Intelligent washing machine and method for controlling washing timing using the same

Patent metadata

Field	Value
Publication number	US-11245544-B2
Application number	US-201916588450-A
Country	US
Kind code	B2
Filing date	Sep 30, 2019
Priority date	Sep 2, 2019
Publication date	Feb 8, 2022
Grant date	Feb 8, 2022

Abstract

According to an embodiment of the present invention, a method of controlling wash timing using an intelligent washer comprises determining to perform a wash, calculating a required time for the wash, predicting a return time of the user, and determining a start time of the wash to terminate the wash corresponding to the return time. According to an embodiment, the washer may be related to artificial intelligence (AI) modules, unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

First claim

What is claimed is:

1. A method of controlling wash timing of a washer placed in a user space when a user is absent, the method comprising:
determining to perform a wash;
calculating a required wash time for the wash;
predicting a return time of the user; and
determining a wash start time of the wash to terminate the wash corresponding to the return time,
wherein predicting the return time includes:
comparing the required wash time with a required return time, and
predicting the return time by learning accumulated return times when the required wash time is longer than the required return time.

2. The method of claim 1 , wherein the wash is determined to be performed when an amount of laundry in the washer is a preset threshold or more.

3. The method of claim 2 , wherein calculating the required wash time includes:
determining the amount of laundry;
obtaining laundry classification information for the laundry; and
calculating the required wash time by learning the amount of the laundry and the laundry classification information.

4. The method of claim 1 , wherein predicting the return time includes performing learning using real-time traffic information and global positioning system (GPS) information for the user as an input value of an artificial intelligence (AI) learning model when the required wash time is shorter than the required return time.

5. The method of claim 4 , wherein predicting the return time includes performing learning using the GPS information matching a particular time per day, as the input value of the AI learning model.

6. The method of claim 5 , wherein determining the wash start time includes performing learning using weight information of laundry, the GPS information matching the particular time per day, and information for personnel in the user space, as the input value of the AI learning model.

7. The method of claim 6 , further comprising:
starting the wash at the determined wash start time;
monitoring a variation in the predicted return time; and
changing a wash condition when the variation in the predicted return time is a preset threshold or more.

8. The method of claim 7 , wherein changing the wash condition includes, when the predicted return time comes later, performing a rinse cycle for a longer time.

9. The method of claim 7 , wherein changing the wash condition includes, when the predicted return time comes earlier, performing a spin cycle for a shorter time.

10. The method of claim 6 , wherein determining the wash start time includes receiving, from a network, downlink control information (DCI) used for scheduling transmission of information for the input value of the AI learning model, and
wherein the information for the input value of the AI learning model is transmitted to the network based on the DCI.

11. The method of claim 10 , further comprising performing an initial access procedure with the network based on a synchronization signal block (SSB),
wherein the information for the input value of the AI learning model is transmitted to the network via a physical uplink shared channel (PUSCH), and
wherein dedicated demodulation reference signals (DM-RSs) of the SSB and the PUSCH are quasi co-located (QCL) for QCL type D.

Assignees

• Lg Electronics Inc

Inventors

• Lee Myunghee

Classifications

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/047

  Probabilistic or stochastic networks · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/09

  Supervised learning · CPC title