Operating State Diagnosis Method, Device and Equipment for Attention Glasses

Abstract

The present application relates to the technical field of brain-computer interfaces, and particularly to a method, device, and equipment for diagnosing the operating state of an attention glasses. The method includes: obtaining the operating data of the attention glasses, generating a monitoring table to determine the abnormal standard; generating a change trajectory according to the abnormal standard; sorting out the problem sources based on the change trajectory to form a fault spectrum; testing the operating indicators according to the fault spectrum, determining the health degree based on the operating indicators, drawing a performance graph based on the health degree, and generating an evaluation table according to the performance graph; counting the attenuation trend according to the evaluation table, calculating the performance decline according to the attenuation trend, predicting the influence range based on the performance decline, and determining the optimization measures according to the influence range; determining the operating scenario according to the optimization measures, determining the intervention time mechanism according to the operating scenario to formulate a diagnosis rule, generating a fault domain, and establishing a repair plan; generating a diagnosis report according to the repair plan to complete the diagnosis of the operating state of the attention glasses. The accuracy of diagnosing the operating state of the attention glasses is improved.

Description

Technical Field

[0001] This application relates to the technical field of brain-computer interfaces, and in particular, to a method, device, and equipment for diagnosing the operating state of an attention glasses. Background Art

[0002] Operating state diagnosis is a key technology to ensure the stable operation of attention glasses. Traditional device diagnosis methods mainly rely on simple state monitoring and fault alarms, and usually can only detect obvious hardware faults and performance anomalies. This method is difficult to cope with complex system operation anomalies, especially difficult to identify performance degradation by gradual change and compound faults caused by multi-system interaction. With the development of intelligent diagnosis technology, fault prediction and diagnosis methods based on multi-dimensional data analysis have gradually matured. These methods can detect potential problems earlier by real-time monitoring the change trends and mutual correlations of multiple system parameters, providing new technical means to improve system reliability. However, there are still challenges in achieving accurate operating state diagnosis on resource-constrained portable devices, especially for intelligent wearable devices such as attention glasses that have strict requirements on computing resources, battery life, and wearing comfort.

[0003] Existing operating state diagnosis technologies have limitations in fault feature extraction and pattern recognition, and it is difficult to effectively distinguish fluctuations caused by normal use from real performance anomalies; the early warning mechanism for system performance degradation is not perfect enough, and problems are often recognized only after the function is significantly damaged; the adaptive ability of the diagnosis model needs to be improved, and it is difficult to dynamically adjust diagnosis parameters according to different users' usage habits and environmental conditions; at the same time, the balance between resource consumption in the real-time diagnosis process and the normal operation of the system also needs to be optimized. Too frequent or complex diagnosis operations may significantly affect the core function and battery life of the device.

[0004] Therefore, there is an urgent need for a method to solve at least one of the above problems. Summary of the Invention

[0005] The embodiments of this application provide a method, device, and equipment for diagnosing the operating state of an attention glasses. The method aims to solve the problems that existing operating state diagnosis technologies have limitations in fault feature extraction and pattern recognition, and it is difficult to effectively distinguish fluctuations caused by normal use from real performance anomalies; the early warning mechanism for system performance degradation is not perfect enough, and problems are often recognized only after the function is significantly damaged; the adaptive ability of the diagnosis model needs to be improved, and it is difficult to dynamically adjust diagnosis parameters according to different users' usage habits and environmental conditions; at the same time, the balance between resource consumption in the real-time diagnosis process and the normal operation of the system also needs to be optimized. Too frequent or complex diagnosis operations may significantly affect the core function and battery life of the device.

[0006] In a first aspect, an embodiment of the present application provides a method for diagnosing the operating state of an attention glasses, including:

[0007] Obtain the operating data of the attention glasses, mark the detection positions, draw a state curve according to the detection positions, and generate a monitoring table based on the state curve; extract the normal range from the monitoring table; set an alarm limit according to the normal range; determine an abnormality standard based on the alarm limit;

[0008] According to the abnormality standard, determine the fluctuation points, and generate a change trajectory according to the fluctuation points; sort out the problem sources based on the change trajectory, and form a fault spectrum according to the problem sources; test the operating indicators according to the fault spectrum, determine the health degree according to the operating indicators, draw a performance graph based on the health degree, and generate an evaluation table according to the performance graph;

[0009] According to the evaluation table, count the attenuation trend, calculate the performance decline according to the attenuation trend, predict the influence range based on the performance decline, and determine the optimization measures according to the influence range; determine the operating scenario according to the optimization measures, determine the intervention timing according to the operating scenario, select a processing method based on the intervention timing, and formulate a diagnostic rule according to the processing method;

[0010] According to the diagnostic rule, generate a fault domain, and obtain emergency measures according to the fault domain; isolate the error source according to the emergency measures, and establish a repair plan according to the error source; generate a diagnostic report according to the repair plan, and complete the diagnosis of the operating state of the attention glasses.

[0011] In a second aspect, the present application further provides an operating state diagnosis device, including:

[0012] A data acquisition unit, configured to obtain the operating data of the attention glasses, mark the detection positions, draw a state curve according to the detection positions, and generate a monitoring table based on the state curve; extract the normal range from the monitoring table; set an alarm limit according to the normal range; determine an abnormality standard based on the alarm limit;

[0013] A fluctuation determination unit, configured to determine the fluctuation points according to the abnormality standard, and generate a change trajectory according to the fluctuation points; sort out the problem sources based on the change trajectory, and form a fault spectrum according to the problem sources; test the operating indicators according to the fault spectrum, determine the health degree according to the operating indicators, draw a performance graph based on the health degree, and generate an evaluation table according to the performance graph;

[0014] An attenuation statistics unit, configured to statistically analyze the attenuation trend according to the evaluation table, calculate the performance degradation according to the attenuation trend, predict the influence range based on the performance degradation, and determine the optimization measures according to the influence range; determine the operation scenario according to the optimization measures, determine the intervention timing according to the operation scenario, select the processing method based on the intervention timing, and formulate the diagnostic rule according to the processing method;

[0015] A diagnosis completion unit, configured to generate a fault domain according to the diagnostic rule, and obtain the emergency measures according to the fault domain; isolate the error source according to the emergency measures, and establish a repair plan according to the error source; generate a diagnostic report according to the repair plan to complete the operation status diagnosis of the attention glasses.

[0016] In a third aspect, the present application further provides a computer device, including a processor and a memory, where the memory is used to store a computer program, and when the computer program is executed by the processor, it implements the operation status diagnosis method of the attention glasses as described in the first aspect.

[0017] This method obtains the operation data of the attention glasses (such as voltage, current, processing frame rate, signal quality, etc.), marks the key detection positions, and draws multi-dimensional state curves based on the detection positions (such as the state curves of power management, image processing, biosensing, wireless communication and other modules), and generates a monitoring table including the normal parameter range. Set the alarm limit according to the normal range in the monitoring table to determine the abnormal criteria (such as fluctuation index, response delay, voltage offset, etc.). Identify the fluctuation points based on the abnormal criteria (such as the signal-to-noise ratio of the sensor being lower than the threshold, the battery voltage deviating from the standard, etc.), and generate a change trajectory including spatio-temporal characteristics (such as time-accumulated faults, concentrated anomalies in the sensor area, etc.). Locate the problem source (such as sensors, power supplies, processing units, etc.) through the change trajectory to form a fault spectrum (sub-system level fault model). Test the operation indicators (such as processing delay, signal stability, etc.), calculate the device health, draw the performance graph and generate the evaluation table. Statistically analyze the performance attenuation trend, calculate the performance degradation rate in combination with the laws of time-accumulated effect, environmental adaptability, etc., and predict the function critical time threshold and the influence range. Formulate the optimization measures (such as heat dissipation improvement, power calibration, etc.) according to the prediction results, determine the intervention timing and the processing method, and form the diagnostic rule. Generate a fault domain (fault influence range model), trigger the emergency measures (such as error source isolation), establish a repair plan and generate a diagnostic report.

[0018] Through high-precision sensors and status curve monitoring, real-time tracking of multi-dimensional parameters (such as voltage, signal quality, processing load, etc.) is achieved, improving the sensitivity of anomaly detection. Based on the fault spectrum and performance degradation model, the problem source (such as sensor failure, power fluctuation, etc.) is quickly located, the remaining life of the device is predicted, and sudden failures are avoided. Combining environmental adaptability and resource balance rules, the alarm limit and optimization measures (such as calibration period, heat dissipation strategy) are dynamically adjusted to extend the service life of the device. Through diagnostic rules and fault domain models, emergency measures and repair plans are automatically generated to shorten the maintenance response time and reduce the maintenance cost.

[0019] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit this application. Brief Description of the Drawings

[0020] Figure 1 It is a schematic flow chart of the operation status diagnosis method of the attention glasses shown in the embodiments of this application;

[0021] Figure 2 It is a schematic structural diagram of the operation status diagnosis device shown in the embodiments of this application;

[0022] Figure 3 It is a schematic structural diagram of the computer device shown in the embodiments of this application. Detailed Description of the Embodiments

[0023] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of this application. However, those skilled in the art should clearly understand that this application can also be implemented in other embodiments without these specific details. In other cases, the detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of this application.

[0024] It should be understood that when used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0025] It should also be understood that the term " / and" as used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] As used in the specification and appended claims of the present application, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]".

[0027] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are used only for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0028] Reference to "one embodiment" or "some embodiments" or the like described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0029] The technical solutions of the embodiments of the present application will be introduced below.

[0030] Operating state diagnosis is a key technology to ensure the stable operation of attention glasses. Traditional device diagnosis methods mainly rely on simple state monitoring and fault alarms, and usually can only detect obvious hardware failures and performance anomalies. This method is difficult to cope with complex system operation anomalies, especially difficult to identify performance gradual decline and compound faults caused by multi-system interactions. With the development of intelligent diagnosis technology, fault prediction and diagnosis methods based on multi-dimensional data analysis have gradually matured. These methods can detect potential problems earlier by real-time monitoring the change trends and mutual correlations of multiple system parameters, providing new technical means for improving system reliability. However, implementing accurate operating state diagnosis on resource-constrained portable devices still faces challenges, especially for intelligent wearable devices such as attention glasses that have strict requirements on computing resources, battery life, and wearing comfort.

[0031] Existing operating state diagnosis technologies have limitations in fault feature extraction and pattern recognition, making it difficult to effectively distinguish fluctuations caused by normal use from true performance anomalies; the early warning mechanism for system performance degradation is not perfect enough, and problems are often recognized only after the function is significantly damaged; the adaptive ability of the diagnosis model needs to be improved, and it is difficult to dynamically adjust diagnosis parameters according to the usage habits and environmental conditions of different users; at the same time, the balance between resource consumption in the real-time diagnosis process and the normal operation of the system also needs to be optimized, and overly frequent or complex diagnosis operations may significantly affect the core functions and battery life of the device. In view of the above technical problems, the present invention proposes a new operating state diagnosis method, which minimizes the impact on the normal operation of the system while ensuring diagnosis accuracy through multi-level data analysis, adaptive threshold adjustment, and intelligent resource scheduling.

[0032] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an operating state diagnosis method for an attention glasses provided in an embodiment of the present application. The operating state diagnosis method for the attention glasses in the embodiment of the present application can be applied to a computer device, and the computer device includes but is not limited to devices such as smart phones, laptop computers, tablet computers, desktop computers, physical servers, and cloud servers. As Figure 1 shown, the operating state diagnosis method for the attention glasses in this embodiment includes steps S101 to S104, which are described in detail as follows:

[0033] Step S101, obtain the operating data of the attention glasses, mark the detection positions, draw a state curve according to the detection positions, generate a monitoring table based on the state curve; extract the normal range in the monitoring table; set the warning limit according to the normal range; determine the anomaly standard based on the warning limit.

[0034] Specifically, as the starting link of the operating state diagnosis of the attention glasses, it is first necessary to collect the device operating data and mark the detection positions.

[0035] In some embodiments, the obtaining the operating data of the attention glasses and marking the detection positions includes: marking the detection positions on the circuit board of the attention glasses by using a high-precision laser positioning system, and performing electrical characteristic verification, heat dissipation characteristic verification, and signal quality verification on the detection points corresponding to each detection position; installing high-precision sensors at each of the detection positions, and configuring the sampling period according to the importance level of the parameters; generating an identification code including parameter types, sampling requirements, and calibration coefficients on a specific layer of the circuit board by laser etching to generate a high-precision three-dimensional coordinate file.

[0036] In the power management unit area, it is necessary to monitor the voltage range (3.3V - 4.2V), current change (50mA - 500mA), power consumption level (0.5W - 2W), and the impedance matching error of the power monitoring point is required to be controlled within 5%; in the image processor area, it is necessary to monitor the processing frame rate (60fps - 120fps), calculation load (30% - 85%), cache usage rate (20% - 75%), and the processor monitoring point needs to consider EMI protection with a grounding resistance less than 0.1Ω; in the biosensor area, it is necessary to monitor the sampling frequency (250Hz - 1000Hz), signal quality (signal-to-noise ratio > 35dB), temperature drift (±0.5℃), and the crosstalk isolation degree of the sensor monitoring point is greater than 70dB; in the wireless communication module area, it is necessary to monitor the signal strength (-30dBm to -85dBm), data throughput (1Mbps - 10Mbps), packet loss rate (<0.1%). When marking the detection positions on the circuit board, a high-precision laser positioning system is used, and the positioning accuracy is controlled within 0.05mm. Each detection point is triple-verified: the electrical characteristics of the monitoring point are verified through an impedance tester, the heat dissipation characteristics of the monitoring point are checked using an infrared thermal imager, and the signal quality of the monitoring point is tested through a signal integrity analyzer. High-precision sensors are installed at each detection position, and the sampling accuracy requirement is within 0.1%. The sampling rate is configured in levels: the sampling period for key parameters is 100ms, the sampling period for important parameters is 500ms, and the sampling period for general parameters is 1s. Finally, the physical marking of the detection positions is completed on a specific layer of the circuit board through laser etching. Each detection position uses a two-dimensional identification code to contain the parameter type, sampling requirements, and calibration coefficients of the detection point, and at the same time, a three-dimensional coordinate file of the marked position is generated, with a coordinate accuracy better than 0.01mm.

[0037] In some embodiments, drawing a status curve according to the detection position and generating a monitoring table based on the status curve includes: drawing voltage, current, and power consumption status curves for the power management unit of the attention glasses, and the monitoring table includes the impedance matching error requirement; drawing processing frame rate, calculation load, and cache usage rate status curves for the image processor of the attention glasses, and the monitoring table includes the grounding resistance and EMI protection requirements; drawing sampling frequency, signal quality, and temperature drift status curves for the biosensor of the attention glasses, and the monitoring table includes the crosstalk isolation degree requirement; drawing signal strength, data throughput, and packet loss rate status curves for the wireless communication module of the attention glasses.

[0038] Based on the physical markers and 3D coordinate files completed in the first paragraph, the system starts to collect data and draw state curves. First, the 3D coordinate files are used for the installation and positioning of sensors, with an installation deviation less than 0.02 mm, and the QR code information at the marker positions is used for parameter configuration and initial calibration. At the marker positions of the power management unit, the data collected by the sensors are processed by a 60-point moving average according to the filtering parameters in the markers, and weighted average is performed using the weight coefficients defined at the marker positions; at the marker positions of the image processor, the sensors collect data based on the 15-minute time window defined in the markers and perform piecewise linear fitting, and abnormal points are removed using the 3σ criterion specified in the markers; at the marker positions of the biosensors, the sensors collect data according to the marker requirements and perform fitting through a Gaussian mixture model to calculate signal characteristic parameters; at the marker positions of the wireless communication module, the sensors collect data according to the time scales specified in the markers and calculate the correlation coefficients of each time scale. In data processing, a parameter mapping based on the topological relationship of the marker positions is established: for every 10% increase in the processor load between adjacent marker positions, the corresponding power consumption increases by 0.2 W; for every 1°C increase in temperature detected at the marker positions of the temperature sensors, the performance decreases by approximately 2%; for every 10 dBm decrease in signal detected at the marker positions of the wireless signal strength, the transmission rate decreases by 1 Mbps. Finally, an atlas of state curves including performance curves, resource curves, and stability curves is drawn. Each curve contains 72 hours of monitoring data, and the sampling period of the curve inherits the regulations of the marker positions.

[0039] By analyzing the atlas of state curves drawn in the second paragraph, a complete device monitoring table is formulated. Through the statistical analysis of the state curves of the power management unit, the standard operating point of the voltage is determined to be 3.7 V and the deviation range is ±0.1 V; through the fluctuation characteristics of the processor performance curve, the standard processing frame rate is determined to be 90 fps and the fluctuation range is ±10 fps; by analyzing the probability distribution of the signal strength curve, the standard signal strength is determined to be -50 dBm and the change range is ±5 dBm. The analysis of the dynamic characteristics of the curves determines the rate-of-change limits: the upper limit of the voltage change rate is 0.1 V / s, the upper limit of the load change rate is 5% / s, and the upper limit of the temperature change rate is 1°C / min. By performing spectral analysis on each curve, the characteristic periods are extracted: the performance fluctuation period is 10 min - 30 min, the temperature fluctuation period is 20 min - 40 min, and the signal strength fluctuation period is 5 min - 15 min. Based on the correlation analysis between the curves, parameter constraints are established: when the processor load exceeds 80%, the temperature must be controlled below 45°C; when the power consumption exceeds 1.5 W, the voltage must not be lower than 3.5 V; when the signal strength drops to -70 dBm, the transmission rate needs to be reduced. The monitoring table creates independent data table entries for all parameters. Each table entry contains the characteristic values obtained from the curve analysis, and a topological graph of parameter relationships is constructed through the overall analysis of the curve clusters.

[0040] Consult the monitoring table of the above steps to extract the normal range; set the alarm limit according to the normal range; determine the abnormal standard based on the alarm limit;

[0041] The data exported from the monitoring table of the above steps shows that the attention glasses have accumulated a large number of operation parameter records during long-term operation. Analyzing the monitoring table, it is found that the daily use process of users mainly includes multiple typical scenarios: for example, when continuously watching videos, the load of the image processor remains at a relatively high level (60% - 85%), accompanied by an increase in power consumption (1.2W - 1.8W) and a rise in temperature (38°C - 42°C); another example is when having a remote meeting, the data throughput of the wireless communication module increases significantly (5Mbps - 8Mbps), and at the same time, the sampling frequency of the biosensor also increases accordingly (500Hz - 800Hz); in the medical monitoring scenario, the signal-to-noise ratio of the biosensor needs to be maintained at a relatively high level (>40dB), and the system will automatically adjust the sampling parameters to ensure data quality. By statistically analyzing the data of these typical scenarios recorded in the monitoring table, the dynamic mean and standard deviation of the parameters are calculated using the sliding window method, and the window size is adaptively adjusted according to the change characteristics of the parameters. For rapidly changing parameters such as processor load, a short window of 5 minutes is used, and for slowly changing parameters such as temperature, a long window of 30 minutes is used. When cleaning the monitoring table data, a triple filtering mechanism is adopted: first, the extreme difference method is used to eliminate obvious outliers (beyond the mean ±3σ), then the moving median method is used to smooth the data fluctuations (11-point smoothing), and finally, the Kalman filter algorithm is applied to dynamically correct the data (process noise covariance 0.001, measurement noise covariance 0.1). During the data analysis process, special attention is paid to the correlation between parameters, and the parameter groups that influence each other are identified through the correlation coefficient matrix. For example, the monitoring table data shows that in the video conference scenario, when the processor load increases by 10% each time, the power consumption will increase by 0.2W accordingly, the temperature will rise by 0.5°C, and the battery voltage will drop by 0.1V; in the outdoor use scenario, when the light intensity increases by 1000 lux, the signal-to-noise ratio of the biosensor will drop by 2dB, and the system needs to increase the sampling frequency by 50Hz to maintain data quality. Based on these correlation relationships, parameter groups are constructed to ensure that the restrictive effects between parameters are considered when extracting the normal range. After analyzing and verifying a large amount of historical data in the monitoring table, the normal operation range of each parameter is finally obtained.

[0042] According to the normal ranges extracted above, the alarm limits of each parameter are systematically set. Differentiated alarm strategies are set respectively according to the characteristics of different operation scenarios. Taking the remote medical consultation scenario as an example: when processing high-definition video streams, the processor load is allowed to fluctuate at a relatively high level (up to 85%), but the temperature must be ensured to be within the safe range (<45°C); during a long-term consultation process (>2 hours), the system will gradually tighten the limits and reduce the maximum load to 75% to protect the hardware. The setting of alarm limits is based on the actual distribution characteristics of the parameters, and a hierarchical threshold structure is adopted. For parameters that follow a normal distribution, the threshold is set based on the standard deviation: the normal range is usually within ±2 standard deviations, the warning area is between ±2 and ±3 standard deviations, and beyond ±3 standard deviations enters the alarm area; for parameters that do not follow a normal distribution, the quantile method is used to determine the threshold: the normal range is between the 15th and 85th percentiles, and the warning area extends to the 5th and 95th percentiles. During the threshold setting process, the correlation between parameters is fully considered, and for parameter groups with strong correlation, a linkage alarm mechanism is designed. To adapt to different usage environments, the alarm system also introduces an environmental adaptability adjustment mechanism: in an environment with a higher temperature (>35°C), the performance threshold will be automatically reduced by 10% and the heat dissipation margin will be increased; in an area with weak signals (<-70dBm), the tolerance for communication fluctuations will be increased, and the packet loss rate threshold will be relaxed from 0.1% to 0.3%.

[0043] Based on the set alarm limits, further clarify the determination criteria for various types of anomalies. The anomaly determination uses a multi-dimensional evaluation method, which not only considers whether the parameter value exceeds the alarm limit, but also pays attention to the degree of excess, the duration, and the change trend. For different types of anomalies, corresponding determination rules are established: instantaneous anomalies require the parameter value to significantly exceed the alarm limit (more than 20% of the threshold), but the duration is short (<30 seconds), such as the instantaneous spike in processor load; cumulative anomalies focus on the residence time of the parameter in the warning area, and are determined to be anomalies when it exceeds the set duration (>5 minutes), such as the continuous increase in temperature; trend anomalies mainly monitor the change rate of the parameter, and trigger anomaly determination when the change speed exceeds the threshold (such as the temperature rise rate >1°C / minute), such as the rapid drop in battery voltage. In practical applications, common complex anomaly scenarios include: using the device for a video conference outdoors in summer, which may simultaneously trigger multiple anomalies such as too high temperature (>42°C), excessive processor load (>85%), and unstable signal (signal strength fluctuation >10dBm). When dealing with anomaly determination, the system uses a fuzzy inference mechanism to classify and process according to the severity and urgency of the anomaly. For example, when it detects a rapid increase in temperature (>0.8°C / minute), the system will immediately reduce the processor frequency by 20% and increase the heat dissipation power at the same time; for the slow drop in battery voltage (<0.1V / hour), it will extend the usage time by gradually reducing the screen brightness and processor performance. Through testing and verification in different environments and usage scenarios, continuously optimize the anomaly determination criteria, and finally form a reliable anomaly determination standard system.

[0044] In step S102, according to the anomaly criteria, determine the fluctuation points, generate a change trajectory based on the fluctuation points; sort out the problem sources based on the change trajectory, and form a fault spectrum according to the problem sources; test the operation indicators according to the fault spectrum, determine the health status according to the operation indicators, draw a performance graph based on the health status, and generate an evaluation form based on the performance graph.

[0045] Specifically, compare with the anomaly criteria of the above steps to detect the fluctuation points; depict the change trajectory according to the fluctuation points; sort out the problem sources based on the change trajectory; form a fault spectrum according to the problem sources.

[0046] In some embodiments, the determining the fluctuation points according to the anomaly criteria and generating a change trajectory according to the fluctuation points includes: determining that the signal-to-noise ratio of the sensor is lower than the preset threshold and the fluctuation index exceeds the standard, the response delay of the processing system exceeds the standard and the memory fragmentation rate is abnormal, the battery voltage curve deviates from the standard, and the communication packet loss rate exceeds the standard as the fluctuation points; generating the change trajectory including time characteristics, spatial distribution, and functional impact, where the time characteristics are manifested as the aggravation of the fault after the preset usage duration, the spatial distribution is concentrated in the sensor area and the processing unit, and the functional impact is manifested as the decrease in data accuracy and the lag of system response.

[0047] Detect using the three types of anomaly criteria (instantaneous anomaly, cumulative anomaly, trend anomaly) set by the above steps, and systematically analyze the operation data of the attention glasses. For the instantaneous anomaly criterion, a sliding window with a width of 30 seconds is used for scanning to identify instantaneous fluctuation points such as spikes in processor load during video compression and sudden drops in signal-to-noise ratio of biosensors during user movement. In the telemedicine scenario, these instantaneous fluctuations are usually related to sudden data processing requirements. For example, during a surgical live broadcast, high-definition video streams and multiple biological signals need to be processed simultaneously, and the system will record the timing characteristics and environmental conditions of each sudden performance fluctuation. For the cumulative anomaly criterion, a 5-minute window is used for detection, and cumulative fluctuation points such as the continuous decrease in battery voltage under high load and the slow increase in temperature in a closed environment are found. Such fluctuations usually reflect the gradual changes in system resources. For example, during a long-term medical data acquisition process, the processor load gradually increases, resulting in a cumulative increase in temperature. In the rehabilitation training scenario, as the training time extends, the system will detect a slow deterioration in the signal quality of biosensors, and sensor position adjustment or recalibration is often required. For the trend anomaly criterion, an adaptive window is used to calculate the rate of change, and trend fluctuation points such as wireless signal fluctuations and processor frequency adjustment are captured. In the outdoor sports monitoring scenario, when the user changes from a walking state to a running state, the sampling frequency of the biosensor will be dynamically adjusted according to the activity intensity, accompanied by coordinated changes in power consumption and temperature. All detected fluctuation points are detailedly recorded according to dimensions such as occurrence time, triggering conditions, and influence scope, and finally summarized to form a fluctuation point dataset.

[0048] Start analyzing the change trajectories from the fluctuation point dataset. In the video consultation scenario, many fluctuation points are related to the processor load. By tracking the development process of these fluctuation points, it is found that after high load persists for a period of time, the temperature rise rate will significantly accelerate, and the system will then lower the priority of non-critical tasks. The fluctuations in biosensor data are mostly related to changes in the usage environment, and these fluctuations will trigger dynamic adjustments of the sampling frequency, thereby affecting system resource allocation. In scenarios with large changes in ambient light, the sensor will automatically adjust the gain parameters, resulting in corresponding changes in power consumption and processing load. The fluctuation points related to wireless communication indicate that when the signal strength drops, the system will sequentially adjust the video compression ratio, transmission frame rate, and data priority to maintain communication quality as much as possible. During long-term operation, some complex fluctuations are also observed, such as high load causing temperature to rise, which in turn affects battery performance and wireless transmission quality. Through time-series correlation analysis of these fluctuation points, a series of typical state change trajectory diagrams are drawn.

[0049] In some embodiments, sorting out the problem sources based on the change trajectory and forming a fault spectrum according to the problem sources includes: obtaining the problem sources according to the change trajectory through correlation analysis; generating a fault spectrum including sensor, processing, power supply, and communication subsystems according to the problem sources.

[0050] By analyzing the state change trajectory diagram, the system identifies various key problems and their causes. In the trajectory related to the processor, it is found that the heat dissipation efficiency shows a non-linear decline as the temperature rises. After exceeding a certain temperature threshold, the heat dissipation performance will deteriorate sharply. This feature is more obvious when used in an enclosed space, and it is often necessary to reduce the system load in a timely manner. The trajectory of wireless communication shows that the signal quality is not only affected by the user's movement state but also closely related to the interference of surrounding electronic devices, especially in an environment with a high density of medical devices. The trajectory of the biosensor indicates that the data quality is affected by the superposition of multiple environmental factors such as light and vibration, and it is necessary to comprehensively consider the change trends of various parameters. The battery performance trajectory reflects the significant impact of the usage pattern on the energy consumption, especially in high-load scenarios, and more intelligent power management strategies are required. In addition, some hidden correlations between parameters are also found, such as the mutual influence between the wireless signal strength and the sensor sampling strategy. Through in-depth analysis of these trajectories, a complete problem source database is sorted out.

[0051] Based on the problem source database, a hierarchical fault spectrum is constructed. The problems related to heat dissipation are sorted out as heat dissipation faults, and the development process from abnormal temperature to performance limitation is detailed, including the change characteristics under different environmental conditions. The wireless communication problems mainly describe the signal characteristics in various scenarios and determine the influence degree of different interference factors. The sensor problems mainly focus on the influencing factors of data quality, establish the corresponding relationship between environmental parameters and data deviation, and also include calibration and compensation strategies. For power management and system performance problems, the performance degradation characteristics during long-term operation are mainly recorded. In addition, special attention is paid to the system performance when multiple problems occur in combination, how to judge the primary and secondary causal relationships, and the corresponding processing strategies. Finally, a structured fault spectrum is formed, which details the discrimination methods, influence degrees, and processing suggestions of various faults.

[0052] Interpret the fault spectrum of the above steps, test the operation indicators; determine the health status according to the operation indicators; draw a performance graph based on the health status; generate an evaluation form according to the performance graph;

[0053] Interpret the fault spectrum formed in the above steps and extract quantifiable test metrics from it. In the heat dissipation fault records, the temperature change curve is used as the main test object, and metrics such as the temperature rise rate, average temperature, and temperature fluctuation range are set. The focus is on the temperature change pattern of the processor under high load and the response characteristics of the heat dissipation system. For signal quality issues, the stability of signal strength, real-time data transmission, and anti-interference ability are mainly tested, especially the communication performance in the environment of user movement and multi-device interference. In terms of sensor data, the signal-to-noise ratio, sampling accuracy, and data loss rate of the signal are tested, and the data reliability under different environmental conditions is mainly verified. System performance tests include parameters such as processor utilization, memory occupancy, and response latency. In the telemedicine scenario, continuous operation tests are carried out to record the performance change trend of the system under high load. For the outdoor mobile scenario, the data continuity and system adjustment ability during signal switching are mainly evaluated. In different lighting environments, the dynamic range adjustment and automatic compensation effects of the sensor are tested. Through repeated tests in the laboratory and actual application environments, a complete set of operation metric data is finally collected.

[0054] Adopt a multi-dimensional analysis method to evaluate the system health based on the operation metric data. The processor performance health mainly examines three aspects: load balance reflects the reasonable degree of task allocation, temperature control effect reflects the working state of the heat dissipation system, and performance stability indicates the reliable degree of the system. In the video conferencing scenario, the real-time processing ability of the system is evaluated by monitoring the processor frequency change and task response time. The wireless communication health is based on signal quality metrics, including signal strength stability, data transmission continuity, and anti-interference performance, and especially focuses on the communication quality change during user movement. The sensor health is evaluated from two dimensions of data accuracy and sampling stability, and it is necessary to ensure reliable physiological data can be obtained in various usage environments. The power management health mainly focuses on power supply stability and energy consumption efficiency, and evaluates the battery service life and charge-discharge performance. In the medical monitoring scenario, higher requirements are put forward for the accuracy of data collection, and the system needs to maintain a long working time while ensuring data quality. By establishing a health evaluation model and comprehensively analyzing the weights and mutual influences of various metrics, the overall health status score of the system is finally obtained.

[0055] Based on the health status score, we start to draw a curve chart reflecting the system performance. In the performance chart, the horizontal axis represents the running time, the vertical axis reflects the performance level, and different colors are used to distinguish the working status of each functional module. The processor performance curve shows the load change trend and temperature control response characteristics, and the adaptability of the system in different working modes can be clearly observed. The wireless communication performance curve records the dynamic changes of signal strength and transmission rate, reflecting the communication stability of the system. The sensor performance curve shows the fluctuation of data quality with environmental changes, which helps to identify potential interference factors. The power performance curve shows the energy consumption characteristics and battery life prediction. In the medical data transmission scenario, the performance curve focuses on the real-time processing capability and data reliability of the system. These curves are superimposed and analyzed, and drawn into a performance map containing multiple dimensions, which intuitively shows the performance characteristics of the system under various working conditions.

[0056] Based on the analysis results of the performance map, a detailed system evaluation table is generated. The evaluation table adopts a hierarchical structure, and the main categories are divided according to the functional modules, and multiple specific evaluation items are set under each category. In the processor performance section, the specific data of computing power, response time and temperature control effect are recorded; the communication performance section contains the evaluation results of signal quality, transmission rate and connection stability; the sensor performance section records the test data of data accuracy, sampling reliability and environmental adaptability in detail; the power performance section contains the evaluation indicators of power supply stability, energy efficiency and battery life. For each indicator, the evaluation table records the standard reference value, measured value and deviation range, and focuses on analyzing the items that exceed the standard range, explaining the reasons for the deviation and the degree of impact. In medical application scenarios, the evaluation table particularly emphasizes the importance of data reliability and system stability, and puts forward targeted optimization suggestions, such as improving heat dissipation design, optimizing signal processing algorithms and other specific measures. This evaluation table not only reflects the performance status of the current system, but also provides a clear direction for subsequent optimization and upgrading.

[0057] Step S103, statistically calculate the attenuation trend according to the evaluation table, calculate the performance degradation according to the attenuation trend, predict the impact range based on the performance degradation, and determine the optimization measures according to the impact range; determine the operation scenario according to the optimization measures, determine the intervention timing according to the operation scenario, select the processing method based on the intervention timing, and formulate the diagnostic rules according to the processing method.

[0058] Specifically, the evaluation table of the above steps is browsed to count the attenuation trend; the performance degradation is estimated according to the attenuation trend; the impact range is predicted based on the performance degradation; and the optimization measures are determined according to the impact range.

[0059] In some embodiments, calculating the performance degradation according to the attenuation trend includes: calculating the overall performance degradation rate and the core function availability index according to the attenuation trend, in combination with the time accumulation effect, environmental adaptability, resource balance, fault chain effect, and the operation law of the recovery mechanism; generating the performance degradation according to the availability index, where the performance degradation is used to predict the time threshold for the device to reach the functional critical state.

[0060] Starting from the evaluation form of the above steps, the attention glasses exhibit various performance attenuation phenomena during long-term operation. In the medical monitoring scenario, the evaluation form data shows that the acquisition accuracy of the biosensor decreases slowly, and the signal fluctuation amplitude gradually increases; the signal-to-noise ratio of the electroencephalogram acquisition channel continuously decreases from the initial state, especially after continuous wearing for more than 4 hours, and the attenuation speed accelerates. In the video conferencing scenario, the system processing delay in the evaluation form gradually increases, manifested as a decrease in the frame refresh rate and an increase in the audio-visual synchronization deviation; the longer the meeting duration, the more obvious the delay increase, especially in high-definition video transmission. During daily use, the battery life recorded in the evaluation form gradually shortens, while the system startup time lengthens and the application switching speed also slows down. By performing time series analysis and regression modeling on these performance indicators in the evaluation form, it is found that the attenuation characteristics in different usage scenarios have significant differences: the accuracy attenuation of sensing data is significantly correlated with the usage duration and changes in environmental temperature and humidity; the system performance degradation attenuates slowly in the light load stage and accelerates in the high load stage, mainly affected by the task load distribution and environmental temperature; the battery performance degradation is closely related to the number of charge and discharge cycles and the frequency of deep discharge. After data normalization, outlier removal, and trend extraction, a trend database containing the attenuation rates and influencing factors of various indicators is finally formed.

[0061] The performance degradation of each functional module of the glasses is further analyzed by using the decay rate and influencing factor information in the trend database. According to the decay rate in the trend database, the signal quality of the sensor decreases by about 5% every 100 hours of operation, which is mainly reflected in data stability and sampling accuracy; there are differences in the decay rates of different types of sensors, with the acceleration sensor having the slowest decay rate and the EEG sensor having the fastest decay rate. Combined with the analysis of influencing factors in the trend database, the system processing performance decreases by 2% per day on average under the influence of continuous high load, and the decay rate is slow under the influence of medium load, especially in video processing and multi-channel data analysis tasks; the memory management efficiency decreases over time, mainly due to the influence of fragmentation. The data transmission efficiency of the communication module also decreases with the extension of usage time. According to the influencing factor of stable connection state in the trend database, the throughput shows a slow decay rate, the decay rate increases under the influence of signal fluctuation environment, and the decay rate is faster in the influence of complex electromagnetic environment. By establishing a multivariate state space model, the performance decay curve of key functions is calculated based on the decay rate and influencing factors of each module. In high-demand scenarios such as medical monitoring, the performance degradation curve shows that once the accuracy of sensor data collection is lower than the standard value of 90%, it will affect the reliability of diagnosis; in remote conferencing scenarios, the performance degradation curve shows that system delays exceeding 200ms will significantly affect the user experience.

[0062] According to the performance degradation curve, the scope of its impact on various system functions and user experience is predicted. According to the performance degradation curve analysis, sensor performance degradation mainly affects the accuracy and reliability of medical monitoring applications: when the data deviation exceeds the threshold predicted by the performance degradation curve, the monitoring results will be unreliable, especially the impact on heart rate variability and brain wave spectrum analysis, which will affect sleep monitoring and cognitive load assessment functions; system performance degradation mainly affects the user interaction experience. When the system response delay exceeds the critical value in the performance degradation curve, the user can clearly perceive the unsmooth operation, which is manifested as extended application startup time and increased screen freeze frequency, especially in complex image processing tasks; communication performance degradation may cause data transmission interruption or delay. The performance degradation curve shows that this will affect the user experience of key applications such as telemedicine and video conferencing. In actual use, these impacts are often superimposed and cascaded: system performance degradation will further aggravate the processing delay of sensor data and reduce real-time performance, while the reduction of sensor data real-time performance will affect decision-making accuracy; communication performance degradation may lead to an increase in data cache, increase the system memory burden, and further reduce the system response speed. By analyzing these complex interactions and feedback loops, a complete impact range model is established based on the performance degradation curve.

[0063] Based on the influence range model, corresponding optimization measures are determined. According to the influence of sensor performance degradation in the influence range model, an adaptive signal processing algorithm is developed, which can dynamically adjust sampling parameters and filtering strategies according to data quality to improve data reliability; the algorithm can still maintain high detection accuracy in a low signal-to-noise ratio environment. In response to the influence of system performance degradation in the influence range model, an intelligent resource scheduling mechanism is designed, which can dynamically allocate computing resources according to task priority, resource usage status, and battery power, extending battery usage time while maintaining the performance of core functions; this mechanism can automatically identify resource-intensive tasks and perform time-sharing multiplexing processing to avoid system overload. To address the influence on communication performance in the influence range model, a context-aware data compression algorithm and a multi-level cache optimization technology are adopted to reduce transmission load; at the same time, an adaptive transmission strategy based on channel quality is implemented, which can automatically reduce the transmission priority of non-critical data in a weak signal environment to ensure the timely transmission of important information. These optimization measures determined based on the influence range model form a complete performance management solution, including multiple levels such as software algorithm optimization, resource scheduling optimization, and data processing optimization. In the attention monitoring and training scenarios, reliability guarantee measures for real-time data analysis are particularly strengthened according to the influence range model, and a dynamic correction and fluctuation compensation mechanism for attention data is implemented to ensure the accurate assessment of the user's attention state and cognitive load changes even in the case of performance degradation.

[0064] Implement the optimization measures determined in the above steps, including adaptive signal processing algorithms, intelligent resource scheduling mechanisms, and data compression technologies, and conduct system tests in the actual usage environment of the attention glasses. The adaptive signal processing algorithm effectively reduces sensor drift and improves the stability of brain wave and attention data; the intelligent resource scheduling mechanism optimizes the allocation of computing resources, enabling the attention analysis algorithm to maintain real-time performance under high load; the data compression technology ensures the continuous transmission of attention data in an environment with unstable network. Through tests in scenarios such as educational environments, workplaces, home spaces, and outdoor activities, several typical operating scenarios were observed: high-temperature operating scenario, when the environmental temperature exceeds 32°C, the system temperature rises, the quality of sensor signals deteriorates, and irregular fluctuations appear in the attention waveform; electromagnetic interference scenario, in areas with dense electronic devices, the quality of wireless transmission fluctuates, data latency increases, resulting in discontinuous attention scores; long-term use scenario, after continuous operation for more than 3 hours, the battery performance deteriorates, sensor drift intensifies, and the measurement deviation of the ratio of alpha waves and beta waves increases; scenario rapid switching, when the user moves between different environments such as classrooms, corridors, and playgrounds, changes in environmental light and noise cause fluctuations in attention data, and the system needs to frequently adjust parameters; multi-person interference environment, in crowded places such as classrooms or meeting rooms, the EEG activities of surrounding people and electronic devices generate cross-interference to the collection of attention signals, increasing the difficulty of extracting the true attention state. In special usage scenarios such as exam monitoring, it was found that continuous high-intensity attention states (beta waves continuously dominant) would accelerate system resource consumption and sensor performance decay. These operating scenarios exhibit different performance characteristics and potential risks, and require targeted intervention strategies.

[0065] Based on the observed characteristics of the operating scenarios, criteria for judging the intervention timing were established. In the high-temperature operating scenario, when the system temperature exceeds 42°C for 5 consecutive minutes, or the temperature rise rate is too large, heat management measures need to be implemented; when the environmental temperature is high and the user is focused for a long time, preventive intervention is implemented during a short attention transfer. For the electromagnetic interference scenario, when the transmission error rate is too high or the signal strength fluctuates violently, the communication mode needs to be adjusted; when regular interference is detected, key data is transmitted using the interference gap. In the long-term use scenario, the energy-saving mode is triggered when the battery power is low and the discharge is abnormal; when the usage time is long and the sensor drift exceeds the standard, calibration is performed after the evaluation period ends. For scenario switching, sensor parameters are immediately adjusted when the environmental conditions change significantly; frequent environmental fluctuations trigger the environmental adaptation mode. In the multi-person interference environment, when the number of surrounding people increases and the signal fluctuates abnormally, signal processing is enhanced; when the data consistency decreases, the strategy is adjusted before the next cycle. These judgment criteria comprehensively consider the system state, environmental conditions, and user behavior to ensure intervention at the appropriate time.

[0066] Based on the determined intervention timing, select corresponding processing methods. For high-temperature scenarios, adopt a dynamic frequency scaling strategy to adjust the processor frequency; implement task delay to postpone non-real-time tasks; enhance heat dissipation control; apply a temperature compensation algorithm to correct sensor data. For electromagnetic interference, enable frequency band adaptive technology to select the best communication channel; implement data grading transmission to ensure key information; expand the local cache to transmit when the signal is good; adjust the antenna directivity to reduce interference. In long-term usage scenarios, apply intelligent power management to adjust power consumption according to the attention state; arrange regular quick calibration; implement brightness adaptive control; perform progressive performance adjustment. For scenario switching, use scenario prediction caching to pre-load configurations in advance; dynamically adjust sensor parameters; prepare multiple preset modes; enable an environment adaptation algorithm. In a multi-person interference environment, strengthen spatial filtering to extract the target signal; apply user feature locking; implement a confidence scoring mechanism; provide interactive calibration when necessary. These methods specifically address performance issues in various scenarios.

[0067] According to the selected processing methods, formulate a systematic diagnostic rule to achieve the evaluation and regulation of the operating state of the attention glasses. The diagnostic rule first evaluates the core functions: when the sensor signal quality is abnormal, it is determined as a sensor problem; when the system response is delayed or the resource usage is abnormal, it is identified as a processing performance limitation; when the battery performance is abnormal, it is confirmed as a power problem; when the data transmission is abnormal, it is diagnosed as a communication failure. Further analyze the correlations between functions: judge the causality from the time sequence of sensor abnormalities and processing delays; the correlation between temperature and performance reveals heat dissipation problems; the association between power fluctuations and signal quality indicates the interference source. Adjust the criteria according to the specific scenario: appropriately relax the sensor requirements but strengthen temperature monitoring in high-temperature environments; distinguish environmental factors from equipment failures in high-interference environments; dynamically adjust the performance tolerance in long-term usage. Establish a special rule for attention monitoring: distinguish physiological changes from equipment problems when the score is abnormal; trigger calibration when the consistency is low; increase inspections when the state does not match the environment. This set of diagnostic rules ensures the reliability of the core functions of the attention glasses in complex environments through multi-level evaluation, providing continuous and effective attention monitoring services.

[0068] Step S104, according to the diagnostic rule, generate a fault domain, obtain emergency measures based on the fault domain; isolate the error source according to the emergency measures, and establish a repair plan based on the error source; generate a diagnostic report according to the repair plan to complete the diagnosis of the operating state of the attention glasses.

[0069] Specifically, in the actual operating environment of the attention glasses, the foregoing diagnostic rules are implemented, and the operating data is collected and analyzed through the system performance monitoring module. The diagnostic results show that the signal-to-noise ratio of the prefrontal electroencephalogram sensor drops to 22 dB and the fluctuation index reaches 0.18, exceeding the safety threshold; the task response delay of the processing system reaches 75 ms and the memory fragmentation rate reaches 28% in high-load scenarios, which is determined to be limited in processing performance; the battery voltage drop curve deviates from the standard curve by 23%, and the temperature and discharge rate show an abnormal correlation; the packet loss rate of the communication quality reaches 2.4% in crowded environments, and the transmission delay fluctuates significantly. Correlation analysis finds that the sensor anomaly appears 7 minutes earlier than the processing delay, and it is diagnosed as "system overload caused by sensor anomaly"; combined with scenario analysis, the system performance degrades after continuous operation in the classroom environment for 4 hours, which belongs to "comprehensive performance decline caused by long-term use". Through these diagnoses, the scope of the fault domain is defined: mainly involving the sensor subsystem, the processing subsystem, the power supply subsystem, and the communication subsystem. The fault space distribution is concentrated in the front sensor area of the device and the main board processing unit. The time characteristic is that it appears and gradually intensifies after 3.5 hours of use. The functional impact is mainly reflected in the decrease in the accuracy of attention data and the system response lag.

[0070] According to the defined fault domain, targeted emergency measures are selected. For the faults of the sensor subsystem, the following measures are implemented: activate the standby sensor channel, switch the data acquisition from the central front sensor to the two-side standby sensors; increase the sampling rate from 250 Hz to 500 Hz to increase data redundancy; enable the enhanced filtering algorithm to enhance the anti-interference ability; perform a quick calibration to reconstruct the sensor baseline. For the processing system limitations, resource optimization measures are taken: release the memory of non-critical tasks and recycle the fragments; downgrade the attention algorithm from full-band analysis to key-band analysis (mainly retaining alpha waves and beta waves); delay the execution of non-real-time tasks; increase the processing priority of core functions. For the power supply anomalies, an energy management plan is implemented: start the energy-saving mode to reduce the display brightness by 30%; turn off non-essential functions such as environmental perception and gesture recognition; adjust the discharge parameters to adapt to the current temperature environment; enable the voltage stabilization circuit to reduce the impact of fluctuations on the sensors. For the communication problems, guarantee measures are implemented: change the real-time transmission to batch transmission; increase the local cache capacity; simplify the transmission data structure and only retain the key attention indicators; enable the enhanced error correction coding to improve the anti-interference ability. These emergency measures ensure the availability of core functions and create conditions for isolating the error sources.

[0071] After the emergency measures were implemented, the system state was temporarily stable, and error source isolation analysis was carried out. Sensor anomaly analysis: After enabling the backup sensor, the data stability improved, and the fluctuation index decreased from 0.18 to 0.09, indicating a problem with the main sensor; the self-check program found that the impedance value of the central forehead sensor increased from the standard 5 kΩ to 12 kΩ; comparing the data at different usage times, it was found that the signal quality degradation was positively correlated with the wearing time and deteriorated rapidly when the temperature exceeded 36°C; detection found that sweat penetrated the electrode contact surface. The comprehensive judgment of the error source was "abnormal impedance caused by aging of the sensor contact surface". Processing system analysis: After reducing the algorithm complexity, the response was significantly improved; memory monitoring found that the attention algorithm had a situation of repeated allocation without release after running continuously for 4 hours; the buffer management efficiency decreased in high-attention fluctuation scenarios; performance limitations were significantly correlated with temperature increase. The confirmed error source was "resource leakage caused by algorithm memory management defects, superimposed with the influence of temperature". Power anomaly analysis: The discharge curve was still abnormal after the energy-saving mode; the internal resistance of the battery increased from 0.12 Ω to 0.26 Ω; the device had completed 312 charge-discharge cycles; there was a 2.3°C deviation between the temperature sensor and the actual temperature. The confirmed error source was "increased internal resistance caused by battery aging, superimposed with inaccurate temperature compensation". Communication problem analysis: After reducing the transmission priority, the packet loss rate decreased; the signal strength in a specific direction attenuated abnormally; the transmit power fluctuated unstably; the signal anomaly was aggravated when a metal object was close. The confirmed error source was "directional signal attenuation caused by parameter drift of the wireless module".

[0072] Based on the isolated error sources, a system repair plan was established. For the problem of "aging of the sensor contact surface": Design a new hydrophobic nano-coated electrode to improve the anti-sweat penetration ability; add an automatic impedance matching circuit to adjust the parameters of the preamplifier in real time; develop a sensor degradation compensation algorithm to adjust the gain and filtering parameters according to the usage duration; add a sensor cleaning reminder function to prompt cleaning when the cumulative usage exceeds 20 hours. For the "algorithm memory management defect": Repair the memory leak problem in the attention algorithm and optimize the spectrum analysis buffer management; implement a real-time memory monitoring mechanism to automatically trigger garbage collection; dynamically adjust the algorithm complexity according to the available resources; improve the heat dissipation design to reduce the processor temperature. For the "increased internal resistance of the aging battery": Develop an adaptive charge-discharge control algorithm to adjust the charging parameters according to the change in internal resistance; recalibrate the temperature sensor to improve the temperature compensation accuracy; add a battery health monitoring function to give early warning of the replacement requirement; optimize the power distribution strategy to avoid instantaneous large current demands. For the "parameter drift of the wireless module": Correct the transmit power control algorithm; implement an adaptive modulation and coding scheme to adjust the data rate according to the signal quality; dynamically adjust the transmit power according to the environmental interference and battery status; improve the circuit shielding design to reduce internal interference. These repair plans form a three-level solution system for short-term, medium-term, and long-term, which not only addresses the current faults but also prevents similar problems from occurring again.

[0073] In some embodiments, generating a diagnostic report according to the repair solution includes: generating a diagnostic record according to the repair solution; the diagnostic record includes a complete problem discovery process, a fault domain definition method, an emergency response strategy, an error source location technique, and implementation details of the solution; extracting experience points according to the diagnostic record; constructing a processing file according to the experience points, and generating a diagnostic report according to the processing file.

[0074] Summarize the foregoing repair solutions to form a complete record of the operating status diagnosis of the attention glasses. In the repair solution, the hydrophobic nano-coating electrode design, automatic impedance matching circuit, sensor degradation compensation algorithm, and cleaning reminder function for "aging of the sensor contact surface" significantly improve the stability of the sensor under long-term wearing and in a humid environment; for the "algorithm memory management defect", memory leak repair, real-time monitoring mechanism, dynamic complexity adjustment, and heat dissipation optimization solve the problem of performance degradation of the system under continuous high load; for the "increase in internal resistance due to battery aging", adaptive charge and discharge control, temperature sensor calibration, battery health monitoring, and power optimization extend the device's battery life and improve power supply stability; for the "parameter drift of the wireless module", power control algorithm correction, adaptive modulation and coding, dynamic power adjustment, and electromagnetic shielding improvement enhance the communication reliability in complex environments. The sorted diagnostic record contains a complete problem discovery process, a fault domain definition method, an emergency response strategy, an error source location technique, and implementation details of the solution. The record shows that the failure modes of the attention glasses have obvious time correlations (performance degradation after 3.5 hours of use) and environmental dependencies (significant effects of temperature, humidity, and electromagnetic environment), and most problems show progressive deterioration rather than sudden failures. During the diagnostic process, correlation analysis methods (such as the temporal correlation between sensor anomalies and processing delays) and scenario analysis (such as the long-term use pattern in a classroom environment) are particularly effective for accurately locating complex faults. The multi-level architecture of the repair solution (from parameter adjustment to hardware upgrade) ensures that the core functions can be maintained under different conditions, reflecting the importance of the system's adaptive design.

[0075] Based on the sorted diagnostic records, extract key experience points to form a knowledge system for diagnosing the operating status of the attention glasses. From the problem discovery process, extract the following sensor performance experiences: the EEG sensor is extremely sensitive to sweat, and the contact impedance increases significantly after more than 3 hours of use, and the high-temperature environment (>36°C) accelerates the performance degradation; the decline in sensor signal quality often occurs prior to other performance problems and can be used as an early warning indicator for system degradation; standby channel switching and sampling rate increase are effective temporary measures to address the decline in sensor performance. From the fault domain definition method, summarize the following processing performance experiences: the attention algorithm is prone to trigger memory management problems in frequently fluctuating scenarios (such as children's attention training); for every 5°C increase in temperature, the algorithm processing performance decreases by an average of 12%; when reducing the algorithm complexity, first degrading the non-critical frequency band analysis can retain the core functions to the greatest extent. Based on the analysis of emergency response strategies, obtain the following power management experiences: the battery cycle life of the attention glasses is approximately 350 times, and the internal resistance increases significantly when approaching the end of life; the temperature sensor deviation is a hidden cause of power management problems, affecting the accuracy of charge and discharge strategies; the display module is the component with the highest power consumption, and reducing its performance first when the power supply is abnormal can effectively extend the emergency operation time. From the error source location technology, extract the following communication stability experiences: in crowded environments, data transmission should adopt batch mode instead of real-time transmission; attention data has highly redundant characteristics, and only transmitting key indicators (such as the α / β ratio) in crisis situations can still maintain the core functions; the performance of the wireless module is highly correlated with the device wearing position and the user's head orientation. According to the implementation details of the solution, summarize the following comprehensive system experiences: the faults of the attention glasses exhibit obvious chain reaction characteristics, and initial sensor abnormalities will gradually lead to an increase in processing load, temperature rise, and accelerated battery consumption; system diagnosis should focus on high-risk scenarios with a usage duration exceeding 3 hours, a temperature exceeding 38°C, and a memory occupancy exceeding 85%; multi-channel information cross-verification (such as comparing sensor data at different positions) is an effective method to improve the diagnostic accuracy.

[0076] Based on the refined experience points, construct an operation status processing file for the attention glasses to form a systematic problem identification and processing framework. Utilize the sensor performance experience to determine the fault characteristics and processing strategies of the sensor system. For example, according to the characteristic that the electroencephalogram sensor is sensitive to sweat, design an automatic impedance detection and warning mechanism. Apply the processing performance experience to establish the monitoring standards and optimization methods of the processing system. For example, based on the experience of the influence of temperature on algorithm performance, implement a temperature-adaptive processing strategy adjustment. Combine the power management experience to establish a battery health assessment and energy optimization plan. For example, according to the battery cycle life data, predict the battery performance and give an early warning. Integrate the communication stability experience to form a communication quality guarantee and exception handling process. For example, based on the transmission strategy experience in crowded environments, automatically switch the communication mode. The processing file is organized in two dimensions: function module and fault type. In the function module dimension, applying the comprehensive system experience, it is divided into four categories: sensor system, processing system, power system, and communication system. In the fault type dimension, it is divided into performance degradation type, parameter drift type, resource depletion type, and external interference type. Establish a standardized processing process for each type of fault: First, determine the fault feature recognition criteria. For example, if the sensor impedance exceeds 10 kΩ, it is determined as an abnormal contact; if the memory fragmentation rate exceeds 25%, it is determined as an abnormal resource management. Secondly, standardize the emergency handling process, clarify the handling priority and resource allocation strategy. For example, the core attention monitoring function always maintains the highest resource priority. Then, unify the error source location method, including isolation test steps and judgment basis. For example, judge the main sensor fault by the performance change after enabling the standby sensor. Finally, standardize the selection criteria for the repair plan, and select an appropriate solution based on the fault severity, resource availability, and usage scenario requirements. The processing file also contains a case library for handling typical scenarios: classroom attention monitoring scenario, focusing on sensor drift and battery consumption caused by long-term use; cognitive training scenario, emphasizing algorithm stability and processing performance guarantee; mobile monitoring scenario, highlighting communication reliability and environmental adaptability. The file organically connects symptoms, causes, and solutions through a decision tree structure to support rapid response and processing automation, and sets differentiated processing strategies for different user groups (students, professionals, researchers) to balance the needs of usability and professionalism.

[0077] Based on the constructed processing file, a comprehensive diagnostic report on the operating status of the attention glasses is generated, providing a basis for system maintenance and improvement. The head of the diagnostic report outlines the background and process of this diagnosis: after 4 hours of continuous use in a classroom environment, the accuracy of attention data decreases and the response latency occurs in the system. Through the diagnostic rules of the above steps, it is determined as the decline of multi-system performance, and four core error sources are located: sensor aging, algorithm resource leakage, battery performance degradation, and communication parameter drift. The main body of the report details the health status assessment of each subsystem: the health of the sensor system is rated as "needs maintenance", and the key indicators deviate from the normal value by 18%, mainly affected by sweat penetration and long-term use; the health of the processing system is rated as "needs optimization", and the performance reserve decreases by 28%, and there are defects in memory management; the health of the power system is rated as "close to critical", the battery has completed 89% of its designed life, and the internal resistance shows an obvious upward trend; the health of the communication system is rated as "needs adjustment", and the directional performance decreases by 23%, and it is vulnerable to environmental interference. The analysis part of the report evaluates the effect of the current repair plan: short-term measures (parameter adjustment, mode switching) have restored the basic functions of the system; medium-term measures (firmware update, algorithm optimization) are being implemented, and it is expected to solve 80% of the stability problems; long-term measures (hardware upgrade) have been included in the product iteration plan. The recommendation part of the report puts forward the improvement direction: strengthen the sensor protection design to improve the sweat resistance performance; optimize the memory management mechanism to enhance the resource recycling efficiency; improve the battery management algorithm to extend the effective service life; enhance the wireless transmission stability to improve the environmental adaptability. The summary part of the report emphasizes that the performance stability of the attention glasses is closely related to the usage environment and method. It is recommended to follow the usage mode of "3 hours - rest - calibration" during high-intensity use and regularly perform system health checks to prevent inaccurate data and degraded user experience caused by performance decline.

[0078] In some embodiments, the completion of the operating status diagnosis of the attention glasses includes: obtaining the operating rules of the attention glasses according to the diagnostic report; improving the diagnostic criteria based on the operating rules, and performing status evaluation based on the diagnostic criteria; and outputting the diagnostic results of the attention glasses according to the status evaluation.

[0079] Verify the diagnostic report generated in the above steps and deeply analyze the operating rules of the attention glasses. The assessment of "needs maintenance" for the sensor system in the diagnostic report reflects the stability problem of the contact EEG sensor; the judgment of "needs optimization" for the processing system in the diagnostic report reveals the challenges of algorithm resource management; the "near critical" state of the power system in the diagnostic report indicates the association between battery aging and temperature compensation; the conclusion of "needs adjustment" for the communication system in the diagnostic report demonstrates the adaptability problem of wireless transmission in complex environments. By analyzing these evaluation results in the diagnostic report, the core operating rules of the attention glasses are summarized: time accumulation effect, the system performance shows obvious time accumulation characteristics, and most faults occur after continuous operation for 3-4 hours; environmental adaptability, environmental factors have a significant impact on the system, especially temperature changes and personnel density; resource balance, the system load distribution is uneven, and attention algorithm processing, display rendering, and wireless transmission are the main resource consumption points; fault chain effect, the initial sensor drift will trigger a chain reaction; recovery mechanism, the performance recovery has hysteresis, and the system needs to go through a calibration and warm-up process after rest. These operating rules indicate that the diagnosis of the operating state of the attention glasses needs to be comprehensively considered from five aspects: time accumulation effect, environmental adaptability, resource balance, fault chain effect, and recovery mechanism.

[0080] According to the summarized operation rules (including time cumulative effect, environmental adaptability, resource balance, fault chain effect and recovery mechanism), improve the diagnostic criteria for the attention glasses. For the time cumulative effect, establish a segmented diagnostic criterion based on the usage duration: 0 - 2 hours is the "standard operation period", with the sensor impedance fluctuation < 15% and the algorithm response delay < 30 ms being normal; 2 - 4 hours is the "performance transition period", allowing the sensor impedance to increase by 25% and the response delay to increase to 50 ms; more than 4 hours is the "performance decline period", and the system status needs to be closely monitored. For environmental adaptability, establish an environmental adaptability diagnostic criterion: in a high - temperature environment, the battery parameter standards are appropriately relaxed; in a crowded area, the communication packet loss rate threshold is adjusted accordingly; in an environment with frequent light changes, the tolerance for sensor signal fluctuations is increased. For resource balance, establish a resource balance diagnostic criterion: the processor load, memory occupancy and communication bandwidth should maintain a reasonable ratio, and the power consumption allocation follows the principle of core function priority. For the fault chain effect, establish a fault chain effect diagnostic criterion: when a certain system index is abnormal, warn of the possible chain problems. For the recovery mechanism, establish a recovery mechanism diagnostic criterion: after a short rest, the core indicators should recover to more than 85% of the nominal value; after full calibration, the sensor accuracy should reach more than 90% of the factory standard; after system pre - heating, the consistency of the algorithm analysis results should reach a qualified level. These improved diagnostic criteria (including the time cumulative effect diagnostic criterion, environmental adaptability diagnostic criterion, resource balance diagnostic criterion, fault chain effect diagnostic criterion and recovery mechanism diagnostic criterion) provide a more comprehensive and accurate standard system for status assessment.

[0081] Based on the perfect diagnostic criteria (including time accumulation effect diagnostic criteria, environmental adaptability diagnostic criteria, resource balance diagnostic criteria, fault chain effect diagnostic criteria and recovery mechanism diagnostic criteria), the current state of the attention glasses is evaluated. According to the time accumulation effect diagnostic criteria, the sensor system is evaluated: the forehead sensor impedance exceeds the standard by 28%, which exceeds the allowable range of the "performance transition period" but is still below the "functional critical value"; the sensor signal stability index is 0.78, which is in the "acceptable" range. According to the recovery mechanism diagnostic criteria, the sensor recovery ability is evaluated: after rest, it can recover to 82% of the nominal value, which is slightly lower than the standard; the accuracy after calibration is 91%. The sensor system is comprehensively evaluated as "maintenance required but functionally available". According to the time accumulation effect diagnostic criteria, the processing system is evaluated: the algorithm response delay meets the expectation of long-term use. According to the resource balance diagnostic criteria, the processing resources are evaluated: the resource balance test shows that the memory usage is low; the garbage collection trigger frequency is higher than the health standard. According to the recovery mechanism diagnostic criteria, the consistency of the algorithm analysis is acceptable after the system is warmed up. The processing system is comprehensively evaluated as "needs optimization but performance is acceptable". The power system was evaluated according to the environmental adaptability diagnostic criteria: the battery internal resistance increased significantly, approaching the design limit; the temperature sensor deviation exceeded the allowable range; the voltage stability test showed that the fluctuation was in the warning range; the load response test met the characteristics of the aging battery. The power system was comprehensively evaluated as "critical state, needing attention". The communication system was evaluated according to the environmental adaptability diagnostic criteria: the packet loss rate was acceptable under standard conditions; the directional test showed that the signal attenuation was obvious at specific angles. According to the recovery mechanism diagnostic criteria, the communication performance was improved after the system was restarted; the anti-interference ability was medium. The communication system was comprehensively evaluated as "performance degraded but reliability is acceptable".

[0082] Based on a comprehensive status assessment (including the "needs maintenance but is still functional" status of the sensor system, the "needs optimization but the performance is acceptable" status of the processing system, the "critical status, requires attention" status of the power supply system, and the "performance degradation but still has acceptable reliability" status of the communication system), the final diagnosis result of the attention glasses is output. According to the comprehensive assessment of the "needs maintenance but is still functional" status of the sensor system, the "needs optimization but the performance is acceptable" status of the processing system, the "critical status, requires attention" status of the power supply system, and the "performance degradation but still has acceptable reliability" status of the communication system, the diagnosis result shows that the overall device is in the "functional but needs maintenance" state, can still be used, but it is recommended to conduct professional maintenance in the near future. The key performance indicators show that the reliability of attention data is 87%, which still meets the basic application requirements; the system battery life is shorter than that of new devices but can still support daily use; the environmental adaptability has decreased, especially in high-temperature and crowded environments; the software functions are complete, but the performance of high-load tasks has degraded. For the "functional but needs maintenance" state, usage suggestions are put forward: adjust the usage mode, adopt a reasonable work-rest rhythm; regularly execute calibration procedures; avoid using the device in adverse environments for a long time; give priority to using the local processing mode; maintain good device maintenance habits. At the same time, for the "functional but needs maintenance" state, it is recommended to carry out system maintenance as planned: perform software updates in the near future, replace key components in the short term, and consider hardware upgrades in the medium and long term. The diagnosis result also includes a prediction of performance trends: if not maintained, it is expected that the device will reach the "functionally critical" state after a certain period of use; if maintained as recommended, it can be restored to a good state and the service life can be extended. It is summarized that although there are multiple performance indicators of this attention glasses that have declined, the core functions are still reliable, and through appropriate adjustment and maintenance, it can continue to provide effective services.

[0083] The provided method has at least the following beneficial effects:

[0084] 1. Multidimensional monitoring and intelligent analysis improve diagnostic accuracy: Through systematic data collection, curve analysis, and alarm limit setting, this method establishes a comprehensive status monitoring system. Combining multi-dimensional correlation analysis and fault domain definition technology, it greatly improves the accuracy of diagnosing the operating status of attention glasses, can effectively distinguish normal usage fluctuations from real performance anomalies, discover potential fault hazards in advance, reduce the misdiagnosis rate, and improve the timeliness of early warning.

[0085] 2. Adaptive diagnostic strategy optimizes resource consumption balance: By adopting an intervention timing judgment based on the operating scenario and a multi-level processing method selection mechanism, combined with precise error source isolation technology, the diagnostic process can dynamically adjust resource allocation according to system load, battery status, and function importance. While ensuring the stable operation of core functions, it completes necessary diagnostic tasks, effectively reducing the impact of the diagnostic process on system performance and solving the problem of resource constraints in portable devices.

[0086] 3. Diagnosis model evolution through experience accumulation and rule summarization: By systematically organizing diagnostic records, refining experience points, and constructing processing archives, a complete knowledge system is formed. Together with the rule summarization of operation patterns and the improvement mechanism of diagnostic criteria, the diagnostic model can continuously learn and self-optimize, automatically adjusting evaluation criteria according to the device's historical performance and environmental changes, enhancing the system's adaptability to different user usage patterns and environmental conditions, and extending the effective service life of the attention glasses.

[0087] To execute the operation status diagnosis method of the attention glasses corresponding to the above method embodiments to achieve the corresponding functions and technical effects. Refer to Figure 2 , Figure 2 FIG. shows a structural block diagram of an operation status diagnosis device 200 provided by an embodiment of the present application. For ease of description, only the parts related to this embodiment are shown. The operation status diagnosis device 200 provided by the embodiment of the present application includes:

[0088] A data acquisition unit 201, configured to acquire operation data of the attention glasses, mark the detection positions, draw a status curve according to the detection positions, generate a monitoring table based on the status curve; extract a normal range in the monitoring table; set an alarm limit according to the normal range; determine an abnormal standard based on the alarm limit;

[0089] A fluctuation determination unit 202, configured to determine fluctuation points according to the abnormal standard, generate a change trajectory according to the fluctuation points; sort out problem sources based on the change trajectory, form a fault spectrum according to the problem sources; test operation indicators according to the fault spectrum, determine a health degree according to the operation indicators, draw a performance graph based on the health degree, and generate an evaluation table according to the performance graph;

[0090] An attenuation statistics unit 203, configured to statistically analyze the attenuation trend according to the evaluation table, calculate performance degradation according to the attenuation trend, predict the influence range based on the performance degradation, and determine an optimization measure according to the influence range; determine an operation scenario according to the optimization measure, determine an intervention timing according to the operation scenario, select a processing method based on the intervention timing, and formulate a diagnostic rule according to the processing method;

[0091] A diagnosis completion unit 204, configured to generate a fault domain according to the diagnostic rule, obtain an emergency measure according to the fault domain; isolate the error source according to the emergency measure, establish a repair plan according to the error source; generate a diagnostic report according to the repair plan, and complete the operation status diagnosis of the attention glasses.

[0092] The above-mentioned operating status diagnosis device 200 can implement the operating status diagnosis method of the attention glasses in the above method embodiment. The optional items in the above method embodiment are also applicable to this embodiment and will not be elaborated here. The remaining content of the embodiment of the present application can refer to the content of the above method embodiment and will not be repeated in this embodiment.

[0093] Figure 3 It is a schematic structural diagram of a computer device provided in an embodiment of the present application. As Figure 3 shown, the computer device 3 in this embodiment includes: at least one processor 30 ( Figure 3 only one is shown here), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30. When the processor 30 executes the computer program 32, it implements the steps in any of the above method embodiments.

[0094] The computer device 3 may be a computing device such as a smart phone, a tablet computer, a desktop computer, and a cloud server. The computer device may include but is not limited to the processor 30 and the memory 31. Those skilled in the art can understand that Figure 3 this is only an example of the computer device 3 and does not constitute a limitation on the computer device 3. It may include more or fewer components than those shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0095] The so-called processor 30 may be a central processing unit (CPU), and the processor 30 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0096] In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 3. Further, the memory 31 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 31 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0097] In addition, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0098] An embodiment of the present application provides a computer program product, and when the computer program product runs on a computer device, the computer device is caused to implement the steps in each of the above method embodiments when executed.

[0099] In several embodiments provided in the present application, it can be understood that each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, the program segment, or the part of code includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block may occur in a different order from that marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.

[0100] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0101] The specific embodiments described above further elaborate on the purpose, technical solution, and beneficial effects of this application. It should be understood that the above are only specific embodiments of this application and are not used to limit the protection scope of this application. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. A method for diagnosing the operating state of an attention glasses, characterized in that Including: Obtain the operation data of the attention glasses, mark the detection positions, draw a status curve according to the detection positions, and generate a monitoring table based on the status curve; Extract the normal range in the monitoring table; set the warning limit according to the normal range; Determine the abnormality standard based on the warning limit; According to the abnormality standard, determine the fluctuation points, generate a change trajectory according to the fluctuation points; sort out the problem sources based on the change trajectory, and form a fault spectrum according to the problem sources; Test the operation indicators according to the fault spectrum, determine the health degree according to the operation indicators, draw a performance graph based on the health degree, and generate an evaluation table according to the performance graph; Statistical attenuation trend according to the evaluation table, calculate the performance decline according to the attenuation trend, predict the influence range based on the performance decline, and determine the optimization measures according to the influence range; Determine the operation scenario according to the optimization measures, determine the intervention timing according to the operation scenario, select the processing method based on the intervention timing, and formulate a diagnostic rule according to the processing method; Generate a fault domain according to the diagnostic rule, obtain emergency measures according to the fault domain; isolate the error source according to the emergency measures, and establish a repair plan according to the error source; Generate a diagnostic report according to the repair plan to complete the diagnosis of the operation status of the attention glasses.

2. The method according to claim 1, characterized in that, The obtaining the operation data of the attention glasses and marking the detection positions includes: Mark the detection positions on the circuit board of the attention glasses using a high-precision laser positioning system, and perform electrical characteristic verification, heat dissipation characteristic verification, and signal quality verification on the detection points corresponding to each detection position; Install high-precision sensors at each detection position, configure the sampling period according to the importance level of the parameters; generate an identification code including parameter type, sampling requirements, and calibration coefficient on a specific layer of the circuit board by laser etching to generate a high-precision three-dimensional coordinate file; the specific layer includes the power management unit area, the image processor area, the biosensor area, and the wireless communication module area.

3. The method according to claim 1, characterized in that, The drawing the status curve according to the detection positions and generating the monitoring table based on the status curve includes: Draw voltage, current, and power consumption status curves for the power management unit of the attention glasses, and the monitoring table includes impedance matching error requirements; Draw processing frame rate, calculation load, and cache usage status curves for the image processor of the attention glasses, and the monitoring table contains grounding resistance and EMI protection requirements; Draw sampling frequency, signal quality, and temperature drift status curves for the biosensor of the attention glasses, and the monitoring table includes crosstalk isolation degree requirements; Draw signal strength, data throughput, and packet loss rate status curves for the wireless communication module of the attention glasses.

4. The method according to claim 1, wherein The determining the fluctuation points according to the abnormality standard and generating the change trajectory according to the fluctuation points includes: Determine that the sensor signal-to-noise ratio is lower than the preset threshold and the fluctuation index exceeds the standard, the processing system response delay exceeds the standard and the memory fragmentation rate is abnormal, the battery voltage curve deviates from the standard, and the communication packet loss rate exceeds the standard as the fluctuation points; Generate the change trajectory including time characteristics, spatial distribution, and functional impacts. The time characteristics are manifested as an exacerbation of faults after a preset usage duration. The spatial distribution is concentrated in the sensor area and the processing unit. The functional impacts are manifested as a decrease in data accuracy and a lag in system response.

5. The method according to claim 1, wherein Sort out the problem sources based on the change trajectory, and form a fault spectrum according to the problem sources, including: Obtain the problem sources through correlation analysis based on the change trajectory; Generate a fault spectrum including sensor, processing, power supply, and communication subsystems according to the problem sources.

6. The method according to claim 1, wherein Calculate the performance decline according to the attenuation trend, including: Calculate the overall performance decline rate and the core function availability index according to the attenuation trend, in combination with the operation rules of time accumulation effect, environmental adaptability, resource balance, fault chain effect, and recovery mechanism; Generate the performance decline according to the availability index, and the performance decline is used to predict the time threshold for the device to reach the function critical state.

7. The method according to claim 1, wherein Generate a diagnostic report according to the repair plan, including: Generate a diagnostic record according to the repair plan; the diagnostic record includes the complete problem discovery process, fault domain definition method, emergency response strategy, error source location technology, and solution implementation details; Extract experience points according to the diagnostic record; Construct a processing file according to the experience points, and generate a diagnostic report according to the processing file.

8. The method according to claim 1, wherein Complete the operation status diagnosis of the attention glasses, including: Obtain the operation rules of the attention glasses according to the diagnostic report; Improve the diagnostic criteria according to the operation rules, and perform status assessment based on the diagnostic criteria; output the diagnostic result of the attention glasses according to the status assessment.

9. A running state diagnosis device, characterized in that, Include: A data acquisition unit for acquiring the operation data of the attention glasses, marking the detection positions, drawing a status curve based on the detection positions, and generating a monitoring table based on the status curve; Extract the normal range in the monitoring table; set the alarm limit according to the normal range; Determine the abnormality standard based on the alarm limit; A fluctuation determination unit for determining fluctuation points according to the abnormality standard, generating a change trajectory based on the fluctuation points; sorting out problem sources based on the change trajectory, and forming a fault spectrum according to the problem sources; Test the operation indicators according to the fault spectrum, determine the health degree according to the operation indicators, draw a performance graph based on the health degree, and generate an evaluation table based on the performance graph; An attenuation statistics unit for statistically analyzing the attenuation trend according to the evaluation table, calculating the performance decline according to the attenuation trend, predicting the influence range based on the performance decline, and determining optimization measures according to the influence range; Determine the operation scenario according to the optimization measures, determine the intervention timing according to the operation scenario, select a processing method based on the intervention timing, and formulate a diagnostic rule according to the processing method; A diagnosis completion unit for generating a fault domain according to the diagnostic rule, obtaining emergency measures according to the fault domain; isolating the error source according to the emergency measures, and establishing a repair plan according to the error source; Generate a diagnostic report according to the repair plan to complete the operation status diagnosis of the attention glasses.

10. A computer device, characterized in that, It includes a memory and a processor; the memory is used for storing a computer program; the processor is used for executing the computer program and implementing the method according to any one of claims 1 to 8 when executing the computer program.

Images