Large scale entity-specific resource classification

摘要

A system and method is described for large scale entity-specific classification of each entity-specific set of candidates in a collection of candidates for each specific entity in a collection of entities. The collection of entities may comprise a specific category or domain of entities (e.g. schools, restaurants, manufacturers, products, events, people). Candidates may comprise webpages or other resources with resource identifiers. Entity specific sets of candidates may be found by leveraging search engine query results and user interaction therewith for queries based on entity-specific attributes. The relationship(s) or class(es) for which candidate resources are being classified relative to a specific entity may comprise an authoritative, official home page (OHP), or other class (e.g. fan page, review, aggregator) relative to a specific entity. A feature generator generates entity-specific features for candidates. In accordance with its features, one or more classifiers rank each candidate for a specific class for a specific entity.

主权项

1. A method performed by at least one computing machine, the method comprising:
generating an aggregate set of candidates for an aggregate set of entities by:
generating at least one entity-specific representative query based, at least in part, on two or more entity-specific attributes for an entity in the aggregate set of entities,identifying one or more previously-submitted search queries similar to the at least one entity-specific representative query,determining a particular candidate for the entity based, at least in part, on one or more historical user selections of the particular candidate responsive to the one or more previously-submitted search queries for the entity, wherein the particular candidate comprises a resource; pairing or otherwise associating the entity with the particular candidate in the entity's entity-specific set of candidates for entity-specific processing of candidates; generating, for the particular candidate, a candidate-specific set of features based, at least in part, on candidate-specific attributes; generating an aggregate set of classifications for the aggregate set of candidates by generating, for the particular candidate, an entity-specific classification based, at least in part, on the candidate-specific set of features; and identifying the particular candidate as a homepage for the entity based, at least in part, on the entity-specific classification and the historical user selections, from a plurality of users, of the particular candidate.