Ranking documents with social tags
AssigneeMicrosoft Corporation
InventorsYauhen Shnitko, Dmitriy Meyerzon
Life of this patent
Estimating the term…
Abstract
Technologies are described herein for ranking documents with social tags. A number ranking feature containing a number of times a document was tagged is received. A textual property ranking feature containing a union of each social tag associated with the document is also received. The number ranking feature is transformed into a static input value. Further, the textual property ranking feature is transformed into a dynamic input value. A document rank for the document is determined by inputting the static input value and/or the dynamic input value into a ranking function.
Claims19
A computer-implemented method for ranking documents with social tags, the computer-implemented method configured on a computer having a processor and a memory, the computer-implemented method comprising:
- collecting information from at least one user profile regarding one or more social tags, the social tags comprising a text string containing one or more terms at least one of describing, categorizing and providing information regarding a document, and being indexed and stored in user profile tables separate from the corresponding documents they are associated with;
- creating a number ranking feature based on the social tags, the number ranking feature containing a number of times the document was tagged with the social tags associated with a plurality of user profiles;
- creating a textual property ranking textual stream based on the social tags, the textual property ranking textual stream containing a union of all the social tags associated with the document;
- transforming the number ranking feature into a static input value by applying a normalization constant to the number ranking feature;
- transforming the textual property ranking textual stream into a dynamic query dependent input value, wherein the dynamic query dependent input value includes a number of times a given term in a query appears in the textual property ranking textual stream;
- and
- determining a document rank for the document by inputting the static input value and the dynamic query dependent input value into a ranking function.
A computer system comprising:
- a processor;
- a memory operatively coupled to the processor;
- and
- a program module (i) which executes in the processor from the memory and (ii) which, when executed by the processor, causes the computer system to rank documents with social tags by:
- crawling a user profile database to collect the social tags associated with a document, the social tags comprising a text string containing one or more terms at least one of describing, categorizing and providing information regarding the document, and being indexed and stored in user profile tables separately from the document they are associated with;
- determining, based on the social tags, a number ranking feature containing a number of times the document was tagged with the social tags;
- determining, based on the social tags, a textual property ranking textual stream containing a union of all the social tags associated with the document;
- transforming the number ranking feature into a static input value by applying a normalization constant to the number ranking feature;
- transforming the textual property ranking textual stream into a dynamic query dependent input value, wherein dynamic query dependent input value includes a number of times a given term in a query appears in the textual property ranking textual stream;
- and
- determining a document rank for the document by inputting the static input value and the dynamic query dependent input value into a ranking function.
One of an optical disk, a solid state storage device or a magnetic storage device having computer-executable instructions stored thereon which, and executed by a computer, cause the computer to:
- crawl documents to obtain document ranking features;
- crawl a profile database to collect social tags associated with a document, the profile database comprising a plurality of user profiles associated with a plurality of users, each user profile comprising the social tags associated with the document by at least one of the plurality of users, the social tags comprising a text string containing one or more terms at least one of describing, categorizing and providing information regarding the document, and being indexed and stored in user profile tables separately from the document they are associated with;
- determine, based on the social tags, a number ranking feature containing a number of times the document was tagged with the social tags by the plurality of users;
- determine, based on the social tags, a textual property ranking textual stream containing a union of all the social tags associated with the document by the plurality of users;
- transform the number ranking feature into a static input value by applying a normalization constant to the number ranking feature, the static input value being query independent;
- transform the textual property ranking textual stream into a dynamic query dependent input value that is query dependent and includes a number of times a given term in a query appears in the textual property ranking textual stream;
- and
- determine a document rank for the document by inputting the static input value and the dynamic query dependent input value into a ranking function, and further inputting the document ranking features into the ranking function.
Dependencies are inferred from the claim text.