# US 11,298,560 B2 · Light output device for caring for user using artificial intelligence and method of operating the same > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,298,560 B2 - Document ID: US11298560B2 - Status: Granted - Kind: B2 - Application number: 16/539,705 - Filed: 2019-08-13 - Published: 2019-12-05 - Granted: 2022-04-12 - Earliest claimed: 2019-07-11 - Assignees: LG Electronics Inc. - Applicants: LG Electronics Inc. - Inventors: Hyoeun Kim; Jaehong Kim; Hangil Jeong - Web page: https://patentgrep.com/patent/US11298560B2 ## CPC - A61N 5/0616: {Skin treatment other than tanning} - A61B 5/442: {Evaluating skin mechanical properties, e.g. elasticity, hardness, texture, wrinkle assessment} - A61B 5/443: {Evaluating skin constituents, e.g. elastin, melanin, water} - A61B 5/7267: {involving training the classification device} - G06T 7/0012: {Biomedical image inspection} - G06V 40/165: {using facial parts and geometric relationships} - A61B 5/4836: {Diagnosis combined with treatment in closed-loop systems or methods (A61B5/0036 takes precedence)} - A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems} - A61N 2005/0647: {the applicator adapted to be worn on the head} - A61N 2005/0659: {infrared} - A61N 2005/0661: {ultraviolet} - A61N 2005/0663: {Coloured light} - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30088: Skin; Dermal - G06T 2207/30201: Face - A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B) - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A light output device for caring for a skin of a user using artificial intelligence includes a plurality of light sources configured to irradiate light, a memory configured to store a skin care model learned using a deep learning algorithm to infer a facial skin state of the user, a camera configured to capture an image of a face of the user, and a processor configured to acquire a skin state of each part of the face based on a first-type face image captured through the camera and the skin care model, and control light output of the plurality of light sources based on the acquired skin state. ## Claims ### Claim 1 A light output device for caring for a skin of a user using artificial intelligence, the light output device comprising: a plurality of light sources configured to irradiate light; a memory configured to store a skin care model learned using a deep learning algorithm to infer a facial skin state of the user; a camera configured to capture an image of a face of the user; and a processor configured to: acquire a skin state of each part of the face based on a first-type face image captured through the camera and the skin care model by classifying the first-type face image into a plurality of main parts and acquiring a plurality of first-type partial images respectively corresponding to the plurality of classified main parts, and converting the plurality of acquired first-type partial images into a plurality of second-type partial images and a plurality of third-type partial images, and control light output of the plurality of light sources based on the acquired skin state, wherein the light output is controlled by adjusting a light irradiation time and a light irradiation intensity of the plurality of light sources according to the acquired skin state of each part of the face. ### Claim 2 (depends on 1) The light output device of claim 1, wherein the first-type partial images correspond to an RGB type, the second-type partial images correspond to an infrared (IR) type and the third-type partial images correspond to an ultraviolet (UV) type. ### Claim 3 (depends on 2) The light output device of claim 2, wherein the memory further stores an image conversion model for converting the first-type partial images into the second-type partial images and the third-type partial images, and wherein the image conversion model is an artificial neural network based model learned using a deep learning algorithm or a machine learning algorithm. ### Claim 4 (depends on 3) The light output device of claim 3, wherein the image conversion model is composed of a convolutional neural network (CNN). ### Claim 5 (depends on 1) The light output device of claim 1, wherein the processor is further configured to determine the skin state from the plurality of second-type partial images and the plurality of third-type partial images using the skin care model. ### Claim 6 (depends on 5) The light output device of claim 5, wherein the skin state comprises at least one of an amount of oil, a degree of wrinkles, an amount of moisture, a degree of elasticity, a degree of pigmentation or a degree of damage vulnerability of each part. ### Claim 7 (depends on 6) The light output device of claim 6, wherein the processor is configured to determine a skin type of each part of the face based on the skin state, wherein the skin type comprises a normal type and a damage type, wherein the normal type comprises a dry type, an oily type, a normal skin type, a combination type, and wherein the damage type comprises a serious pigmentation type and a serious damage vulnerability type. ### Claim 8 (depends on 7) The light output device of claim 7, wherein, when a degree of pigmentation is greater than or equal to a certain degree of pigmentation, the processor is further configured to determine that the skin type is the serious pigmentation type regardless of the normal type. ### Claim 9 (depends on 7) The light output device of claim 7, wherein, when a degree of damage vulnerability is greater than or equal to a certain degree of vulnerability, the processor is further configured to determine that the skin type is the serious pigmentation type regardless of the normal type. ### Claim 10 (depends on 7) The light output device of claim 7, wherein the processor is further configured to: control light output of the plurality of light sources to perform a light output mode in a normal care mode based on a determination that the skin type is the normal type, and control light output of the plurality of light sources to perform the light output mode in a concentrated care mode based on a determination that the skin type is the damage type. ### Claim 11 (depends on 1) The light output device of claim 1, further comprising a sound output unit; wherein the processor is configured to output information on the acquired skin state through the sound output unit. ### Claim 12 A method of operating a light output device for caring for a skin of a user using artificial intelligence, the method comprising: capturing an image of a face of the user; acquiring a skin state of each part of the face based on a skin care model learned using a captured first-type face image and a deep learning algorithm to infer a skin state of the face of the user by classifying the first-type face image into a plurality of main parts and acquiring a plurality of first-type partial images respectively corresponding to the plurality of classified main parts, and converting the plurality of acquired first-type partial images into a plurality of second-type partial images and a plurality of third-type partial images using an image conversion model; and controlling light output of a plurality of light sources based on the acquired skin state, wherein the light output is controlled by adjusting a light irradiation time and a light irradiation intensity of the plurality of light sources according to the skin state of each part. ### Claim 13 (depends on 12) The method of claim 12, wherein the first type is an RGB type, the second type is an infrared (IR) type and the third type is an ultraviolet (UV) type. ### Claim 14 (depends on 13) The method of claim 13, wherein the image conversion model is an artificial neural network based model learned using a deep learning algorithm or a machine learning algorithm, and wherein the image conversion model is composed of a convolutional neural network (CNN). ### Claim 15 (depends on 13) The method of claim 13, further comprising determining the skin state from the plurality of second-type partial images and the plurality of third-type partial images using the skin care model. ### Claim 16 (depends on 15) The method of claim 15, wherein the skin state comprises at least one of an amount of oil, a degree of wrinkles, an amount of moisture, a degree of elasticity, a degree of pigmentation or a degree of damage vulnerability of each part. ### Claim 17 (depends on 16) The method of claim 16, further comprising determining the skin type of each part of the face based on the skin type, wherein the skin type comprises a normal type and a damage type, wherein the normal type comprises a dry type, an oily type, a normal skin type, a combination type, and wherein the damage type comprises a serious pigmentation type and a serious damage vulnerability type.