US 8,751,498 B2Granted

Finding and disambiguating references to entities on web pages

AssigneeGoogle Inc.

InventorsLeonardo A. Laroco, Jr., Nikola Jevtic, Nikolai V. Yakovenko, Jeffrey Reynar

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system and method for disambiguating references to entities in a document. In one embodiment, an iterative process is used to disambiguate references to entities in documents. An initial model is used to identify documents referring to an entity based on features contained in those documents. The occurrence of various features in these documents is measured. From the number occurrences of features in these documents, a second model is constructed. The second model is used to identify documents referring to the entity based on features contained in the documents. The process can be repeated, iteratively identifying documents referring to the entity and improving subsequent models based on those identifications. Additional features of the entity can be extracted from documents identified as referring to the entity.

Claims20

Dependent claims

A method for identifying documents referring to an entity, the entity being associated with a first set of features, the method comprising:

at a computer having one or more processors and memory storing programs for execution by the one or more processors:
identifying a first set of documents based on a first model and the first set of features, wherein the first model includes a first set of rules specifying at least one combination of features from the first set of features that are sufficient for identifying a document referring to the entity, and each document in the first set of documents includes a sufficient number of features in common with the first set of features to identify a document referring to the entity according to the first model;
determining a second model based on features included in one or more documents in the first set of documents, wherein the second model includes a second set of rules specifying at least one combination of features from the first set of documents that are sufficient for identifying a document referring to the entity;
identifying a second set of documents based on the second model, wherein each document in the second set of documents includes a sufficient number of features in common with the first set of features to identify a document referring to the entity according to the second model, and wherein the second set of documents includes at least one document not included in the first set of documents;
and
extracting one or more facts from the second set of documents and associating the extracted facts with the entity.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 13/364,244Filed 1 Feb 2012 · continuation
Priority: 20 Oct 2006
Published: US 2012/0203777 A19 Aug 2012
Granted: 10 Jun 2014
Term ends: Not estimatedThe source records don’t support an estimate.

Classification6 codes

G06F 16/93
Details of database functions independent of the retrieved data types: document management systems
G06F 16/955
Retrieval from the web: using information identifiers, e.g. uniform resource locators [URL]
G06N 5/04
Computing arrangements using knowledge-based models: inference or reasoning models
G06N 20/00
Machine learning

Family

Application11/551,657Parent of this continuation · filed 20 Oct 2006
US 8,122,026 B1Parent of this continuation · filed 21 Feb 2012
US 2012/0203777 A1Pre-grant publication · published 9 Aug 2012
US 8,751,498 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key