AR glasses case anti-theft method, system, electronic device and storage medium

Abstract

An AR glasses case anti-theft method, system, electronic device and storage medium, relating to the field of data processing. In this method, biometric information, geographic location, first time information and ambient light intensity are obtained; the regional theft risk coefficient is calculated based on the geographic location and first time information, and the biometric verification failure threshold is determined according to the regional theft risk coefficient; the biometric information is verified through a preset feature database; when the number of verification failures reaches the biometric verification failure threshold, a graded alarm is activated according to the ambient light intensity; environmental image data and audio data are synchronously collected, and an encrypted evidence package is generated in combination with the geographic location; the encrypted evidence package is divided into multiple data blocks, and the multiple data blocks are sent to a mobile terminal bound to the AR glasses case. By implementing the technical solution provided in this application, an AR glasses case anti-theft method that adapts to environmental risks and has an intelligent alarm mechanism and terminal linkage can be obtained.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to an anti-theft method, system, electronic device, and storage medium for an AR glasses case. Background Art

[0002] With the breakthrough development of augmented reality (AR) technology, AR glasses have evolved from conceptual devices to consumer-grade smart terminals. Their lightweight design and immersive interactive capabilities have enabled them to quickly become popular in industries such as industry, medical care, and education.

[0003] Current mainstream AR glasses anti-theft technology relies primarily on biometric verification (such as fingerprint and facial recognition) combined with GPS tracking. Existing technologies typically pre-set fixed verification processes and thresholds (e.g., a fixed number of retries). However, their core authentication mechanisms exhibit significant rigidity. This static verification logic lacks adaptability across different scenarios, making it difficult to flexibly enhance security levels or promptly block potential threats, resulting in a low overall security redundancy. Summary of the Invention

[0004] In order to obtain an AR glasses case anti-theft method that can solve the rigid verification mechanism in traditional solutions, the present application provides an AR glasses case anti-theft method, system, electronic device and storage medium.

[0005] In a first aspect of the present application, a method for preventing theft of an AR glasses case is provided, specifically comprising:

[0006] Obtain biometric information, geographic location, first time information and ambient light intensity;

[0007] calculating a regional theft risk coefficient based on the geographic location and the first time information, and determining a biometric verification failure threshold according to the regional theft risk coefficient;

[0008] Verifying the biometric information using a preset feature database;

[0009] When the number of verification failures reaches the biometric verification failure threshold, a graded alarm is activated according to the ambient light intensity;

[0010] Synchronously collecting environmental image data and audio data, and generating an encrypted evidence package in combination with the geographic location;

[0011] The encrypted evidence package is divided into multiple data blocks, and the multiple data blocks are sent to the mobile terminal bound to the AR glasses box.

[0012] By adopting this technical solution, the regional theft risk coefficient is dynamically calculated by integrating geographic location and real-time information. The number of biometric verification failures allowed is intelligently adjusted accordingly, achieving an adaptive balance between security and user experience. When the verification failure threshold is reached, a graded alarm mechanism is activated based on ambient light intensity (audio and light warning in strong light environments, vibration reminder in low light environments, and multi-mode linkage in mixed environments), deterring theft while avoiding nighttime disturbances. This also triggers encrypted evidence collection, associating environmental images and audio data with geographic location and timestamps, packaging them into data blocks, and transmitting them to the user's mobile terminal, forming an unalterable distributed chain of evidence. This ensures traceability while mitigating the risk of privacy leaks in the cloud. This effectively addresses the technical issue of rigid verification mechanisms in existing technologies.

[0013] Optionally, calculating a regional theft risk coefficient based on the geographic location and the first time information includes:

[0014] Obtaining historical theft event frequency data from a pre-set regional security database associated with the geographic location;

[0015] A time risk weight factor is determined according to the first time information, and the regional theft risk coefficient is obtained by weighted calculation based on the time risk weight factor combined with the historical theft event frequency data.

[0016] By adopting the above-mentioned technical solution, dynamic data in the temporal and spatial dimensions are incorporated into the risk assessment model, breaking through the limitations of traditional static thresholds. The system can automatically adjust the risk factor based on the historical patterns of theft in a specific area and current time characteristics (such as day and night differences, holiday factors), thereby providing a more accurate quantitative basis for the dynamic setting of subsequent biometric verification thresholds, significantly improving the adaptability and response sensitivity of anti-theft strategies to different scenarios.

[0017] Optionally, determining a biometric verification failure threshold according to the regional theft risk coefficient includes:

[0018] Inputting the regional theft risk coefficient into a preset threshold mapping function to obtain a preliminary threshold;

[0019] Calculating a behavior risk coefficient based on the user's historical usage habits, including the average number of verification attempts and usage time patterns;

[0020] The behavior risk coefficient and the preliminary threshold are weighted and calculated to obtain the biometric verification failure threshold.

[0021] By adopting the above technical solutions, firstly, based on the preliminary threshold generation mechanism of the regional theft risk coefficient, through the spatiotemporal correlation analysis of geographic fence data and crime heat map, the security strategy can automatically adapt to different scenarios (such as reducing the threshold by 30% at night in commercial areas and increasing the protection level by 20% in residential areas during the early morning hours), significantly enhancing environmental adaptability; secondly, the user behavior profiling engine analyzes historical usage data through machine learning to construct a multi-dimensional behavior baseline that includes characteristics such as the fluctuation curve of biometric verification frequency and time preference distribution, enabling the system to distinguish between normal operation fluctuations (such as repeated verification caused by user discomfort) and abnormal attack behavior, thereby reducing the false alarm rate; finally, through the adaptive weighting algorithm, environmental risks and individual behavior characteristics are integrated to establish a dynamic decision surface. While maintaining the security strength of high-risk areas, the verification fault tolerance rate of conventional usage scenarios is improved, forming a three-in-one intelligent protection system that can effectively resist brute force attacks while avoiding the user experience gap caused by fixed thresholds, achieving the best balance between security protection and user convenience.

[0022] Optionally, when the number of verification failures reaches the biometric verification failure threshold, initiating a graded alarm according to the ambient light intensity includes:

[0023] If the ambient light intensity is lower than a preset first intensity threshold, control the speaker of the AR glasses box to play an alarm sound and control the LED light to flash;

[0024] If the ambient light intensity is higher than a preset second intensity threshold, controlling the linear motor of the AR glasses box to vibrate and controlling the speaker to play an alarm sound, wherein the first intensity threshold is lower than the second intensity threshold;

[0025] If the ambient light intensity is between the first intensity threshold and the second intensity threshold, the speaker is controlled to play an alarm sound, the LED light is controlled to flash, and the linear motor is controlled to vibrate.

[0026] By adopting the above technical solution, a multimodal alarm decision-making mechanism based on ambient light intensity was constructed, and sound, light, and vibration alarm resources were intelligently allocated for different lighting conditions: in low-light environments, the sound and light combination is prioritized (using sound penetration and LED flashing visual warnings), in strong light environments, emphasis is placed on the coordination of vibration and sound (to compensate for light interference), and medium light triggers full-dimensional alarms, forming a three-dimensional warning network covering all lighting scenes, significantly improving the perceptibility and deterrent effect of alarm signals in complex environments.

[0027] Optionally, the synchronously collecting environmental image data and audio data and generating an encrypted evidence package in combination with the geographic location includes:

[0028] Collecting the environmental image data through the camera of the AR glasses box, and collecting the audio data through the microphone of the AR glasses box;

[0029] Associating and packaging the environmental image data, the audio data, the geographic location, and the second time information of the current moment to obtain packaged data;

[0030] The packaged data is encrypted using a preset encryption algorithm to generate the encrypted evidence package.

[0031] By adopting the above technical solutions, spatiotemporal information (geographic location, timestamp) and environmental data (images, audio) are deeply integrated to form a three-dimensional evidence chain with tamper-proof characteristics: the timestamp ensures the temporal validity of the evidence, the geographic location provides a spatial anchor point, and the encryption algorithm ensures the security of data transmission. This solves the problems of evidence fragmentation and easy tampering in traditional solutions, and provides complete evidence support with legal effect for subsequent tracing or device tracking. At the same time, the block encryption transmission mechanism further improves the reliability and anti-attack capability of data in complex network environments.

[0032] Optionally, the method further includes:

[0033] When the verification is successful, continuously detecting the in-place status of the AR glasses in the AR glasses box and the straight-line distance between the mobile terminal and the AR glasses box;

[0034] When the in-place state is in-place and the straight-line distance exceeds a preset safety threshold, the motor on the AR glasses box is driven to close the AR glasses box, and an early warning is sent to the mobile terminal.

[0035] By adopting the above technical solution, the reliability of anti-theft in daily use scenarios is significantly improved, targeting the high-frequency risk scenario where the user temporarily leaves the AR glasses and forgets to close the glasses case. By continuously detecting the presence status of the AR glasses and the real-time distance from the mobile terminal, the system can accurately identify the abnormal state of "glasses in the case but the user has left". This solution is particularly suitable for temporary placement scenarios such as desks and coffee shops. By predicting user behavior patterns and actively intervening in the protection process, it effectively solves the risk of device exposure caused by negligence, and upgrades the anti-theft strategy from post-accountability to pre-emptive prevention, greatly reducing the probability of AR glasses being lost due to users temporarily forgetting to use them, while maintaining the convenience of device use.

[0036] Optionally, after the verification is successful, the continuously detecting the in-place status of the AR glasses and the straight-line distance between the mobile terminal and the AR glasses box includes:

[0037] Pairing the AR glasses box and the AR glasses through a device identifier;

[0038] Continuously monitoring the presence status of the AR glasses paired with the AR glasses case according to a presence detection sensor in the AR glasses case;

[0039] The signal strength between the AR glasses box and the mobile terminal is obtained, and the straight-line distance is calculated based on the signal strength and a preset signal attenuation model.

[0040] By adopting the above technical solutions, a real-time monitoring system based on device identity binding and multi-sensor fusion has been established: Device identifiers are used to uniquely pair the AR glasses with their case, ensuring accurate status monitoring. In-situ detection sensors (such as Hall elements and pressure sensors) capture the physical connection status in real time to prevent abnormal device separation. Distance measurement based on signal strength and attenuation models upgrades traditional Bluetooth monitoring to precise distance measurement based on physical models, resolving misjudgments caused by signal fluctuations. This multi-layered monitoring mechanism not only improves the reliability of device status perception but also provides a solid data foundation for subsequent proactive protection strategies (such as abnormal distance triggering lid closure), forming a complete closed loop from identity authentication to status monitoring to risk response.

[0041] In a second aspect of the present application, an AR glasses case anti-theft system is provided, specifically comprising:

[0042] A data acquisition module is used to obtain biometric information, geographic location, first time information and ambient light intensity;

[0043] a data processing module, configured to calculate a regional theft risk coefficient based on the geographic location and the first time information, and determine a biometric verification failure threshold according to the regional theft risk coefficient;

[0044] A feature matching module, configured to verify the biometric information using a preset feature database;

[0045] an alarm module, configured to initiate a graded alarm according to the ambient light intensity when the number of verification failures reaches the biometric verification failure threshold;

[0046] an encryption module for synchronously collecting environmental images and audio data and generating an encrypted evidence package in combination with the geographic location;

[0047] A data transmission module is used to divide the encrypted evidence package into multiple data blocks and send the multiple data blocks to the mobile terminal bound to the AR glasses box.

[0048] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs any of the methods described above.

[0049] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions. When the instructions are executed, any one of the methods described above is executed.

[0050] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0051] By integrating geographic location and time information to build a regional theft risk assessment model, the biometric verification failure threshold is dynamically adjusted to achieve an intelligent balance between protection strength and user experience; a hierarchical alarm mechanism based on ambient light intensity links sound, light, and vibration multi-modal warning methods to enhance the perceptibility and deterrence of alarms in different scenarios while avoiding disturbing the public; spatiotemporal information and environmental data are encrypted, associated, packaged, and transmitted in blocks to form an unalterable distributed chain of evidence to ensure judicial traceability and data security; through multi-level monitoring of device binding, on-site detection, and signal models, the box lid is automatically closed and an early warning is issued in abnormal scenarios, moving the anti-theft line of defense from post-response to pre-prevention; the modular system architecture decouples each functional module, giving the system flexible scalability and hardware adaptability, and reserving interfaces for subsequent technical upgrades. The overall solution effectively solves problems such as rigid verification mechanism, single alarm method, incomplete evidence chain, lack of active protection, and insufficient system scalability in traditional anti-theft solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a schematic diagram of the system architecture of an embodiment of an AR glasses case anti-theft method or system applying the present application;

[0053] Figure 2 This is a flow chart of an AR glasses case anti-theft method disclosed in an embodiment of the present application;

[0054] Figure 3 This is a module diagram of an AR glasses case anti-theft system disclosed in an embodiment of the present application;

[0055] Figure 4 This is a structural diagram of an electronic device disclosed in an embodiment of the present application.

[0056] Explanation of the accompanying drawings: 301, data acquisition module; 302, data processing module; 303, feature matching module; 304, alarm module; 305, encryption module; 306, data transmission module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0058] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0059] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0060] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0061] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as model training applications, video recognition applications, web browser applications, social platform software, etc.

[0062] Terminal devices 101, 102, and 103 can be hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3) players, MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers, and desktop computers, etc. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules (for example, multiple software or software modules used to provide distributed services), or they can be implemented as a single software or software module. No specific limitation is made here.

[0063] This embodiment discloses an anti-theft method for AR glasses case. Figure 2 This is a flow chart of an AR glasses case anti-theft method disclosed in an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps:

[0064] S201. Obtain biometric information, geographic location, first time information, and ambient light intensity.

[0065] Specifically, the biometric data input by the user is captured in real time through the biometric collection component on the surface of the AR glasses box (such as a fingerprint recognition module and an iris scanning device). The component has a built-in optical sensor and a signal processing unit, which can reduce noise and extract features from the collected raw data such as fingerprint texture and iris pattern; the current geographic location information is obtained by using a satellite positioning device (such as GPS, Beidou) integrated in the AR glasses box or in a mobile terminal bound to it. The device calculates the latitude and longitude coordinates and altitude by receiving signals from multiple satellites; the precise current time information is obtained through the system's built-in clock or network time synchronization protocol to ensure the accuracy of the timestamp; the ambient light sensing device (such as a photosensor) is used to collect ambient light intensity data in real time. The device can convert optical signals into electrical signals and output digital quantities through an analog-to-digital conversion circuit. Finally, the data collection unit synchronously integrates the above-mentioned biometric data, geographic location coordinates, time information and ambient light intensity values ​​into the data cache for subsequent processing flow calls.

[0066] S202: Calculate a regional theft risk coefficient based on the geographic location and the first time information, and determine a biometric verification failure threshold according to the regional theft risk coefficient.

[0067] Specifically, the acquired geographic coordinates are first matched against a pre-set regional security database, which stores historical theft distribution data for different geographic regions. A spatial interpolation algorithm (such as Kriging interpolation) is then used to estimate the historical theft frequency at the current location. Simultaneously, a time risk weight factor is matched from a pre-set time risk weight table based on current time information (such as time of day, day of the week, and holiday attributes). This weight factor characterizes the theft risk probability at different time periods (e.g., nighttime has a higher weight than daytime). The historical theft frequency and the time risk weight factor are weighted and summed to obtain a regional theft risk coefficient (ranging from 0 to 1). Subsequently, the risk coefficient is divided into multiple intervals using a pre-set threshold mapping rule, each corresponding to a different biometric verification failure threshold (e.g., a low-risk interval corresponds to a higher failure threshold, while a high-risk interval corresponds to a lower failure threshold). This rule is trained using a machine learning algorithm using historical theft data and verification failure records, thereby dynamically adjusting the verification fault tolerance based on real-time risk.

[0068] Optionally, calculating a regional theft risk coefficient based on the geographic location and the first time information includes:

[0069] Obtaining historical theft event frequency data from a pre-set regional security database associated with the geographic location;

[0070] A time risk weight factor is determined according to the first time information, and the regional theft risk coefficient is obtained by weighted calculation based on the time risk weight factor combined with the historical theft event frequency data.

[0071] Specifically, the system first integrates security data from multiple sources, including public theft alarm records, incident reports from commercial security service platforms, insurance company theft and robbery claims, and geotagged safety tips from social media and local forums. The system then structures this raw information, using semantic analysis to identify and extract key information from the text, such as the type of incident, specific time of occurrence, and coordinate location. The system then maps discrete incident locations onto a unified geographic grid system, calculates the historical frequency of incidents within each grid cell at an hourly granularity, and constructs a three-dimensional risk matrix based on date types (e.g., weekdays, weekends, and holidays), creating a refined electronic map covering the target area. To ensure data timeliness and integrity, the system automatically updates official police alarm data daily and utilizes an intelligent crowdsourcing mechanism. When the device is stationary, it collects ambient audio features, such as siren sound spectra, as auxiliary data for risk warnings. To calculate spatial risk, the system uses a co-kriging algorithm, incorporating geographic parameters such as road density and nighttime light intensity, to estimate the risk of the target location. The algorithm integrates the distribution of historical events within a 500-meter radius and performs weighted interpolation calculations. For areas with insufficient data coverage, the system fills in the gaps through transfer learning of historical data from similar areas, ensuring the integrity of the risk heat map. Ultimately, the system generates a dynamic risk heat map with a resolution of 50 meters by 50 meters. This heat map not only reflects the long-term security situation in the region but also captures real-time risk fluctuations. From this heat map, historical theft frequency data for each geographic grid cell can be extracted, providing an accurate data foundation for subsequent regional theft risk coefficient calculations and dynamic verification strategy adjustments.

[0072] Furthermore, the system first parses the current time information and extracts key elements such as hours, week types, and holiday attributes. Based on these elements, the system queries the preset time risk weight table, which is pre-set by analyzing the time distribution pattern of historical theft data. For example, the whole day is divided into 24-hour periods and assigned different weight values. In a typical configuration, the weight of the late night period (0:00-6:00) is set to 0.7, the early morning to early morning (6:00-8:00) is 0.6, the daytime period (8:00-18:00) is the baseline value of 0.4, and the evening to late night (18:00-24:00) is 0.5. At the same time, the weekend weight is increased by 20%, and an additional 10% risk bonus is added on holidays. After obtaining the time risk weight factor corresponding to the current time, the system weights it with the historical theft frequency data of the target area. The system adopts a normalized weighted model: let the time risk weight factor be W t , the historical frequency value is f h , then the calculation formula of regional theft risk coefficient R is:

[0073]

[0074] in f t is the time-related risk value (obtained by querying the preset time-risk mapping table, such as the nighttime risk value is set to 0.8), f h The historical theft frequency data obtained in the previous step (e.g., an average of 0.05 times / hour in a certain area over the past three months). For example, if the current time is late at night (W t =0.7, f t =0.8), and the regional historical frequency f h =0.05, then the calculation result is: R=0.7×0.8+0.3×0.05=0.56+0.015=0.575.

[0075] Optionally, determining a biometric verification failure threshold according to the regional theft risk coefficient includes:

[0076] Inputting the regional theft risk coefficient into a preset threshold mapping function to obtain a preliminary threshold;

[0077] Calculating a behavior risk coefficient based on the user's historical usage habits, including the average number of verification attempts and usage time patterns;

[0078] The behavior risk coefficient and the preliminary threshold are weighted and calculated to obtain the biometric verification failure threshold.

[0079] Specifically, the nonlinear mapping function stored in the security policy database is first called. This function adopts the form of modified hyperbolic tangent function (a mathematical function with an S-shaped curve that can smoothly map input values ​​to a limited output range). The mathematical expression of the threshold mapping function f(x) is: , where x is the regional theft risk coefficient normalized to the range of 0 to 1. The function parameters are based on a dataset of 100,000 historical theft events and biometric verification failure thresholds (the dataset includes geographic location grid codes, theft event times, and the daily average verification failure thresholds for the corresponding regions). They are obtained through iterative optimization using the Levenberg-Marquardt algorithm (a nonlinear optimization algorithm). The optimization objective is to minimize the mean squared error between the predicted threshold and the actual observed value. When the server executes the calculation, the risk coefficient value is read from memory, and the mathematical operation unit completes the hyperbolic tangent calculation. The calculation process of the function expression is implemented through multiplication and addition operations. Finally, the initial verification failure threshold is output as an integer after rounding, achieving a stable conversion from risk coefficient to operational threshold. (Typical examples include outputting the threshold once for a risk coefficient input of 0.15, three times for an input of 0.60, and four times for an input of 0.92).

[0080] Furthermore, the historical operation records of the last 30 days were extracted from the user behavior database to calculate the average daily number of verification attempts (defined as the total number of daily biometric verifications divided by the number of valid use days) and the frequency of use during non-common periods (the proportion of verification operations from 23:00 to 05:00 the next day local time). The average daily number of verification attempts was compared with the preset safety benchmark value (the system configuration is 1.2 times / day), and the deviation of the number of attempts was calculated (formula: deviation = min (average number of daily user attempts / safety benchmark value, 3.0)). At the same time, the frequency of use during non-common periods was multiplied by The time period risk coefficient (preset to 2.5) generates the time period risk factor; ultimately, the user-specific risk value is calculated using the weighted formula: behavior risk coefficient = 0.7 × attempt number deviation + 0.3 × time period risk factor. The weight coefficient is determined based on an analysis of 100,000 user behavior data (deviation contributes 70% of high-risk users). The calculation result is written to the memory cache for the threshold correction module to call (a typical example is when the user has an average of 2.5 attempts per day and unused time periods account for 20%: deviation = 2.08, time period risk factor = 0.5, and risk coefficient = 1.606).

[0081] Furthermore, the behavioral risk coefficient and the preliminary threshold are multiplied, and the calculated result is integerized: when the decimal part is ≥ 0.5, it is rounded up, otherwise it is rounded down; the integerized result is limited to the preset safety range [minimum threshold 2 times, maximum threshold 6 times], and if it exceeds the range, it is forcibly set to the boundary value; the processed integer is written to the security policy register as the final effective threshold (typical implementation example: when the preliminary threshold is 3 times and the behavioral risk coefficient is 1.6, the calculated value is 4.8, which is rounded to 5 times; if the preliminary threshold is 4 times and the risk coefficient is 2.1, the calculated value is 8.4, and it is forcibly set to 6 times if it exceeds the upper limit).

[0082] S203: Verify the biometric information through a preset feature database.

[0083] Specifically, deep learning models, such as a facial encoding network based on a modified ResNet-50 (50-layer residual network architecture) or a lightweight fingerprint recognition model, are used to generate encrypted, stored, and transmitted using homomorphic encryption. During verification, the system retrieves the target user's registration template from a distributed database, which is stored on physically isolated nodes using hash sharding and requires dynamic token authentication for access. The comparison process uses a two-stage protocol: first, cosine similarity is used to quickly screen candidate sets with similarity exceeding a threshold (e.g., 0.7). A support vector machine (SVM) is then used for secondary discrimination to prevent forgery attacks. The system dynamically adjusts its policy based on the regional risk level: low-risk areas allow single-modal verification (e.g., facial recognition only), medium-risk areas enable dual-modal fusion (facial + fingerprint), and high-risk areas require mandatory trimodal cross-validation with a 0.95 match threshold for all modalities. The entire process runs in the Trusted Execution Environment (TEE) built by the Hardware Security Module (HSE), and regularly updates and optimizes model parameters through cloud-based threat intelligence to ensure protection against emerging attack methods.

[0084] S204: When the number of verification failures reaches the biometric verification failure threshold, a graded alarm is initiated according to the ambient light intensity.

[0085] Specifically, when the number of biometric verification failures reaches a preset threshold, the system detects the light intensity in real time through the ambient light sensor. If the intensity is lower than the first intensity threshold (such as a dark environment), the speaker of the AR glasses box is triggered to play an alarm sound and synchronously drive the LED light to flash to enhance the warning effect; if the intensity is higher than the second intensity threshold (such as a strong light environment), the linear motor vibration is activated in conjunction with the speaker alarm, reducing environmental noise interference through tactile and auditory dual prompts; when the light intensity is between the two, the system activates three alarm modes simultaneously to ensure that effective warnings can still be provided under complex lighting conditions. All alarm strategies are dynamically adapted based on preset hierarchical thresholds. The first and second thresholds are calibrated through historical environmental data to balance power consumption and response intensity.

[0086] Optionally, when the number of verification failures reaches the biometric verification failure threshold, initiating a graded alarm according to the ambient light intensity includes:

[0087] If the ambient light intensity is lower than a preset first intensity threshold, control the speaker of the AR glasses box to play an alarm sound and control the LED light to flash;

[0088] If the ambient light intensity is higher than a preset second intensity threshold, controlling the linear motor of the AR glasses box to vibrate and controlling the speaker to play an alarm sound, wherein the first intensity threshold is lower than the second intensity threshold;

[0089] If the ambient light intensity is between the first intensity threshold and the second intensity threshold, the speaker is controlled to play an alarm sound, the LED light is controlled to flash, and the linear motor is controlled to vibrate.

[0090] Specifically, when the ambient light intensity falls below a preset first intensity threshold, a light sensor integrated into the AR glasses (such as a photoresistor or the TSL2571 digital ambient light sensor) captures real-time light data at a 100Hz sampling rate. A sliding window filtering algorithm is then used to eliminate transient interference and obtain a stable light intensity value. When the detected value falls below the first threshold (e.g., 50 Lux, corresponding to a low-light environment), the microcontroller immediately triggers an alarm process: a command is sent to the audio decoder chip via the I2C interface (Integrated Circuit Bus), driving the embedded speaker to play an alarm tone at a preset frequency (e.g., 2kHz). Simultaneously, a PWM (Pulse Width Modulation) signal is output via the GPIO port (General Purpose Input / Output) to control the LED driver circuit, causing the LED to flash at a 1Hz frequency. To ensure effective warning, the alarm tone uses a graded volume strategy: 80dB for the first three seconds. If no user intervention (such as re-authentication or cancellation) is detected, the volume automatically increases to 95dB and remains until manually terminated. The LED flashing mode is also configured as a 50% duty cycle square wave drive to prevent overheating caused by prolonged high brightness. The entire process ensures a response delay of less than 50ms through task priority scheduling of the RTOS (Real-Time Operating System). After the alarm is triggered, it continuously monitors changes in ambient light and automatically downgrades to low-power monitoring mode if the light intensity rises above the first threshold.

[0091] Furthermore, when the ambient light intensity exceeds a second threshold (e.g., 500 Lux, corresponding to bright sunlight), the microcontroller immediately initiates the alarm process: it sends a command to the audio decoder chip via the I2C interface, driving the embedded speaker to play a highly penetrating alarm tone at a preset frequency (e.g., 3kHz). Simultaneously, it outputs a PWM signal through the GPIO (General-Purpose Input / Output) port to control the linear motor driver circuit, causing the motor to vibrate at a frequency of 150Hz. To ensure effective warning, the alarm tone uses a graded volume strategy, initially outputting at 85dB. If no user intervention (such as re-authentication or cancellation) is detected within 10 seconds, the volume automatically increases to 100dB and remains until manually terminated. The linear motor's vibration mode is configured as a 50% duty cycle square wave drive to avoid excessive power consumption caused by prolonged, high-intensity vibration. The entire process ensures response latency below 30ms through task priority scheduling within the real-time operating system. After the alarm is triggered, the system continuously monitors ambient light changes. If the light intensity drops below the second threshold, the system automatically downgrades to a low-power monitoring mode, while retaining vibration feedback to accommodate noisy environments.

[0092] Furthermore, when the ambient light intensity falls within a preset mid-range (e.g., between 50 Lux and 500 Lux), the microcontroller immediately initiates a complex alarm process: It sends commands to the audio decoder chip, LED driver circuit, and linear motor driver module via the I2C (Inter-Integrated Circuit) interface, driving the embedded speaker to play an alarm tone at a preset frequency (e.g., 2.5 kHz), flashing the LED at 2 Hz, and activating the linear motor to vibrate at 100 Hz. To ensure effective warnings, the alarm tone uses a graded volume strategy, initially outputting at 80 dB. If no user intervention (e.g., re-authentication or cancellation) is detected within 5 seconds, the volume automatically increases to 95 dB and remains until manually terminated. The LED flashing mode is configured as a 60% duty cycle square wave drive to balance visibility and power consumption. The linear motor's vibration intensity is dynamically adjusted using a PWM signal to prevent overheating caused by prolonged high-intensity vibration. The entire process ensures that the delay of multi-component collaborative response is less than 40ms through task priority scheduling of the real-time operating system (RTOS), and continuously monitors changes in ambient light after the alarm is triggered. If the light intensity exceeds the middle range, the alarm mode is automatically adjusted. At the same time, a triple warning mechanism is retained to adapt to user perception needs under complex lighting conditions.

[0093] S205: Synchronously collect environmental image data and audio data, and generate an encrypted evidence package in combination with the geographic location.

[0094] Specifically, synchronous collection is started within 500 milliseconds after the alarm is triggered. The camera captures 1080P resolution environmental images (H.264 encoding), and the microphone collects 48kHz / 16bit environmental audio (AAC encoding). The two are aligned through hardware-level timestamps; the real-time geographic location obtained by Beidou / GPS dual-mode positioning (converted to Geohash-7 encoding) is encapsulated into a raw data packet according to a predefined binary protocol; the national secret SM4 algorithm is used to encrypt the data packet (the key is generated based on the device ID), and the generated encrypted evidence package is written into the temporary storage area.

[0095] Optionally, the synchronously collecting environmental image data and audio data and generating an encrypted evidence package in combination with the geographic location includes:

[0096] Collecting the environmental image data through the camera of the AR glasses box, and collecting the audio data through the microphone of the AR glasses box;

[0097] Associating and packaging the environmental image data, the audio data, the geographic location, and the second time information of the current moment to obtain packaged data;

[0098] The packaged data is encrypted using a preset encryption algorithm to generate the encrypted evidence package.

[0099] Specifically, within 500 milliseconds of an alarm being triggered, the AR glasses' built-in camera captures real-time 1080P image data (using an H.264 encoder for frame-level compression). Simultaneously, the AR glasses' directional microphone array collects audio data at a 48kHz sampling rate and 16-bit depth (using an AAC-LC encoder for real-time compression). The image and audio data streams generate a unified, high-precision timestamp using a shared hardware clock source (with an accuracy of ±1ms), ensuring strict cross-modal data alignment. During this process, the AR glasses' integrated Beidou / GPS dual-mode positioning chip acquires real-time latitude and longitude coordinates and converts them into Geohash-7 encoding (with an accuracy of approximately ±12 meters). These three types of data are encapsulated into raw data packets according to a predefined binary protocol. The packet header contains a 4-byte synchronization flag (0x53415242) and an 8-byte nanosecond timestamp. The main body contains, in that order, a 12-byte Geohash location code, H.264 I-frame keyframe data (with a 4-byte length marker), and AAC audio frame data (with a 4-byte length marker). After packaging, the data packet is encrypted using the national SM4 algorithm in CTR mode. The encryption key is derived from the device's unique ID via the SM3 hash function. The encrypted evidence packet is then written to the pre-allocated encrypted storage partition of the AR glasses' eMMC flash memory chip. A SHA-256 checksum is also generated and written to the end of the packet.

[0100] Furthermore, based on the hardware-level master timestamp, a synchronization marker header (including time reference, frame sequence number and associated audio block index) is embedded in each frame of image data, the audio stream is sliced ​​according to a fixed duration and marked with the corresponding timestamp and slice length, and the geographic location information is bound to the dual time reference to generate an encrypted location certificate; the above elements are packaged in sequence through a predefined protocol: the protocol identifier and version information are written at the starting position, and then the encrypted location certificate is added, and the video frame sequence with synchronization marks and the audio slice sequence with timestamps are filled in turn. Finally, the package body is attached with an anti-tampering check code generated by the time reference, media data feature value and location certificate to form a complete data packet with strict time and space alignment. Its structure has a built-in anti-disassembly check mechanism to ensure that data relevance is inseparable.

[0101] Furthermore, through the preset SM4 encryption engine, a dynamic key derived from the device's unique identifier is used as the encryption seed to perform group encryption operations on the packaged binary data stream; the encryption process adopts a counter mode to ensure independent obfuscation of data blocks, and synchronously injects signed integrity check vectors to generate an indivisible evidence package containing encrypted content and verification mechanism, which is finally written into the secure storage area and marked with a judicial evidence identification.

[0102] S206: Divide the encrypted evidence package into multiple data blocks, and send the multiple data blocks to the mobile terminal bound to the AR glasses box.

[0103] Specifically, the encrypted evidence package generated above is divided into data blocks of equal size (the last block is automatically filled with a random number to the standard length) according to the preset judicial evidence storage protocol, and a verification header containing the block sequence number, the total number of blocks and the package characteristic value is added to the header of each data block; the block data is pushed to the bound mobile terminal in sequence through the dual-channel communication module built into the AR glasses box (low-latency Bluetooth link is preferred), and the transmission process adopts a secondary encryption handshake mechanism: when the mobile terminal receives the first block, it returns the dynamically generated session public key, and all subsequent data blocks are encrypted block by block using the SM2 algorithm using the public key, and a chain verification code generated based on the hash value of the previous block is attached to ensure that the integrity and order of the block transmission cannot be tampered with; the mobile terminal verifies the chain association of the data blocks in real time. If it fails continuously, the AR glasses box retransmission mechanism is triggered until all blocks are received and reorganized into the original encrypted evidence package.

[0104] Optionally, the method further includes:

[0105] When the verification is successful, continuously detecting the in-place status of the AR glasses in the AR glasses box and the straight-line distance between the mobile terminal and the AR glasses box;

[0106] When the in-place state is in-place and the straight-line distance exceeds a preset safety threshold, the motor on the AR glasses box is driven to close the AR glasses box, and an early warning is sent to the mobile terminal.

[0107] Specifically, after the biometric verification is successful, the AR glasses box continuously monitors the changes in the contact capacitance value of the temple contacts in real time through the embedded capacitive sensor array to determine the status of the AR glasses. At the same time, it uses the Bluetooth low energy protocol to interact with the mobile terminal for directional signals, combines phase difference detection and motion sensor data to dynamically calculate the three-dimensional straight-line distance, and transmits the dual-modal monitoring data to the server analysis system in real time through an encrypted channel.

[0108] Furthermore, when the server determines that the AR glasses remain in place but the mobile terminal's linear distance exceeds a preset safety threshold, it immediately sends a closing command to the AR glasses case. This command activates the worm gear mechanism within the case through the stepper motor drive module, forcing the lid to close within a specified time and triggering the mechanical self-locking mechanism. Simultaneously, an encrypted early warning message (including real-time geographic location, distance offset, and timestamp) is generated and encrypted using the national secret SM4 algorithm. This message is then sent to the mobile terminal via a low-latency communication link, triggering a high-frequency vibration alarm on the terminal and a dynamic fence violation notification on the map interface. The security event is also automatically recorded in the backend to the blockchain audit node. The total time from command issuance to closing the case is controlled within a strict time window, ensuring real-time coordination between physical device security and information warnings.

[0109] Optionally, after the verification is successful, the continuously detecting the in-place status of the AR glasses and the straight-line distance between the mobile terminal and the AR glasses box includes:

[0110] Pairing the AR glasses box and the AR glasses through a device identifier;

[0111] Continuously monitoring the presence status of the AR glasses paired with the AR glasses case according to a presence detection sensor in the AR glasses case;

[0112] The signal strength between the AR glasses box and the mobile terminal is obtained, and the straight-line distance is calculated based on the signal strength and a preset signal attenuation model.

[0113] Specifically, during the device initialization phase, the AR glasses box calls the physical unclonable function (PUF) of the security chip to generate a unique device identifier, and at the same time reads the hardware identifier solidified in the fuse of the AR glasses through the near-field communication (NFC) module; the two parties implement two-way authentication based on the national secret algorithm: the glasses box first generates an SM2 signature challenge frame with a timestamp and sends it to the AR glasses. After the AR glasses verify the validity of the signature, they use the elliptic curve key exchange protocol (ECDH-SM2) to negotiate the session key and return a binding confirmation code encrypted by the key (including two-way identifier cross-verification information). Finally, a secure pairing relationship with the device identifier as the trust root is established at the hardware layer. The binding relationship is written into the device's secure storage area and synchronized to the server's blockchain evidence node, forming an inseparable hardware-level binding relationship.

[0114] Furthermore, after the device binding is completed, the AR glasses box continuously scans the contact capacitance characteristics of the paired AR glasses temple contacts through the built-in matrix capacitive sensor array, and dynamically compares the real-time collected capacitance gradient data with the reference template in the secure binding state (using spatial vector similarity analysis). When a capacitance response mismatch caused by contact detachment, unauthorized displacement or physical impact is detected, the in-place state is immediately determined to be invalid; the monitoring results are converted into encrypted status codes in real time and uploaded to the server, and multi-level responses are triggered synchronously: if the capacitance abnormality continues to reach the threshold, the sound and light alarm is activated, the biometric recognition function is frozen after server verification, and continuous abnormalities drive the worm motor to force the box to close and fuse the key. All monitoring data are transmitted in the form of tamper-resistant encrypted streams to ensure real-time and reliable linkage between physical status and security response.

[0115] Furthermore, the AR glasses box periodically sends directional detection signals through the low-power Bluetooth protocol, and the mobile terminal parses the received signal strength value (RSSI, Received Signal Strength Indication) and carrier phase information and then sends back an encrypted response frame; the glasses box's built-in ranging engine performs dynamic preprocessing on the original signal: filtering out environmental radio frequency interference, and integrating 6-axis motion sensor data to compensate for the impact of device posture on antenna gain; based on a preset path loss model (including a laboratory-calibrated benchmark attenuation value, an environmental attenuation factor dynamically updated by machine learning, and a multipath effect compensation term), the signal flight time is calculated in combination with the carrier phase difference, and finally the real-time straight-line distance with centimeter-level accuracy is output through the three-dimensional space solution engine. This calculation process uses an adaptive calibration mechanism to continuously optimize model parameters to cope with complex environmental changes.

[0116] This embodiment also discloses an AR glasses case anti-theft system. Figure 3 This is a module diagram of an AR glasses case anti-theft method disclosed in an embodiment of the present application. Figure 3 As shown, the system includes:

[0117] Data acquisition module 301, used to obtain biometric information, geographic location, first time information and ambient light intensity;

[0118] A data processing module 302 is configured to calculate a regional theft risk coefficient based on the geographic location and the first time information, and determine a biometric verification failure threshold according to the regional theft risk coefficient;

[0119] A feature matching module 303 is used to verify the biometric information using a preset feature database;

[0120] An alarm module 304 is configured to initiate a graded alarm based on the ambient light intensity when the number of verification failures reaches the biometric verification failure threshold;

[0121] Encryption module 305, for synchronously collecting environmental images and audio data, and generating an encrypted evidence package in combination with the geographic location;

[0122] The data transmission module 306 is used to divide the encrypted evidence package into multiple data blocks and send the multiple data blocks to the mobile terminal bound to the AR glasses box.

[0123] Optionally, the data processing module 302 is specifically configured to:

[0124] Obtaining historical theft event frequency data from a pre-set regional security database associated with the geographic location;

[0125] A time risk weight factor is determined according to the first time information, and the regional theft risk coefficient is obtained by weighted calculation based on the time risk weight factor combined with the historical theft event frequency data.

[0126] Optionally, the data processing module 302 is specifically configured to:

[0127] Inputting the regional theft risk coefficient into a preset threshold mapping function to obtain a preliminary threshold;

[0128] Calculating a behavior risk coefficient based on the user's historical usage habits, including the average number of verification attempts and usage time patterns;

[0129] The behavior risk coefficient and the preliminary threshold are weighted and calculated to obtain the biometric verification failure threshold.

[0130] Optionally, the alarm module 304 is specifically configured to:

[0131] If the ambient light intensity is lower than a preset first intensity threshold, control the speaker of the AR glasses box to play an alarm sound and control the LED light to flash;

[0132] If the ambient light intensity is higher than a preset second intensity threshold, controlling the linear motor of the AR glasses box to vibrate and controlling the speaker to play an alarm sound, wherein the first intensity threshold is lower than the second intensity threshold;

[0133] If the ambient light intensity is between the first intensity threshold and the second intensity threshold, the speaker is controlled to play an alarm sound, the LED light is controlled to flash, and the linear motor is controlled to vibrate.

[0134] Optionally, the encryption module 305 is specifically configured to:

[0135] Collecting the environmental image data through the camera of the AR glasses box, and collecting the audio data through the microphone of the AR glasses box;

[0136] Associating and packaging the environmental image data, the audio data, the geographic location, and the second time information of the current moment to obtain packaged data;

[0137] The packaged data is encrypted using a preset encryption algorithm to generate the encrypted evidence package.

[0138] Optionally, the system further includes a security protection control module 307, specifically configured to:

[0139] When the verification is successful, continuously detecting the in-place status of the AR glasses in the AR glasses box and the straight-line distance between the mobile terminal and the AR glasses box;

[0140] When the in-place state is in-place and the straight-line distance exceeds a preset safety threshold, the motor on the AR glasses box is driven to close the AR glasses box, and an early warning is sent to the mobile terminal.

[0141] Optionally, the security protection control module 307 is specifically configured to:

[0142] Pairing the AR glasses box and the AR glasses through a device identifier;

[0143] Continuously monitoring the presence status of the AR glasses paired with the AR glasses case according to a presence detection sensor in the AR glasses case;

[0144] The signal strength between the AR glasses box and the mobile terminal is obtained, and the straight-line distance is calculated based on the signal strength and a preset signal attenuation model.

[0145] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0146] This embodiment also discloses an electronic device, referring to Figure 4 The electronic device may include: at least one processor 401 , at least one communication bus 402 , a user interface 403 , a network interface 404 , and at least one memory 405 .

[0147] The communication bus 402 is used to implement the connection and communication between these components.

[0148] The user interface 403 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 403 may also include a standard wired interface and a wireless interface.

[0149] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0150] Processor 401 may include one or more processing cores. Using various interfaces and circuits, processor 401 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in memory 405, as well as accesses data stored in memory 405, to perform various server functions and process data. Optionally, processor 401 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). Processor 401 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 401 and implemented as a separate chip.

[0151] Among them, the memory 405 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 405 may also be optionally at least one storage device located away from the aforementioned processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for an AR glasses case anti-theft method.

[0152] exist Figure 4 In the electronic device shown, the user interface 403 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 401 can be used to call an application program storing an AR glasses case anti-theft method in the memory 405. When executed by one or more processors 401, the electronic device executes one or more methods as in the above embodiments.

[0153] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0155] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0156] In addition, the functional units in the various embodiments of the present application can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory 405 and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned memory 405 includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a magnetic disk, or an optical disk.

[0157] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An anti-theft method for an AR glasses case, characterized in that: Applied to a server, the method includes: Obtain biometric information, geographic location, first time information and ambient light intensity; calculating a regional theft risk coefficient based on the geographic location and the first time information, and determining a biometric verification failure threshold according to the regional theft risk coefficient; Verifying the biometric information using a preset feature database; When the number of verification failures reaches the biometric verification failure threshold, a graded alarm is activated according to the ambient light intensity; Synchronously collecting environmental image data and audio data, and generating an encrypted evidence package in combination with the geographic location; Splitting the encrypted evidence package into multiple data blocks, and sending the multiple data blocks to a mobile terminal bound to the AR glasses box; Determining the biometric verification failure threshold according to the regional theft risk coefficient includes: Inputting the regional theft risk coefficient into a preset threshold mapping function to obtain a preliminary threshold; Calculating a behavior risk coefficient based on the user's historical usage habits, including the average number of verification attempts and usage time patterns; The behavior risk coefficient and the preliminary threshold are weighted and calculated to obtain the biometric verification failure threshold.

2. The method according to claim 1, characterized in that Calculating a regional theft risk coefficient based on the geographical location and the first time information includes: Obtaining historical theft event frequency data from a pre-set regional security database associated with the geographic location; A time risk weight factor is determined according to the first time information, and the regional theft risk coefficient is obtained by weighted calculation based on the time risk weight factor combined with the historical theft event frequency data.

3. The method according to claim 1, characterized in that When the number of verification failures reaches the biometric verification failure threshold, initiating a graded alarm according to the ambient light intensity includes: If the ambient light intensity is lower than a preset first intensity threshold, control the speaker of the AR glasses box to play an alarm sound and control the LED light to flash; If the ambient light intensity is higher than a preset second intensity threshold, controlling the linear motor of the AR glasses box to vibrate and controlling the speaker to play an alarm sound, wherein the first intensity threshold is lower than the second intensity threshold; If the ambient light intensity is between the first intensity threshold and the second intensity threshold, the speaker is controlled to play an alarm sound, the LED light is controlled to flash, and the linear motor is controlled to vibrate.

4. The method according to claim 1, wherein The synchronous collection of environmental image data and audio data and the generation of an encrypted evidence package in combination with the geographic location include: Collecting the environmental image data through the camera of the AR glasses box, and collecting the audio data through the microphone of the AR glasses box; Associating and packaging the environmental image data, the audio data, the geographic location, and the second time information of the current moment to obtain packaged data; The packaged data is encrypted using a preset encryption algorithm to generate the encrypted evidence package.

5. The method according to claim 1, wherein The method further comprises: When the verification is successful, continuously detecting the in-place status of the AR glasses in the AR glasses box and the straight-line distance between the mobile terminal and the AR glasses box; When the in-place state is in-place and the straight-line distance exceeds a preset safety threshold, the motor on the AR glasses box is driven to close the AR glasses box, and an early warning is sent to the mobile terminal.

6. The method according to claim 5, characterized in that When the verification is successful, the continuously detecting the in-place status of the AR glasses and the straight-line distance between the mobile terminal and the AR glasses box includes: Pairing the AR glasses box and the AR glasses through a device identifier; Continuously monitoring the presence status of the AR glasses paired with the AR glasses case according to a presence detection sensor in the AR glasses case; The signal strength between the AR glasses box and the mobile terminal is obtained, and the straight-line distance is calculated based on the signal strength and a preset signal attenuation model.

7. An AR glasses case anti-theft system, characterized in that: Specifically include: A data acquisition module is used to obtain biometric information, geographic location, first time information and ambient light intensity; a data processing module, configured to calculate a regional theft risk coefficient based on the geographic location and the first time information, and determine a biometric verification failure threshold according to the regional theft risk coefficient; A feature matching module, configured to verify the biometric information using a preset feature database; an alarm module, configured to initiate a graded alarm according to the ambient light intensity when the number of verification failures reaches the biometric verification failure threshold; an encryption module for synchronously collecting environmental images and audio data and generating an encrypted evidence package in combination with the geographic location; A data transmission module is used to divide the encrypted evidence package into multiple data blocks and send the multiple data blocks to the mobile terminal bound to the AR glasses box. The data processing module is further configured to: Inputting the regional theft risk coefficient into a preset threshold mapping function to obtain a preliminary threshold; Calculating a behavior risk coefficient based on the user's historical usage habits, including the average number of verification attempts and usage time patterns; The behavior risk coefficient and the preliminary threshold are weighted and calculated to obtain the biometric verification failure threshold.

8. An electronic device, characterized in that: The electronic device comprises a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 6 is executed.

Images