Search engine optimization in social question and answer systems

• US 10,031,970 B1
• Filed: 09/12/2013
• Issued: 07/24/2018
• Est. Priority Date: 09/12/2013
• Status: Active Grant

• Current Assignee: Intuit, Inc.
• Original Assignee: Intuit, Inc.
• Inventors: Podgorny, Igor A., Goodyear, Todd Frey, Feeley, Bradly S.
• Primary Examiner(s): Kumar, Anil N
• Application Number:
  US14/025,470
• Time in Patent Office: 1,776 Days
• CPC Class Codes: G06F 16/3347 using vector based model
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

The described embodiments relate to techniques for facilitating text inputs with long-tail keywords from a user in a social question and answer (Q&A) application. During operation, the system receives an input from the user. The system then applies a predictive model to determine a predicted business outcome for the received input from the user. Next, the system renders a user interface (UI) for subsequent user interaction with the social Q&A application, based on the predicted business outcome. Finally, the system displays the rendered UI to the user.

Claims

1. A method for facilitating text inputs with long-tail keywords from a user in a social question and answer (Q&

A) application, comprising;

receiving, at a server, a text input from the user at a client computer, wherein the text input poses a query within a community associated with the social Q&

A application, wherein the server comprises a processor and a memory;

applying, by the processor, a predictive model to the received text input;

determining, by the processor, a predicted business outcome associated with the received text input based on the applied predictive model, wherein the predicted business outcome comprises an increase in user traffic resulting from an external search engine referring users of the external search engine to the community, that is predicted to be generated from the received text input based in part on long-tail keywords within the received text input;

determining, by the processor, a type of user interface (UI) to be generated for display to the user for subsequent interaction based on the evaluation predicted business outcome, wherein the type of UI facilitates one of;

a tailored navigation through one or more answers databases before providing a UI component to post the received text input to the community if the predicted business value is below a certain threshold value, or

a direct posting of the received text to the community and receiving a subsequent text input from the user to include in the direct posting of the received text if the predicted business value is above a certain threshold value; and

sending the determined type of UI to the client computer for display at the client computer to facilitate subsequent user-interaction with the Q&

A application.

2. The method of claim 1, wherein the type of UI generated for display is one that facilitates a tailored navigation through one or more answers databases when the predicted business outcome is below a first predefined threshold.

3. The method of claim 1, wherein the type of UI generated for display is one that facilitates the direct posting of the received text when the predicted business outcome is above a second predefined threshold.

4. The method of claim 3, wherein the subsequent text input is directed to the community associated with the Q&

A application.

5. The method of claim 1, wherein applying the predictive model involves obtaining model attributes from one or more of:

content of the received input;

data associated with the user; and

data associated with a product.

6. The method of claim 5, wherein obtaining values for the model attributes from the content of the received input involves:

preprocessing the received input with a natural-language processing model; and

converting the text into an array using a bag-of-words model, wherein the array may be based on an analysis of the most frequently used keywords associated with the Q&

A application.

7. The method of claim 5, wherein values for the model attributes from the data associated with the user are based on one or more of:

a type of the user;

a type of web browser;

a type of operating system; and

a location of the user.

8. The method of claim 5, wherein the values for the model attributes from the data associated with the product are based on one or more of:

a type of product;

a type of product flavor; and

a type of platform.

9. The method of claim 1, wherein determining the predicted business outcome for the received input involves determining one or more of:

a number of potential search engine users who will click on a search engine snippet based on the received input and create an account;

or

a number of potential search engine users who will click on a search engine snippet based on the received input, create an account, and convert to a specified product.

10. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for facilitating text inputs with long-tail keywords from a user in a social question and answer (Q&

A) application, the method comprising;

receiving, at a server, a text input from the user at a client computer, wherein the text input poses a query within a community associated with the social Q&

A application, wherein the server comprises a processor and a memory within a community associated with the social Q&

A application;

applying, by the processor, a predictive model to the received text input;

determining, by the processor, a predicted business outcome associated with the received text input based on the applied predictive model, wherein the predicted business outcome comprises an increase in user traffic resulting from an external search engine, referring users of the external search engine to the community, that is predicted to be generated from the received text input based in part on long-tail keywords within the received text input;

determining, by the processor, a type of user interface (UI) to be generated for display to the user for subsequent interaction based on the evaluation predicted business outcome, wherein the type of UI facilitates one of;

a tailored navigation through one or more answers databases before providing a UI component to post the received text input to the community if the predicted business value is below a certain threshold value, or

a direct posting of the received text to the community and receiving a subsequent text input from the user to include in the direct posting of the received text if the predicted business value is above a certain threshold value; and

sending the determined type of UI to the client computer for display at the client computer to facilitate subsequent user-interaction with the Q&

A application.

11. The computer-readable storage medium of claim 10, the type of UI generated for display is one that facilitates a tailored navigation through one or more answers databases when the predicted business outcome is below a first predefined threshold.

12. The computer-readable storage medium of claim 10, wherein the type of U I generated for display is one that facilitates the direct posting of the received text when the predicted business outcome is above a second predefined threshold.

13. The computer-readable storage medium of claim 12, wherein the subsequent text input is directed to the community associated with the Q&

A application.

14. The computer-readable storage medium of claim 10, wherein applying the predictive model involves obtaining model attributes from one or more of:

content of the received input;

data associated with the user; and

data associated with a product.

15. The computer-readable storage medium of claim 14, wherein obtaining values for the model attributes from the content of the received input involves:

preprocessing the received input with a natural-language processing model; and

converting the text into an array using a bag-of-words model, wherein the array may be based on an analysis of the most frequently used keywords associated with the Q&

A application.

16. The computer-readable storage medium of claim 14, wherein values for the model attributes from the data associated with the user are based on one or more of:

a type of the user;

a type of web browser;

a type of operating system; and

a location of the user.

17. The computer-readable storage medium of claim 14, wherein the values for the model attributes from the data associated with the product are based on one or more of:

a type of product;

a type of product flavor; and

a type of platform.

18. The computer-readable storage medium of claim 10, wherein determining the predicted business outcome for the received input involves determining one or more of:

a number of potential search engine users who will click on a search engine snippet based on the received input and create an account;

or

a number of potential search engine users who will click on a search engine snippet based on the received input, create an account, and convert to a specified product.

19. A system for facilitating text inputs with long-tail keywords from a user in a social question and answer (Q&

A) application, comprising;

a memory;

a processor;

a receiving mechanism configured to receive a text input from the user at a client computer, wherein the text input poses a query within a community associated with the social Q&

A application;

an evaluating mechanism configured to apply a predictive model to the received text input;

a first determining mechanism configured to determine a predicted business outcome associated with the received text input based on the applied predictive model, wherein the predicted business outcome comprises an increase in user traffic resulting from an external search engine, referring users of the external search engine to the community, that is predicted to be generated from the received text input based in part on long-tail keywords within the received text input;

a second determining mechanism configured to determine a type of user interface (UI) to be generated for display to the user for subsequent interaction based on the predicted business outcome, wherein the type of UI facilitates one of;

a tailored navigation through answer databases before providing a UI component to post the received text input to the community if the predicted business value is below a certain threshold value, or

a direct posting of the received text to the community and receiving a further text input from the user if the predicted business value is above a certain threshold value; and

a sending mechanism configured to send the determined type of UI to the client computer for display at the client computer to facilitate subsequent user-interaction with the Q&

A application.

20. The system of claim 19, wherein the application mechanism is further configured to determine the predicted business outcome for the received input by determining one or more of:

a number of potential search engine users who will click on a search engine snippet based on the received input and create an account;

or

a number of potential search engine users who will click on a search engine snippet based on the received input, create an account, and convert to a specified product.