Navigation system with classification mechanism and method of operation thereof

• US 9,798,821 B2
• Filed: 12/05/2014
• Issued: 10/24/2017
• Est. Priority Date: 12/09/2013
• Status: Active Grant

• Current Assignee: TeleNav Incorporated
• Original Assignee: TeleNav Incorporated
• Inventors: Yang, Jianyi, Maddali, Kumar
• Primary Examiner(s): Anwari, Maceeh
• Application Number:
  US14/562,461
• Publication Number:
  US 20150160017A1
• Time in Patent Office: 1,054 Days
• Field of Search: 701400
• CPC Class Codes: G01C 21/3679 Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities G01C21/3611 takes precedence
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

A method of operation of a navigation system includes: generating a signal weight with a control unit based on a feature extracted from a user activity; generating an activity model based on the signal weight for representing the feature as a positive weight or a negative weight depending on an activity type, a category of interest, or a combination thereof; classifying a user entry based on comparing the feature of the user entry to the feature represented in the activity model; and determining a user'"'"'s intention based on the user entry classified for presenting a point of interest on a device.

Claims

1. A method of operation of a navigation system comprising:

generating a signal weight with a control unit based on a feature extracted from a user activity;

generating an activity model based on the signal weight for representing the feature as a positive weight, representing the signal weight above a weight threshold, or a negative weight, representing the signal weight below the weight threshold, depending on an activity type, a category of interest, or a combination thereof;

classifying a user entry newly received, including multiple instances of the feature including the activity type and the category of interest, based on comparing the activity type and the category of interest to each other for identifying the feature with the higher instance of the signal weight to compare with the activity model; and

determining a user'"'"'s intention based on the user entry classified for presenting a point of interest on a device.

2. The method as claimed in claim 1 further comprising adjusting the signal weight of the feature relative to each instance of a plurality of the activity type, the category of interest, or a combination thereof.

3. The method as claimed in claim 1 wherein generating the signal weight includes generating the signal weight for a same instance of the feature as the positive weight for one instance of the activity type and the negative weight for another instance of the activity type.

4. The method as claimed in claim 1 wherein generating the signal weight includes generating the signal weight for a same instance of the feature as the positive weight for one instance of the category of interest and the negative weight for another instance of the category of interest.

5. The method as claimed in claim 1 further comprising determining a weight priority of a plurality of the signal weight based on a travel context for identifying the user'"'"'s intention for the user activity in a given instance of the travel context.

6. The method as claimed in claim 1 further comprising determining an entry relevancy of a plurality of the feature based on an entry pattern, the category of interest, an activity history, or a combination thereof.

7. The method as claimed in claim 1 further comprising determining a weight priority based on a weight type of the signal weight generated for the activity type, the category of interest, or a combination thereof.

8. The method as claimed in claim 1 further comprising determining a weight priority based on a travel context for prioritizing one instance of the signal weight over another instance of the signal weight in a given instance of the travel context.

9. The method as claimed in claim 1 further comprising identifying an entry category of the user activity based on the activity type subsequent to the user activity.

10. The method as claimed in claim 1 further comprising calculating a category score based on the signal weight of the feature for the category of interest.

11. A navigation system comprising:

a control unit for;

generating a signal weight with a control unit based on a feature extracted from a user activity,

generating an activity model based on the signal weight for representing the feature as a positive weight, representing the signal weight above a weight threshold, or a negative weight, representing the signal weight below the weight threshold, depending on an activity type, a category of interest, or a combination thereof,

classifying a user entry newly received, including multiple instances of the feature including the activity type and the category of interest, based on comparing the activity type and the category of interest to each other for identifying the feature with the higher instance of the signal weight to compare with the activity model,

determining a user'"'"'s intention based on the user entry classified, and

a communication interface, coupled to the control unit, for communicating the user'"'"'s intention for displaying a point of interest on a device.

12. The system as claimed in claim 11 wherein the control unit is for adjusting the signal weight of the feature relative to each instance of a plurality of the activity type, the category of interest, or a combination thereof.

13. The system as claimed in claim 11 wherein the control unit is for generating the signal weight for a same instance of the feature as the positive weight for one instance of the activity type and the negative weight for another instance of the activity type.

14. The system as claimed in claim 11 wherein the control unit is for generating the signal weight for a same instance of the feature as the positive weight for one instance of the category of interest and the negative weight for another instance of the category of interest.

15. The system as claimed in claim 11 wherein the control unit is for determining a weight priority of a plurality of the signal weight based on a travel context for identifying the user'"'"'s intention for the user activity in a given instance of the travel context.

16. A non-transitory computer readable medium including instructions for execution, the instructions comprising:

generating a signal weight based on a feature extracted from a user activity;

generating an activity model based on the signal weight for representing the feature as a positive weight, representing the signal weight above a weight threshold, or a negative weight, representing the signal weight below the weight threshold, depending on an activity type, a category of interest, or a combination thereof;

classifying a user entry newly received, including multiple instances of the feature including the activity type and the category of interest, based on comparing the activity type and the category of interest to each other for identifying the feature with the higher instance of the signal weight to compare with activity model; and

determining a user'"'"'s intention based on the user entry classified for presenting a point of interest on a device.

17. The non-transitory computer readable medium as claimed in claim 16 further comprising adjusting the signal weight of the feature relative to each instance of a plurality of the activity type, the category of interest, or a combination thereof.

18. The non-transitory computer readable medium as claimed in claim 16 wherein generating the signal weight includes generating the signal weight for a same instance of the feature as the positive weight for one instance of the activity type and the negative weight for another instance of the activity type.

19. The non-transitory computer readable medium as claimed in claim 16 wherein generating the signal weight includes generating the signal weight for a same instance of the feature as the positive weight for one instance of the category of interest and the negative weight for another instance of the category of interest.

20. The non-transitory computer readable medium as claimed in claim 16 further comprising determining a weight priority of a plurality of the signal weight based on a travel context for identifying the user'"'"'s intention for the user activity in a given instance of the travel context.