Google Inc.

International Business Machines Corporation

Nissan Hajaj

Yoram Nelken

Dani Cohen

Josemina Marcella Magdalen

Jesse Louis Alpert

Jeffrey Adgate Dean

Kai Chen

Quoc V Le

Yi Zhang

Kun Zhang

James Wilson

Gregory Sean Corrado

Yingwei Cui

Andrew M Dai

Alvin Rishi Rajkomar

Peter Junteng Liu

Randy Jessee

Sam Michelson

Eyal Oren

Benjamin Irvine

James Wexler

Patrik Sundberg

Xiaobing Liu

Michael Bluger

Israel Nelken

Xiaomi Sun

Michaela Hardt

Hector Yee

Avi Margalit

Beth Lanin

Tsachy Shacham

Amir Navot

Ronen Hod

Jacob Marcus

Alexander Mossin

Chi Zhang

Erik Gross

Seyed Vahab Mirrokni Banadaki

Silvio Lattanzi

Gerardo Flores

Brian Swanson

Kurt Litsch

Gavin Duggan

Changxun Wu

Garrett Yaun

Stewart Elliot

Yosemina Magdalen

Jerry Yi Ding

Eduardo Madeira Fleury

A system for predicting and summarizing medical events from electronic health records includes a computer memory storing aggregated electronic health records from a multitude of patients of diverse age, health conditions, and demographics including medications, laboratory values, diagnoses, vital signs, and medical notes. The aggregated electronic health records are converted into a single standardized data structure format and ordered arrangement per patient, e.g., into a chronological order. A computer (or computer system) executes one or more deep learning models trained on the aggregated health records to predict one or more future clinical events and summarize pertinent past medical events related to the predicted events on an input electronic health record of a patient having the standardized data structure format and ordered into a chronological order. An electronic device configured with a healthcare provider-facing interface displays the predicted one or more future clinical events and the pertinent past medical events of the patient.

System and method for predicting and summarizing medical events from electronic health records

One embodiment of the present invention provides a system that produces a ranking for web pages. During operation, the system receives a set of pages to be ranked, wherein the set of pages are interconnected with links. The system also receives a set of seed pages which include outgoing links to the set of pages. The system then assigns lengths to the links based on properties of the links and properties of the pages attached to the links. The system next computes shortest distances from the set of seed pages to each page in the set of pages based on the lengths of the links between the pages. Next, the system determines a ranking score for each page in the set of pages based on the computed shortest distances. The system then produces a ranking for the set of pages based on the ranking scores for the set of pages.

Producing a ranking for pages using distances in a web-link graph

Systems and methods for sending asynchronous messages include receiving, using at least one processor, at a node in a distributed graph, a message with a first value and determining, at the node, that the first value replaces a current value for the node. In response to determining that the first value replaces the current value, the method also includes setting a status of the node to active and sending messages including the first value to neighboring nodes. The method may also include receiving the messages to the neighboring nodes at a priority queue. The priority queue propagates messages in an intelligently asynchronous manner, and the priority queue propagates the messages to the neighboring nodes, the status of the node is set to inactive. The first value may be a cluster identifier or a shortest path identifier.

Asynchronous message passing for large graph clustering

A system and method for increasing email productivity based on an analysis of the content of received email messages. The system includes a content analysis engine that analyzes the content of a received email message using natural language processing techniques. A prioritization module produces a priority score and a priority level for the message using a prioritization knowledge base. A message sorting module produces a set of suggested folders for the message using a sorting knowledge base. A junkmail module produces a junkman score for the message using a junkmail knowledge base. The prioritization knowledge base, the sorting knowledge base, and the junkmail knowledge base are updated with feedback from the user for each received email message, which allows the system to learn in real-time the user's preferences.

System and method for increasing email productivity

Systems and methods for finding multiple shortest paths. A directed graph representing web resources and links are divided into shards, each shard comprising a portion of the graph representing multiple web resources. Each of the shards is assigned to a server, and a distance table is calculated in parallel for each of the web resources in each shard using a nearest seed computation in the server to which the shard was assigned.

Scalable system for determining short paths within web link network

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for producing a ranking for pages on the web. In one aspect, a system receives a set of pages to be ranked, wherein the set of pages are interconnected with links. The system also receives a set of seed pages which include outgoing links to the set of pages. The system then assigns lengths to the links based on properties of the links and properties of the pages attached to the links. The system next computes shortest distances from the set of seed pages to each page in the set of pages based on the lengths of the links between the pages. Next, the system determines a ranking score for each page in the set of pages based on the computed shortest distances. The system then produces a ranking for the set of pages based on the ranking scores for the set of pages.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for collecting user interaction data of a plurality of users for each of a first plurality of document-text pairs, wherein the user interaction data is collected for the document-text pair from a respective service for which the respective text of the document-text pair was selected. A respective weight is calculated for each of the first plurality of document-text pairs based on, at least, the collected user interaction data for the document-text pair. One or more topics are associated with one or more of the sources based on, at least, the respective weights associated with a plurality of first document-text pairs that are associated with the source.

Identification of new sources for topics

One or more hierarchies of string patterns are generated a plurality of URL strings according to a pattern extraction procedure. Repeated string patterns are selected from the generated hierarchies of string patterns. A URL class is defined for each of selected repeated string patterns. Each URL class is associated with a respective group of URL strings in the plurality of URL strings, where the respective group of URL strings contains a repeated string pattern that defines the URL class. Respective aggregated data is calculated for each URL class. The respective aggregated data is based on respective data of each respective document of each URL string in the group of URL strings associated with the URL class. Respective data for a respective document referenced by a lookup-URL is predicted based on respective aggregated data of one or more of the URL classes.

Predicting data for document attributes based on aggregated data for repeated URL patterns

Systems and methods for checkpointing a computation distributed over multiple peer servers. On each server, sequentially storing checkpoints collectively representing a current state of the computation on that server as of a most recent checkpoint, each checkpoint having a checkpoint timestamp. When restarting a first server, rebuilding a most recent state of the first server from the checkpoints written by the first server through a most recent checkpoint having a most recent checkpoint timestamp, and requesting from each of the other peer servers updates from the most recent checkpoint timestamp time of the first server. On each server, in response to a first request for updates as of a particular time, deriving the requested updates from the state data in the server uncommitted to a checkpoint and the state data in checkpoints of the server that have a timestamp no earlier than the particular time of the first request, and providing the requested updates to the first server.

Distributed parallel determination of single and multiple source shortest paths in large directed graphs

A software tool for creating, training and testing a knowledge base of a computerized customer relationship management system is disclosed. The software tool includes corpus editing processes for displaying and editing text-based corpus items, and assigning selected categories to individual corpus items. Knowledge base construction processes construct a knowledge base by analyzing a first subset of the corpus items, and testing processes test the knowledge base on a second subset of the corpus items. Reporting processes generate reports containing indicia representative of the testing results, which may be utilized to edit the corpus items and retrain the knowledge base so as to improve performance.

Software tool for training and testing a knowledge base

A system and method for classifying text includes a pre-processor, a knowledge base, and a statistical engine. The pre-processor identifies concepts in the text and creates a structured text object that contains the concepts. The structured text object is then passed to a statistical engine, which applies statistical information provided in nodes of a knowledge base to the structured text object in order to calculate a set of match scores, each match score representing the relevance of the text to an associated one of a plurality of predefined categories. The pre-processor may be implemented in the form of an interpreter which selects and executes a script that includes language- and scenario-specific instructions for performing linguistic and semantic analysis of the text.

System and method for classifying text

System and method for electronic communication management

Growing community of inventors

Foster City, CA, United States of America

Nissan Hajaj