A sound transmission accessory parameter optimization method and system for smart glasses

Abstract

This invention relates to the field of sound transmission accessory manufacturing technology, and particularly to a method and system for optimizing sound transmission accessory parameters for smart glasses. The method includes: constructing a 3D head model and a 3D smart glasses model based on point cloud data of the user's head and the smart glasses, respectively; generating multiple initial accessory parameter sets based on the head and smart glasses models; generating multiple simulated accessories based on the initial parameter sets; conducting sound quality performance tests on the simulated accessories; iteratively optimizing the initial accessory parameter sets using a pre-built optimization algorithm; and verifying the optimized parameter sets to complete the optimization of sound transmission accessory parameters for smart glasses. This invention uses digital simulation to accurately predict the optimized parameter sets and automatically iteratively corrects the parameter sets when the simulation results do not meet preset performance indicators, thereby obtaining an optimized parameter set that improves sound leakage prevention performance, sound quality signal-to-noise ratio, and wearing stability.

Description

Technical Field

[0001] This invention relates to the field of agricultural product price early warning technology, and in particular to a method and system for optimizing the parameters of audio transmission accessories for smart glasses. Background Technology

[0002] As an important branch of wearable devices, the audio transmission performance of smart glasses directly affects the user experience. As the core component for sound transmission in smart glasses, the optimized design of its structural parameters has a decisive impact on sound leakage prevention, sound quality clarity, and wearing stability.

[0003] In existing technologies, the parameter design of sound transmission components mainly relies on traditional trial production and verification methods. Parameter combinations are designed based on experience, physical samples are manufactured, and manual testing is conducted. The parameters are then repeatedly adjusted based on the test results.

[0004] While the aforementioned methods can achieve basic functional verification, they have significant limitations: reliance on designer experience leads to limited parameter coverage, physical sample production is costly and time-consuming, and it's difficult to quantify and evaluate the synergistic optimization of multiple performance indicators. Furthermore, traditional methods lack digital analysis of the compatibility between the user's head anatomy and smart glasses, resulting in poor accessory universality and an inability to meet the personalized needs of users with different head shapes. Therefore, a method is needed that can accurately predict the optimized parameter set through digital simulation and automatically iterate and correct the parameter set when the simulation results fail to meet preset performance indicators, thereby obtaining an optimized parameter set that improves sound leakage prevention performance, sound quality signal-to-noise ratio, and wearing stability. Summary of the Invention

[0005] This invention provides a method for optimizing the parameters of a sound transmission accessory for smart glasses and a computer-readable storage medium. Its main purpose is to accurately predict the optimized parameter set through digital simulation, and automatically iterate and correct the parameter set when the simulation results do not meet the preset performance indicators, thereby obtaining an optimized parameter set that improves sound leakage prevention performance, sound quality signal-to-noise ratio and wearing stability.

[0006] To achieve the above objectives, the present invention provides a method for optimizing the parameters of a sound transmission accessory for smart glasses, comprising: Obtain point cloud data of the user's head and the smart glasses, and construct a 3D model of the head and a 3D model of the smart glasses based on the point cloud data of the user's head and the smart glasses, respectively. Multiple sets of initial accessory parameters are generated based on the 3D head model and the 3D smart glasses model, and multiple simulated accessories are generated based on the multiple sets of initial accessory parameters. Multiple analog components were tested for sound quality performance, resulting in multiple sets of performance test results. Based on multiple performance test result sets, a pre-built optimization algorithm is used to iteratively optimize multiple initial component parameter sets to obtain an optimized parameter set. The optimized parameter set was verified, the verification results were obtained, and the parameter optimization of the sound transmission accessories used for smart glasses was completed.

[0007] Optionally, acquiring the point cloud data of the user's head and the point cloud data of the smart glasses includes: A pre-built 3D scanning device is used to perform a 3D scan of the user's head and smart glasses to obtain head data and smart glasses data. The head data includes multiple head point data, and the smart glasses data includes multiple glasses point data. Extract one header point from the header data sequentially to obtain the target data, and then perform the following operations on the target data: Confirm the adjacent head point data of the target data to obtain multiple adjacent data. The adjacent head point data is the head point data within a spherical region constructed based on a preset denoising radius with the target data as the center. Calculate the distance between each of the multiple adjacent data points and the target data point to obtain multiple distance values. Calculate the average of the multiple distance values ​​to obtain the average distance to the target. Sum the average distances of the targets to obtain the average distances of multiple targets; Based on the average distance between multiple targets, the head data is denoised to obtain denoised head data. The denoised header data is smoothed to obtain smoothed header data, which is then recorded as the point cloud data of the user's head. The smart glasses data is denoised to obtain denoised glasses data. The denoised glasses data is then smoothed to obtain smoothed glasses data. The smoothed glasses data is recorded as the point cloud data of the smart glasses.

[0008] Optionally, the step of denoising the head data based on the average distance of multiple targets to obtain denoised head data includes: Calculate the average of the average distances to multiple targets to obtain the total average distance, and then use the total average distance to calculate the standard deviation of the average distances to multiple targets. Calculate the product of the standard deviation and the preset coefficient to obtain the coefficient difference; calculate the sum of the coefficient difference and the mean to obtain the mean difference. Extract the average distance of one target from a set of multiple average target distances, and then perform the following operations on the extracted average target distance: Compare the average distance and average difference of the target. If the average distance of the target is greater than the average difference, remove the target data corresponding to the average distance of the target from the header data to obtain the denoised header data. If the average distance to the target is less than or equal to the average difference, the target data corresponding to the average distance to the target is retained, and the header data of the retained target data is confirmed as the denoised header data.

[0009] Optionally, the smoothing process of the denoised header data to obtain smoothed header data includes: Identify multiple denoised data points in the denoised header data, extract one denoised data point from the multiple denoised data points in sequence to obtain the target denoised data, and perform the following operations on the target denoised data; Identify the adjacent denoised data points of the target denoised data to obtain multiple adjacent denoised data points. The adjacent denoised data points are the denoised data points within a spherical region constructed with the target denoised data as the center and based on a preset smoothing radius. The pre-constructed polynomial function is used to fit multiple adjacent denoised data to obtain a fitted surface. The target denoised data is then projected onto the fitted surface to obtain the projected data. By aggregating multiple projection data, smooth head data is obtained.

[0010] Optionally, the sound quality performance test is performed on multiple analog accessories to obtain multiple performance test result sets, including: Extract one simulated component from a set of multiple simulated components, and then perform the following operations on the extracted simulated component: Acquire multiple smart glasses of different models to obtain multiple models of glasses. Perform 3D modeling on multiple models of glasses to obtain multiple glasses models. Copy the simulated parts to obtain multiple copied parts. Combine the multiple copied parts and multiple glasses models to obtain multiple combined models. Each combined model includes one copied part and one glasses model. Extract one combined model from multiple combined models sequentially, and perform the following operations on the extracted combined model: The copied parts are assembled onto the glasses model to obtain assembled glasses. The assembled glasses are then combined to obtain multiple assembled glasses. By combining multiple simulated parts into multiple assembled glasses, multiple simulated glasses are obtained; Adaptation tests are performed on multiple simulated glasses to obtain multiple adaptation test data. The multiple adaptation test data are compared with the preset adaptation standards to obtain the comparison results. Based on the comparison results, the multiple simulated glasses are adapted and screened to obtain multiple adapted glasses. The number of multiple adapted glasses and the number of multiple simulated glasses are counted to obtain the number of adapted glasses and the number of glasses. The ratio of the number of adapted glasses to the number of glasses is calculated to obtain the adaptation success rate. If the adaptation success rate is less than the preset adaptation threshold, multiple sets of second-generation accessory parameter sets are generated. These multiple sets of second-generation accessory parameter sets are used as the multiple initial accessory parameter sets. The process of generating multiple simulated accessories based on the multiple initial accessory parameter sets is repeated until the adaptation success rate is greater than or equal to the preset adaptation threshold, resulting in multiple optimized adapted glasses. One optimized adapted glass is then extracted from the multiple optimized adapted glasses, and the following operations are performed on the extracted optimized adapted glasses: A simulated sound leakage test was conducted on the optimized and fitted glasses to obtain the sound leakage results. The sound quality improvement effect of the optimized glasses was simulated and tested to obtain the sound quality improvement results. Simulated stability tests were conducted on the optimized fitting glasses to obtain stability results. Based on the optimized glasses, the results of sound leakage, sound quality improvement, and stability were summarized to obtain multiple performance test result sets. Among them, the performance test result set includes one sound leakage result, one sound quality improvement result, and one stability result.

[0011] Optionally, the step of performing a simulated sound leakage test on the optimized fitting glasses to obtain sound leakage results includes: Based on the aforementioned three-dimensional head model and optimized fitting glasses, a sound leakage accessory model is constructed. A first sound source is set in the sound leakage accessory model, wherein the first sound source includes a first sound pressure level. The first sound pressure of the first sound source in the sound leakage component model is measured to obtain the component sound pressure. When the first sound source is transmitted to the preset first position, the sound pressure at the preset first position is measured to obtain the component position sound pressure. The difference between the component sound pressure and the component position sound pressure is calculated to obtain the component sound leakage attenuation value. The model of the optimized and adapted glasses is extracted from multiple models of glasses to obtain the target sound leakage smart glasses. A sound leakage glasses model is constructed based on the target sound leakage smart glasses and the head three-dimensional model. A second sound source is set in the sound leakage glasses model, and the second sound source includes a second sound pressure. Based on the sound leakage glasses model, the second sound source, and the second sound pressure level, a sound leakage test was conducted to obtain the sound leakage attenuation value of the glasses. The difference between the sound leakage attenuation value of the glasses and the sound leakage attenuation value of the accessories is calculated to obtain the sound leakage result.

[0012] Optionally, the step of conducting a simulated sound quality improvement test on the optimized fitting glasses to obtain the sound quality improvement result includes: Based on the aforementioned 3D head model and optimized fitting glasses, a sound quality accessory model is constructed. A first standard sound source is set in the sound quality accessory model, which includes an accessory ear model. The first standard sound source is transmitted to the accessory ear model, and the pre-built accessory sensor model is used to capture the sound signal received by the first standard sound source in the accessory ear model to obtain the accessory sound signal. The sound signal of the component is decomposed into the normal signal and the noise signal. The intensity of the normal signal and the noise signal are measured respectively to obtain the normal intensity and the noise intensity. The ratio between the normal intensity and the noise intensity is calculated to obtain the signal-to-noise ratio of the component. The model of the optimized and adapted glasses is extracted from multiple models of glasses to obtain the target sound quality smart glasses. Based on the target sound quality smart glasses and the head 3D model, a sound quality glasses model is constructed. A second standard sound source is set in the sound quality glasses model. The sound quality glasses model includes the glasses ear model. The signal-to-noise ratio of the glasses was obtained by testing the signal-to-noise ratio based on a pre-constructed glasses sensor model and a second standard sound source. The difference between the signal-to-noise ratio of the accessory and the signal-to-noise ratio of the glasses is calculated to obtain the sound quality improvement result.

[0013] Optionally, the step of conducting a simulated stability test on the optimized fitting glasses to obtain stability results includes: The optimized and adapted glasses are fixed to the head 3D model to obtain a fixed 3D model. Environmental parameters are set on the fixed 3D model to obtain the set model. Dynamic loads are applied to the model to obtain a motion model. The position and contact area of ​​the optimized and adapted glasses and the three-dimensional head model in the motion model are monitored to obtain the position change results and area change results. The position change results and area change results are recorded as stability results.

[0014] Optionally, the step of validating the optimized parameter set to obtain the validation result includes: Based on the optimized parameter set, the sound transmission component is manufactured, and the sound transmission component is loaded into smart glasses to obtain sound transmission glasses. The sound transmission glasses are configured using pre-built audio transmission settings to obtain configured sound transmission glasses. Multi-user sound quality evaluation is performed on the configured sound transmission glasses to obtain multiple sound transmission scores. Multi-user smart glasses evaluation is performed using pre-built smart audio and smart glasses to obtain multiple glasses scores. Calculate the average of multiple glasses scores and multiple sound transmission scores to obtain the average glasses score and the average sound transmission score. Calculate the difference between the average glasses score and the average sound transmission score to obtain the score difference. The wearing comfort of the sound transmission accessories was tested, and the comfort results were obtained. The comfort results and the difference in scores are recorded as the verification results.

[0015] To achieve the above objectives, the present invention also provides a parameter optimization system for audio transmission accessories in smart glasses, comprising: The simulation module is used to acquire point cloud data of the user's head and the smart glasses. Based on the point cloud data of the user's head and the smart glasses, a 3D model of the head and a 3D model of the smart glasses are constructed respectively. Multiple sets of initial accessory parameter sets are generated based on the 3D model of the head and the 3D model of the smart glasses. Multiple simulated accessories are generated based on the multiple sets of initial accessory parameter sets. The simulation test module is used to perform sound quality performance tests on multiple simulated components and obtain multiple performance test result sets. The parameter optimization module is used to iteratively optimize multiple initial component parameter sets based on multiple performance test result sets using pre-built optimization algorithms to obtain optimized parameter sets. The parameter quality inspection module is used to verify the optimized parameter set, obtain the verification results, and complete the parameter optimization of the sound transmission accessories used in smart glasses.

[0016] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: A memory that stores at least one instruction; and a processor that executes the instructions stored in the memory to implement the above-described method for optimizing the parameters of a sound transmission accessory for smart glasses.

[0017] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the above-described method for optimizing the parameters of a sound transmission accessory for smart glasses.

[0018] To address the problems described in the background art, this invention acquires point cloud data of the user's head and smart glasses, and constructs 3D models of the head and smart glasses respectively based on these data. This invention achieves digital analysis of the compatibility between the user's head anatomy and smart glasses by acquiring point cloud data of the user's head and smart glasses, overcoming the shortcomings of traditional methods that lack personalized consideration. Multiple initial accessory parameter sets are generated based on the head and smart glasses 3D models, and multiple simulated accessories are generated based on these initial parameter sets. This invention avoids the problem of limited parameter coverage due to reliance on designer experience, as well as the drawbacks of high cost and long production cycle of physical samples. Sound quality performance tests are conducted on multiple simulated accessories to obtain multiple performance test result sets. Based on these performance test result sets, a pre-built optimization algorithm is used to iteratively optimize the multiple initial accessory parameter sets to obtain an optimized parameter set. This invention solves the problem of traditional methods struggling to coordinate and optimize multiple performance indicators, such as sound leakage prevention, sound clarity, and wearing stability, by quantitatively evaluating these indicators. This achieves precise and efficient parameter design. The optimized parameter set is validated, and the results are used to optimize the parameters of the sound transmission components for smart glasses. Finally, the optimized parameter set is validated again to ensure it meets the preset performance indicators. Therefore, this invention uses digital simulation to accurately predict the optimized parameter set and automatically iterates and corrects the parameter set when the simulation results do not meet the preset performance indicators, thereby obtaining an optimized parameter set that improves sound leakage prevention, sound quality signal-to-noise ratio, and wearing stability. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating a method for optimizing the parameters of a sound transmission accessory for smart glasses, according to an embodiment of the present invention. Figure 2 A functional block diagram of a sound transmission accessory parameter optimization system for smart glasses provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the method for optimizing the parameters of the sound transmission accessories for smart glasses, according to an embodiment of the present invention.

[0020] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] This application provides a method for optimizing the parameters of a sound transmission accessory for smart glasses. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for optimizing the parameters of a sound transmission accessory for smart glasses can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0024] Reference Figure 1 The diagram shown is a flowchart illustrating a method for optimizing the parameters of a sound transmission accessory for smart glasses according to an embodiment of the present invention. In this embodiment, the method for optimizing the parameters of a sound transmission accessory for smart glasses includes: S1. Obtain point cloud data of the user's head and the smart glasses. Construct a 3D model of the head and a 3D model of the smart glasses based on the point cloud data of the user's head and the smart glasses respectively. Generate multiple sets of initial accessory parameter sets based on the 3D model of the head and the 3D model of the smart glasses. Generate multiple simulated accessories based on the multiple sets of initial accessory parameter sets.

[0025] It should be noted that the point cloud data for the user's head is obtained by performing a 3D scan of the user's head, followed by denoising and smoothing, and is used to construct the 3D head model. Similarly, the point cloud data for the smart glasses is obtained by performing a 3D scan of the smart glasses, followed by denoising and smoothing, and is used to construct the 3D model of the smart glasses. (Smart glasses) Understandably, building a 3D head model is for generating structural data of the ears in software, such as the length, width, and thickness of the ears in 3D simulation software. Similarly, building a 3D model of the smart glasses is for generating structural data of the smart glasses in software, such as the length, width, and thickness of the temples. This, in turn, generates multiple sets of initial accessory parameters that match the structural data of the ears and smart glasses. In other words, based on these initial accessory parameter sets, multiple simulated accessories are generated that conform to the shapes of the ears and smart glasses.

[0026] It should be understood that the initial accessory parameter set is a collection of parameters generated based on the 3D head model and the 3D smart glasses model, used to simulate the fabrication of the accessories. For example, the accessory's width is 21mm and its height is 19mm. The simulated accessory is a simulated accessory generated in the software based on the aforementioned multiple sets of initial accessory parameter sets. It is used for subsequent simulated sound quality performance testing to obtain a performance test result set, and then iteratively optimizes the multiple sets of initial accessory parameter sets based on the multiple performance test result sets.

[0027] Importantly, analog accessories are simulations of sound transmission accessories. Sound transmission accessories are used to prevent sound leakage and improve sound quality when installed on smart glasses.

[0028] Furthermore, the acquisition of point cloud data of the user's head and point cloud data of the smart glasses includes: A pre-built 3D scanning device is used to perform a 3D scan of the user's head and smart glasses to obtain head data and smart glasses data. The head data includes multiple head point data, and the smart glasses data includes multiple glasses point data. Extract one header point from the header data sequentially to obtain the target data, and then perform the following operations on the target data: Confirm the adjacent head point data of the target data to obtain multiple adjacent data. The adjacent head point data is the head point data within a spherical region constructed based on a preset denoising radius with the target data as the center. Calculate the distance between each of the multiple adjacent data points and the target data point to obtain multiple distance values. Calculate the average of the multiple distance values ​​to obtain the average distance to the target. Sum the average distances of the targets to obtain the average distances of multiple targets; Based on the average distance between multiple targets, the head data is denoised to obtain denoised head data. The denoised header data is smoothed to obtain smoothed header data, which is then recorded as the point cloud data of the user's head. The smart glasses data is denoised to obtain denoised glasses data. The denoised glasses data is then smoothed to obtain smoothed glasses data. The smoothed glasses data is recorded as the point cloud data of the smart glasses.

[0029] It's important to clarify that 3D scanning equipment is used to perform 3D scanning of a user's head and smart glasses. For example, a 3D scanner. Head data is obtained by performing a 3D scan of the user's head using the 3D scanning equipment; it's a collection of data from multiple head points. Smart glasses data is obtained by performing a 3D scan of the smart glasses using the 3D scanning equipment; it's a collection of data from multiple glasses points. Head point data, obtained from the 3D scan of the user's head, represents the position of each point on the user's head. Glasses point data, obtained from the 3D scan of the smart glasses, represents the position of each point on the smart glasses.

[0030] Understandably, target data refers to a single head point extracted from the head data. Adjacent data refers to the head points adjacent to the target data. Adjacent head points are head points within a spherical region constructed based on a preset denoising radius and centered on the target data. The denoising radius is a manually preset radius used to determine the adjacent head points of the target data. The spherical region is a spherical area constructed based on the denoising radius and centered on the target data.

[0031] In detail, the distance value is the Euclidean distance between a neighboring data point and the target data. The Euclidean distance is a prior art technique, and will not be elaborated further in this invention. The target average distance is the average of multiple distance values. The denoised head data is the data after denoising the head data. The smoothed head data is the data after smoothing the denoised head data, and is also recorded as the point cloud data of the user's head.

[0032] For example, head point data A is extracted from the head data as target data A. Then, a spherical region A is constructed with the target data A as the center and a preset noise reduction radius of 4. The head point data in the spherical region A other than the target data are all adjacent head point data of the target data. Adjacent head data is recorded as adjacent data.

[0033] As a further example, the coordinates of target data A are three-dimensional coordinates. In the spherical region A, neighboring data B and neighboring data C are found to have three-dimensional coordinates in the same coordinate system as target data A. Then, the Euclidean distance between neighboring data B and target data A is the distance value BA, and the Euclidean distance between neighboring data C and target data A is the distance value CA. Then, the target average distance A of target data A is calculated as the average of distance value BA and distance value CA.

[0034] Importantly, the denoising process in this invention removes erroneous head point data caused by environmental interference during 3D scanning. For example, flowing hair strands might be misidentified as head point data. Smoothing the head data ensures the generated 3D head model closely approximates the contour of a realistic user's head. Both denoising and smoothing processes essentially aim to construct a realistic user head contour, providing a reference for generating multiple initial accessory parameter sets later.

[0035] It should be understood that the denoised glasses data is the data obtained by denoising the smart glasses data. The smoothed glasses data is the data obtained by smoothing the denoised glasses data, and is also recorded as the point cloud data of the smart glasses. The process and reasons for denoising and smoothing the smart glasses data are the same as those for denoising and smoothing the head data, and will not be repeated here.

[0036] Furthermore, the step of denoising the head point data based on the average distance of multiple targets to obtain denoised head data includes: Calculate the average of the average distances to multiple targets to obtain the total average distance, and then use the total average distance to calculate the standard deviation of the average distances to multiple targets. Calculate the product of the standard deviation and the preset coefficient to obtain the coefficient difference; calculate the sum of the coefficient difference and the mean to obtain the mean difference. Extract the average distance of one target from a set of multiple average target distances, and then perform the following operations on the extracted average target distance: Compare the average distance and average difference of the target. If the average distance of the target is greater than the average difference, remove the target data corresponding to the average distance of the target from the header data to obtain the denoised header data. If the average distance to the target is less than or equal to the average difference, the target data corresponding to the average distance to the target is retained, and the header data of the retained target data is confirmed as the denoised header data.

[0037] It should be noted that the total average distance is the average of the average distances of multiple targets. The calculation of the standard deviation of the average distances of multiple targets using the total average distance involves using the standard deviation formula to calculate the standard deviation of the average distances of multiple targets based on the total average distance. The standard deviation formula is as follows: , in, Indicates standard deviation, The index representing the average distance to all targets. Indicates the first Index of average distance to each target Indicates the first Average distance to each target This represents the total average distance.

[0038] It should be understood that the preset coefficients are manually set values ​​that determine which target data needs to be removed from the head data; these coefficients are based on historical experience. The coefficient difference is the product of the standard deviation and the preset coefficients. The mean difference is the sum of the coefficient differences and the mean.

[0039] Importantly, the overall average distance serves as a benchmark for the tightness of clustering among adjacent data points of all target data. In 3D scanning, due to scanning errors, occlusion, or other factors, some point cloud data may not lie on the contour of the scanned head; these points are considered outliers. Since normal point cloud data lies on the head contour, the distances between normal point cloud data and its neighbors are small and uniform. Outliers, on the other hand, are isolated or far from normal point cloud data, resulting in larger distances between them and their neighbors. Therefore, this invention uses the average difference as the criterion for distinguishing between outliers and normal point cloud data. If the target average distance is greater than the average difference, it indicates that multiple adjacent data points are far from the target data, not tightly clustered, and deviate from the overall distribution pattern of the head data. Therefore, this invention identifies target data with an average distance greater than the average difference as data that needs to be removed from the head data, thereby improving the head point data and making it more accurately represent the head contour.

[0040] Understandably, if the average distance to the target is less than or equal to the average difference, it means that the target data is closely combined with the adjacent data and is the head point data in the normal head data. Therefore, it is retained.

[0041] Furthermore, the smoothing process for the denoised header data to obtain smoothed header data includes: Identify multiple denoised data points in the denoised header data, extract one denoised data point from the multiple denoised data points in sequence to obtain the target denoised data, and perform the following operations on the target denoised data; Identify the adjacent denoised data points of the target denoised data to obtain multiple adjacent denoised data points. The adjacent denoised data points are the denoised data points within a spherical region constructed with the target denoised data as the center and based on a preset smoothing radius. The pre-constructed polynomial function is used to fit multiple adjacent denoised data to obtain a fitted surface. The target denoised data is then projected onto the fitted surface to obtain the projected data. By aggregating multiple projection data, smooth head data is obtained.

[0042] It should be noted that the denoised header data contains multiple denoised point data points. These denoised point data points are the target data retained after removing target data points whose average distance is greater than the average difference from the header data. The target denoised data is a single denoised point data point extracted from these multiple denoised point data points. Adjacent denoised data points are the adjacent denoised point data points of the target denoised data. Adjacent denoised point data points are denoised point data points within a spherical region constructed based on a preset smoothing radius and centered on the target denoised data. The smoothing radius is a manually preset radius used to determine the adjacent denoised data points of the target denoised data. The spherical region is a spherical region constructed based on the smoothing radius and centered on the target denoised data.

[0043] For example, it is confirmed that the denoised header data includes denoised data point A, denoised data point B, denoised data point C, denoised data point D, and denoised data point E. Denoising data point A is extracted as the target denoised data A. A spherical region is constructed with a smoothing radius of 3 centered on the target denoised data A. If denoised data point A, denoised data point B, and denoised data point D exist within the spherical region, then denoised data point B and denoised data D are identified as adjacent denoised data point B and adjacent denoised data point D, respectively.

[0044] Understandably, the fitted surface is a surface constructed by fitting a pre-built polynomial function to multiple adjacent denoised data points. The projected data is the data after projecting the target denoised data onto the fitted surface. The smoothed head data is a collection of multiple projected data points.

[0045] Specifically, the polynomial function is shown below: , in, , , , , Both represent the coefficients of a polynomial function. Indicates the first The vertical coordinates of adjacent denoised data Indicates the first The x-axis of adjacent denoised data Indicates the first The ordinate of adjacent denoised data Indicates the first An index of adjacent denoised data.

[0046] Important , , , , The method involves inputting the coordinates of a polynomial function and multiple adjacent denoised data into a mathematical library (such as Python's NumPy), which automatically provides the coefficients of the optimal polynomial function.

[0047] It should be understood that fitting multiple adjacent denoised data using a pre-constructed polynomial function refers to the process of inputting the polynomial function and the coordinates of multiple adjacent denoised data into a mathematical library, obtaining coefficients from the mathematical library, and then determining a fitting surface based on the given coefficients and the polynomial function.

[0048] Specifically, projecting the target denoised data onto the fitted surface involves substituting the horizontal and vertical coordinates of the target denoised data into the surface equation to calculate the vertical coordinate, and then using the horizontal and vertical coordinates of the target denoised data and the calculated vertical coordinate as the spatial coordinates of the projected data.

[0049] For example, given by the math library , , , , The coefficients are 0.1, 0.05, -0.02, 0.1, and 3, respectively. Therefore, the polynomial function with given coefficients and the surface equation of the fitted surface are: The target denoised data coordinates P are (2, 3, 4.2), and the x-axis 2 is taken as... and the vertical axis 3 as Substitute into the surface equation and calculate =3.75, Indicates the first The vertical coordinates of the projected data of the target denoised point data are obtained, and then the spatial coordinates of the projected data (2, 3, 3.75) are obtained. The target denoised data is then projected onto the fitted surface, and the projected data is 3.75.

[0050] S2. Perform sound quality performance tests on multiple analog accessories to obtain multiple performance test result sets.

[0051] It should be noted that the performance test result set is a collection of performance test results obtained from sound quality performance testing of analog components.

[0052] Furthermore, the sound quality performance testing of multiple simulated accessories yields multiple performance test result sets, including: Extract one simulated component from a set of multiple simulated components, and then perform the following operations on the extracted simulated component: Acquire multiple smart glasses of different models to obtain multiple models of glasses. Perform 3D modeling on multiple models of glasses to obtain multiple glasses models. Copy the simulated parts to obtain multiple copied parts. Combine the multiple copied parts and multiple glasses models to obtain multiple combined models. Each combined model includes one copied part and one glasses model. Extract one combined model from multiple combined models sequentially, and perform the following operations on the extracted combined model: The copied parts are assembled onto the glasses model to obtain assembled glasses. The assembled glasses are then combined to obtain multiple assembled glasses. By combining multiple simulated parts into multiple assembled glasses, multiple simulated glasses are obtained; Adaptation tests are performed on multiple simulated glasses to obtain multiple adaptation test data. The multiple adaptation test data are compared with the preset adaptation standards to obtain the comparison results. Based on the comparison results, the multiple simulated glasses are adapted and screened to obtain multiple adapted glasses. The number of multiple adapted glasses and the number of multiple simulated glasses are counted to obtain the number of adapted glasses and the number of glasses. The ratio of the number of adapted glasses to the number of glasses is calculated to obtain the adaptation success rate. If the adaptation success rate is less than the preset adaptation threshold, multiple sets of second-generation accessory parameter sets are generated. These multiple sets of second-generation accessory parameter sets are used as the multiple initial accessory parameter sets. The process of generating multiple simulated accessories based on the multiple initial accessory parameter sets is repeated until the adaptation success rate is greater than or equal to the preset adaptation threshold, resulting in multiple optimized adapted glasses. One optimized adapted glass is then extracted from the multiple optimized adapted glasses, and the following operations are performed on the extracted optimized adapted glasses: A simulated sound leakage test was conducted on the optimized and fitted glasses to obtain the sound leakage results. The sound quality improvement effect of the optimized glasses was simulated and tested to obtain the sound quality improvement results. Simulated stability tests were conducted on the optimized fitting glasses to obtain stability results. Based on the optimized glasses, the results of sound leakage, sound quality improvement, and stability were summarized to obtain multiple performance test result sets. Among them, the performance test result set includes one sound leakage result, one sound quality improvement result, and one stability result.

[0053] It should be noted that "model glasses" refers to specific models of smart glasses, such as Xiaomi smart glasses and Huawei smart glasses. The glasses model is a model created after 3D scanning of the model glasses. "Copy accessories" are accessories replicated from the simulated accessories. The combined model is a model resulting from combining the copied accessories and the glasses model. The phrase "obtaining multiple different models of smart glasses" refers to collecting multiple different models of smart glasses from the market.

[0054] For example, Xiaomi smart glasses and Huawei smart glasses are acquired, and 3D scanning is performed on Xiaomi smart glasses and Huawei smart glasses to construct glasses models of Xiaomi smart glasses and Huawei smart glasses. Simulated accessories are copied to obtain a first copied accessory and a second copied accessory. The first copied accessory is combined with the glasses model of Xiaomi smart glasses to obtain a first combined model {first copied accessory, glasses model of Xiaomi smart glasses}. The second copied accessory is combined with the glasses model of Huawei smart glasses to obtain a second combined model {second copied accessory, glasses model of Huawei smart glasses}.

[0055] It is understood that the assembled eyeglasses are an eyeglasses model obtained by assembling replicated parts onto an eyeglasses model. The assembly of replicated parts onto the eyeglasses model includes: Obtain the fitting section and transition section of the simulated accessory, obtain the horn hole of the eyeglass model, clean the horn hole to obtain a clean horn hole, align the fitting section with the clean horn hole to obtain an aligned horn hole, apply simulated pressure to the transition section, move the fitting section toward the horn hole to obtain a fitted horn hole, and confirm the fitted horn hole as the assembled eyeglasses.

[0056] For example, the first replica accessory in the first combined model {first replica accessory, glasses model of Xiaomi smart glasses} is assembled into the glasses model of Xiaomi smart glasses to obtain the first assembled glasses. Multiple simulated glasses refer to multiple assembled glasses with multiple simulated accessories as multiple simulated glasses.

[0057] It should be understood that the adaptation test data is data obtained by performing adaptation tests on simulated glasses. The comparison result is obtained by comparing the adaptation test data with preset adaptation standards. Adaptation standards are artificially set standards used to check whether simulated glasses are suitable, such as the size of the temples. Adapted glasses are those that meet the adaptation standards after screening multiple simulated glasses based on the comparison results. For example, glasses with temple sizes in the range of 7-10mm can be directly fitted with the simulated accessories. The number of adapted glasses is the number of multiple adapted glasses, and the number of glasses is the number of multiple simulated glasses. The adaptation success rate is the ratio of the number of adapted glasses to the number of glasses. Performing adaptation tests on multiple simulated glasses involves checking the coverage of the fitting sections and horn holes in the simulated glasses, i.e., the glasses to be fitted.

[0058] For example, a fitting test is performed on the first assembled glasses and the second simulated glasses. The first fitting test data shows that the sleeve section of the first simulated glasses covers the horn hole, while the second fitting test data shows that the sleeve section of the second simulated glasses does not cover the horn hole. The preset fitting standard is that the sleeve section completely covers the horn hole. The first and second fitting test data are then compared with the fitting standard. The comparison result is that the first simulated glasses meet the fitting standard, while the second simulated glasses do not. Based on the comparison result, the first simulated glasses are confirmed as the first fitted glasses, and the second simulated glasses are not fitted glasses. Therefore, the number of fitted glasses is 1, and the number of glasses is 2. The ratio of the number of fitted glasses to the number of glasses is 1 / 2 = 0.5. The fitting success rate is generally expressed as a percentage, so the fitting success rate is 50%.

[0059] Importantly, the adaptation threshold is a pre-set threshold used to compare with the adaptation success rate. Its purpose is to verify whether the multiple simulated accessories generated from the initial accessory parameter sets are compatible with multiple eyeglass models, thereby ensuring that the simulated accessories subsequently produced in actual production are suitable for most smart glasses on the market. The second-generation accessory parameter set is a set of parameters generated when the adaptation success rate is less than the pre-set adaptation threshold, and it differs from the set of parameters used in simulating the preparation of sound transmission accessories in the initial accessory parameter set. For example, parameters such as length in the initial accessory parameter set are numerically different from those in the second-generation accessory parameter set. Optimized adapted glasses are those with an adaptation success rate greater than or equal to the pre-set adaptation threshold.

[0060] In detail, the sound leakage result is obtained from a simulated sound leakage prevention test of the optimized glasses; the sound quality improvement result is obtained from a simulated sound quality improvement effect test of the optimized glasses; and the stability result is obtained from a simulated stability test of the optimized glasses. The performance test result set is a collection of sound leakage results, sound quality improvement results, and stability results.

[0061] Furthermore, the simulated sound leakage test on the optimized fitting glasses, to obtain the sound leakage results, includes: Based on the aforementioned three-dimensional head model and optimized fitting glasses, a sound leakage accessory model is constructed. A first sound source is set in the sound leakage accessory model, wherein the first sound source includes a first sound pressure level. The first sound pressure of the first sound source in the sound leakage component model is measured to obtain the component sound pressure. When the first sound source is transmitted to the preset first position, the sound pressure at the preset first position is measured to obtain the component position sound pressure. The difference between the component sound pressure and the component position sound pressure is calculated to obtain the component sound leakage attenuation value. The model of the optimized and adapted glasses is extracted from multiple models of glasses to obtain the target sound leakage smart glasses. A sound leakage glasses model is constructed based on the target sound leakage smart glasses and the head three-dimensional model. A second sound source is set in the sound leakage glasses model, and the second sound source includes a second sound pressure. Based on the sound leakage glasses model, the second sound source, and the second sound pressure level, a sound leakage test was conducted to obtain the sound leakage attenuation value of the glasses. The difference between the sound leakage attenuation value of the glasses and the sound leakage attenuation value of the accessories is calculated to obtain the sound leakage result.

[0062] It should be noted that the sound leakage accessory model is a model constructed by adding optimized fitting glasses to the aforementioned 3D head model, used for simulating sound leakage prevention testing. The first sound source is a sound source artificially set in the sound leakage accessory model, and the first sound pressure is the sound pressure of the first sound source. Sound pressure refers to the change in atmospheric pressure caused by sound wave disturbance. Simply put, the higher the sound pressure, the louder the sound heard by the human ear. Therefore, this invention uses sound pressure detection as the basis for sound leakage prevention testing. The construction of the sound leakage accessory model based on the aforementioned 3D head model and optimized fitting glasses involves combining the optimized fitting glasses with the 3D head model in software to simulate a real-world scenario where a user wears smart glasses equipped with sound transmission accessories.

[0063] Understandably, the component sound pressure level is the first sound pressure level of the first sound source in the sound leakage component model, and the component position sound pressure level is the sound pressure level at the preset first position when the first sound source is transmitted to that position. The first position is a manually set position. The component sound leakage attenuation value is the difference between the component sound pressure level and the component position sound pressure level.

[0064] For example, in the simulation software, the optimized fitting glasses are combined with the three-dimensional head model to obtain the sound leakage accessory model. A first sound source is set in the sound leakage accessory model. The sound pressure of the first sound source in the sound leakage accessory model is measured to be 85dB using a sound pressure sensor in the simulation software. At the same time, the preset first position is set in the simulation software to be 50cm away from the sound leakage accessory model. When the first sound source is transmitted to the first position, the sound pressure at the first position is measured to be 25dB using a sound pressure sensor. Therefore, the sound leakage attenuation value of the accessory is 60dB.

[0065] It should be understood that the target sound-leaking smart glasses are selected from multiple models of glasses and optimized to match the corresponding model. For example, if the optimized glasses are obtained by configuring simulated accessories onto Xiaomi smart glasses, then the target sound-leaking smart glasses are Xiaomi smart glasses. The sound-leaking glasses model is a model constructed by adding the target sound-leaking smart glasses onto the aforementioned 3D head model, used to simulate the scenario of a user wearing smart glasses in reality. The second sound source is a sound source set in the sound-leaking glasses model, and the second sound pressure is the sound pressure of the second sound source. The sound leakage attenuation value of the glasses is a value obtained by conducting sound leakage tests based on the sound-leaking glasses model, the second sound source, and the second sound pressure.

[0066] Importantly, to ensure the comparability of the sound leakage attenuation value between the glasses and the accessories, i.e. the validity of the sound leakage results, the first and second sound sources are identical except for their positions. Similarly, the first sound pressure level is identical to the second sound pressure level.

[0067] Specifically, the process of obtaining the sound leakage attenuation value of the glasses based on the sound leakage glasses model, the second sound source, and the second sound pressure level is the same as the process of obtaining the sound leakage attenuation value of the accessory, and will not be repeated here. The sound leakage attenuation value of the glasses reflects the sound leakage prevention effect of the smart glasses themselves, while the sound leakage attenuation value of the accessory reflects the sound leakage prevention effect after the smart glasses and the accessory are combined. Therefore, this invention calculates the difference between the sound leakage attenuation value of the glasses and the sound leakage attenuation value of the accessory, that is, the sound leakage result reflects the sound leakage prevention effect of the accessory. For example, if the sound leakage attenuation value of the accessory is 60dB and the sound leakage attenuation value of the glasses is 35dB, then the sound leakage result is 25dB.

[0068] Furthermore, the simulated sound quality improvement test on the optimized glasses, to obtain the sound quality improvement results, includes: Based on the aforementioned 3D head model and optimized fitting glasses, a sound quality accessory model is constructed. A first standard sound source is set in the sound quality accessory model, which includes an accessory ear model. The first standard sound source is transmitted to the accessory ear model, and the pre-built accessory sensor model is used to capture the sound signal received by the first standard sound source in the accessory ear model to obtain the accessory sound signal. The sound signal of the component is decomposed into the normal signal and the noise signal. The intensity of the normal signal and the noise signal are measured respectively to obtain the normal intensity and the noise intensity. The ratio between the normal intensity and the noise intensity is calculated to obtain the signal-to-noise ratio of the component. The model of the optimized and adapted glasses is extracted from multiple models of glasses to obtain the target sound quality smart glasses. Based on the target sound quality smart glasses and the head 3D model, a sound quality glasses model is constructed. A second standard sound source is set in the sound quality glasses model. The sound quality glasses model includes the glasses ear model. The signal-to-noise ratio of the glasses was obtained by testing the signal-to-noise ratio based on a pre-constructed glasses sensor model and a second standard sound source. The difference between the signal-to-noise ratio of the accessory and the signal-to-noise ratio of the glasses is calculated to obtain the sound quality improvement result.

[0069] It should be noted that the audio quality accessory model is a model constructed using a 3D head model and optimized adaptive glasses, used for simulating audio quality improvement effects testing. The first standard sound source is a sound source artificially set in the audio quality accessory model. The accessory ear model is a model in the audio quality accessory model that simulates the ear wearing the optimized adaptive glasses. The transmission of the first standard sound source to the accessory ear model is achieved by transmitting the first standard sound source to the accessory ear model through the optimized adaptive glasses, simulating a scenario where a user listens to sound while wearing smart glasses equipped with the audio transmission accessory. The accessory sound signal is the signal obtained by the accessory sensor model capturing the sound signal from the first standard sound source received by the accessory ear model. The accessory sensor model is a model of sensors constructed in the simulation software for capturing sound signals.

[0070] For example, an optimized fitting glasses are worn on a 3D head model to obtain an audio accessory model. Music is set in the audio accessory model, and then the music is transmitted to the accessory's ear model. The accessory's sensor model in simulation software captures the signal emitted by the music received by the accessory's ear model to obtain the accessory's sound signal.

[0071] Importantly, the normal signal and noise signal of the accessory are two signals obtained after decomposing the accessory's sound signal. The normal signal refers to the signal from the designated first standard sound source. The noise signal is the interference signal generated by the first standard sound source during transmission. For example, when the optimized glasses play music, the vibration of the internal structure generates interference signals, which are accessory noise signals. The normal intensity of the accessory is the strength of the normal signal, and the noise intensity is the strength of the noise signal. The signal-to-noise ratio (SNR) of the accessory is the ratio between the normal intensity and the noise intensity, that is, the SNR equals the normal intensity divided by the noise intensity, reflecting the SNR of the glasses model equipped with the sound transmission accessory.

[0072] Understandably, the target sound quality smart glasses are optimized and adapted from multiple glasses models. The sound quality glasses model is constructed using the target sound quality smart glasses and a 3D head model to simulate the user wearing the smart glasses. The second standard sound source is a manually set sound source in the sound quality glasses model. The glasses ear model is a model of the ear area in the sound quality glasses model. The glasses signal-to-noise ratio (SNR) is obtained by testing the SNR of the pre-built glasses sensor model and the second standard sound source, reflecting the SNR of the glasses model itself.

[0073] It should be understood that the process of obtaining the signal-to-noise ratio (SNR) of the glasses based on the pre-constructed glasses sensor model and the second standard sound source is the same as the process of obtaining the accessory SNR, and will not be described again here. The sound quality improvement result is the difference between the accessory SNR and the glasses SNR, that is, the sound quality improvement result is equal to the accessory SNR minus the glasses SNR.

[0074] Importantly, the sound quality improvement results reflect the effect of the sound transmission accessories on improving the signal-to-noise ratio of the glasses model. The greater the sound quality improvement result, the better the effect of the sound transmission accessories on improving the signal-to-noise ratio of the glasses model.

[0075] Furthermore, the simulated stability test of the optimized fitting glasses to obtain stability results includes: The optimized and adapted glasses are fixed to the head 3D model to obtain a fixed 3D model. Environmental parameters are set on the fixed 3D model to obtain the set model. Dynamic loads are applied to the model to obtain a motion model. The position and contact area of ​​the optimized and adapted glasses and the three-dimensional head model in the motion model are monitored to obtain the position change results and area change results. The position change results and area change results are recorded as stability results.

[0076] It should be noted that the fixed 3D model is the model after the optimized adaptive glasses are fixed to the head 3D model. Fixing the optimized adaptive glasses to the head 3D model involves equipping the head 3D model with the optimized adaptive glasses in simulation software. Setting the model involves setting environmental parameters for the fixed 3D model. These environmental parameters describe the real-world environment, such as atmospheric pressure and temperature. To realistically simulate the scenario of a user wearing the optimized adaptive glasses, this invention sets environmental parameters for the fixed 3D model.

[0077] Understandably, a motion model is a model with dynamic loads applied to a given model. Dynamic loads refer to external loads that cause rapid changes in speed over a short period. For example, a force suddenly applied with drastically changing magnitude within a short time is a dynamic load, simulating the forces generated by the up-and-down movement of a user. The stability of the user wearing the optimized glasses is then analyzed through position and area change results. Position change results are obtained by monitoring the position of the optimized glasses and the 3D head model within the motion model, while area change results are obtained by monitoring the contact area of ​​the optimized glasses and the 3D head model within the motion model. Stability results refer to both position and area change results.

[0078] For example, a force is applied to the model along the vertical direction (up and down) of the ground plane. The force increases from 0 to 5N in 0.1 seconds, remains at 5N for 0.1 seconds, and then decreases from 5N to 0N in 0.1 seconds, repeating this cycle three times to obtain the motion model. Position and contact area monitoring are performed on the optimized glasses and the 3D head model within the motion model, yielding positional changes (0.21mm, 0.15mm, 0.23mm) and area changes (2.95cm², 2.90cm², 2.92cm²). Here, 0.21mm represents the distance between the optimized glasses and the 3D head model in the motion model during the first cycle, and 2.95cm² represents the contact area between the optimized glasses and the 3D head model in the motion model during the first cycle.

[0079] Importantly, the contact area represents the degree of deviation between the optimized glasses and the 3D head model. If the glasses are very stable, even with external force, they can follow head movements and maintain a close fit to the skin, thus the change in contact area will be very small. If the glasses are unstable, when external force is applied, they will deviate from the head surface, causing the nose pads and temples to become loose in contact with the skin, or even partially suspended. In this case, the actual, effective contact area will decrease.

[0080] It should be understood that the stability results need to be compared with a preset position change threshold and a preset initial area to determine the stability of the optimized glasses. The preset position change threshold is a manually set threshold for position changes. The preset initial area is the contact area between the optimized glasses and the 3D head model in the set model.

[0081] Specifically, if the position change exceeds a preset position change threshold, it indicates that the set dynamic load has caused the optimized fitting glasses to detach from the head 3D model. Secondly, the difference between the area change and the initial area needs to be calculated, and a preset area range needs to be established. The difference between the area change and the initial area is then compared with this area range. The area range is a manually preset range.

[0082] In detail, if the difference between the changed area and the initial area exceeds the upper limit of the area range, it indicates that the optimized glasses exert significant pressure on the head's 3D model, causing discomfort for the user. If the difference between the changed area and the initial area exceeds the lower limit of the area range, it indicates that the optimized glasses have detached from the head's 3D model during movement.

[0083] Understandably, the optimized glasses are considered stable only when the position change result is less than or equal to the preset position change threshold and the difference between the area change result and the initial area is within the preset area range.

[0084] S3. Based on multiple performance test result sets, use a pre-built optimization algorithm to iteratively optimize multiple initial component parameter sets to obtain an optimized parameter set.

[0085] It should be noted that optimization algorithms are algorithms that iteratively optimize multiple sets of initial component parameters, such as particle swarm optimization and Bayesian optimization. The optimization parameter set is the set of parameters obtained after iterative optimization of multiple sets of initial component parameters.

[0086] It should be understood that the iterative optimization of multiple initial component parameter sets using a pre-built optimization algorithm involves finding the correlation between multiple performance test result sets and multiple initial component parameter sets, and then identifying the optimal parameter set as the optimization parameter set. For example, since the thickness of the sound transmission component affects the sound leakage result (one of the performance test results), the particle swarm optimization algorithm is used to find out how each change in the thickness of the sound transmission component affects the sound leakage result from multiple sound leakage results and multiple sound transmission component thicknesses. Based on this change, the optimal sound leakage result is found, and then the corresponding sound transmission component thickness is selected as a parameter in the optimization parameter set.

[0087] S4. Verify the optimized parameter set, obtain the verification results, and complete the parameter optimization of the sound transmission accessories used for smart glasses.

[0088] It should be noted that the verification results are the results of verifying the optimized parameter set.

[0089] Furthermore, the verification of the optimized parameter set to obtain the verification results includes: Based on the optimized parameter set, the sound transmission component is manufactured, and the sound transmission component is loaded into smart glasses to obtain sound transmission glasses. The sound transmission glasses are configured using pre-built audio transmission settings to obtain configured sound transmission glasses. Multi-user sound quality evaluation is performed on the configured sound transmission glasses to obtain multiple sound transmission scores. Multi-user smart glasses evaluation is performed using pre-built smart audio and smart glasses to obtain multiple glasses scores. Calculate the average of multiple glasses scores and multiple sound transmission scores to obtain the average glasses score and the average sound transmission score. Calculate the difference between the average glasses score and the average sound transmission score to obtain the score difference. The wearing comfort of the sound transmission accessories was tested, and the comfort results were obtained. The comfort results and the difference in scores are recorded as the verification results.

[0090] It should be noted that the audio transmission accessory is an accessory manufactured based on an optimized parameter set. Audio transmission glasses are smart glasses with the audio transmission accessory installed. Configuring the audio transmission glasses refers to setting the audio transmission audio on the glasses. The audio transmission audio is a manually set audio value. The audio transmission score is a user's evaluation of the configured audio transmission glasses. The glasses score is a score generated by performing a user's smart glasses evaluation using pre-built smart audio and the smart glasses themselves. The smart audio is a manually set audio value.

[0091] For example, a sound transmission accessory is manufactured by optimizing the parameter set, and then the sound transmission accessory is installed into Xiaomi smart glasses to obtain Xiaomi sound transmission glasses. A piece of music is set in the Xiaomi sound transmission glasses, and multiple users conduct evaluations to obtain multiple sound transmission scores (8, 9, 7, 9). Similarly, the same piece of music is set in the Xiaomi smart glasses, and the same multiple users conduct evaluations to obtain multiple glasses scores (7, 6, 5, 7).

[0092] Understandably, the glasses average is the average of multiple glasses scores, and the sound transmission average is the average of multiple sound transmission scores. The score difference is the difference between the glasses average and the sound transmission average. The comfort result is the result of a wearing comfort test on the sound transmission accessory.

[0093] It should be understood that the aforementioned wearing comfort test for the audio transmission accessory involves multiple users rating smart glasses equipped with the accessory to obtain multiple audio transmission comfort scores, and multiple users rating smart glasses without the accessory to obtain multiple glasses comfort scores. The average of these multiple audio transmission comfort scores and multiple glasses comfort scores is then calculated to obtain an average audio transmission comfort score and an average glasses comfort score. Finally, the difference between the average audio transmission comfort score and the average glasses comfort score is calculated to obtain the comfort result. The verification result refers to the comfort result and the score difference.

[0094] Importantly, if the score difference or comfort result is negative or zero, it indicates that the smart glasses with the audio transmission accessory are not as good as the smart glasses without the audio transmission accessory in the user experience. Therefore, it is necessary to generate multiple sets of second accessory parameter sets, use these multiple sets of second accessory parameter sets as the multiple sets of initial accessory parameter sets, and return to the step of generating multiple simulated accessories based on the multiple sets of initial accessory parameter sets until the score difference and comfort result are both positive, thus completing the audio transmission accessory parameter optimization for smart glasses.

[0095] To address the problems described in the background art, this invention acquires point cloud data of the user's head and smart glasses, and constructs 3D models of the head and smart glasses respectively based on these data. This invention achieves digital analysis of the compatibility between the user's head anatomy and smart glasses by acquiring point cloud data of the user's head and smart glasses, overcoming the shortcomings of traditional methods that lack personalized consideration. Multiple initial accessory parameter sets are generated based on the head and smart glasses 3D models, and multiple simulated accessories are generated based on these initial parameter sets. This invention avoids the problem of limited parameter coverage due to reliance on designer experience, as well as the drawbacks of high cost and long production cycle of physical samples. Sound quality performance tests are conducted on multiple simulated accessories to obtain multiple performance test result sets. Based on these performance test result sets, a pre-built optimization algorithm is used to iteratively optimize the multiple initial accessory parameter sets to obtain an optimized parameter set. This invention solves the problem of traditional methods struggling to coordinate and optimize multiple performance indicators, such as sound leakage prevention, sound clarity, and wearing stability, by quantitatively evaluating these indicators. This achieves precise and efficient parameter design. The optimized parameter set is validated, and the results are used to optimize the parameters of the sound transmission components for smart glasses. Finally, the optimized parameter set is validated again to ensure it meets the preset performance indicators. Therefore, this invention uses digital simulation to accurately predict the optimized parameter set and automatically iterates and corrects the parameter set when the simulation results do not meet the preset performance indicators, thereby obtaining an optimized parameter set that improves sound leakage prevention, sound quality signal-to-noise ratio, and wearing stability.

[0096] like Figure 2 The diagram shown is a functional block diagram of a sound transmission accessory parameter optimization system for smart glasses provided in an embodiment of the present invention.

[0097] The audio transmission accessory parameter optimization system 100 for smart glasses described in this invention can be installed in an electronic device. Depending on the functions implemented, the audio transmission accessory parameter optimization system 100 for smart glasses may include a simulation module 101, a simulation testing module 102, a parameter optimization module 103, and a parameter quality inspection module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and is stored in the memory of the electronic device.

[0098] The simulation module 101 is used to acquire point cloud data of the user's head and point cloud data of the smart glasses, construct a three-dimensional model of the head and a three-dimensional model of the smart glasses based on the point cloud data of the user's head and the point cloud data of the smart glasses respectively, generate multiple sets of initial accessory parameter sets based on the three-dimensional model of the head and the three-dimensional model of the smart glasses, and generate multiple simulated accessories based on the multiple sets of initial accessory parameter sets. The simulation test module 102 is used to perform sound quality performance tests on multiple simulated accessories and obtain multiple performance test result sets. The parameter optimization module 103 is used to iteratively optimize multiple initial accessory parameter sets based on multiple performance test result sets using a pre-built optimization algorithm to obtain an optimized parameter set. The parameter quality inspection 104 is used to verify the optimized parameter set, obtain the verification results, and complete the parameter optimization of the sound transmission accessories for smart glasses.

[0099] In detail, the modules in the audio transmission accessory parameter optimization system 100 for smart glasses described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method used is the same as the parameter optimization method for audio transmission accessories for smart glasses described in the article, and can produce the same technical effect, so it will not be repeated here.

[0100] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a method for optimizing the parameters of a sound transmission accessory for smart glasses, according to an embodiment of the present invention.

[0101] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a method program for optimizing the parameters of a sound transmission accessory for smart glasses.

[0102] The memory 11 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as code for a method program for optimizing the parameters of audio transmission accessories for smart glasses, but also to temporarily store data that has been output or will be output.

[0103] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device via various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a method for optimizing audio transmission accessory parameters for smart glasses) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0104] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0105] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0106] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0107] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0108] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0109] The memory 11 in the electronic device 1 stores a method program for optimizing the parameters of the audio transmission accessories for smart glasses. This program is a combination of multiple instructions, which, when run in the processor 10, can achieve the following: Obtain point cloud data of the user's head and the smart glasses, and construct a 3D model of the head and a 3D model of the smart glasses based on the point cloud data of the user's head and the smart glasses, respectively. Multiple sets of initial accessory parameters are generated based on the 3D head model and the 3D smart glasses model, and multiple simulated accessories are generated based on the multiple sets of initial accessory parameters. Multiple analog components were tested for sound quality performance, resulting in multiple sets of performance test results. Based on multiple performance test result sets, a pre-built optimization algorithm is used to iteratively optimize multiple initial component parameter sets to obtain an optimized parameter set. The optimized parameter set was verified, the verification results were obtained, and the parameter optimization of the sound transmission accessories used for smart glasses was completed.

[0110] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0111] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0112] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: Obtain point cloud data of the user's head and the smart glasses, and construct a 3D model of the head and a 3D model of the smart glasses based on the point cloud data of the user's head and the smart glasses, respectively. Multiple sets of initial accessory parameters are generated based on the 3D head model and the 3D smart glasses model, and multiple simulated accessories are generated based on the multiple sets of initial accessory parameters. Multiple analog components were tested for sound quality performance, resulting in multiple sets of performance test results. Based on multiple performance test result sets, a pre-built optimization algorithm is used to iteratively optimize multiple initial component parameter sets to obtain an optimized parameter set. The optimized parameter set was verified, the verification results were obtained, and the parameter optimization of the sound transmission accessories used for smart glasses was completed.

[0113] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0114] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0116] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for optimizing parameters of a sound transmission accessory for smart glasses, the method comprising: receiving a plurality of sound transmission accessory parameters; determining a plurality of sound transmission accessory parameter values; and outputting a plurality of sound transmission accessory parameter values. The method includes: Obtain point cloud data of the user's head and the smart glasses, and construct a 3D model of the head and a 3D model of the smart glasses based on the point cloud data of the user's head and the smart glasses, respectively. Multiple sets of initial accessory parameters are generated based on the 3D head model and the 3D smart glasses model, and multiple simulated accessories are generated based on the multiple sets of initial accessory parameters. Multiple analog components were tested for sound quality performance, resulting in multiple sets of performance test results. Based on multiple performance test result sets, a pre-built optimization algorithm is used to iteratively optimize multiple initial component parameter sets to obtain an optimized parameter set. The optimized parameter set was verified, the verification results were obtained, and the parameter optimization of the sound transmission accessories used for smart glasses was completed.

2. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 1, characterized in that, The acquisition of point cloud data of the user's head and the smart glasses includes: A pre-built 3D scanning device is used to perform a 3D scan of the user's head and smart glasses to obtain head data and smart glasses data. The head data includes multiple head point data, and the smart glasses data includes multiple glasses point data. Extract one header point from the header data sequentially to obtain the target data, and then perform the following operations on the target data: Confirm the adjacent head point data of the target data to obtain multiple adjacent data. The adjacent head point data is the head point data within a spherical region constructed based on a preset denoising radius with the target data as the center. Calculate the distance between each of the multiple adjacent data points and the target data point to obtain multiple distance values. Calculate the average of the multiple distance values ​​to obtain the average distance to the target. Sum the average distances of the targets to obtain the average distances of multiple targets; Based on the average distance between multiple targets, the head data is denoised to obtain denoised head data. The denoised header data is smoothed to obtain smoothed header data, which is then recorded as the point cloud data of the user's head. The smart glasses data is denoised to obtain denoised glasses data. The denoised glasses data is then smoothed to obtain smoothed glasses data. The smoothed glasses data is recorded as the point cloud data of the smart glasses.

3. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 2, characterized in that, The method of denoising the head data based on the average distance of multiple targets to obtain denoised head data includes: Calculate the average of the average distances to multiple targets to obtain the total average distance, and then use the total average distance to calculate the standard deviation of the average distances to multiple targets. Calculate the product of the standard deviation and the preset coefficient to obtain the coefficient difference; calculate the sum of the coefficient difference and the mean to obtain the mean difference. Extract the average distance of one target from a set of multiple average target distances, and then perform the following operations on the extracted average target distance: Compare the average distance and average difference of the target. If the average distance of the target is greater than the average difference, remove the target data corresponding to the average distance of the target from the header data to obtain the denoised header data. If the average distance to the target is less than or equal to the average difference, the target data corresponding to the average distance to the target is retained, and the header data of the retained target data is confirmed as the denoised header data.

4. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 3, characterized in that, The smoothing process for the denoised header data to obtain smoothed header data includes: Identify multiple denoised data points in the denoised header data, extract one denoised data point from the multiple denoised data points in sequence to obtain the target denoised data, and perform the following operations on the target denoised data; Identify the adjacent denoised data points of the target denoised data to obtain multiple adjacent denoised data points. The adjacent denoised data points are the denoised data points within a spherical region constructed with the target denoised data as the center and based on a preset smoothing radius. The pre-constructed polynomial function is used to fit multiple adjacent denoised data to obtain a fitted surface. The target denoised data is then projected onto the fitted surface to obtain the projected data. By aggregating multiple projection data, smooth head data is obtained.

5. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 4, characterized in that, The sound quality performance of multiple simulated accessories was tested, resulting in multiple performance test result sets, including: Extract one simulated component from a set of multiple simulated components, and then perform the following operations on the extracted simulated component: Acquire multiple smart glasses of different models to obtain multiple models of glasses. Perform 3D modeling on multiple models of glasses to obtain multiple glasses models. Copy the simulated parts to obtain multiple copied parts. Combine the multiple copied parts and multiple glasses models to obtain multiple combined models. Each combined model includes one copied part and one glasses model. Extract one combined model from multiple combined models sequentially, and perform the following operations on the extracted combined model: The copied parts are assembled onto the glasses model to obtain assembled glasses. The assembled glasses are then combined to obtain multiple assembled glasses. By combining multiple simulated parts into multiple assembled glasses, multiple simulated glasses are obtained; Adaptation tests are performed on multiple simulated glasses to obtain multiple adaptation test data. The multiple adaptation test data are compared with the preset adaptation standards to obtain the comparison results. Based on the comparison results, the multiple simulated glasses are adapted and screened to obtain multiple adapted glasses. The number of multiple adapted glasses and the number of multiple simulated glasses are counted to obtain the number of adapted glasses and the number of glasses. The ratio of the number of adapted glasses to the number of glasses is calculated to obtain the adaptation success rate. If the adaptation success rate is less than the preset adaptation threshold, multiple sets of second-generation accessory parameter sets are generated. These multiple sets of second-generation accessory parameter sets are used as the multiple initial accessory parameter sets. The process of generating multiple simulated accessories based on the multiple initial accessory parameter sets is repeated until the adaptation success rate is greater than or equal to the preset adaptation threshold, resulting in multiple optimized adapted glasses. One optimized adapted glass is then extracted from the multiple optimized adapted glasses, and the following operations are performed on the extracted optimized adapted glasses: A simulated sound leakage test was conducted on the optimized and fitted glasses to obtain the sound leakage results. The sound quality improvement effect of the optimized glasses was simulated and tested to obtain the sound quality improvement results. Simulated stability tests were conducted on the optimized fitting glasses to obtain stability results. Based on the optimized glasses, the results of sound leakage, sound quality improvement, and stability were summarized to obtain multiple performance test result sets. Among them, the performance test result set includes one sound leakage result, one sound quality improvement result, and one stability result.

6. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 5, characterized in that, The simulated sound leakage test on the optimized fitting glasses, and the sound leakage results obtained, include: Based on the aforementioned three-dimensional head model and optimized fitting glasses, a sound leakage accessory model is constructed. A first sound source is set in the sound leakage accessory model, wherein the first sound source includes a first sound pressure level. The first sound pressure of the first sound source in the sound leakage component model is measured to obtain the component sound pressure. When the first sound source is transmitted to the preset first position, the sound pressure at the preset first position is measured to obtain the component position sound pressure. The difference between the component sound pressure and the component position sound pressure is calculated to obtain the component sound leakage attenuation value. The model of the optimized and adapted glasses is extracted from multiple models of glasses to obtain the target sound leakage smart glasses. A sound leakage glasses model is constructed based on the target sound leakage smart glasses and the head three-dimensional model. A second sound source is set in the sound leakage glasses model, wherein the second sound source includes a second sound pressure. Based on the sound leakage glasses model, the second sound source, and the second sound pressure level, a sound leakage test was conducted to obtain the sound leakage attenuation value of the glasses. The difference between the sound leakage attenuation value of the glasses and the sound leakage attenuation value of the accessories is calculated to obtain the sound leakage result.

7. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 6, characterized in that, The simulated sound quality improvement test on the optimized glasses yielded sound quality improvement results, including: Based on the aforementioned 3D head model and optimized fitting glasses, a sound quality accessory model is constructed. A first standard sound source is set in the sound quality accessory model, which includes an accessory ear model. The first standard sound source is transmitted to the accessory ear model, and the pre-built accessory sensor model is used to capture the sound signal received by the first standard sound source in the accessory ear model to obtain the accessory sound signal. The sound signal of the component is decomposed into the normal signal and the noise signal. The intensity of the normal signal and the noise signal are measured respectively to obtain the normal intensity and the noise intensity. The ratio between the normal intensity and the noise intensity is calculated to obtain the signal-to-noise ratio of the component. The model of the optimized and adapted glasses is extracted from multiple models of glasses to obtain the target sound quality smart glasses. Based on the target sound quality smart glasses and the head 3D model, a sound quality glasses model is constructed. A second standard sound source is set in the sound quality glasses model. The sound quality glasses model includes the glasses ear model. The signal-to-noise ratio of the glasses was obtained by testing the signal-to-noise ratio based on a pre-constructed glasses sensor model and a second standard sound source. The difference between the signal-to-noise ratio of the accessory and the signal-to-noise ratio of the glasses is calculated to obtain the sound quality improvement result.

8. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 7, characterized in that, The simulation stability test of the optimized fitting glasses, to obtain the stability results, includes: The optimized and adapted glasses are fixed to the head 3D model to obtain a fixed 3D model. Environmental parameters are set on the fixed 3D model to obtain the set model. Dynamic loads are applied to the model to obtain a motion model. The position and contact area of ​​the optimized and adapted glasses and the three-dimensional head model in the motion model are monitored to obtain the position change results and area change results. The position change results and area change results are recorded as stability results.

9. The method for optimizing the parameters of a sound transmission accessory for smart glasses as described in claim 8, characterized in that, The verification of the optimized parameter set, and the resulting verification results, include: Based on the optimized parameter set, the sound transmission component is manufactured, and the sound transmission component is loaded into smart glasses to obtain sound transmission glasses. The sound transmission glasses are configured using pre-built audio transmission settings to obtain configured sound transmission glasses. Multi-user sound quality evaluation is performed on the configured sound transmission glasses to obtain multiple sound transmission scores. Multi-user smart glasses evaluation is performed using pre-built smart audio and smart glasses to obtain multiple glasses scores. Calculate the average of multiple glasses scores and multiple sound transmission scores to obtain the average glasses score and the average sound transmission score. Calculate the difference between the average glasses score and the average sound transmission score to obtain the score difference. The wearing comfort of the sound transmission accessories was tested, and the comfort results were obtained. The comfort results and the difference in scores are recorded as the verification results.

10. A parameter optimization system for audio transmission accessories in smart glasses, characterized in that, The system includes: The simulation module is used to acquire point cloud data of the user's head and the smart glasses. Based on the point cloud data of the user's head and the smart glasses, a 3D model of the head and a 3D model of the smart glasses are constructed respectively. Multiple sets of initial accessory parameter sets are generated based on the 3D model of the head and the 3D model of the smart glasses. Multiple simulated accessories are generated based on the multiple sets of initial accessory parameter sets. The simulation test module is used to perform sound quality performance tests on multiple simulated components and obtain multiple performance test result sets. The parameter optimization module is used to iteratively optimize multiple initial component parameter sets based on multiple performance test result sets using pre-built optimization algorithms to obtain optimized parameter sets. The parameter quality inspection module is used to verify the optimized parameter set, obtain the verification results, and complete the parameter optimization of the sound transmission accessories used in smart glasses.

Images