Intelligent glasses design method and device, electronic equipment and storage medium

Abstract

The application provides a smart glasses design method and device, an electronic device and a storage medium, and belongs to the technical field of hardware design and integration. The method comprises the following steps: acquiring the layout difficulty of each part in the smart glasses; determining a plurality of candidate smart glasses design schemes based on the layout difficulty of each part; evaluating the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme based on the layout position of each part in the candidate smart glasses design scheme; and selecting a target smart glasses design scheme from the candidate smart glasses design schemes based on the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme. The smart glasses design method and device, the electronic device and the storage medium provided by the application can take into account the operation convenience of the AI button and the integration stability with other hardware, and significantly improve the overall design quality of the smart glasses.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of hardware design and integration, and more particularly to a smart glasses design method and device, an electronic device, and a storage medium. BACKGROUND

[0002] Compared with the conventional keys on smart glasses, the AI key has a significant difference. Other keys usually only take care of a single, fixed function, such as the power key controlling the device to turn on or off, and the volume key adjusting the sound size, and the operation logic is simple and the executed instruction after triggering is clear. However, the AI key, as the core interaction entrance connecting the user and the AI function of the smart glasses, is often associated with complex intelligent responses, such as waking up the voice assistant, starting real-time translation, triggering scene-based services, etc. Behind it involves a series of AI algorithms such as speech recognition, semantic understanding, and context association, and the requirements for response speed and accuracy are higher, and the frequency and dependence of user operation are also much higher than other keys. In the design process of smart glasses, the position design of the AI key is a key link affecting the product experience and hardware stability, and the position of the AI key needs to be considered to facilitate user operation and ensure good integration of the AI key with other hardware.

[0003] However, in the prior art, the position design of the AI key of the smart glasses is mainly dependent on the experience of engineers for subjective arrangement, and lacks systematic quantitative analysis and scheme comparison, which is easy to cause the designed position of the AI key to be inconvenient to operate or the designed scheme to have hardware integration conflicts. SUMMARY

[0004] The purpose of the present application is to provide a smart glasses design method and device, an electronic device, and a storage medium to improve the overall design quality of smart glasses.

[0005] In a first aspect, the present application provides a smart glasses design method, comprising:

[0006] obtaining the arrangement difficulty of each part in the smart glasses respectively;

[0007] determining a plurality of candidate smart glasses design schemes based on the arrangement difficulty of each part respectively;

[0008] evaluating the AI key operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme based on the arrangement position of each part in the candidate smart glasses design scheme;

[0009] selecting a target smart glasses design scheme from the candidate smart glasses design schemes based on the AI key operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme.

[0010] The layout difficulty of each part in the smart glasses is determined by the following method:

[0011] The size factor of the part is obtained by calculating the ratio of the volume of the part to the total part volume;

[0012] The shape complexity of the part is obtained by calculating the ratio of the number of curved surfaces of the part;

[0013] The heat dissipation requirement index of the part is obtained by simulating the heat flux density of the part during work through a finite element analysis tool;

[0014] The larger value between the number of interfaces and the number of connection wires of the part is taken as the electrical connection complexity index of the part;

[0015] The tolerance level of the part is taken as the assembly accuracy requirement index of the part;

[0016] The layout difficulty coefficient of the part is obtained by weighted sum of the size factor, the shape complexity, the heat dissipation requirement index, the electrical connection complexity index, and the assembly accuracy requirement index.

[0017] In one possible implementation, based on the respective layout difficulty of each part, a plurality of candidate smart glasses design schemes are determined, including:

[0018] A glasses skeleton model is established, and a part layout area is set in the glasses skeleton model;

[0019] Based on the respective layout difficulty of each part, each part to be laid out is placed in the part layout area without overlapping in order from large to small according to the layout difficulty, and the layout position of each part is updated based on the gradient descent method until the change rate of the layout position is less than a preset threshold, to obtain a plurality of candidate smart glasses design schemes.

[0020] In one possible implementation, for each candidate smart glasses design scheme, based on the layout position of each part in the candidate smart glasses design scheme, an AI button operation effect score of the candidate smart glasses design scheme is evaluated, including:

[0021] Based on the target finger length of each user and the layout position of the AI button in the candidate smart glasses design scheme, the average distance from the user's fingertip to the AI button is calculated as the AI button accessibility index of the candidate smart glasses design scheme;

[0022] Based on the trigger pressure of the AI button in the candidate smart glasses design scheme, the AI button comfort index of the candidate smart glasses design scheme is calculated;

[0023] determine, based on the Monte Carlo method, a mis-touch rate of the user in operating the AI button in the candidate smart glasses design scheme in a simulated daily use scenario;

[0024] determine, based on the Monte Carlo method, a success rate of the user in operating the AI button in the candidate smart glasses design scheme in a gloved hand and a humid environment, as an environmental adaptability index of the AI button in the candidate smart glasses design scheme;

[0025] weight and sum the AI button accessibility index, the AI button comfort index, the mis-touch rate, and the environmental adaptability index of the AI button to obtain an AI button operation effect score of the candidate smart glasses design scheme.

[0026] In a possible implementation, for each candidate smart glasses design scheme, based on the arrangement positions of the parts in the candidate smart glasses design scheme, a hardware integration relationship score of the candidate smart glasses design scheme is evaluated, including:

[0027] based on the arrangement positions of the parts in the candidate smart glasses design scheme, measure a minimum distance between the AI button and the surrounding parts in the candidate smart glasses design scheme as a spatial compatibility index of the candidate smart glasses design scheme;

[0028] based on the arrangement positions of the parts in the candidate smart glasses design scheme, simulate, by using a finite element analysis tool, an electromagnetic interference value between the AI button and other parts in the candidate smart glasses design scheme, and take a maximum value in the electromagnetic interference value as an electromagnetic compatibility index of the candidate smart glasses design scheme;

[0029] based on the arrangement positions of the parts in the candidate smart glasses design scheme, simulate, by using a finite element analysis tool, a thermal resistance between the AI button and other parts in the candidate smart glasses design scheme, and take a maximum value in the thermal resistance as a heat conduction index of the candidate smart glasses design scheme;

[0030] weight and sum the spatial compatibility index, the electromagnetic compatibility index, and the heat conduction index to obtain the hardware integration relationship score of the candidate smart glasses design scheme.

[0031] In a possible implementation, based on the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme, a target smart glasses design scheme is selected from the candidate smart glasses design schemes, including:

[0032] weight and sum the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme to obtain a comprehensive score of the candidate smart glasses design scheme;

[0033] The candidate intelligent glasses design scheme with the largest comprehensive score is selected as the target intelligent glasses design scheme.

[0034] In a possible implementation, before the AI key operation effect score and the hardware integration relationship score of each candidate intelligent glasses design scheme are weighted and summed to obtain the comprehensive score of the candidate intelligent glasses design scheme, the method further includes:

[0035] The weight of the AI key operation effect score is calculated based on the occurrence proportion of a plurality of preset scenes and the use frequency of the AI key in each preset scene, wherein the preset scenes include a daily use scene, a mobile scene, and a professional work scene.

[0036] In a possible implementation, the calculation formula of the weight of the AI key operation effect score is as follows:

[0037]

[0038] wherein, is the weight of the AI key operation effect score, is the occurrence proportion of the i-th scene, is the use frequency of the AI key in the i-th scene.

[0039] In a second aspect, an intelligent glasses design device is provided, including:

[0040] An acquisition module is configured to acquire the arrangement difficulty of each part in the intelligent glasses.

[0041] A determination module is configured to determine a plurality of candidate intelligent glasses design schemes based on the arrangement difficulty of each part.

[0042] An evaluation module is configured to evaluate the AI key operation effect score and the hardware integration relationship score of each candidate intelligent glasses design scheme based on the arrangement position of each part in the candidate intelligent glasses design scheme.

[0043] A selection module is configured to select a target intelligent glasses design scheme from the plurality of candidate intelligent glasses design schemes based on the AI key operation effect score and the hardware integration relationship score of each candidate intelligent glasses design scheme.

[0044] When acquiring the arrangement difficulty of each part in the intelligent glasses, the acquisition module is specifically configured to:

[0045] Calculate the size factor of the part by calculating the ratio of the volume of the part to the total part volume.

[0046] Calculate the shape complexity of the part by calculating the surface number proportion of the part.​​

[0047] simulate the heat flux density of the part when working through a finite element analysis tool, to obtain the heat dissipation requirement index of the part;

[0048] the greater value between the number of interfaces and the number of connection wire harnesses of the part as the electrical connection complexity index of the part;

[0049] the tolerance grade of the part as the assembly precision requirement index of the part;

[0050] weighting and summing the size factor, the shape complexity, the heat dissipation requirement index, the electrical connection complexity index and the assembly precision requirement index to obtain the layout difficulty coefficient of the part.

[0051] In a third aspect, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the smart glasses design method described above when executing the computer program.

[0052] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the smart glasses design method described above.

[0053] The smart glasses design method and device, electronic device, and storage medium provided by the embodiments of the present application have the following beneficial effects:

[0054] By prioritizing the layout difficulty of each part in the smart glasses, multiple candidate schemes are generated, which can avoid the limitations of a single scheme while considering the layout difficulty of each part in the smart glasses, providing sufficient selection basis for subsequent evaluation; the operation effect and hardware integration relationship evaluation based on the part layout position realizes quantitative analysis of the scheme, ensuring the objectivity and accuracy of the evaluation result; finally, the target scheme is selected according to the evaluation result, which can balance the operation convenience of the AI button and the integration stability with other hardware, significantly improve the overall design quality of the smart glasses, reduce the rework times in the design later stage, reduce the research and development cost, shorten the period from design to mass production, and improve the market competitiveness of the product. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0056] Figure 1 A flowchart of a smart glasses design method according to an embodiment of the present application is shown in FIG. 1.

[0057] Figure 2 A structural block diagram of a smart glasses design device according to an embodiment of the present application is shown in FIG. 2.

[0058] Figure 3 A schematic block diagram of an electronic device according to an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION

[0059] In the following description, specific details are set forth, such as a particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, persons skilled in the art will understand that the present application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and methods have not been described in detail in order to avoid obscuring the description of the present application.

[0060] In order to make the objects, technical solutions and advantages of the present application clearer, the following will be described in detail with reference to the accompanying drawings.

[0061] Reference is made to Figure 1 , Figure 1 A flowchart of a smart glasses design method according to an embodiment of the present application is shown in FIG. 1. The method includes:

[0062] S101: Obtain the layout difficulty of each part in the smart glasses.

[0063] The layout difficulty of each part in the smart glasses is determined in the following manner:

[0064] Calculate the ratio of the volume of the part to the total part volume to obtain the size factor of the part;

[0065] Calculate the ratio of the number of curved surfaces of the part to obtain the shape complexity of the part;

[0066] Simulate the heat flux density of the part when working by a finite element analysis tool to obtain the heat dissipation requirement index of the part;

[0067] Take the greater value between the number of interfaces and the number of connection harnesses of the part as the electrical connection complexity index of the part;

[0068] Take the tolerance grade of the part as the assembly accuracy requirement index of the part;

[0069] Weighted sum the size factor, the shape complexity, the heat dissipation requirement index, the electrical connection complexity index, and the assembly accuracy requirement index to obtain the layout difficulty coefficient of the part.

[0070] In this embodiment, the size factor is the ratio of the volume of the first part to the total volume of the parts, reflecting the proportion of the part's size in the whole. Shape complexity is represented by the proportion of curved surfaces, which is calculated by counting the number of curved surfaces on the part's surface. and number of planes Shape complexity This reflects the complexity of the part's shape.

[0071] The heat dissipation requirement is reflected by the heat flux density, which reflects the heat dissipation needs of the parts. The unit of heat flux density H is W / cm². The specific calculation process is as follows: if H > 5, the heat dissipation requirement is 1; if H < 1, it is 0.2; if 1 ≤ H ≤ 5, it is calculated as (H-1) / (5-1)×(1-0.2)+0.2.

[0072] The electrical connection complexity index is selected from the larger value between the number of interfaces N_connection and the number of wiring harnesses N_wire. First, N_connection and N_wire are normalized to the range of 0-1 (e.g., when the maximum number of interfaces is 10, N_connection = actual number of interfaces / 10). Then, the larger value of the two is taken as E to reflect the complexity of the electrical connection.

[0073] Assembly accuracy requirements are based on the tolerance grades of the parts, which range from IT01 to IT18. These grades are mapped to a range of 0-1, with IT5 and below taking a value of 1, and IT10 and above taking a value of 0.3. For values ​​between IT5 and IT10, the formula is (IT10 - actual tolerance grade) / (IT10 - IT5) × (1 - 0.3) + 0.3, reflecting the required level of assembly precision. These parameters comprehensively reflect the key factors affecting the layout of parts.

[0074] The weighted sum of these indicators yields a layout difficulty coefficient, comprehensively considering the impact of various factors on layout difficulty, ensuring the coefficient fully reflects the actual ease or difficulty of layout. These parameters were chosen because they encompass key dimensions affecting component layout, providing a scientific basis for quantifying layout difficulty. In practice, values ​​for each indicator are obtained through measurement and simulation, then weighted to obtain the coefficient. The value of this process lies in transforming the assessment of component layout difficulty from subjective judgment to objective quantification, providing a reliable reference standard for subsequent component layout in order of difficulty.

[0075] S102: Based on the deployment difficulty of each component, several candidate smart glasses design schemes were determined.

[0076] In this embodiment, the candidate smart glasses design scheme refers to a design scheme generated through a specific process that includes information such as the placement of various components of the smart glasses. Since smart glasses have numerous components, different placement methods will bring different effects. Comparing multiple schemes can provide a basis for selecting the optimal scheme and avoid the limitations of a single scheme.

[0077] In an implementation, first, a glasses skeleton model is constructed in computer aided design (CAD) software, the area where the parts can be arranged is determined, then the parts are placed in order from large to small according to the arrangement difficulty coefficient, the position is continuously optimized by using the gradient descent method until the position change rate is less than a preset threshold, thereby obtaining multiple candidate schemes. The selection of the preset threshold needs to be combined with the design accuracy requirement, and is usually set to 0.01-0.1 mm, which can ensure the position accuracy and will not excessively increase the calculation amount. The beneficial effect of this is that multiple schemes are generated by the system, the influence of subjective experience is reduced, sufficient selection space is provided for subsequent evaluation, and the scientificity and comprehensiveness of the design are improved.

[0078] S103: Based on the arrangement positions of each part in each candidate smart glasses design scheme, an AI button operation effect score and a hardware integration relationship score of the candidate smart glasses design scheme are evaluated.

[0079] In this embodiment, the AI button operation effect score is a quantitative index for measuring the convenience and comfort of user operation of the AI button, and the hardware integration relationship score reflects the compatibility of the AI button with other hardware, and the two together constitute the core dimension for evaluating the pros and cons of the scheme.

[0080] When selecting parameters, the weights of the scoring indicators are determined according to the actual use scene, for example, the weight of the operation effect is higher in the daily high-frequency use scene. The implementation can specifically include: according to the specific arrangement positions of the parts in the candidate scheme, the operation effect and the hardware integration are calculated respectively according to the ergonomics principle and the hardware characteristics, and the scores are obtained by summarizing the indicators.

[0081] In this embodiment, through quantitative evaluation, the pros and cons of different schemes are clearly presented, providing an objective basis for subsequent selection of the target scheme, avoiding the deviation of subjective judgment, and providing a reliable reference for subsequent selection.

[0082] S104: Based on the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme, a target smart glasses design scheme is selected from the candidate smart glasses design schemes.

[0083] In this embodiment, the target smart glasses design scheme is the scheme with the best overall performance. The selection principle is to compare the scores of the candidate schemes and select the scheme with the best overall performance in terms of operation effect and hardware integration.

[0084] When implemented, the scheme with the best overall performance can be determined by analyzing and comparing the scores of the schemes. It is ensured that the finally selected scheme achieves the best balance in user experience and hardware stability, and improves the overall quality of the smart glasses.

[0085] From the above, the embodiment of the application can avoid the limitations of a single scheme by generating multiple candidate schemes, providing a sufficient selection basis for subsequent evaluation; the evaluation of the operation effect and the hardware integration relationship based on the part layout position realizes quantitative analysis of the scheme, ensuring the objectivity and accuracy of the evaluation results; finally, the target scheme is selected according to the evaluation results, which can balance the operation convenience of the AI button and the integration stability with other hardware, significantly improve the overall design quality of the intelligent glasses, reduce the rework times in the design later stage, reduce the research and development cost, shorten the period from design to mass production, and improve the market competitiveness of the product.

[0086] In a possible implementation, the multiple candidate intelligent glasses design schemes are determined based on the layout difficulty corresponding to each part, including:

[0087] A glasses skeleton model is established, and a part layout area is set in the glasses skeleton model;

[0088] Based on the layout difficulty corresponding to each part, each part to be laid out is placed in the part layout area without overlapping in order of the layout difficulty from large to small, and the layout position of each part is updated based on the gradient descent method until the change rate of the layout position is less than a preset threshold, to obtain the multiple candidate intelligent glasses design schemes.

[0089] In the embodiment, the CAD design software can accurately construct a three-dimensional model, facilitating the layout and adjustment of parts. The glasses skeleton model is a basic structure model of the intelligent glasses, and the part layout area is a specific area in the model for placing each part. The implementation principle is to first build a basic framework and then reasonably layout the parts in the framework to ensure that the part layout has rules to follow.

[0090] The layout difficulty coefficient is an index reflecting the difficulty of part layout, which is obtained by comprehensively considering factors such as part size and shape complexity. In the generation process of the design scheme, the parts are laid out in order of the layout difficulty coefficient from large to small, and the difficult-to-lay parts are processed first to reduce the conflicts in subsequent adjustment.

[0091] The gradient descent method is an optimization algorithm used to adjust the position of the part to make the layout more reasonable, and the preset threshold is a critical value for judging whether the position is stable, which can be set according to actual needs. In implementation, the glasses skeleton model is first constructed, and the area where the parts can be laid out is determined, then the parts are laid out in order of difficulty and adjusted by the gradient descent method until the position change rate is less than the threshold, to obtain multiple schemes, which can make the generated candidate schemes more reasonable, reduce the conflicts between parts, and improve the scheme quality.

[0092] In the process of optimizing the part layout position by the gradient descent method, the specific implementation steps are as follows:

[0093] Firstly, define the objective function of position optimization, which quantifies the rationality of part placement position, usually aiming at minimizing the spatial conflict between parts, the lowest complexity of assembly path, and the best compatibility with surrounding key parts, and convert these goals into calculable mathematical expressions. For example, the objective function can be set as the weighted sum of the inverse of the minimum distance between parts and the number of assembly path turning points, and the smaller the value, the more reasonable the position.

[0094] Secondly, initialize the part position, assign an initial three-dimensional coordinate (x0, y0, z0) to each part based on the preset placement area in the CAD model, and the coordinate value should be within the boundary range of the placement area (such as the x-axis range of the left arm of the frame is 50-100mm).

[0095] Next, calculate the gradient of the objective function, i.e. the partial derivative of the function with respect to the x, y, and z coordinate axes. The gradient direction reflects the direction in which the objective function value rises fastest, and the optimization needs to adjust the position in the opposite direction of the gradient (i.e. the direction in which the objective function value decreases fastest). For example, if the partial derivative of a part in the x-axis direction is positive, moving in the positive x-axis direction will increase the objective function value (decrease the position rationality), so the position needs to be adjusted in the negative x-axis direction.

[0096] Then, determine the step size (learning rate), which determines the magnitude of each position adjustment, usually set to 0.1-1mm (can be dynamically adjusted according to the size of the part, the step size can be increased for large-sized parts). Calculate the new position based on the gradient direction and step size: new coordinates = current coordinates - step size x gradient value, get the adjusted three-dimensional coordinates (x1, y1, z1).

[0097] After that, calculate the position change rate, which is the Euclidean distance between the new position and the current position divided by the distance from the current position to the origin (or directly take the average of the absolute values of the change in each coordinate axis direction). For example, if the x-axis change is 0.05mm, the y-axis is 0.03mm, and the z-axis is 0.02mm, the average change is (0.05+0.03+0.02) / 3=0.033mm, and if the distance from the current position to the origin is 100mm, the change rate is 0.033 / 100=0.00033.

[0098] Then judge whether the change rate is less than the preset threshold (usually set to 0.001, i.e. 0.1%), if not, take the new position as the current position, repeat the steps of calculating the gradient, adjusting the position, and calculating the change rate; if it is less than, stop iteration, and the position at this time is the optimized stable position.

[0099] Finally, after completing the position optimization of all parts according to the above steps, save the current part placement coordinates as a candidate design scheme; by adjusting the initial position or the weight of the objective function, repeat the entire optimization process to generate multiple different candidate schemes.

[0100] In a possible implementation, for each candidate smart glasses design scheme, an AI button operation effect score of the candidate smart glasses design scheme is evaluated based on the arrangement positions of the parts in the candidate smart glasses design scheme, including:

[0101] Based on the target finger lengths of the plurality of users respectively and the arrangement positions of the AI buttons in the candidate smart glasses design scheme, an average distance from the fingertips of the users to the AI buttons is calculated as an AI button accessibility index of the candidate smart glasses design scheme.

[0102] Based on the trigger pressure of the AI button in the candidate smart glasses design scheme, an AI button comfort index of the candidate smart glasses design scheme is calculated.

[0103] Based on the Monte Carlo method, a mis-touch rate of the user in operating the AI button in the candidate smart glasses design scheme in a simulated daily use scenario is determined.

[0104] Based on the Monte Carlo method, a success rate of the user in operating the AI button in the candidate smart glasses design scheme in a gloved hand and a humid environment is determined as an AI button environmental adaptability index of the candidate smart glasses design scheme.

[0105] The AI button accessibility index, the AI button comfort index, the mis-touch rate, and the AI button environmental adaptability index are weighted and summed to obtain the AI button operation effect score of the candidate smart glasses design scheme.

[0106] In this embodiment, when evaluating the AI button operation effect score, the finger length data of the plurality of users is introduced. Specifically, 50 users of different genders and ages can be selected, the lengths of their index fingers L are measured, the average distance A from the fingertips of the users to the AI buttons is calculated based on this, the distance d_i from the fingertips of each user to the AI buttons when wearing glasses is obtained by using a three-dimensional coordinate measuring instrument, the average distance A is (d1+d2+…+d50) / 50, if A≤3cm, 100 points are obtained, if A>8cm, 0 points are obtained, if 3<A≤8, the comfort index B is calculated according to (8-A) / (8-3)×100. The finger length data of the plurality of users is used to more comprehensively reflect the operation conditions of different users, and the average distance is used as the accessibility index to reflect the convenience of the fingertips of the users to the AI buttons.

[0107] The trigger pressure of the AI button directly affects the muscle fatigue degree of the user during operation. The trigger pressure F (unit: N) is measured by using a pressure sensor, if F<5, 100 points are obtained, if F>20, 0 points are obtained, if 5≤F≤20, the comfort index B is calculated according to (20-F) / (20-5)×100.

[0108] In the design stage of AI button without physical device, the trigger pressure can be simulated by combining simulation modeling and parameterized analysis, and the specific implementation is as follows:

[0109] Firstly, a three-dimensional mechanical model of the AI button is constructed. In the CAD or CAE software, a virtual model is established according to the design parameters of the button (such as button stroke, button cap size, elastic element type and size), and the structure of the button is defined, including the button cap, elastic support (such as spring, silica gel pad), trigger contact, etc. The mechanical properties of the elastic element (such as the stiffness coefficient of the spring, the Young's modulus of the silica gel) need to be preset by referring to the material parameter library of the same type of button (for example, a spring with a diameter of 0.5 mm and a free length of 3 mm is selected, and the stiffness coefficient is set to 5 N / mm; the silica gel pad is set to Shore hardness 60A, and the Young's modulus is 2 MPa).

[0110] Secondly, the simulation conditions of the trigger pressure are defined. When simulating the user's pressing action, a uniform load is applied on the top of the button cap perpendicular to the contact surface, and the load range is set to 0-25 N to cover the trigger pressure range of common buttons. At the same time, the displacement of the bottom and the surrounding structure of the button is constrained to ensure that the simulation boundary conditions are consistent with the actual assembly state (such as the button is installed in the fixed slot of the frame arm, and the bottom does not displace).

[0111] Then, the trigger pressure curve is calculated by finite element analysis. During the simulation process, the displacement-load relationship of the button from the initial position to the contact of the trigger contact (i.e. the end of the button stroke) is recorded: when the elastic element is compressed, the load increases linearly or nonlinearly with the displacement (the spring is linear, and the silica gel pad is nonlinear due to the material properties), and the load value at the moment of contact is taken as the simulated trigger pressure. For example, if the button stroke is 1.5 mm, the spring stiffness coefficient is 5 N / mm, and the friction resistance is ignored, the theoretical trigger pressure is 5 N / mm x 1.5 mm = 7.5 N; if the nonlinear deformation of the silica gel pad is considered, the load at 1.5 mm displacement is 8.2 N through simulation, i.e. the simulated trigger pressure is 8.2 N.

[0112] At the same time, the user operation variable is introduced to correct the simulation results. Combined with the finger pressure distribution data of the target user group (the average initial pressure is 2-3 N and the maximum pressing pressure is 15-20 N by collecting the pressing force range of 20-50 users through a pressure sensor array), the trigger pressure obtained by simulation is corrected: if the simulation value is higher than the average maximum pressing pressure of the user, the elastic element parameters need to be adjusted (such as reducing the spring stiffness coefficient) to re-simulate until the trigger pressure falls within the comfortable range of 5-15 N.

[0113] In addition, the triggering pressure of different design schemes can be simulated by multi-parameter iterative optimization. By changing variables such as key stroke (e.g., 1 mm, 2 mm), material parameters of elastic elements (e.g., spring diameter, silicone hardness), and repeating the above simulation steps, multiple sets of triggering pressure data are obtained to provide a basis for comfort index calculation of different candidate schemes.

[0114] This simulation method does not require physical equipment and can quantify the triggering pressure through structure modeling and mechanical simulation. It can quickly respond to adjustments of design parameters, providing reliable pressure data support for early design optimization of AI keys, and ensuring the accuracy of subsequent comfort evaluation.

[0115] The Monte Carlo method is used to determine the mis-touch rate. 1000 daily operations are simulated, and the mis-touch frequency Nmis is counted. The mis-touch rate C = Nmis / 1000. If C = 0, 100 points are obtained. If C > 15%, 0 points are obtained. If 0 < C ≤ 15%, calculate (15%-C) / 15%*100.

[0116] The environmental adaptability index is simulated by the Monte Carlo method under the conditions of wearing gloves and in a humid environment. Each simulation is performed 1000 times, and the success frequency is Nsuccess. The success rate D = Nsuccess / 2000. If D = 100%, 100 points are obtained. If D < 60%, 0 points are obtained. If 60% ≤ D < 100%, calculate (D-60%) / (100%-60%) * 100.

[0117] Finally, the operation effect score is obtained by weighted sum of the above indicators. The weight can be set according to the actual situation, and the operation performance is quantitatively evaluated from multiple aspects. These parameters and methods can describe the operation performance of AI keys from multiple angles, ensuring the comprehensiveness and accuracy of the evaluation. In actual operation, the average distance is calculated, the triggering pressure is analyzed, and the Monte Carlo method is used to simulate, and then the weighted sum is performed to obtain the score. The advantage of this process is that the operation effect evaluation is more scientific and accurate, and can truly reflect the user's operation experience in actual use.

[0118] In one possible implementation, for each candidate smart glasses design scheme, based on the layout positions of the parts in the candidate smart glasses design scheme, a hardware integration relationship score of the candidate smart glasses design scheme is evaluated, which can specifically include:

[0119] Based on the layout positions of the parts in the candidate smart glasses design scheme, the minimum distance between the AI key and the surrounding parts in the candidate smart glasses design scheme is measured as a spatial compatibility index of the candidate smart glasses design scheme.

[0120] Based on the layout positions of each part in the candidate smart glasses design scheme, the electromagnetic interference value between the AI button and other parts in the candidate smart glasses design scheme is simulated through a finite element analysis tool, and the maximum value in the electromagnetic interference value is taken as the electromagnetic compatibility index of the candidate smart glasses design scheme.

[0121] Based on the layout positions of each part in the candidate smart glasses design scheme, the thermal resistance between the AI button and other parts in the candidate smart glasses design scheme is simulated through a finite element analysis tool, and the maximum value in the thermal resistance is taken as the heat conduction index of the candidate smart glasses design scheme.

[0122] The spatial compatibility index, the electromagnetic compatibility index and the heat conduction index are weighted and summed to obtain the hardware integration relationship score of the candidate smart glasses design scheme.

[0123] In this embodiment, the minimum distance Sspace (unit: mm) between the AI button and the surrounding parts is measured by using CAD software. If Sspace≥2, 100 points are obtained, if Sspace<0.5, 0 points are obtained, and if 0.5≤Sspace<2, the spatial compatibility index is calculated according to (Sspace-0.5) / (2-0.5)×100.

[0124] The electromagnetic interference value Einterference (unit: dBm) obtained by simulation through a finite element analysis tool is Einterference<-80, 100 points are obtained, Einterference>-40, 0 points are obtained, and -80≤Einterference≤-40, the electromagnetic compatibility index is calculated according to (-40-Einterference) / (-40+80)×100.

[0125] The maximum thermal resistance Tresistance (unit: K / W) is taken as the heat conduction index. If Tresistance>5, 100 points are obtained, if Tresistance<1, 0 points are obtained, and if 1≤Tresistance≤5, the heat conduction index is calculated according to (Tresistance-1) / (5-1)×100.

[0126] The hardware integration relationship score is obtained by weighted sum of these indexes. The weight can be set according to the actual situation. The compatibility of the AI button and other parts in the key hardware performance dimensions such as space, electromagnetic field and heat conduction is comprehensively evaluated, so that the score can fully reflect the quality of hardware integration. These parameters can directly reflect the core problems in hardware integration, and ensure the pertinence and effectiveness of the evaluation.

[0127] In specific operation, the distance is measured, the electromagnetic interference and the thermal resistance are simulated, and then the score is obtained by weighted sum. The value of this process lies in that the evaluation of hardware integration relationship is more objective and quantitative, which can accurately reflect the compatibility of the AI button and other parts, and provide reliable basis for scheme optimization.

[0128] In a possible implementation, the target smart glasses design scheme is selected from the candidate smart glasses design schemes based on the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme, including:

[0129] The AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme are weighted and summed to obtain a comprehensive score of the candidate smart glasses design scheme.

[0130] The candidate smart glasses design scheme with the maximum comprehensive score is taken as the target smart glasses design scheme.

[0131] In this embodiment, the AI button operation effect score and the hardware integration relationship score of each candidate scheme are weighted and summed to obtain a comprehensive score Z = a x O + (1-a) x I, where a is the weight of the operation effect score, O is the operation effect score, and I is the hardware integration relationship score.

[0132] The comprehensive score can integrate the performance of the two key dimensions and comprehensively reflect the overall quality of the scheme. The internal logic is that a high-quality design of smart glasses needs to meet good user operation experience and stable hardware integration performance at the same time, and the comprehensive score is exactly the comprehensive consideration of these two aspects. In actual operation, the scheme with the highest score is selected as the target scheme by calculating the comprehensive scores of the schemes, and the positive effect of this process is to ensure that the finally selected scheme can achieve the best balance between user experience and hardware performance, thereby improving the overall competitiveness of smart glasses.

[0133] In a possible implementation, before the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme are weighted and summed to obtain a comprehensive score of the candidate smart glasses design scheme, the method further includes:

[0134] The weight of the AI button operation effect score is calculated based on the occurrence proportion of a plurality of preset scenes and the use frequency of the AI button in each preset scene, wherein the preset scenes include a daily use scene, a mobile scene, and a professional work scene.

[0135] In this embodiment, the use scenes of smart glasses can be divided into typical scenes such as daily commuting, office work, sports, and leisure entertainment, and each scene is further divided into specific use behaviors (such as waking up a voice assistant when commuting, switching function menus when working, etc.). Then, through a questionnaire survey, user interviews, or a simulation use experiment, the use frequency data of the AI button of users in different scenes is collected. For example, users are asked to record the number of times of pressing the AI button in each scene within a day, or a counting module is implanted in a smart glasses prototype to count the number of uses in different scenes.

[0136] The appearance distribution proportion of the scene is obtained by analyzing user activity data, representing the statistical probability of each scene in the total use time. By analyzing the user logs for a week, the active time proportion of each scene is counted, and the number of AI button uses in a certain scene is divided by the total use number of all scenes to obtain the appearance proportion of the scene. For example: daily office (65%), commuting driving (20%), sports (10%), professional operation (5%). This time distribution proportion is the basis for calculating the scene weight.

[0137] In a possible implementation, the calculation formula of the weight of the AI button operation effect score is:

[0138]

[0139] wherein, is the weight of the AI button operation effect score, is the appearance proportion of the i-th scene, is the use frequency of the AI button in the i-th scene. In this embodiment, is the use frequency of the AI button in the i-th scene, for example, 5 times per hour in daily commuting, and the highest use frequency is 10 times / hour, so

[0140] =5 / 10=0.5. Through the formula, the operation effect and the evaluation result of the hardware integration are combined to realize comprehensive evaluation of the candidate scheme, the value of will be dynamically adjusted with the change of the AI button use frequency, the more frequently it is used, the greater it is, and the more it focuses on the operation effect. Through this weight calculation method, human factor engineering data can be deeply integrated into design evaluation, so that high-frequency key operations can obtain higher optimization priority.

[0141] Corresponding to the smart glasses design method in the above embodiment, is a structural block diagram of a smart glasses design device provided by an embodiment of the present application. For ease of illustration, only parts related to the embodiments of the present application are shown. Referring to , the smart glasses design device 2 comprises:

[0142] Figure 2 An acquisition module 21 is configured to acquire the arrangement difficulty of each part in the smart glasses. Figure 2 A determination module 22 is configured to determine a plurality of candidate smart glasses design schemes based on the arrangement difficulty of each part.

[0143]

[0144]

[0145] ​​​The evaluation module 23 is configured to evaluate the AI button operation effect score and the hardware integration relationship score of the candidate smart glasses design scheme based on the arrangement positions of the parts in the candidate smart glasses design scheme.

[0146] The selection module 24 is configured to select a target smart glasses design scheme from the candidate smart glasses design schemes based on the AI button operation effect scores and the hardware integration relationship scores.

[0147] When the obtaining module 21 obtains the arrangement difficulty of each part in the smart glasses, the obtaining module 21 is specifically configured to:

[0148] Calculate the size factor of the part by calculating the ratio of the volume of the part to the total volume of the parts;

[0149] Calculate the shape complexity of the part by calculating the ratio of the number of curved surfaces of the part;

[0150] Obtain the heat dissipation requirement index of the part by simulating the heat flux density of the part when the part works through a finite element analysis tool;

[0151] Take the greater value between the number of interfaces and the number of connection wire harnesses of the part as the electrical connection complexity index of the part;

[0152] Take the tolerance level of the part as the assembly accuracy requirement index of the part;

[0153] Obtain the arrangement difficulty coefficient of the part by weightedly summing the size factor, the shape complexity, the heat dissipation requirement index, the electrical connection complexity index, and the assembly accuracy requirement index.

[0154] In a possible implementation, the determination module 22 is specifically configured to:

[0155] Establish a glasses skeleton model and set a part arrangement area in the glasses skeleton model;

[0156] According to the order from large to small of the arrangement difficulties of the parts, the parts to be arranged are placed in the part arrangement area in a non-overlapping manner in sequence based on the arrangement difficulties of the parts, and the arrangement positions of the parts are updated based on the gradient descent method until the change rate of the arrangement positions is less than a preset threshold, to obtain the multiple candidate smart glasses design schemes.

[0157] In a possible implementation, the evaluation module 23 is specifically configured to:

[0158] Calculate the average distance from the fingertips of the user to the AI button as the AI button accessibility index of the candidate smart glasses design scheme based on the target finger length of the user and the arrangement position of the AI button in the candidate smart glasses design scheme.

[0159] based on the trigger pressure of the AI button in the candidate smart glasses design scheme, calculate the AI button comfort index of the candidate smart glasses design scheme;

[0160] based on the Monte Carlo method, determine the mis-touch rate of the user operating the AI button in the candidate smart glasses design scheme in the simulated daily use scenario;

[0161] based on the Monte Carlo method, determine the success rate of the user operating the AI button in the candidate smart glasses design scheme in the gloves and humid environment, as the AI button environmental adaptability index of the candidate smart glasses design scheme;

[0162] weight and sum the AI button accessibility index, the AI button comfort index, the mis-touch rate and the AI button environmental adaptability index to obtain the AI button operation effect score of the candidate smart glasses design scheme.

[0163] In a possible implementation, the evaluation module 23 is specifically configured to:

[0164] based on the layout positions of each part in the candidate smart glasses design scheme, measure the minimum distance between the AI button and each surrounding part in the candidate smart glasses design scheme as the spatial compatibility index of the candidate smart glasses design scheme;

[0165] based on the layout positions of each part in the candidate smart glasses design scheme, simulate the electromagnetic interference value between the AI button and each other part in the candidate smart glasses design scheme through a finite element analysis tool, and take the maximum value in the electromagnetic interference value as the electromagnetic compatibility index of the candidate smart glasses design scheme;

[0166] based on the layout positions of each part in the candidate smart glasses design scheme, simulate the thermal resistance between the AI button and each other part in the candidate smart glasses design scheme through a finite element analysis tool, and take the maximum value in the thermal resistance as the thermal conductivity index of the candidate smart glasses design scheme;

[0167] weight and sum the spatial compatibility index, the electromagnetic compatibility index and the thermal conductivity index to obtain the hardware integration relationship score of the candidate smart glasses design scheme.

[0168] In a possible implementation, the selection module 24 is specifically configured to:

[0169] weight and sum the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme to obtain the comprehensive score of the candidate smart glasses design scheme;

[0170] take the candidate smart glasses design scheme with the maximum comprehensive score as the target smart glasses design scheme.

[0171] In one possible implementation, the selection module 24 is also used for:

[0172] Before obtaining the comprehensive score of each candidate smart glasses design by weighted summing of the AI ​​button operation effect score and the hardware integration relationship score, the weight of the AI ​​button operation effect score is calculated based on the occurrence ratio of multiple preset scenarios and the usage frequency of the AI ​​button in each preset scenario; among which, preset scenarios include daily use scenarios, mobile scenarios and professional work scenarios.

[0173] In one possible implementation, the formula for calculating the weight of the AI ​​button operation effect score is as follows:

[0174]

[0175] in, The weighting of the AI ​​button operation performance score. For the first The percentage of occurrence in each scenario For the first Frequency of AI button usage in various scenarios.

[0176] This invention generates multiple candidate solutions by prioritizing the layout difficulty of each component in the smart glasses. This avoids the limitations of a single solution while considering the layout difficulty of each component, providing a sufficient basis for subsequent evaluation. The evaluation of operational effects and hardware integration relationships based on component layout positions enables quantitative analysis of the solutions, ensuring the objectivity and accuracy of the evaluation results. Finally, the target solution is selected based on the evaluation results, which can balance the ease of operation of the AI ​​button and the stability of integration with other hardware, significantly improving the overall design quality of the smart glasses, reducing the number of reworks in the later stages of design, reducing R&D costs, shortening the product cycle from design to mass production, and enhancing the product's market competitiveness.

[0177] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example...Figure 2 The functions of the acquisition module 21, the determination module 22, the evaluation module 23 and the selection module 24 are shown.

[0178] It should be understood that, in the embodiments of the present application, the processor 301 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0179] The input device 302 can include a touchpad, a fingerprint collection sensor (for collecting fingerprint information and direction information of a fingerprint of a user), a microphone, etc., and the output device 303 can include a display (LCD, etc.), a speaker, etc.

[0180] The memory 304 can include a read-only memory and a random access memory, and provide instructions and data for the processor 301. A part of the memory 304 can also include a non-volatile random access memory. For example, the memory 304 can also store device type information.

[0181] In specific implementations, the processor 301, the input device 302 and the output device 303 described in the embodiments of the present application can execute the implementation manners described in the first embodiment and the second embodiment of the intelligent glasses design method provided by the embodiments of the present application, and can also execute the implementation manners of the electronic device described in the embodiments of the present application, which will not be described here.

[0182] In another embodiment of the present application, a computer readable storage medium is provided, which stores a computer program. The computer program includes program instructions, which, when executed by a processor, implement all or part of the processes of the above-mentioned embodiment methods. The computer program can also instruct related hardware to complete the implementation. The computer program can be stored in a computer readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0183] The computer readable storage medium can be an internal storage unit of the electronic device of any of the preceding embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the electronic device. The computer readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0184] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in general terms in the above description. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0185] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic device and the units described above can refer to the corresponding processes in the above-mentioned method embodiments, which will not be described here.

[0186] In several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other manners. For example, the embodiments of the apparatus described above are merely schematic; the division of the units is merely logical function division; an actual implementation can be divided into different units depending on actual conditions; or a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, or can be in electrical, mechanical or other forms.

[0187] The units described as separated components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0188] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically as a separate unit, or two or more units can be integrated in one unit. The integrated unit can be implemented in the form of hardware, or in the form of a software functional unit.

[0189] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto; any skilled person in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of designing smart glasses, characterized in that, The method comprises the following steps: obtaining the layout difficulty of each part in the smart glasses respectively; determining a plurality of candidate smart glasses design schemes based on the layout difficulty of each part respectively; based on the layout position of each part in each candidate smart glasses design scheme, evaluating the AI button operation effect score and the hardware integration relationship score of the candidate smart glasses design scheme; selecting a target smart glasses design scheme from the candidate smart glasses design schemes based on the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme; wherein the layout difficulty of each part in the smart glasses is determined by the following method: calculate the ratio of the volume of the part to the total part volume to obtain the size factor of the part; calculate the proportion of the number of curved surfaces of the part as the shape complexity of the part; simulate the heat flux density of the part when working through the finite element analysis tool to obtain the heat dissipation requirement index of the part; take the larger value between the number of interfaces and the number of connection wires of the part as the electrical connection complexity index of the part; take the tolerance grade of the part as the assembly accuracy requirement index of the part; weight and sum the size factor, shape complexity, heat dissipation requirement index, electrical connection complexity index and assembly accuracy requirement index to obtain the layout difficulty coefficient of the part.

2. The smart glasses design method of claim 1, wherein, determining a plurality of candidate smart glasses design schemes based on the layout difficulty of each part respectively, comprising: establishing a glasses skeleton model and setting a part layout area in the glasses skeleton model; based on the layout difficulty of each part respectively, in the order of layout difficulty from large to small, sequentially place each part to be laid out in the part layout area without overlapping, and update the layout position of each part based on the gradient descent method until the change rate of the layout position is less than a preset threshold, to obtain a plurality of candidate smart glasses design schemes.

3. The smart glasses design method of claim 1, wherein, For each candidate smart glasses design scheme, based on the layout position of each part in the candidate smart glasses design scheme, evaluate the AI button operation effect score of the candidate smart glasses design scheme, comprising: based on the target finger length of a plurality of users respectively and the layout position of the AI button in the candidate smart glasses design scheme, calculate the average distance from the user's fingertip to the AI button as the AI button accessibility index of the candidate smart glasses design scheme; based on the trigger pressure of the AI button in the candidate smart glasses design scheme, calculate the AI button comfort index of the candidate smart glasses design scheme; determine the mis-touch rate of the user operating the AI button in the candidate smart glasses design scheme in the simulated daily use scenario based on the Monte Carlo method; determine the success rate of the user operating the AI button in the candidate smart glasses design scheme in the gloves and humid environment based on the Monte Carlo method as the AI button environmental adaptability index of the candidate smart glasses design scheme; weight and sum the AI button accessibility index, the AI button comfort index, the mis-touch rate and the AI button environmental adaptability index to obtain the AI button operation effect score of the candidate smart glasses design scheme.

4. The smart glasses design method of claim 1, wherein, For each candidate smart glasses design scheme, based on the layout positions of the parts in the candidate smart glasses design scheme, the hardware integration relationship score of the candidate smart glasses design scheme is evaluated, including: Based on the layout positions of the parts in the candidate smart glasses design scheme, the minimum distance between the AI button and the surrounding parts in the candidate smart glasses design scheme is measured as the space compatibility index of the candidate smart glasses design scheme; Based on the layout positions of the parts in the candidate smart glasses design scheme, the electromagnetic interference value between the AI button and other parts in the candidate smart glasses design scheme is simulated by a finite element analysis tool, and the maximum value in the electromagnetic interference value is taken as the electromagnetic compatibility index of the candidate smart glasses design scheme; Based on the layout positions of the parts in the candidate smart glasses design scheme, the thermal resistance between the AI button and other parts in the candidate smart glasses design scheme is simulated by a finite element analysis tool, and the maximum value in the thermal resistance is taken as the thermal conductivity index of the candidate smart glasses design scheme; The space compatibility index, the electromagnetic compatibility index and the thermal conductivity index are weighted and summed to obtain the hardware integration relationship score of the candidate smart glasses design scheme.

5. The smart glasses design method of claim 1, wherein, The AI button operation effect score and the hardware integration relationship score based on each candidate smart glasses design scheme are used to select a target smart glasses design scheme from the candidate smart glasses design schemes, including: The AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme are weighted and summed to obtain the comprehensive score of the candidate smart glasses design scheme; The candidate smart glasses design scheme with the highest comprehensive score is taken as the target smart glasses design scheme.

6. The method of designing smart glasses as claimed in claim 5, wherein, Before the AI button operation effect score and the hardware integration relationship score of each candidate smart glasses design scheme are weighted and summed to obtain the comprehensive score of the candidate smart glasses design scheme, it further includes: Based on the occurrence proportion of a plurality of preset scenes and the use frequency of the AI button under each preset scene, the weight of the AI button operation effect score is calculated, and the preset scene includes a daily use scene, a mobile scene and a professional work scene.

7. The method of designing smart glasses as claimed in claim 6, wherein, The calculation formula of the weight of the AI button operation effect score is: wherein, a weight for scoring the AI key operation effect, a proportion of occurrence of the first scene, a proportion of occurrence of the first scene.

8. An intelligent glasses design apparatus, characterized by comprising: It includes: An acquisition module is configured to acquire a layout difficulty corresponding to each part in smart glasses; A determination module is configured to determine a plurality of candidate smart glasses design schemes based on the layout difficulty corresponding to each part; An evaluation module is configured to evaluate an AI button operation effect score and a hardware integration relationship score of each candidate smart glasses design scheme based on the layout positions of the parts in the candidate smart glasses design scheme; A selection module is configured to select a target smart glasses design scheme from the candidate smart glasses design schemes based on the AI button operation effect scores and the hardware integration relationship scores; When the acquisition module acquires the layout difficulty corresponding to each part in the smart glasses, it is specifically configured to: Calculate the volume ratio of the part to the total part volume to obtain the size factor of the part; Calculate the surface number ratio of the part as the shape complexity of the part; Simulate the heat flux density of the part when working through a finite element analysis tool, and obtain the heat dissipation requirement index of the part; Take the larger value between the number of interfaces and the number of connection wire harnesses of the part as the electrical connection complexity index of the part; Take the tolerance grade of the part as the assembly precision requirement index of the part; Weighted sum the size factor, the shape complexity, the heat dissipation requirement index, the electrical connection complexity index and the assembly precision requirement index to obtain the layout difficulty coefficient of the part.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 7.

Images