System and method for auto-curation of Q and A websites for search engine optimization

Patent metadata

Field	Value
Publication number	US-10191985-B1
Application number	US-201414283112-A
Country	US
Kind code	B1
Filing date	May 20, 2014
Priority date	May 20, 2014
Publication date	Jan 29, 2019
Grant date	Jan 29, 2019

Abstract

A computer-implemented method of generating rich content webpages from a question and answer (Q&A) library includes providing a topic and one or more seed questions related to the topic. The computing device searches the one or more seed questions against all questions in the Q&A library and identifies questions related to the topic. The computing device clusters the text of the questions related to the topic into a plurality of clusters and then removes substantial duplicates from the plurality of clusters. The computing device generates a rich content webpage by aggregating a question from each cluster onto a single webpage containing the topic.

First claim

What is claimed is:

1. A computer-implemented method of automatically generating rich content landing webpage for a question and answer (Q&A) website, the computer-implemented method comprising:
analyzing, by a computing device including a processor executing computer-executable instructions and in communication with a database hosting a Q&A library and in communication through respective networks with a server that serves respective webpages to respective computers of respective users in response to respective requests submitted through a search engine, respective user click histories of questions contained within the Q&A library;
generating, by the computing device, a click graph comprising related questions obtained from co-clicks by users as determined by analyzing the click history;
clustering, by the computing device, the click graph;
selecting, by the computing device, a plurality of seed questions from the clustered click graph, wherein said selection corresponds to a plurality of seed questions related to a common topic;
searching, by the computing device, the seed questions against a set of questions stored in the Q&A library;
identifying, by the computing device, questions related to the common topic based on common words found in the one or more seed questions;
clustering, by the computing device, the text of the questions related to the common topic into a plurality of clusters under the common topic, wherein each cluster represents a different sub-topic of the common topic;
comparing, by the computing device, the text of at least one of the questions to the text of at least another one of the questions;
determining, by the computing device, that the at least one of the questions is a substantial duplicate of the at least another one of the questions based on the comparing indicating that the at least one of the questions has a textual similarity to the at least another one of the questions above a predetermined textual similarity threshold;
removing, by the computing device, the at least one substantial duplicate from the plurality of clusters;
selecting, by the computing device, a separate question from each cluster after the at least one substantial duplicate has been removed; and
automatically generating, by the computing device, a rich content landing webpage for the Q&A website, the automatically generated rich content landing webpage displaying each selected separate question on a single webpage containing the common topic, the automatically generated rich content landing webpage being presented through a display of a user computer in response to a user search request associated with the common topic.

2. The computer-implemented method of claim 1 , wherein the Q&A library comprises a plurality of tax-related questions.

3. The computer-implemented method of claim 1 , wherein the seed questions are selected at least in part on user votes.

4. The computer-implemented method of claim 1 , wherein the method of generating rich content webpages is performed periodically on the Q&A library.

5. The computer-implemented method of claim 1 , wherein the method of generating rich content webpages is performed dynamically on the Q&A library.

6. The computer-implemented method of claim 1 , further comprising tagging each of the plurality of clusters under the common topic as product-related or tax-related.

7. The computer-implemented method of claim 6 , wherein the rich content webpage contains only product-related questions.

8. The computer-implemented method of claim 6 , wherein the rich content webpage contains only tax-related questions.

9. The computer-implemented method of claim 1 , wherein after the computing device searches the seed questions against the set of questions in the Q&A library and identifies questions related to the common topic, the computing device ranks the identified questions related to the common topic based on top matches.

10. The computer-implemented method of claim 1 , wherein the plurality of clusters under the common topic includes five to fifteen clusters.

11. The computer-implemented method of claim 1 , wherein the single webpage containing the common topic includes five to thirty questions.

12. The computer-implemented method of claim 1 , wherein the automatically generated rich content landing webpage is more likely to have a higher ranking by the search engine.

13. The computer-implemented method of claim 12 , wherein the automatically generated rich content landing webpage is more prominently displayed to users of the search engine by appearing higher on a list of search results generated in response to a query submitted through the search engine.

Assignees

• Intuit Inc

Inventors

• Sarshar Nima
• Goldman Jonathan
• Podgorny Igor A
• Goodyear Todd

Classifications

• G06F17/30864 Primary

  Physics · mapped topic

• G06F16/355 Primary

  Creation or modification of classes or clusters · CPC title

• G06F16/3329

  Natural language query formulation · CPC title

• G06F16/951 Primary

  Indexing; Web crawling techniques · CPC title