System, method and computer readable medium for placing advertisements into web pages

• US 10,699,235 B2
• Filed: 05/05/2009
• Issued: 06/30/2020
• Est. Priority Date: 05/05/2009
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Hauser, Robert R
• Primary Examiner(s): Chakravarti, Arunava
• Application Number:
  US12/435,770
• Publication Number:
  US 20100287134A1
• Time in Patent Office: 4,074 Days
• Field of Search: 705 14
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0263 based upon Internet or website rating
• CPC Class Codes: G06Q 30/0277 Online advertisement

Abstract

Selection of web page advertisements for placement into a web page may use attention data that ranks the elements of the web page according to the attention the elements receive from users during interactions with the web page. The content of ads can be matched to the content of the most highly ranked elements of the web page rather than the web page as a whole. Alternatively, ads can be selected that historically produce a preferred pattern of behavior such as an attention shift from a highly ranked element of the web page to the ad.

Claims

1. A computer-implemented method for dynamically placing content into web pages, the method comprising:

accessing web page data corresponding to a web page, the web page corresponding to a plurality of versions including at least a first version and a second version, the first version including a first set of document object model (DOM) elements and the second version including a second set of DOM elements, the first set of DOM elements being at least partially different from the second set of DOM elements, each DOM element of the first and second set of DOM elements being associated with a screen area on the web page and an event handler that detects cursor movements within the screen area of the DOM element;

continuously receiving, at an event server, an event data stream representing a plurality of cursor movements occurring along a path of a cursor over the web page;

detecting a plurality of events within the event data stream, each event of the plurality of events being detected using the event handler corresponding to a DOM element of the screen area in which the event occurred, and the event handler detecting an event of the plurality of events in response to at least one cursor movement occurring along the path of the cursor within the corresponding DOM element;

grouping one or more events of the plurality of detected events to form a sequence of detected events within the group, the grouping of the one or more events being based on at least one cursor movement pattern that indicates a probabilistic locus of a user'"'"'s attention;

determining at least one attention event as a result of forming the sequence of detected events, the detection of the at least one attention event indicating a probability that a DOM element is associated with a user'"'"'s attention, the probability being based at least in part on a movement characteristic of the at least one attention event, and the DOM element associated with the user'"'"'s attention being the DOM element within which the event occurred or another DOM element adjacent to the DOM element in which the event occurred;

determining a ranking for each DOM element included in each of the first set and second set of DOM elements associated with the plurality of versions of the web page, the ranking representing a popularity of the DOM element within the version of the web page, and the ranking being based on a ratio between a number of attention events associated with the DOM element and a total number of attention events associated with the DOM elements included in the first set and second set of DOM elements;

selecting a DOM element from amongst the DOM elements included in the first set and second set of DOM elements, the selection being based on the ranking associated with the DOM element;

identifying a plurality of candidate content elements for placing into the web page;

comparing content data of each candidate content element of the plurality of candidate content elements to content data of the selected DOM element;

based at least in part on the comparison, determining a relevance score for each of the plurality of candidate content elements selecting, based at least in part on the relevance score, a candidate content element from the plurality of candidate content elements; and

placing the selected candidate content element into the web page.

2. The computer-implemented method according to claim 1, further comprising deriving attention data, wherein deriving the attention data comprises:

recording event data for a plurality of user interactions with the web page;

processing the event data for at least one interaction to create an attention data set for that interaction; and

processing a plurality of the attention data sets to determine the attention data for the web page.

3. The computer-implemented method according to claim 2 wherein processing a plurality of the attention data sets comprises:

selecting a content element;

selecting an attention data set; and

determining a ratio of interaction time attributable to the selected content element relative to a total interaction time of the selected attention data set, wherein the attention data comprises a list of content elements for the web page ranked at least partially dependent on said ratio.

4. The computer-implemented method according to claim 2 wherein processing the event data comprises determining at least one attention event in respect of at least one content element, and wherein processing a plurality of the attention data sets comprises:

selecting a content element;

selecting an attention data set; and

determining a ratio of attention events attributable to the selected content element relative to a total interaction time of the selected attention data set, wherein the attention data comprises a list of content elements for the web page ranked at least partially dependent on said ratio.

5. The computer-implemented method according to claim 2 wherein the content elements comprise DOM elements of a document object model of the web page.

6. The computer-implemented method according to claim 2 wherein the event data comprises a plurality of mouse move events.

7. The computer-implemented method according to claim 1, wherein attention data comprises a plurality of recorded attention events, wherein at least one attention event is derived from an interaction between a user and the web page comprising an embedded candidate advertisement within the web page, and wherein the at least one attention event indicates a shift in user attention from a source element of the web page to the embedded candidate advertisement.

8. The computer-implemented method according to claim 7 comprising determining a relevance score for at least one candidate content element dependent on the attention events for the respective candidate content element.

9. The computer-implemented method according to claim 8 wherein determining a relevance score for a candidate content element comprises:

determining a set of attention events for the web page, the set of attention events comprising the candidate content element as a destination element;

for each attention event of the set, determining the web page source element of the attention event; and

determining the relevance score dependent on the source elements of the attention events.

10. The computer-implemented method according claim 9 wherein the attention data comprises an attention rank of the source elements and wherein the relevance score is dependent on the attention rank.

11. The computer-implemented method according to claim 10, wherein selecting content element comprises selecting an advertisement for which the attention data comprises at least one attention event comprising a highest ranked element as the source element and the selected candidate content element as the destination element.

12. The computer-implemented method according to claim 7 comprising:

recording event stream data from the interaction; and

processing the event stream data to derive one or more of the attention events;

wherein the event stream data comprises a plurality of mouse move events.

13. A server for placing content elements into a web page, the server comprising:

a data store that stores a plurality of content elements;

a content interest data store that stores a list of document object (DOM) elements of the web page, the web page corresponding to a plurality of versions including a first version and a second version, the first version including a first set of DOM elements and the second version including a second set of DOM elements, the first set of DOM elements being at least partially different from the second set of DOM elements, each DOM element of the first and second set of DOM elements being associated with a screen area on the web page and an event handler that detects cursor movements and interactions within the screen area of the DOM element; and

a processing module configured to;

receive a request corresponding to a Uniform Resource Locator (URL);

continuously receive an event data stream representing a plurality of cursor movements occurring along a path of a cursor over the web page;

detect a plurality of events within the event data stream, each event of the plurality of events being detected using the event handler corresponding to a DOM element of the screen area in which the event occurred, and the event handler detecting an event of the plurality of events in response to at least one cursor movement occurring along the path of the cursor within the corresponding DOM element;

group one or more events of the plurality of detected events to form a sequence of detected events within the group, the grouping of the one or more events being based on at least one cursor movement pattern that indicates a probabilistic locus of a user'"'"'s attention;

determining at least one attention event as a result of forming the sequence of detected events, the detection of the at least one attention event indicating a probability that a DOM element is associated with a user'"'"'s attention, the probability being based at least in part on a movement characteristic of the at least one attention event, and the DOM element associated with the user'"'"'s attention being the DOM element within which the event occurred or another DOM element adjacent to the DOM element in which the event occurred;

determine a ranking for each DOM element included in each of the first set and second set of DOM elements associated with the plurality of versions of the web page, the ranking representing a popularity of the DOM element within the version of the web page, and the ranking being based on a ratio between a number of attention events associated with the DOM element and a total number of attention events associated with the DOM elements included in the first set and second set of DOM elements

select a DOM element from amongst the DOM elements included in the first set and second set of DOM elements, the selection being based on the ranking associated with the DOM element;

identify a plurality of candidate content elements for placing into the web page;

compare content data of each candidate content element of the plurality of candidate content elements to content data of the selected DOM element;

based at least in part on the comparison, determine a relevance score for each of the plurality of candidate content elements select, based at least in part on the relevance score, a candidate content element place the selected candidate content element into the web page; and

placing the selected candidate content element into the web page.

14. The server according to claim 13, wherein the processing module is configured to select an ad for which ad performance statistics comprise at least one attention event comprising a highest ranked document object model as a source element and the selected ad as a destination element.

15. A non-transitory computer-readable medium comprising computer executable instructions for execution by a processor, that, when executed, cause the processor to:

access web page data corresponding to a web page, the web page corresponding to a plurality of versions including a first version and a second version, the first version including a first set of document object model (DOM) elements and the second version including a second set of DOM elements, the first set of Dom elements being at least partially different from the second set of DOM elements, each DOM element of the first set and second set of DOM elements being associated with a screen area on the web page and an event handler that detects cursor movements or interactions within the screen area of the DOM element;

continuously receive, at an event server, an event data stream representing a plurality of cursor movements occurring along a path of a cursor over the web page;

detect a plurality of events within the event data stream, each event of the plurality of events being detected using the event handler corresponding to a DOM element of the screen area in which the event occurred, and the event handler detecting an event of the plurality of events in response to at least one cursor movement occurring along the path of the cursor within the corresponding DOM element;

group one or more events of the plurality of detected events to form a sequence of detected events within the group, the grouping of the one or more events being based on at least one cursor movement pattern that indicates a probabilistic locus of a user'"'"'s attention;

determine at least one attention event as a result of forming the sequence of detected events, the detection of the at least one attention event indicating a probability that a DOM element is associated with a user'"'"'s attention, the probability being based at least in part on a movement characteristic of the at least one attention event, and the DOM element associated with the user'"'"'s attention being the DOM element within which the event occurred or another DOM element adjacent to the DOM element in which the event occurred;

determine a ranking for each DOM element included in each of the first set and second set of DOM elements associated with the plurality of versions of the web page, the ranking representing a popularity of the DOM element within the version of the web page, and the ranking being based on a ratio between a number of attention events associated with the DOM element and a total number of attention events associated with the DOM elements included in the first set and second set of DOM elements;

select a DOM element from amongst the DOM elements included in the first set and second set of DOM elements, the selection being based on the ranking associated with the DOM element;

identify a plurality of candidate content elements for placing into the web page;

compare content data of each candidate content element of the plurality of candidate content elements to content data of the selected DOM element;

based at least in part on the comparison, determine a relevance score for each of the plurality of candidate content elements select, based at least in part on the relevance score, a candidate content element from the plurality of candidate content elements; and

place the selected candidate content element into the web page.

16. The non-transitory computer-readable medium according to claim 15 wherein determining the relevance score comprises:

determining a set of attention events for the web page that comprise the respective candidate content element as a destination element;

for each attention event of the set, determining the DOM element that is a source of the attention event; and

weighting the relevance score dependent on the rank of the source element of the attention events.