Method and apparatus for automated selection of interesting content for presentation to first time visitors of a website

• US 9,501,580 B2
• Filed: 07/19/2013
• Issued: 11/22/2016
• Est. Priority Date: 05/04/2012
• Status: Active Grant

• Current Assignee: Pearl.com LLC (JustAnswer LLC)
• Original Assignee: Pearl.com LLC (JustAnswer LLC)
• Inventors: Cooper, Edwin
• Primary Examiner(s): Hutton, Nan
• Application Number:
  US13/946,989
• Publication Number:
  US 20130304749A1
• Time in Patent Office: 1,222 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

Embodiments of the present invention provide systems and methods for automatically identifying content that may be interesting visitors of a website in the absence of any information on the visitors'"'"' interest or preferences.

Claims

1. A computer implemented method, comprising:

selecting a content item from a plurality of content that is candidate for presentation to first time visitors of a website;

identifying all topics present in the selected content item;

scoring each identified topic;

associating each scored topic with at least one subject matter category;

calculating a first score associated with the selected content item based on an intercategory topic density determined for the selected content item;

calculating a second score associated with the selected content item based on a topic density determined for the selected content item;

calculating a third score associated with the selected content item based on a presentability of the selected content item;

calculating a weighted average of the first, second and third score to compute an interestingness score for the selected content item; and

presenting the selected content item to the first time visitors of the website when it is determined that the interestingness score calculated for the selected content item is greater than a threshold.

2. The method of claim 1, wherein computing the interestingness score includes an analysis of information about the first time visitors.

3. The method of claim 2, wherein the information includes a browser type of the first time visitors, a physical location of the first time visitors, and information about how the first time visitors landed on the website.

4. The method of claim 1, wherein calculating the first, second, and third scores is based on an importance measure.

5. The method of claim 4, wherein the scoring uses a modified TFIDF methodology.

6. The method of claim 1, wherein the scored topics are filtered based on logical conditions such as how often each topic appears in a subject category.

9. The method of claim 1, wherein calculating the first score includes identifying a number of topics present within the selected content item that are each associated with a plurality of subject matter categories.

10. The method of claim 1, wherein calculating the second score includes identifying a total number of topics present within the selected content item.

11. The method of claim 1, wherein the third score is calculated for the selected content item based on a capitalization of words within the selected content item, a number of grammatical errors within the selected content item, a use of correct punctuation within the selected content item, a length of a display window associated with the selected content item, and a length of the selected content item compared to the length of the display window associated with the selected content item.

12. The method of claim 11, wherein the third score is reduced when it is determined that the length of the selected content item is shorter or longer than the length of the display window.

13. The method of claim 12, wherein the third score is reduced by a first amount when it is determined that the length of the selected content item is shorter than the length of the display window, and is reduced by a second amount greater than the first amount when it is determined that the length of the selected content item is longer than the length of the display window.

7. A non-transitory machine-readable storage medium having embodied thereon instructions which when executed by at least one processor, causes a machine to perform a method comprising:

selecting a content item from a plurality of content that is candidate for presentation to first time visitors of a website;

identifying all topics present in the selected content item;

scoring each identified topic;

associating each scored topic with at least one subject matter category;

calculating a first score associated with the selected content item based on an intercategory topic density determined for the selected content item;

calculating a second score associated with the selected content item based on a topic density determined for the selected content item;

calculating a third score associated with the selected content item based on a presentability of the selected content item;

calculating a weighted average of the first, second and third score to compute an interestingness score for the selected content item; and

presenting the selected content item to the first time visitors of the website when it is determined that the interestingness score calculated for the selected content item is greater than a threshold.

8. An apparatus, including

a processor, memory connected to the processor;

and

instructions stored on the memory, that when executed by the processor, perform the following;

selecting a content item from a plurality of content that is candidate for presentation to first time visitors of a website;

identifying all topics present in the selected content item;

scoring each identified topic;

associating each scored topic with at least one subject matter category;

calculating a first score associated with the selected content item based on an intercategory topic density determined for the selected content item;

calculating a second score associated with the selected content item based on a topic density determined for the selected content item;

calculating a third score associated with the selected content item based on a presentability of the selected content item;

calculating a weighted average of the first, second and third score to compute an interestingness score for the selected content item; and

presenting the selected content item to the first time visitors of the website when it is determined that the interestingness score calculated for the selected content item is greater than a threshold.