Ford Global Technologies, LLC

Microsoft Technology Licensing, LLC

Google Inc.

Sct Incorporated

Sct Technology, Ltd.

Amazon Technologies, Inc.

Kla Tencor Corporation

Openwave Systems Inc.

Beijing Didi Infinity Technology and Development Co., Ltd.

Samsung Electronics Co., Ltd.

Dropbox, Inc.

Altigen Communications, Inc.

Cisco Technology, Inc.

Jds Uniphase Corporation

Beijing Wodong Tianjun Information Technology Co., Ltd.

Yi Zhang

Eric Li

Shang-Kuan Tang

Vidya Nariyambut Murali

Jun Xu

Nathan Peter Lucash

Yingwei Cui

Brandon Murdock Pearcy

Shean-Yih Chiou

Manohar Karkal Prabhu

Bahman Rabii

Gaofeng Zhao

Madeline Jane Goh

Niyati Yagnik

Michael Eugene Aiello

Timothy S Lipus

Roger Scott Jenke

Wenjie Yang

Paul Edmonds

Creighton Thomas

Erick Michael Lavoie

Sridhar Srinivasan

Patrick Daniel Maguire

Kun Zhang

Rama Krishna Sandeep Pokkunuri

Shouhong Tang

Hyung Min Baek

Daniel Yancy Parish

Rodolfo Palma

Li Xu

Shoou-Jiun Wang

Aaron Lamar Wilson

Maryam Moosaei

Hui Song

Eyal Oren

Jeffrey Adgate Dean

Kai Chen

Quoc V Le

James Wilson

Gregory Sean Corrado

Peng Zhang

Fei Wu

Omar Aftab

Andrew M Dai

Satish Joseph Thomas

Tony Xu

Eric Myers

Nissan Hajaj

Juinn-Yan Chen

Alvin Rishi Rajkomar

John Hal Howard

Colin Craig McCulloch

Peter Junteng Liu

Chunsheng J Huang

Ephraim Suhir

Dongran Liu

Hua Shu

Shahnad Nadershahi

Harshal Pimpalkhute

Benjamin Irvine

Swaminathan Sivasubramanian

Fei Wang

Roger Arnold Trombley

Luke Niewiadomski

Thomas Edward Pilutti

Chen Zhang

Ying Li

Eric Hongtei Tseng

Tao Wang

Carlos Dangelo

Matthew Strecker Burriesci

Gary A Ball

Chun Lu

David Charles Wrighton

Min Liu

Douglas J Rogan

Carlos Armesto

David Mitford Gillies

Yuan Gao

Katrin Kirchhoff

Ganesh Kumar Gella

Thomas Shimko

Jun Tian

Andrew Zeng

Yahor Pushkin

Denise G Caballero-McCann

Yaser Al-Onaizan

Shannon Brooks-Lehnert

Mike Dong

Donggun Keung

Dou Shen

Si Qin

Syed K Ali

Morgan Asher Brown

Meisam Mehravaran

Arijit Basu

Shirley T Sun

Gilbert Hu

Vasanth Philomin

Di Wu

A natural language processing system may implement one or more composite slot types. The natural language processing system may receive a request to create a composite parameter type for causing performance by the natural language processing system of an intended action. The natural language processing system determines based on the request, a plurality of sub-parameters of the composite parameter type and generates a Boolean expression that relates two or more sub-parameters. The natural language processing system may apply the composite parameter type to determine that the pluralities of sub-parameters in an input text satisfies the Boolean expression to initiate performance of the intended action.

Composite slot type for natural language processing

A method and system for adjusting ads auction using predicted user responses to an in-ad survey is provided. The method includes (1) providing a content item associated with an actionable object, which when selected, causes a computing device to present a plurality of interactive elements each corresponding to a different one of a plurality of reasons for restricting the content item; (2) receiving, from the computing device, data indicating a particular reason, of the plurality of reasons, for restricting the content item, and the particular reason corresponding to a particular interactive element, of the plurality of interactive elements, that was selected by the user; and (3) updating, using the received data, a content selection model for selecting content items, wherein the content selection model is associated with the user.

Adjust ads auction using predicted user response to an in-ad survey

Embodiments are provided for suggesting topics in a messaging system. A set of queries is received from a chat transcript history, where the set of queries includes a set of unhandled queries, and each unhandled query comprises a query for which a bot did not identify a corresponding topic (e.g., queries that did not trigger selection of a topic by the bot). A vector representation is generated for each unhandled query in the set of unhandled queries. The vector representations for the set of unhandled queries are clustered to generate one or more clusters of vector representations, each cluster corresponding to a group of unhandled queries. A corresponding suggested topic is generated for each cluster and provided to an authoring tool that comprises one or more interactive elements to enable an author to select at least one of the suggested topics for implementation in the bot.

Topic suggestion in messaging systems

Embodiments of the disclosed technologies are capable of providing engagement feedback for an online system while maintaining user privacy. Embodiments determine one or more user groups. A user group includes users, and a size of the user group is selected to protect user privacy. A user action is received from a user in a first group. The user action includes an interaction with a piece of content. A group action count is updated for the first group based on the user action. The group action count indicates a number of interactions with the piece of content by any of the users in the first group. An estimated number of unique engagements is calculated based on the group action count and the size of the first group. The estimated number of unique engagements is provided to the online system as the engagement feedback for the piece of content.

Estimated unique engagement measurement with user privacy protection

A method includes receiving from a client device a request for content, and transmitting to the client device a first content item, a second content item, and a script for displaying the first and second content items within an information resource. The script includes instructions that cause the client device to (1) display the first content item within a content slot having a first size occupying a first region of the information resource, (2) identify a user interaction associated with the first content item, (3) expand, responsive to the user interaction associated with the first content item, the content slot from a first size to a second size, and (4) display, responsive to the user interaction and in the expanded content slot, the first content item and the second content item and an actionable object configured to reduce the content slot from the second size to the first size.

Expandable content items for presenting additional content

Techniques for updating a machine learning model based on user interactions are described. In particular, in some examples, user interactions with a chatbot provide aspects of a data set to be used to train or fine-tune a ML model. In some examples, this is accomplished by collecting data from a first plurality of interactions with a machine learning (ML) model; generating a variant of the ML model using the collected data by: filtering the collected data to create a first data set, training the ML model based on the first data set to generate an adapted ML model, and fine-tuning the adapted ML model on a second data set, different than the first data set to generate the variant of the ML model.

Adaptations of task-oriented agents using user interactions

A system receives one or more transcripts of communications between entities. The system identifies a requested action in the communications based at least in part on a mapping between the requested action and an application programming interface. The system identifies one or more statements eliciting information, based on parameters to the application programming interface. The system generates a definition of an artificial agent based, at least in part, on the requested action and the one more statements eliciting information.

Artificial agent generator

A system and method for concurrent multi-path processing of audio signals for automatic speech recognition is presented. Audio information defining a set of audio signals may be obtained (). The audio signals may convey mixed audio content produced by multiple audio sources. A set of source-specific audio signals may be determined by demixing the mixed audio content produced by the multiple audio sources. Determining the set of source-specific audio signals may comprises providing the set of audio signals to both a first signal processing path and a second signal processing path (). The first signal processing path may determine a value of a demixing parameter for demixing the mixed audio content (). The second signal processing path may apply the value of the demixing parameter to the individual audio signals of the set of audio signals () to generate the individual source-specific audio signals ().

Concurrent multi-path processing of audio signals for automatic speech recognition systems

The present technology provides a browser extension that can recognize downloadable objects on a webpage and provides functionality that makes it easier and more efficient to download the downloadable objects to a location in a content management system. For example the present technology can analyze a document object model of a webpage to find attributes indicating a URL is associated with a downloadable object.

Identifying downloadable objects in markup language

Embodiments are provided for detecting overlapping topics in a messaging system. In an example system, a plurality of trigger phrases is received, where each trigger phrase is configured to trigger a bot that receives the trigger phrase to select a corresponding topic for conversation. For each trigger phrase, a vector representation is generated. Measures of similarity are generated based at least on the vector representations, where each measure of similarity represents a degree of similarity between a respective pair of vector representations. A topic overlap is detected based on a pair of vector representations having a measure of similarity above a similarity threshold, where the topic overlap indicates two trigger phrases that are overlapping. The topic overlap is provided to an authoring tool that comprises one or more interactive elements to enable a user to change at least one of the two trigger phrases that are overlapping.

Topic overlap detection in messaging systems

The present disclosure selects third party content based on feedback. A selector identifies several content items including first and second content items (or more) responsive to a request. A machine learning engine determines a first feature of the first content item, a second feature of the second content item, and a third feature of the web page or a device associated with the request. The machine learning engine determines, responsive to the first feature and the third feature, a first score for the first content item based on a machine learning model generated using historical signals received from devices via a metadata channel formed from an electronic feedback interface. The machine learning engine determines a second score for the second content item responsive to the second feature and the third feature. A bidding module determines a price for the first content item based on the first and second scores.

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 or more servers can implement a method including generating an information resource comprising a content package including first content, metadata of a content extension, and a script for displaying the first content, and transmitting the information resource to a client device to cause the client device to: display the first content within an inline frame; identify an interaction with a user interface feature; transmit, responsive to identifying the interaction, a content extension request based on the metadata of the content extension; receive, responsive to the content extension request, a second content item; responsive to identifying the interaction, expand the inline frame from the first size to a second size; and display, in the expanded inline frame, the second content item, the second content item different from the first content item.

The disclosed technology is generally directed to chatbot conversation management. In one example of the technology, a generic model associated with a first property associated with a chatbot manager is received. The generic model is generated based on machine learning. A refined model that is associated with the first property is generated based on the generic model and a first plurality of phrases. A first conversation is held between a chatbot and an end user. Upon determining that the value of the first property for the end user is not stored in the database, via the chatbot, during the first conversation, the refined model is used to dynamically ask questions to the end user to determine a value of the first property for the end user. In a second conversation between the chatbot and the end user, the value of the first property for the end user is referenced.

Intelligent, personalized, and dynamic chatbot conversation

Growing community of inventors

Sunnyvale, CA, United States of America

Yi Zhang