System and method for prospecting digital information

• US 8,073,682 B2
• Filed: 08/12/2008
• Issued: 12/06/2011
• Est. Priority Date: 10/12/2007
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Palo Alto Research Center, Inc. (Xerox Holdings Corp.)
• Inventors: Stefik, Mark Jeffrey
• Primary Examiner(s): RIDER, JUSTIN W
• Application Number:
  US12/190,560
• Publication Number:
  US 20090099839A1
• Time in Patent Office: 1,211 Days
• Field of Search: None
• US Class Current: 704/9
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/358 Browsing; Visualisation therefor
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching

Abstract

A system and method for prospecting digital information is provided. A home evergreen index for a home subject area within a corpus of digital information is maintained and includes topic models matched to the corpus. A frontier evergreen index for a frontier subject area within the corpus topically distinct from the home subject area is identified. Quality assessments for frontier articles from the corpus identified by the topic models of the frontier evergreen index are obtained. The frontier articles with positive quality assessments are reclassified against the topic models in the home evergreen index. The frontier articles are provided in a display with home articles previously classified against the topic models in the home evergreen index.

Claims

1. A system for prospecting digital information, comprising:

an information collection configured to maintain a home evergreen index for a home subject area within a corpus of digital information and comprising topic models matched to the corpus;

a frontier community identifier configured to identify a frontier evergreen index for a frontier subject area within the corpus topically distinct from the home subject area, and to obtain quality assessments for frontier articles from the corpus identified by the topic models of the frontier evergreen index; and

a frontier information integrator configured to reclassify the frontier articles with positive quality assessments against the topic models in the home evergreen index, and to provide the frontier articles in a display with home articles previously classified against the topic models in the home evergreen index.

2. A system according to claim 1, further comprising:

an evaluator configured to comparing the home subject area to candidate frontier subject areas for a plurality of candidate frontier evergreen indexes, wherein the candidate frontier evergreen indexes are selected based on domain-informed evaluation of differences between the candidate frontier subject areas.

3. A system according to claim 1, further comprising:

an information collector configured to identify the information sources used by the home evergreen index and for a plurality of candidate frontier evergreen indexes, and to identify candidate frontier articles referenced by the candidate frontier evergreen indexes; and

an evaluator configured to determine overlap of at least one of the information sources and the home articles and the candidate frontier articles, wherein the candidate frontier evergreen indexes exhibiting positive overlap are selected.

4. A system according to claim 1, further comprising:

an evaluator configured to identify a plurality of candidate neighboring augmented communities that each comprise a candidate frontier evergreen index, and to generate similarity measures to each of the neighboring augmented communities, wherein the candidate neighboring communities comprising the similarity measures meeting at least one of a minimum threshold or up to a fixed number of the frontier articles are selected.

5. A system according to claim 1, wherein only those frontier articles matching the topic models in the home evergreen index are retained.

6. A system according to claim 1, further comprising:

an evaluator configured to compare those frontier articles failing to match the topic models in the home evergreen index, wherein the topic models in the home evergreen index are supplemented with names of new topics based on the non-matching frontier articles.

7. A system according to claim 1, further comprising:

a user services module configured to collaboratively vote on the frontier articles and the home articles as a community associated with the home evergreen index; and

to adjust placement of the frontier articles and the home articles in order of the votes.

8. A system according to claim 1, wherein the digital information comprises one or more of printed documents, Web pages, and material written in a digital media.

9. A method for prospecting digital information, comprising:

maintaining a home evergreen index for a home subject area within a corpus of digital information and comprising topic models matched to the corpus;

identifying a frontier evergreen index for a frontier subject area within the corpus topically distinct from the home subject area;

obtaining quality assessments for frontier articles from the corpus identified by the topic models of the frontier evergreen index;

reclassifying the frontier articles with positive quality assessments against the topic models in the home evergreen index; and

providing the frontier articles in a display with home articles previously classified against the topic models in the home evergreen index.

10. A method according to claim 9, further comprising:

comparing the home subject area to candidate frontier subject areas for a plurality of candidate frontier evergreen indexes; and

selecting the candidate frontier evergreen indexes based on domain-informed evaluation of differences between the candidate frontier subject areas.

11. A method according to claim 9, further comprising:

identifying the information sources used by the home evergreen index and for a plurality of candidate frontier evergreen indexes;

identifying candidate frontier articles referenced by the candidate frontier evergreen indexes;

determining overlap of at least one of the information sources and the home articles and the candidate frontier articles; and

selecting the candidate frontier evergreen indexes exhibiting positive overlap.

12. A method according to claim 9, further comprising:

identifying a plurality of candidate neighboring augmented communities that each comprise a candidate frontier evergreen index;

generating similarity measures to each of the neighboring augmented communities; and

selecting the candidate neighboring communities comprising the similarity measures meeting at least one of a minimum threshold or up to a fixed number of the frontier articles.

13. A method according to claim 9, further comprising:

retaining only those frontier articles matching the topic models in the home evergreen index.

14. A method according to claim 9, further comprising:

comparing those frontier articles failing to match the topic models in the home evergreen index; and

supplementing the topic models in the home evergreen index with names of new topics based on the non-matching frontier articles.

15. A method according to claim 9, further comprising:

collaboratively voting on the frontier articles and the home articles as a community associated with the home evergreen index; and

adjusting placement of the frontier articles and the home articles in order of the votes.

16. A method according to claim 9, wherein the digital information comprises one or more of printed documents, Web pages, and material written in a digital media.

17. An apparatus for prospecting digital information, comprising:

means for maintaining a home evergreen index for a home subject area within a corpus of digital information and comprising topic models matched to the corpus;

means for identifying a frontier evergreen index for a frontier subject area within the corpus topically distinct from the home subject area;

means for obtaining quality assessments for frontier articles from the corpus identified by the topic models of the frontier evergreen index;

means for reclassifying the frontier articles with positive quality assessments against the topic models in the home evergreen index; and

means for providing the frontier articles in a display with home articles previously classified against the topic models in the home evergreen index.