Recommending terms to specify ontology space

Patent metadata

Field	Value
Publication number	US-9081852-B2
Application number	US-24305008-A
Country	US
Kind code	B2
Filing date	Oct 1, 2008
Priority date	Oct 5, 2007
Publication date	Jul 14, 2015
Grant date	Jul 14, 2015

Abstract

In one embodiment, a set of target search terms for a search is received. Candidate terms are selected, where a candidate term is selected to reduce an ontology space of the search. The candidate terms are sent to a computer to recommend the candidate terms as search terms. In another embodiment, a document stored in one or more tangible media is accessed. A set of target tags for the document is received. Terms are selected, where a term is selected to reduce an ontology space of the document. The terms are sent to a computer to recommend the terms as tags.

First claim

What is claimed:

1. A computer-implemented method comprising:
accessing a document stored in one or more tangible media;
receiving a set of target tags for the document;
using a microprocessor of a computer, identifying a plurality of terms, each identified term selected to reduce an ontology space of the document due to the identified term having a higher affinity with a target tag and a lower affinity with the other identified terms;
sending the plurality of identified terms to a user of the computer via a user interface of the computer to recommend the plurality of identified terms as tags;
receiving, via the user interface of the computer, a selection by the user of one or more terms of the plurality of identified terms and identifying one or more of the plurality of identified terms that were not selected by the user;
using the microprocessor of the computer, determining a plurality of next terms that have both (i) an affinity with the one or more terms selected by the user that is above a first affinity threshold and (ii) an affinity with the one or more terms that were not selected by the user that is below a second affinity threshold; and
sending the next terms to the user via the user interface of the computer to recommend the terms as tags.

2. The method of claim 1 , the accessing the set of target tags for the document further comprising:
receiving a target tag of the set of target tags from a source selected from a group consisting of:
user input; and
a computer analysis; and

recording the source of the target tag.

3. The method of claim 1 , further comprising:
establishing a source of each target tag of the set of target tags;
retrieving a plurality of search results, a search result associated with a target tag; and
ranking the search results according to the sources of the target tags.

4. The method of claim 1 , further comprising:
removing one or more redundant terms from the set of target tags.

5. The method of claim 1 , further comprising:
initiating display of a graphical element configured to receive a requested degree of relatedness that a tag should have to a particular term.

6. The method of claim 1 , further comprising identifying the plurality of terms according to affinity by:
identifying one or more terms having a higher affinity with a target tag from a cluster corresponding to the target tag.

7. The method of claim 1 , further comprising identifying the plurality of terms according to affinity, the affinity further comprising one or more affinities selected from a group consisting of an affinity, an average affinity, a directional affinity, and a differential affinity.

8. One or more non-transitory computer-readable tangible media encoding software operable when executed to:
access a document stored in one or more tangible media;
receive a set of target tags for the document;
identify a plurality of terms, each identified term selected to reduce an ontology space of the document due to the identified term having a higher affinity with a target tag and a lower affinity with the other identified terms;
send the plurality of identified terms to a computer to recommend the plurality of identified terms as tags;
receive a selection by a user of one or more terms of the plurality of identified terms and identifying one or more of the plurality of identified terms that were not selected by the user;
determine a plurality of next terms that have both (i) an affinity with the one or more terms selected by the user that is above a first affinity threshold and (ii) an affinity with the one or more terms that were not selected by the user that is below a second affinity threshold; and
send the next terms to the computer to recommend the terms as tags.

9. The computer-readable tangible media of claim 8 , the software when executed operable to access the set of target tags for the document by:
receiving a target tag of the set of target tags from a source selected from a group consisting of:
user input; and
a computer analysis; and

recording the source of the target tag.

10. The computer-readable tangible media of claim 8 , the software when executed operable to:
establish a source of each target tag of the set of target tags;
retrieve a plurality of search results, a search result associated with a target tag; and
rank the search results according to the sources of the target tags.

11. The computer-readable tangible media of claim 8 , the software when executed operable to:
remove one or more redundant terms from the set of target tags.

12. The computer-readable tangible media of claim 8 , the software when executed operable to:
initiate display of a graphical element configured to receive a requested degree of relatedness that a tag should have to a particular term.

13. The computer-readable tangible media of claim 8 , the software when executed operable to identify the plurality of terms according to affinity by:
identifying one or more terms having a higher affinity with a target tag from a cluster corresponding to the target tag.

14. The computer-readable tangible media of claim 8 , the software when executed operable to identify the plurality of terms according to affinity, the affinity further comprising one or more affinities selected from a group consisting of an affinity, an average affinity, a directional affinity, and a differential affinity.

15. A computer-implemented method comprising:
receiving a set of target search terms for a search;
using a microprocessor of a computer, selecting a plurality of candidate terms, each candidate term selected to reduce an ontology space of the document due to the candidate term having a higher affinity with a target tag and a lower affinity with the other candidate terms;
sending the candidate terms to a user of the computer via a user interface of the computer to recommend the candidate terms as search terms;
receiving, via the user interface of the computer, a selection by the user of one or more terms of the candidate terms and identifying one or more terms of the candidate terms that were not selected by the user;
using the microprocessor of the computer, determining a plurality of next terms that have both (i) an affinity with the one or more terms selected by the user that is above a first affinity threshold and (ii) an affinity with the one or more terms that were not selected by the user that is below a second affinity threshold; and
sending the next terms to the user via the user interface of the computer to recommend the next terms as search terms.

16. The method of claim 15 , the receiving the set of target search terms for the search further comprising:
receiving a target search term of the set of target search terms from a source selected from a group consisting of:
user input; and
a computer analysis; and

recording the source of the target search term.

17. The method of claim 15 , further comprising:
establishing a source of each target search term of the set of target search terms;
retrieving a plurality of search results, a search result associated with a target search term; and
ranking the search results according to the sources of the target search terms.

18. The method of claim 15 , further comprising:
removing one or more redundant terms from the set of target search terms.

19. The method of claim 15 , further comprising:
initiating display of a graphical element configured to receive a requested degree of relatedness that a candidate term should have to a search term.

Assignees

• Marvit David L
• Jain Jawahar
• Stergiou Stergios
• Gilman Alex
• Adler B Thomas
• Sidorowich John J
• Reinhardt Albert
• Labrou Yannis
• Fujitsu Ltd

Inventors

• Marvit David L
• Jain Jawahar
• Stergiou Stergios
• Gilman Alex
• Adler B Thomas
• Sidorowich John J
• Reinhardt Albert
• Labrou Yannis

Classifications

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F16/3325

  Reformulation based on results of preceding query · CPC title

• G06F16/313

  Selection or weighting of terms for indexing · CPC title

• G06F16/3338 Primary

  Query expansion · CPC title

• G06F17/30864

  Physics · mapped topic