Determining relevant content for keyword extraction

• US 9,667,733 B2
• Filed: 03/04/2015
• Issued: 05/30/2017
• Est. Priority Date: 03/04/2015
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Duggal, Ashish, Soni, Sachin, Dhawan, Anmol, Chang, Walter W.
• Primary Examiner(s): Lim, Krisna
• Application Number:
  US14/638,737
• Publication Number:
  US 20160261701A1
• Time in Patent Office: 818 Days
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04N 19/436 using parallelised computational arrangements
• CPC Class Codes: H04N 19/44 Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder
• CPC Class Codes: H04N 19/625 using discrete cosine transform [DCT]
• CPC Class Codes: H04N 19/91 Entropy coding, e.g. variable length coding [VLC] or arithmetic coding
• CPC Class Codes: H04N 19/93 Run-length coding

Abstract

The present disclosure is directed toward systems and methods for analyzing user-specific information and determining content within one or more web pages that has been experienced by one or more users. Furthermore, the present disclosure is directed toward identifying and providing actionable data based on keywords experienced by one or more users.

Claims

1. In a digital medium environment for analyzing web traffic, a method for enhancing analytics of user navigation of a website comprising:

identifying a first user navigation path comprising navigation from a first web page to a second web page by a user;

identifying a first set of keywords from content experienced by the user from the first web page;

identifying a second set of keywords from content experienced by the user from the second web page;

associating the first set of keywords with a navigation from the first web page to the second web page;

associating the second set of keywords with a navigation away from the second web page; and

generating a report associated with the first user navigation path, wherein the report is based, at least in part, on the association of the first set of keywords with the navigation from the first web page to the second web page, and on the association of the second set of keywords with the navigation away from the second web page.

2. The method as recited in claim 1, wherein identifying the first user navigation path comprising the first web page and the second web page navigated by the user comprises parsing one or more web server log files.

3. The method as recited in claim 1, wherein

identifying a first set of keywords from content experienced by the user from the first web page comprises monitoring scroll behavior of the user to identify content experienced by the user at a particular scroll position within the first web page, and

identifying a second set of keywords from content experienced by the user from the second web page comprises monitoring scroll behavior of the user to identify content experienced by the user at a particular scroll position within the second web page.

4. The method as recited in claim 1, wherein

identifying a first set of keywords from content experienced by the user from the first web page comprises tracking eye movement of the user to identify a portion of content within the first web page corresponding with the eye movement, and

identifying a second set of keywords from content experienced by the user from the second web page comprises tracking eye movement of the user to identify a portion of content within the second web page corresponding with the eye movement.

5. The method as recited in claim 3, wherein

identifying the first set of keywords from content experienced by the user from the first web page further comprises extracting the first set of keywords from content experienced by the user at the particular scroll position within the first web page utilizing a natural language processing engine, and

identifying the second set of keywords from content experienced by the user from the second web page further comprises extracting the second set of keywords from content experienced by the user at the particular scroll position within the second web page utilizing the natural language processing engine.

6. The method as recited in claim 3, further comprising assigning a weight to each of the first set of keywords relative to a time spent by the user at the particular scroll position within the first web page.

7. The method as recited in claim 1, further comprising:

identifying a second user navigation path comprising navigation from the second web page to a third web page by the user;

identifying a third set of keywords from content experienced by the user from the third web page;

assigning a weight to each of the third set of keywords based on a time spent by the user at a particular scroll position within the third web page;

associating of the second set of keywords with a navigation from the second web page to the third web page; and

associating the third set of keywords with a navigation away from the third web page.

8. The method as recited in claim 1, wherein generating the report associated with the first user navigation path comprises generating one or more of a next page keyword report, a previous page keyword report, or a prominent keyword report.

9. The method as recited in claim 8, wherein generating the next page keyword report comprises generating a display of keywords associated with navigation away from the second web page.

10. The method as recited in claim 8, wherein generating the previous page keyword report comprises generating a display of keywords associated with navigation to the second web page.

11. The method as recited in claim 8, wherein generating the prominent keyword report comprises:

identifying one or more keywords from the first set of keywords having a weight above a particular threshold; and

generating a display of the identified one or more keywords.

12. The method as recited in claim 8, wherein generating the report comprises generating a display of a connecting keywords tag cloud.

13. In a digital medium environment for analyzing web traffic, a method for enhancing analytics of user navigation of websites comprising:

identifying a user navigation path comprising a plurality of web pages including at least a first web page and a second web page of a web site navigated by a user, wherein the second web page represents an exit point of the user from the website;

identifying a first set of keywords from content experienced by the user from the first web page;

identifying a second set of keywords from content experienced by the user from the second web page within a threshold amount of time preceding the exit point of the user from the web site;

associating the first set of keywords with a navigation from the first web page to the second web page;

associating the second set of keywords with a navigation away from the website; and

generating a fallout report associated with the user navigation path, wherein the fallout report is based, at least in part, on the association of the second set of keywords with the navigation away from the website.

14. The method as recited in claim 13, wherein

identifying the first set of keywords from content experienced by the user from the first web page comprises monitoring scroll behavior of the user to identify content experienced by the user at a particular scroll position within the first web page, and

identifying the second set of keywords from content experienced by the user from the second web page comprises monitoring scroll behavior of the user to identify content experienced by the user at a particular scroll position within the second web page before exiting the website.

15. The method as recited in claim 14, wherein

identifying the first set of keywords from content experienced by the user from the first web page further comprises extracting the first set of keywords from content experienced by the user at the particular scroll position within the first web page utilizing a natural language processing engine, and

identifying the second set of keywords from content experienced by the user from the second web page further comprises extracting the second set of keywords from content experienced by the user at the particular scroll position within the second web page utilizing the natural language processing engine.

16. The method as recited in claim 15, further comprising associating a weight with each of the first set of keywords and each of the second set of keywords, wherein the weight assigned to a particular keyword within the first set of keywords or the second set of keywords is relative to a time spent by the user at the particular scroll position indicating the content experienced by the user from which the particular keyword is identified.

17. The method as recited in claim 16, wherein generating ft the fallout report comprises generating a display of the keywords associated with the exit point of user from the website.

18. The method as recited in claim 17, further comprising:

identifying one or more additional user navigation paths navigated by additional users, wherein the one or more additional user navigation paths each include an additional navigation away from the web site;

identifying a third set of keywords from content experienced by each of the additional users within the threshold amount of time before navigating away from the website;

associating the third set of keywords with the navigation away from the website; and

updating the fallout report to generate an additional display including the third set of keywords.

19. The method as recited in claim 18, further comprising generating a full path report, wherein generating the full path report comprises:

identifying, from within the user navigation path, a sequence of web pages navigated by the user starting at an entry point of the user into the web site and ending at the exit point of the user from the website;

identifying, for each of the web pages indicated in the sequence of web pages navigated by the user, a set of keywords from content experienced by the user on each web page; and

providing, for each of the web pages indicated in the sequence of web pages navigated by the user, a further display of the set of keywords.

20. In a digital medium environment for analyzing web traffic, a system for enhancing analytics of user navigation of a website comprising:

at least one processor; and

at least one non-transitory computer-readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to;

identify a first user navigation path comprising navigation from a first web page to a second web page by a user;

identify a first set of keywords from content experienced by the user from the first web page;

identify a second set of keywords from content experienced by the user from the second web page;

associate the first set of keywords with a navigation from the first web page to the second web page;

associated the second set of keywords with a navigation away from the second web page; and

generate a report associated with the first user navigation path, wherein the report is based, at least in part, on the association of the first set of keywords with the navigation from the first web page to the second web page, and the association of the second set of keywords with the navigation away from the second web page.