Context based networking

• US 8,700,648 B2
• Filed: 03/16/2009
• Issued: 04/15/2014
• Est. Priority Date: 03/16/2009
• Status: Expired due to Fees

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Bhamidipati, Narayan Lakshmi, Dutta, Debajyoti
• Primary Examiner(s): Uddin, Md. I
• Application Number:
  US12/404,345
• Publication Number:
  US 20100235389A1
• Time in Patent Office: 1,856 Days
• Field of Search: 709/206, 709/207, 707/708, 707/718, 707/728, 707/769, 707/748, 707/749, 707/758, 707/771
• US Class Current: 707/758
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Context based networking. A method for context based networking includes receiving a query. Further, the method includes obtaining behavioral targeting scores of a plurality of first buddy nodes of a node corresponding to the query. Furthermore, the method includes updating the behavioral targeting scores of the plurality of first buddy nodes based on behavioral targeting score of at least one second buddy node of each first buddy node. In addition, the method includes forwarding the query to at least one first buddy node based on the updated behavioral targeting scores. Further, the method includes obtaining a response associated with the query. The method also includes electronically providing the response to a user of the node.

Claims

1. An article of manufacture comprising:

a non-transitory machine-readable medium; and

instructions carried by the medium and operable to cause a programmable processor to perform;

receiving a query for nodes in a social network;

identifying characteristics of the query, the characteristics including ambiguity, temporal sensitivity, and spatial sensitivity, and further including authority sensitivity for other than navigational queries;

obtaining behavioral targeting scores of a plurality of first buddy nodes of a node corresponding to the query, wherein the behavioral targeting scores are calculated based on weighted combinations of different metrics observed from historical behavior of the first buddy node, where the behavioral targeting score=I+R+P, where;

(i) I is an intensity score based on intensity weights of the observed historical behavior,

(ii) R is a recency score based on recency weights of the observed historical behavior, and

(iii) P is an intercept which is a constant related to click-through rate (CTR),

and wherein the first buddy nodes are nodes which are in a social network of the node corresponding to the query, and wherein the behavioral targeting score accounts for the one or more identified characteristics;

updating the behavioral targeting scores of the plurality of first buddy nodes based on;

using behavioral targeting scores of at least one second buddy node of each first buddy node, wherein a second buddy node of a first buddy node is a node which is in a social network of the first buddy node but not in a social network of the node corresponding to the query, and

storing web usage history of the user of the node, the web usage history being extracted from a web log corresponding with a user'"'"'s cookie, and including at least one of queries that were searched, links clicked in the search result, sponsored link clicks, display ad views, display ad clicks, and pages viewed, and

modifying the behavioral targeting scores based on the web usage history, the web usage history comprising activities of the user external to internal query responses of the user;

forwarding the query to at least one first buddy node based on the updated behavioral targeting scores;

receiving a response associated with the query; and

electronically providing the response to a user of the node.

2. The article of manufacture of claim 1 further comprising instructions operable to cause the programmable processor to perform:

identifying one or more categories associated with the query, the categories including sports, finances, stocks, shares, electronic commerce, entertainments, digital devices, pharmaceutical, automobiles, traveling, hot jobs, and education, and the categories being identified using query categorization techniques.

3. The article of manufacture of claim 1 further comprising instructions operable to cause the programmable processor to perform:

prioritizing the plurality of first buddy nodes based on the updated behavioral targeting scores.

4. The article of manufacture of claim 1 further comprising instructions operable to cause the programmable processor to perform:

sending the query to a second buddy node of the at least one first buddy node.

5. The article of manufacture of claim 1 further comprising instructions operable to cause the programmable processor to perform:

recommending one or more buddies to the user based on the query and behavioral targeting scores of the one or more buddies.

6. A computer-implemented method for context based networking, the computer-implemented method comprising:

receiving a query for nodes in a social network;

identifying characteristics of the query, the characteristics including ambiguity, temporal sensitivity, and spatial sensitivity, and further including authority sensitivity for other than navigational queries;

obtaining behavioral targeting scores of a plurality of first buddy nodes of a node corresponding to the query, wherein the behavioral targeting scores are calculated based on weighted combinations of different metrics observed from historical behavior of the first buddy node, where the behavioral targeting score=I+R+P, where

(i) I is an intensity score based on intensity weights of the observed historical behavior,

(ii) R is a recency score based on recency weights of the observed historical behavior, and

(iii) P is an intercept which is a constant related to click-through rate (CTR),

and wherein the first buddy nodes are nodes which are in a social network of the node corresponding to the query, and wherein the behavioral targeting score accounts for the one or more identified characteristics;

updating the behavioral targeting scores of the plurality of first buddy nodes based on;

using behavioral targeting score of at least one second buddy node of each first buddy node, wherein a second buddy node of a first buddy node is a node which is in a social network of the first buddy node but not in a social network of the node corresponding to the query, and

storing web usage history of the user of the node, the web usage history being extracted from a web log corresponding with a user'"'"'s cookie, and including at least one of queries that were searched, links clicked in the search result, sponsored link clicks, display ad views, display ad clicks, and pages viewed, and modifying the behavioral targeting scores based on the web usage history, the web usage history comprising activities of the user external to internal query responses of the user;

forwarding the query to at least one first buddy node based on the updated behavioral targeting scores;

obtaining a response associated with the query; and

electronically providing the response to a user of the node.

7. The computer-implemented method of claim 6 further comprising:

identifying the one or more categories associated with the query, the categories including sports, finances, stocks, shares, electronic commerce, entertainments, digital devices, pharmaceutical, automobiles, traveling, hot jobs, and education, and the categories being identified using query categorization techniques.

8. The computer-implemented method of claim 6 further comprising:

prioritizing the plurality of first buddy nodes based on the updated behavioral targeting scores.

9. The computer-implemented method of claim 6 further comprising:

sending the query to a second buddy node of the at least one first buddy node.

10. The computer-implemented method of claim 6 further comprising:

recommending one or more buddies to the user based on the query and behavioral targeting scores of the one or more buddies.

11. A system for context based networking, the system comprising:

a user electronic device in communication with a network connected to a plurality of buddy electronic devices;

a storage unit for storing instructions;

a processor for executing the instructions, the instructions for;

receiving a query for nodes in a social network;

identifying characteristics of the query, the characteristics including ambiguity, temporal sensitivity, and spatial sensitivity, and further including authority sensitivity for other than navigational queries;

obtaining behavioral targeting scores of a plurality of first buddy nodes of a node corresponding to the query, wherein the behavioral targeting scores are calculated based on weighted combinations of different metrics observed from historical behavior of the first buddy node, where the behavioral targeting score=I+R+P, where

(i) I is an intensity score based on intensity weights of the observed historical behavior,

(ii) R is a recency score based on recency weights of the observed historical behavior, and

(iii) P is an intercept which is a constant related to click-through rate (CTR),

and wherein the first buddy nodes are nodes which are in a social network of the node corresponding to the query, and wherein the behavioral targeting score accounts for the one or more identified characteristics;

updating the behavioral targeting scores of the plurality of first nodes based on;

using behavioral targeting scores of at least one second buddy node of each first buddy node, wherein a second buddy node of a first buddy node is a node which is in a social network of the first buddy node but not in a social network of the node corresponding to the query; and

storing web usage history of the user of the node, the web usage history being extracted from a web log corresponding with a user'"'"'s cookie, and including at least one of queries that were searched, links clicked in the search result, sponsored link clicks, display ad views, display ad clicks, and pages viewed, and modifying the behavioral targeting scores based on the web usage history, the web usage history comprising activities of the user external to internal query responses of the user;

forwarding the query to at least one buddy node based on the updated behavioral targeting scores;

obtaining a response associated with the query; and

electronically providing the response to a user of the node.