Method, device, storage medium and electronic equipment for predicting coated lens information

Abstract

This application discloses a method, apparatus, storage medium, and electronic device for predicting information about coated lenses. The application coats a specified type of film within the optically effective area of ​​a lens. Based on a pre-trained first model, it determines a first mapping relationship between the surface shape information of the optically effective area and the performance information of the lens assembled from the lens. Based on a pre-trained second model, it determines a second mapping relationship between the surface shape information of the optically effective area and the manufacturing information of the non-optically effective area. Based on the first and second mapping relationships, it predicts the manufacturing information of the lens to be assembled with the target lens, or predicts the performance information of the lens assembled with the target lens based on the manufacturing information of a second area of ​​the target lens. Therefore, this application can predict the lens performance information based on the lens information before the lens is assembled into a lens, improving the lens manufacturing yield.

Description

Technical Field

[0001] This application generally relates to the technical field of assembling optical lenses into optical lenses. More specifically, this application relates to methods, apparatus, storage media, and electronic devices for predicting information about coated lenses. Background Technology

[0002] In the field of optical imaging for mobile devices, manufacturers of mobile phones, handheld cameras, drones and other terminals have a continuous pursuit of improving image quality and reducing costs. As one of the core components of imaging, improving the manufacturing precision and yield of lenses is the key to achieving the above goals.

[0003] Lenses are typically composed of multiple aspherical lens elements assembled together. Even minute errors in the parameters of these aspherical lenses can degrade the performance of the assembled lens, resulting in substandard lenses. In special cases such as lens edge cutting, the lens coating needs to be upgraded to an ultra-low reflectivity micro / nano structure coating. The surface reflectivity of the coated lens may be as low as 1%, making it difficult for commonly used rapid surface inspection equipment to identify lens defects. Due to limitations in cost and efficiency, existing solutions cannot inspect mass-produced lenses with ultra-low reflectivity coatings, only identifying substandard products after lens assembly, resulting in a low lens manufacturing yield.

[0004] Therefore, how to quickly and cost-effectively inspect lenses coated with ultra-low reflectivity films before lens assembly to improve lens manufacturing yield has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, storage medium, and electronic device for predicting coated lens information, in order to partially solve the above-mentioned problems existing in the prior art.

[0006] The embodiments of this application adopt the following technical solutions:

[0007] In a first aspect, this application provides a method for predicting coated lens information, wherein the lens includes an optically effective region and a non-optically effective region, and a specified type of coating is coated within the optically effective region. The method includes: designating the optically effective region as a first region and at least a portion of the non-optically effective region as a second region; determining a first mapping relationship between surface information of the first region and performance information of a lens assembled from the lens, based on a pre-trained first model; and determining a second mapping relationship between surface information of the first region and manufacturing information of the second region, based on a pre-trained second model; and predicting manufacturing information of a lens assembled from the target lens, based on the first mapping relationship and the second mapping relationship, according to the performance information of the target lens, or predicting performance information of a lens assembled from the target lens, based on the manufacturing information of the second region of the target lens.

[0008] Optionally, the first model is pre-trained by: acquiring a sample lens and assembling the sample lens into a lens as a sample lens; determining the surface profile information of the first region of the sample lens after coating with a specified type of film based on the second mapping relationship and the manufacturing information of the second region of the sample lens; predicting the performance information to be optimized of the sample lens based on the surface profile information of the first region of the sample lens after coating with a specified type of film and the first model to be trained; acquiring the performance information of the sample lens as the actual performance information; and training the first model to be trained based on the performance information to be optimized and the actual performance information.

[0009] Optionally, the second model is pre-trained by: acquiring a sample lens; acquiring complete surface information of the sample lens before it is coated with a specified type of film and manufacturing information of the second region, wherein the complete surface information includes the surface information of the first region of the sample lens before it is coated with the specified type of film and the surface information of the second region of the sample lens; and training the second model to be trained based on the complete surface information and the manufacturing information of the second region, so that the trained second model is used to predict the surface information of the first region of the sample lens after it is coated with the specified type of film, corresponding to the manufacturing information of the second region.

[0010] Optionally, based on the complete surface information and the manufacturing information of the second region, the second model to be trained is trained, specifically including: extracting features of the surface information of the first region of the sample lens before the coating of the specified type of film and features of the surface information of the second region of the sample lens; associating the manufacturing information of the second region, the features of the surface information of the first region of the sample lens before the coating of the specified type of film, and the features of the surface information of the second region of the sample lens to obtain associated features; and training the second model to be trained based on the associated features.

[0011] Optionally, extracting features of the surface profile information of the first region of the sample lens before the coating of the specified type of film and features of the surface profile information of the second region of the sample lens respectively includes: inputting the surface profile information of the first region of the sample lens before the coating of the specified type of film into a feature extraction model to obtain the features of the first region of the sample lens before the coating of the specified type of film output by the feature extraction model; and inputting the surface profile information of the second region of the sample lens into a feature extraction model to obtain the features of the second region of the sample lens output by the feature extraction model.

[0012] Optionally, the surface profile information includes at least one of the following: (1) a lens surface topography map; (2) a height distribution map obtained by processing the lens surface topography map; (3) information obtained by performing Fourier transform processing on the lens surface topography map; and (4) a difference map obtained by processing the lens surface topography map.

[0013] Optionally, the difference map is obtained by: acquiring a standard lens surface topography map when designing the lens; determining the difference between the lens surface topography map and the acquired standard lens surface topography map; and determining the difference map based on the determined difference.

[0014] Optionally, surface type information includes differences before and after changes in environmental information; performance information includes differences before and after changes in environmental information.

[0015] Optionally, the method further includes: determining whether the predicted performance information meets the preset standard based on the preset performance information standard, and processing the target lens based on the determination result.

[0016] Optionally, the second region is the region with the lowest reflectivity in the non-optically effective region.

[0017] Optionally, the manufacturing information includes mold manufacturing information and / or mold usage information for manufacturing lenses. The mold manufacturing information includes at least one of the following: mold cavity surface roughness, machining tolerance, contour error, and flow channel structure parameters, venting structure parameters, and water channel structure parameters connected to the mold cavity. The mold usage information includes at least one of the following: barrel temperature, nozzle temperature, mold temperature, heating gradient, material type, material batch, injection pressure, holding pressure, injection speed, molding time, holding time, cooling time, and annealing time. The performance information includes at least one of the following: resolution, modulation transfer function (MTF), illuminance, aberrations, stray light, ghosting, depth of field, surface defects, maximum principal ray angle, focal length, aperture, field of view, and maximum image height.

[0018] In a second aspect, this application provides an apparatus for predicting coated lens information. The lens includes an optically effective region and a non-optically effective region, and a film of a specified type is coated within the optically effective region. The apparatus includes: a defining module for defining the optically effective region as a first region and at least a portion of the non-optically effective region as a second region; a determining module for determining a first mapping relationship between surface information of the first region and performance information of a lens assembled from the lens, based on a pre-trained first model, and for determining a second mapping relationship between the surface information of the first region and manufacturing information of the second region, based on a pre-trained second model; and a predicting module for predicting manufacturing information of the lens assembled from the target lens, based on the first mapping relationship and the second mapping relationship, according to the performance information of the target lens, or predicting the performance information of the lens assembled from the target lens, based on the manufacturing information of the second region of the target lens.

[0019] In a third aspect, this application provides a computer-readable storage medium, characterized in that the storage medium stores a computer program, which, when executed by a processor, implements the above-described method for predicting coated lens information.

[0020] In a fourth aspect, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the program to implement the above-described method for predicting coated lens information.

[0021] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: In this application, the lens includes an optically effective region and a non-optically effective region. A film of a specified type is coated within the optically effective region, which is designated as the first region, and at least a portion of the non-optically effective region is designated as the second region. Based on a pre-trained first model, a first mapping relationship is determined between the surface profile information of the first region and the performance information of the lens assembled from the lens. Based on a pre-trained second model, a second mapping relationship is determined between the surface profile information of the first region and the manufacturing information of the second region. Based on the first and second mapping relationships, the manufacturing information of the lens assembled from the target lens is predicted according to the performance information of the target lens, or the performance information of the lens assembled from the target lens is predicted according to the manufacturing information of the second region of the target lens. In some embodiments of this application, by determining the correspondence between the manufacturing information of the non-optically effective area and the surface information of the optically effective area after coating, and by determining the correspondence between the surface information of the optically effective area after coating and the performance information of the lens, the manufacturing information of the non-optically effective area and the lens performance information are correlated. This application solves the problem in the prior art that surface inspection equipment has difficulty identifying lens defects due to the coating of ultra-low reflection film on the lens. Furthermore, this application can predict the performance information of the lens based on the manufacturing information of the non-optically effective area of ​​the lens before the ultra-low reflection film-coated lens is assembled into a lens, so as to identify ultra-low reflection film-coated lenses that do not meet the lens performance requirements, thereby preventing unqualified lenses from entering the subsequent process. This solves the problem in the prior art that the lens performance is only found to be substandard after the ultra-low reflection film-coated lens is assembled into a lens, and achieves the effect of improving the lens manufacturing yield.

[0022] Furthermore, based on the mapping relationship between the manufacturing information of lenses coated with ultra-low reflection coatings and lens performance information, this application can determine the conditions that the manufacturing information of lenses coated with ultra-low reflection coatings needs to meet before manufacturing lenses coated with ultra-low reflection coatings, in order to manufacture lenses coated with ultra-low reflection coatings that meet the requirements, thereby improving the manufacturing yield of lenses. Attached Figure Description

[0023] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of this application are illustrated by way of example and not limitation, and the same or corresponding reference numerals denote the same or corresponding parts, wherein: Figure 1 A flowchart illustrating a method for predicting coated lens information provided in this application embodiment; Figure 2 This is a schematic diagram of an optical lens coating provided in an embodiment of this application; Figure 3This is a schematic diagram of another optical lens coating provided in an embodiment of this application; Figure 4 This is an example of the actual coating effect on the optical lens provided in the embodiments of this application; Figure 5 A schematic diagram of the structure of a device for predicting coated lens information provided in an embodiment of this application; Figure 6 A schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] The following explains the terms related to the manufacture of optical lenses and the performance of optical lenses in this application.

[0026] I. Lens Structure and Geometric Parameter Terminology Center thickness: refers to the thickness at the geometric center of the lens, and is a core structural parameter of the lens.

[0027] Aspherical coefficient: A coefficient used to define the surface profile of an aspherical lens, determined by the aspherical equation to account for the curvature variation of the lens surface.

[0028] Outer diameter: The maximum radial dimension of the lens, used to determine the assembly dimensions between the lens and the lens barrel.

[0029] Sagittal height: The vertical distance from the reference plane at the edge of the lens surface to the highest point of the lens surface, representing the degree of curvature of the lens surface.

[0030] Fastening diameter: The radial dimension of the lens used for fastening and positioning with the lens barrel or spacer, ensuring the radial positioning accuracy of the lens.

[0031] Support position: The position where the lens is axially supported and limited within the lens barrel, used to control the assembly position of the lens along the optical axis.

[0032] Eccentricity: The radial offset of the geometric center of the lens relative to the optical axis of the optical system, which is an assembly error.

[0033] Tilt: The tilt angle of the lens surface normal relative to the optical axis, which is an assembly error.

[0034] II. Lens Surface Precision and Quality Terminology Peak-to-Valley (PV): The difference between the highest and lowest points on the lens surface, representing the accuracy of the lens surface shape.

[0035] Arithmetic Mean Roughness (Ra): The arithmetic mean of the microscopic irregularities on the surface of a lens, characterizing the smoothness of the surface.

[0036] Root Mean Square (RMS): The root mean square value of surface profile error, used to more accurately characterize surface quality.

[0037] Lens contour error: the deviation between the actual surface of the lens and the ideal design surface shape.

[0038] Aspherical equations: mathematical expressions used to accurately describe the surface shape of aspherical lenses.

[0039] III. Mold-related terminology (compression molding / injection mold) Mold material: The material used to manufacture lens forming molds, which affects the mold life and forming accuracy.

[0040] Mold coating: A functional film layer applied to the surface of a mold cavity to improve demolding performance, wear resistance, and surface quality.

[0041] Mold cavity inner surface roughness: The surface smoothness of the mold forming cavity directly determines the arithmetic mean roughness Ra of the lens.

[0042] Machining tolerance: Allowable dimensional deviations during mold machining.

[0043] The contour error of the mold cavity refers to the overall geometric deviation between the actual inner surface contour shape of the mold cavity and the theoretical design reference contour, which includes radial deviation of the contour, surface undulation, curvature deviation and local concave and convex deformation.

[0044] Damage caused by mold use: wear, scratches, deformation and other damage caused by repeated molding.

[0045] The runner structure parameters connected to the mold cavity refer to the geometric and structural dimensional parameters of the gating system in the injection mold, from the main runner and branch runners to the gating system before entering the lens cavity. These parameters include all structural features such as runner cross-sectional shape, runner diameter / cross-sectional length and width, runner length, runner taper, corner fillets, branch layout, runner slope, and gate connection dimensions. These parameters are used to control melt flow rate, flow velocity, shear rate, flow balance, pressure loss, and temperature holding capacity. They are key pre-construction structural parameters that directly determine the filling pattern, residual stress, and surface replication accuracy inside the mold cavity.

[0046] Flow channel length and shape: The size and shape of the material flow channels in an injection or molding system.

[0047] Nozzle shape: The structural shape of the injection molding machine nozzle affects the stability of material injection.

[0048] Gate shape and size: The structure and size of the entrance for material to enter the mold cavity, which affects the filling effect and appearance quality.

[0049] Venting structure parameters: These include structural parameters such as the depth, width, length, spacing, number of venting stages, and pressure relief channel dimensions of the venting grooves at the corresponding positions of the mold cavity. These parameters are used to promptly discharge trapped air inside the mold cavity and volatile gases generated by the resin during the injection molding process.

[0050] Venting structure location: The structural location in the mold used to vent gas from the mold cavity to avoid defects such as air bubbles and insufficient glue.

[0051] Water channel structural parameters: These include geometric parameters such as the diameter of the cooling water channels, the distance between the water channels and the mold cavity, the water channel layout, the water channel direction, the bend radius, and the symmetrical arrangement of the water channels. These parameters refer to the geometric dimensions and layout characteristics of the cooling water channels arranged around the mold cavity in the injection mold. They are used to control the cooling rate, temperature field uniformity, heat dissipation efficiency, and thermal balance of the mold and mold cavity. They are the core structural parameters for regulating the shrinkage, deformation, residual stress, and surface accuracy of the lens during injection molding.

[0052] The positional distribution of water channels relative to runners and gates: The layout of the mold cooling water channels affects the uniformity of cooling and molding efficiency.

[0053] IV. Injection Molding / Compression Molding Process Terminology Barrel temperature: The heating temperature of the injection molding machine barrel affects the molten state of the material.

[0054] Nozzle temperature: The temperature at the nozzle position of the injection molding machine.

[0055] Mold temperature: The forming temperature of the mold cavity affects the lens precision and internal stress.

[0056] Temperature gradient: The rate of temperature change during the heating process.

[0057] Material type: Model of optical plastic or optical glass.

[0058] Material batches: Different production batches of the same type of optical material can affect consistency.

[0059] Injection pressure: The pressure that propels material into the mold cavity during injection molding.

[0060] Maintaining pressure (also known as holding pressure): The amount of pressure maintained inside the mold cavity after filling is completed.

[0061] Injection speed: The volume or rate at which material is injected into the mold cavity per unit time.

[0062] Molding time: The total time required to complete one molding cycle.

[0063] Holding time: The duration of the holding phase.

[0064] Cooling time: The time it takes for the lens to cool and solidify inside the mold.

[0065] Annealing time: The heat treatment time used to eliminate internal stress in the lens.

[0066] V. Lens Optical Performance Terminology Modulation Transfer Function (MTF): A core indicator for evaluating the sharpness, clarity, and resolution of a lens image.

[0067] Resolution: The MTF value characterizes the imaging resolution at different spatial frequencies.

[0068] Aberrations: Optical deviations that affect image quality, including spherical aberration, coma, astigmatism, field curvature, chromatic aberration, distortion, etc.

[0069] Color difference: Color deviation caused by inconsistent focusing of light of different wavelengths.

[0070] Optical distortion: is one of the inherent monochromatic aberrations of an optical system. It refers to the relative deviation between the actual principal ray image height and the ideal paraxial image height at different field of view positions. It is used to characterize the degree of bending and deformation that occurs after an optical lens images a straight object in the object space. It includes barrel distortion and pincushion distortion.

[0071] TV distortion is a quantitative indicator of the overall shape distortion of an imaging system on the image plane, representing the geometric deformation caused by the inconsistent magnification of the image edges relative to the center.

[0072] Field curvature: The ideal imaging surface is a plane, but in reality it is a curved surface, resulting in blurred edges in the field of view.

[0073] Illuminance: Generally refers to relative illuminance, the ratio of the brightness at the edge of the image plane to the brightness at the center, characterizing the uniformity of brightness.

[0074] Stray light: Interference light generated when scattered or reflected light, which is not required for imaging, reaches the image plane.

[0075] Ghosting: A false image formed by multiple reflections between lenses.

[0076] Depth of field: The range of object distances from which a lens can produce a clear image.

[0077] Maximum Chief Ray Angle Max (CRAmax): The maximum angle between the chief ray and the optical axis.

[0078] Effective Focal Length (EFL): This refers to the axial distance between the principal plane of an optical system and the point where parallel incident rays converge.

[0079] F-number: denoted as f / #, it is the aperture value of a lens, which is the ratio of the effective focal length (EFL) of the optical system to the entrance pupil diameter, and represents the light transmission capability.

[0080] Field of view (FOV): refers to the maximum range of a scene that an optical lens can clearly image, usually expressed as diagonal field of view, horizontal field of view, and vertical field of view.

[0081] Maximum image height (ImgH): The maximum effective imaging height of the image plane, which refers to the radial height of the image plane corresponding to the maximum field of view in the optical system, that is, the vertical distance from the center of the optical axis to the outermost edge of the effective imaging area.

[0082] Defective appearance: Visual defects such as stains, cracks, bubbles, scratches, and missing glue appear on the lens surface.

[0083] In existing technologies, lenses are typically composed of multiple aspherical lens elements assembled together. Currently, aspherical lenses are usually manufactured using conventional plastic processing techniques such as injection molding. During manufacturing, unavoidable errors occur in mold processing, process control, and coating due to lens coating. This leads to significant deviations between the actual optical performance of the aspherical lens and its theoretical design, making it difficult to achieve ideal performance and manufacturing yield in the assembled lens. For example, these errors can cause inaccuracies in various parameters of the aspherical lens, such as thickness, aspherical coefficient, outer diameter, sagitta, snapping diameter, and bearing position. Even an error of only 1-2 micrometers in any parameter, such as eccentricity, tilt, PV, or Ra, can degrade the specific field-of-view performance of the assembled lens, resulting in defective products. Furthermore, since a lens is assembled from multiple aspherical lens elements, the various errors within these elements can have a cumulative coupling effect, collectively affecting the overall imaging performance of the lens.

[0084] Furthermore, when lens stray light and ghosting issues are severe due to special circumstances such as lens edge cutting, the lens coating needs to be upgraded to an ultra-low reflectivity micro / nano structure coating. This involves using processes such as PVD evaporation, sputtering, or atomic layer deposition (ALD) to add multilayer films of varying thicknesses ranging from tens to hundreds of nanometers to the lens surface to achieve effects such as anti-reflection, hardening, and waterproofing. After using such an ultra-low reflectivity coating, the surface reflectivity of the lens may be as low as below 1%, causing a decrease in the detection accuracy of some commonly used rapid surface shape inspection equipment, such as multi-wavelength interferometry and white light interferometry, due to insufficient reflection intensity. Moreover, the microstructure of the ultra-low reflectivity coating itself and coating defects will also affect the surface shape inspection results. In summary, defects in lenses coated with ultra-low reflectivity coatings will be difficult to identify. In addition, when mass-producing lenses with ultra-low reflectivity coating systems, the lenses will immediately enter the next process for coating after injection molding. Even if lens defects can be accurately detected, time and cost constraints make it impossible to conduct such inspections. Defective lenses must also enter the subsequent assembly process, resulting in a decrease in yield.

[0085] In view of this, embodiments of this application provide a method for predicting coated lens information, which enables the prediction of coated lenses with surface defects while minimizing the impact on mass production efficiency, thereby improving lens manufacturing yield. Specifically, the lens includes an optically effective region and a non-optically effective region. A specified type of film is coated within the optically effective region. This method involves using the optically effective region as a first region and at least a portion of the non-optically effective region as a second region. Based on a pre-trained first model, a first mapping relationship is determined between the surface information of the first region and the performance information of the lens assembled from the lens. Furthermore, based on a pre-trained second model, a second mapping relationship is determined between the surface information of the first region and the manufacturing information of the second region. Based on the first and second mapping relationships, the manufacturing information of the lens assembled with the target lens is predicted according to the performance information of the target lens, or the performance information of the lens assembled with the target lens is predicted according to the manufacturing information of the second region of the target lens. On the one hand, this application can predict the surface profile of the optically effective area of ​​the lens after it has been coated with special films such as ultra-low reflection coating, based on the manufacturing information of the non-optically effective area of ​​the lens. Therefore, based on the predicted surface profile information, it can predict the performance information of the lens assembled from the lens, thereby predicting whether the lens will be defective before assembly and improving the lens manufacturing yield. On the other hand, this application can also predict the manufacturing information of the lens required to manufacture the lens after determining the lens's performance information, for example, by designing the standard performance information of the lens. This allows for the manufacture of the lens according to the lens's manufacturing information, further improving the lens manufacturing yield.

[0086] The specific embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0087] Figure 1 A flowchart of a method for predicting coated lens information provided in this application embodiment may include the following steps: Step S110: Using the optically effective area as a first area and at least a portion of the non-optically effective area as a second area; Step S130: Based on a pre-trained first model, determining a first mapping relationship between the surface information of the first area and the performance information of the lens assembled from the lens, and, based on a pre-trained second model, determining a second mapping relationship between the surface information of the first area and the manufacturing information of the second area; Step S150: Based on the first mapping relationship and the second mapping relationship, predicting the manufacturing information of the lens assembled from the target lens according to the performance information of the target lens, or predicting the performance information of the lens assembled from the target lens according to the manufacturing information of the second area of ​​the target lens.

[0088] In step S110, the optically effective region refers to the area within the lens through which the light rays used for imaging pass, while the non-optically effective region refers to other areas within the lens besides the optically effective region, i.e., the areas within the lens through which the light rays used for imaging do not pass. In some embodiments of this application, the first region can be the entire optically effective region or a portion of it. At least a portion of the second region can be a part of the non-optically effective region or the entire non-optically effective region. After coating with a specified type of film, the first region can be an undetectable region, and the second region can be a detectable region.

[0089] In some embodiments of this application, the lens includes an optically effective region and a non-optically effective region. Due to practical needs, a specified type of film is deposited within the optically effective region. Generally, ultra-low reflectivity micro / nano structure coatings can be applied within the optically effective region. Therefore, in some embodiments of this application, the specified type of film deposited within the optically effective region can be an ultra-low reflectivity film. Furthermore, if other types of films are deposited within the optically effective region, and commonly used rapid surface inspection equipment struggles to identify defects in the coated lens for other reasons, the method for predicting coated lens information provided in this application can also be applied. That is, the specified type of film in this application is a film that makes it difficult for commonly used rapid surface inspection equipment to identify lens defects, including ultra-low reflectivity films, etc.

[0090] Because a specified type of film is deposited within the optically effective area of ​​the lens, this application can divide the lens into detectable and undetectable regions. This application provides two different embodiments for depositing the specified type of film onto the lens.

[0091] In one embodiment provided in this application, Figure 2 This is a schematic diagram of an optical lens coating provided in an embodiment of this application. Figure 2 In this process, the lens includes an optically effective area 210 (i.e., a dark-colored circular area) and a non-optically effective area 220 (i.e., a light-colored area). An ultra-low reflectivity film can be deposited only in the optically effective area 210, or different reflectivity films can be deposited in the optically effective area 210 and the non-optically effective area 220 respectively. First, a higher reflectivity anti-reflection film (1%-5%) that meets the reflectivity requirements for detection is deposited. Then, a special fixture is used to shield the area so that when the ultra-low reflectivity (<1%) anti-reflection film is deposited in the optically effective area 210, the non-optically effective area 220 retains its original anti-reflection film. This ensures that stray light and ghosting in the optically effective area 210 are controlled without affecting the detection of the non-optically effective area 220.

[0092] use Figure 2 After coating in the illustrated method, since the non-optically effective region 220 is not coated with an ultra-low reflectivity film, any position in the non-optically effective region 220 can be considered as a detection region (i.e., the second region). Considering that the optically effective region 210 is coated with an ultra-low reflectivity film, in order to make the surface shape information of the optically effective region 210 after being coated with an ultra-low reflectivity film, which is predicted based on the surface shape information of the non-optically effective region 220, more accurate, when selecting the second region in the non-optically effective region 220, the region with a reflectivity close to that of the optically effective region 210 can be selected as the second region according to the reflectivity of each position in the non-optically effective region 220. Therefore, in this embodiment, the second region can be the region with the lowest reflectivity in the non-optically effective region.

[0093] In another embodiment provided in this application, Figure 3 This is a schematic diagram of another optical lens coating provided in an embodiment of this application. Figure 3 In this process, several regions of preset sizes can be selected in the non-optically effective region 220 as measurement windows. The optically effective region 210 and the non-optically effective region 220 can be coated with the same ultra-low reflectivity film system, but the reserved measurement window area in the non-optically effective region 220 is blocked by a fixture (as shown by window 231 or window 232 in the figure) to prevent the window from being covered by the ultra-low reflectivity film system, so that the measurement window area can still meet the accuracy requirements of the measurement.

[0094] Based on the above information regarding lens coating, this application provides actual image diagrams showing the effect of lens coating. Figure 4 The image shows the effect of the actual coating on the optical lens provided in the embodiment of this application.

[0095] exist Figure 4In this design, a lens 41 for assembling an optical lens includes an optically effective region 210 at its center and a non-optically effective region 220 outside the optically effective region 210. The optically effective region 210 is typically circular, forming a circle with an optically effective diameter as its radius. The optically effective diameter is the boundary of the area through which light rays used for imaging pass. The non-optically effective region 220, outside the optically effective diameter, does not transmit light and is used to design a support structure so that adjacent lenses can rest against each other. A portion 420 within the optically effective region 210 and a portion 430 within the non-optically effective region 220 are selected respectively, and their coating effects are as follows: Figure 4 As shown, coating image 422 displays the coating condition of a portion of region 420 within the optically effective region 210, and coating image 432 displays the coating condition of a portion of region 430 within the non-optically effective region 220. Among these, Figure 4 The description of the coating within the non-optically effective region 220 is as follows: a portion 430 within the non-optically effective region 220 may be any region arbitrarily selected within the non-optically effective region 220 when only a specified type of film is coated within the optically effective region 210 in this application, or it may be a reserved measurement window region within the non-optically effective region 220 (i.e., the window marked 231 or 232 above) when both the optically effective region 210 and the non-optically effective region 220 are coated with a specified type of film in this application.

[0096] In step S130, the surface profile information of the first region reflects the surface profile information of the optically effective region in the lens. In some embodiments of this application, the surface profile information of the first region can reflect the surface profile information of the entire range of the optically effective region in the lens. The manufacturing information of the second region can reflect the manufacturing information of the entire lens before the optically effective region is coated with a specified type of film.

[0097] In some embodiments of this application, a lens can be obtained by assembling a single lens, or by assembling two or more lenses in a specific assembly sequence.

[0098] In some embodiments of this application, the manufacturing information includes mold manufacturing information and / or mold usage information for manufacturing lenses. The mold manufacturing information includes at least one of the following: mold cavity surface roughness, machining tolerance, contour error, and flow channel structure parameters, venting structure parameters, and water channel structure parameters connected to the mold cavity. The mold usage information includes at least one of the following: barrel temperature, nozzle temperature, mold temperature, heating gradient, material type, material batch, injection pressure, holding pressure, injection speed, molding time, holding time, cooling time, and annealing time. Performance information includes at least one of the following: resolution, modulation transfer function (MTF), illuminance, aberrations, stray light, ghosting, depth of field, surface defects, maximum principal ray angle, focal length, aperture, field of view, and maximum image height.

[0099] For explanations of terms related to optical lenses and optical lenses in the manufacturing and performance information, please refer to the above content, which will not be repeated here.

[0100] In some embodiments of this application, the surface profile information of the lens may include a lens surface topography map, a height distribution map, etc. Before coating the lens with a specified type of film, the lens is measured to obtain a lens surface topography map, and the height distribution map of the lens is determined based on the lens surface topography map.

[0101] In one embodiment of this application, a surface topography image of the lens is acquired before coating. The lens can be measured using either interferometry or confocal methods. The interferometry method involves interfering the reference laser with the laser reflected by the lens under test to observe the changes in the circular interference fringes in the interference pattern. When measuring an aspherical lens, aspherical wavefront compensation is performed on the reference laser, and the resulting changes in the interference fringes can be directly converted into a height distribution map of the lens. The confocal method involves scanning the lens surface point by point with a focused laser, collecting the reflected light corresponding to each scanning point through a pinhole at the conjugate surface to calculate the physical height of the lens surface and outputting a height distribution map.

[0102] In some embodiments of this application, the surface profile information further includes a difference map obtained by processing a lens surface topography image. The difference map is obtained by: acquiring a standard lens surface topography image used in lens design; determining the difference between the lens surface topography image and the acquired standard lens surface topography image; and determining the difference map based on the determined difference. Specifically, the lens height distribution map can be compared with the curve of the aspherical equation exported from optical design software. The difference between the actual surface profile data and the theoretical surface profile data forms a difference map, and a first model is used to extract features of a first region and features of a second region from the difference map. Because the features of the difference map of the first region more directly reflect the surface profile error, the correlation with performance information will also be more direct, reducing the requirement for training data and improving the accuracy of the first model.

[0103] In some embodiments of this application, the surface shape information can also be processed. For example, Fourier transform processing can be performed on the surface shape information to convert it to the frequency domain, thereby achieving noise reduction and image size compression. Based on the above description, this application can perform Fourier transform processing on lens surface topography maps, height distribution maps, difference maps, etc., to achieve the effect of noise reduction and image size compression.

[0104] In some embodiments of this application, the surface profile information also includes the difference information of the surface profile information (e.g., lens surface topography) before and after changes in environmental information; the performance information also includes the difference information of the performance information before and after changes in environmental information. Specifically, this application can consider the changes in the surface profile information of the lens and the performance information of the lens with time, temperature, or humidity. Because the physical properties of the lens are also changed after coating, the performance information may change even more significantly after 24-48 hours of placement, with the temperature rising from room temperature to 85 degrees or falling to -50 degrees, and the humidity increasing from 50% to 80%, resulting in differences in the manufacturing yield of the lens under different external environments. This application can collect the surface profile information and its changes of the optically effective area, as well as the performance information and its changes of the lens, as training data for machine learning to establish a first model, which is used to predict the range of processing errors of the lens surface profile within its optically effective diameter when the performance information can meet a certain yield requirement.

[0105] Both the first and second models in this application are machine learning models, such as neural network models or other machine learning models. The first model extracts features based on the predicted surface profile information of the first region after coating, and predicts the lens performance information corresponding to the surface profile information of the first region after coating, thereby determining the mapping relationship between the surface profile information of the first region after coating and the lens performance information. When the manufacturing information of the second region corresponds to the manufacturing information of the lens surface profile before coating, the second model extracts features based on both the surface profile information of the first region before coating and the surface profile information of the second region, and predicts the surface profile information of the first region after coating based on the extracted features, thereby determining the mapping relationship between the surface profile information of the first region after coating and the manufacturing information of the second region.

[0106] Therefore, the first and second models can extract features from the surface information. These can be neural network models, such as convolutional neural network models with residual connections, including several convolutional layers for extracting core features, pooling layers for compressing the extracted features, a non-linear activation function, a series of fully connected layers for output dimensionality reduction, and a softmax layer for output. Ultimately, the input surface information is transformed into a series of high-dimensional vector sequences that can be processed by machines. The neural network model can also be a ViT structure model, composed of multiple transformer encoders. The transformer encoder includes parallel multi-head self-attention weighting, multilayer perceptrons, layer normalization, and residual connection mechanisms, thereby transforming image patches into vector sequences. First and second feature vectors are extracted from the surface information of the first and second regions, respectively. A second model is then built using convolutional neural networks, deep networks based on attention mechanisms, random forests, gradient boosting trees (GBDT), etc., to predict the manufacturing error of optically effective regions that are not detected based on the detection results of the detection window.

[0107] This application can select different types of machine learning models as the first model and the second model. When the selected machine learning model is the second model, it can predict the surface shape information of the first region after coating based on the surface shape information of the lens before coating, thereby determining the second mapping relationship between the surface shape information of the first region and the manufacturing information of the second region. When the selected machine learning model is the first model, it can predict the performance information of the lens assembled from the lens based on the surface shape information of the first region after coating predicted by the second model, thereby determining the first mapping relationship between the surface shape information of the first region and the performance information of the lens. The specific details of this application regarding the pre-training of the first model and the second model will be described in detail below.

[0108] In step S150, firstly, based on the first mapping relationship and the second mapping relationship, the manufacturing information of the lens to be assembled with the target lens is predicted according to the performance information of the target lens. Generally, when the performance information of the lens is known first, and then the manufacturing information of the lens is predicted, it is common in the scenario of designing the target lens. When designing the target lens, the performance information of the target lens can be determined, that is, the standard performance information of the target lens when designing the target lens. Then, based on the standard performance information, through the first model and the first mapping relationship, the surface type information of the lens to be coated with a specified type of film required for assembling the target lens is predicted. Through the second model and the second mapping relationship, the manufacturing information of the lens to be assembled with the target lens before coating with the specified type of film (that is, the manufacturing information of the second region) is predicted. Thus, when manufacturing the target lens, at least one lens manufacturing mold can be selected to manufacture the lens according to the predicted manufacturing information of the second region. For example, the lens manufacturing mold used for the lens with the largest overlap range can be selected according to the overlap range between the manufacturing information of the lenses manufactured by each lens manufacturing mold and the predicted manufacturing information of the second region, thereby obtaining the target lens assembled by the lens manufactured by the selected lens manufacturing mold.

[0109] Secondly, based on the first and second mapping relationships, and according to the manufacturing information of the second region of the target lens, the performance information of the lens assembled from the target lens is predicted. Based on preset performance information standards, it is determined whether the predicted performance information meets the preset standards, and the target lens is processed according to the determination result. Generally, predicting the performance information of a lens assembled after coating, based on the manufacturing information of the lens before coating, is common in actual optical lens manufacturing scenarios. Before coating a specified type of film on the manufactured lens, the overall surface shape information of the lens can be obtained. Based on the overall surface shape information and the second model, the surface shape information of the first region of the lens after coating is predicted, thereby enabling the first model to predict the performance information of the lens assembled after coating. Based on the lens performance information predicted by the first model, and according to the preset performance information standards, it is determined whether the lens assembled after coating the lens with the specified type of film meets the requirements, that is, whether the lens meets the standards. If the lens meets the requirements, it can be fed into subsequent processes to produce lenses that meet the requirements, thereby improving the lens manufacturing yield. Otherwise, if the lens is determined not to meet the requirements, it means that the lens assembled from the lens with the specified type of coating is substandard and cannot be allowed to proceed to the next process, so as to avoid producing a lens that does not meet the requirements and thus improve the lens manufacturing yield.

[0110] In one embodiment of this application, an aspherical lens is divided into a first region and a second region; first and second lens surface topography images of the first and second regions are acquired; performance information is acquired for a lens assembled from one or more lenses; first and second feature vectors are extracted using a neural network; the correspondence between the first feature vector and performance information is machine-learned to form a first artificial intelligence detection module; the correspondence between the second feature vector and the first feature vector is machine-learned to form a second artificial intelligence detection module; and the first and second artificial intelligence detection modules are cascaded to predict the second lens surface topography image corresponding to when the performance information meets a preset threshold, wherein the reflectivity of the first region is lower than that of the second region. A detection window region (i.e., the second region) is reserved in the lens, where the reflectivity still allows for high-precision surface shape detection. The overall surface shape defects of the lens are then predicted based on the detection results of the window region, making it possible to exclude coated lenses with defects that do not meet the standards before assembly. This allows for detection even for lenses using ultra-low reflectivity coatings, improving manufacturing yield. Alternatively, a sampling inspection method can be used to acquire lens surface topography images of the second region and input them into the cascaded first and second models to determine whether the lens performance information meets the preset threshold. In actual production, multiple lenses from a production batch can be randomly sampled. Based on the inspection results in the inspection window, a cascaded model can be used to predict whether the distribution range of performance information after assembly of the lenses in this batch meets the predetermined yield requirements relative to the lens quality standards. If the probability of non-compliance exceeds the acceptable range, the production process for this batch needs to be improved, and lenses produced in this batch should be prevented from flowing into other subsequent manufacturing processes before assembly. Alternatively, based on certain yield requirements, a distribution range of performance information can be proposed, and the model can output the lens surface morphology map of the inspection window corresponding to this range.

[0111] The step of machine learning the correspondence between the first and second feature vectors to form the second artificial intelligence detection module further includes associating the first and second feature vectors under the same set of manufacturing information for the aspherical lens. This manufacturing information includes mold cavity surface roughness, machining tolerances, contour errors, and flow channel structure parameters, venting structure parameters, water channel structure parameters, barrel temperature, nozzle temperature, mold temperature, heating gradient, material type, material batch, injection pressure, holding pressure, injection speed, molding time, holding time, cooling time, and annealing time. In some embodiments of this application, associating the manufacturing error distributions of the first and second regions under the same manufacturing conditions can reduce the amount of training data required, making model building easier and the prediction results more consistent with actual on-site manufacturing data.

[0112] Based on the above, this application can also pre-train the first model and the second model. For training the first model, sample lenses can be obtained and assembled into a lens as a sample lens; based on the second mapping relationship and the manufacturing information of the second region of the sample lens, the surface profile information of the first region of the sample lens after coating with a specified type of film is determined; based on the surface profile information of the first region of the sample lens after coating with the specified type of film and the first model to be trained, the performance information to be optimized of the sample lens is predicted; the performance information of the sample lens is obtained as the actual performance information; and the first model to be trained is trained based on the performance information to be optimized and the actual performance information.

[0113] Specifically, lenses coated with a specified type of film can be obtained as sample lenses. After obtaining the sample lenses, coating and assembly steps can be performed to assemble them into a sample lens. The performance information of the assembled lens is collected. After the lens is assembled into a lens, its performance information is measured, including the MTF function reflecting resolution, relative illumination, aberrations (including chromatic aberration, optical distortion, TV distortion, field curvature, etc.), stray light, ghosting (referring to the phenomenon where light rays are reflected and scattered within the lens, causing non-image-forming light to reach the image plane), depth of field, appearance defects (referring to visual defects such as blemishes and cracks), maximum principal ray angle (CRAmax), focal length (EFL), aperture (f / #), field of view (FOV), and maximum image height (ImgH), etc. These indicators can all fail to meet standards due to lens processing defects. The measured performance information is the actual performance information of the sample lens. Using the second mapping relationship and the manufacturing information of the second region of the sample lens, the second model determines the surface profile information of the first region of the sample lens after coating with a specified type of film. Based on this surface profile information and the first model to be trained, the performance information to be optimized for the sample lens is predicted. According to the difference between the actual performance information of the sample lens and the predicted performance information to be optimized, the first model to be trained is trained with minimizing this difference as the training objective. This enables the trained first model to determine the first mapping relationship between the surface profile information of the first region of the lens after coating with the specified type of film and the lens performance information.

[0114] For training the second model, in some embodiments of this application, a sample lens can be obtained; complete surface information of the sample lens before the coating of a specified type of film and manufacturing information of the second region can be obtained, the complete surface information including the surface information of the first region of the sample lens before the coating of the specified type of film and the surface information of the second region of the sample lens; based on the complete surface information and the manufacturing information of the second region, the second model to be trained is trained, so that the trained second model is used to predict the surface information of the first region of the sample lens after the coating of the specified type of film, corresponding to the manufacturing information of the second region.

[0115] During training, the input information for the second model can be the surface profile information of the first region before coating with a specified type of film, the surface profile information of the second region, or the features of the surface profile information of the first region before coating with a specified type of film, and the features of the surface profile information of the second region. The features of the surface profile information of the first region before coating with a specified type of film and the features of the surface profile information of the second region can be extracted by the second model or by another feature extraction model.

[0116] In other embodiments, features of the surface profile information of the first region of the sample lens before the coating of a specified type of film and features of the surface profile information of the second region of the sample lens can be extracted respectively; the manufacturing information of the second region, the features of the surface profile information of the first region of the sample lens before the coating of a specified type of film and the features of the surface profile information of the second region of the sample lens are associated to obtain associated features; and the second model to be trained is trained based on the associated features.

[0117] Specifically, the features of the surface profile information of the first region before the coating of a specified type of film and the features of the surface profile information of the second region can be associated through a second model or a feature extraction model. Since the manufacturing information of the second region in this application forms a correspondence with the surface profile information of the first region before the coating of a specified type of film and the surface profile information of the second region, in some embodiments of this application, the manufacturing information of the second region can also be input into the second model, thereby obtaining a mapping relationship between the manufacturing information of the second region and the surface profile information of the first region after the coating of a specified type of film based on the second model.

[0118] In some embodiments of this application, the manufacturing information of the second region can be the manufacturing information of the entire lens, including both optically effective and non-optically effective regions, before the coating of a specified type of film.

[0119] In some embodiments of this application, the complete surface profile information of the sample lens before the coating of a specified type of film includes the surface profile information of a first region and the surface profile information of a second region of the sample lens before the coating of a specified type of film. Therefore, the complete surface profile information of the sample lens can correspond to the manufacturing information of the second region. That is, when using the manufacturing information of the second region, the sample lens can be produced and the complete surface profile information of the sample lens can be obtained.

[0120] However, after the optically effective area is coated with a specified film, the surface profile information of the optically effective area changes to the point that it is difficult for the detection device to detect the surface profile information. Therefore, this application uses the complete surface profile information of the lens manufactured based on the manufacturing information of the second area (i.e., including the surface profile information of the first area before the specified type of film is coated and the surface profile information of the second area) to extract features using a second model, predict the surface profile information of the first area after the specified type of film is coated, and thus obtain the mapping relationship between the manufacturing information of the second area and the surface profile information of the first area after the specified type of film is coated.

[0121] Furthermore, when training the second model, since the detection window is not located within the optically effective area, its manufacturing error is difficult to correspond one-to-one with the manufacturing error of the optically effective area. To enhance prediction accuracy, the feature vectors of two regions under the same set of manufacturing information can be correlated, so that a highly accurate second model can be established without using too much detection data for training.

[0122] In some embodiments, manufacturing information includes cavity surface roughness, machining tolerance, contour error, and flow channel structure parameters, venting structure parameters, water channel structure parameters, barrel temperature, nozzle temperature, mold temperature, heating gradient, material type, material batch, injection pressure, holding pressure, injection speed, molding time, holding time, cooling time, and annealing time.

[0123] When extracting features from the surface profile information of the first and second regions, the extraction can be performed by a second model or by a separate feature extraction model. Specifically, the surface profile information of the first region of the sample lens is input into the feature extraction model to obtain the features of the first region of the sample lens output by the feature extraction model; similarly, the surface profile information of the second region of the sample lens is input into the feature extraction model to obtain the features of the second region of the sample lens output by the feature extraction model. The feature extraction model can extract the feature vector of the lens's surface profile information, thereby obtaining the feature image of the lens. The feature extraction model in this application can be a different type of machine learning model, such as a neural network model, as long as it can extract the surface profile information of the lens to obtain a feature image.

[0124] In some embodiments of this application, a first model and a second model can be cascaded, thereby training the cascaded first and second models simultaneously. Specifically, based on the manufacturing information of the second region of the sample lens, and according to the surface profile information of the first region of the sample lens before the coating of the specified type of film and the surface profile information of the second region, the second model can predict the surface profile information of the first region of the sample lens after the coating of the specified type of film. Then, based on the surface profile information of the first region after the coating of the specified type of film, the first model can predict the performance information of the sample lens (i.e., the performance information to be optimized mentioned above). Based on the actual performance information of the sample lens and the performance information to be optimized, the cascaded first and second models can be trained in a supervised manner.

[0125] Since the cascaded first and second models together form an end-to-end prediction system for "from non-optically effective area surface information (in some embodiments of this application, this may also be manufacturing information corresponding to the surface information of the lens before coating) to lens performance information," when the second model is trained unsupervised, even if its predicted surface information of the first region after coating may be biased, this result is only used as an intermediate variable (i.e., the prediction result will be used for the prediction of the first model), and it is insufficient to affect the first model's prediction judgment of lens performance information. Therefore, the bias is acceptable, and there is no need to independently verify the prediction accuracy of the second model. In other words, the final training and optimization goal of the cascaded first and second models in this application is to achieve an accurate correspondence between the final output lens performance information prediction result and the lens manufacturing information, rather than pursuing absolute perfection in intermediate surface reconstruction.

[0126] Based on the above, in some embodiments of this application, the first model and the second model can be coupled to determine the performance information of the lens assembled from the lens based on the manufacturing information of the second region of the lens coated with a specified type of film. This allows for the prediction of the performance information of the lens assembled into a lens before the lens with the specified type of film is assembled, determining whether the lens meets the standards. If it does not meet the standards, the lens with the specified type of film can be prevented from entering subsequent processes, thereby improving the lens manufacturing yield. Alternatively, based on the lens performance information, the manufacturing information of the second region of the lens to be assembled into a lens can be predicted, and the lens can be manufactured based on the predicted manufacturing information of the second region of the lens, so that the performance information of the manufactured lens after assembly meets the requirements, thereby improving the lens manufacturing yield.

[0127] Specifically, since there is no direct physical correlation between the shape of the detection window and the performance of the final overall lens, the accuracy of the model based solely on the former is insufficient when training data is limited. Therefore, the model is divided into two levels, coupled between the two layers through serial cascading and feature cascading. The first layer is a model that establishes a more direct causal relationship between the manufacturing error of the effective diameter region and performance information. The second layer further derives the manufacturing error of the effective diameter region based on the manufacturing error of the non-effective diameter portion. These two layers employ different methods to reduce the demand for training data. The first layer utilizes the difference from the theoretical aspherical surface shape, while the second layer, even without aspherical surface shape data, can correlate the first and second feature vectors under the same set of manufacturing information based on historically accumulated detection data, thereby providing the statistical distribution probability of the first feature vector under a certain second feature vector.

[0128] Based on the method for predicting coated lens information shown in the above embodiments, this application also provides a schematic diagram of the structure of a device for predicting coated lens information, as shown below. Figure 5 As shown.

[0129] Figure 5 This is a schematic diagram of a device for predicting coated lens information according to an embodiment of this application. The lens includes an optically effective region and a non-optically effective region. A film of a specified type is coated within the optically effective region. The device includes: a definition module 500, used to define the optically effective region as a first region and at least a portion of the non-optically effective region as a second region; a determination module 502, used to determine a first mapping relationship between the surface information of the first region and the performance information of the lens assembled from the lens, based on a pre-trained first model, and to determine a second mapping relationship between the surface information of the first region and the manufacturing information of the second region, based on a pre-trained second model; and a prediction module 504, used to predict the manufacturing information of the lens assembled from the target lens based on the first mapping relationship and the second mapping relationship, according to the performance information of the target lens, or to predict the performance information of the lens assembled from the target lens based on the manufacturing information of the second region of the target lens.

[0130] Optionally, the device further includes: a first training module 506; the first training module 506 is specifically configured to: acquire a sample lens; assemble the sample lens into a lens as a sample lens; determine the surface profile information of the first region of the sample lens after coating with a specified type of film according to the second mapping relationship and the manufacturing information of the second region of the sample lens; predict the performance information to be optimized of the sample lens based on the surface profile information of the first region of the sample lens after coating with a specified type of film and the first model to be trained; acquire the performance information of the sample lens as actual performance information; and train the first model to be trained according to the performance information to be optimized and the actual performance information.

[0131] Optionally, the device further includes: a second training module 508; the second training module 508 is specifically used to: acquire a sample lens; acquire complete surface information of the sample lens before it is coated with a specified type of film and manufacturing information of the second region, the complete surface information including the surface information of the first region of the sample lens before it is coated with the specified type of film and the surface information of the second region of the sample lens; and train a second model to be trained based on the complete surface information and the manufacturing information of the second region, so that the trained second model is used to predict the surface information of the first region of the sample lens after it is coated with the specified type of film, corresponding to the manufacturing information of the second region.

[0132] Optionally, the second training module 508 is specifically used to: extract the features of the surface profile information of the first region of the sample lens before the coating of the specified type of film and the features of the surface profile information of the second region of the sample lens; associate the manufacturing information of the second region, the features of the surface profile information of the first region of the sample lens before the coating of the specified type of film, and the features of the surface profile information of the second region of the sample lens to obtain associated features; and train the second model to be trained based on the associated features.

[0133] Optionally, the surface profile information includes at least one of the following: (1) a lens surface topography map; (2) a height distribution map obtained by processing the lens surface topography map; (3) information obtained by performing Fourier transform processing on the lens surface topography map; and (4) a difference map obtained by processing the lens surface topography map.

[0134] Optionally, the device further includes: a difference module 510: the difference module 510 is specifically used to: acquire a standard lens surface topography image when designing the lens; determine the difference between the lens surface topography image and the acquired standard lens surface topography image; and determine the difference image based on the determined difference.

[0135] Optionally, surface type information includes differences before and after changes in environmental information; performance information includes differences before and after changes in environmental information.

[0136] Optionally, the device further includes a judgment module 512; the judgment module 512 is specifically used to judge whether the predicted performance information meets the preset standard according to the preset performance information standard, and to process the target lens according to the judgment result.

[0137] Optionally, the second region is the region with the lowest reflectivity in the non-optically effective region.

[0138] Optionally, the manufacturing information includes mold manufacturing information and / or mold usage information for manufacturing lenses. The mold manufacturing information includes at least one of the following: mold cavity surface roughness, machining tolerance, contour error, and flow channel structure parameters, venting structure parameters, and water channel structure parameters connected to the mold cavity. The mold usage information includes at least one of the following: barrel temperature, nozzle temperature, mold temperature, heating gradient, material type, material batch, injection pressure, holding pressure, injection speed, molding time, holding time, cooling time, and annealing time. The performance information includes at least one of the following: resolution, modulation transfer function (MTF), illuminance, aberrations, stray light, ghosting, depth of field, surface defects, maximum principal ray angle, focal length, aperture, field of view, and maximum image height.

[0139] This application also provides a computer-readable storage medium storing a computer program that can be used to execute the method for predicting coated lens information provided in the above embodiments.

[0140] This application also provides a computer program product, which includes a computer program or computer-executable instructions, and is stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the method for predicting coated lens information provided in this application.

[0141] Based on the method for predicting coated lens information shown in the above embodiments, this application also proposes... Figure 6 The diagram shows a schematic structure of the electronic device 600. Figure 6 At the hardware level, the electronic device 600 includes a processor 610 and a memory 620, and may also include an internal bus, network interface, memory, and other hardware required for the business. The processor 610 reads the corresponding computer program from the memory 620 into memory and then runs it to implement the method for predicting coated lens information as described in the above embodiments.

[0142] Of course, in addition to software implementation, this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0143] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0144] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0145] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0146] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0147] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0149] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0150] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0151] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0153] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0154] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0155] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0156] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0157] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0158] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims in this specification.

Claims

1. A method for predicting information of coated lenses, characterized in that, The lens includes an optically effective region and a non-optically effective region, and a film of a specified type is deposited within the optically effective region. The method includes: The optically effective region is designated as the first region, and at least a portion of the non-optically effective region is designated as the second region. Based on a pre-trained first model, a first mapping relationship is determined between the surface shape information of the first region and the performance information of the lens assembled from the lens; and based on a pre-trained second model, a second mapping relationship is determined between the surface shape information of the first region and the manufacturing information of the second region. Based on the first mapping relationship and the second mapping relationship, the manufacturing information of the lens assembled with the target lens is predicted according to the performance information of the target lens, or the performance information of the lens assembled from the target lens is predicted according to the manufacturing information of the second region of the target lens.

2. The method as described in claim 1, characterized in that, The first model was obtained in advance through the following training: Obtain sample lenses and assemble them into a lens as a sample lens; Based on the second mapping relationship and the manufacturing information of the second region of the sample lens, the surface profile information of the first region of the sample lens after coating with a specified type of film is determined; Based on the surface shape information of the first region of the sample lens after coating with a specified type of film and the first model to be trained, predict the performance information of the sample lens to be optimized. The performance information of the sample lens is obtained as the actual performance information; The first model to be trained is trained based on the performance information to be optimized and the actual performance information.

3. The method as described in claim 1, characterized in that, The second model was obtained in advance through the following training: Obtain sample lenses; Obtain complete surface profile information of the sample lens before it is coated with a specified type of film and manufacturing information of the second region. The complete surface profile information includes the surface profile information of the first region of the sample lens before it is coated with a specified type of film and the surface profile information of the second region of the sample lens. Based on the complete surface information and the manufacturing information of the second region, the second model to be trained is trained so that the trained second model can be used to predict the surface information of the first region of the sample lens after the specified type of film is coated, corresponding to the manufacturing information of the second region.

4. The method as described in claim 3, characterized in that, Based on the complete surface information and the manufacturing information of the second region, the second model to be trained is trained, specifically including: The features of the surface profile information of the first region of the sample lens before the coating of the specified type of film and the features of the surface profile information of the second region of the sample lens are extracted respectively. The manufacturing information of the second region, the surface features of the first region of the sample lens before the coating of the specified type of film, and the surface features of the second region of the sample lens are correlated to obtain the associated features. Based on the aforementioned association features, the second model to be trained is trained.

5. The method as described in claim 4, characterized in that, The features of the surface profile information of the first region of the sample lens before the coating of the specified type of film and the features of the surface profile information of the second region of the sample lens are extracted respectively, specifically including: The surface profile information of the first region of the sample lens before the coating of a specified type is input into a feature extraction model to obtain the features of the first region of the sample lens before the coating of the specified type is output by the feature extraction model; and... The surface shape information of the second region of the sample lens is input into the feature extraction model to obtain the features of the second region of the sample lens output by the feature extraction model.

6. The method as described in claim 1, characterized in that, Face type information includes at least one of the following: (1) Lens surface morphology diagram; (2) A height distribution map obtained by processing the surface topography of the lens; (3) Information obtained by performing Fourier transform on the surface topography of the lens; (4) The difference map obtained based on the processing of the surface topography map of the lens.

7. The method as described in claim 6, characterized in that, The difference map is obtained in the following way: Obtain a standard lens surface topography image when designing the lens; Determine the differences between the surface topography of the lens and the obtained standard lens surface topography; The difference map is determined based on the identified differences.

8. The method as described in claim 1, characterized in that, Face shape information includes the differences in face shape information before and after changes in environmental information; Performance information includes the differences in performance information before and after changes in environmental information.

9. The method as described in claim 1, characterized in that, The method further includes: Based on the preset performance information standard, it is determined whether the predicted performance information meets the preset standard, and the target lens is processed according to the determination result.

10. The method as described in claim 1, characterized in that, The second region is the region with the lowest reflectivity in the non-optically effective region.

11. The method as described in claim 1, characterized in that, The manufacturing information includes mold manufacturing information and / or mold usage information when manufacturing lenses. The mold manufacturing information includes at least one of the following: mold cavity surface roughness, machining tolerance, contour error, and flow channel structure parameters, venting structure parameters, and water channel structure parameters connected to the mold cavity. The mold usage information includes at least one of the following: barrel temperature, nozzle temperature, mold temperature, heating gradient, material type, material batch, injection pressure, holding pressure, injection speed, molding time, holding pressure time, cooling time, and annealing time. The performance information includes at least one of the following: resolution, modulation transfer function (MTF), illuminance, aberration, stray light, ghosting, depth of field, appearance defects, maximum principal ray angle, focal length, aperture, field of view, and maximum image height.

12. A device for predicting information about coated lenses, characterized in that, The lens includes an optically effective area and a non-optically effective area, and a film of a specified type is deposited within the optically effective area. The device includes: A definition module is used to define the optically effective region as a first region and at least a portion of the non-optically effective region as a second region. The determining module is used to determine a first mapping relationship between the surface shape information of the first region and the performance information of the lens assembled from the lens, based on a pre-trained first model, and to determine a second mapping relationship between the surface shape information of the first region and the manufacturing information of the second region, based on a pre-trained second model. The prediction module is used to predict the manufacturing information of the lens assembled with the target lens based on the first mapping relationship and the second mapping relationship, according to the performance information of the target lens, or to predict the performance information of the lens assembled from the target lens based on the manufacturing information of the second region of the target lens.

13. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1-11.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1-11.

Images