METHOD AND/OR SYSTEM FOR WALKING ROUTE RECOMMENDATION

• US 20160187151A1
• Filed: 12/30/2014
• Published: 06/30/2016
• Est. Priority Date: 12/30/2014
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Barbieri, Nicola, Quercia, Daniele
• Granted Patent: US 9,803,988 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/3446 Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
• 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

Abstract

Methods and/or systems are provided that may be utilized to recommend a contextual walking route for a number of venues, for example.

Claims

1. A method of determining a walking route for a selection of venues comprising:

generating a segment graph of the venues substantially in accordance with a spatial relationship, wherein edges of the segment graph have an associated cost; and

estimating an associated cost of the edges of the segment graph based at least in part on distance, number of turns and/or predicted usage.

2. The method of claim 1, wherein the estimating the predicted usage of venues on the edges under given contextual variables is determined by factorization machine techniques.

3. The method of claim 2, wherein the factorization machine techniques include at least one of stochastic gradient descent, alternating least-squares, and/or Markov Chain Monte Carlo inference.

4. The method of claim 1, wherein the generating the segment graph is based in part on angular segment evaluation techniques.

5. The method of claim 1, wherein the estimating the predicted usage of venues is based at least in part on usage of the venues on the edges;

usage of the edges on the same axial line; and

/or usage of other segments crossing the edges.

6. The method of claim 1, wherein the spatial relationship comprises the space syntax framework.

7. The method of claim 1, wherein the estimating the distance of edges on the walking route further comprises weighting the distance of the edges by appeal of venues located on the edges.

8. The method of claim 1, further comprising generating a contextual route recommendation based at least in part on the estimating the associated cost of the edges of the segment graph.

9. A system comprising:

a computing device to generate a segment graph of venues substantially in accordance with a spatial relationship and to estimate an associated cost of edges of the segment graph;

wherein the associated cost of the edges to be based at least in part on distance, number of turns and/or predicted venue appeal.

10. The system of claim 9, wherein the predicted appeal of venues on the edges under given contextual variables is to be determined by factorization machine techniques.

11. The system of claim 10, wherein the factorization machine techniques include at least one of stochastic gradient descent, alternating least-squares, and/or Markov Chain Monte Carlo inference.

12. The system of claim 9, wherein the segment graph is to be based at least in part on angular segment evaluation techniques.

13. The system of claim 9, wherein the predicted usage of venues is to be based at least in part on usage of the venues on the edges;

usage of the edges on the same axial line; and

/or usage of other segments crossing the edges.

14. The system of claim 9, wherein the spatial relationship is to comprise the space syntax framework.

estimating an associated cost of the edges of the segment graph based at least in part on distance comprises means for weighting distance of the edges by appeal of venues located on the edges.

15. The system of claim 9, wherein an associated cost of the edges of the segment graph to be based at least in part on distance is to comprise distance of the edges to be weighed substantially in accordance with appeal of venues located on the edges.

16. An apparatus comprising:

means for generating a segment graph of the venues substantially in accordance with a spatial relationship, wherein edges of the segment graph have an associated cost; and

means estimating an associated cost of the edges of the segment graph based at least in part on distance, number of turns and/or predicted usage.

17. The apparatus of claim 16, wherein the means for estimating the predicted usage of venues comprises:

means for estimating usage of the venues on the edges;

means for estimating usage of the edges on the same axial line; and

/or means for estimating usage of other segments crossing the edges.

18. The apparatus of claim 16, wherein the spatial relationship comprises the space syntax framework.

19. The apparatus of claim 16, wherein the means for generating a segment graph comprises means for angular segment evaluation.

20. The apparatus of claim 16, wherein the means estimating an associated cost of the edges of the segment graph based at least in part on distance comprises means for weighting distance of the edges by appeal of venues located on the edges.