US 9,436,742 B1Granted

Ranking search result documents based on user attributes

AssigneeGoogle Inc.

InventorsMoustafa Hammad, Dandapani Sivakumar, Pranav Kumar Tiwari, Sumit Kumar Sanghai, Shachi Dave, Selvam Mahalingam, Deepak Raghuwanshi

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

Methods and apparatus for ranking search result documents for a query of a user based on one or more attributes of the user that are associated with one or more of the search result documents. User attributes of the user's user profile may be matched to user attributes of a search result document and the search result document ranked based at least in part on bias measures associated with the matched user attributes. Some implementations are directed to determining, for each of a plurality of documents, multiple user attributes and associated bias measures to associate with the document. A user attribute and associated bias measure for the document may be determined based on indicated interactions with the document by a set of users associated with the user attribute.

Claims19

Dependent claims

A computer-implemented method, comprising:

identifying search result documents for a query submitted by a user;
identifying one or more user attributes associated with the user;
identifying, for a given document of the search result documents, a set of one or more of the user attributes that are each associated with the given document;
identifying, for each of the user attributes of the set, a bias measure for the given document,
wherein the bias measure for a user attribute of the set is based on a quantity of indicated interactions with the given document by a set of users associated with the user attribute compared to a second quantity of indicated interactions with the given document by a second set of users, wherein the second set of users include users non-associated with the user attribute, and wherein the indicated interactions with the given document include interactions with the given document independent of the query;
determining an overall bias measure for the given document based on the bias measures for the user attributes of the set;
and
determining a ranking of the given document for the query based on the overall bias measure.

5 more elements

A computer-implemented method, comprising:

identifying a first user attribute;
identifying a given document;
identifying first user attribute indicated interactions with the given document by a first set of users associated with the first user attribute, the first user attribute indicated interactions including indicated interactions with the given document in response to more than one query;
identifying additional indicated interactions with the given document by a second set of users, the second set of users including users non-associated with the first user attribute and the indicated interactions including indicated interactions with the given document in response to more than one query;
determining a bias measure for the given document for the first user attribute, the determining the bias measure based on comparison of the first user attribute indicated interactions and the additional indicated interactions wherein determining the bias measure includes:
comparing a quantity of the first user attribute indicated interactions with a larger quantity of indicated interactions by the first set of users, the larger quantity of indicated interactions including interactions with documents in addition to the given document, and
comparing a second quantity of the additional indicated interactions with a second larger quantity of indicated interactions by the second set of users, the second larger quantity of indicated interactions including interactions with the documents in addition to the given document;
and
associating the bias measure for the first user attribute with the given document.

6 more elements

A system including memory and one or more processors operable to execute instructions stored in the memory, comprising instructions to:

identify search result documents for a query submitted by a user;
identify one or more user attributes associated with the user;
identify, for a given document of the search result documents, a set of one or more of the user attributes that are each associated with the given document;
identify, for each of the user attributes of the set, a bias measure for the given document,
wherein the bias measure for a user attribute of the set is based on a quantity of indicated interactions with the given document by a set of users associated with the user attribute compared to a second quantity of indicated interactions with the given document by a second set of users, wherein the second set of users include users non-associated with the user attribute, and wherein the indicated interactions with the given document include interactions with the given document independent of the query;
determine an overall bias measure for the given document based on the bias measures for the user attributes of the set;
and
determine a ranking of the given document for the query based on the overall bias measure.

5 more elements

Dependencies are inferred from the claim text.