Google Inc.

Christopher Semturs

Lode Vandevenne

Dale R Webster

Lily Hao Yi Peng

David Lecomte

Avinash Vaidyanathan Varadarajan

Danila Sinopalnikov

Alexander Lyashuk

Sebastian Steiger

Henrik Grimm

Nathanael Martin Schärli

Akinori Mitani

Jun Yin

Joshua James Estelle

Jeffrey Chin

Piyush Prahladka

David Thomas Morgan

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing fundus images using fundus image processing machine learning models.

Processing fundus images using machine learning models to generate blood-related predictions

Computer-implemented systems and methods are provided for extracting and storing information regarding entities from documents, such as webpages. In one implementation, a system is provided that detects an entity candidate in a document and determines that the detected candidate is a new entity. The system also detects a known entity proximate to the known entity based on the one or more entity models. The system also detects a context proximate to the new and known entities having a lexical relationship to the known entity. The system also determines a second entity class associated with the known entity and a context class associated with the context. The system also generates a first entity class based on the second entity class and the context class. The system also generates an entry in the one or more entity models reflecting an association between the new entity and the first entity class.

Computerized systems and methods for extracting and storing information regarding entities

Computer-implemented systems and methods are disclosed for building knowledge bases, such as knowledge graphs, using context clouds. According to certain embodiments, a target object is identified in a portion of unstructured or semi-structured data in a target document, which does not conform to a predefined structure or pattern. A knowledge server may build a context cloud for the target document. The knowledge server may analyze one or more other documents stored in a networked database, to identify candidate documents that may include a meaning or relationship associated with the target object. The knowledge server may analyze one or more context clouds for the candidate documents to determine a meaning or relationship of the target object based on objects in the candidate document(s). The knowledge server may associate the determined meanings and/or relationships with the target object in the target document, thereby creating a new portion of a knowledge graph.

Computerized systems and methods for building knowledge bases using context clouds

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for testing the compatibility of client devices with web services. In one aspect, a method includes receiving a request from a first client device; obtaining a response to the request from a web service, wherein the web service provides responses according to a web service schema that defines a plurality of possible response formats, and wherein the response conforms to a first response format of the plurality of possible response formats; selecting a second, different response format of the plurality of possible response formats defined by the web service schema; modifying the response to generate a modified response, wherein the modified response conforms to the second, different response format; and sending the modified response to the first client device.

Testing compatibility with web services

Many websites publish variants of their web pages based on language and region. However, when a user is directed toward the incorrect web page for the user's language preference, it there is not a simple way for the user to select the appropriate localized or region specific version of the web page. According to an embodiment, a language preference from a user may be received. A first language for a first web page may be identified and the first web page may be received by a computing device of the user. A second language for a second web page may be identified. The second web page may comprise an alternate version of the first web page. The first web page or the second web page may be selected according to the language preference of the user and the selected web page may be presented to the user.

Alternative web pages suggestion based on language

A device may identify, in a first document, a reference to a second document, the second document being different than the first document; identify that the reference to the second document is associated with a relation indicator; determine, based on identifying that the reference to the second document includes a relation indicator, that content of the second document is related to content of the first document; and process the second document based on determining that content of the second document is related to content of the first document.

Identifying related documents based on links in documents

Growing community of inventors

Ottenbach, Switzerland

Christopher Semturs