# US 11,307,593 B2 · Artificial intelligence device for guiding arrangement location of air cleaning device and operating method thereof > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,307,593 B2 - Document ID: US11307593B2 - Status: Granted - Kind: B2 - Application number: 16/539,810 - Filed: 2019-08-13 - Published: 2019-12-05 - Granted: 2022-04-19 - Earliest claimed: 2019-07-22 - Assignees: LG Electronics Inc. - Applicants: LG Electronics Inc. - Inventors: Kokeun Kim; Suyeon Kim; Kamin Lee; Seungah Chae - Web page: https://patentgrep.com/patent/US11307593B2 ## CPC - A47L 9/009: {Carrying-vehicles; Arrangements of trollies or wheels; Means for avoiding mechanical obstacles} - A47L 9/2857: {User input or output elements for control, e.g. buttons, switches or displays} - B01D 46/429: {Means for wireless communication} - B01D 46/46: automatic - G05D 1/00: Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots (drive control systems specially adapted for autonomous road vehicles B60W60/00) - G05D 1/0219: {ensuring the processing of the whole working surface} - G06N 3/08: Learning methods - G06N 3/092: Reinforcement learning - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - A47L 9/2815: {using optical detectors} - A47L 9/2852: {Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles} - A47L 2201/04: Automatic control of the travelling movement; Automatic obstacle detection - B01D 2279/55: for cleaning appliances, e.g. suction cleaners - A47L: DOMESTIC WASHING OR CLEANING (brushes A46B; cleaning quantities of bottles or of other hollow articles of one kind B08B9/00; laundry D06F); SUCTION CLEANERS IN GENERAL (cleaning in general B08) - B01D: SEPARATION (separating solids from solids by wet methods B03B, B03D; by pneumatic jigs or tables B03B; by other dry methods B07; magnetic or electrostatic separation of solid materials from solid materials or fluids, separation by high-voltage electric fields B03C; centrifuges, vortex apparatus B04; presses per se for squeezing-out liquid from liquid-containing material B30B9/02; treatment of water C02F, e.g. softening by ion-exchange C02F1/42; {arrangements of air intake cleaners in gas turbine plants F02C7/05} ; arrangements or mounting of filters in air-conditioning, air-humidification or ventilation F24F13/28) - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract An artificial intelligence (AI) device for guiding an arrangement location of an air cleaning device includes a memory to store an air cleaning device arrangement model to infer the arrangement location of the air cleaning device based on information on fine dust in a house and a processor configured to acquire information on a map of the house and information on fine dust distribution in the house, and to determine the arrangement location of the air cleaning device based on the information on the map and the information on the fine dust distribution, by using the air cleaning device arrangement model. ## Claims ### Claim 1 An artificial intelligence (AI) device for guiding an arrangement location of an air cleaning device, the AI device comprising: a display unit configured to display an arrangement guide screen to guide the arrangement location of the air cleaning device; a memory to store an air cleaning device arrangement model to infer the arrangement location of the air cleaning device based on information on fine dust in a building; and a processor configured to: acquire information on a map of the building and information on fine dust distribution in the building; determine the arrangement location of the air cleaning device based on the information on the map and the information on the fine dust distribution using the air cleaning device arrangement model; and cause the display unit to display a map on the arrangement guide screen based on receiving a user input for a number of air cleaning devices, wherein the map on the arrangement guide screen comprises one or more indicators identifying arrangement locations of air cleaning devices, wherein the one or more indicators correspond to the number of air cleaning devices. ### Claim 2 (depends on 1) The AI device of claim 1, wherein the air cleaning device arrangement model is a model trained in reinforcement learning based on a deep learning algorithm or a machine learning algorithm, and wherein the reinforcement learning is performed through a Markov Decision Process (MDP). ### Claim 3 (depends on 2) The AI device of claim 2, wherein the processor is further configured to: acquire, as an output result of the air cleaning device arrangement model, the arrangement location of the air cleaning device from the information on the map and a fine dust distribution degree, and train the air cleaning device arrangement model by rewarding or penalizing the air cleaning device arrangement model based on a fine dust concentration in the building after the fine dust concentration is re-measured. ### Claim 4 (depends on 3) The AI device of claim 3, wherein the processor is further configured to: reward the air cleaning device arrangement model based on the re-measured fine dust concentration being lower than a previously measured fine dust concentration, and penalize the air cleaning device arrangement model based on the re-measured fine dust concentration being higher than the previously measured fine dust concentration. ### Claim 5 (depends on 4) The AI device of claim 4, wherein the processor is further configured to be repeatedly trained until a future reward for the air cleaning device arrangement model becomes a maximum value. ### Claim 6 (depends on 1) The AI device of claim 1, wherein the information on the map of the building is information comprising a map showing a structure of the building, and wherein the information on the fine dust distribution comprises information indicating the fine dust distribution on the map. ### Claim 7 (depends on 1) The AI device of claim 1, further comprising: a communication unit configured to communicate with a robot cleaner, wherein the communication unit receives the information on the map and the information on the fine dust distribution from the robot cleaner. ### Claim 8 An operating method of an AI device to guide an arrangement location of an air cleaning device, the operating method comprising: displaying an arrangement guide screen to guide the arrangement location of the air cleaning device; acquiring information on a map of a building and information on fine dust distribution in the building; determining the arrangement location of the air cleaning device based on the information on the map and the information on the fine dust distribution, by using an air cleaning device arrangement model to infer the arrangement location of the air cleaning device based on the information on the fine dust in the building; outputting the determined arrangement location of the air cleaning device, and displaying a map on the arrangement guide screen based on receiving a user input for a number of air cleaning devices, wherein the map on the arrangement guide screen comprises one or more indicators identifying arrangement locations of air cleaning devices, wherein the one or more indicators correspond to the number of air cleaning devices. ### Claim 9 (depends on 8) The operating method of claim 8, wherein the air cleaning device arrangement model is a model to be trained in reinforcement learning based on a deep learning algorithm or a machine learning algorithm, and wherein the reinforcement learning is performed through a Markov Decision Process (MDP). ### Claim 10 (depends on 9) The operating method of claim 9, further comprising: acquiring, as an output result of the air cleaning device arrangement model, the arrangement location of the air cleaning device from the map information and a fine dust distribution degree; and training the air cleaning device arrangement model by rewarding or penalizing the air cleaning device arrangement model based on a fine dust concentration in the building, wherein the fine dust concentration is re-measured. ### Claim 11 (depends on 10) The operating method of claim 10, further comprising: rewarding the air cleaning device arrangement model based on the re-measured fine dust concentration being lower than a previously measured fine dust concentration, and penalizing the air cleaning device arrangement model based on the re-measured fine dust concentration based higher than the previously measured fine dust concentration. ### Claim 12 (depends on 11) The operating method of claim 11, wherein the air cleaning device arrangement model is repeatedly trained until a future reward for the air cleaning device arrangement model becomes a maximum value. ### Claim 13 (depends on 8) The operating method of claim 8, wherein the information on the map of the building is information comprising a map showing a structure of the building, and wherein the information on the fine dust distribution comprises information indicating the fine dust distribution on the map. ### Claim 14 (depends on 8) The operating method of claim 8, wherein the acquiring of the information on the map of the building and the information on the fine dust distribution in the building comprises: receiving the information on the map and the information on the fine dust distribution from a robot cleaner.