Method and system for determining a level of popularity of submission content, prior to publicizing the submission content with a question and answer support system

• US 10,147,037 B1
• Filed: 07/28/2015
• Issued: 12/04/2018
• Est. Priority Date: 07/28/2015
• Status: Active Grant

• Current Assignee: Intuit, Inc.
• Original Assignee: Intuit, Inc.
• Inventors: Podgorny, Igor A., Cannon, Matthew
• Primary Examiner(s): CHEN, ALAN S
• Application Number:
  US14/810,656
• Time in Patent Office: 1,225 Days
• Field of Search: None
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

A method and system determines a level of popularity of submission content, prior to publicizing the submission content with a question and answer customer support system, to improve user satisfaction with content of the question and answer customer support system, according to one embodiment. The method and system include receiving submission content from a user, and identifying a plurality of attributes of the submission content, according to one embodiment. The method and system include applying at least some of the attributes of the submission content to an analytics model to generate a score that is indicative of a likely level of popularity of the submission content, according to one embodiment. Prior to publicizing the submission content with the question and answer customer support system, the method and system include providing suggestions to the user for altering attributes of the submission content, to affect the score, according to one embodiment.

Claims

1. A computer-implemented method for determining a level of popularity of submission content, prior to publicizing the submission content with a question and answer customer support system, to improve user satisfaction with content of the question and answer customer support system, the method comprising:

receiving, with a computing system, submission content from a user, with a question and answer customer support system;

identifying a plurality of attributes of the submission content;

applying at least some of the attributes of the submission content to an analytics model to generate a score from the analytics model that is indicative of a likely level of popularity of the submission content, wherein the analytics decreases the score with increases in the character length of a question summary included within the submission content; and

prior to publicizing the submission content with the question and answer customer support system, providing suggestions to the user for altering attributes of the submission content, to affect the score that is indicative of the likely level of popularity of the submission content.

2. The method of claim 1, wherein the submission content includes question details.

3. The method of claim 2, wherein attributes of the submission content are selected from a group of attributes consisting of:

a character length of the question details; and

a first token of the question summary.

4. The method of claim 3, wherein the analytics model increases the score with increases in the character length of question details.

5. The method of claim 3, wherein the analytics model adjusts the score at least partially based on the first token of the question summary.

6. The method of claim 2, wherein altering the submission content includes increasing or decreasing a character length of at least one of the question summary and the question details.

7. The method of claim 1, wherein providing suggestions to the user for altering the submission content includes providing popularity-lowering suggestions that are likely to decrease the score that is indicative of the likely level of popularity of the submission content, to reduce a likelihood of views of the submission content by users of the question and answer customer support system after the question and answer customer support system publicizes the submission content.

8. The method of claim 1, wherein providing suggestions to the user for altering the submission content includes providing popularity-raising suggestions that are likely to increase the score that is indicative of the likely level of popularity of the submission content, to increase a likelihood of views of the submission content by users of the question and answer customer support system after the question and answer customer support system publicizes the submission content.

9. The method of claim 1, wherein the score is a floating point number having a range that includes 0 and 1.

10. The method of claim 1, wherein the analytics model is one of a number of analytics models used by the question and answer customer support system for determining the score that is indicative of the likely level of popularity of the submission content.

11. The method of claim 1, wherein the analytics model generates the score using at least one of logistic regression, classification, multinomial logistic regression, and neural networks.

12. The method of claim 1, wherein the score represents a likelihood that the likely level of popularity exceeds a predetermined threshold.

13. The method of claim 12, wherein the predetermined threshold is top 10 percent of viewed content that is posted by the question and answer customer support system.

14. The method of claim 12, wherein the predetermined threshold is top 10 percent of voted-on content that is posted by the question and answer customer support system.

15. The method of claim 1, further comprising:

comparing the score to one or more thresholds to assign the submission content to one or more classes of popularity of content that is posted by the question and answer customer support system.

16. The method of claim 1, further comprising:

determining a likely level of quality of response to the submission content, at least partially based on at least some of the attributes of the submission content,

wherein providing suggestions to the user for altering the submission content includes providing popularity-lowering suggestions that are likely to decrease the score that is indicative of the likely level of popularity of the submission content, if the likely level of quality of response to the submission content is below a first threshold, to reduce a likelihood of views of the submission content by users of the question and answer support system after the question and answer customer support system publicizes the submission content,

wherein providing suggestions to the user for altering the submission content includes providing popularity-raising suggestions that are likely to increase the score that is indicative of the likely level of popularity of the submission content, if the likely level of quality of response to the submission content exceeds a second threshold, to increase the likelihood of views of the submission content by users of the question and answer customer support system after the question and answer customer support system publicizes the submission content.

17. The method of claim 16, wherein the likely level of quality of response is associated with a likelihood of receiving an up vote other than a down vote from users who read the response to the submission content.

18. The method of claim 1, further comprising:

determining a likely level of quality of response to the submission content, at least partially based on at least some of the attributes of the submission content; and

altering the submission content to selectively increase or decrease the score generated by the analytics model for the submission content, to selectively increase or decrease the likely level of popularity of the submission content, to improve a reputation of quality for content of the question and answer customer support system, and to improve conversion rates of potential customers to paying customers for a tax return preparation system associated with the question and answer customer support system.

19. The method of claim 18, wherein altering the submission content includes altering the submission content without notifying the user.

20. The method of claim 1, further comprising:

training the analytics model using one or more previous years content in the question and answer customer support system.

21. A system for determining a level of popularity of submission content, prior to publicizing the submission content with a question and answer customer support system, to improve user satisfaction with content of the question and answer customer support system, the system comprising:

at least one processor; and

at least one memory coupled to the at least one processor, the at least one memory having stored therein instructions which, when executed by any set of the one or more processors, perform a process for determining a level of popularity of submission content, the process including;

receiving, with a computing system, submission content from a user, with a question and answer customer support system;

identifying a plurality of attributes of the submission content;

applying at least some of the attributes of the submission content to an analytics model to generate a score from the analytics model that is indicative of a likely level of popularity of the submission content wherein the analytics model increases the score with increases in a character length of a question summary included within the submission content; and

prior to publicizing the submission content with the question and answer customer support system, providing suggestions to the user for altering attributes of the submission content, to affect the score that is indicative of the likely level of popularity of the submission content.

22. The system of claim 21, wherein the submission content includes question details.

23. The system of claim 22, wherein the plurality of attributes of the submission content are selected from a group of attributes consisting of:

a character length of the question details; and

a first token of the question summary.

24. The system of claim 23, wherein the analytics model increases the score with increases in the character length of question details.

25. The system of claim 23, wherein the analytics model adjusts the score at least partially based on the first token of the question summary.

26. The system of claim 22, wherein altering the submission content includes increasing or decreasing a character length of at least one of the question summary and the question details.

27. The system of claim 21, wherein providing suggestions to the user for altering the submission content includes providing popularity-lowering suggestions that are likely to decrease the score that is indicative of the likely level of popularity of the submission content, to reduce a likelihood of views of the submission content by users of the question and answer customer support system after the question and answer customer support system publicizes the submission content.

28. The system of claim 21, wherein providing suggestions to the user for altering the submission content includes providing popularity-raising suggestions that are likely to increase the score that is indicative of the likely level of popularity of the submission content, to increase a likelihood of views of the submission content by users of the question and answer customer support system after the question and answer customer support system publicizes the submission content.

29. The system of claim 21, wherein the score is a floating point number having a range that includes 0 and 1.

30. The system of claim 21, wherein the analytics model is one of a number of analytics models used by the question and answer customer support system for determining the score that is indicative of the likely level of popularity of the submission content.

31. The system of claim 21, wherein the analytics model generates the score using at least one of logistic regression, classification, multinomial logistic regression, and neural networks.

32. The system of claim 21, wherein the score represents a likelihood that the likely level of popularity exceeds a predetermined threshold.

33. The system of claim 32, wherein the predetermined threshold is top 10 percent of viewed content that is posted by the question and answer customer support system.

34. The system of claim 32, wherein the predetermined threshold is top 10 percent of voted-on content that is posted by the question and answer customer support system.

35. The system of claim 21, wherein the process further comprises:

comparing the score to one or more thresholds to assign the submission content to one or more classes of popularity of content that is posted by the question and answer customer support system.

36. The system of claim 21, wherein the process further comprises:

determining a likely level of quality of response to the submission content, at least partially based on at least some of the attributes of the submission content,

wherein providing suggestions to the user for altering the submission content includes providing popularity-lowering suggestions that are likely to decrease the score that is indicative of the likely level of popularity of the submission content, if the likely level of quality of response to the submission content is below a first threshold, to reduce a likelihood of views of the submission content by users of the question and answer support system after the question and answer customer support system publicizes the submission content,

wherein providing suggestions to the user for altering the submission content includes providing popularity-raising suggestions that are likely to increase the score that is indicative of the likely level of popularity of the submission content, if the likely level of quality of response to the submission content exceeds a second threshold, to increase the likelihood of views of the submission content by users of the question and answer customer support system after the question and answer customer support system publicizes the submission content.

37. The system of claim 36, wherein the likely level of quality of response is associated with a likelihood of receiving an up vote other than a down vote from users who read the response to the submission content.

38. The system of claim 21, wherein the process further comprises:

determining a likely level of quality of response to the submission content, at least partially based on at least some of the attributes of the submission content; and

altering the submission content to selectively increase or decrease the score generated by the analytics model for the submission content, to selectively increase or decrease the likely level of popularity of the submission content, to improve a reputation of quality for content of the question and answer customer support system, and to improve conversion rates of potential customers to paying customers for a tax return preparation system associated with the question and answer customer support system.

39. The system of claim 38, wherein altering the submission content includes altering the submission content without notifying the user.

40. The system of claim 21, wherein the process further comprises:

training the analytics model using one or more previous years content in the question and answer customer support system.