Method and apparatus for determining peer groups based upon observed usage patterns

• US 7,693,836 B2
• Filed: 02/08/2006
• Issued: 04/06/2010
• Est. Priority Date: 12/27/2005
• Status: Expired due to Fees

• 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:
  US11/350,428
• Publication Number:
  US 20070150470A1
• Time in Patent Office: 1,518 Days
• Field of Search: 707/3, 707/6, 709/224, 715/205
• US Class Current: 707/603
• 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 encompasses 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 computer implemented method for automatically determining, in an on-line community, any of importance of an on-line asset, topic of said asset, a user'"'"'s current context/topic of interest, and relationships among users, without asking said on-line community'"'"'s members directly, comprising the processor executed steps of:

observing individual and community usage by a community of peers and experts;

employing automatic techniques to extract patterns from said usage;

identifying usefulness of an online asset by observing user implicit behaviors in connection with said usage patterns of said online asset and by extracting behavioral patterns from said observations;

refining said identified online asset usefulness by context, wherein the context of each online asset is automatically detected based on observed terms/topics from individual and group user behaviors when said online asset is determined to be useful based upon said individual and group user behaviors;

determining a user'"'"'s current context/topic based on an aggregation of the identified context of each online asset that the said user has found useful during their navigation, where an asset'"'"'s contribution to the aggregate context is weighted by an asset'"'"'s recency of use;

refining said identified user context based on searches performed during the user'"'"'s navigation, where a search'"'"'s contribution to the aggregate context is weighted by the recency of the search;

comparing the identified context of the current user with previously identified contexts of other users and assigning to each user a similarity score based on its similarity to the current user'"'"'s context;

and using said similarity score to automatically determine each user'"'"'s peer group;

said observed usage patterns comprising user online search, navigation, and interaction behavior, said behavior including any of searches performed and position in user trail, assets viewed and position in user trail, dwell, range, scrolling, think time, and mouse movement on an asset, anchors and lines used in asset text, virtual bookmarks and virtual printing, and explicit downloading, emailing, printing, saving, and removing to and/or from a computer hardware memory.

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

determining similarity between users based on a combination of shared use of assets inverse weighted by overall asset popularity, shared areas of expertise as determined by observing individual and community usage patterns, and shared use of search terms.

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

representing asset use, expertise, and term usage in vector-space and compared using an asymmetric similarity metric, said metric optionally comprising a dot product.

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

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 said asset, said 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 said asset, and browser window state, said state comprising any of foreground, background, minimized, maximized, and closed.

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

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

6. The method of claim 1, further comprising the steps of:

analyzing all observations; and

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

wherein said 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.

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

for a given user who may be anonymous, said 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 said user that allow said user to navigate said site more efficiently.

8. The method of claim 1, further comprising the steps of:

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 said recommendations to refine and augment a resulting search.

9. The method of claim 6, further comprising the step of:

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

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

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.

11. An apparatus for automatically determining, in an on-line community, any of importance of an on-line asset, a user'"'"'s current context/topic, and relationships among user without asking said on-line community'"'"'s members directly, comprising:

means for observing individual and community usage by a community of peers and experts;

a processor for employing automatic techniques to extract patterns from said usage;

said processor identifying usefulness of an online asset by observing user implicit behaviors in connection with said usage patterns of said online asset and by extracting behavioral patterns from said observations;

said processor refining said identified online asset usefulness by context, wherein the context of each online asset is automatically detected based on observed terms/topics from individual and group user behaviors when said online asset is determined to be useful based upon said individual and group user behaviors;

said processor determining a user'"'"'s current context/topic based on an aggregation of the identified context of each online asset that the said user has found useful during their navigation, where an asset'"'"'s contribution to the aggregate context is weighted by an asset'"'"'s recency of use;

said processor refining said identified user context based on searches performed during the user'"'"'s navigation, where a search'"'"'s contribution to the aggregate context is weighted by the recency of the search;

said processor comparing the identified context of the current user with previously identified contexts of other users and assigning to each user a similarity score based on its similarity to the current user'"'"'s context; and

said processor using said similarity score observed usage patterns to automatically determine each user'"'"'s peer group;

said observed usage patterns comprising user online search, navigation, and interaction behavior, said behavior including any of searches performed and position in user trail, assets viewed and position in user trail, dwell, range, scrolling, think time, and mouse movement on an asset, anchors and lines used in asset text, virtual bookmarks and virtual printing, and explicit downloading, emailing, printing, saving, and removing.

12. The apparatus of claim 11, further comprising:

said processor determining similarity between users based on a combination of shared use of assets inverse weighted by overall asset popularity, shared areas of expertise as determined by observing individual and community usage patterns, and shared use of search terms.

13. The apparatus of claim 11, further comprising:

said processor representing asset use, expertise, and term usage in vector-space and compared using an asymmetric similarity metric, said metric optionally comprising a dot product.

14. The apparatus of claim 11, further comprising:

said processor for 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 said asset, said 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 said asset, and browser window state, said state comprising any of foreground, background, minimized, maximized, and closed.

15. The apparatus of claim 11, further comprising:

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

16. The apparatus of claim 11, further comprising:

said processor analyzing all observations; and

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

wherein said 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.

17. The apparatus of claim 11, further comprising:

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

18. The apparatus of claim 11, further comprising:

said 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, said processor using said recommendations to refine and augment a resulting search.

19. The apparatus of claim 18, further comprising:

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

20. The apparatus of claim 19, further comprising:

said 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.