Snippet Extraction and Ranking

• US 20110302162A1
• Filed: 06/08/2010
• Published: 12/08/2011
• Est. Priority Date: 06/08/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Xiao, Rong, Wang, Changhu, Cai, Rui, Zhang, Lei, Hao, Qiang
• Granted Patent: US 8,954,425 B2
• Time in Patent Office: Days
• US Class Current: 707/724
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering

Abstract

Described herein is a technology that facilitates efficient automated mining of topic-related aspects of user-generated content based on automated analysis of the user-generated content. Locations are automatically learned based on dividing documents into document segments, and decomposing the segments into local topics and global topics. Techniques are described that facilitate automatically extracting snippets. These techniques include, for example, computer annotating travelogues with learned tags and images, performing topic learning to obtain an interest model, performing location matching based on the interest model, calculating geographic and semantic relevance scores, ranking snippets based on the geographic and semantic relevance scores, and searching snippets with a “location+context term” query.

Claims

1. A computer-readable medium having computer executable instructions encoded thereon, the computer executable instructions for execution by a processor to perform location-related mining operations, the operations comprising:

receiving a query comprising a location and a context term;

identifying at least one snippet, wherein a snippet comprises a segment of user-generated content;

extracting the location from the at least one snippet;

mining the context term from the at least one snippet;

calculating a geographic relevance score for the at least one snippet based at least on the location;

calculating a semantic relevance score for the at least one snippet based at least on the context term;

computing a snippet score based at least on the geographic relevance score and the semantic relevance score for the at least one snippet; and

ranking the at least one snippet and at least one other snippet based at least on the snippet score.

2. A computer-readable medium as recited in claim 1, wherein the context term comprises one of a style word or keyword corresponding to a local topic.

3. A computer-readable medium as recited in claim 1, wherein the query is received in a form of location-representative knowledge from an automated knowledge mining operation.

4. A computer-readable medium as recited in claim 1, wherein the at least one snippet originates from a travelogue.

5. A computer-readable medium as recited in claim 1, the operations further comprising building a snippet collection from one or more travelogues.

6. A computer-readable medium as recited in claim 5, wherein building a snippet collection from one or more travelogues comprises:

identifying one or more locations mentioned in one or more travelogues;

segmenting the one or more travelogues into one or more snippets, each snippet containing at least one location identified;

determining whether the one or more snippets meet a length constraint;

compiling the snippet collection from the one or more snippets that meet the length constraint.

7. A computer-readable medium as recited in claim 6, wherein the length constraint comprises one or both of a minimum number of words or a maximum number of words.

8. A computer-readable medium as recited in claim 1, the operations further comprising enriching a travelogue with one or more images based at least on matching the location and the context term.

9. A computer-readable medium as recited in claim 1, wherein the at least one snippet is represented by at least one location, words the at least one snippet comprises other than locations, and a snippet quality score.

10. A method comprising:

identifying a travelogue for location-related mining;

decomposing the travelogue to identify a location and a context term;

extracting the location from the travelogue as decomposed;

mining the context term from the travelogue as decomposed;

creating a geo-snippet comprising the location and the context term;

obtaining a geographic relevance score corresponding to the geo-snippet;

obtaining a semantic relevance score corresponding to the geo-snippet; and

computing a snippet score corresponding to the geo-snippet based at least on the geographic relevance score and the semantic relevance score.

11. A method as recited in claim 10, further comprising ranking a plurality of geo-snippets based at least on the snippet score.

13. A method as recited in claim 10, further comprising building at least one tag from information comprising one or both of the location or the context term.

14. A computer-readable medium having computer-executable instructions encoded thereon to program a computer to perform the method of claim 10.

15. A computer-implemented method comprising:

identifying at least one snippet;

extracting a location from the at least one snippet;

mining a context term from the at least one snippet;

calculating a geographic relevance score for the at least one snippet based at least on the location;

calculating a semantic relevance score for the at least one snippet based at least on the context term;

computing a snippet score based at least on the geographic relevance score and the semantic relevance score for the at least one snippet; and

ranking the at least one snippet based at least on the snippet score.

16. A method as recited in claim 15, wherein the semantic relevance score is calculated based at least on a sum of distances in a topic space from a query word to a plurality of unique words contained in the at least one snippet.

17. A method as recited in claim 15, wherein computing the snippet score based at least on the geographic relevance score and the semantic relevance score for the at least one snippet includes determining a quality score based at least on snippet length.

18. A method as recited in claim 15, further comprising receiving the location and the context term from a query.

19. A method as recited in claim 15, further comprising:

receiving the location and the context term from a query; and

returning the at least one snippet ranked based at least on the snippet score responsive to the query.

20. A method as recited in claim 15, further comprising normalizing the snippet score.