Learning and predictive navigation system

• US 20160195405A1
• Filed: 12/23/2015
• Published: 07/07/2016
• Est. Priority Date: 01/05/2015
• Status: Active Grant

• Current Assignee: Harman International Industries Incorporated (Samsung Electronics Co. Ltd.)
• Original Assignee: Harman International Industries Incorporated (Samsung Electronics Co. Ltd.)
• Inventors: Kreifeldt, Richard Allen
• Granted Patent: US 11,162,806 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement

Abstract

Various embodiments provide techniques for performing an operation that includes receiving a request specifying one or more geospatial commands. The operation further includes generating a navigation query based on the one or more geospatial commands and using a user-specific geospatial command model generated based on collected user behavior and feedback. The operation also includes executing the navigation query against a navigation database to determine route and destination information.

Claims

1. A non-transitory computer-readable storage medium including instructions that, when executed by a processor, cause the processor to perform the steps of:

receiving a request specifying one or more geospatial commands;

generating a navigation query based on the one or more geospatial commands and using a user-specific geospatial command model generated based on at least one of collected user behavior and feedback data; and

executing the generated navigation query against a navigation database to determine route and destination information.

2. The non-transitory computer-readable medium of claim 1, wherein the collected user behavior and feedback data comprises data describing user navigational preferences.

3. The non-transitory computer-readable medium of claim 2, further comprising the steps of:

generating the user-specific geospatial command model, comprising;

generating an initial user-specific geospatial command model;

transmitting the initial user-specific geospatial command model to a remote server, wherein the remote server is configured to generate a refined user-specific geospatial command model using supplemental user information; and

receiving the refined user-specific geospatial command model from the remote server, wherein the refined user-specific geospatial command model is used to generate the navigation query.

4. The non-transitory computer-readable medium of claim 2, wherein the collected user behavior and feedback data further comprises at least one of:

(i) destination history information specifying a plurality of previously visited destinations;

(ii) parking preference data indicating a user preference for one or more types of parking;

(iii) social media data representing interactions on one or more social media sites; and

(iv) driving preference data indicating a preference for one or more types of roads.

5. The non-transitory computer-readable medium of claim 2, further comprising the steps of:

generating the user-specific geospatial command model, comprising;

receiving descriptive user metadata describing a user associated with the collected user behavior and feedback data, the descriptive user metadata comprising at least one of user age information, user geolocation information, and user navigational preference information;

classifying the user into one of a plurality of affinity groups, based on the received descriptive user metadata; and

generating the user-specific geospatial command model, based on a second geospatial command model corresponding to the affinity group the user was classified into.

6. The non-transitory computer-readable medium of claim 5, further comprising the step of refining an aspect of the user-specific geospatial command model, based on the collected user behavior and feedback data.

7. The non-transitory computer-readable medium of claim 6, further comprising the step of refining an aspect of the second geospatial command model corresponding to the affinity group, based on the refined user-specific geospatial command model.

8. The non-transitory computer-readable medium of claim 1, further comprising the step of determining user profile information describing previously visited destinations and route preferences, wherein generating the navigation query further uses the user profile information to determine the route and destination information.

9. The non-transitory computer-readable medium of claim 1, further comprising the steps of:

presenting a plurality of route and destination options; and

receiving a user selection of one or the plurality of route and destination options for use in creating a current travel plan.

10. The non-transitory computer-readable medium of claim 1, further comprising the step of determining a predicted destination for the navigation query, based on user information.

11. The non-transitory computer-readable medium of claim 10, wherein generating the navigation query comprises determining a distance relative to the determined predicted destination, using the user-specific geospatial command model.

12. A navigation device, comprising:

a memory that includes a navigation component; and

a processor that is coupled to the memory and, upon executing the navigation component, is configured to;

identify one or more geospatial commands;

generate a navigation query based on the one or more geospatial commands and using a user-specific geospatial command model generated based on collected user behavior and feedback data; and

execute the navigation query against a navigation database to determine route and destination information.

13. The navigation device of claim 12, wherein the collected user behavior and feedback data comprises data describing user navigational preferences.

14. The navigation device of claim 13, wherein the processor is further configured to:

generate the user-specific geospatial command model, comprising;

generating an initial user-specific geospatial command model;

transmitting the initial user-specific geospatial command model to a remote server, wherein the remote server is configured to generate a refined user-specific geospatial command model using supplemental user information; and

receiving the refined user-specific geospatial command model from the remote server, wherein the refined user-specific geospatial command model is used to generate the navigation query.

15. The navigation device of claim 13, wherein the collected user behavior and feedback data further comprises at least one of:

(i) destination history information specifying a plurality of previously visited destinations;

(ii) parking preference data indicating a user preference for one or more types of parking;

(iii) social media data representing interactions on one or more social media sites; and

(iv) driving preference data indicating a preference for one or more types of roads.

16. The navigation device of claim 13, wherein the processor is further configured to:

generate the user-specific geospatial command model, comprising;

receiving descriptive user metadata describing a user associated with the collected user behavior and feedback data, the descriptive user metadata comprising at least one of user age information, user geolocation information, and user navigational preference information;

classify the user into one of a plurality of affinity groups, based on the received descriptive user metadata; and

generate the user-specific geospatial command model, based on a second geospatial command model corresponding to the affinity group the user was classified into.

17. The navigation device of claim 16, the wherein the processor is further configured to:

refine an aspect of the user-specific geospatial command model, based on the collected user behavior and feedback data; and

refine an aspect of the second geospatial command model corresponding to the affinity group, based on the refined user-specific geospatial command model.

18. The navigation device of claim 12, wherein the processor is further configured to determine a predicted destination for the navigation query, based on user information.

19. The navigation device of claim 18, wherein generating the navigation query further comprises determining a distance relative to the determined predicted destination, using the user-specific geospatial command model.

20. A method, comprising:

receiving one or more geospatial commands;

generating, by operation of one or more computer processors, a navigation query based on at least one of the one or more geospatial commands and a user-specific geospatial command model; and

executing the navigation query to determine route and destination information.