whether an operation deviation occurs, then set a dynamic threshold, calculate the deviation coefficient, and evaluate the severity of the state change. Collect information such as electromagnetic field strength data, device power consumption characteristics, network traffic anomalies, operation logs, etc. to form dynamic risk characteristics. Finally, use a multi - layer perceptron neural network combined with an attention mechanism to calculate the alarm priority under different device states, and set an alarm gradient factor to measure the adjustment range of the alarm level. Combine reinforcement learning to train the optimal alarm response strategy to reduce false alarms and missed alarms, and use the alarm response strategy after reinforcement learning training as the elastic alarm gradient.

[0074] It should be noted that in this application, the alarm correlation tensor represents the alarm mode of the device in different states; the dynamic risk feature refers to the operation information composed of factors such as state deviation, abnormal signal, and fault risk generated during the operation of the target electronic device; the elastic alarm gradient refers to the warning threshold for protecting the electronic device when the operation state of the target electronic device changes.

[0075] In step S3, the environmental entropy state characteristics of the target electronic device in the operating environment are collected, the environmental entropy state characteristics are co-verified, the co-confidence path of the target electronic device on each environmental node is obtained, and then the interaction verification label of the target electronic device in the operating environment is determined from the co-confidence path.

[0076] In this embodiment, the collection of the environmental entropy state characteristics of the target electronic device in the operating environment can be implemented by the following steps:

[0077] Collect the environmental parameters of the target electronic device through a multi-source sensor array;

[0078] Perform a joint time-frequency domain analysis on the environmental parameters to obtain the dynamic fusion information of the target electronic device in the operating environment;

[0079] Determine the environmental entropy state characteristics of the target electronic device in the operating environment according to the dynamic fusion information.

[0080] In specific implementation, first, a variety of sensors such as fiber Bragg grating sensors, microelectromechanical system sensors, gas sensors, and electromagnetic field sensors are adopted to cover the operating environment of the target electronic device. The sensors are arranged according to the spatial distribution optimization algorithm to maximize the comprehensiveness and accuracy of the collected information. A distributed data acquisition architecture is adopted. Through the time synchronization protocol, the data of different sensors have consistent timestamps, and the data is preprocessed through edge computing to reduce transmission delay and improve real-time performance. The preprocessed results are used as the environmental parameters of the target electronic device. Then, the sliding window algorithm is used to extract the short-term change trend of the environmental parameters, and the long short-term memory network is used to predict the short-term fluctuation mode of the environmental parameters to improve the anomaly detection ability. The fast Fourier transform is used to extract the frequency characteristics of the environmental signal and analyze the periodic pattern in the environmental change. Then, combined with wavelet transform for multi-scale feature decomposition to improve the ability to capture signal details. The Kalman filter is used to dynamically fuse the time-domain and frequency-domain analysis results, and the fused results are used as the dynamic fusion information of the target electronic device in the operating environment. Finally, information entropy is used to calculate the uncertainty of the environmental parameters to measure the dynamic complexity of the environment. The linear fitting algorithm is used to evaluate the information richness of multi-sensor data at different time scales to capture the long-term evolution trend of the environmental state. The Markov chain is used to model and predict the transition probability of the environmental state to construct the environmental evolution path. Combined with the adaptive dynamic time warping method, the change pattern of the environmental entropy state characteristics of the target electronic device is analyzed, and the analyzed results are used as the environmental entropy state characteristics.

[0081] It should be noted that in this application, the environmental parameters represent various data of the environment where the target electronic device is located, such as physical quantities such as temperature, humidity, electromagnetic field strength, and air pressure; the dynamic fusion information represents the change situation of the operating environment of the target electronic device; the environmental entropy state characteristics refer to the degree of uncertainty that appears in the operating environment of the target electronic device.

[0082] Preferably, in this embodiment, the environmental entropy state characteristics are collaboratively verified to obtain the collaborative confidence path of the target electronic device at each environmental node. Refer to Figure 3 As shown, this figure is a schematic flow chart of determining the collaborative confidence path in some embodiments of this application. The collaborative confidence path in this embodiment can be implemented by the following steps:

[0083] In step S31, according to the environmental entropy state characteristics, the spatio-temporal collaborative verification information of the target electronic device at each environmental node is determined;

[0084] In step S32, the environmental parameter abnormal nodes are identified through the dynamic weight voting mechanism, and the node confidence score at each environmental node is output;

[0085] In step S33, determine the collaborative path topology of the target electronic device on each environmental node according to the spatio-temporal collaborative verification information;

[0086] In step S34, determine the collaborative confidence path of the target electronic device on each environmental node according to the node confidence score and the collaborative path topology.

[0087] When specifically implemented, first, based on the environmental entropy state characteristics of the target electronic device, use spatio-temporal data processing methods to extract the time-domain and space-domain characteristics of the environmental nodes, and then adopt a spatio-temporal convolutional neural network (ST-CNN) to extract information in the time and space dimensions through convolutional operations to form the spatio-temporal collaborative verification information of each environmental node. Combine the spatio-temporal characteristics through a spatio-temporal graph neural network, establish the behavior patterns of the device on different environmental nodes, and consider the correlation between environmental changes and device states to dynamically update the spatio-temporal state of each node and generate spatio-temporal collaborative verification information. Then, use a dynamic weight voting mechanism to dynamically adjust the weights according to the data inputs of multiple sensor nodes to identify abnormal parameters existing in the environment, associate the abnormal detection of sensor data with the entropy value change of environmental parameters, adopt an isolation forest or local outlier factor algorithm to detect outliers, evaluate the abnormal data of each environmental node, calculate the confidence score of each node, which is weighted and calculated according to the degree of abnormality, spatio-temporal correlation degree and the reliability of the node, and then use a weighted average algorithm to fuse the sensor data to form the final confidence score of each node, that is, the node confidence score. Then, use a graph algorithm to construct the collaborative path topology of the target electronic device on each environmental node. According to the spatio-temporal collaborative verification information, calculate the shortest path or optimal path between environmental nodes according to the spatio-temporal distance and collaborative level between different nodes to form the collaborative path topology of the device. Finally, according to the confidence score of each environmental node, use the weighted summation method to calculate the collaborative confidence path of the target electronic device on each environmental node. Through the analytic hierarchy process, comprehensively consider the confidence score of the node and the collaborative path topology to determine the final collaborative confidence path, that is, obtain the collaborative confidence path of the target electronic device on each environmental node.

[0088] It should be noted that in this application, an environmental node refers to a physical or virtual location with specific functions or roles in the operating environment of the target electronic device; spatio-temporal collaborative verification information refers to the state characteristics of the target electronic device on each environmental node; the node confidence score refers to the reliability of each environmental node; the collaborative path topology represents the collaborative path structure of the target electronic device on different environmental nodes; the collaborative confidence path refers to the collaborative confidence path characteristics of the target electronic device on each environmental node.

[0089] In this embodiment, the interactive verification label of the target electronic device in the operating environment determined by the collaborative confidence path can be implemented by the following steps:

[0090] Determine the path credibility parameters between the target electronic device and each environmental node according to the collaborative confidence path;

[0091] Bind the credibility parameter to the device operating state characteristics to generate an interaction verification primitive label with a time limit constraint;

[0092] Determine the interaction verification label of the target electronic device in the operating environment according to the interaction verification primitive label.

[0093] Specifically, when implementing, use graph algorithms, such as Dijkstra's algorithm, to calculate the shortest path distance between each environmental node and the target electronic device, and calculate the credibility parameters between the target electronic device and each environmental node through weighted calculation of this distance. Combine the confidence score of the path, for example, node confidence and path quality (such as latency, packet loss rate), and calculate the final path credibility parameter through weighted average method, that is, the path credibility parameter between the target electronic device and each environmental node. Then, according to the device operating state characteristics (such as temperature, power consumption, load, etc.), bind the path credibility parameter to the device state data to form a verification primitive label with strong timeliness, and use time series data analysis method to combine the device operating state with the path credibility parameter, establish a state mapping with time as the dimension, and add a time limit constraint when generating the verification primitive label to ensure that the label is valid within a specified time range. Adopt a timestamp mechanism and validity period limit to prevent the label from expiring or being misused, and use the final result as an interaction verification primitive label with a time limit constraint. Finally, summarize and combine the generated interaction verification primitive labels to form a complete interaction verification label. Among them, summarization and combination can encrypt the generated labels through an encryption algorithm to enhance security.

[0094] It should be noted that in this application, the path credibility parameter refers to the quantitative value of the path quality between the target electronic device and the environmental node; the time limit constraint refers to; the interaction verification primitive label refers to the verification basis for the identity and behavior of the target electronic device; the interaction verification label refers to the label for verifying the legality of the identity and behavior of the target electronic device.

[0095] In step S4, perform anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interaction verification label.

[0096] In this embodiment, performing anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interaction verification label can be implemented by the following steps:

[0097] Generate the device security situation value of the target electronic device according to the elastic alarm gradient and the interaction verification label;

[0098] Match the device security situation value with a preset prevention and control strategy library to trigger a gradient authentication challenge mechanism;

[0099] Execute a hierarchical anti-theft strategy based on the response result of the gradient authentication challenge mechanism and the device spatial coordinates.

[0100] When specifically implemented, first, multi-dimensional data fusion technology can be used to weight the elastic alarm gradient and interactive verification tags, that is, the weighted average method or a fusion algorithm (such as Support Vector Machine (SVM)) can be used to generate the security situation value of the device; then, a preset prevention and control strategy library is used, which contains anti-theft strategies for different security situation value ranges. The prevention and control strategy library sets different security response mechanisms according to the security situation value of the device to help evaluate and respond to different security risks. The decision tree algorithm is adopted to match the most suitable prevention and control strategy according to the device security situation value. When the security situation value meets a certain preset threshold range, the gradient authentication challenge mechanism is triggered. This mechanism requires the device to provide further authentication information according to the current security state of the device, such as identity verification or behavior verification. The gradient authentication challenge mechanism verifies the legitimacy of the device through a series of authentication questions, operations or behavior detections to ensure the security of the device in a high-risk environment. Finally, according to the response result of the gradient authentication challenge mechanism, evaluate whether the device has passed the identity and behavior verification. If the device passes the authentication, it enters the normal operation process; if not, more advanced anti-theft measures are triggered; identity authentication can be achieved through multi-factor authentication (such as passwords, fingerprints, behavior recognition, etc.), and behavior verification is analyzed according to the historical behavior pattern of the device to ensure that the device is in a compliant state. Combine the spatial coordinate information of the device (such as GPS positioning, sensor data, etc.) with the authentication result to analyze the specific location and state of the device. Based on the current spatial location and authentication response of the device, execute appropriate hierarchical anti-theft strategies, for example: strengthen anti-theft control in high-risk areas, or implement basic protection measures in low-risk areas. Different levels of anti-theft strategies are adopted according to the authentication response and spatial coordinates of the device. Measures such as permission control, alarm triggering, and access restriction can be used to limit the operation of the device or further detection. In a high-risk state, the device may need to perform more strict identity verification or real-time monitoring measures; in a low-risk state, conventional protection measures are executed.

[0101] It should be noted that in this application, the device security situation value represents an indicator of the current security state of the device; the prevention and control strategy library represents a preset series of security policies for matching corresponding anti-theft measures according to the device security situation value; the gradient authentication challenge mechanism represents a dynamic authentication mechanism triggered based on the device security situation value and the risk situation; the hierarchical anti-theft strategy represents different levels of anti-theft measures determined according to information such as the device authentication result and the spatial coordinate; the spatial coordinate information represents the position data of the device in the physical environment, usually obtained through GPS, sensors or network positioning.

[0102] It can be seen that in this application, the authentication accuracy of electronic device anti-theft can be improved; among them, through real-time magnetic field detection and the acquisition of dynamic field strength data, the change of the device operation environment can be accurately monitored, potential security threats can be discovered in time, and the response ability and adaptability of the device anti-theft system can be enhanced; by combining the operation state of the device with the hierarchical marking of keys, more refined security control can be achieved, and the security state of the device can be evaluated in real time through the elastic alarm gradient, providing a flexible protection response to adapt to the dynamic environmental risks; through the collection and collaborative verification of environmental entropy state characteristics, the interaction behavior between the device and the surrounding environment can be deeply analyzed, the risks of the device at different environmental nodes can be accurately identified, the legality of the device behavior can be ensured, and the accuracy of anti-theft authentication can be improved; combining the elastic alarm gradient and the interactive verification label for anti-theft alarm authentication makes the anti-theft authentication of the device more comprehensive and accurate, can respond to potential security threats in real time and execute appropriate protection measures, and improves the security and real-time performance of the overall anti-theft system.

[0103] In summary, the technical solution adopted in this application can perform real-time magnetic field detection and alarm on electronic devices in a complex dynamic environment to improve the effectiveness of electronic device anti-theft.

[0104] Embodiment 2, this application provides an anti-theft system for an electronic device, refer to Figure 4 As shown, this figure is a module structure diagram of the anti-theft system of the electronic device according to this embodiment of this application. The anti-theft system includes:

[0105] A magnetic field detection module 100, configured to construct an electromagnetic heterogeneous detection area through an integrated fiber Bragg grating sensing array, and perform magnetic field detection on a target electronic device by the electromagnetic heterogeneous detection area to obtain dynamic field strength data around the target electronic device;

[0106] An operation identification module 200, configured to hierarchically mark the operation state of the target electronic device by using keys in the fiber broadband operation service to obtain a distributed operation identification of the target electronic device during operation control, and determine an elastic alarm gradient of the target electronic device when activating spatial alarm isolation according to the distributed operation identification and the dynamic field strength data;

[0107] The collaborative verification module 300 is used to collect the environmental entropy state characteristics of the target electronic device in the operating environment, perform collaborative verification on the environmental entropy state characteristics to obtain the collaborative confidence path of the target electronic device on each environmental node, and then determine the interactive verification label of the target electronic device in the operating environment based on the collaborative confidence path;

[0108] The alarm authentication module 400 is used to perform anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interactive verification label.

[0109] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or a device for realizing the functions specified in multiple blocks.

[0110] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable storage medium, and the storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0111] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

Claims

1. An anti-theft method for electronic equipment, characterized in that: The anti-theft method comprises the following steps: An electromagnetic heterogeneous detection area is constructed by integrating a fiber grating sensor array, and the electromagnetic heterogeneous detection area detects the magnetic field of the target electronic device to obtain dynamic field strength data around the target electronic device; The operating state of the target electronic device is hierarchically marked using the key in the optical fiber broadband operation service to obtain the distributed operation identification of the target electronic device during operation control, and the elastic alarm gradient of the target electronic device when activating the spatial alarm isolation is determined according to the distributed operation identification and the dynamic field strength data; Collecting environmental entropy state characteristics of the target electronic device in the operating environment, collaboratively verifying the environmental entropy state characteristics, obtaining a collaborative trust path of the target electronic device at each environmental node, and then determining an interactive verification tag of the target electronic device in the operating environment from the collaborative trust path; The target electronic device is authenticated for anti-theft alarm according to the elastic alarm gradient and the interactive verification tag.

2. The anti-theft method for electronic equipment according to claim 1, characterized in that: The electromagnetic isomerization detection area performs magnetic field detection on the target electronic device to obtain dynamic field strength data around the target electronic device, specifically including: Arrange multi-modal magnetic field sensors in a ring around the target electronic device to build a heterogeneous detection network; The feature extraction of the electromagnetic heterogeneous detection area is performed through the heterogeneous detection network to obtain dynamic field strength data around the target electronic device.

3. The anti-theft method for electronic equipment according to claim 1, characterized in that: The dynamic field strength data refers to the distribution data of the magnetic field around the target electronic device that changes with time.

4. The anti-theft method for electronic equipment according to claim 1, characterized in that: The key in the optical fiber broadband operation service is used to hierarchically mark the operation status of the target electronic device, and the distributed operation identification of the target electronic device during operation control is obtained, which specifically includes: Based on the dynamic key distribution protocol in the optical fiber broadband network, an association mapping relationship between the operating status of the target electronic device and the key is established; Extracting a behavior feature vector of a target electronic device synchronized with a key period according to the association mapping relationship; Constructing hierarchical tagging evidence through the behavioral feature vector; The hierarchical tag evidence is used to determine the distributed operation identification of the target electronic device during operation control.

5. The anti-theft method for electronic equipment according to claim 1, characterized in that: Determining the elastic alarm gradient of the target electronic device when activating the spatial alarm isolation according to the distributed operation identifier and the dynamic field strength data specifically includes: Determining, according to the distributed operation identifier, an alarm correlation tensor of the target electronic device when spatial alarm isolation is activated; Determine the dynamic risk characteristics of target electronic equipment when it deviates from its operation; The elastic alarm gradient of the target electronic device when spatial alarm isolation is activated is determined by the alarm association tensor and the dynamic risk feature.

6. The anti-theft method for electronic equipment according to claim 1, characterized in that: The environmental entropy characteristics of the target electronic device in the operating environment are collected specifically including: Collect environmental parameters of target electronic equipment through a multi-source sensor array; Performing a joint analysis of the environmental parameters in the time and frequency domains to obtain dynamic fusion information of the target electronic device in the operating environment; The environmental entropy state characteristics of the target electronic device in the operating environment are determined according to the dynamic fusion information.

7. The anti-theft method for electronic equipment according to claim 1, characterized in that: The environmental entropy state characteristic refers to the degree of uncertainty in the operating environment of the target electronic device.

8. The anti-theft method for electronic equipment according to claim 1, characterized in that: Determining the interactive verification tag of the target electronic device in the operating environment by the collaborative trust path specifically includes: Determining path credibility parameters between the target electronic device and each environmental node according to the collaborative trusted path; Binding the credibility parameter with the device operation status feature to generate an interactive verification primitive label with time constraint; The interactive verification tag of the target electronic device in the operating environment is determined according to the interactive verification primitive tag.

9. The anti-theft method for electronic equipment according to claim 1, characterized in that: Performing anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interactive verification tag specifically includes: Generate a device security situation value of the target electronic device according to the elastic alarm gradient and the interactive verification tag; The gradient authentication challenge mechanism is triggered by matching the security situation value of the device with a preset prevention and control strategy library; A hierarchical anti-theft strategy is executed according to the response result of the gradient authentication challenge mechanism and the device space coordinates.

10. An electronic device anti-theft system, used to execute an electronic device anti-theft method according to any one of claims 1 to 9, characterized in that: The anti-theft system comprises: A magnetic field detection module is used to construct an electromagnetic heterogeneous detection area by integrating a fiber grating sensor array, and the electromagnetic heterogeneous detection area performs magnetic field detection on a target electronic device to obtain dynamic field strength data around the target electronic device; An operation identification module, used to hierarchically mark the operation status of the target electronic device using the key in the optical fiber broadband operation service, obtain the distributed operation identification of the target electronic device during operation control, and determine the elastic alarm gradient of the target electronic device when activating the spatial alarm isolation according to the distributed operation identification and the dynamic field strength data; A collaborative verification module is used to collect environmental entropy state characteristics of the target electronic device in the operating environment, perform collaborative verification on the environmental entropy state characteristics, obtain a collaborative trust path of the target electronic device at each environmental node, and then determine the interactive verification label of the target electronic device in the operating environment from the collaborative trust path; The alarm authentication module is used to perform anti-theft alarm authentication on the target electronic device according to the elastic alarm gradient and the interactive verification tag.

Images