Intelligent glasses data grading processing method, system and equipment and storage medium

Abstract

The invention relates to the technical field of Internet, in particular to a smart glasses data grading processing method, system and device and a storage medium, and the method comprises the steps: collecting related induction data through a plurality of sensors built in smart glasses, preprocessing the collected related induction data, and storing the data according to time nodes; performing grading operation on the related sensing data according to the priority and the processing requirement of the data; processing the data with different priorities by adopting corresponding algorithms; and dynamically scheduling a processor and storage resources of the intelligent glasses according to the priority and the processing requirement of the data. The method has the effect of improving the data processing efficiency.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, system, device and storage medium for hierarchical processing of smart glasses data. Background Art

[0002] As smart wearable devices become more and more popular in the market, smart glasses, as an emerging member, have become a key factor in determining the quality of user experience through their data collection and processing capabilities. In actual use, smart glasses can obtain a large amount of environmental data, such as light intensity and the wearer's posture information, with the help of various built-in sensors. These data play an indispensable role in realizing important functions such as environmental perception and health monitoring for smart glasses.

[0003] However, existing technologies have shortcomings in smart glasses data processing. Current data processing methods fail to fully consider the complexity and diversity of smart glasses data, resulting in low processing efficiency and high resource consumption, which to some extent affects the performance and endurance of smart glasses, limiting the further improvement of their functions and the optimization of user experience.

[0004] Therefore, based on the above problems, the prior art still needs to be improved. Summary of the invention

[0005] The purpose of this application is to provide a smart glasses data hierarchical processing method, system, device and storage medium, aiming to solve the problems of low processing efficiency and high resource consumption due to the complexity and diversity of data.

[0006] The first object of this application is to provide a method for hierarchical processing of smart glasses data, comprising: Collect relevant sensing data through several sensors built into the smart glasses, pre-process the collected relevant sensing data, and save them according to time nodes; Performing hierarchical operations on the relevant sensing data according to data priority and processing requirements; For data with different priorities, corresponding algorithms are used to implement processing; The processor and storage resources of smart glasses are dynamically scheduled based on data priority and processing requirements.

[0007] By adopting the above technical solutions, the data processing efficiency of smart glasses is improved, resource utilization is optimized, and data of different importance and processing requirements can be reasonably graded and processed. The corresponding algorithms are used to ensure user experience while reducing resource consumption. The processor and storage resources can be dynamically scheduled according to data priority and demand, thereby extending the battery life of smart glasses and improving user experience.

[0008] In a possible implementation of the present application, the plurality of sensors include an acceleration sensor and an ambient light sensor, the acceleration sensor is used for posture judgment, and the ambient light sensor is used for light detection.

[0009] By adopting the above technical solution, the posture information and ambient lighting information of the smart glasses wearer can be accurately obtained, providing a comprehensive and accurate data basis for subsequent data classification processing, further improving the accuracy and effectiveness of data processing, and optimizing the user experience of smart glasses in different environments. At the same time, it helps to make more rational use of resources and improve the performance and endurance of smart glasses.

[0010] In a possible implementation manner of the present application, the step of using the acceleration sensor for posture judgment includes: Setting a first acquisition frequency of the acceleration sensor; The angle value recording mode of the acceleration sensor is set to distinguish different directions, and the posture of the user wearing the smart glasses is divided into a vertical direction and a horizontal direction. The vertical direction includes lowering the head and looking up the head. The angle value in the lowering direction is represented by an even number for a positive value, and the angle value in the looking up direction is represented by an odd number for a negative value; the horizontal direction includes left tilting the head and right tilting the head. The angle value in the left tilting direction is represented by an odd number for a positive value, and the angle value in the right tilting direction is represented by an even number for a negative value; A plurality of angle values ​​are acquired based on the first acquisition frequency, and after removing a maximum value and a minimum value therefrom, a first average value of the remaining angle values ​​is calculated.

[0011] By adopting the above technical solution, the posture data of users wearing smart glasses can be accurately obtained with a specific collection frequency and a unique angle value recording method. The interference of abnormal values ​​can be reduced by removing the maximum value and taking the average value, thereby improving the accuracy and stability of posture judgment data, providing more reliable data support for subsequent data processing and analysis, helping to better understand users' posture habits and promptly discover abnormal posture situations, thereby improving the performance and practicality of smart glasses in posture monitoring.

[0012] In a possible implementation manner of the present application, the step of using the ambient light sensor for light detection includes: Setting a second acquisition frequency of the ambient light sensor; Acquire multiple light intensity values ​​based on the second acquisition frequency, and calculate a second average value of the remaining light intensity values ​​after removing the maximum value and the minimum value; The second average value is compared with a preset value correspondence table to obtain a code, and the code is saved according to time nodes.

[0013] By adopting the above technical solution, it is possible to obtain light intensity data at a set collection frequency, remove the extreme value and take the average value to improve data accuracy, and obtain the code by comparing with the numerical correspondence table and saving it according to time nodes, thereby achieving effective processing and standardized storage of light intensity data, which helps smart glasses to better perceive ambient lighting conditions, provide an accurate basis for making corresponding adjustments according to lighting changes (such as screen brightness adjustment, etc.), and improve the performance and practicality of smart glasses in light detection.

[0014] In a possible implementation manner of the present application, the step of performing a hierarchical operation on the relevant sensing data according to the priority and processing requirements of the data includes: dividing the relevant sensing data into real-time processing data and non-real-time processing data; Determining that the priority of the real-time processing data is a high priority, the real-time processing data is data that the smart glasses need to process immediately, including rapid changes in light intensity and abnormal posture information of the user wearing the glasses; The priority of the non-real-time processing data is determined to be low priority. The non-real-time processing data is data that can be processed later by the smart glasses, including long-term light intensity recording information and posture change trend information of the wearing user.

[0015] By adopting the above technical solution, it is possible to reasonably classify the relevant sensing data, distinguish between real-time processing data and non-real-time processing data, and clarify their priorities, so that smart glasses can perform targeted processing according to the importance and urgency of the data, ensuring timely response to key information such as rapid changes in light intensity and abnormal posture. At the same time, resources are reasonably arranged to process data such as long-term lighting and posture trends, thereby optimizing the data processing process, improving the overall performance and resource utilization efficiency of smart glasses, and enhancing user experience.

[0016] In a possible implementation manner of the present application, for data with different priorities, the steps of using corresponding algorithms to implement processing include: Determine whether the smart glasses are in idle time; If the smart glasses are not in idle time, the real-time processing data is processed using a fast response algorithm, and the processing steps of the real-time processing data include: Based on the angle value and the first average value, determining whether the abnormal posture information of the wearing user exists; If the abnormal posture information exists, sending a first prompt message; Based on the light intensity value and the second average value, acquiring the rapid change information, and dynamically adjusting the display brightness of the smart glasses; If the smart glasses are in idle time, the non-real-time processing data is processed using a resource optimization algorithm, and the processing steps of the non-real-time processing data include: Based on the angle value and the light intensity value, generating the light intensity record information and the posture change trend information; The light intensity record information and the posture change trend information are analyzed to generate a health report.

[0017] By adopting the above technical solution, the corresponding algorithm can be used for processing according to the idle state and data priority of smart glasses. When not idle, it can quickly respond to real-time data, handle posture abnormalities and prompts in time, adjust the display brightness, and ensure user safety and good experience; when idle, it can optimize resources for non-real-time data, analyze and generate health reports, etc., make full use of idle time to mine data value, improve the overall pertinence and effectiveness of data processing, optimize the functions and resource utilization of smart glasses, and enhance user experience and practicality of smart glasses.

[0018] In a possible implementation of the present application, the step of dynamically scheduling the processor and storage resources of the smart glasses according to the priority and processing requirements of the data includes: When the smart glasses receive the relevant sensing data, determining the priority of the relevant sensing data; If the relevant sensing data is high-priority real-time processing data, sufficient processor resources are allocated to ensure that the fast response algorithm can be quickly executed, and a high-speed storage area is created to quickly store and read the real-time processing data; If the relevant sensing data is low-priority non-real-time processing data, when the smart glasses are in idle time, the processor resources are reasonably allocated to process the resource optimization algorithm, and the non-real-time processing data is stored in a low-speed but large-capacity storage area in a compressed storage method, so as to analyze and process the non-real-time processing data; Continuously monitor the operating status and data processing status of the smart glasses, and dynamically adjust the allocation of processor and storage resources.

[0019] By adopting the above technical solution, it is possible to dynamically schedule processors and storage resources according to data priority, allocate sufficient resources to high-priority real-time data to ensure fast processing and storage, reasonably allocate resources to low-priority non-real-time data when idle and use compressed storage, continuously monitor and adjust allocation, improve resource utilization efficiency, ensure rapid response of real-time data, and provide suitable conditions for the analysis and processing of non-real-time data, optimize the data processing flow and overall performance of smart glasses, and enhance user experience.

[0020] The second object of the present application is to provide a smart glasses data classification processing system, the system comprising: Related sensing data acquisition module: collects related sensing data through several sensors built into the smart glasses, pre-processes the collected related sensing data, and saves them according to time nodes; Data hierarchical operation processing module: performs hierarchical operations on the relevant sensing data according to the priority and processing requirements of the data; Data algorithm implementation processing module: for data with different priorities, corresponding algorithms are used for implementation processing; Processor and storage resource scheduling module: Dynamically schedule the processor and storage resources of smart glasses according to data priority and processing requirements.

[0021] By adopting the above technical solutions, the data processing efficiency of smart glasses is improved, resource utilization is optimized, and data of different importance and processing requirements can be reasonably graded and processed. The corresponding algorithms are used to ensure user experience while reducing resource consumption. The processor and storage resources can be dynamically scheduled according to data priority and demand, thereby extending the battery life of smart glasses and improving user experience.

[0022] The third object of the present application is to provide a smart glasses data classification processing device, the device comprising: A memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned smart glasses data classification processing method.

[0023] The fourth objective of this application is to provide a storage medium.

[0024] The fourth application objective of this application is achieved through the following technical solutions: A storage medium stores a computer program that can be loaded by a processor and execute the above-mentioned smart glasses data classification processing method.

[0025] In summary, the present application includes at least one of the following beneficial technical effects: 1. Improve the data processing efficiency of smart glasses and realize the reasonable processing of data of different priorities.

[0026] 2. Optimize resource utilization, including processor and storage resources, to improve the performance and battery life of smart glasses. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flowchart of a smart glasses data classification processing method provided in an embodiment of the present application; Figure 2 It is a virtual structural diagram of a smart glasses data classification processing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0030] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0031] The present application embodiment provides a smart glasses data classification processing method, referring to Figure 1 , the main process of the method is described as follows: S1: collecting relevant sensing data through several sensors built into the smart glasses, preprocessing the collected relevant sensing data, and saving them according to time nodes; Among them, the smart glasses have built-in acceleration sensors (such as LIS2DH12TR three-axis acceleration sensors) and ambient light sensors (such as OPT3001 ambient light sensors). For the acceleration sensor, the first acquisition frequency is set to once every 5 seconds. The angle value recording method is set, and the posture of the user wearing the smart glasses is divided into vertical and horizontal directions based on the Z axis. The vertical direction includes lowering the head and looking up the head. The angle value in the lowering direction is represented by an even number for positive values, and the angle value in the looking up direction is represented by an odd number for negative values; the horizontal direction includes left tilting the head and right tilting the head. The angle value in the left tilting direction is represented by an odd number for positive values, and the angle value in the right tilting direction is represented by an even number for negative values. For the ambient light sensor, the second acquisition frequency is set to once every 5 seconds.

[0032] The acceleration sensor collects attitude data at a set frequency to obtain multiple angle values. For example, the acceleration sensor collects data 12 times in one minute, and then removes the maximum and minimum values ​​therefrom to calculate the first average value of the remaining angle values.

[0033] The ambient light sensor collects light intensity values ​​at a set frequency, also collecting data 12 times in one minute. After removing the maximum and minimum values, the second average value of the remaining light intensity values ​​is calculated. The second average value is then compared with the preset value correspondence table (which divides the illumination value range into 0 to 99) to obtain the corresponding two-digit code, and the corresponding time node is saved. The collected related sensing data (including posture data and light intensity data) are saved according to the time node.

[0034] S2: performing hierarchical operations on the relevant sensing data according to data priority and processing requirements; Among them, the relevant sensing data is divided into real-time processing data and non-real-time processing data. Real-time processing data is data that smart glasses need to process immediately, including information about rapid changes in light intensity and abnormal posture information of the user wearing it, and its priority is high. Non-real-time processing data is data that smart glasses can process later, including long-term light intensity recording information and posture change trend information of the user wearing it, and its priority is low.

[0035] S3: Use corresponding algorithms to process data with different priorities; Among them, the smart glasses determine in real time whether they are in idle time. If the smart glasses are not in idle time, the real-time processing data is processed using a fast response algorithm. Based on the angle value collected by the acceleration sensor and the calculated first average value, it is determined whether there is abnormal posture information of the wearing user. For example, if the angle value exceeds the normal range (such as outside the set range of plus or minus 89 degrees), it is determined that abnormal posture information exists, and at this time, a first prompt message is sent to the wearing user, such as through vibration or voice prompts. Based on the light intensity value collected by the ambient light sensor and the calculated second average value, the rapid change information of the light intensity is obtained. If the difference between the current light intensity value and the previously saved average value exceeds a certain threshold, it is determined that the light intensity changes rapidly, and the display brightness of the smart glasses is dynamically adjusted.

[0036] If the smart glasses are in idle time, the resource optimization algorithm is used to process the non-real-time processing data. Based on the angle value collected by the acceleration sensor and the light intensity value collected by the ambient light sensor, light intensity record information and posture change trend information are generated. For example, the average light intensity change trend and the posture angle value change trend over a period of time are counted. The light intensity record information and posture change trend information are analyzed to generate a health report. For example, the wearer's cervical spine health status is analyzed based on the posture change trend, and the light pattern of the wearer's environment is analyzed based on the light intensity record.

[0037] S4: Dynamically schedule the processor and storage resources of smart glasses based on data priority and processing requirements.

[0038] Among them, when the smart glasses receive relevant sensing data, the priority of the relevant sensing data is first determined. If the relevant sensing data is high-priority real-time processing data, sufficient processor resources are allocated to ensure that the fast response algorithm can be executed quickly. For example, the processor's main frequency is increased or multiple cores are allocated to process real-time data. At the same time, a high-speed storage area (such as a cache or fast flash memory area) is created to quickly store and read real-time processing data to ensure the timeliness of data processing. If the relevant sensing data is low-priority non-real-time processing data, when the smart glasses are in idle time, the processor resources are reasonably allocated to process the resource optimization algorithm. For example, the processor's main frequency is reduced to save energy, and at the same time, the non-real-time processing data is stored in a low-speed but large-capacity storage area (such as a specific partition of ordinary flash memory) by compressed storage, so as to analyze and process the non-real-time processing data and improve the utilization of storage resources. Continuously monitor the operating status and data processing of the smart glasses, and dynamically adjust the allocation of processors and storage resources. For example, if the smart glasses change from an idle state to a non-idle state, adjust the resource allocation in time to give priority to the processing of real-time processing data; if the amount of real-time processing data suddenly increases, further optimize the resource allocation to meet the processing requirements.

[0039] Specifically, in some possible embodiments, the plurality of sensors include an acceleration sensor and an ambient light sensor, the acceleration sensor is used for posture judgment, and the ambient light sensor is used for light detection.

[0040] Among them, the smart glasses have built-in acceleration sensors (such as LIS2DH12TR three-axis acceleration sensors) and ambient light sensors (such as OPT3001 ambient light sensors). In other embodiments, the smart glasses can also be equipped with other types of sensors, such as heart rate sensors and gyroscope sensors. Select a suitable heart rate sensor, such as the MAX30102 heart rate sensor, and install it in a position that is in close contact with the skin, such as the inner side of the temple of the smart glasses, so as to accurately detect the wearer's heart rate data. Set the sensor acquisition frequency to once every 10 seconds to ensure that the wearer's heart rate changes can be monitored in real time while avoiding excessive power consumption. The heart rate sensor continuously collects the wearer's heart rate data. Over a period of time, such as one minute, multiple heart rate values ​​are obtained, and after removing the maximum and minimum values, the average heart rate value is calculated. The heart rate data is combined with the posture data and the illumination data for analysis. For example, if it is detected that the wearer's heart rate is significantly increased when performing strenuous exercise (judged by the acceleration sensor), some functions of the smart glasses can be adjusted at this time, such as temporarily turning off some non-critical notification prompts to avoid disturbing the wearer. As part of real-time data processing, when the heart rate suddenly rises or falls beyond the normal range, it can be determined that the wearer may be in an abnormal state, such as over-exercise or physical discomfort. At this time, the smart glasses can send a second prompt message to remind the wearer to pay attention to the physical condition or adjust the intensity of exercise. In non-real-time data processing, long-term heart rate records can be analyzed together with posture change trends and light intensity records to generate a more comprehensive health report. For example, combining heart rate data and posture data of bowing the head for a long time can remind the wearer of the adverse effects that bowing the head for a long time with a high heart rate may have on the body.

[0041] A high-performance gyroscope sensor, such as the MPU6050 six-axis gyroscope sensor, is installed inside the frame of the smart glasses to accurately detect the rotation and movement direction of the wearer's head. The acquisition frequency of the gyroscope sensor is set to once every 3 seconds to capture the rapid movement and rotation changes of the head in a timely manner. The gyroscope sensor collects the rotation angle and movement direction data of the wearer's head. Over a period of time, such as 30 seconds, multiple data points are obtained and filtered to remove noise and outliers. The average angle of head rotation and the change trend of the movement direction are calculated. For example, if it is detected that the wearer frequently and quickly rotates his head left and right, it may indicate that the wearer is in a scene that requires rapid observation of the surrounding environment. In real-time processing data, the data of the gyroscope sensor can be combined with the data of the acceleration sensor to more accurately determine the abnormal posture of the wearer. For example, if the acceleration sensor detects a head-down posture, but the gyroscope sensor also detects a rapid rotation of the head, it may indicate that the wearer is doing some special activities rather than simply a bad posture. At this time, the abnormal posture prompt may not be sent. In non-real-time processing data, the data of the gyroscope sensor can be used to analyze the wearer's head movement habits and behavior patterns. For example, by combining long-term light intensity records and head rotation data, the wearer's head movement preferences in different lighting environments can be determined, thereby providing a more personalized basis for the functional adjustment of smart glasses. For example, if it is found that the wearer often turns his head quickly in a strong light environment, the smart glasses can automatically adjust the display brightness and contrast to improve visual comfort.

[0042] Specifically, in some possible embodiments, the step of using the acceleration sensor for posture judgment includes: Setting a first acquisition frequency of the acceleration sensor; The angle value recording mode of the acceleration sensor is set to distinguish different directions, and the posture of the user wearing the smart glasses is divided into a vertical direction and a horizontal direction. The vertical direction includes lowering the head and looking up the head. The angle value in the lowering direction is represented by an even number for a positive value, and the angle value in the looking up direction is represented by an odd number for a negative value; the horizontal direction includes left tilting the head and right tilting the head. The angle value in the left tilting direction is represented by an odd number for a positive value, and the angle value in the right tilting direction is represented by an even number for a negative value; A plurality of angle values ​​are acquired based on the first acquisition frequency, and after removing a maximum value and a minimum value therefrom, a first average value of the remaining angle values ​​is calculated.

[0043] The acquisition frequency of the acceleration sensor is set to once every 5 seconds. This frequency can be adjusted appropriately according to actual needs and factors such as battery life, but it is necessary to ensure that enough data can be obtained to accurately judge the posture. Considering the power consumption and data processing capabilities of smart glasses, the first acquisition frequency is set to once every 5 seconds. This frequency can ensure that enough data points are obtained within a certain period of time to accurately judge the posture without excessively consuming battery power. For example, if the frequency is set too high, the battery of the smart glasses may be consumed too quickly, affecting the user experience; if the frequency is set too low, the wearer's posture changes may not be captured in time, reducing the accuracy of posture judgment. A mechanism for dynamically adjusting the acquisition frequency is established, and it is adjusted according to the usage scenario and battery power of the smart glasses. For example, when the smart glasses are in a low-power state, the acquisition frequency can be automatically reduced to save power; when the wearer is in motion or needs more accurate posture judgment, the acquisition frequency can be appropriately increased. Assuming that the smart glasses detect that the battery power is less than 20%, the first acquisition frequency is reduced from once every 5 seconds to once every 10 seconds. When it is detected that the wearer is performing exercises such as running, the collection frequency can be increased to once every 3 seconds in order to more accurately judge posture changes.

[0044] Set the angle value recording method to distinguish postures in different directions. Based on the Z axis, the posture of the user wearing the smart glasses is divided into the vertical direction and the horizontal direction. The vertical direction includes lowering the head and looking up. The angle value in the lowering direction uses an even number to represent a positive value. For example, if the acceleration sensor detects +10 degrees, the angle value is 10, which means that the user lowers his head 10 degrees; the angle value in the looking up direction uses an odd number to represent a negative value. For example, if the acceleration sensor detects -15 degrees, the angle value is 15, which means that the user leans back 15 degrees. When the acceleration sensor detects +19.8 degrees, the angle value is 20, which means that the user lowers his head 20 degrees. When the acceleration sensor detects -20.4 degrees, the angle value is 21, which means that the user leans back 21 degrees. The horizontal direction includes left and right tilted heads. The angle value in the left tilted head direction uses an odd number to represent a positive value, and the angle value in the right tilted head direction uses an even number to represent a negative value, such as the above-mentioned lowering or looking up detection value recording. In order to more accurately judge the posture, the effective range of positive and negative angle values ​​is determined to be 0 to 89 degrees. This range can cover most daily head posture changes, while avoiding inaccurate judgments caused by excessive angle values. For example, if the detected angle value exceeds this range, such as a 95-degree head-down angle, it can be considered an abnormal value and can be specially processed or ignored in subsequent data processing.

[0045] According to the set acquisition frequency, the accelerometer continuously acquires the angle value data of the wearer's head posture. Within a period of time, such as one minute (satisfying 12 acquisitions), multiple angle values ​​are obtained. The acquired angle values ​​are processed to remove the maximum and minimum values. This is to reduce the impact of abnormal values ​​on posture judgment, such as abnormal angle values ​​that may be caused by the wearer's sudden and violent movements. The average value of the remaining angle values ​​is calculated, and this average value will serve as an important basis for judging the wearer's posture. By comparing with the set normal posture angle range, it can be judged whether the wearer's posture is normal and whether there are abnormal posture conditions, such as bowing the head for a long time or tilting the head excessively. For example, the accelerometer continuously acquires the angle value data of the wearer's head according to the set first acquisition frequency. Within one minute, multiple angle values ​​are obtained. Assuming that the first acquisition frequency is once every 5 seconds, 12 angle values ​​can be obtained within one minute. Within one minute, the angle values ​​collected by the accelerometer in sequence are: 12 degrees, 10 degrees, 8 degrees, 15 degrees, 14 degrees, 10 degrees, 10 degrees, 14 degrees, 10 degrees, 12 degrees, 10 degrees, 13 degrees. Remove the maximum value 14 and the minimum value 15 (odd numbers are negative), 12+10+8+10+10+14+10+12+10+(-13)=83 degrees. The first average value of the remaining angle values ​​is: the number of remaining data is 10, so the first average value is 83÷10=8.3 degrees. This first average value will serve as an important basis for judging the wearer's posture. For example, if the first average value is positive, it is within the direction of bowing and the value is large, it may indicate that the wearer bows his head for a long time; if it is within the range of the direction of raising the head and the value is large, it may indicate that the wearer raises his head frequently. The first average value +8.3 is stored as an even number 8 according to the time node, and the even number 8 means that the wearer bows his head an average of 8 degrees in 1 minute. If the first average value is -8.3, it is stored as an odd number 9, and the odd number 9 means that the wearer raises his head an average of 9 degrees in 1 minute.

[0046] Specifically, in some possible embodiments, the step of using the ambient light sensor for light detection includes: Setting a second acquisition frequency of the ambient light sensor; Acquire multiple light intensity values ​​based on the second acquisition frequency, and calculate a second average value of the remaining light intensity values ​​after removing the maximum value and the minimum value; The second average value is compared with a preset value correspondence table to obtain a code, and the code is saved according to time nodes.

[0047] Among them, in order to accurately detect the change of light intensity, while considering the power consumption and data processing capability of the smart glasses, the second acquisition frequency of the ambient light sensor is set to once every 5 seconds. The ambient light sensor continuously collects the light intensity value of the surrounding environment according to the set second acquisition frequency. In a period of time, for example, within one minute, multiple light intensity values ​​are obtained. Assuming that the second acquisition frequency is once every 5 seconds, 12 light intensity values ​​can be obtained within one minute. For example, within one minute, the light intensity values ​​collected by the ambient light sensor in sequence are: 1000lux, 1200lux, 800lux, 1100lux, 900lux, 1050lux, 1150lux, 950lux, 1000lux, 1100lux, 1050lux, 1200lux. The multiple light intensity values ​​obtained are processed to remove the maximum and minimum values. This is to reduce the impact of abnormal values ​​on light intensity judgment. In the above example, the maximum value is 1200lux and the minimum value is 800lux. After removing these two values, the remaining light intensity values ​​are: 1000lux, 1100lux, 900lux, 1050lux, 1150lux, 950lux, 1000lux, 1100lux, 1050lux, 1100lux.

[0048] Calculate the second average value of the remaining light intensity values. Add the remaining light intensity values ​​and then divide them by the number of remaining light intensity values ​​to obtain the second average value. In the above example, the sum of the remaining light intensity values ​​is: 1000+1100+900+1050+1150+950+1000+1100+1050+1100=10500lux. The number of remaining light intensity values ​​is 10, so the second average value is 10500÷10=1050lux. A numerical correspondence table is pre-set to divide the illumination value range into different intervals and assign a two-digit code to each interval. For example, the illumination value range can be divided into 0-999lux as interval one, with code "01"; 1000-1999lux as interval two, with code "02"; and so on. The purpose of this setting is to simplify continuous light intensity values ​​into specific codes for easy storage and subsequent data processing. The calculated second average value is compared with the preset value correspondence table to determine the illumination interval in which the average value is located, and the corresponding code is obtained. In the above example, the second average value is 1050 lux. According to the value correspondence table, it is in the second interval of 1000-1999 lux, so the obtained code is "02".

[0049] The obtained code is saved according to the time node. For example, the code can be stored in the storage device of the smart glasses together with the corresponding timestamp. In this way, the light intensity at different time points can be recorded to provide a basis for subsequent data analysis and application. Assuming that the current time is 10:30:00 on October 29, 2024, the code "02" is saved together with this time node. In the subsequent data analysis, the code at different time nodes can be viewed to understand the changing trend and law of light intensity.

[0050] Specifically, in some possible embodiments, according to the priority and processing requirements of the data, the step of performing a hierarchical operation on the relevant sensing data includes: dividing the relevant sensing data into real-time processing data and non-real-time processing data; Determining that the priority of the real-time processing data is a high priority, the real-time processing data is data that the smart glasses need to process immediately, including rapid changes in light intensity and abnormal posture information of the user wearing the glasses; The priority of the non-real-time processing data is determined to be low priority. The non-real-time processing data is data that can be processed later by the smart glasses, including long-term light intensity recording information and posture change trend information of the wearing user.

[0051] Among them, based on the timeliness of the data and the degree of impact on the functions of smart glasses, the relevant sensing data are divided into real-time processing data and non-real-time processing data. For the rapid change information of light intensity and the abnormal posture information of the wearer, these data have an immediate impact on the user's experience and safety, and need to be processed immediately by smart glasses, so they are divided into real-time processing data. For example, when the light intensity suddenly increases or decreases, it may cause discomfort to the user's vision. Smart glasses need to immediately adjust parameters such as display brightness to adapt to environmental changes; when abnormal user posture is detected, such as suddenly lowering or raising the head, it may indicate that the user is physically unwell or in a dangerous state, and smart glasses need to issue a reminder immediately. Long-term light intensity recording information and user posture change trend information, these data have relatively less urgent impact on users and can be processed at the right time, so they are divided into non-real-time processing data. For example, long-term light intensity recording can be used to analyze the lighting pattern of the user's environment so that smart glasses can automatically adjust parameters in different time periods to improve user experience; posture change trend information can be used to evaluate the user's health status or habits and provide users with long-term health advice.

[0052] Real-time processing data is determined as a high priority because the data needs to be processed in the shortest possible time to meet the immediate needs of users. When processing real-time processing data, smart glasses will prioritize the allocation of system resources to ensure that the data can be processed quickly. For example, when rapid changes in light intensity are detected, smart glasses will immediately adjust the display brightness, which may require calling the processor's high-priority task queue, prioritizing the data of the light sensor, and quickly calculating the appropriate display brightness value. For abnormal posture information of the user wearing it, smart glasses may immediately issue reminders through vibration, sound, etc., which requires a rapid response to the data of the acceleration sensor and real-time posture analysis and judgment. In order to ensure the processing speed of real-time processing data, smart glasses can adopt some optimization strategies, such as setting up a dedicated hardware acceleration module or optimization algorithm to reduce processing time. For example, for posture anomaly detection, algorithms such as fast Fourier transform can be used to analyze the data of the acceleration sensor in real time to quickly determine whether the user's posture is abnormal.

[0053] Non-real-time processing data is determined to be low priority because this data can be processed without affecting the user's immediate experience. When processing non-real-time processing data, smart glasses will process it when system resources are idle or under low load. For example, during the period when the user is not using smart glasses, or when the smart glasses are in low power mode, the long-term light intensity recording information and posture change trend information can be analyzed and processed. For non-real-time processing data, some batch processing or offline processing methods can be used to improve processing efficiency. For example, batch analysis of light intensity recording data over a period of time can be performed to find out the changing pattern of light intensity; offline analysis of the posture change trend information of the wearer can be performed to generate a health report or habit suggestion for the user.

[0054] Specifically, in some possible embodiments, for data with different priorities, the steps of using corresponding algorithms to implement processing include: Determine whether the smart glasses are in idle time; If the smart glasses are not in idle time, the real-time processing data is processed using a fast response algorithm, and the processing steps of the real-time processing data include: Based on the angle value and the first average value, determining whether the abnormal posture information of the wearing user exists; If the abnormal posture information exists, sending a first prompt message; Based on the light intensity value and the second average value, acquiring the rapid change information, and dynamically adjusting the display brightness of the smart glasses; If the smart glasses are in idle time, the non-real-time processing data is processed using a resource optimization algorithm, and the processing steps of the non-real-time processing data include: Based on the angle value and the light intensity value, generating the light intensity record information and the posture change trend information; The light intensity record information and the posture change trend information are analyzed to generate a health report.

[0055] Among them, the idle time of smart glasses can be defined as the time period when the user does not actively use the functions of the smart glasses and has no urgent data processing needs. For example, when the user is not watching videos, browsing information, or performing other operations that require real-time response from smart glasses, and there is no real-time processing data waiting to be processed, this period of time can be considered as the idle time of smart glasses. It can be determined whether the smart glasses are in idle time by monitoring the sensor usage of the smart glasses, user operation records, and the status of the data processing queue. For example, if the acceleration sensor and ambient light sensor do not detect obvious changes for a period of time, and there is no real-time processing data waiting to be processed, then it can be determined that the smart glasses are in idle time.

[0056] Based on the angle value and the first average value, it is determined whether there is abnormal posture information of the user wearing the device. For example, a threshold range of abnormal posture is set. If the first average value exceeds this range, or an obviously abnormal value appears in the angle value (such as the angle of lowering the head exceeds 45 degrees, the angle of raising the head exceeds 30 degrees, etc.), it is considered that there is abnormal posture information.

[0057] For example, within a period of time, the first average value of the angle value collected by the acceleration sensor is -25 degrees (indicating a large head tilt angle), which exceeds the range of normal posture. At this time, it can be determined that there is abnormal posture information. If abnormal posture information exists, the first prompt information is sent. The first prompt information can be a vibration, sound, or a prompt text displayed on the display screen of the smart glasses to remind the user to adjust the posture. For example, when it is detected that the user bows his head for a long time or tilts his head too much, the smart glasses can use vibration and sound to remind the user to "please pay attention to adjust the posture and protect the cervical spine."

[0058] Based on the light intensity value and the second average value, rapid change information is obtained. Whether there is rapid change information can be determined by comparing the difference between the current light intensity value and the light intensity value or the second average value at the previous moment. If the difference exceeds a certain threshold, it is considered that there is rapid change information. Dynamically adjust the display brightness of the smart glasses. According to the rapid change information, the smart glasses can use a corresponding algorithm to adjust the display brightness to adapt to different lighting environments. For example, a linear adjustment algorithm or an exponential adjustment algorithm can be used to adjust the display brightness according to the amplitude of the change in light intensity. For example, when the ambient light sensor detects that the light intensity suddenly increases, the smart glasses can quickly reduce the display brightness to avoid damage to the user's eyes; when the light intensity decreases, the smart glasses can appropriately increase the display brightness to ensure that the user can clearly see the content on the display screen. At the same time, when the wearer is using the display electronic device, the smart glasses box display electronic device can be connected wirelessly or wired, and the smart glasses send a display brightness adjustment signal to the display electronic device to protect the eye health of the wearer.

[0059] Based on the angle value and the light intensity value, light intensity record information and posture change trend information are generated. The angle value and light intensity value within a period of time can be statistically analyzed to obtain the distribution of light intensity and the trend of posture change. For example, by statistically analyzing the light intensity value within a period of time, the average value, maximum value, minimum value and other information of the light intensity in different time periods can be obtained, so as to understand the lighting law of the user's environment; by analyzing the angle value, the user's posture distribution in different time periods can be obtained, such as the time of lowering the head, the time of raising the head, the time of tilting the head left and right, etc., so as to understand the user's posture change trend. The light intensity record information and posture change trend information are analyzed to generate a health report. Based on the light intensity record information and posture change trend information, combined with medical knowledge and health standards, the user's health status can be evaluated and recommended. For example, according to the user's posture change trend, if it is found that the user lowers his head or raises his head for a long time, the user may be reminded to pay attention to the health of the cervical spine; according to the light intensity record information, if it is found that the user is often in a strong light or weak light environment, the user may be reminded to pay attention to eye protection. Health reports can be presented to users in the form of text, charts or voice, so that users can better understand their health status.

[0060] Specifically, in some possible embodiments, the steps of dynamically scheduling the processor and storage resources of the smart glasses according to the priority and processing requirements of the data include: When the smart glasses receive the relevant sensing data, determining the priority of the relevant sensing data; If the relevant sensing data is high-priority real-time processing data, sufficient processor resources are allocated to ensure that the fast response algorithm can be quickly executed, and a high-speed storage area is created to quickly store and read the real-time processing data; If the relevant sensing data is low-priority non-real-time processing data, when the smart glasses are in idle time, the processor resources are reasonably allocated to process the resource optimization algorithm, and the non-real-time processing data is stored in a low-speed but large-capacity storage area in a compressed storage method, so as to analyze and process the non-real-time processing data; Continuously monitor the operating status and data processing status of the smart glasses, and dynamically adjust the allocation of processor and storage resources.

[0061] When the smart glasses receive relevant sensing data, they first need to identify and classify the data to determine its priority. This can be done by reading the specific identifier of the data or judging based on the source and type of the data. For example, abnormal posture information from the acceleration sensor and rapid changes in light intensity from the ambient light sensor can be identified as high-priority real-time processing data; while long-term light intensity recording information and posture change trend information can be identified as low-priority non-real-time processing data.

[0062] If the relevant sensing data is high-priority real-time processing data, sufficient processor resources are allocated to ensure that the fast response algorithm can be executed quickly. This can be achieved by increasing the clock frequency of the processor, increasing the number of processing cores used, or prioritizing real-time processing tasks. For example, when the smart glasses detect that the user's posture is abnormal or the light intensity changes rapidly, the processor performance can be immediately improved to ensure that the fast response algorithm can complete the processing in the shortest time, send prompt information to the user in time, or adjust the display brightness. In order to quickly store and read real-time processing data, a high-speed storage area is created. This storage area can use storage media such as high-speed flash memory or memory to ensure that the data read and write speed can meet the requirements of real-time processing. For example, when the smart glasses receive real-time processing data, the data can be temporarily stored in the high-speed storage area so that the fast response algorithm can quickly read and process the data. After the processing is completed, the data can be transferred to other storage areas or backed up to free up space in the high-speed storage area.

[0063] If the relevant sensing data is low-priority non-real-time processing data, the processor resources are reasonably allocated to process the resource optimization algorithm when the smart glasses are in idle time. This can be achieved by reducing the clock frequency of the processor, reducing the number of processing cores used, or arranging non-real-time processing tasks in a low-priority task queue to wait for processing. For example, when the smart glasses are in idle time, the resource optimization algorithm can be started to analyze and process the long-term light intensity recording information and posture change trend information. During the processing, the allocation of processor resources can be dynamically adjusted according to the system load and resource usage to ensure the stability and efficiency of the system. The non-real-time processing data is stored in a low-speed but large-capacity storage area using compressed storage. This can be done by using a data compression algorithm, such as a lossless compression algorithm or a lossy compression algorithm, to compress and store the non-real-time processing data to reduce the storage space occupied. For example, long-term light intensity recording information and posture change trend information can be stored in the built-in storage chip or external storage card of the smart glasses using compressed storage. When analysis and processing are required, the data can be decompressed and read into the memory for processing.

[0064] Continuously monitor the operating status and data processing of the smart glasses, including the processor load, storage resource usage, and data processing task progress. This can be achieved by using system monitoring tools or sensors. For example, you can use the processor performance monitoring tool to monitor the processor load, use the storage device capacity monitoring tool to monitor the storage resource usage, and use the task manager to monitor the progress of data processing tasks. Dynamically adjust the allocation of processor and storage resources based on the monitored operating status and data processing. This can be achieved by adjusting the processor clock frequency, increasing or decreasing the number of processing cores used, adjusting the size of the storage area, or replacing the storage medium. For example, if it is detected that the processor load is too high, the priority of non-real-time processing tasks can be reduced to reduce the allocation of processor resources; if it is detected that the storage resources are insufficient, unnecessary data can be cleaned up or the capacity of the storage device can be increased.

[0065] Another embodiment of the present application provides a smart glasses data classification processing system, wherein, referring to Figure 2 , a smart glasses data classification processing system, comprising: Related sensing data acquisition module 100: collects related sensing data through several sensors built into the smart glasses, pre-processes the collected related sensing data, and saves them according to time nodes; Data classification operation processing module 200: performs classification operation on the relevant sensing data according to the priority and processing requirements of the data; Data algorithm implementation processing module 300: for data with different priorities, adopt corresponding algorithms to implement processing; Processor and storage resource scheduling module 400: dynamically schedules the processor and storage resources of the smart glasses according to the priority and processing requirements of the data.

[0066] The smart glasses data grading processing system provided in this embodiment can implement the various steps of the aforementioned embodiments due to the functions of its modules themselves and the logical connections between each other, and thus can achieve the same technical effects as the aforementioned embodiments. The principle analysis can be found in the relevant description of the steps of the aforementioned smart glasses data grading processing method, which will not be repeated here.

[0067] An embodiment of the present application further provides a smart glasses data grading processing device, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the above-mentioned smart glasses data grading processing method.

[0068] An embodiment of the present application further provides a storage medium, in which a computer program capable of being loaded by a processor and executing the above-mentioned smart glasses data classification processing method is stored.

[0069] The storage medium provided in this embodiment can achieve the same technical effects as the aforementioned embodiments because the computer program therein implements the various steps of the aforementioned embodiments after being loaded and run on the processor. The principle analysis can be found in the relevant description of the aforementioned method steps, which will not be repeated here.

[0070] The storage medium includes, for example, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0071] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0072] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0073] In addition, the term "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined, and is only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0074] Thus, any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0075] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for hierarchical processing of smart glasses data, characterized in that: include: Collect relevant sensing data through several sensors built into the smart glasses, pre-process the collected relevant sensing data, and save them according to time nodes; Performing hierarchical operations on the relevant sensing data according to data priority and processing requirements; For data with different priorities, corresponding algorithms are used to implement processing; The processor and storage resources of smart glasses are dynamically scheduled based on data priority and processing requirements.

2. The method for hierarchical processing of smart glasses data according to claim 1, characterized in that: The plurality of sensors include an acceleration sensor and an ambient light sensor. The acceleration sensor is used for posture judgment, and the ambient light sensor is used for light detection.

3. The method for hierarchical processing of smart glasses data according to claim 2, characterized in that: The steps of using the acceleration sensor for posture judgment include: Setting a first acquisition frequency of the acceleration sensor; The angle value recording mode of the acceleration sensor is set to distinguish different directions, and the posture of the user wearing the smart glasses is divided into a vertical direction and a horizontal direction. The vertical direction includes lowering the head and looking up the head. The angle value in the lowering direction is represented by an even number for a positive value, and the angle value in the looking up direction is represented by an odd number for a negative value; the horizontal direction includes left tilting the head and right tilting the head. The angle value in the left tilting direction is represented by an odd number for a positive value, and the angle value in the right tilting direction is represented by an even number for a negative value; A plurality of angle values ​​are acquired based on the first acquisition frequency, and after removing a maximum value and a minimum value therefrom, a first average value of the remaining angle values ​​is calculated.

4. The method for hierarchical processing of smart glasses data according to claim 3, characterized in that: The steps of using the ambient light sensor for light detection include: Setting a second acquisition frequency of the ambient light sensor; Acquire multiple light intensity values ​​based on the second acquisition frequency, and calculate a second average value of the remaining light intensity values ​​after removing the maximum value and the minimum value; The second average value is compared with a preset value correspondence table to obtain a code, and the code is saved according to time nodes.

5. The method for hierarchical processing of smart glasses data according to claim 4, characterized in that: According to the priority and processing requirements of the data, the steps of performing a hierarchical operation on the relevant sensing data include: dividing the relevant sensing data into real-time processing data and non-real-time processing data; Determining that the priority of the real-time processing data is a high priority, the real-time processing data is data that the smart glasses need to process immediately, including rapid changes in light intensity and abnormal posture information of the user wearing the glasses; The priority of the non-real-time processing data is determined to be low priority. The non-real-time processing data is data that can be processed later by the smart glasses, including long-term light intensity recording information and posture change trend information of the wearing user.

6. The method for hierarchical processing of smart glasses data according to claim 5, characterized in that: For data with different priorities, the steps of using corresponding algorithms to implement processing include: Determine whether the smart glasses are in idle time; If the smart glasses are not in idle time, the real-time processing data is processed using a fast response algorithm, and the processing steps of the real-time processing data include: Based on the angle value and the first average value, determining whether the abnormal posture information of the wearing user exists; If the abnormal posture information exists, sending a first prompt message; Based on the light intensity value and the second average value, acquiring the rapid change information, and dynamically adjusting the display brightness of the smart glasses; If the smart glasses are in idle time, the non-real-time processing data is processed using a resource optimization algorithm, and the processing steps of the non-real-time processing data include: Based on the angle value and the light intensity value, generating the light intensity record information and the posture change trend information; The light intensity record information and the posture change trend information are analyzed to generate a health report.

7. The method for hierarchical processing of smart glasses data according to claim 6, characterized in that: The steps to dynamically schedule the processor and storage resources of smart glasses based on data priority and processing requirements include: When the smart glasses receive the relevant sensing data, determining the priority of the relevant sensing data; If the relevant sensing data is high-priority real-time processing data, sufficient processor resources are allocated to ensure that the fast response algorithm can be quickly executed, and a high-speed storage area is created to quickly store and read the real-time processing data; If the relevant sensing data is low-priority non-real-time processing data, when the smart glasses are in idle time, the processor resources are reasonably allocated to process the resource optimization algorithm, and the non-real-time processing data is stored in a low-speed but large-capacity storage area in a compressed storage method, so as to analyze and process the non-real-time processing data; Continuously monitor the operating status and data processing status of the smart glasses, and dynamically adjust the allocation of processor and storage resources.

8. A smart glasses data classification processing system, characterized in that: include: Related sensing data acquisition module: collects related sensing data through several sensors built into the smart glasses, pre-processes the collected related sensing data, and saves them according to time nodes; Data hierarchical operation processing module: performs hierarchical operations on the relevant sensing data according to the priority and processing requirements of the data; Data algorithm implementation processing module: for data with different priorities, corresponding algorithms are used for implementation processing; Processor and storage resource scheduling module: Dynamically schedule the processor and storage resources of smart glasses according to data priority and processing requirements.

9. A smart glasses data classification processing device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes any one of the smart glasses data grading processing methods according to claims 1-7.

10. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes any one of the smart glasses data classification processing methods according to claims 1-7.

Images