Discerning human intent based on user-generated metadata

• US 10,185,754 B2
• Filed: 12/23/2013
• Issued: 01/22/2019
• Est. Priority Date: 07/31/2010
• Status: Active Grant

• Current Assignee: Cision US Inc. (Cision Ltd.)
• Original Assignee: Vocus NM, LLC (Cision Ltd.)
• Inventors: Sankhla, Vishal Harshvardhan, Kadam, Rajeev Anand
• Primary Examiner(s): Waldron, Scott A.
• Assistant Examiner(s): Lodhi, Andalib F
• Application Number:
  US14/138,718
• Publication Number:
  US 20140114959A1
• Time in Patent Office: 1,856 Days
• Field of Search: 707741, 707769
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods and systems for discerning human intent based on user-generated metadata are provided. Communications from a plurality of social networks are evaluated to determine whether they are associated with contexts indicative of user intent. When a social network communication is determined to be associated with such a context, a tag may be generated associating the social network communication with the indicated human intent. In addition, information regarding the social network communication may be exported to an application responsible for responsive action.

Claims

1. A method for discerning human intent based on metadata, the method comprising:

receiving information over a communication network indicative of an interest in a topic and a human intent related to the topic;

accessing a plurality of sources of digital data over the communication network, the plurality of sources publishing digital data regarding a plurality of different topics and indicative of a plurality of different human intents; and

executing instructions stored in memory, wherein execution of the instructions by a processor;

automatically filters the digital data based on language associated with the topic of interest,

automatically refines the filtered results based on identifying one or more additional keywords or metadata indicative of common contexts from a set of a plurality of communications published in a same timeframe, the contexts indicative of human intents of interest, wherein the human intents of interest include intent to buy and dissatisfaction,

automatically generates a tag associating the filtered and refined results with one or more action items associated with each human intent of interest,

automatically exports a set of filtered and refined results that have been tagged in association with intent to buy to a first application for performing the one or more actions items associated with the intent to buy, and

automatically exports a set of filtered and refined results that have been tagged in association with dissatisfaction to a second application for performing the one or more actions items associated with dissatisfaction.

2. The method of claim 1, further comprising storing information in memory regarding a plurality of topics, each topic associated with one or more keywords.

3. The method of claim 1, further comprising storing information in memory regarding a plurality of human intents, each human intent associated with one or more indicative contexts.

4. The method of claim 1, further comprising sending the tagged results to one or more designated recipients for performance of the action items.

5. The method of claim 1, further comprising identifying a user associated with each of the tagged results.

6. The method of claim 5, further comprising receiving subsequent digital data indicating that the user is no longer associated with the human intent of interest with respect to the topic, and updating the tag.

7. The method of claim 6, wherein a new action item associated with the updated tag cancels a previous action item associated with the user.

8. The method of claim 1, wherein the contexts include metadata associated with the language.

9. The method of claim 8, wherein the contexts include metadata in communications surrounding or responsive to the language.

10. The method of claim 8, wherein the contexts include metadata generated in a same timeframe as the language.

11. An apparatus for discerning human intent based on metadata, the apparatus comprising:

a communication interface for communicating over a communication network to;

receive information indicative of an interest in a topic and a human intent related to the topic, and

access a plurality of sources of digital data, the plurality of sources publishing digital data regarding a plurality of different topics and indicative of a plurality of different human intents; and

a processor for executing instructions stored in memory, wherein execution of the instructions by the processor;

automatically filters the digital data based on language associated with the topic of interest,

automatically refines the filtered results based on identifying one or more additional keywords or metadata indicative of common contexts from a set of a plurality of communications published in a same specified timeframe, the contexts indicative of human intents of interest, wherein the human intents of interest include intent to buy and dissatisfaction,

automatically generates a tag associating the filtered and refined results with one or more action items associated with each human intent of interest,

automatically exports a set of filtered and refined results that have been tagged in association with intent to buy to a first application for performing the one or more actions items associated with the intent to buy, and

automatically exports a set of filtered and refined results that have been tagged in association with dissatisfaction to a second application for performing the one or more actions items associated with dissatisfaction.

12. The apparatus of claim 11, further comprising a memory for storing information in memory regarding a plurality of topics, each topic associated with one or more keywords.

13. The apparatus of claim 11, further comprising a memory for storing information in memory regarding a plurality of human intents, each human intent associated with one or more indicative contexts.

14. The apparatus of claim 11, wherein the communications interface sends the tagged results to one or more designated recipients for performance of the action items.

15. The apparatus of claim 11, wherein further execution of instructions by the processor identifies a user associated with each of the tagged results.

16. The apparatus of claim 15, wherein the communications interface receives subsequent digital data indicating that the user is no longer associated with the human intent of interest with respect to the topic, and updating the tag.

17. The apparatus of claim 16, wherein a new action item associated with the updated tag cancels a previous action item associated with the user.

18. The apparatus of claim 11, wherein the contexts include metadata associated with the language.

19. The apparatus of claim 18, wherein the contexts include metadata in communications surrounding or responsive to the language.

20. The apparatus of claim 18, wherein the contexts include metadata generated in a same timeframe as the language.

21. A non-transitory computer-readable storage medium, having embodied thereon a program executable by a processor to perform a method for discerning human intent based on metadata, the method comprising:

receiving information over a communication network indicative of an interest in a topic and a human intent related to the topic;

accessing a plurality of sources of digital data over the communication network, the plurality of sources publishing digital data regarding a plurality of different topics and indicative of a plurality of different human intents;

automatically filtering the digital data based on language associated with the topic of interest;

automatically refining the filtered results based on identifying one or more additional keywords or metadata indicative of common contexts from a set of a plurality of communications published in a same specified timeframe, the contexts indicative of human intents of interest, wherein the human intents of interest include intent to buy and dissatisfaction;

automatically generating a tag associating the filtered and refined results with one or more action items associated with each human intent of interest;

automatically exporting a set of filtered and refined results that have been tagged in association with intent to buy to a first application for performing the one or more actions items associated with the intent to buy; and

automatically exporting a set of filtered and refined results that have been tagged in association with dissatisfaction to a second application for performing the one or more actions items associated with dissatisfaction.