System and method for providing targeted content

• US 20100106599A1
• Filed: 06/26/2007
• Published: 04/29/2010
• Est. Priority Date: 06/26/2007
• Status: Active Grant

• Current Assignee: RichRelevance Incorporated
• Original Assignee: RichRelevance Incorporated
• Inventors: Kohn, Tyler, Selinger, David, DeCourcey, Michael
• Granted Patent: US 8,209,214 B2
• Time in Patent Office: Days
• US Class Current: 705/14.540
• CPC Class Codes: G06Q 10/0637 Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search

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. An arrangement for determining the relative strength of a contextual relationship for a group of words, the arrangement comprising:

memory for storing at least one hierarchically structured contextual relationship graph, wherein the contextual relationship graph defines a plurality of contextual relationships for a plurality of nodes; and

a controller that receives the contextual relationship graph and a plurality of words to be analyzed by said controller, analyzes the plurality of words, or any subset thereof, to determine nodes that are related to the plurality of words using first and higher order relationships and determines the relative strength of the contextual relationship of the plurality of words to the subject of the hierarchically structured contextual relationship graph based on the relationships identified.

2. The arrangement of claim 1 wherein the relative strength of contextual relationship is based, at least in part, on the number of identified nodes in the plurality of words.

3. The arrangement of claim 1 wherein the relative strength of contextual relationship is based, at least in part, on the proximity of identified nodes to each other within the plurality of words to be analyzed.

4. The arrangement of claim 1 wherein the relative strength of contextual relationship is based, at least in part, on a weighted system for prioritizing the identified nodes.

5. The arrangement of claim 1 wherein the relative strength of contextual relationship is based, at least in part, on the number of occurrences of specifically identified nodes.

6. The arrangement of claim 1 wherein the relative strength of contextual relationship is based, at least in part, on an analysis of both positive and negative relationships.

7. The arrangement of claim 1 wherein said contextual relationship graph is selected from the group of contextual relationship graphs consisting of:

content graphs, category graphs and content/category graphs.

8. The arrangement of claim 1 wherein said memory is a database.

9. The arrangement of claim 1 wherein the set of words analyzed is determined, at least in part, by the distance between words within the plurality of words.

10. A computer-readable medium having computer-executable instructions for determining the relative strength of a contextual relationship for a group of words, the computer-executable instructions causing the arrangement to perform the steps of:

receiving, in the arrangement, at least one hierarchically structured contextual relationship graph, wherein the contextual relationship graph defines a plurality of contextual relationships for a plurality of nodes, and a plurality of words to be analyzed;

analyzing the plurality of words, or any subset thereof, to determine nodes that are related to the plurality of words using first and higher order relationships; and

determining the relative strength of the contextual relationship of the plurality of words to the subject of the hierarchically structured contextual relationship graph based on the relationships identified.

11. The computer-readable medium of claim 10 wherein the contextual relationship graph is selected from the group of contextual relationship graphs consisting of:

content graphs, category graphs and content/category graphs.

12. The computer-readable medium of claim 11 wherein the category graph is a hierarchy of products and/or services from a vendor.

13. The computer-readable medium of claim 11 wherein the category graph is a hierarchy of products and/or services from a plurality vendors.

14. The computer-readable medium of claim 11 where first order relationships are determined utilizing the description of products/services in a category graph.

15. The computer-readable medium of claim 11 wherein first order relationships are determined utilizing the category names in a category graph.

16. The computer-readable medium of claim 10 wherein the plurality of words to be analyzed are acquired from the content of a web page.

17. The computer-readable medium of claim 10 wherein the plurality of words to be analyzed are selected by a user.

18. The computer-readable medium of claim 10 wherein the plurality of words to be analyzed are acquired from the content of a web page.

19. The computer-readable medium of claim 10 wherein the plurality of words to be analyzed are acquired from the content of a product description.

20. The computer-readable medium of claim 10 wherein the relative strength of classification is based, at least in part, on an analysis of both positive and negative relationships.

21. The computer-readable medium of claim 10 wherein the relative strength of contextual relationship is based, at least in part, on the number of identified nodes in the plurality of words.

23. The method of claim 21 wherein the contextual relationship graph is selected from the group of contextual relationship graphs consisting of:

content graphs, category graphs and content/category graphs.

22. A method of discovering and assigning data regarding contextual content of a group of words via an arrangement, the method comprising the steps of:

receiving, in the arrangement, at least one hierarchically structured contextual relationship graph, wherein the contextual relationship graph defines a plurality of contextual relationships for a plurality of nodes, and a plurality of words to be analyzed;

analyzing the plurality of words, or any subset thereof, to determine nodes that are related to the plurality of words using first and higher order relationships; and

determining the relative strength of the contextual relationship of the plurality of words to the subject of the hierarchically structured contextual relationship graph based on the relationships identified.

24. The method of claim 22 wherein determining the relative strength of the contextual relationship includes utilizing collaborative filtering.

25. The method of claim 22 wherein determining the relative strength of the contextual relationship includes utilizing Bayesian learning.