# US 12,758,000 B2 · Modulation of coloring formulation components for hair coloring device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,758,000 B2 - Document ID: US12758000B2 - Status: Granted - Kind: B2 - Application number: 18/501,469 - Filed: 2023-11-03 - Published: 2025-05-08 - Granted: 2026-10-13 - Earliest claimed: 2023-11-03 - Assignees: L'oreal - Applicants: L'Oreal - Inventors: Rafael Feliciano; Heba S. Said; Hyosik Dennis Min - Web page: https://patentgrep.com/patent/US12758000B2 ## CPC - A45D 44/005: {for selecting or displaying personal cosmetic colours or hairstyle} - A45D 19/0066: {Coloring or bleaching} - G06Q 30/0621: {by configuring or customising goods or services} - G06Q 30/0631: {Recommending goods or services} - G06T 7/40: Analysis of texture (depth or shape recovery from texture G06T7/529) - G06T 7/60: Analysis of geometric attributes - G06T 7/90: Determination of colour characteristics - A45D 2044/007: {Devices for determining the condition of hair or skin or for selecting the appropriate cosmetic or hair treatment} - G06T 2207/20081: Training; Learning - G06T 2207/30196: Human being; Person - A45D: HAIRDRESSING OR SHAVING EQUIPMENT (wigs, toupees or the like A41G3/00, A41G5/00; hairdressers' chairs A47C1/04; hair cutting appliances, razors B26B); EQUIPMENT FOR COSMETICS OR COSMETIC TREATMENTS, e.g. FOR MANICURING OR PEDICURING - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A computer system obtains digital image data of hair of a live subject; provides the digital image data to a style recommendation engine of the computer system; determines, by the style recommendation engine of the computer system, color of the hair of the live subject based on the digital image data; and executes a machine learning model of the style recommendation engine using the color of the hair of the live subject as input to generate a style profile as output. The style profile comprises parameters configured to control discharge of one or more components of a hair coloring formulation by a formulation dispensing system of a hair coloring device. ## Claims ### Claim 1 A non-transitory computer-readable medium having stored thereon instructions configured to, when executed by one or more computing devices of a computer system, cause the computer system to perform operations comprising: obtaining digital image data of hair of a live subject; providing the digital image data to a style recommendation engine of the computer system; determining, by the style recommendation engine of the computer system, color of the hair of the live subject based on the digital image data; and executing a machine learning model of the style recommendation engine using the color of the hair of the live subject as input to generate a style profile as output, wherein the style profile comprises parameters configured to control discharge of one or more components of a hair coloring formulation by a formulation dispensing system of a hair coloring device, wherein the style profile generated by the machine learning model further comprises a pattern of hair coloring, wherein the pattern comprises a gradient effect, and wherein the parameters are further configured to modulate discharge of the one or more components to color the hair of the live subject to achieve the gradient effect. ### Claim 2 (depends on 1) The non-transitory computer-readable medium of claim 1, wherein the style profile generated by the machine learning model further comprises one or more custom components of the hair coloring formulation. ### Claim 3 (depends on 1) The computer-readable medium of claim 1, the operations further comprising determining length or texture of the hair of the live subject, wherein the executing of the machine learning model uses the length or texture of the hair as additional input to generate the style profile as output. ### Claim 4 (depends on 1) The computer-readable medium of claim 1, the operations further comprising obtaining environmental data associated with the environment of the live subject, wherein the executing of the machine learning model uses the environmental data as additional input to generate the style profile as output. ### Claim 5 (depends on 4) The computer-readable medium of claim 4, wherein the environmental data includes temperature data, humidity data, or a combination thereof. ### Claim 6 (depends on 1) The computer-readable medium of claim 1, the operations further comprising: obtaining sensor information from the hair coloring device during a hair coloring operation; and modifying the discharge of the one or more components based on the sensor information. ### Claim 7 (depends on 6) The computer-readable medium of claim 6, wherein the sensor information comprises position sensor data, and wherein modifying the discharge of the one or more components based on the sensor information comprises: calculating, based on the position sensor data, a position of the hair coloring device relative to the hair of the live subject; and modifying the discharge of the one or more components based on the calculated position. ### Claim 8 (depends on 1) The computer-readable medium of claim 1, wherein determining the color of the hair of the live subject based on the digital image data comprises: executing a machine learning model of the style recommendation engine using the digital image data as input to generate the determined color of the hair as output. ### Claim 9 A computer-implemented method executed by one or more computing devices of a computer system, the method comprising: obtaining digital image data of hair of a live subject; providing the digital image data to a style recommendation engine of the computer system; determining, by the style recommendation engine of the computer system, color of the hair of the live subject based on the digital image data; and executing a machine learning model of the style recommendation engine using the color of the hair of the live subject as input to generate a style profile as output, and wherein the style profile comprises parameters configured to control discharge of one or more components of a hair coloring formulation by a formulation dispensing system of a hair coloring device, wherein the style profile generated by the machine learning model further comprises a pattern of hair coloring, wherein the pattern comprises a gradient effect, and wherein the parameters are further configured to modulate discharge of the one or more components to color the hair of the live subject to achieve the gradient effect. ### Claim 10 (depends on 9) The method of claim 9, wherein the style profile generated by the machine learning model comprises one or more custom components of the hair coloring formulation. ### Claim 11 (depends on 9) The method of claim 9 further comprising determining length or texture of the hair of the live subject, wherein the executing of the machine learning model uses the length or texture of the hair as additional input to generate the style profile as output. ### Claim 12 (depends on 9) The method of claim 9 further comprising obtaining environmental data associated with the environment of the live subject, wherein the executing of the machine learning model uses the environmental data as additional input to generate the style profile as output. ### Claim 13 (depends on 12) The method of claim 12, wherein the environmental data includes temperature data, humidity data, or a combination thereof. ### Claim 14 (depends on 9) The method of claim 9 further comprising: obtaining sensor information from the hair coloring device during a hair coloring operation; and modifying the discharge of the one or more components of the hair coloring formulation based on the sensor information. ### Claim 15 (depends on 14) The method of claim 14, wherein the sensor information comprises position sensor data, and wherein modifying the discharge of the one or more components based on the sensor information comprises: calculating, based on the position sensor data, a position of the hair coloring device relative to the hair of the live subject; and modifying the discharge of the one or more components of the hair coloring formulation based on the calculated position. ### Claim 16 (depends on 9) The method of claim 9, wherein determining the color of the hair of the live subject based on the digital image data comprises: executing a machine learning model of the style recommendation engine using the digital image data as input to generate the determined color of the hair as output. ### Claim 17 A hair coloring device, comprising: a formulation dispensing system; and computational circuitry configured to: receive a style profile comprising parameters configured to control discharge of one or more components of a hair coloring formulation by the formulation dispensing system; and operate the formulation dispensing system according to the style profile, wherein the style profile is generated as output of a machine learning model of a style recommendation engine, wherein the style profile generated by the machine learning model further comprises a pattern of hair coloring, wherein the pattern comprises a gradient effect, and wherein the parameters are further configured to modulate discharge of the one or more components to color the hair of the live subject to achieve the gradient effect. ### Claim 18 (depends on 17) The hair coloring device of claim 17 further comprising one or more sensors, wherein the computational circuitry is further configured to: obtain sensor information from the one or more sensors during a hair coloring operation; and modulate the discharge of the one or more components of the hair coloring formulation based on the sensor information. ### Claim 19 (depends on 17) The hair coloring device of claim 17, wherein the parameters are further configured to cause the formulation dispensing system to gradually increase or decrease dye loads along the length of the hair to achieve the gradient effect. ### Claim 20 (depends on 19) The hair coloring device of claim 19, wherein the pattern of hair coloring comprises balayage styling.