Natural language interaction for smart assistant

Patent metadata

Field	Value
Publication number	US-10460215-B2
Application number	US-201715656994-A
Country	US
Kind code	B2
Filing date	Jul 21, 2017
Priority date	Feb 14, 2017
Publication date	Oct 29, 2019
Grant date	Oct 29, 2019

Abstract

A method for natural language interaction includes recording speech provided by a human user. The recorded speech is translated into a machine-readable natural language input relating to an interaction topic. An interaction timer is maintained that tracks a length of time since a last machine-readable natural language input referring to the interaction topic was translated. Based on a current value of the interaction timer being greater than an interaction engagement threshold, a message relating to the interaction topic is delivered with a first natural language phrasing that includes an interaction topic reminder. Based on the current value of the interaction timer being less than the interaction engagement threshold, the message relating to the interaction topic is delivered with a second natural language phrasing that lacks the interaction topic reminder.

First claim

The invention claimed is:

1. A method for natural language interaction, comprising:
recording speech provided by a human user;
translating the recorded speech into a machine-readable natural language input relating to an interaction topic;
maintaining an interaction timer tracking a length of time since a last machine-readable natural language input relating to the interaction topic;
based on a current value of the interaction timer being greater than an interaction engagement threshold, delivering a message relating to the interaction topic with a first natural language phrasing that includes an interaction topic reminder; or
based on the current value of the interaction timer being less than the interaction engagement threshold, delivering the message relating to the interaction topic with a second natural language phrasing that lacks the interaction topic reminder.

2. The method of claim 1 , further comprising performing natural language processing on the recorded speech provided by the human user to ascertain the interaction topic.

3. The method of claim 1 , where the interaction topic reminder includes one or more words explicitly referring to the interaction topic.

4. The method of claim 3 , where the interaction topic reminder refers to the interaction topic using at least one proper noun.

5. The method of claim 1 , where the interaction topic reminder includes a summary of a most recent interaction with the human user relating to the interaction topic.

6. The method of claim 1 , where the first natural language phrasing includes more words than the second natural language phrasing.

7. The method of claim 1 , where the second natural language phrasing includes one or more non-specific pronouns that implicitly refer to the interaction topic.

8. The method of claim 1 , where the interaction engagement threshold is dynamically adjusted based on one or more user engagement factors.

9. The method of claim 8 , where the one or more user engagement factors include the interaction topic.

10. The method of claim 8 , where the one or more user engagement factors include a current time of day.

11. The method of claim 8 , where the one or more user engagement factors include an identity of the human user.

12. The method of claim 8 , where the one or more user engagement factors include a language spoken by the human user when providing the recorded speech.

13. The method of claim 8 , where the interaction engagement threshold is reduced based on determining that the human user has left a local environment of a smart assistant device.

14. The method of claim 8 , where the interaction engagement threshold is reduced based on determining that the human user has begun a new activity since the natural language input was translated.

15. The method of claim 8 , where the interaction engagement threshold is reduced based on determining that the human user is interacting with one or more other humans.

16. A smart assistant device, comprising:
a logic processor; and
a storage device holding instructions executable by the logic processor to:
record speech provided by a human user;
translate the recorded speech into a machine-readable natural language input relating to an interaction topic;
maintain an interaction timer tracking a length of time since a last machine-readable natural language input relating to the interaction topic;
based on a current value of the interaction timer being greater than an interaction engagement threshold, deliver a message relating to the interaction topic with a first natural language phrasing that includes an interaction topic reminder; or
based on the current value of the interaction timer being less than the interaction engagement threshold, deliver the message relating to the interaction topic with a second natural language phrasing that lacks the interaction topic reminder.

17. The smart assistant device of claim 16 , where the interaction topic reminder includes one or more words explicitly referring to the interaction topic.

18. The smart assistant device of claim 17 , where the interaction topic reminder refers to the interaction topic using at least one proper noun.

19. The smart assistant device of claim 16 , where the second natural language phrasing includes one or more non-specific pronouns that implicitly refer to the interaction topic.

20. A method for natural language interaction, comprising:
recording speech provided by a human user;
translating the recorded speech into a machine-readable natural language input relating to an entity;
maintaining an interaction timer tracking a length of time since a last machine-readable natural language input referring to the entity;
based on a current value of the interaction timer being greater than an interaction engagement threshold, delivering a message relating to the entity to the human user with a first natural language phrasing, the first natural language phrasing referring to the entity with a proper noun; or
based on the current value of the interaction timer being less than the interaction engagement threshold, delivering the message relating to the entity to the human user with a second natural language phrasing, the second natural language phrasing implicitly referring to the entity with a non-specific pronoun.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Herold Keith Coleman
• Solomon Oz

Classifications

• G06F40/35

  Discourse or dialogue representation · CPC title

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

• G07C9/32

  in combination with an identity check · CPC title

• G07C9/28

  the pass enabling tracking or indicating presence · CPC title

• H04N23/611

  where the recognised objects include parts of the human body · CPC title