Method and system for determining parameters used to manufacture an optical article and associated optical articles

Description

FIELD OF THE INVENTION

[0001] The present invention relates to a method and system for determining parameters to be used to manufacture an optical article.BACKGROUND OF THE INVENTION

[0002] Manufacturing optical articles such as ophthalmic lenses implies surfacing complex optics on the rear face and possibly also front face of semi-finished lenses, applying added value treatments and edging the lenses so that they fit in a frame chosen by the patient. To that end, each order for a pair of glasses contains the prescription of the patient as well as the features of the desired final product, such as the frame, the optical design, the options, the added values, etc.

[0003] The complex optics as well as the manufacturing parameters needed to make the final products are usually computed on the fly for each order coming into the production laboratory. Such computation is done using sophisticated calculation software, referred to as a lens design software (LDS).

[0004] Today, LDS systems usually run the above-mentioned computation for every job sent to them by a laboratory management system (LMS). This computation involves long logic and algorithm execution, as well as mathematical optimizations.

[0005] As a consequence, the computation consumes a lot of resources related to information technology, such as computers, server farms, software licenses, load balancers for distributing jobs according to the processing load of a plurality of servers, etc. This incurs a significant cost for optical article manufacturing companies.

[0006] In addition, it is necessary to size server resources in order to process the maximum load that may be requested at any given moment. This means that, if the production laboratories enter their respective jobs for the day at the same time, the server resources must be sized in such a manner as to be able to process all those simultaneous orders, even if, during the rest of the day, those server resources do not have the same workload.

[0007] Therefore, there is a need to reduce the time required to compute the optical and other parameters used to manufacture an optical article for a given prescription.

[0008] WO 2005 / 050290 A1 (Warden et al, Ophthonix Inc; System for manufacturing an optical lens; 2 June 2005) discloses a neural network-based system for manufacturing an optical lens, configured to correct optical aberrations, and including a measurement system configured to measure optical aberrations in a patient's eye and to create measured optical aberration data, as well as a calculation system configured to receive the measured optical aberration data and to determine a lens definition based on the measured optical aberration data.SUMMARY OF THE INVENTION

[0009] An object of the invention is to overcome the above-mentioned drawbacks of the prior art.

[0010] 10 To that end, the invention provides a method according to claim 1. Therefore, due to the leveraging of neural networks for predicting parameters used to manufacture the optical article, the computation time is reduced, the service level of production laboratories and optical stores to customers is increased, the requirement for sizing the information technology back-end system 15 is reduced and the resulting costs for optical article manufacturing companies are reduced.

[0011] The invention also provides a system according to claim 8.

[0012] The invention further provides a computer program product according to claim 9. 20BRIEF DESCRIPTION OF THE DRAWINGS

[0013] For a more complete understanding of the description provided herein and the advantages thereof, reference is now made to the brief descriptions below, taken in connection with the accompanying drawings and detailed description, wherein 25 like reference numerals represent like parts.

[0014] FIG. 1 is a schematic view of a system for determining parameters used to manufacture an optical article according to the invention, in a particular embodiment.

[0015] FIG. 2 is a flowchart showing steps of a method for determining parameters used to manufacture an optical article according to the invention, in a particular 30 embodiment.DETAILED DESCRIPTION OF THE INVENTION

[0016] In the description which follows, the drawing figures are not necessarily to scale and certain features may be shown in generalized or schematic form in the interest of clarity and conciseness or for informational purposes. In addition, although making and using various embodiments are discussed in detail below, it should be appreciated that as described herein are provided many inventive concepts that may embodied in a wide variety of contexts. Embodiments discussed herein are merely representative and do not limit the scope of the invention. It will also be obvious to one skilled in the art that all the technical features that are defined relative to a process can be transposed, individually or in combination, to a device and conversely, all the technical features relative to a device can be transposed, individually or in combination, to a process.

[0017] The terms "comprise" (and any grammatical variation thereof, such as "comprises" and "comprising"), "have" (and any grammatical variation thereof, such as "has" and "having"), "contain" (and any grammatical variation thereof, such as "contains" and "containing"), and "include" (and any grammatical variation thereof such as "includes" and "including") are open-ended linking verbs. They are used to specify the presence of stated features, integers, steps or components or groups thereof, but do not preclude the presence or addition of one or more other features, integers, steps or components or groups thereof. As a result, a method, or a step in a method, that "comprises", "has", "contains", or "includes" one or more steps or elements possesses those one or more steps or elements, but is not limited to possessing only those one or more steps or elements.

[0018] Figure 1 is a schematic view of a system 10 for determining parameters used to manufacture an optical article according to the invention, in a particular embodiment. Such parameters will be referred to as "specification parameters". They may relate to the optical and / or geometrical properties of the optical article, as well as to its manufacturing process.

[0019] The system 10 comprises a lens design module (LDS) 12 and a laboratory management system (LMS) 14. The LMS 14 sends prescription parameters 16 to the LDS 12 and receives from the LDS 12 computation results 18 enabling manufacturing of an optical article which, in a particular embodiment, comprises at least one ophthalmic lens.

[0020] The prescription parameters 16 comprise all the features relating to the prescription, such as the ophthalmic correction required by the prescription for correcting one or more visual deficiencies, the selected frame, the material and possibly other features regarding the desired final product, such as the type of semi-finished lens to be used and specific optical requirements.

[0021] The computation results 18 comprise a set of predicted specification parameters. The predicted specification parameters may include optical and / or geometrical data relating to the optical article (e.g. thickness characteristics, wearer power compensations, etc.) and / or at least one parameter relating to a manufacturing process required to manufacture the optical article (e.g. parameters for a given manufacturing equipment such as a blocking ring to be used on an alloy blocker, as detailed below).

[0022] According to the invention, the system 10 further comprises one or more neural networks 20 which, in a particular embodiment, may be embedded inside the LDS 12.

[0023] The manufacturing process of an ophthalmic lens may comprise a grinding step, during which the ophthalmic lens is presented at a proper angle to a grinding wheel. To that end, a blocking step consists of using a tool called a blocking ring, which is known by the skilled person, for blocking the ophthalmic lens in the appropriate position with respect to the grinding wheel.

[0024] The invention makes it possible to predict the blocking rings to be used in the blocking steps.

[0025] In the particular embodiment shown in Figure 1, the system 10 comprises one neural network 20. As a non-limiting example, the neural network 20 may have eight input neurons and twenty-four output neurons, with one output neuron per blocking ring. In that example, the eight inputs are as follows: type of manufacturing process, refractive index value, prescription sphere, prescription cylinder, prescription addition, semi-finished lens base, diameter to grind and semi-finished lens diameter.

[0026] In addition, as a non-limiting example, the neural network 20 may have one hidden layer with thirty neurons. As a variant, the neural network may have more than one hidden layer and different numbers of neurons in the hidden layers, different numbers of neurons at the input of the network and different numbers of neurons at the output of the network.

[0027] In any case, the data entered into the neural network 20 have to be formatted so as to be adapted to the number of inputs and outputs of the neural network 20.

[0028] The neural network 20 receives prescription parameters 16 as an input, and outputs prediction results 22 that contain all the necessary predicted specification parameters computed by the neural network 20 regarding the optical article to be manufactured.

[0029] The neural network 20 is configured to predict a predefined piece of data. For each piece of data to be predicted, the input neurons of the neural network 20 are configured to match the data input and the output neurons are configured to match the type of data to be predicted. The hidden layers of the neural network 20 are configured so as to provide the most accurate output.

[0030] According to the invention, in order to be operational and be able to predict the specification parameters of an optical article, the neural network 20 undergoes a training step 200, as shown in Figure 2.

[0031] During the training step, a training data set comprising a plurality of training prescription parameters and corresponding training specification parameters, previously computed by means of the usual logic and optimization resources 24, is entered into the neural network 20. Advantageously, a large quantity of training data is used in order to improve the prediction capability of the neural network 20.

[0032] In a particular embodiment, the training step comprises teaching the neural network 20 how to select an appropriate blocking ring for manufacturing a given optical article.

[0033] In a particular embodiment, the training step comprises an iterative phase including measuring an error 28 in the output of the neural network 20 and updating weights in the neural network 20 in order to reduce the error 28.

[0034] The error 28 is measured in a comparison module 30, in which the prediction results 22 are compared with the computation results 26. As a non-limiting example, the error 28 may be the variance between the prediction results 22 and the computation results 26.

[0035] The training step 200 may be carried out until the error 28 is below a predetermined threshold.

[0036] As a variant, the training step 200 may be carried out for a predetermined number of iterations of the iterative phase. As a non-limiting example, the predetermined number of iterations may be at least 2000.

[0037] Once the neural network 20 is fully trained, it is able to predict, in a step 202 shown in Figure 2, specification parameters of an optical article, on the basis of input prescription parameters relating to the optical article.

[0038] In a particular embodiment, the method according to the invention is computer-implemented. Namely, a computer program product comprises one or more stored sequences of instructions that are accessible to a processor and that, when executed by the processor, cause the processor to carry out steps 200 and 202 described above.

[0039] The sequence(s) of instructions may be stored in a computer readable storage medium.

[0040] The method, system and computer program product according to the invention may be used not only for significantly reducing the time and costs involved in manufacturing optical articles, but also in a point of sale, when the optician dispensing a pair of glasses to a customer wishes to know what the ophthalmic lenses will look like with the customer's prescription, depending on the thickness and weight of the ophthalmic lenses and possible options chosen by the customer. Such operation is very sensitive to computation time, since the person dispensing the pair of glasses is in front of the customer in the meantime. Thanks to the reduction in computation time provided by the invention, such operation will be significantly accelerated and will thus bring greater satisfaction to the customer.

[0041] Although representative processes and articles have been described in detail herein, those skilled in the art will recognize that various substitutions and modifications may be made without departing from the scope of protection which is defined by the appended claims.

Claims

1. A computer-implemented method for determining specification parameters to be used to manufacture at least one ophthalmic lens, said specification parameters including optical and / or geometrical data relating to said at least one ophthalmic lens, and blocking ring parameters relating to a manufacturing process required to manufacture said at least one ophthalmic lens, wherein each blocking ring parameter corresponds to a specific type of blocking ring to be used in a blocking step of the manufacturing process prior to a grinding step of the manufacturing process, the method comprising steps of: training (200) a neural network, by using a training data set comprising a plurality of training prescription parameters and corresponding training specification parameters; and predicting (202) the specification parameters to be used to manufacture said at least one ophthalmic lens by means of the trained neural network, from prescription parameters relating to said at least one ophthalmic lens.

2. A method according to claim 1, wherein said prescription parameters relating to said at least one ophthalmic lens comprise at least one parameter relating to an ophthalmic correction for correcting a given visual deficiency.

3. A method according to any of the preceding claims, further comprising: selecting a blocking ring to be used in the manufacturing process based on the predicted specification parameters.

4. A method according to any of the preceding claims, wherein said neural network has 8 input neurons and 24 output neurons.

5. A method according to any of the preceding claims, wherein said training step comprises an iterative phase including measuring an error in the output of said neural network and updating weights in said neural network in order to reduce said error.

6. A method according to claim 5, wherein said training step is carried out until said error is below a predetermined threshold.

7. A method according to claim 5, wherein said training step is carried out for a predetermined number of iterations of said iterative phase.

8. A system configured to determine specification parameters to be used to manufacture at least one ophthalmic lens, from prescription parameters relating to said at least one ophthalmic lens, said specification parameters including optical and / or geometrical data relating to said at least one ophthalmic lens, and blocking ring parameters relating to a manufacturing process required to manufacture said ophthalmic lens, wherein each blocking ring parameter corresponds to a specific type of blocking ring to be used in a blocking step of the manufacturing process prior to a grinding step of the manufacturing process, the system comprising a neural network (20) trained by a method according to any of the preceding claims.

9. A computer program product comprising one or more sequences of instructions that are accessible to a processor and that, when executed by said processor, cause said processor to carry out a method according to any of claims 1 to 7.