Intelligent glasses case based on artificial intelligence and wireless charging control method thereof

Abstract

The invention discloses an intelligent glasses box based on artificial intelligence and a wireless charging control method thereof, and relates to the technical field of intelligent wearable equipment, and the method comprises the steps: generating a cooperative charging strategy matrix in a local network through an equipment group distributed voting mechanism based on an encrypted prediction parameter packet; generating an electromagnetic field focusing parameter configuration table through a time-frequency-space three-dimensional resource allocation scheme based on the cooperative charging strategy matrix and the three-dimensional coordinates of the equipment in the glasses box; the electromagnetic field focusing parameter configuration table drives the programmable coil array to dynamically adjust the charging signal and generate a charging efficiency real-time monitoring curve; and detecting the actual charging efficiency in the charging efficiency real-time monitoring curve, and dynamically generating an increment optimization parameter packet. Through space coordinate mapping and dynamic spectrum isolation in time-frequency-space three-dimensional resource allocation, accurate directional transmission of electromagnetic energy is realized, wireless interference among multiple devices is eliminated, and charging efficiency optimization and compatibility guarantee are achieved.

Description

Technical Field

[0001] The charging device of the present invention more specifically relates to the technical field of smart wearable devices, especially an artificial intelligence-based smart glasses box and its wireless charging control method. Background Art

[0002] In recent years, wearable device charging technology has shown two major development trends: at the hardware level, multi-coil array wireless charging modules optimize device placement tolerance by increasing spatial freedom; at the control strategy level, charging scheduling algorithms based on user behavior predictions analyze historical usage data to establish charging demand models. Existing technologies include adaptive charging systems.

[0003] While existing distributed charging systems incorporate inter-device communication mechanisms, their central node scheduling model suffers from two inherent flaws: First, device behavior verification relies on historical data stored by the central node, which can lead to coordination failures when the central node is offline. Second, the lack of encrypted data transmission makes device status broadcasts vulnerable to man-in-the-middle attacks. These shortcomings directly restrict the real-time responsiveness and security of multi-device wireless charging systems, creating significant bottlenecks in applications requiring high availability, such as medical-grade smart glasses. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an artificial intelligence-based smart glasses box and a wireless charging control method thereof to solve the collaborative failure risk and data transmission man-in-the-middle attack vulnerability problems caused by dependence on the central node.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides an artificial intelligence-based smart glasses case and a wireless charging control method thereof, which includes collecting user operation data and environmental feature vectors, applying a sliding window statistical method to perform probability weighted analysis on recent behavior characteristics, and generating an encrypted prediction parameter package; Based on the encrypted prediction parameter package, a collaborative charging strategy matrix is ​​generated in the local network through a distributed voting mechanism among the device groups; Based on the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case, an electromagnetic field focusing parameter configuration table is generated through a three-dimensional time-frequency-space resource allocation scheme; The electromagnetic field focusing parameter configuration table drives the programmable coil array, dynamically adjusts the charging signal, and generates a real-time monitoring curve for charging efficiency; The actual charging efficiency in the real-time monitoring curve of charging performance is detected, and an incremental optimization parameter package is dynamically generated.

[0007] As a preferred solution of the artificial intelligence-based smart glasses case and its wireless charging control method of the present invention, the user operation data includes the three-dimensional acceleration waveform, operation duration, operation force peak value and operation frequency statistics of the glasses picking and placing action; The environmental feature vector includes a GPS geo-fence tag, a Bluetooth broadcast device battery percentage, an ambient temperature value, an electromagnetic interference intensity index, and a real-time time window identifier.

[0008] As a preferred solution of the artificial intelligence-based smart glasses box and its wireless charging control method of the present invention, the steps of applying the sliding window statistical method to perform probability weighted analysis on recent behavioral characteristics and generating an encrypted prediction parameter package are as follows: The user operation data and the environment feature vector are time-scaled aligned using a hardware timer to generate a behavior-environment fusion dataset. Based on the behavior-environment fusion dataset, the operation frequency value is calculated through the sliding window statistical method, and the probability weighted analysis of recent behavior characteristics is performed to obtain the time period emergency demand index; The time period emergency demand index and the device unique ID are combined into a plaintext data block, which is encrypted and encapsulated through the hardware-level AES-128 encryption engine to generate an encrypted prediction parameter package.

[0009] As a preferred solution of the artificial intelligence-based smart glasses box and its wireless charging control method of the present invention, the steps of generating a collaborative charging strategy matrix in the local network based on the encrypted prediction parameter package through the device group distributed voting mechanism are as follows: Based on the encrypted prediction parameter package, the voting request data frame is broadcast to the collaborative device group through the Bluetooth network, while monitoring the response timeout status and generating a list of devices to respond; Based on the broadcast voting request data frame and the list of devices to be responded to, each collaborative device performs behavior pattern matching verification in the local network and generates a device group verification result table; According to the device group verification result table, the device priority weight is dynamically adjusted through voting confidence, and the collaborative charging strategy matrix is ​​generated in combination with the real-time power status.

[0010] As a preferred solution of the artificial intelligence-based smart glasses case and its wireless charging control method according to the present invention, the steps of generating an electromagnetic field focusing parameter configuration table based on the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case through the time-frequency-space three-dimensional resource allocation scheme are as follows: The spatiotemporal semantic parsing engine is used to parse the emergency charging window period and power allocation instructions in the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case to generate a spatial strategy fusion dataset. Based on the spatial strategy, the data set is integrated and a three-dimensional resource allocation plan is generated through time slot cutting, dynamic frequency band allocation and spatial beam focusing parameter calculation. Based on the three-dimensional resource allocation scheme of time, frequency and space, the beamforming phase angle of the main device is calculated, the frequency hopping timing of the secondary device is configured, the coil drive current parameters are set, and the safety tolerance rules are loaded, and finally integrated into the electromagnetic field focusing parameter configuration table.

[0011] As a preferred solution of the artificial intelligence-based smart glasses case and its wireless charging control method according to the present invention, the electromagnetic field focusing parameter configuration table drives the programmable coil array to dynamically adjust the charging signal and generate a real-time monitoring curve of charging efficiency as follows: The electromagnetic field focusing parameter configuration table drives the programmable coil array and synchronously turns on the backscatter signal receiving circuit to capture the original electromagnetic signal waveform fed back by the device; Extract signal strength, noise, and phase indicators based on the original electromagnetic signal waveform, optimize the charging waveform in real time, and integrate temperature data to generate a performance monitoring package; According to the performance monitoring package, the four-dimensional data stream convergence processor integrates time series data to generate a real-time monitoring curve for charging efficiency.

[0012] As a preferred solution of the artificial intelligence-based smart glasses box and its wireless charging control method according to the present invention, the actual charging efficiency in the real-time monitoring curve of charging efficiency is detected in the following steps: Based on the actual charging efficiency in the real-time monitoring curve of charging efficiency, dynamic comparison is performed on adjacent time slot data to generate abnormal event markers; Based on abnormal event markers, it captures multi-source real-time signals within the abnormal time window, calculates the operating force peak and power fluctuation coefficient, as well as the causal strength of ambient temperature and efficiency changes, and generates a root cause analysis report.

[0013] As a preferred solution of the artificial intelligence-based smart glasses box and its wireless charging control method described in the present invention, the dynamic generation of the incremental optimization parameter package refers to the optimization instruction generator dynamically creating a calibration instruction set based on the root cause analysis report, and adding user prompts at the same time, and encapsulating the calibration instruction set and the user prompt text into an incremental optimization parameter package.

[0014] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the artificial intelligence-based smart glasses box and its wireless charging control method as described in the first aspect of the present invention is implemented.

[0015] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the artificial intelligence-based smart glasses box and its wireless charging control method as described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of this invention are: through encrypted broadcast communication and local behavior verification consensus in the distributed voting mechanism of the device group, a completely decentralized collaborative decision-making network is realized, eliminating the single point of failure risk of the centralized architecture, achieving improved robustness and enhanced anti-tamper security. Through spatial coordinate mapping and dynamic spectrum isolation in the three-dimensional time-frequency-space resource allocation, precise and directional transmission of electromagnetic energy is achieved, eliminating wireless interference between multiple devices, and achieving optimized charging efficiency and guaranteed compatibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 The following is a flow chart of an artificial intelligence-based smart glasses box and its wireless charging control method.

[0019] Figure 2 This is a flowchart for allocating three-dimensional resources in time, frequency and space.

[0020] Figure 3 Flowchart generated for encrypted prediction parameter package.

[0021] Figure 4 Flowchart of the distributed voting mechanism for a group of devices. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0025] Reference Figures 1 to 4 , is an embodiment of the present invention, which provides an artificial intelligence-based smart glasses box and a wireless charging control method thereof, comprising the following steps: S1: Collect user operation data and environmental feature vectors, apply sliding window statistics to perform probability weighted analysis on recent behavior characteristics, and generate an encrypted prediction parameter package; S1.1: User operation data includes the three-dimensional acceleration waveform of the glasses pick-up and put-down actions, operation duration, operation force peak value, and operation frequency statistics; It should be noted that the three-dimensional acceleration waveform of the glasses pick-up and placement action is continuously sampled by a nine-axis sensor to obtain a three-axis spatial motion trajectory. The operation duration records the time difference between the start and end of the complete glasses pick-up and placement action. The peak operation force captures the maximum instantaneous value of the vertical spatial coordinate component during the action. The operation frequency statistics accumulate the frequency of effective glasses pick-up and placement actions within a fixed time period. The output strictly includes the four complete elements of the glasses pick-up and placement action: the three-dimensional acceleration waveform, the operation duration, the peak operation force, and the operation frequency statistics.

[0026] S1.2: The environmental feature vector includes the GPS geofence tag, the battery percentage of the Bluetooth broadcast device, the ambient temperature value, the electromagnetic interference intensity index, and the real-time time window identifier; It should be noted that GPS geofence tags use satellite positioning signals to parse spatial coordinates and then map them to pre-set geographic area classifications. The Bluetooth broadcast device battery percentage intercepts broadcast message data from surrounding Bluetooth devices and decodes power status parameters. A temperature sensor is used to capture the instantaneous physical quantity of heat distribution in the space where the device is located. The electromagnetic interference intensity index quantifies the energy fluctuation level of the RF signal in a specific frequency band. The real-time time window identifier generates periodic time period markers based on a fixed time segment segmentation mechanism. The final output strictly contains the five complete elements: the GPS geofence tag, the Bluetooth broadcast device battery percentage, the ambient temperature value, the electromagnetic interference intensity index, and the real-time time window identifier.

[0027] The geographic area classification uses satellite positioning signals to analyze the current latitude and longitude coordinates of the device, mapping the physical coordinates to a preset discrete geographic grid. The administrative division change data of the Ministry of Civil Affairs is synchronized monthly through the geographic fence management platform to ensure that the regional classification remains synchronized with physical space changes.

[0028] S1.3: Use a hardware timer to align the time scales of user operation data and environment feature vectors to generate a behavior-environment fusion dataset. A hardware timer is used to assign unified time tags to the three-dimensional acceleration waveform, operation duration, operation force peak and operation frequency statistics of the glasses' pick-up and placement actions, as well as the GPS geo-fence tags, Bluetooth broadcast device battery percentage, ambient temperature value, electromagnetic interference intensity index and real-time time window identifier. According to the time tags, the data point time series of the three-dimensional acceleration waveform, operation duration, operation force peak and operation frequency statistics of the glasses' pick-up and placement actions, as well as the GPS geo-fence tags, Bluetooth broadcast device battery percentage, ambient temperature value, electromagnetic interference intensity index and real-time time window identifier, are aligned and fused to form a behavior-environment fusion dataset.

[0029] S1.4: Based on the behavior-environment fusion dataset, calculate the operation frequency value using the sliding window statistical method, perform probability weighted analysis on recent behavior characteristics, and obtain the time period emergency demand index; Based on the behavior-environment fusion dataset, the sliding window statistical method is applied to continuously move time segments to calculate the operation frequency value. The operation frequency value is used as the weight factor to perform probability weighted analysis on recent behavior characteristics, and the probability distribution function is calculated to obtain a quantitative assessment of the urgency. Finally, the time period emergency demand index is obtained as the output result.

[0030] Recent behavioral characteristics specifically include the following four elements: the three-dimensional acceleration waveform of the glasses pick-up and put-down action reflects the changing pattern of the spatial motion trajectory; the operation duration describes the length of time it takes to complete the glasses pick-up and put-down action; the peak force of the operation records the maximum instantaneous value of the vertical spatial coordinate component; and the operation frequency statistics count the number of times the glasses pick-up and put-down action occurs within a fixed time period. All four elements are extracted using sliding window statistics to form the behavioral characteristic analysis benchmark based on temporally adjacent sequence data.

[0031] The formula for calculating the period emergency demand index is: ; in, Indicates the period emergency demand index; Represents the total number of sliding window time segments, that is, the number of discretized time axis slices; Indicates the time segment number, representing the time windows; Indicates the weighting coefficient of the normalized value of the peak value of the operation force, and the setting range is (0.40-0.60); Indicates the The maximum instantaneous value of the vertical spatial coordinate component within the time period is linearly mapped to the interval [0,1]; Indicates the weighting coefficient of the operation frequency statistics value, the setting range is (0.25-0.45); Indicates the The number of glasses picking and placing actions that occur within a time segment; The weighting coefficient representing the dynamic entropy of the three-dimensional acceleration waveform is set in the range of (0.15-0.35); Indicates the motion disorder of the three-dimensional acceleration waveform of the glasses pick-up and put-down action; Indicates the Three-dimensional acceleration waveform of time period; Indicates the first The time decay weight of the reverse time segments.

[0032] S1.5: Combine the time period emergency demand index and the device unique ID into a plaintext data block, perform encryption encapsulation through the hardware-level AES-128 encryption engine, and generate an encrypted prediction parameter package.

[0033] S2: Based on the encrypted prediction parameter package, a collaborative charging strategy matrix is ​​generated in the local network through a distributed voting mechanism of the device group; S2.1: Based on the encrypted prediction parameter package, broadcast the voting request data frame to the collaborative device group via the Bluetooth network, monitor the response timeout status, and generate a list of devices waiting to respond; Based on the encrypted prediction parameter package, a Bluetooth network broadcast transmission operation is initiated, and a complete data copy of the voting request data frame is sent to all members of the collaborative device group. A countdown counter is started to monitor the response status returned by each device. When any device in the collaborative device group fails to return a confirmation message with a valid encrypted signature within a fixed time, this device is marked as unresponsive. The identifiers of all unresponsive devices are summarized to generate a list of devices to be responded and output.

[0034] The response timeout status refers to the communication fault flag triggered when a member of the collaborative device group fails to return a confirmation message with a valid encrypted signature within a fixed time after receiving the voting request data frame on the Bluetooth network. This status actually means that the physical layer wireless link of the target device is interrupted or the application layer protocol stack processing is abnormal, causing the current device to be marked as unreachable.

[0035] S2.2: Based on the broadcast voting request data frame and the list of devices to respond, each collaborative device performs behavior pattern matching verification in the local network and generates a device group verification result table; After receiving the broadcast voting request data frame, each member of the collaborative device group extracts the behavior verification pattern feature vector from the broadcast voting request data frame, compares it with the list of responding devices, locates the specific device unit to be verified, performs a matching calculation within the historical behavior data stored by the device, and records the device identification, matching status, and confidence score for each item to generate a device group verification result table. The output strictly contains the device identification field, matching status field, and confidence field.

[0036] The distributed voting mechanism of the device group means that after receiving the broadcast voting request data frame, each member of the collaborative device group independently performs the verification of the behavioral feature data stored locally, encapsulates the local verification results into a signature data packet and broadcasts it to the device group. Each device verifies the validity and statistically votes on all received signature data packets based on the preset majority rule, and finally generates a distributed voting conclusion report for the device group that includes the device identification, final voting status and group consensus results.

[0037] The preset majority rule means that if and only if the number of devices with the "matching status" field in the signature data packet being "true" is ≥ 50% of the total number of online collaborative devices, the device is deemed to have passed the verification and the "group consensus result" field is output as a valid state.

[0038] S2.3: Based on the device group verification result table, dynamically adjust the device priority weight through voting confidence, and generate a collaborative charging strategy matrix based on the real-time power status.

[0039] According to the device group verification result table, extract the confidence field data in the device group verification result table to calculate the device priority weight update coefficient, and recalibrate the device priority weight value; synchronously collect the real-time power percentage value of the collaborative device group, merge the device priority weight value and the real-time power percentage value, and generate a collaborative charging strategy matrix containing the device ID key value, priority value, target power value, and power allocation ratio field.

[0040] S3: Based on the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case, an electromagnetic field focusing parameter configuration table is generated through a three-dimensional time-frequency-space resource allocation scheme; S3.1: Using the spatiotemporal semantic parsing engine, the collaborative charging strategy matrix and the emergency charging window periods and power allocation instructions in the 3D coordinates of the devices in the glasses case are parsed to generate a spatial strategy fusion dataset. The spatiotemporal semantic parsing engine first extracts the emergency charging window period string and power allocation ratio field value corresponding to the device ID key value in the collaborative charging strategy matrix, and decomposes the time window into the start timestamp and end timestamp through a regular expression syntax tree; it simultaneously parses the three-dimensional coordinate mapping table of the device in the glasses case to accurately locate the spatial coordinates of the target device; and finally fuses and outputs structured records: a spatial strategy fusion dataset consisting of the device ID key value, three-dimensional coordinate point, charging window start timestamp, charging window end timestamp, and power allocation ratio value.

[0041] S3.2: Based on the spatial strategy, the dataset is integrated and a three-dimensional resource allocation plan is generated through time slot cutting, dynamic frequency band allocation, and spatial beam focusing parameter calculation. Based on the spatial strategy fusion dataset, the following process is executed: first, the charging cycle is divided into fixed-length time slot units, continuous time segments are allocated to high-priority devices, and primary frequency band resources are bound at the same time; compensation frequency band resources are allocated to secondary devices in the compensation time window; the horizontal azimuth and vertical pitch angles of the electromagnetic beam are calculated based on the three-dimensional coordinate points in the spatial strategy fusion dataset, and integrated to generate a three-dimensional resource allocation plan containing the time window allocation table field, the frequency band binding list field, and the spatial focusing parameter field.

[0042] Among them, time slot cutting discretizes the charging cycle into fixed-duration basic time units, divides continuous time segments according to the emergency charging window period field in the spatial strategy fusion dataset, locks the main time slot blocks that high-priority devices need to occupy, and divides the compensation time slot windows for secondary devices. The output time window allocation table field records the start and end times of all time slot allocations and the bound device identifiers.

[0043] Dynamic frequency allocation allocates differentiated communication frequency bands based on device priority weights: primary frequency band resources are allocated to primary devices, and non-overlapping compensation frequency band resources are allocated to secondary devices. The frequency band binding list field displays the mapping between bound device identifiers and frequency points, ensuring that the primary / compensation frequency band spacing meets electromagnetic compatibility specifications.

[0044] The spatial beam focusing parameter calculation analyzes the three-dimensional coordinate field of the device, calculates the horizontal azimuth and vertical pitch angle through the spherical coordinate system conversion formula, and outputs the spatial focusing parameter field to record the beam angle parameters of each device, guiding the electromagnetic beam to accurately cover the spatial position of the target device.

[0045] S3.3: Based on the three-dimensional time-frequency-space resource allocation scheme, calculate the beamforming phase angle of the main device, configure the frequency hopping timing of the secondary device, set the coil drive current parameters and load the safety tolerance rules, and finally integrate them into the electromagnetic field focusing parameter configuration table.

[0046] Based on the time-frequency-space three-dimensional resource allocation scheme, the following operations are performed: First, the phase compensation amount of each antenna array unit is deduced according to the numerical value of the main device beam angle in the spatial focusing parameter field, and the phase angle offset matrix is ​​generated through spatial projection component operation; second, the secondary device frequency point value in the frequency band binding list field is extracted, and the high and low frequency point alternating allocation strategy is implemented according to the frequency point bandwidth and priority weight, and the frequency hopping timing sequence with millisecond-level accuracy is constructed in combination with the basic time slot length; third, a segmented mapping strategy is implemented according to the device priority weight value, and the higher weight value maps the driving current level according to the square root curve, and the lower weight value enables linear transition calculation; at the same time, the preset safety tolerance rule library is loaded, covering the four-dimensional constraints of spatial tolerance, spectrum tolerance, energy tolerance and timing tolerance; finally, the four core parameters of phase angle offset matrix, frequency hopping timing sequence, driving current value and real-time tolerance status word are integrated to output a complete electromagnetic field focusing parameter configuration table in the form of a structured form.

[0047] Safety tolerance rules achieve millisecond-level response through hardware circuits: Coil temperature monitoring: NTC thermistor sampling frequency ≥ 1kHz, Standing wave ratio detection: Directional coupler calculates forward / reverse power ratio in real time. When any parameter exceeds the threshold, a safety interrupt is triggered within 3ms. The preset mapping relationship for coil drive current parameters utilizes a hierarchical dynamic rule architecture: first, device priority weights are normalized and converted into standard values ​​ranging from 0 to 1, eliminating dimensional differences between different devices. Second, a baseline current value is calculated based on the device's physical characteristics. Finally, a nonlinear amplification mechanism is used to provide high-priority devices with a disproportionate current boost, ensuring precise distribution of charging energy according to demand. Triple adaptive compensation is also integrated: when the ambient temperature exceeds 30°C, current intensity is automatically attenuated to prevent overheating; when the device's battery level drops below 20%, current is intelligently increased to accelerate charging; and if strong electromagnetic interference is detected, output power is actively suppressed to maintain stability. This mechanism ultimately generates a precise matching table of device IDs and current values, which is directly written into the electromagnetic field focusing parameter configuration table, enabling multi-dimensional dynamic adaptation of charging energy to device status.

[0048] The safety tolerance rule includes two hard constraints: a coil temperature upper threshold and a standing wave ratio (SWR) tolerance threshold. The coil temperature upper threshold enforces the coil surface operating temperature (monitored in real time via an NTC thermistor), while the SWR tolerance threshold constrains the RF reflected power ratio. After the rule is loaded, a validation conditional statement is generated, and the output field records the threshold name and value, ensuring that the device operates within the ISO 60601-2-33 medical safety standard.

[0049] The coil temperature upper threshold serves as a core safety barrier, strictly limiting the maximum operating surface temperature of the coil to 85°C. This operating mechanism, based on a high-precision NTC thermistor real-time monitoring system, captures temperature changes at a sampling rate of 1000 times per second, maintaining a measurement error within ±0.5°C. When the ambient temperature exceeds 30°C, the system automatically activates a temperature compensation mechanism, dynamically lowering the threshold as the ambient temperature rises (by 0.33°C for every 1°C increase), ensuring a safety margin under extreme operating conditions. If a temperature violation is detected, the hardware protection circuit shuts off the power supply within 3 milliseconds, fundamentally eliminating the risk of thermal deformation and burns.

[0050] The VSWR tolerance threshold enforces a maximum 1.5 RF VSWR (equivalent reflected power ratio ≤ 4%). Closed-loop control is achieved through real-time monitoring of the forward-to-reflected wave energy ratio via a directional coupler. When the electromagnetic interference intensity index exceeds 0.4, the threshold is automatically tightened to 1.3 (reflected power ratio ≤ 1.7%) to enhance interference mitigation. Exceeding the threshold triggers a dual protection response, with the impedance matching network immediately initiating adaptive retuning to optimize energy transmission efficiency. The drive current intensity is simultaneously reduced by 30%, effectively suppressing electromagnetic interference (EMI) from RF signal distortion on medical equipment.

[0051] S4: The electromagnetic field focusing parameter configuration table drives the programmable coil array, dynamically adjusts the charging signal, and generates a real-time monitoring curve for charging efficiency; S4.1: The electromagnetic field focusing parameter configuration table drives the programmable coil array and simultaneously activates the backscatter signal receiving circuit to capture the original electromagnetic signal waveform fed back by the device; The electromagnetic field focusing parameter configuration table is transmitted to the programmable coil array control interface, and the phase angle offset matrix parameter items, frequency sequence parameter items, drive current value parameter items and safety tolerance threshold parameter items are loaded; the programmable coil array is driven to activate the dynamic beam focusing mode; at the same time, the high-sensitivity acquisition channel of the backscattered signal receiving circuit is started to capture the original electromagnetic signal waveform fed back by the device, and continuously output the original electromagnetic signal waveform fed back by the device.

[0052] The safety tolerance threshold parameter item, as the core safety control element in the electromagnetic field focusing parameter configuration table, implements active protection by solidifying the dual hard boundaries of the coil temperature upper limit and the standing wave ratio tolerance threshold. The temperature threshold is dynamically compensated in real time based on the ambient temperature, and the standing wave ratio threshold is automatically tightened with the electromagnetic interference intensity index. When this parameter item is loaded into the programmable coil array, while activating the dynamic beam focusing mode, the backscatter signal receiving circuit simultaneously monitors the physical layer parameters with high precision. If either the coil temperature or the standing wave ratio is detected to exceed the threshold, the device triggers a triple protection response within 3 milliseconds: the impedance matching network is immediately retuned, the drive current intensity is attenuated by 30%, and the beam focusing mode is switched to the safe transmission mode. Under extreme operating conditions, the parameter item activates the hardware fuse mechanism to disconnect the power circuit and record the diagnostic code. Through structured fields, an active defense system that complies with the ISO 60601-2-33 medical standard is constructed to ensure that the spatial energy focusing process will control the operational risk to less than one billionth of the failure rate.

[0053] S4.2: Extract signal strength, noise, and phase metrics based on the original electromagnetic signal waveform, optimize the charging waveform in real time, and integrate temperature data to generate a performance monitoring package. Based on the original electromagnetic signal waveform, fast Fourier transform calculation is performed to extract the signal strength characteristics, power spectrum density analysis is performed to obtain the noise suppression value index, and the zero-crossing time difference is detected to derive the carrier phase offset angle index; the millisecond-level coil temperature rise data of the temperature sensor is synchronously read; the signal strength characteristics, noise suppression value index, phase offset angle index and coil temperature rise data are combined to generate an efficiency monitoring package.

[0054] S4.3: Based on the performance monitoring package, the four-dimensional data stream convergence processor integrates the time series data to generate a real-time monitoring curve for charging performance.

[0055] According to the performance monitoring package, the four-dimensional data stream convergence processor performs the following operations: forcibly aligning the millisecond time stamp sequence in the performance monitoring package, aggregating the signal strength feature sequence, noise suppression value indicator sequence, phase offset angle indicator sequence and coil temperature rise data sequence to form a time axis index; continuously outputting structured timestamp data points with a time resolution of 3 milliseconds, and serially constructing a real-time monitoring curve for charging performance consisting of the time axis field, signal strength field, noise suppression field, phase offset field, and temperature rise rate field.

[0056] The four-dimensional data stream convergence processor is a dedicated hardware logic unit that is used to aggregate five-dimensional monitoring data of the time axis field, signal strength field, noise suppression field, phase offset field, and temperature rise rate field, integrates discrete performance monitoring package data points with millisecond-level timing alignment accuracy, and reconstructs continuous monitoring curves through piecewise cubic spline interpolation algorithm. S5: Detect the actual charging efficiency in the real-time monitoring curve of charging efficiency and dynamically generate an incremental optimization parameter package.

[0057] S5.1: Based on the actual charging efficiency in the real-time charging efficiency monitoring curve, dynamically compare the data of adjacent time slots and generate abnormal event markers; Based on the real-time monitoring curve of charging efficiency, the actual charging efficiency values ​​of consecutive time slot nodes are extracted, and the absolute difference of the actual charging efficiency values ​​of adjacent time slots is calculated; when the actual charging efficiency value decreases by more than the preset abnormal judgment threshold in two consecutive time slots, the abnormal event identifier is marked in the corresponding timestamp, and finally the abnormal event mark sequence consisting of the timestamp field and the abnormal type field is output.

[0058] This abnormal judgment threshold serves as the core trigger mechanism of the dynamic optimization system, and realizes real-time fault diagnosis of charging efficiency through the preset continuous efficiency decay rate limit. The specific operating logic is: real-time calculation of the absolute difference in the actual charging efficiency of adjacent time slot nodes. When it is detected that the efficiency decay amplitude exceeds the preset threshold value in two consecutive calculation cycles, the abnormal event identifier is immediately marked in the corresponding timestamp, and a structured tag sequence consisting of a precise timestamp field and an abnormal type field is generated. The threshold design fully considers the particularity of the medical equipment charging scenario. When the continuous decay of efficiency indicates potential risks such as equipment displacement, uncontrolled temperature rise or increased electromagnetic interference, the preset rigid decay rate judgment boundary ensures that the alarm is triggered within 10 milliseconds before the efficiency loss reaches the critical point, providing a key time window for subsequent root cause analysis, and supporting the multi-source signal capture and optimization instruction generation described in S5.2 of the manual.

[0059] S5.2: Capture multi-source real-time signals within the abnormal time window based on abnormal event markers, calculate the peak operating force and power fluctuation coefficient, as well as the causal strength of ambient temperature and efficiency changes, and generate a root cause analysis report; Based on the time window of abnormal event marker positioning, three parallel calculations are performed: the maximum instantaneous absolute value of the vertical spatial coordinate component in the corresponding time period is extracted from the peak of the operating force; the power fluctuation coefficient is calculated as the ratio of the standard deviation to the mean of the actual transmission power in adjacent time slots in the real-time monitoring curve of charging efficiency; and the causal strength between the ambient temperature value and the efficiency change value is calculated using the Pearson correlation coefficient formula.

[0060] The peak force of an operation refers to the maximum instantaneous absolute value of the vertical spatial coordinate component (i.e., Z-axis acceleration) within a specific time window. The nine-axis sensor continuously samples the three-dimensional acceleration waveform of the glasses' pick-up and placement actions, extracts the Z-axis acceleration sequence, and calculates the maximum absolute value over the entire process. This parameter quantifies the physical intensity of the user's operation, expressed in units of standard gravity.

[0061] The power fluctuation coefficient measures the stability of charging power and is calculated as the ratio of the sliding window standard deviation to the mean of the actual transmission power sequence. Based on the actual transmission power field in the real-time charging efficiency monitoring curve, the standard deviation σ and mean μ within a fixed window length are calculated, ultimately outputting a dimensionless ratio. A higher dimensionless ratio indicates more severe power fluctuations.

[0062] The Pearson correlation coefficient formula is: ; in, Indicates the degree of linear correlation between ambient temperature value and efficiency change value; No. Ambient temperature value of each sampling point; Indicates the Efficiency change value of each sampling point; Indicates the number of sampling points involved in the calculation; represents the average temperature; Indicates the average efficiency.

[0063] S5.3: Based on the root cause analysis report, the optimization instruction generator dynamically creates a calibration instruction set, adds user prompts, and encapsulates the calibration instruction set and the user prompt text into an incremental optimization parameter package.

[0064] Based on the root cause analysis report, the following operations are performed: a calibration instruction set is generated based on the causal strength fields of the operation intensity peak value, power fluctuation coefficient, ambient temperature value, and efficiency change value in the root cause analysis report; a preset rule library is synchronously matched to output user prompt text; the calibration instruction set and the user prompt text are integrated into a structured data unit, and the encapsulated generation field includes an incremental optimization parameter package with an instruction code field and a prompt content field.

[0065] This embodiment also provides a computer device suitable for an artificial intelligence-based smart glasses box and a wireless charging control method thereof, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the artificial intelligence-based smart glasses box and a wireless charging control method thereof proposed in the above embodiment.

[0066] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0067] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the artificial intelligence-based smart glasses box and its wireless charging control method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0068] In summary, this invention achieves a fully decentralized collaborative decision-making network through encrypted broadcast communication and local behavior verification consensus within a distributed voting mechanism for device groups, eliminating the single point of failure risk inherent in centralized architectures and achieving enhanced robustness and tamper-proof security. Through spatial coordinate mapping and dynamic spectrum isolation in time-frequency-space three-dimensional resource allocation, precise directional transmission of electromagnetic energy is achieved, eliminating wireless interference between multiple devices, optimizing charging efficiency, and ensuring compatibility.

[0069] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An artificial intelligence-based smart glasses case and a wireless charging control method thereof, characterized by: include, Collect user operation data and environmental feature vectors, apply sliding window statistics to perform probability weighted analysis on recent behavior characteristics, and generate an encrypted prediction parameter package; Based on the encrypted prediction parameter package, a collaborative charging strategy matrix is ​​generated in the local network through a distributed voting mechanism among the device groups; Based on the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case, an electromagnetic field focusing parameter configuration table is generated through a three-dimensional time-frequency-space resource allocation scheme; The electromagnetic field focusing parameter configuration table drives the programmable coil array, dynamically adjusts the charging signal, and generates a real-time monitoring curve for charging efficiency; The actual charging efficiency in the real-time monitoring curve of charging performance is detected, and an incremental optimization parameter package is dynamically generated.

2. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 1, characterized in that: The user operation data includes the three-dimensional acceleration waveform, operation duration, operation force peak value and operation frequency statistics of the glasses picking and placing action; The environmental feature vector includes a GPS geo-fence tag, a Bluetooth broadcast device battery percentage, an ambient temperature value, an electromagnetic interference intensity index, and a real-time time window identifier.

3. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 2, characterized in that: The sliding window statistical method is used to perform probability weighted analysis on recent behavioral characteristics to generate an encrypted prediction parameter package. The steps are as follows: The user operation data and the environment feature vector are time-scaled aligned using a hardware timer to generate a behavior-environment fusion dataset. Based on the behavior-environment fusion dataset, the operation frequency value is calculated through the sliding window statistical method, and the probability weighted analysis of recent behavior characteristics is performed to obtain the time period emergency demand index; The time period emergency demand index and the device unique ID are combined into a plaintext data block, which is encrypted and encapsulated through the hardware-level AES-128 encryption engine to generate an encrypted prediction parameter package.

4. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 3, characterized in that: The steps of generating a collaborative charging strategy matrix in the local network based on the encrypted prediction parameter package through the distributed voting mechanism of the device group are as follows: Based on the encrypted prediction parameter package, the voting request data frame is broadcast to the collaborative device group through the Bluetooth network, while monitoring the response timeout status and generating a list of devices to respond; Based on the broadcast voting request data frame and the list of devices to be responded to, each collaborative device performs behavior pattern matching verification in the local network and generates a device group verification result table; According to the device group verification result table, the device priority weight is dynamically adjusted through voting confidence, and the collaborative charging strategy matrix is ​​generated in combination with the real-time power status.

5. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 4, characterized in that: The steps of generating an electromagnetic field focusing parameter configuration table based on the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case through the time-frequency-space three-dimensional resource allocation scheme are as follows: The spatiotemporal semantic parsing engine is used to parse the emergency charging window period and power allocation instructions in the collaborative charging strategy matrix and the three-dimensional coordinates of the device in the glasses case to generate a spatial strategy fusion dataset. Based on the spatial strategy, the data set is integrated and a three-dimensional resource allocation plan is generated through time slot cutting, dynamic frequency band allocation and spatial beam focusing parameter calculation. Based on the three-dimensional resource allocation scheme of time, frequency and space, the beamforming phase angle of the main device is calculated, the frequency hopping timing of the secondary device is configured, the coil drive current parameters are set, and the safety tolerance rules are loaded, and finally integrated into the electromagnetic field focusing parameter configuration table.

6. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 5, characterized in that: The electromagnetic field focusing parameter configuration table drives the programmable coil array to dynamically adjust the charging signal and generate a real-time monitoring curve for charging efficiency. The steps are as follows: The electromagnetic field focusing parameter configuration table drives the programmable coil array and synchronously turns on the backscatter signal receiving circuit to capture the original electromagnetic signal waveform fed back by the device; Extract signal strength, noise, and phase indicators based on the original electromagnetic signal waveform, optimize the charging waveform in real time, and integrate temperature data to generate a performance monitoring package; According to the performance monitoring package, the four-dimensional data stream convergence processor integrates time series data to generate a real-time monitoring curve for charging efficiency.

7. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 6, characterized in that: The actual charging efficiency in the real-time monitoring curve of charging efficiency is detected in the following steps: Based on the actual charging efficiency in the real-time monitoring curve of charging efficiency, dynamic comparison is performed on adjacent time slot data to generate abnormal event markers; Based on abnormal event markers, it captures multi-source real-time signals within the abnormal time window, calculates the operating force peak and power fluctuation coefficient, as well as the causal strength of ambient temperature and efficiency changes, and generates a root cause analysis report.

8. The artificial intelligence-based smart glasses case and wireless charging control method thereof according to claim 7, wherein: The dynamic generation of the incremental optimization parameter package refers to the optimization instruction generator dynamically creating a calibration instruction set based on the root cause analysis report, adding user prompts, and encapsulating the calibration instruction set and the user prompt text into an incremental optimization parameter package.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the artificial intelligence-based smart glasses box and the wireless charging control method thereof are implemented as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the artificial intelligence-based smart glasses box and the wireless charging control method thereof are implemented as described in any one of claims 1 to 8.

Images