System and method for recommending pleasant routes from the sentiment of geo-tagged photographs

Patent metadata

Field	Value
Publication number	US-2018238692-A1
Application number	US-201815948021-A
Country	US
Kind code	A1
Filing date	Apr 9, 2018
Priority date	May 7, 2014
Publication date	Aug 23, 2018
Grant date	—

Abstract

A system and method generates and recommends a short and pleasant path between a source s and destination d in a geo-location such as a city or city center. The routes are not only short but emotionally pleasant, offering an engaging user experience, going beyond just showing paths on a map.

First claim

1 . A method, comprising:
determining a route between a source address and a destination address within a geographic location by performing:
identifying M shortest paths connecting the source address and the destination address;
iteratively computing an average rank for locations within m paths, wherein m is less than M;
at each iteration, recording a path with a best average rank; and
terminating when the best average rank improves less than a predetermined amount; and
presenting the route on a map of the geographic location.

2 . The method of claim 1 , comprising selecting the route from amongst two or more routes comprising the route and a second route.

3 . The method of claim 1 , comprising building a location graph of the geographic location with nodes representing sites within the geographic location.

4 . The method of claim 3 , comprising computing one or more pleasantness scores for the nodes.

5 . The method of claim 4 , wherein computing the one or more pleasantness scores comprises retrieving data about the nodes from a crowdsourcing website.

6 . The method of claim 4 , wherein computing the one or more pleasantness scores comprises accessing geo-tagged photos of the geographic location.

7 . The method of claim 6 , comprising processing tags associated with the geo-tagged photos to capture one or more words expressing at least one of emotional or cognitive perceptions of a node.

8 . The method of claim 4 , wherein computing the one or more pleasantness scores comprises:
computing a first pleasantness score for a first node of the nodes; and computing a second pleasantness score for a second node of the nodes.

9 . An information processing system, comprising:
a processor device; and a memory operably coupled with the processor device, the memory comprising computer-executable instructions causing a computer to perform:
determining a route between a source address and a destination address within a geographic location by performing:
identifying M shortest paths connecting the source address and the destination address;
iteratively computing an average rank for locations within m paths, wherein m is less than M;
at each iteration, recording a path with a best average rank; and
terminating when the best average rank improves less than a predetermined amount; and

presenting the route on a map of the geographic location.

10 . The information processing system of claim 9 , wherein the computer-executable instructions comprise selecting the route from amongst two or more routes comprising the route and a second route.

11 . The information processing system of claim 9 , wherein the computer-executable instructions comprise building a location graph of the geographic location with nodes representing sites within the geographic location.

12 . The information processing system of claim 11 , wherein the computer-executable instructions comprise computing one or more pleasantness scores for the nodes.

13 . The information processing system of claim 12 , wherein computing the one or more pleasantness scores comprises retrieving data about the nodes from a crowdsourcing website.

14 . The information processing system of claim 12 , wherein computing the one or more pleasantness scores comprises accessing geo-tagged photos of the geographic location.

15 . The information processing system of claim 14 , wherein the computer-executable instructions comprise processing tags associated with the geo-tagged photos to capture one or more words expressing at least one of emotional or cognitive perceptions of a node.

16 . A computer program product comprising a non-transitory computer-readable storage medium with computer-executable instructions stored thereon, the computer-executable instructions comprising:
building a location graph of a geographic location with nodes representing sites within the geographic location, wherein building the location graph comprises:
building a geographical bounding box for the geographic location;
dividing the geographical bounding box into a plurality of cells, wherein a size of each cell is associated with a walkable distance; and
linking geographic neighboring cells of the plurality of cells to form the location graph;
computing one or more pleasantness scores for the nodes; and presenting a route on a map of the geographic location based upon the location graph and the one or more pleasantness scores.

17 . The computer program product of claim 16 , wherein the computer-executable instructions for computing the one or more pleasantness scores comprises retrieving data about the nodes from a crowdsourcing website.

18 . The computer program product of claim 16 , wherein the computer-executable instructions for computing the one or more pleasantness scores is based upon one or more words expressing emotional perceptions of a node.

19 . The computer program product of claim 16 , wherein the computer-executable instructions for computing the one or more pleasantness scores is based upon one or more words expressing cognitive perceptions of a node.

20 . The computer program product of claim 16 , wherein the route is from a source address to a destination address.

Assignees

• Oath Inc

Inventors

• Aiello Luca Maria
• Quercia Daniele
• Schifanella Rossano

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N7/005

  Physics · mapped topic

• G01C21/36

  Input/output arrangements for on-board computers · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G01C21/3407 Primary

  specially adapted for specific applications · CPC title