System and method for providing targeted content

• US 8,156,138 B2
• Filed: 06/26/2007
• Issued: 04/10/2012
• Est. Priority Date: 06/26/2007
• Status: Active Grant

• Current Assignee: RichRelevance Incorporated
• Original Assignee: RichRelevance Incorporated
• Inventors: Kohn, Tyler, Selinger, David, DeCourcey, Michael
• Primary Examiner(s): Kerzhner, Aleksandr
• Application Number:
  US11/823,453
• Publication Number:
  US 20090132553A1
• Time in Patent Office: 1,750 Days
• Field of Search: 707/3, 707/769, 707/999.003
• US Class Current: 707/769
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

An arrangement for providing targeted content includes data repositories storing information from which targeted content may be selected. The data repositories store at least one contextual relationship graph. The arrangement also includes an input/output interface through which a request for targeted content is made. The arrangement further includes a controller that receives the request for targeted content and selects targeted content using the contextual relationship graph. The controller further provides the selected targeted content through the input/output interface. An arrangement for determining the relative strength of a classification for a group of words includes memory for storing a contextual relationship graph for a given classification and a processor that receives the contextual relationship graph and a plurality of words to be analyzed by the processor, identifies occurrences of the relationships identified in the contextual relationship graph and determines the relative strength of classification based on the identified occurrences.

Claims

1. A system for providing targeted content comprising:

one or more data repositories configured to store information from which targeted content may be selected and to store information including a hierarchically structured contextual relationship graph, wherein the contextual relationship graph defines a plurality of hierarchical relationships between a plurality of nodes within the contextual relationship graph that correspond to the stored information from which the targeted content may be selected, the plurality of nodes each having one or more associated keywords and one or more corresponding pieces of content;

an input/output interface that is configured to receive a request for targeted content, wherein said request includes request-associated attributes; and

a controller processor that is configured to analyze at least some of the request-associated attributes to identify nodes of the contextual relationship graph that are related to the request-associated attributes, and to provide targeted content from the one or more data repositories that is selected based on at least a number of the identified nodes,

wherein identifying of the nodes of the contextual relationship graph that are related to the request-associated attributes includes matching the at least some request-associated attributes with the one or more associated keywords for each of multiple of the plurality of nodes and includes selecting those multiple nodes as the identified nodes,

wherein selecting of the targeted content includes;

performing a calculation of a score for each of at least some of the identified nodes, the calculated score for each of the at least some identified nodes being based on a function of a quantity of (a) matches of the at least some request-associated attributes with the one or more keywords associated with the identified node being scored and of (b) matches of the at least some request-associated attributes with the one or more keywords associated with other of the identified nodes that are identified as having a subordinate relationship in the contextual relationship graph to the identified node being scored;

selecting one or more of the at least some identified nodes whose calculated scores are above the calculated scores of other of the at least some identified nodes that are not selected; and

identifying at least one of the one or more corresponding pieces of content for each of the selected one or more identified nodes as the selected targeted content, and

wherein the providing of the selected targeted content by the controller processor occurs through the input/output interface.

2. The system of claim 1 wherein said one or more data repositories are databases.

3. The system of claim 1 wherein said information from which the targeted content may be selected is one of a group consisting of:

advertising, promotional offers, multimedia content, interactive content, news or other stories, service announcements and binary data.

4. The system of claim 1 wherein said contextual relationship graph is selected from a group consisting of:

a content graph, a category graph, and a content/category graph.

5. The system of claim 4 wherein the contextual relationship graph is a category graph representing a hierarchy of multiple categories of products or services.

6. The system of claim 4 wherein the contextual relationship graph is a category graph representing multiple categories of at least one of products and of services from a plurality of vendors.

7. The system of claim 5 wherein the nodes in the category graph correspond to a description of the products or services, and wherein the identifying of the nodes of the contextual relationship graph that are related to the request-associated attributes includes determining nodes that have a first order relationship to the request-associated attributes.

8. The system of claim 5 wherein at least some of the nodes in the category graph correspond to category names for the products or services, and wherein the identifying of the nodes of the contextual relationship graph that are related to the request-associated attributes includes determining one or more of the at least some nodes that have a first order relationship to the request-associated attributes.

9. The system of claim 1 wherein said request-associated attributes include a plurality of words.

10. The system of claim 9 wherein the analyzing of the at least some request-associated attributes includes determining which of the plurality of words to analyze based at least in part on a distance between words within the plurality of words.

11. The system of claim 1 wherein the performing of the calculation of the score for each of the at least some identified nodes is based on a sum of a log of a quantity of keyword matches for identified nodes in the contextual relationship graph that have a subordinate relationship to the identified node being scored.

12. The system of claim 1 wherein the identifying of the nodes of the contextual relationship graph that are related to the request-associated attributes further includes using a weighted system for prioritizing the identified nodes by determining other lower priority nodes in the contextual relationship graph that have a subordinate relationship to one or more of the identified nodes based on a number of associations of the request-associated attributes with the one or more keywords associated with each of the other lower priority nodes.

13. The system of claim 1 wherein each of the plurality of nodes represents at least one of a category and of an attribute.

14. The system of claim 1 wherein the identifying of the nodes of the contextual relationship graph that are related to the request-associated attributes is based at least in part on an analysis of both positive and negative relationships.

15. The system of claim 1 wherein said request-associated attributes include attributes selected from a group consisting of:

contextual attributes, profile attributes and behavioral attributes.

16. The system of claim 1 wherein said request-associated attributes include data regarding a location in which the selected targeted content is to be provided.

17. The system of claim 1 wherein said request-associated attributes include data regarding a target to which the selected targeted content will be directed.

18. The system of claim 1 wherein said controller processor is a microprocessor.

19. The system of claim 1 wherein each of the plurality of nodes represents at least one category, and wherein the hierarchical relationships between the plurality of nodes are contextual relationships that define categories and sub-categories.

20. The system of claim 1 wherein at least some of the hierarchical relationships between the plurality of nodes are contextual relationships between the one or more keywords associated with each of the plurality of nodes and one or more pieces of related particular content of the stored information.

21. The system of claim 1 wherein each of the plurality of nodes represents at least one of one or more categories, and wherein the hierarchical relationships between the plurality of nodes are contextual relationships between categories and pieces of related particular content of the stored information.

22. A non-transmission computer-readable storage medium having computer-executable instructions stored thereon, the computer-executable instructions configuring a computer system to perform steps of:

receiving a request for targeted content including request-associated attributes;

identifying one or more of a plurality of nodes of a hierarchically structured contextual relationship graph that are related to the request-associated attributes, the identified nodes being selected from at least some of the plurality of nodes that each have one or more associated keywords and that correspond to information about content stored in one or more data repositories, and wherein the identifying of the one or more nodes includes matching at least some of the request-associated attributes with the one or more keywords associated with each of the identified nodes; and

selecting the targeted content for the request from the content stored in the one or more data repositories based on at least one of a number of the identified nodes and of a weighted system for prioritizing the identified nodes,

wherein selecting of the targeted content based on the number of the identified nodes includes;

performing a calculation of a score for each of the identified nodes, the calculated score for each identified node being based on a function of a quantity of (a) matches of the at least some request-associated attributes with the one or more keywords associated with the identified node being scored and of (b) any matches of the at least some request-associated attributes with the one or more keywords associated with other of the at least some nodes that have a subordinate relationship in the contextual relationship graph to the identified node being scored;

selecting at least one of the identified nodes having a highest calculated score; and

identifying one or more corresponding pieces of content for each of the selected at least one identified nodes as the selected targeted content, and

wherein selecting of the targeted content based on the weighted system includes performing further analysis for at least one of the identified nodes whose calculated score exceeds a particular value, the performing of the further analysis including determining the selected targeted content.

23. The computer-readable medium of claim 22 wherein the configured computer system includes the one or more data repositories, and wherein said request originates from the configured computer system.

24. The computer-readable medium of claim 22 wherein said request originates externally to a system that includes the one or more data repositories.

25. The computer-readable medium of claim 22 wherein the configured computer system includes a controller that automatically performs the selecting of the targeted content, and wherein the targeted content selected is a choice set from which more specifically targeted content will be selected.

26. The computer-readable medium of claim 22 wherein the selecting of the targeted content includes utilizing closed loop feedback to filter some of the content stored in the one or more data repositories.

27. The computer-readable medium of claim 22 wherein the request-associated attributes include an identification of a recipient of the targeted content, and wherein the selecting of the targeted content includes utilizing a variety filter to remove content that has been previously selected for the recipient.

28. The computer-readable medium of claim 22 wherein the selecting of the targeted content includes first selecting a category from which the targeted content will be selected, then selecting a choice set from the selected category, and then selecting the targeted content from the selected choice set.

29. The computer readable medium of claim 22 wherein the identifying of the one or more nodes includes comparing the request-associated attributes to the plurality of nodes of the hierarchically structured contextual relationship graph to identify the one or more nodes.

30. The computer readable medium of claim 22 wherein the computer-executable instructions further configure the computer system to perform the step of providing one or more indications of the selected targeted content in response to the received request.

31. The computer readable medium of claim 22 wherein the identified one or more nodes correspond to particular content of the content stored in the one or more data repositories.

32. The computer readable medium of claim 22 wherein the identified one or more nodes represent at least one category, and wherein hierarchical relationships between the identified one or more nodes are contextual relationships that define categories and sub-categories.

33. The computer readable medium of claim 22 wherein at least some hierarchical relationships between the identified one or more nodes are contextual relationships between the one or more keywords associated with the identified one or more nodes and one or more pieces of related stored content.

34. The computer readable medium of claim 22 wherein the identified one or more nodes represent at least one of one or more categories and one or more particular pieces of content, and wherein hierarchical relationships between the identified one or more nodes are contextual relationships between categories and pieces of related particular content.

35. A computer-implemented method for selecting targeted content comprising:

receiving a request for targeted content, the request including request-associated attributes;

automatically comparing the request-associated attributes to at least one hierarchically structured contextual relationship graph to identify one or more of a plurality of nodes of one of the at least one contextual relationship graph that are related to the request-associated attributes, wherein the one contextual relationship graph defines a plurality of hierarchical contextual relationships between the plurality of nodes, wherein the identified nodes are selected from at least some of the plurality of nodes that each have one or more associated keywords and that correspond to stored content that is available to be selected, and wherein the automatic comparing is performed by a programmed computing system and includes matching at least some of the request-associated attributes with the one or more keywords associated with each of the identified nodes;

automatically selecting targeted content based on at least one of a number of the identified one or more nodes and of a weighted system for prioritizing the identified one or more nodes, the automatic selecting being performed by the programmed computing system,

wherein selecting of the targeted content based on the number of the identified nodes includes;

performing a calculation of a score for each of the identified nodes, the calculated score for each identified node being based on a function of a quantity of (a) matches of the at least some request-associated attributes with the one or more keywords associated with the identified node being scored and of (b) any matches of the at least some request-associated attributes with the one or more keywords associated with other of the at least some nodes that have a subordinate relationship in the contextual relationship graph to the identified node being scored;

selecting at least one of the identified nodes having a highest calculated score; and

identifying one or more corresponding pieces of content for each of the selected at least one identified nodes as the selected targeted content, and

wherein selecting of the targeted content based on the weighted system includes performing further analysis for at least one of the identified nodes whose calculated score exceeds a particular value, the performing of the further analysis including determining the selected targeted content; and

providing one or more indications of the selected targeted content in response to the received request.

36. The method of claim 35 wherein the identified one or more nodes represent at least one of a category and an attribute.

37. The method of claim 35 wherein the automatic selecting of the targeted content is performed based on the number of the identified one or more nodes.

38. The method of claim 35 wherein the automatic selecting of the targeted content is based at least in part on the weighted system for prioritizing the identified one or more nodes.

39. The method of claim 35 wherein each of the identified one or more nodes represents at least one category, and wherein the hierarchical contextual relationships between the identified one or more nodes define relationships between categories and sub-categories.

40. The method of claim 35 wherein at least some of the hierarchical contextual relationships between the identified one or more nodes are relationships between the one or more keywords associated with each of the identified nodes and one or more pieces of related particular content available to be used as the targeted content.

41. The method of claim 35 wherein each of the identified one or more nodes represents at least one of one or more categories and one or more particular pieces of content that are available to be used as the targeted content, and wherein the hierarchical contextual relationships are relationships between one or more categories and one or more related pieces of the particular pieces of content.