# US 12,216,342 B2 · Method and system for determining parameters used to manufacture an optical article and a corresponding optical article > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,342 B2 - Document ID: US12216342B2 - Status: Granted - Kind: B2 - Application number: 17/294,276 - Filed: 2019-11-06 - Published: 2022-01-06 - Granted: 2025-02-04 - Earliest claimed: 2018-11-15 - Assignees: Essilor International - Applicants: Essilor International - Inventors: Sébastien Piraube; Kord Schrowangen; Charles Goodrum; Brad Gelb - Web page: https://patentgrep.com/patent/US12216342B2 ## CPC - G02C 7/027: {considering wearer's parameters} - B29D 11/00009: {Production of simple or compound lenses} - B29D 11/00961: {using microprocessors or computers} - G02C 7/028: {Special mathematical design techniques} - G06N 3/04: Architecture, e.g. interconnection topology - G06N 3/0499: Feedforward networks - G06N 3/09: Supervised learning - G06N 3/084: Backpropagation, e.g. using gradient descent - G02C: SPECTACLES; SUNGLASSES OR GOGGLES INSOFAR AS THEY HAVE THE SAME FEATURES AS SPECTACLES; CONTACT LENSES (trial frames for testing the eyes A61B3/04; goggles or eyeshields not having the same features as spectacles A61F9/00) - B29D: PRODUCING PARTICULAR ARTICLES FROM PLASTICS OR FROM SUBSTANCES IN A PLASTIC STATE (making granules B29B9/00; making preforms B29B11/00) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract This method for determining specification parameters used to manufacture an optical article includes steps of: training at least one neural network to predict the specification parameters, by using a training data set including a plurality of training prescription parameters and corresponding training specification parameters; and predicting specification parameters of the optical article by the at least one neural network, from prescription parameters relating to the optical article, on the basis of the training. ## Claims ### Claim 1 A method for determining specification parameters used to manufacture at least one ophthalmic lens, said specification parameters including one or more of: (i) optical and/or geometrical data relating to said at least one ophthalmic lens, and (ii) at least one parameter relating to a manufacturing process required to manufacture said ophthalmic lens, the method comprising: training at least one neural network to predict said specification parameters used to manufacture the at least one ophthalmic lens, by using a training data set comprising a plurality of training prescription parameters and corresponding training specification parameters; and predicting the specification parameters of said at least one ophthalmic lens by said at least one trained neural network, from prescription parameters relating to said at least one ophthalmic lens, based on said training. ### Claim 2 (depends on 1) The 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 to correct a specific visual deficiency. ### Claim 3 (depends on 2) The method according to claim 2, wherein said training comprises teaching said neural network how to select an appropriate blocking ring to manufacture said at least one ophthalmic lens. ### Claim 4 (depends on 2) The method according to claim 2, wherein said neural network has 8 input neurons and 24 output neurons. ### Claim 5 (depends on 2) The method according to claim 2, wherein said training 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. ### Claim 6 (depends on 1) The method according to claim 1, wherein said training comprises teaching said neural network how to select an appropriate blocking ring to manufacture said at least one ophthalmic lens. ### Claim 7 (depends on 6) The method according to claim 6, wherein said neural network has 8 input neurons and 24 output neurons. ### Claim 8 (depends on 6) The method according to claim 6, wherein said training 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. ### Claim 9 (depends on 1) The method according to claim 1, wherein said neural network has 8 input neurons and 24 output neurons. ### Claim 10 (depends on 9) The method according to claim 9, wherein said training 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. ### Claim 11 (depends on 1) The method according to claim 1, wherein said training 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. ### Claim 12 (depends on 11) The method according to claim 11, wherein said training is carried out until said error is below a predetermined threshold. ### Claim 13 (depends on 11) The method according to claim 11, wherein said training is carried out for a predetermined number of iterations of said iterative phase. ### Claim 14 (depends on 1) A system for determining specification parameters used to manufacture at least one ophthalmic lens, said specification parameters including one or more of: (i) optical and/or geometrical data relating to said at least one ophthalmic lens, and (ii) at least one parameter relating to a manufacturing process required to manufacture said ophthalmic lens, the system comprising: at least one neural network predicting said specification parameters by performing the method according to claim 1. ### Claim 15 (depends on 1) An ophthalmic lens manufactured by using the specification parameters determined by implementing the method according to claim 1. ### Claim 16 (depends on 1) A non-transitory computer-readable medium on which is stored a computer program 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 the method according to claim 1.