Robot control method and companion robot

Patent metadata

Field	Value
Publication number	US-11511436-B2
Application number	US-201916276576-A
Country	US
Kind code	B2
Filing date	Feb 14, 2019
Priority date	Aug 17, 2016
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

The present invention provides a robot control method, and the method includes: collecting interaction information of a companion target, and obtaining digital person information of a companion person (101), where the interaction information includes interaction information of a sound or an action of the companion target toward the robot, and the digital person information includes a set of digitized information of the companion person; and determining, by using the interaction information and the digital person information, a manner of interacting with the companion target (103); generating, based on the digital person information of the companion person and by using a machine learning algorithm, an interaction content corresponding to the interaction manner (105); and generating a response action toward the companion target based on the interaction manner and the interaction content (107).

First claim

What is claimed is:

1. A robot control method, comprising:
collecting interaction information of a companion target and obtaining digital person information of a companion person, wherein the interaction information comprises information of a sound or an action of the companion target toward a robot, and the digital person information comprises a set of digitized information of the companion person;
determining, based on the interaction information and the digital person information, a manner of interacting with the companion target;
generating, based on the digital person information of the companion person using a machine learning algorithm, an interaction content corresponding to the interaction manner;
generating a response action toward the companion target based on the interaction manner and the interaction content;
obtaining behavior information of the companion person in a time period prior to a current moment; and
obtaining digital person update information of the companion person by analyzing the behavior information, wherein the digital person update information is used to update the digital person information of the companion person.

2. The control method according to claim 1 ,
wherein generating, based on the digital person information of the companion person using the machine learning algorithm, the interaction content corresponding to the interaction manner comprises:
generating, based on the digital person information and the behavior information of the companion person using the machine learning algorithm, a plurality of available interaction contents corresponding to the interaction manner, and
selecting one or more interaction contents from the plurality of available interaction contents.

3. The control method according to claim 1 ,
wherein determining, based on the interaction information and the digital person information, the manner of interacting with the companion target further comprises: determining, based on the interaction information, the digital person information, and the behavior information, the manner of interacting with the companion target.

4. The control method according to claim 1 , further comprising:
before obtaining the digital person information of the companion person, adding the digital person update information with an additional weight to the digital person information to modify the digital person information based on the digital person update information.

5. The control method according to claim 4 , further comprising: adjusting a value of the additional weight to increase or decrease an impact caused by the behavior information of the companion person in the time period prior to the current moment on the digital person information.

6. The control method according to claim 1 , wherein the digital person information comprises one or more of the following types of information: personal basic information, personal experience information, values information, educational idea information, or behavior habit information; and
the determining, based on the interaction information and the digital person information, the manner of interacting with the companion target comprises:
calculating a semantic similarity between the digital person information and the interaction manner and a semantic similarity between the interaction information and the interaction manner, the semantic similarity determined using a word vector analysis, and
selecting an interaction manner with maximum similarity as the manner of interacting with the companion target.

7. The control method according to claim 1 , further comprising:
generating, based on the digital person information of the companion person, scores of a plurality of interaction contents corresponding to the interaction manner, and
selecting the interaction content from the plurality of interaction contents based on the scores.

8. The control method according to claim 7 , wherein the generating, based on the digital person information of the companion person, the scores of the plurality of interaction contents corresponding to the interaction manner comprises: generating, using a model generated by training, the scores of the plurality of interaction contents corresponding to the interaction manner, wherein the model uses the digital person information as an input, and produces the scores of the plurality of interaction contents corresponding to the interaction manner as an output.

9. The control method according to claim 1 , wherein the companion person comprises a plurality of companion persons, and the digital person information of the companion person is a weighted summation of feature information of the plurality of companion persons.

10. A robot device, comprising:
an information obtaining module configured to: collect interaction information of a companion target, and obtain digital person information of a companion person, wherein the interaction information comprises information of a sound or an action of the companion target, and the digital person information comprises a set of digitized information of the companion person;
an interaction manner generation module configured to: determine, based on the interaction information and the digital person information, a manner of interacting with the companion target, and generate, based on the digital person information of the companion person using a machine learning algorithm, an interaction content corresponding to the interaction manner; and
a response module configured to generate a response action toward the companion target based on the interaction manner and the interaction content,
wherein the information obtaining module is further configured to:
obtain behavior information of the companion person in a time period prior to a current moment, wherein the behavior information of the companion person is collected by a mobile device carried by the companion person; and
obtain digital person update information of the companion person by analyzing the behavior information, wherein the digital person update information is used to update the digital person information, and the digital person information is determined by analyzing the behavior information of the companion person or in a manual input manner.

11. The robot device according to claim 10 , wherein:
the interaction manner generation module is further configured to:
determine, based on the interaction information and the digital person information, the manner of interacting with the companion target,
generate, based on the digital person information and the behavior information of the companion person using the machine learning algorithm, a plurality of available interaction contents corresponding to the interaction manner, and
select one or more interaction contents from the plurality of available interaction contents.

12. The robot device according to claim 10 , wherein:
the interaction manner generation module is further configured to:
determine, based on the interaction information, the digital person information, and the behavior information, the manner of interacting with the companion target, and
generate, based on the digital person information of the companion person using the machine learning algorithm, the interaction content corresponding to the interaction manner.

13. The robot device according to claim 11 , wherein:
the information obtaining module is further configured to add the digital person update information with an additional weight to the digital person information to modify the digital person information by using the digital person update information.

14. The robot device according to cla

Assignees

• Huawei Tech Co Ltd

Inventors

• Yang Sixiao
• Liao Heng
• Huang Maosheng
• Wei Jiansheng
• Huo Dawei
• Sun Wenhua

Classifications

• G06N20/00

  Machine learning · CPC title

• G06N3/008 Primary

  based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour · CPC title

• G06F3/01

  Input arrangements or combined input and output arrangements for interaction between user and computer (G06F3/16 takes precedence) · CPC title

• B25J11/0005 Primary

  Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title