Determining relevant content for keyword extraction

• US 9,906,613 B2
• Filed: 04/18/2017
• Issued: 02/27/2018
• Est. Priority Date: 03/04/2015
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Dhawan, Anmol, Chang, Walter W., Soni, Sachin, Duggal, Ashish
• Primary Examiner(s): Lim, Krisna
• Application Number:
  US15/490,570
• Publication Number:
  US 20170223124A1
• Time in Patent Office: 315 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 internet-based traffic comprising:

analyzing analytics data associated with internet-based navigation by a plurality of users;

for a user interaction associated with a webpage in the internet-based navigation, identifying content on the webpage experienced by each user who performed the user interaction;

identifying one or more keywords from the identified content experienced by each user who performed the user interaction; and

generating a report for the internet-based navigation, wherein the report is based, at least in part, on an association of the user interaction with the identified one or more keywords.

2. The method as recited in claim 1, wherein analyzing analytics data associated with internet-based navigation by the plurality of users comprises identifying a plurality of user interactions performed by the plurality of users in association with webpages in the internet-based navigation.

3. The method as recited in claim 2, wherein identifying the plurality of user interactions performed by the plurality of users comprises identifying one or more of scrolling behavior, eye movements, or other interactions associated with each webpage visited by users of the plurality of users.

4. The method as recited in claim 3, wherein identifying scrolling behavior comprises identifying at least one of:

a total time spent on the webpage, a time spent at a particular scroll position within the webpage, or a time that elapsed between particular scroll positions within the webpage.

5. The method as recited in claim 3, wherein identifying eye movements comprises identifying fixations and saccades in the eye movements of the users of the plurality of users.

6. The method as recited in claim 3, wherein identifying other interactions associated comprises identifying at least one of:

mouse hovers, touch gestures, clicks, page lands, or keyboard inputs.

7. The method as recited in claim 1, wherein, for the user interaction associated with the webpage in the internet-based navigation, identifying content on the webpage experienced by each user who performed the user interaction comprises:

identifying one or more portions of the webpage indicated by the user interaction as having been experienced by each user who performed the user interaction; and

extracting content from the identified one or more portions of the webpage.

8. The method as recited in claim 7, wherein extracting content from the identified one or more portions of the webpage comprises extracting content from one or more of:

a block of text in an identified portion of the webpage, a metatag associated with an identified portion of the webpage, or a uniform resource locator within a hyperlink displayed in an identified portion of the webpage.

9. The method as recited in claim 8, wherein identifying one or more keywords from the identified content experienced by each user who performed the user interaction comprises utilizing natural language processing to determine one or more topics of the identified content, wherein the one or more keywords comprise the determined one or more topics.

10. The method as recited in claim 9, further comprising calculating a weight for each of the identified one or more keywords, wherein calculating the weight for each of the identified one or more keywords comprises:

determining an amount of time associated with each occurrence of the user interaction in the internet-based navigation; and

calculating the weight for each of the identified one or more keywords that is proportional to the determined amount of time.

11. The method as recited in claim 10, wherein generating the report for the internet-based navigation comprises the identified one or more keywords and the calculated weights for each of the identified one or more keywords.

12. In a digital media environment for analyzing web traffic, a method for enhancing analytics of internet-based traffic comprising:

analyzing analytics data associated with internet-based navigation by a plurality of users;

for each user interaction in the internet-based navigation, identifying content experienced by each user who performed the user interaction;

identifying one or more keywords from the identified content experienced by each user who performed the user interaction; and

generating a report for the internet-based navigation that indicates identified keywords experienced in connection with each user interaction in the internet-based navigation.

13. The method as recited in claim 12, wherein:

a user interaction in the internet-based navigation comprises entry to a webpage;

identifying content experienced by each user who performed the user interaction comprises identifying content viewed by each user prior to entry to the webpage;

identifying one or more keywords from the identified content experienced by each user who performed the user interaction comprises extracting the one or more keywords from the identified content viewed by each user prior to entry to the webpage; and

generating the report comprises associating the extracted one or more keywords with the entry to the webpage by users of the plurality of users.

14. The method as recited in claim 12, wherein:

a user interaction in the internet-based navigation comprises exit from a webpage;

identifying content experienced by each user who performed the user interaction comprises identifying content viewed by each user prior to exit from the webpage;

identifying one or more keywords from the identified content experienced by each user who performed the user interaction comprises extracting the one or more keywords from the identified content viewed by each user prior to exit from the webpage; and

generating the report comprises associating the extracted one or more keywords with the exit from the webpage by users of the plurality of users.

15. The method as recited in claim 12, wherein:

a user interaction in the internet-based navigation comprises navigation from a first webpage to a second webpage;

identifying content experienced by each user who performed the user interaction comprises identifying content viewed by each user in connection with the navigation from the first webpage to the second webpage;

identifying one or more keywords from the identified content experienced by each user who performed the user interaction comprises extracting the one or more keywords from the identified content viewed by each user in connection with the navigation from the first webpage to the second webpage; and

generating the report comprises associating the extracted one or more keywords with the navigation from the first webpage to the second webpage by users of the plurality of users.

16. The method as recited in claim 12, wherein the internet-based navigation includes a sequence of webpages most frequently followed by the plurality of users to a web site.

17. The method as recited in claim 12, further comprising determining a weight for each of the identified keywords in the report.

18. The method as recited in claim 17, wherein determining the weight for a given keyword associated with a given user interaction comprises one or more of:

determining an amount of time that was spent by each user while experiencing content associated with the given user interaction from which the given keyword was extracted;

or

a number of users of the plurality of users that experienced the given keyword when performing the given user interaction.

19. In a digital medium environment for analyzing web traffic, a system for enhancing analytics of internet-based traffic comprising:

at least one server; and

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

analyze analytics data associated with internet-based navigation by a plurality of users;

for a user interaction associated with a webpage in the internet-based navigation, identify content on the webpage experienced by each user who performed the user interaction;

identify one or more keywords from the identified content experienced by each user who performed the user interaction; and

generate a report for the internet-based navigation, wherein the report is based, at least in part, on an association of the user interaction with the identified one or more keywords.

20. The system as recited in claim 19, further comprising instructions that, when executed by the at least one server, cause the system to track, for each user of the plurality of users, a total time spent on the webpage, a time spent at a particular scroll position within the webpage, or a time that elapsed between particular scroll positions within the webpage.