Charging method and terminal based on user usage habit model

Patent metadata

Field	Value
Publication number	US-11545703-B2
Application number	US-201816205418-A
Country	US
Kind code	B2
Filing date	Nov 30, 2018
Priority date	Jun 1, 2016
Publication date	Jan 3, 2023
Grant date	Jan 3, 2023

Abstract

The present disclosure provides a charging method and a terminal. The method includes: automatically learning, by the terminal, historical data by using a machine learning algorithm, to establish a habit model of a user, and matching a current time with the usage habit model of the user to determine a current charging intention of the user, so as to determine a charging mode according to the charging intention. By means of the technical solutions, a charging requirement of a user can be effectively identified, and on-demand charging can be implemented. This improves user experience while avoiding a battery life decrease caused by frequent fast charging.

First claim

What is claimed is:

1. A charging method, wherein the method comprises:
training, by using a preset machine learning algorithm, historical data that a user uses a terminal to obtain a usage habit model of the user;
obtaining a location of the terminal and a current time in response to detecting that a connection is established between the terminal and a charger;
matching the location of the terminal and the current time with the usage habit model of the user to obtain a charging intention of the user;
determining a charging mode corresponding to the charging intention of the user; and
charging the terminal according to the charging mode.

2. The method according to claim 1 , wherein the historical data that the user uses the terminal comprises historical location information of the terminal.

3. The method according to claim 2 , wherein before training, by using the preset machine learning algorithm, the historical data that the user uses the terminal, the method further comprises:
obtaining the historical data that the user uses the terminal within a preset time period; and
wherein training, by using the preset machine learning algorithm, the historical data that the user uses the terminal comprises:
analyzing the historical data by using the preset machine learning algorithm; and
correcting an analysis result, and setting the corrected analysis result to the usage habit model of the user.

4. The method according to claim 1 ,
wherein matching the location of the terminal and the current time with the usage habit model of the user to obtain the charging intention of the user comprises:
determining the charging intention of the user according to the current time, the location of the terminal, and the usage habit model of the user.

5. The method according to claim 4 , wherein before matching the location of the terminal and the current time with the usage habit model of the user to obtain the charging intention of the user, the method further comprises:
obtaining information about an environment in which the terminal is located; and
wherein matching the location of the terminal and the current time with the usage habit model of the user to obtain the charging intention of the user comprises:
determining the charging intention of the user according to the current time, the location of the terminal, the information about the environment in which the terminal is located, and the usage habit model of the user.

6. The method according to claim 1 , wherein after determining the charging mode corresponding to the charging intention of the user, the method further comprises:
sending a charging mode confirmation request to the user, wherein the charging mode confirmation request is used to ask the user whether charging is performed according to the charging mode; and
in response to receiving an instruction that the user confirms that charging is performed according to the charging mode, charging the terminal according to the charging mode.

7. The method according to claim 6 , wherein the method further comprises:
in response to receiving a charging mode change instruction entered by the user, prompting the user to select a new charging mode; and
in response to receiving a user-selected charging mode:
performing charging according to the user-selected charging mode; and
correcting a usage habit pattern of the user according to the user-selected charging mode.

8. The method according to claim 1 , wherein the method further comprises:
when obtaining the usage habit model of the user fails, determining whether the current time is in a preset sleep time period;
calculating a length of time available for charging according to the current time and the preset sleep time period when the current time is in the preset sleep time period; and
determining the charging mode according to the length of time available for charging.

9. The method according to claim 1 , wherein the method further comprises:
when obtaining the usage habit model of the user fails, obtaining a remaining electricity quantity and a current location of the terminal; and
when the remaining electricity quantity is less than a first preset threshold and the current location does not belong to a preset location set, determining that the charging mode is a fast charging mode.

10. The method according to claim 1 , wherein the method further comprises:
when obtaining the usage habit model of the user fails, obtaining a remaining electricity quantity of the terminal, and detecting whether there is a running application program in the terminal; and
when the remaining electricity quantity is less than a second preset threshold and there is a running application program, determining that the charging mode is a fast charging mode.

11. The method according to claim 1 , wherein the current time is input into the usage habit model of the user to obtain the charging intention of the user, and the preset machine learning algorithm include at least one of a classification algorithm, a clustering algorithm, a regression algorithm, an enhanced learning algorithm, a migration learning algorithm, or a deep learning algorithm.

12. A terminal, wherein the terminal comprises:
at least one processor; and
a non-transitory computer-readable storage medium coupled to the at least one processor and storing programming instructions for execution by the at least one processor, the programming instructions instruct the at least one processor to:
train, by using a preset machine learning algorithm, historical data that a user uses the terminal to obtain a usage habit model of the user;
obtain a location of the terminal and a current time in response to detecting that a connection is established between the terminal and a charger;
match the location of the terminal and the current time with the usage habit model of the user to obtain a charging intention of the user;
determine a charging mode corresponding to the charging intention of the user; and
instruct a charger to charge the terminal according to the charging mode.

13. The terminal according to claim 12 , wherein the historical data that the user uses the terminal comprises historical location information of the terminal.

14. The terminal according to claim 13 , wherein the programming instructions instruct the at least one processor to:
obtain the historical data that the user uses the terminal within a preset time period;
analyze the historical data by using the preset machine learning algorithm to obtain an analysis result; and
correct the analysis result, and set the corrected analysis result to the usage habit model of the user.

15. The terminal according to claim 12 , wherein the programming instructions instruct the at least one processor to:
determine the charging intention of the user according to the current time, the location of the terminal, and the usage habit model of the user.

16. The terminal according to claim 15 , wherein the programming instructions instruct the at least one processor to:
obtain information about an environment in which the terminal is located; and
determine the charging intention of the user according to the current time, the location of the terminal, the information about the environment in which the terminal is located, and the usage habit model of the user.

17. The terminal according to claim 12 , wherein the programming instructions instruct the at least one processor to:
send a charging mode confirmation request to the user, wherein the charging mode confirmation request is used to ask the user whether

Assignees

• Huawei Tech Co Ltd

Inventors

• Huo Dawei
• Ding Jie
• Wang Pinghua
• Li Hui
• Ma Jinbo

Classifications

• H01M10/44 Primary

  Methods for charging or discharging (circuits for charging H02J7/00) · CPC title

• Y02E60/10

  Energy storage using batteries · CPC title

• H02J7/04

  Regulation of charging current or voltage · CPC title

• G06N20/00

  Machine learning · CPC title

• H02J7/92

  with prioritisation of loads or sources · CPC title