Progressive lens design method and obtained progressive lens

Abstract

The invention relates to the technical field of progressive lenses, in particular to a progressive lens design method and an obtained progressive lens. The progressive lens design method comprises the steps that a visual demand coefficient is defined, and the change speed of a principal curvature and the change speed of an average curvature are dynamically adjusted; dynamically adjusting the width of the transition area according to the hyperopia and myopia requirements of the user; performing region division on the transition region in the width direction, and establishing a new weight distribution function for each region; establishing a satisfaction model for prediction; for lens processing equipment, initial tau average curvature 0, tau main curvature 0, Wbase, Wbase (x) and each demand coefficient reference value are provided, and a curvature control module, an area division module and multi-interval power distribution are adjusted according to calculation. According to the method, a feedback and production guidance mechanism is established, the defects of an existing progressive lens design method can be effectively overcome, the problem that a fixed design cannot meet personalized requirements is solved, it is ensured that the diopter continuously changes in far, middle and near visual fields, and more comfortable visual experience is provided for a user.

Description

Technical Field

[0001] The present invention relates to the technical field of progressive lenses, and in particular to a design method of a progressive lens and the obtained progressive lens. Background Art

[0002] Progressive lenses are lenses that can continuously change the diopter in the far, medium and near fields of vision. They are usually divided into four areas, including the far vision area, the near vision area, the transition area and the peripheral area. The transition area connects the far vision area and the near vision area to achieve a smooth diopter transition position. Through smooth diopter changes, users will not feel sudden visual jumps when looking far and near.

[0003] In order to design high-performance progressive lenses, in existing design methods, mathematical models are usually used to minimize the optical error of the lens. The mathematical model takes into account the principal curvature difference and the mean curvature of the lens surface, and uses different weight distribution functions to affect the calculation results of the model. In the current public technology, spline interpolation is often used to design multiple sets of weight distribution functions. These weight functions correspond to different speeds of change in the transition area and are used to connect different areas on the lens: high-weight areas and low-weight areas. This design method aims to study the impact of changing the width of the weight transition on the refractive power and astigmatism distribution of the lens.

[0004] In the above design method, the weight distribution function is pre-set and unchanged in different areas of the lens. The weight distribution function is used to control the optical performance of each area of ​​the lens and adjust the optical design of these areas, such as by adjusting the change of the principal curvature difference and the mean curvature to meet the optical needs of different areas; in the far vision area and near vision area, the weight is often larger to ensure clear visual effects, while in the peripheral area, the weight is smaller to reduce peripheral astigmatism. These weight distribution functions are usually set in advance and will not be adjusted according to the needs of individual users or other external factors.

[0005] In order to achieve a smooth transition, the existing progressive lens design method has used the spline interpolation method to generate a weight distribution function, thereby ensuring a smooth and controllable change in optical performance between different areas. However, since a fixed weight distribution function is used, especially in the design of the transition area, the width and weight change speed are fixed, and therefore it cannot fully meet the personalized needs of each wearer. Summary of the invention

[0006] The present invention provides a design method for a progressive lens and the obtained progressive lens, which can effectively solve the problems in the background technology.

[0007] In order to achieve the above object, the technical solution adopted by the present invention is:

[0008] A method for designing a progressive lens, comprising:

[0009] S1: Obtain visual demand data of different users and define the visual demand coefficient D u，

[0010] D u =f(D far ,D near ,D astig ,D activity );

[0011] Among them, D far is the hyperopia demand coefficient, D near is the myopia demand coefficient, D astig is the astigmatism demand coefficient, P activity is the coefficient of living habit demand;

[0012] S2: According to the visual demand coefficient D u , dynamically adjust the change speed of the principal curvature and the mean curvature, the formula is as follows:

[0013] τ 平均曲率 =τ 平均曲率0 ·(1+m1·(D u -D ref ));

[0014] τ 主曲率 =τ 主曲率0 ·(1+m2·(D u -D ref ));

[0015] Among them, τ 平均曲率0 and τ 主曲率0 are the standard curvature change rates of the mean curvature and the principal curvature, m1 and m2 are the first adjustment coefficient and the second adjustment coefficient, respectively. ref is the reference value of the visual demand coefficient;

[0016] S3: Dynamically adjust the width W of the transition area according to the user's hyperopia and myopia needs (x,y) , the formula is:

[0017] W (x,y) =W base ·(1+k1·(D far -D ref,far )+k2·(D near -D ref,near ));

[0018] Among them, W base is the standard width of the transition region, k1 and k2 are the first control coefficient and the second control coefficient, respectively, D ref,far and Dref,near are the reference values ​​of demand coefficients for hyperopia and myopia respectively;

[0019] S4: Divide the transition area into regions in the width direction, and establish a new weight distribution function W for each region. adjusted(x) , the formula is:

[0020] W adjusted(X) =W base(X) ·(1+a·exp(b·(D u -D ref ))+c·ln(1+d·|D u -D ref |));

[0021] Among them, W base(x) is the basic weight distribution function of the corresponding area, representing the initial state in the design of progressive lenses; a, b, c, d are the first control parameter, the second control parameter, the third control parameter and the fourth control parameter, respectively, which are used to adjust the influence of the exponential and logarithmic parts, and are targeted according to the corresponding area;

[0022] S5: Establish a satisfaction model, predict m1, m2, k1, k2 and a, b, c, d of the corresponding areas according to user feedback data, and calculate τ according to the prediction results 平均曲率 , τ 主曲率 , W (x,y) And the W of each region adjusted(x) ;

[0023] S6: Provide initial τ for lens processing equipment 平均曲率0 , τ 主曲率0 , W base , W base(x) and the reference values ​​of each demand coefficient, according to the calculated m1, m2, τ 平均曲率 and τ 主曲率 Adjust the curvature control module according to the calculated k1, k2 and W (x,y) Adjust the area division module, and use a, b, c, d and W of each corresponding area adjusted(x) Adjust multi-interval power distribution.

[0024] Furthermore, the D u is the weighting function, and the calculation formula is:

[0025] D u =Q far ·D far +W near ·D near +W astig ·D astig +W activity ·Dactivity

[0026] Among them, W far , W near , W astig , W activity They are the weight coefficients for each demand, which are adjusted dynamically according to the user's specific situation and living habits.

[0027] Furthermore, the training data of the satisfaction model includes user feedback data, design parameter data and demand data;

[0028] The user feedback data is a feature combination obtained by calculating the subjective feedback data and the objective data through the feature interaction technology; the design parameter data is a feature combination of the existing design parameters after feature combination and feature transformation; the demand data is a feature combination obtained by calculating different demand features through the feature interaction technology.

[0029] Furthermore, establishing a satisfaction model includes:

[0030] A1: Determine the model target to meet the user's visual satisfaction;

[0031] A2: Obtain training data, and divide the training data into a training set, a validation set, and a test set;

[0032] A3: constructing a model structure for outputting predicted design parameter data by inputting the user feedback data and demand data;

[0033] A4: Model training and optimization: use machine learning algorithms to train the model, use validation set data to validate the model, and use test set data for final testing.

[0034] Furthermore, the machine learning algorithm is one of linear regression, decision tree, random forest, and neural network.

[0035] Furthermore, a nonlinear fusion function F is established combined , the input is the combination of three features of user feedback data, design parameter data and demand data, and the output is the fused comprehensive feature vector. The formula is as follows;

[0036] F combined =ReLU(W2·ReLU(W1[F feedbace ,F design ,F demand ]+b1)+b2)

[0037] Among them, F feedback is the feature combination of user feedback data, F design is the characteristic combination of design parameter data, F demandis the feature combination of the required data, W1, W2 are the weight matrices of the neural network, b1, b2 are bias terms, and ReLU is the nonlinear activation function.

[0038] Furthermore, the satisfaction model includes:

[0039] An input layer, receiving the comprehensive feature vector as input;

[0040] A feature extraction layer extracts high-level features from the comprehensive feature vector;

[0041] Output layer, which generates the final model prediction output.

[0042] Furthermore, the same feature interaction technology is used for the user feedback data and the demand data.

[0043] Furthermore, the feature interaction technology is a feature interaction technology based on random forest.

[0044] A progressive lens is obtained by adopting the design method of the progressive lens as described above.

[0045] The technical solution of the present invention can achieve the following technical effects:

[0046] The present invention can effectively solve the shortcomings of existing progressive lens design methods by acquiring personalized visual demand data, dynamically adjusting curvature and weight distribution, and establishing a feedback and production guidance mechanism, overcome the problem that fixed design cannot meet personalized needs, and allow the optical performance of the lens to be dynamically adjusted according to the needs of each user, ensuring that the refractive power changes continuously in the far, medium and near fields of vision, providing users with a more comfortable visual experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 A flowchart of a design method for progressive lenses;

[0049] Figure 2 Schematic diagram of the composition of satisfaction model training data;

[0050] Figure 3 Flowchart for establishing satisfaction model;

[0051] Figure 4 This is the framework diagram of the satisfaction model. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0054] Embodiment 1

[0055] like Figure 1 As shown, a method for designing a progressive lens comprises:

[0056] S1: Obtain visual demand data of different users and define the visual demand coefficient D u ,

[0057] D u =f(D far ,D near ,D astig ,D activity );

[0058] Among them, D far is the hyperopia demand coefficient, D near is the myopia demand coefficient, D astig is the astigmatism demand coefficient, P activity The coefficient of living habit demand; this step ensures that the starting point of the design plan is based on targeted differentiated data, reflecting the specific visual needs and lifestyle of each user, so that the subsequent design can be precisely adjusted to each wearer;

[0059] S2: According to the visual demand coefficient D u , dynamically adjust the change speed of the principal curvature and the mean curvature, the formula is as follows:

[0060] τ 平均曲率 =τ 平均曲率0 ·(1+m1·(D u -D ref ));

[0061] τ 主曲率 =τ 主曲率0 ·(1+m2·(D u -D ref ));

[0062] Among them, τ 平均曲率0 and τ 主曲率0 are the standard curvature change rates of the mean curvature and the principal curvature, m1 and m2 are the first adjustment coefficient and the second adjustment coefficient, respectively. ref is the reference value of the visual demand coefficient; in the implementation process, m1 and m2 are used to adjust the amplitude and direction of the curvature change. This dynamic adjustment overcomes the defects of the fixed curvature design and allows the curvature change of the lens surface to be flexibly adjusted according to individual needs to ensure a smooth transition of vision. This solves the different needs of different wearers for far, medium and near vision when the diopter changes, so that the optical performance of each area is optimized;

[0063] S3: Dynamically adjust the width W of the transition area according to the user's hyperopia and myopia needs (x,y) , the formula is:

[0064] W (x,y) =W base ·(1+k1·(D far -D ref,far )+k2·(D near -D ref,near ));

[0065] Among them, W base is the standard width of the transition area, k1 and k2 are the first control coefficient and the second control coefficient respectively, D ref,far and D ref,near They are the reference values ​​of the demand coefficients for hyperopia and myopia respectively; the dynamic adjustment of the transition area solves the problem of fixed width in the existing design. By adjusting the width of the transition area according to the differences in different needs, it ensures that the diopter changes in the transition area are smoother, reduces the visual jump, and improves visual comfort;

[0066] S4: Divide the transition area in the width direction and establish a new weight distribution function W for each area adjusted(x) , the formula is:

[0067] W adjusted(X) =W base(X) ·(1+a·exp(b·(D u -D ref ))+c·ln(1+d·|D u -D ref |));

[0068] Among them, W base(x)is the basic weight distribution function of the corresponding area, representing the initial state in the design of progressive lenses; a, b, c, d are the first control parameter, the second control parameter, the third control parameter and the fourth control parameter, respectively, which are used to adjust the influence of the index and the logarithmic part, and take targeted values ​​according to the corresponding area; the new weight distribution function can dynamically adjust the distribution of diopter and astigmatism according to the different needs of each area, so as to make the optical performance of the lens more personalized and optimized;

[0069] S5: Establish a satisfaction model, predict m1, m2, k1, k2 and a, b, c, d of the corresponding areas according to user feedback data, and calculate τ according to the prediction results 平均曲率 , τ 主曲率 , W (x,y) And the W of each region adjusted(x) ; This mechanism allows the design process to be adaptive and continuously improved, ensuring that the design can be continuously optimized to meet the user's personalized needs and actual wearing effects, solving the problem in existing technologies that cannot be dynamically adjusted based on external factors or individual feedback;

[0070] S6: Provide initial τ for lens processing equipment 平均曲率0 , τ 主曲率0 , W base , W base(x) and the reference values ​​of each demand coefficient, according to the calculated m1, m2, τ 平均曲率 and τ 主曲率 Adjust the curvature control module according to the calculated k1, k2 and W (x,y) Adjust the area division module, and use a, b, c, d and W of each corresponding area adjusted(x) Adjust the multi-interval power distribution. Directly apply the optimized parameters to the actual production process to ensure that the manufactured lenses meet the personalized optical design requirements.

[0071] Visual demand coefficient D u The parameters of different visual needs of users are comprehensively considered, including hyperopia, myopia, astigmatism and living habits. These needs will directly affect the optical performance requirements of the lens. far and D near Determines the refractive adjustment of the lens in hyperopia and myopia, which needs to be adapted by changes in the main curvature and the mean curvature; D astig Determines the consistency of the lens's refractive power in different directions, and needs to minimize astigmatism by adjusting the principal curvature and the mean curvature; D activityIt reflects the user's usage pattern in daily life, such as close work or long-term long-distance viewing, which needs to be considered in the curvature design. Combining all needs helps to comprehensively optimize the optical performance of the lens and ensure the user's visual clarity and comfort in various usage scenarios. Step S1 is the starting point of the entire design process and provides a basis for the dynamic adjustment and optimization of parameters in subsequent steps; Step S2 provides basic curvature data for the width adjustment of the transition area to ensure the rationality of the area division and the smoothness of the diopter transition. The subsequent area division provides a clear area boundary for the establishment of the weight distribution function to ensure that the design of the weight distribution function meets user needs.

[0072] The present invention can effectively solve the shortcomings of existing progressive lens design methods by acquiring personalized visual demand data, dynamically adjusting curvature and weight distribution, and establishing a feedback and production guidance mechanism, overcome the problem that fixed design cannot meet personalized needs, and allow the optical performance of the lens to be dynamically adjusted according to the needs of each user, ensuring that the refractive power changes continuously in the far, medium and near fields of vision, providing users with a more comfortable visual experience.

[0073] As a preferred embodiment of the above, D u is the weighting function, and the calculation formula is:

[0074] D u =W far ·D far +W near ·D near +W astig ·D astig +W activity ·D activity ;

[0075] Among them, W far , W near , W astig , W activity are the weight coefficients of each demand, which are adjusted dynamically according to the user’s specific situation and living habits. far In situations where long-distance visual clarity is more important to the user, such as driving, watching sports games or meetings, this coefficient will be given a higher weight; W near In situations where close-range visual clarity is more important to the user, such as reading, using electronic devices, and working, this coefficient will be given a higher weight; W astig For users who need special astigmatism correction, this factor will be given a higher weight; W activity Dynamic adjustments are made based on monitoring data of the user's lifestyle habits, including user wearing effects and activity pattern data. For example, if the user reports experiencing more glare or visual fatigue when driving at night, the weight factor can be adjusted to enhance the performance of the lens in that specific activity.

[0076] In the above preferred embodiment, after assigning weights, the calculated D u It is more in line with the users' actual needs and lifestyles, comprehensively considers the importance and priority of various visual needs in users' lives, improves the visual experience and comfort, enhances the efficiency and explanatory power of design optimization, and ensures the consistency and stability of the design.

[0077] As a preferred embodiment of the above, Figure 2 As shown, the training data of the satisfaction model includes user feedback data, design parameter data and demand data; the user feedback data is the feature combination obtained by calculating the subjective feedback data and objective data through the feature interaction technology; the design parameter data is the feature combination of the existing design parameters after feature combination and feature transformation; the demand data is the feature combination calculated by the feature interaction technology for different demand features.

[0078] Among them, the subjective feedback in the user feedback data refers to the user's feelings and satisfaction with the visual effects after wearing the lenses, such as comfort and fatigue when looking far or near, and using for a long time; the objective data refers to the precise values ​​of visual clarity, astigmatism change, refractive accuracy, etc. obtained by equipment measurement; the feature interaction technology for the two generates new combined features by analyzing the relationship between multiple features to more accurately reflect the user's overall visual experience. For example, subjective feedback data may have a strong correlation with specific objective data (such as refractive error). Through feature interaction, new feature combinations can be constructed to optimize the predictive ability of the model.

[0079] Design parameter data refers to various parameters involved in the current lens design, such as the curvature of the lens surface, the weight distribution function, the width of the transition zone and other related parameters. These parameters generate new features after feature combination and feature transformation, so that the model can better understand the relationship between design parameters and user feedback; by combining features of different design parameters, the model can identify which combination of parameters has the greatest impact on the visual effect. Feature transformation technology can convert design parameters into different representations, such as improving the expression ability of the model through nonlinear transformation and capturing more complex relationships.

[0080] Demand data refers to the personalized needs of different users (such as hyperopia needs, myopia needs, astigmatism correction, living habits, etc.). These data generate new feature combinations through feature interaction technology to optimize the adaptability of the design; demand data can come from user lifestyle surveys, activity pattern monitoring, etc.; demand data interacts with other features (such as design parameters and feedback data) through feature interaction technology to generate new combined features. For example, a user may have a higher demand for long-distance clarity and a strong demand for myopia correction. The interaction technology can be used to discover the mutual influence between these needs and form a more accurate combination of demand features.

[0081] As a preferred embodiment of the above, Figure 3 As shown, establishing a satisfaction model includes:

[0082] A1: Determine the model target to meet the user's visual satisfaction;

[0083] A2: Obtain training data and divide the training data into training set, validation set and test set;

[0084] A3: Construct a model structure to output predicted design parameter data by inputting user feedback data and demand data;

[0085] A4: Model training and optimization: use machine learning algorithms to train the model, use validation set data to validate the model, and use test set data for final testing.

[0086] Determining the model goal is the basis of the entire model design. It clarifies the direction of modeling. By setting visual satisfaction as the optimization goal, the model will automatically adjust the design parameters (such as transition area width, curvature change speed, etc.) to improve the user's wearing experience. In this preferred solution, the core structure of the satisfaction model is a machine learning model. The input is the user's feedback data and demand data, and the output is the predicted design parameter data. This model needs to learn the relationship between a large number of features (such as hyperopia, myopia, astigmatism, etc.) and user satisfaction feedback.

[0087] Among them, the machine learning algorithm is one of linear regression, decision tree, random forest, and neural network; specifically, the complexity of the model depends on the complexity of the data and the feature interaction relationship that needs to be captured. For example, simpler relationships can use linear regression, while complex, nonlinear relationships can be modeled through deep neural networks.

[0088] As a preferred embodiment of the above, a nonlinear fusion function F is established. combined , the input is the combination of three features of user feedback data, design parameter data and demand data, and the output is the fused comprehensive feature vector. The formula is as follows;

[0089] F combined =ReLU(W2·ReLU(W1[F feedbace ,F design ,F demand ]+b1)+b2);

[0090] Among them, F feedback is the feature combination of user feedback data, F design is the characteristic combination of design parameter data, F demand is the feature combination of the required data, W1, W2 are the weight matrices of the neural network, b1, b2 are bias terms, and ReLU is the nonlinear activation function.

[0091] During the implementation process, the nonlinear fusion function of the multi-layer perceptron structure is used to capture the complex nonlinear relationship between input features. Specifically, through the combination of multiple fully connected layers using weight matrices W1, W2, and nonlinear activation function ReLU, the model can learn the deep interactive relationship between user feedback data, design parameter data and demand data. In actual scenarios, the relationship between user visual feedback, lens design parameters and demand characteristics is usually not linear. Through this formula, the model can explore the complex patterns hidden in different feature combinations, thereby improving prediction ability and accuracy; each fully connected layer composed of weight matrices W1, W2 and bias terms b1, b2 in the formula can linearly transform input features and introduce nonlinearity through the ReLU activation function, so that the fused output features have stronger expression capabilities,

[0092] During the implementation process, by splicing all the input features together and fusing them through two layers of fully connected layers and nonlinear activation functions, all features can be efficiently processed and fused within a unified framework. This processing method reduces the feature engineering work that needs to be manually designed, and leaves the data fusion process to the model for automatic learning, which can achieve effective feature fusion in less training time; the weight matrices W1, W2 and the bias items b1, b2 are trainable parameters, which will be continuously updated during the model training process, so that the model automatically learns the relative importance of the input features.

[0093] By performing feature fusion before inputting the satisfaction model, the model structure can be simplified, the computational efficiency and feature learning ability can be improved, the generalization and adaptability of the model can be enhanced, the dependence on feature engineering can be reduced, and the stability of training can be improved. This fusion strategy can better integrate feature information from different data sources, improve the prediction effect and optimization performance of the model. Specifically, as a specific structural form of the satisfaction model that can accept the fused feature vector, such as Figure 4As shown, the satisfaction model includes: an input layer, which receives a comprehensive feature vector as input; a feature extraction layer, which extracts high-level features from the comprehensive feature vector; and an output layer, which generates the final model prediction output.

[0094] During the implementation process, the input layer accepts a single feature vector, reducing the complexity of multi-channel input. For the implementation of the feature extraction layer, 1 to 2 fully connected layers can be used to extract nonlinear features. Finally, a fully connected layer can be used to output the optimized design parameters and user satisfaction scores.

[0095] As a preferred embodiment of the above, the same feature interaction technology is used for user feedback data and demand data. Using the same feature interaction technology to process user feedback data and demand data can improve the consistency of feature interaction, simplify the model structure, improve generalization ability and interpretability, and reduce the risk of overfitting. The model can automatically capture the complex interactive relationship between feedback and demand, effectively process multi-dimensional and multi-type data, and improve the personalization and overall performance of progressive lens design.

[0096] Specifically, the feature interaction technology is a feature interaction technology based on random forests. Random forests are an integrated model composed of multiple decision trees, which naturally have the ability to capture feature interactions. The splitting process of each tree divides the space layer by layer according to the data features, and this split will naturally form interactions between different features. For example, a decision tree can first split according to the need for hyperopia, and then further split according to the need for astigmatism, thereby forming the interactive features of the two. Since random forests are an integrated model composed of multiple trees, they can capture more complex and subtle feature interactions through the diversity of trees.

[0097] During the implementation process, there may be complex nonlinear relationships between user feedback data (subjective feedback and objective data) and demand data (such as hyperopia demand, myopia demand, living habits, etc.). Through the splitting mechanism of random forests, the model can automatically handle these nonlinear relationships without manually setting interaction terms, reducing the complexity of manual intervention. At the same time, random forests can better deal with data noise or the randomness of some feedback data, thereby improving the robustness and generalization ability of the model. In practical applications, user feedback data may be volatile or highly subjective. Random forests can smooth these noises through ensemble learning, so that the model still performs well in different user scenarios.

[0098] Embodiment 2

[0099] A progressive lens is obtained by using the design method of the progressive lens as described in Example 1. The technical effect achieved by this embodiment is as described in the above Example 1, and will not be repeated here.

[0100] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for designing a progressive lens, characterized in that: include: S1: Obtain visual demand data of different users and define the visual demand coefficient D u , D u =f(D far ,D rear ,D astig ,D activity ); Among them, D far is the hyperopia demand coefficient, D rear is the myopia demand coefficient, D astig is the astigmatism demand coefficient, P activity is the coefficient of living habit demand; S2: According to the visual demand coefficient D u , dynamically adjust the change speed of the principal curvature and the mean curvature, the formula is as follows: t 平均曲率 =t 平均曲率0 ·(1+m1·(D u -D ref )); τ 主曲率 =τ 主曲率0 ·(1+m2·(D u -D ref )); Among them, τ 平均曲率0 and T 主曲率0 are the standard curvature change rates of the mean curvature and the principal curvature, m1 and m2 are the first adjustment coefficient and the second adjustment coefficient, respectively. ref is the reference value of the visual demand coefficient; S3: Dynamically adjust the width W of the transition area according to the user's hyperopia and myopia needs (x，y) , the formula is: W (x，y) =W base ·(1+k1·(D far -D ref,far )+k2·(D near -D ref,near )); Among them, W base is the standard width of the transition region, k1 and k2 are the first control coefficient and the second control coefficient, respectively, D ref，far and D ref，near are the reference values ​​of demand coefficients for hyperopia and myopia respectively; S4: Divide the transition area into regions in the width direction, and establish a new weight distribution function W for each region. adjusted(x) , the formula is: W adjusted(X) =W base(X) ·(1+a·exp(b·(D u -D ref ))+c·ln(1+d·|D u -D ref |)); Among them, W base(x) is the basic weight distribution function of the corresponding area, representing the initial state in the design of progressive lenses; a, b, c, d are the first control parameter, the second control parameter, the third control parameter and the fourth control parameter, respectively, which are used to adjust the influence of the exponential and logarithmic parts, and are targeted according to the corresponding area; S5: Establish a satisfaction model, predict m1, m2, k1, k2 and a, b, c, d of each corresponding area according to user feedback data, and calculate τ according to the prediction results 平均曲率 , τ 主曲率 , W (x，y) And the W of each region adjusted(x) ; S6: Provide initial τ for lens processing equipment 平均曲率0 , τ 主曲率0 , W base , W base(x) and the reference values ​​of each demand coefficient, according to the calculated m1, m2, τ 平均曲率 and τ 主曲率 Adjust the curvature control module according to the calculated k1, k2 and W (x，y) Adjust the area division module, and use a, b, c, d and W of each corresponding area adjusted(x) Adjust multi-interval power distribution.

2. The method for designing a progressive lens according to claim 1, characterized in that: The D u is the weighting function, and the calculation formula is: D u =W far ·D far +W nean ·D near +W astig ·D astig +W activity ·D activity ; Among them, W far , W near , W astig , W activity They are the weight coefficients for each demand, which are adjusted dynamically according to the user's specific situation and living habits.

3. The method for designing a progressive lens according to claim 1, characterized in that: The training data of the satisfaction model includes user feedback data, design parameter data and demand data; The user feedback data is a feature combination obtained by calculating the subjective feedback data and the objective data through the feature interaction technology; the design parameter data is a feature combination of the existing design parameters after feature combination and feature transformation; the demand data is a feature combination obtained by calculating different demand features through the feature interaction technology.

4. The method for designing a progressive lens according to claim 3, characterized in that: Building a satisfaction model includes: A1: Determine the model target to meet the user's visual satisfaction; A2: Obtain training data, and divide the training data into a training set, a validation set, and a test set; A3: constructing a model structure for outputting predicted design parameter data by inputting the user feedback data and demand data; A4: Model training and optimization: use machine learning algorithms to train the model, use validation set data to validate the model, and use test set data for final testing.

5. The method for designing a progressive lens according to claim 4, characterized in that: The machine learning algorithm is one of linear regression, decision tree, random forest, and neural network.

6. The method for designing a progressive lens according to claim 3, characterized in that: Establish nonlinear fusion function F combined , the input is the combination of three features of user feedback data, design parameter data and demand data, and the output is the fused comprehensive feature vector. The formula is as follows; <h2 style=";text-align:left;direction:ltr">F<h2 style=";text-align:left;direction:ltr"> combined <h2 style=";text-align:left;direction:ltr"> =ReLU(W2·ReLU(W1[F<h2 style=";text-align:left;direction:ltr"> feedbace <h2 style=";text-align:left;direction:ltr"> ,F<h2 style=";text-align:left;direction:ltr"> design <h2 style=";text-align:left;direction:ltr"> ,F<h2 style=";text-align:left;direction:ltr"> demand <h2 style=";text-align:left;direction:ltr"> ]+b1)+b2); Among them, F feedback is the feature combination of user feedback data, F design is the characteristic combination of design parameter data, F demand is the feature combination of the required data, W1, W2 are the weight matrices of the neural network, b1, b2 are bias terms, and ReLU is the nonlinear activation function.

7. The method for designing a progressive lens according to claim 6, characterized in that: The satisfaction model includes: An input layer, receiving the comprehensive feature vector as input; A feature extraction layer extracts high-level features from the comprehensive feature vector; Output layer, which generates the final model prediction output.

8. The method for designing a progressive lens according to claim 3, characterized in that: The same feature interaction technology is used for the user feedback data and the demand data.

9. The method for designing a progressive lens according to claim 8, characterized in that: The feature interaction technology is a feature interaction technology based on random forest.

10. A progressive lens, characterized in that: The method for designing a progressive lens as claimed in any one of claims 1 to 9 is used to obtain the progressive lens.

Images