Comparative web search

• US 7,571,162 B2
• Filed: 03/01/2006
• Issued: 08/04/2009
• Est. Priority Date: 03/01/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Wang, Xuanhui, Chen, Zheng, Sun, Jian-Tao, Shen, Dou, Wang, Jian, Zeng, Hua-Jun
• Primary Examiner(s): Robinson; Greta L
• Assistant Examiner(s): Weinrich; Brian E
• Application Number:
  US11/365,961
• Publication Number:
  US 20070208701A1
• Time in Patent Office: 1,252 Days
• Field of Search: 707/5
• US Class Current: 1/1
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

Methods and systems are provided for performing a comparative search. In one example, the comparative search is performed over a network, such as the web, or a database. In one exemplary implementation, a user transmits a plurality of queries which represent the topics that a user wants to compare, and a computing system can automatically retrieve and rank web pages or documents based on both their relevance to queries and the comparative contents they contain. In one such example, the comparative pages are displayed in a pair or other form of a grouping. In another example, comparative results having similar contents may be clustered into meaningful themes.

Claims

1. A computer-implemented method performed by a computer for ranking comparative web results comprising the steps of:

receiving a first search query;

receiving a second search query that is related to the first search query;

processing the first search query to produce first search results, the first search results having elements that are relevant to the first query, and processing the second search query to produce second search results, the second search results having elements that are relevant to the second query; and

generating by the computer a plurality of comparative search result groups that each include an element from the first search results and an element from the second search results by

calculating a score for pairs of elements with a first element of the pair being from the first search results and a second element of the pair being from the second search results, each score for a pair indicating likeliness that the elements form a comparative pair corresponding to the first and second queries, and being based on similarity between content of the elements of the pair, relevance of the first element to the first query, and relevance of the second element to the second query, the score being calculated according to the following equation;

f_q1q2(p1,p2)=α

·

R(p1,q1)+β

·

R(p2,q2)+γ

·

S(p1\q1,p2\q2), p1∈

SR1,p2∈

SR2

wherein SR1 represents the first search results for the first search query q1, SR2 represents the second search results for the second search query q2, p1 represents an element from SR1, p2 represents an element from SR2, R represents relevance of an element to a query, S represents similarity between two elements, p1\q1 represents text content of p1 after removing terms of q1, p2\q2 represents text content of p2 after removing terms of q2, and α

, β

, and γ

represents constants; and

repeatedly selecting in score order a previously unselected pair of elements neither of whose elements are currently in a comparative search result group and creating a comparative search result group with the elements of the selected pair.

2. The computer-implemented method of claim 1, wherein at least one of the search result groups is a pair of web pages.

3. The computer-implemented method of claim 2, further comprising the step of:

displaying the pair of web pages in a pair wise manner.

4. The computer-implemented method of claim 2, further comprising the steps of:

extracting at least one portion of each web page within the pair, the portion comprising at least one element from either the first or second search results.

5. The computer-implemented method of claim 1, wherein the first search query relates to a consumer product and the second search query relates to a similar consumer product.

6. The computer-implemented method of claim 1, further comprising the steps of:

determining that a subset of the plurality of comparative search result groups comprise similar information; and

clustering the subset into a cluster.

7. The computer-implemented method of claim 6, further comprising the step of:

extracting at least one portion of at least one element within the cluster, the at least one element being from either the first or second search results.

8. A computer-implemented method for obtaining comparative web results from a computing device operatively connected to a network through a browser comprising the steps of:

transmitting a first search query to obtain a first search result;

transmitting a second search query that is related to the first search query to obtain a second search result;

receiving at the computing results the plurality of comparative search result groups that each include a first element from the first search result and a second element from the second search result, the plurality of the comparative search result groups being generated based on the following equation;

f_q1q2(p1,p2)=α

·

R(p1,q1)+β

·

R(p2,q2)+γ

·

S(p1\q1,p2\q2), p1∈

SR1,p2∈

SR2

 

wherein SR1 represents the first search results for the first search query q1, SR2 represents the second search results for the second search query q2, p1 represents an element from SR1, p2 represents an element from SR2, R represents relevance of an element to a query, S represents similarity between two elements, p1\q1 represents text content of p1 after removing terms of p1, p2\q2 represents text content of p2 after removing terms of q2, and α

, β

, and γ

represents constants

wherein the elements are grouped based on relevance of the first element to the first search query and relevance of the second element to the second search query.

9. The computer-implemented method of claim 8, wherein at least one of the search result groups is a pair of web pages.

10. The computer-implemented method of claim 9, further comprising the step of:

displaying on a display device the pair of web pages to a user in a pair wise manner.

11. The computer-implemented method of claim 8, further comprising the step of:

displaying a cluster comprising a subset of the plurality of comparative search result groups that comprise similar information.

12. The computer-implemented method of claim 11, further comprising the step of:

displaying a summary of the information within the subset of the plurality of comparative search results, the summary comprising at least one element from either the first or second search results.

13. A computing device for ranking comparative web results, the device having a processor, and a computer-readable medium, the computer-readable medium comprising computer-readable instructions that when executed perform the method of:

receiving a first search query;

receiving a second search query that is related to the first search query;

processing the first search query to produce first search results and processing the second search query to produce second search results; and

generating a plurality of comparative search result groups that each include an element from the first search results and an element from the second search results based on the following equation;

f_q1q2(p1,p2)=α

·

R(p1,q2)+β

·

R(p2,q2)+γ

·

S(p1\q1,p2\q2), p1∈

SR1,p2∈

SR2

 

wherein SR1 represents the first search results for the first search query q1, SR2 represents the second search results for the second search query q2, p1 represents an element from SR1, p2 represents an element from SR2, R represents relevance of an element to a query, S represents similarity between two elements, p1\q1 represents text content of p1 after removing terms of q1, p2\q2 represents text content of p2 after removing terms of q2, and α

, β

, and α

represents constants;

wherein the elements are grouped based on similarity between the content of the elements.

14. The computing device of claim 13, wherein at least one of the search result groups is a pair of web pages.

15. The computing device of claim 14, wherein the computer-readable instructions further comprise the step of:

extracting at least one portion of each web_page within the pair, the portion comprising including at least one element from either the first or second search results.

16. The computing device of claim 13, wherein the computer-readable instructions further comprise the steps of:

determining that a subset of the plurality of comparative search result groups comprise similar information; and

clustering the subset into a cluster.