Determining relevance of a document to a query based on spans of query terms

• US 7,480,652 B2
• Filed: 10/26/2005
• Issued: 01/20/2009
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ma, Wei-Ying, Wen, Ji-Rong, Song, Ruihua
• Primary Examiner(s): Mahmoudi; Tony
• Assistant Examiner(s): Zhao; Yu
• Application Number:
  US11/259,621
• Publication Number:
  US 20070094234A1
• Time in Patent Office: 1,182 Days
• Field of Search: 707/2, 707/3, 707/4, 707/5, 715/513
• US Class Current: 1/1
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A relevance system determines the relevance of a query term to a document based on spans within the document that contain the query term. The relevance system aggregates the relevance of the query terms into an overall relevance for the document. For each query term, the relevance system calculates a span relevance for each span that contains that query term. The relevance system then aggregates the span relevances for a query term into a query term relevance for that document. The relevance system may aggregate the query term relevances into a document relevance.

Claims

1. A method in a computer system with a processor and memory for determining relevance of a query to a document, the query having query terms, the method comprising:

receiving from a user the query;

for each of a plurality of documents,

identifying spans of query terms within the document with no repeated occurrences of a query term, each span including multiple query terms and having a span width, wherein at least one span includes at least three query terms, wherein a distance between adjacent query terms within a span is less than a threshold distance, and wherein the distance between two query terms is based on the number of non-query terms between the two query terms;

for each identified span, calculating a span relevance based on the number of query terms in the span and the inverse of the width of the span;

for each query term, aggregating the calculated span relevances for each span that contains the query term into a query term relevance of the query term to the document, wherein the aggregating includes summing the calculated span relevance for each span that contains the query term; and

aggregating the query term relevances for the query terms into a document relevance indicating relevance of the document to the query; and

displaying an indication of the documents in an order based on the relevance of the documents to the received query.

2. The method of claim 1 wherein the span relevance for a span is calculated based on the following:

$f<br><br>\left(t,{\mathrm{espan}}_i\right)=\frac{n_i^y}{{\mathrm{Width}<br><br>\left({\mathrm{espan}}_i\right)}^x}$

where t is a query term, espan_i is a span that contains t, n_i is the number of query terms that occur in espan_i, Width(espan_i) is the span width of espan_i, x is an exponent that is used to control the influence of the span width, and y is an exponent that is used to control the influence of the number of query terms in the span.

3. The method of claim 1 including replacing a term frequency with the query term relevance in an equation for calculating relevance of a document to a query.

4. The method of claim 3 wherein the equation before replacing is based on term frequency and inverse document frequency.

5. The method of claim 3 wherein term frequency is not used to calculate relevance.

6. The method of claim 1 wherein the document is a web page.

7. A method in a computer system with a processor and memory for calculating relevance of a document to a query of query terms, the method comprising:

receiving from a user the query;

for each of a plurality of documents,

identifying spans of query terms within the document, wherein a span includes no repeated occurrences of a query term, wherein at least one span has at least three query terms, wherein each span includes multiple query terms and has a span width, wherein a distance between adjacent query terms within a span is less than a threshold distance, and wherein the distance between two query terms is based on the number of non-query terms between the two query terms;

calculating a relevance contribution of each query term based on the identified spans that contain that query term, the relevance contributing being based on the number of query terms in the identified span and the inverse of the width of the identified span; and

determining relevance of the document to the query based on the calculated relevance contributions without using term frequency by replacing a term frequency with the query term relevance in an equation for calculating relevance of a document to a query; and

displaying an indication of the documents in an order based on the relevance of the documents to the received query.

8. The method of claim 7 wherein the calculating of the relevance contribution of a query term includes calculating relevance of the query term resulting from a span based on the following:

$f<br><br>\left(t,{\mathrm{espan}}_i\right)=\frac{n_i^y}{\mathrm{Width}<br><br><br><br>{\left({\mathrm{espan}}_i\right)}^x}$

where t is a query term, espan_i is a span that contains t, n_i is the number of query terms that occur in espan_i, Width(espan_i) is the span width of espan_i, x is an exponent that is used to control the influence of the span width, and y is an exponent that is used to control the influence of the number of query terms in the span.

9. The method of claim 7 wherein the determining of relevance is based on an equation that uses inverse document frequency.

10. The method of claim 9 wherein term frequency within the equation is replaced with the calculated relevance contribution.

11. A computer-readable storage medium containing instructions for controlling a computer system to identify spans of query terms of a query within a document for use in determining relevance of documents to the query, by a method comprising:

receiving from a user a query of query terms;

for each of a plurality of documents,

identifying query terms within the document;

identifying sequences of query terms wherein a sequence includes no repeated occurrences of a query term, wherein at least one sequence includes at least three query terms, wherein a distance between adjacent query terms within a sequence is less than a threshold distance, and wherein the distance between two query terms is based on the number of non-query terms between the two query terms wherein a sequence is a span of query terms; and

for each of the identified query terms of the document,

for each span that contains the query term, increasing relevance of the document to the received query by a span relevance of the query term that is based on the number of query terms within the span and an inverse of the span width, wherein the relevance of the document is based on replacing a term frequency with a query term relevance derived from the span relevance in an equation for calculating relevance of a document to a query; and

displaying an indication of documents in an order based on the relevance of the documents to the received query.

12. The computer-readable storage medium of claim 11 wherein when a sequence of query terms is adjacent to two occurrences of the same query term, including within the sequence the query term that is closest to a query term of the sequence.

13. The computer-readable storage medium of claim 11 including calculating a relevance of query terms based on the following:

$f<br><br>\left(t,{\mathrm{espan}}_i\right)=\frac{n_i^y}{{\mathrm{Width}<br><br>\left({\mathrm{espan}}_i\right)}^x}$

where t is a query term, espan_i is a span that contains t, n_i is the number of query terms that occur in espan_i, Width(espan_i) is the span width of espan_i, x is an exponent that is used to control the influence of the span width, and y is an exponent that is used to control the influence of the number of query terms in the span.