System and method for providing orientation into subject areas of digital information for augmented communities

• US 8,930,388 B2
• Filed: 03/10/2014
• Issued: 01/06/2015
• 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, Stefik, Barbara S.
• Primary Examiner(s): Alam, Hosain
• Assistant Examiner(s): JOHNSON, JOHNESE T
• Application Number:
  US14/203,507
• Publication Number:
  US 20140195543A1
• Time in Patent Office: 302 Days
• Field of Search: 707/759
• US Class Current: 707/759
• CPC Class Codes: G06F 16/2228 Indexing structures
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A system and method for providing orientation into subject areas of digital information for augmented communities is provided. Topics are provided for subject areas. Each subject area is associated with an augmented community and each topic is hierarchically organized under a fine-grained topic category. Evergreen indexes are maintained and includes topic models that are each matched to topics associated with each augmented community. Interrelatedness of the evergreen indexes is determined by identifying the topics found in the topic hierarchy for each evergreen index that are shared. A social network including neighbors made up of each augmented community associated with each interrelated evergreen index is formed. A user interest is determined and each of the plurality of topic models for the evergreen indexes is evaluated against the digital information. Access to the digital information via the identified best matched evergreen index and the identified other evergreen index is provided.

Claims

1. A computer-implemented system for providing orientation into subject areas of digital information for augmented communities, comprising:

a memory;

a processor operatively couple to the memory and configured to execute computer executable program modules, comprising;

an information collection module configured to obtain a plurality of topics for each subject area in a plurality of subject areas, each subject area being associated with an augmented community, each topic being hierarchically organized under a fine-grained topic category in a topic hierarchy;

an information storage module configured to maintain a plurality of evergreen indexes, each evergreen index comprising a plurality of topic models that are each matched to one of the topics in the topic hierarchy associated with each augmented community;

an interrelatedness module configured to determine interrelatedness of the plurality of evergreen indexes by identifying the topics found in the topic hierarchy for each evergreen index that are shared;

a social network module configured to arrange a social network comprising neighbors made up of each augmented community associated with each of the plurality of evergreen indexes that are interrelated;

an interest module configured to determine a user interest in digital information for a subject area;

an evaluation module configured to evaluate each of the plurality of topic models for the evergreen indexes against the digital information, comprising;

a best matching module configured to identify one of the evergreen indexes quantitatively best matched to the digital information; and

a neighbor matching module configured to identify the other evergreen index associated with each augmented community that is a neighbor of the augmented community with the identified evergreen index; and

an evergreen index access module configured to provide access to the digital information of the subject area via at least one of the identified best matched evergreen index and the identified other evergreen index.

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

a similarity topic module configured to identify similarities in core subject matter of each topic between at least two sets of the augmented communities; and

a neighbor classification module configured to classify the augmented communities as neighbors sharing at least one topic in common.

3. A system according to claim 1, the plurality of evergreen indexes further comprising:

a topic category module configured to receive each topic model matched to one of the topics for each evergreen index being sheparded and vetted into at least one of the fine-grained topic categories based on at least one member of the augmented community associated with the evergreen index.

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

a commentary module configured to associate user-editable commentary with each topic associated with the augmented community.

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

a new information module configured to identify new digital information;

a new information matching module configured to match the new digital information against the topic models of the evergreen index and determining topics of the new digital information; and

a new information addition module configured to add the topics of the new digital information into the matched evergreen index.

6. A system according to claim 1, the topic model further comprising at least one of:

a pattern module configured to obtain a pattern evaluable against the digital information; and

a term vector module configured to obtain term vectors evaluable against the digital information.

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

a user interface module configured to provide access to the digital information through a user interface,

wherein the user interface displays a list of the topics for at least one of the identified evergreen indexes visually separated by each of the identified evergreen indexes.

8. A system according to claim 7, wherein the list is based on at least one of relevancy to the determined user interest and a degree of interest tailored to a user based on information specific to the user'"'"'s history or state.

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

a ranking module configured to associate a ranking with each of the topics of at least one of the evergreen indexes as assigned by the augmented communities; and

a presentation module configured to present the digital information regarding each topic associated with the ranking on the user interface based on the ranking of their respective evergreen indexes.

10. 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.

11. A computer-implemented method for providing orientation into subject areas of digital information for augmented communities, comprising:

obtaining a plurality of topics for each subject area in a plurality of subject areas, each subject area being associated with an augmented community, each topic being hierarchically organized under a fine-grained topic category in a topic hierarchy;

maintaining a plurality of evergreen indexes, each evergreen index comprising a plurality of topic models that are each matched to one of the topics in the topic hierarchy associated with each augmented community;

determining interrelatedness of the plurality of evergreen indexes by identifying the topics found in the topic hierarchy for each evergreen index that are shared;

arranging a social network comprising neighbors made up of each augmented community associated with each of the plurality of evergreen indexes that are interrelated;

determining a user interest in digital information for a subject area;

evaluating each of the plurality of topic models for the evergreen indexes against the digital information, comprising;

identifying one of the evergreen indexes quantitatively best matched to the digital information; and

identifying the other evergreen index associated with each augmented community that is a neighbor of the augmented community with the identified evergreen index; and

providing access to the digital information of the subject area via at least one of the identified best matched evergreen index and the identified other evergreen index,

wherein a non-transitory computer readable storage medium stores code for executing on a computer system to perform all the method steps.

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

identifying similarities in core subject matter of each topic between at least two sets of the augmented communities; and

classifying the augmented communities as neighbors sharing at least one topic in common.

13. A method according to claim 11, the plurality of evergreen indexes further comprising:

receiving each topic model matched to one of the topics for each evergreen index being sheparded and vetted into at least one of the fine-grained topic categories based on at least one member of the augmented community associated with the evergreen index.

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

associating user-editable commentary with each topic associated with the augmented community.

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

identifying new digital information;

matching the new digital information against the topic models of the evergreen index and determining topics of the new digital information; and

adding the topics of the new digital information into the matched evergreen index.

16. A method according to claim 11, the topic model further comprising at least one of:

obtaining a pattern evaluable against the digital information; and

obtaining term vectors evaluable against the digital information.

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

providing access to the digital information through a user interface; and

displaying on the user interface a list of the topics for at least one of the identified evergreen indexes visually separated by each of the identified evergreen indexes.

18. A method according to claim 17, wherein the list is based on at least one of relevancy to the determined user interest and a degree of interest tailored to a user based on information specific to the user'"'"'s history or state.

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

associating a ranking with each of the topics of at least one of the evergreen indexes as assigned by the augmented communities; and

presenting the digital information regarding each topic associated with the ranking on the user interface based on the ranking of their respective evergreen indexes.

20. A method according to claim 11, wherein the digital information comprises one or more of printed documents, Web pages, and material written in a digital media.