# US 11,910,083 B2 · Method and system with optimization of lens module assembly > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,910,083 B2 - Document ID: US11910083B2 - Status: Granted - Kind: B2 - Application number: 17/397,136 - Filed: 2021-08-09 - Published: 2022-05-12 - Granted: 2024-02-20 - Earliest claimed: 2020-11-06 - Assignees: Samsung Electro-Mechanics Co., Ltd.; Kyonggi University Industry & Academia Cooperation Foundation - Applicants: Samsung Electro-Mechanics Co., Ltd.; Kyonggi University Industry & Academia Cooperation Foundation - Inventors: Hye Geun Min; Ye Rim Choi; Yeon Bin Son; Sung Hoon Kim; Eun Young Choi - Web page: https://patentgrep.com/patent/US11910083B2 ## CPC - G06N 20/10: using kernel methods, e.g. support vector machines [SVM] - H04N 23/64: {Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image} - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - H04N 23/55: Optical parts specially adapted for electronic image sensors; Mounting thereof - H04N 23/57: Mechanical or electrical details of cameras or camera modules specially adapted for being embedded in other devices - H04N 23/617: Upgrading or updating of programs or applications for camera control - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract A lens module assembly optimization method includes: in preparing a lens module including assembled N lenses respectively formed in cavities: receiving characteristic information of at least N lenses respectively formed in N cavity groups each including a respective plurality of cavities; and processing information for selecting N cavities from the N cavity groups, based on the characteristic information. A past cavity selection result, a fitness function configured based on data of the assembled N lenses or data of the prepared lens module according to the past cavity selection result, and a genetic algorithm are received or stored. The processing of the information includes updating chromosome entity information based on the fitness function and output chromosome information crossed or mutated based on the genetic algorithm from input chromosome information corresponding to the past cavity selection result, and processing the information based on the chromosome entity information and the characteristic information. ## Claims ### Claim 1 A method with optimization of a lens module assembly, comprising: in preparing a lens module including assembled N lenses respectively formed in cavities to overlap each other on an optical axis, wherein N is a natural number of 2 or more: receiving, by a computing system, characteristic information of at least N lenses respectively formed in N cavity groups each including a respective plurality of cavities having a similarity to each other that is higher than a similarity to each other of the assembled N lenses; and processing, by the computing system, information for selecting N cavities from the N cavity groups, based on the characteristic information, wherein the computing system receives or stores a past cavity selection result obtained by the processing of the information for selecting the N cavities, a fitness function configured based on data of the assembled N lenses or data of the prepared lens module according to the past cavity selection result, and a genetic algorithm, and wherein the processing of the information for selecting the N cavities includes updating chromosome entity information based on the fitness function and output chromosome information crossed or mutated based on the genetic algorithm from input chromosome information corresponding to the past cavity selection result, and processing the information for selecting the N cavities based on the chromosome entity information and the characteristic information. ### Claim 2 (depends on 1) The method of claim 1, wherein chromosome information used in the genetic algorithm is composed of a plurality of gene information respectively having N pieces of point information, or the chromosome information used in the genetic algorithm is composed of N pieces of gene information respectively having a plurality of point information. ### Claim 3 (depends on 2) The method of claim 2, wherein the output chromosome information is generated through either one or both of a point crossover and a gene crossover between a plurality of input chromosome information. ### Claim 4 (depends on 2) The method of claim 2, wherein the updating of the chromosome entity information is performed based on a number of values, greater than or equal to a reference value, among a plurality of values according to a quality prediction model of a plurality of gene information included in the input chromosome information or the output chromosome information. ### Claim 5 (depends on 1) The method of claim 1, wherein each of the N cavity groups includes M cavities, wherein M is a natural number of 2 or more, and wherein the updating of the chromosome entity information is performed based on a number of values, greater than or equal to a reference value, among a plurality of values according to a quality prediction model of an M cavity selection result selected from the N cavity groups. ### Claim 6 (depends on 1) The method of claim 1, wherein a plurality of lenses corresponding to the plurality of cavities included in one of the N cavity groups are formed at the same time. ### Claim 7 (depends on 1) The method of claim 1, wherein the characteristic information of the N lens groups includes optical or physical measurement information of the N lens groups. ### Claim 8 (depends on 1) The method of claim 1, wherein the fitness function is repeatedly updated based on data of the assembled N lenses or data of the prepared lens module according to the past cavity selection result. ### Claim 9 (depends on 1) The method of claim 1, further comprising processing, by the computing system, angle information on rotation of at least one of N lenses corresponding to the N cavities in a direction around the optical axis, when the N lenses corresponding to the N cavities are assembled to overlap on the optical axis, based on the information for selecting the N cavities. ### Claim 10 (depends on 9) The method of claim 9, further comprising performing updating of the fitness function based on data of each of the N lenses corresponding to the N cavities selected by the processing of the information for selecting the N cavities, and updating of the fitness function based on data of a lens module assembled at an angle corresponding to the processing of the angle information, according to a machine learning algorithm. ### Claim 11 (depends on 1) A non-transitory, computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1. ### Claim 12 A method with optimization of a lens module assembly, comprising: in preparing a lens module including assembled N lenses respectively formed in cavities to overlap each other on an optical axis, wherein N is a natural number of 2 or more: receiving, by a computing system, characteristic information of at least N lenses respectively formed in N cavity groups each including a respective plurality of cavities having a similarity to each other that is higher than a similarity to each other of the assembled N lenses; processing, by the computing system, information for selecting N cavities from the N cavity groups, based on a fitness function and the characteristic information; and processing, by the computing system, angle information on rotation of at least one of N lenses corresponding to the N cavities in a direction around the optical axis, when the N lenses corresponding to the N cavities are assembled to overlap on the optical axis, based on the information for selecting the N cavities, wherein the computing system receives or stores a past cavity selection result obtained by the processing of the information for selecting the N cavities, and the fitness function configured based on data of the assembled N lenses or data of the prepared lens module according to the past cavity selection result, and wherein the computing system performs updating of the fitness function based on data of each of the N lenses corresponding to the N cavities selected by the processing of the information for selecting the N cavities, and updating of the fitness function based on data of a lens module assembled at an angle corresponding to the processing of the angle information, according to a machine learning algorithm. ### Claim 13 (depends on 12) The method of claim 12, wherein the processing of the angle information comprises processing the angle information by applying the information for selecting the N cavities to a rotation angle prediction model updated based on the data of a lens module assembled at the angle corresponding to the processing of the angle information. ### Claim 14 (depends on 12) The method of claim 12, wherein each of the N cavity groups includes M cavities, wherein M is a natural number of 2 or more, and wherein fitness information output from the fitness function comprises information on a number of values, greater than or equal to a reference value, among a plurality of values according to a quality prediction model of an M cavity selection result selected from the N cavity groups. ### Claim 15 (depends on 12) The method of claim 12, wherein the plurality of cavities included in one of the N cavity groups have a higher isotropic property, respectively, than a plurality of lenses corresponding to the one of the N cavity groups. ### Claim 16 (depends on 12) The method of claim 12, wherein the plurality of cavities included in one of the N cavity groups are connected to each other before a plurality of lenses corresponding to the one of the N cavity groups are formed, and are separated from each other after the plurality of lenses corresponding to the one of the N cavity groups are formed. ### Claim 17 (depends on 12) A non-transitory, computer-readable storage medium storing instructions that when executed by a processor, cause the processor to perform the method of claim 12. ### Claim 18 A system with optimization of a lens module assembly, comprising: at least one processor configured to, in preparing a lens module including assembled N lenses respectively formed in cavities to overlap each other on an optical axis, wherein N is a natural number of 2 or more: receive characteristic information of at least N lenses respectively formed in N cavity groups each including a plurality of cavities; and process information for selecting N cavities from the N cavity groups, based on the characteristic information, wherein the system is configured to obtain a past cavity selection result obtained by the processing of the information for selecting the N cavities, a fitness function configured based on data of the assembled N lenses or data of the prepared lens module according to the past cavity selection result, and a genetic algorithm, and wherein the at least one processor is further configured to process the information for selecting the N cavities by updating chromosome entity information based on the fitness function and output chromosome information generated by the genetic algorithm from input chromosome information corresponding to the past cavity selection result, and processing the information for selecting the N cavities based on the chromosome entity information and the characteristic information. ### Claim 19 (depends on 18) The system of claim 18, wherein the plurality of cavities have a similarity to each other that is higher than a similarity to each other of the assembled N lenses. ### Claim 20 (depends on 18) The system of claim 18, wherein, in each of the N cavity groups, a plurality of lenses are respectively formed in the plurality of cavities at the same time. ### Claim 21 (depends on 18) The system of claim 18, wherein chromosome information used in the genetic algorithm is composed of a plurality of gene information respectively having N pieces of point information, or the chromosome information used in the genetic algorithm is composed of N pieces of gene information respectively having a plurality of point information. ### Claim 22 (depends on 21) The system of claim 21, wherein the output chromosome information is generated through either one or both of a point crossover and a gene crossover between a plurality of input chromosome information. ### Claim 23 (depends on 18) The system of claim 18, wherein each of the N cavity groups includes M cavities, wherein M is a natural number of 2 or more, and wherein the processor is further configured to perform the updating of the chromosome entity information based on a number of values, greater than or equal to a reference value, among a plurality of values according to a quality prediction model of an M cavity selection result selected from the N cavity groups.