Method and apparatus for determining usefulness of a digital asset

• US 7,856,446 B2
• Filed: 02/08/2006
• Issued: 12/21/2010
• Est. Priority Date: 12/27/2005
• Status: Active Grant

• Current Assignee: Monetate, Inc. (StartApp, Inc.)
• Original Assignee: Baynote Incorporated (StartApp, Inc.)
• Inventors: Brave, Scott, Bradshaw, Robert, Minson, Christopher, Jia, Jack
• Primary Examiner(s): Alam; Shahid A
• Assistant Examiner(s): Bromell; Alexandria Y
• Application Number:
  US11/350,904
• Publication Number:
  US 20070150515A1
• Time in Patent Office: 1,777 Days
• Field of Search: 707/776, 707/966
• US Class Current: 707/776
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: Y10S 707/966 Distributed
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

The invention comprises a set of complementary techniques that dramatically improve enterprise search and navigation results. The core of the invention is an expertise or knowledge index, called UseRank that tracks the behavior of website visitors. The expertise-index is designed to focus on the four key discoveries of enterprise attributes: Subject Authority, Work Patterns, Content Freshness, and Group Know-how. The invention produces useful, timely, cross-application, expertise-based search and navigation results. In contrast, traditional Information Retrieval technologies such as inverted index, NLP, or taxonomy tackle the same problem with an opposite set of attributes than what the enterprise needs: Content Population, Word Patterns, Content Existence, and Statistical Trends. Overall, the invention emcompasses Baynote Search—a enhancement over existing IR searches, Baynote Guide—a set of community-driven navigations, and Baynote Insights—aggregated views of visitor interests and trends and content gaps.

Claims

1. A method for identifying, extracting using a processor, capturing, and leveraging expertise and knowledge comprising:

observing, between and among peers and experts who show high affinity with regard to any of the users, assets, and topics/terms, a user heartbeat which comprises user activity, including mouse movement and stable pauses on an asset, while the asset is in a user display foreground;

based upon the observing, detecting user think time for the asset;

employing automatic techniques to extract patterns from at least the user think time; and

learning affinities between and among any of the users, assets and topics/terms from the extracted patterns for any of;

automatically determining each user'"'"'s peer group,

predicting a desired destination of the users in a navigation context,

calculating an expert and peer impact factor, an asset impact factor, or rareness,

determining importance of an asset and/or expertise that individuals possess, without asking the individuals directly,

automatically disambiguating query terms in an online search, and/or

effecting a predictive query by suggesting search terms to the users or automatically inserting search terms into user queries to expand a search, wherein learning affinities includes applying a formula to lower weights of the term as the terms become associated with more assets.

2. The method of claim 1, further comprising:

classifying usage of a given asset by a given user as successful or unsuccessful use based on a combination of factors comprising any of time spent on an asset, explicit user actions taken on the asset, the actions comprising any of print, save, email, and bookmark, mouse and keyboard behavior, length and distribution of stable pauses between activity, navigation to and from the asset, and browser window state, the state comprising any of foreground, background, minimized, maximized, and closed.

3. The method of claim 1, further comprising:

providing a significantly greater weighting to the importance of implicit observations over the weighting provided to explicit observations.

4. The method of claim 1, further comprising:

analyzing all observations; and

via the analysis, generating a set of recommendations comprising distilled experiences from a community of users;

wherein the recommendations age over time and are discarded if they have relatively little value; and

wherein recommendations which are most valuable based on repeated usage are stored into a long term memory.

5. The method of claim 1, further comprising:

for a given user who may be anonymous, the user visiting a particular site, and a given context comprising any of what page the user is on and how the user got there, providing recommendations to the user that allow the user to navigate the site more efficiently.

6. The method of claim 1, further comprising:

generating a set a recommendations that may be applied to a search; and

for a given user who may be anonymous, and a given search query, using the recommendations to refine and augment a resulting search.

7. The method of claim 6, further comprising:

driving the recommendations not just by individual uses, but by the use of communities, leveraging the wisdom of crowds and community emergent behavior.

8. The method of claim 1, further comprising:

identifying communities comprising any of peer groups and expert groups based on an information context;

wherein communities are nested and defined by different levels of contexts.

9. The method of claim 1, the observing step further, comprising:

observing an implicit user action taken on an asset to enable easy, efficient future recovery of, and reference to the asset by the user; and

based upon the observing, detecting a virtual bookmark.

10. The method of claim 9, further comprising:

considering an asset left open in “

a user display foreground or background for a significant period of time to be virtually bookmarked.

11. A method for identifying, extracting using a processor, capturing, and leveraging expertise and knowledge comprising:

observing, between and among peers and experts who show high affinity with regard to any of the users, assets, and topics/terms, a user heartbeat which comprises user activity, including mouse movement and stable pauses on an asset, while the asset is in a user display foreground;

based upon the observing, detecting whether the asset is or is not useful for a given user;

employing automatic techniques to extract patterns from at least the detecting whether the asset is or is not useful for a given user; and

learning affinities between and among any of the users, assets and topics/terms from the extracted patterns for any of;

automatically determining each user'"'"'s peer group,

predicting a desired destination of the users in a navigation context,

calculating an expert and peer impact factor, an asset impact factor, or rareness,

determining importance of an asset and/or expertise that individuals possess, without asking the individuals directly,

automatically disambiguating query terms in an online search, and/or

effecting a predictive query by suggesting search terms to the users or automatically inserting search terms into user queries to expand a search, wherein learning affinities includes applying a formula to lower weights of the term as the terms become associated with more assets.

12. The method of claim 11, further comprising:

using a predominance of seeking behavior, including scrolling, over think time as an indication of an asset not being useful.

13. The method of claim 11, further comprising:

classifying usage of a given asset by a given user as successful or unsuccessful use based on a combination of factors comprising any of time spent on an asset, explicit user actions taken on the asset, the actions comprising any of print, save, email, and bookmark, mouse and keyboard behavior, length and distribution of stable pauses between activity, navigation to and from the asset, and browser window state, the state comprising any of foreground, background, minimized, maximized, and closed.

14. The method of claim 11, further comprising:

providing a significantly greater weighting to the importance of implicit observations over the weighting provided to explicit observations.

15. The method of claim 11, further comprising:

analyzing all observations; and

via the analysis, generating a set of recommendations comprising distilled experiences from a community of users;

wherein the recommendations age over time and are discarded if they have relatively little value; and

wherein recommendations which are most valuable based on repeated usage are stored into a long term memory.

16. The method of claim 11, further comprising:

for a given user who may be anonymous, the user visiting a particular site, and a given context comprising any of what page the user is on and how the user got there, providing recommendations to the user that allow the user to navigate the site more efficiently.

17. The method of claim 11, further comprising:

generating a set a recommendations that may be applied to a search; and

for a given user who may be anonymous, and a given search query, using the recommendations to refine and augment a resulting search.

18. The method of claim 17, further comprising:

driving the recommendations not just by individual uses, but by the use of communities, leveraging the wisdom of crowds and community emergent behavior.

19. The method of claim 11, further comprising:

identifying communities comprising any of peer groups and expert groups based on an information context;

wherein communities are nested and defined by different levels of contexts.

20. An apparatus for identifying, extracting, capturing, and leveraging expertise and knowledge, comprising:

means for observing, between and among peers and experts who show high affinity with regard to any of the users, assets, and topics/terms, a user heartbeat which comprises any user activity, including mouse movement and stable pauses on an asset, while the asset is in a user display foreground;

based upon the observing, a processor for detecting user think time for the asset;

the processor employing automatic techniques to extract patterns from at least the user think time; and

the processor learning affinities between and among any of the users, assets and topics/terms from the extracted patterns for any of;

automatically determining each user'"'"'s peer group,

predicting a desired destination of the users in a navigation context,

calculating an expert and peer impact factor, an asset impact factor, or rareness,

determining importance of an asset and/or expertise that individuals possess, without asking the individuals directly,

automatically disambiguating query terms in an online search, and/or

effecting a predictive query by suggesting search terms to the users or automatically inserting search terms into user queries to expand a search, wherein learning affinities includes applying a formula to lower weights of the terms as the terms become associated with more assets.

21. The apparatus of claim 20, further comprising:

the processor classifying usage of a given asset by a given user as successful or unsuccessful use based on a combination of factors comprising any of time spent on an asset, explicit user actions taken on the asset, the actions comprising any of print, save, email, and bookmark, mouse and keyboard behavior, length and distribution of stable pauses between activity, navigation to and from the asset, and browser window state, the state comprising any of foreground, background, minimized, maximized, and closed.

22. The apparatus of claim 20, further comprising:

the processor providing a significantly greater weighting to the importance of implicit observations over the weighting provided to explicit observations.

23. The apparatus of claim 20, further comprising:

the processor analyzing all observations; and

via the analysis, said processor generating a set of recommendations comprising distilled experiences from a community of users;

wherein the recommendations age over time and are discarded if they have relatively little value; and

wherein recommendations which are most valuable based on repeated usage are stored into a long term memory.

24. The apparatus of claim 20, further comprising:

for a given user who may be anonymous, the user visiting a particular site, and a given context comprising any of what page the user is on and how the user got there, the processor providing recommendations to the user that allow the user to navigate the site more efficiently.

25. The apparatus of claim 20, further comprising:

the processor generating a set a recommendations that may be applied to a search; and

for a given user who may be anonymous, and a given search query, the processor using the recommendations to refine and augment a resulting search.

26. The apparatus of claim 25, further comprising:

the processor driving the recommendations not just by individual uses, but by the use of communities, leveraging the wisdom of crowds and community emergent behavior.

27. The apparatus of claim 20, further comprising:

the processor identifying communities comprising any of peer groups and expert groups based on an information context;

wherein communities are nested and defined by different levels of contexts.

28. The apparatus of claim 20 further comprising:

based upon the observing, means for detecting a virtual bookmark.

29. The apparatus of claim 28, further comprising:

means for considering an asset left open in a user display foreground or background for a significant period of time to be virtually bookmarked.

30. An apparatus for identifying, extracting, capturing, and leveraging expertise and knowledge, comprising:

means for, observing, between and among peers and experts who show high affinity with regard to any of users, assets, and topics/terms, a user heartbeat which comprises user activity, including mouse movement and stable pauses on an asset, while the asset is in a user display foreground;

based upon the observing, a processor for detecting whether the asset is or is not useful for a given user;

the processor employing automatic techniques to extract patterns from at least detecting whether the asset is or is not useful for a given user; and

the processor learning affinities between and among any of the users, assets and topics/terms from the extracted patterns for any of;

automatically determining each user'"'"'s peer group,

predicting a desired destination of the users in a navigation context,

calculating an expert and peer impact factor, an asset impact factor, or rareness,

determining importance of an asset and/or expertise that individuals possess, without asking the individuals directly,

automatically disambiguating query terms in an online search, and/or

effecting a predictive query by suggesting search terms to the users or automatically inserting search terms into user queries to expand a search, wherein learning affinities includes applying a formula to lower weights of the terms as the terms become associated with more assets.

31. The apparatus of claim 30, further comprising:

the processor using a predominance of seeking behavior, including scrolling, over think time as an indication of an asset not being useful.

32. The apparatus of claim 30, further comprising:

the processor classifying usage of a given asset by a given user as successful or unsuccessful use based on a combination of factors comprising any of time spent on an asset, explicit user actions taken on the asset, the actions comprising any of print, save, email, and bookmark, mouse and keyboard behavior, length and distribution of stable pauses between activity, navigation to and from the asset, and browser window state, the state comprising any of foreground, background, minimized, maximized, and closed.

33. The apparatus of claim 30, further comprising:

the processor providing a significantly greater weighting to the importance of implicit observations over the weighting provided to explicit observations.

34. The apparatus of claim 30, further comprising:

the processor analyzing all observations; and

via the analysis, the processor generating a set of recommendations comprising distilled experiences from a community of users;

wherein the recommendations age over time and are discarded if they have relatively little value; and

wherein recommendations which are most valuable based on repeated usage are stored into a long term memory.

35. The apparatus of claim 30, further comprising:

for a given user who may be anonymous, the user visiting a particular site, and a given context comprising any of what page the user is on and how the user got there, the processor providing recommendations to the user that allow the user to navigate the site more efficiently.

36. The apparatus of claim 30, further comprising:

the processor generating a set a recommendations that may be applied to a search; and

for a given user who may be anonymous, and a given search query, means for using the recommendations to refine and augment a resulting search.

37. The apparatus of claim 36, further comprising:

the processor driving the recommendations not just by individual uses, but by the use of communities, leveraging the wisdom of crowds and community emergent behavior.

38. The apparatus of claim 37, further comprising:

the processor identifying communities comprising any of peer groups and expert groups based on an information context;

wherein communities are nested and defined by different levels of contexts.