CANDIDATE PATH RECOMMENDATION

• US 20150308846A1
• Filed: 06/22/2015
• Published: 10/29/2015
• Est. Priority Date: 04/25/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ding, Jian Dong, Duan, Ning, Ji, Peng, Zhao, Qian Kun, Zhu, Jun
• Granted Patent: US 9,562,786 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 21/3492 employing speed data or traffic data, e.g. real-time or historical traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/444 Spatial browsing, e.g. 2D maps, 3D or virtual spaces
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

A method for recommending a candidate path includes, in response to receiving a query from a user, looking up a plurality of paths that conform to the query; with respect to a current path among the plurality of paths, obtaining behavior data of the user and behavior data of at least one other user associated with the current path; determining a recommendation indicator associated with the current path, based on the behavior data of the user and the behavior data of the at least one other user; and recommending the candidate path to the user based on at least a recommendation indicator associated with at least one of the plurality of paths.

Claims

1. A method for recommending a candidate path, comprising:

in response to receiving a query from a user, looking up, with a processor, a plurality of paths that conform to the query;

with respect to a current path among the plurality of paths, obtaining behavior data of the user and behavior data of at least one other user associated with the current path;

determining a recommendation indicator associated with the current path, based on the behavior data of the user and the behavior data of the at least one other user; and

recommending the candidate path to the user based on at least a recommendation indicator associated with at least one of the plurality of paths.

2. The method of claim 1, wherein the at least one other user is a user who has once driven on at least one part of the current path.

3. The method of claim 1, wherein the determining a recommendation indicator associated with the current path based on the behavior data of the user and the behavior data of the at least one other user comprises:

with respect to a current segment of at least one segment of the current path, determining a segment behavior parameter of the at least one other user in the current segment based on the behavior data of the at least one other user;

determining a segment recommendation indicator associated with the current segment by comparing the behavior data of the user with the segment behavior parameter; and

determining a recommendation indicator associated with the current path based on the segment recommendation indicator.

4. The method of claim 3, wherein the determining a segment behavior parameter of the at least one other user in the current segment based on the behavior data of the at least one other user comprises:

clustering the at least one other user based on at least one of profile data and the behavior data of the at least one other user;

weighting the behavior data of the at least one other user based on the clustering; and

determining the segment behavior parameter based on the weighted behavior data of the at least one other user.

5. The method of claim 4, wherein a segment behavior parameter seg_m with respect to the current segment m is determined based on the equation:

6. The method of claim 5, wherein a segment recommendation indicator Seg Rec_m associated with the segment is determined based on the equation:

7. The method of claim 6, wherein a recommendation indicator Path Rec associated with the current path is determined based the equation:

PathRec=Σ

_m=1^M Seg Rec_m, wherein M represents the number of segments in the current path.

8. The method of claim 1, wherein the recommending the candidate path to the user based on at least a recommendation indicator associated with at least one of the plurality of paths comprises:

obtaining a base priority score associated with at least one of the plurality of paths;

recommending the candidate path to the user based on the base priority score associated with at least one of the plurality of paths and a recommendation indicator associated with the at least one of the plurality of paths.

9. The method of claim 1, wherein context data of the at least one other user is similar to context data of the user, wherein the context data comprises at least one of:

time information, road information, traffic information, weather information, and vehicle type.

10. The method of claim 1, wherein:

the behavior data of the user describes counts of behaviors of the user during driving, and the behaviors comprise at least one of;

speedup information, slowdown information, overspeed behavior, and engine over rotation.