Translation of verbal directions into a list of maneuvers

Patent metadata

Field	Value
Publication number	US-11573094-B2
Application number	US-202117505969-A
Country	US
Kind code	B2
Filing date	Oct 20, 2021
Priority date	Sep 6, 2016
Publication date	Feb 7, 2023
Grant date	Feb 7, 2023

Abstract

Natural language directions are received and a set of maneuver/context pairs are generated based upon the natural language directions. The set of maneuver/context pairs are provided to a routing engine to obtain route information based upon the set of maneuver/context pairs. The route information is provided to an output system for surfacing to a user.

First claim

What is claimed is:

1. A method performed by a computing system, the method comprising:
receiving a natural language input;
generating one or more natural language instructions based on identifying linguistic units in the natural language input and performing natural language processing on the linguistic units;
identifying, based on the one or more natural language instructions, an end point for a route and a trigger that comprises a navigation maneuver and corresponding context information, the corresponding context information being indicative of a location corresponding to performance of the navigation maneuver;
generating route information that represents a portion of the route that includes the trigger and the end point; and
rendering the route information.

2. The method of claim 1 , wherein performing natural language processing on the linguistic units comprises identifying semantic meaning of the linguistic units.

3. The method of claim 1 , and further comprising identifying, based on the natural language input, a plurality of natural language instructions.

4. The method of claim 3 , wherein the plurality of natural language instructions are indicative of a sequential set of navigation maneuvers to be performed along the route, and the location comprises a waypoint along the route.

5. The method of claim 1 , wherein the trigger comprises a first trigger, and further comprising:
identifying, based on the one or more natural language instructions, an ordered set of triggers comprising the first trigger and a second trigger; and
generating route information representing a portion of the route between the first and second triggers.

6. The method of claim 1 , and further comprising:
identifying a geographic limiter in the one or more natural language instructions; and
generating the trigger to include the geographic limiter, along with the navigation maneuver and the corresponding context information.

7. The method of claim 1 , and further comprising:
performing disambiguation of the context information and the geographic limiter to identify a geographic location corresponding to the context information and the geographic limiter.

8. The method of claim 1 , and further comprising:
identifying a plurality of natural language instructions, each indicative of a different navigation maneuver to be performed along the route;
matching each of the plurality of natural language instructions with a pre-defined navigation maneuver;
identifying context information corresponding to each of the pre-defined navigation maneuvers;
generating, as a set of ordered triggers, a set of pairs of the pre-defined navigation maneuvers and corresponding context information; and
generating route information that identifies a portion of the route between successive pairs of triggers in the set of ordered triggers.

9. The method of claim 1 , and further comprising:
rendering the route information as a set of turn-by-turn navigation instructions.

10. The method of claim 9 , wherein the natural language input comprises a textual user input.

11. The method of claim 9 , wherein the natural language input comprises a speech user input.

12. The method of claim 11 , wherein rendering comprises:
rendering a portion of the speech input in association with the turn-by-turn navigation instructions.

13. The method of claim 12 , wherein rendering a portion of the speech input comprises:
obtaining a snippet from the speech input; and
audibly rendering the snippet to the user in association with a corresponding navigation instruction in the set of turn-by-turn navigation instructions.

14. A computing system, comprising:
a processor; and
memory storing instructions executable the processor, wherein the instructions, when executed, cause the computing system to:
receive a natural language input;
generate one or more natural language instructions based on identifying linguistic units in the natural language input and performing natural language processing on the linguistic units;
identify, based on the one or more natural language instructions, an end point for a route and a trigger that comprises a navigation maneuver and corresponding context information, the corresponding context information being indicative of a location corresponding to performance of the navigation maneuver;
generate route information that represents a portion of the route that includes the trigger and the end point; and
render the route information.

15. The computing system of claim 14 , wherein the one or more natural language instructions are indicative of a sequential set of navigation maneuvers to be performed along the route, and the location comprises a waypoint along the route.

16. The computing system of claim 14 , wherein the trigger comprises a first trigger, and the instructions, when executed, cause the computing system to:
identify, based on the one or more natural language instructions, an ordered set of triggers comprising the first trigger and a second trigger; and
generate route information representing a portion of the route between the first and second triggers.

17. The computing system of claim 14 , wherein the instructions, when executed, cause the computing system to:
identify a geographic limiter in the one or more natural language instructions; and
generate the trigger to include the geographic limiter, along with the navigation maneuver and the corresponding context information.

18. The computing system of claim 14 , wherein the instructions, when executed, cause the computing system to:
identify a plurality of natural language instructions, each indicative of a different navigation maneuver to be performed along the route;
match each of the plurality of natural language instructions with a pre-defined navigation maneuver;
identify context information corresponding to each of the pre-defined navigation maneuvers;
generate, as a set of ordered triggers, a set of pairs of the pre-defined navigation maneuvers and corresponding context information; and
generate route information that identifies a portion of the route between successive pairs of triggers in the set of ordered triggers.

19. The computing system of claim 14 , wherein the instructions, when executed, cause the computing system to
render the route information as a set of turn-by-turn navigation instructions.

20. The computing system of claim 19 , wherein the natural language input comprises at least one of a textual user input or a speech user input, and the instructions, when executed, cause the computing system to:
render a portion of the natural language input in association with the turn-by-turn navigation instructions.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Salowitz Elizabeth P
• Grochocki Jr David
• West Jeff

Classifications

• G01C21/3608 Primary

  using speech input, e.g. using speech recognition · CPC title

• G06F40/30

  Semantic analysis · CPC title