System and method for providing targeted content

• US 9,639,846 B2
• Filed: 06/14/2012
• Issued: 05/02/2017
• Est. Priority Date: 06/26/2007
• Status: Active Grant

• Current Assignee: RichRelevance Incorporated
• Original Assignee: RichRelevance Incorporated
• Inventors: Kohn, Tyler, Selinger, David, DeCourcey, Michael James
• Primary Examiner(s): SCHEUNEMANN, RICHARD N
• Application Number:
  US13/523,737
• Publication Number:
  US 20120316970A1
• Time in Patent Office: 1,783 Days
• Field of Search: None
• 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. A computer-implemented method comprising:

receiving, by a configured computer system, a request for targeted advertising content to be provided to a user along with a page of information, the request including a plurality of words associated with the page;

obtaining, by the configured computer system, one or more contextual relationship graphs that represent one or more product categories and include a plurality of nodes corresponding to products within the represented one or more product categories;

analyzing, by the configured computer system, the plurality of words and the one or more contextual relationship graphs to identify one or more of the plurality of nodes that are related to the plurality of words, wherein the analyzing is based in part on one or more profile attributes related to the user that include information about a purchase history of the user, and wherein the analyzing is further based on one or more contextual attributes related to the page of information, the one or more contextual attributes including information about prior changes to content of the page of information;

receiving click-through-rates of advertising content for each of the plurality of nodes corresponding to the products;

filtering at least one of the identified nodes to a filtered set of one or more nodes based on feedback from the click-through-rates being less than a threshold for each of the filtered at least one identified nodes;

selecting, by the configured computer system, the targeted advertising content for the received request to reflect one or more products corresponding to the filtered set of one or more nodes; and

indicating, by the configured computer system, the selected targeted advertising content to enable the selected targeted advertising content to be provided to the user along with the page of information.

2. The method of claim 1 wherein the one or more contextual relationship graphs include at least one of a content graph, a category graph, and a content/category graph.

3. The method of claim 1 wherein the analyzing of the plurality of words and the one or more contextual relationship graphs includes determining a relative strength of a contextual relationship of the plurality of words to at least one of the identified one or more nodes, and wherein the selecting of the targeted advertising content is based at least in part on the determined relative strength.

4. The method of claim 3 wherein the determining of the relative strength of the contextual relationship includes utilizing at least one of collaborative filtering and Bayesian learning.

5. The method of claim 3 wherein the determining of the relative strength of the contextual relationship is based on a number of the identified nodes and a proximity within the one or more contextual relationship graphs of the identified one or more nodes to each other.

6. The method of claim 1 wherein the products within the represented one or more product categories are at least one of products from a vendor and of services from the vendor.

7. The method of claim 1 wherein the one or more contextual relationship graphs include hierarchical relationships between the plurality of nodes that are defined using first order and higher order relationships, and wherein the analyzing of the plurality of words and the one or more contextual relationship graphs is based at least in part on the hierarchical relationships.

8. The method of claim 1 wherein the page of information is a web page, and wherein the receiving of the request for targeted advertising content includes acquiring the plurality of words from contents of the web page.

9. The method of claim 1 wherein the received request further includes the one or more profile attributes related to the user, and wherein the one or more profile attributes further include an IP (Internet Protocol) address associated with the user.

10. The method of claim 1 wherein the analyzing of the plurality of words and the one or more contextual relationship graphs is further based on one or more behavioral attributes related to prior actions of multiple users.

11. A non-transitory computer-readable storage medium having computer-executable instructions stored thereon that when executed configure a computer system to:

receive, by the configured computer system, a request for targeted advertising content to be provided to a user along with a page of information, the request having information about an environment of the page of information that includes one or more attributes associated with the page;

obtain, by the configured computer system, one or more contextual relationship graphs that represent one or more product categories and include a plurality of nodes corresponding to products within the represented one or more product categories;

analyze, by the configured computer system, the information about the environment of the page of information and the one or more contextual relationship graphs to identify one or more of the plurality of nodes that are related to the environment of the page of information, wherein the analyzing is based in part on one or more profile attributes related to the user that include information about a purchase history of the user, and wherein the analyzing is further based on one or more contextual attributes related to the page of information, the one or more contextual attributes including information about prior changes to content of the page of information;

receive click-through-rates of advertising content for each of the plurality of nodes corresponding to the products;

filter at least one of the identified nodes to a filtered set of one or more nodes based on feedback from the click-through-rates being less than a threshold for each of the filtered at least one identified nodes;

select, by the configured computer system, the targeted advertising content for the received request to reflect one or more products corresponding to the filtered set of one or more nodes; and

indicate, by the configured computer system, the selected targeted advertising content to enable the selected targeted advertising content to be provided to the user along with the page of information.

12. The non-transitory computer-readable storage medium of claim 11 wherein the information about the environment of the page of information that is received in the request includes a plurality of words that are contents of the page of information.

13. The non-transitory computer-readable storage medium of claim 11 wherein the configured computer system is further configured to obtain additional information about the environment of the page of information that includes one or more keywords associated with a location on the page of information, and wherein the analyzing by the configured computer system further includes analyzing the additional information about the environment of the page of information.

14. The non-transitory computer-readable storage medium of claim 11 wherein the information about the environment of the page of information that is received in the request includes audio content that is from contents of the page of information.

15. The non-transitory computer-readable storage medium of claim 11 wherein the one or more attributes include one or more profile attributes related to the user, the one or more profile attributes including information about a history of activities of the user in accessing information.

16. The non-transitory computer-readable storage medium of claim 11 wherein the one or more attributes include one or more behavioral attributes related to prior actions of one or more users, the one or more contextual relationship graphs being further based on the one or more behavioral attributes.

17. The non-transitory computer-readable storage medium of claim 11 wherein the analyzing of the information about the environment of the page of information and the one or more contextual relationship graphs includes determining a relative strength of a contextual relationship of the one or more attributes to at least one of the identified one or more nodes, and wherein the selecting of the targeted advertising content is based at least in part on the determined relative strength.