Microsoft Technology Licensing, LLC

Meta Platforms, Inc.

Google Inc.

Facebook, Inc.

Emmanouil Koukoumidis

Joseph Edwin Johnson, Jr

Brian C Beckman

Hailong Mu

Ying Wang

Michael Robert Hanson

Dustin Isaac Abramson

Donald Brinkman

Yuan Yuan

Michial Allen Gunter

Fuchun Peng

Di Li

Kevin Yu

Norm Bryar

Matthew W Schuerman

Hudong Wang

Carroll Philip Gossett

Benoit F Dumoulin

Rajen Subba

Jinsong Yu

Mohsen M Agsen

Rushin N Shah

Heidi Young

Jeremy Gillmor Kahn

Chandrasekhar Iyer

Jason Schissel

Xiaofang Jiang

Maria Alexandropoulou

Namita Parab

Konstantinos Aisopos

Steven G Zittrower

Kelli A Stuckart

Aleksey Sergeyevich Fadeev

Arjmand Samuel

Wenhai Yang

Kun Han

Daniel Massey

Qi Yao

Sumit Kumar

Kati Amanda London

Zhan Chen

Oussama Elachqar

Adam Edward Shirey

Nicholas Donald Atkins Lane

Nicholas Robin

James Anthony Whittaker

Cheng Zhang

Vivek Narayanan

Maria A Rangel

Pengfei Hao

Shane Haladuick

Jie Jerry Liu

Douglas Christopher Burger

Feng Zhao

Stephen L Lawler

Dimitrios Lymberopoulos

Evan Huang

Anthony Nino Bice

Donald Frank Brinkman, Jr

Elad Gerson

Scott A Schwarz

Xiao Liu

Michael Andrews

Michael E Lanning

Daniel Vann

Cezar Augusto Alevatto Guimaraes Neto

Lukas Rutishauser

Caroll Philip Gossett

Fuchen Peng

Xiaofan Jiang

Sergei Tuterov

Nikolaos Kofinas

Kiran Bellare

Anthony Turner

Brian J Alseth

Richard P Lozada

Dan Vann

Youssef Hammad

Christopher Alme

Vanya Avramova

Daniel Lee Massey

Joseph Edwin Johnson

Arjmand Micheal Samuel

In one embodiment, a method includes receiving a user query inputted on a head-mounted device from the head-mounted device, wherein the user query corresponds to multiple dialog-intents, executing multiple tasks corresponding to the multiple dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the multiple tasks, wherein the stitching model combines the two or more of the execution results based on natural language processing, and wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and sending instructions to the head-mounted device for presenting the multi-perspective response on the head-mounted device.

Generating multi-perspective responses by assistant systems

A computer-implemented method includes receiving a document insight request that requests document insights for a corpus of documents. The document insight request includes the corpus of documents, a set of entities contained within each document of the corpus of documents, and document insight request parameters that includes a confidence value threshold. The method also includes generating the document insights for the corpus of documents based on the confidence value threshold. Here, the document insights include an accuracy target and a user review rate target. The method also includes transmitting the document insights to the user device causing a graphical user interface to display the document insights on the user device.

Human-augmented artificial intelligence configuration and optimization insights

In one embodiment, a method includes, by a client system, receiving a user input from the first user of an online social network, where the user input is associated with a subject and an intent, determining whether one or more agents associated with the intent are able to resolve the user input, identifying, responsive to determining that the one or more agents are not able to resolve the user input, one or more entities related to the subject, where each identified entity is connected to the first user via the online social network, and presenting, at the client system, one or more recommendations to the first user corresponding to the one or more entities.

Suggestions for fallback social contacts for assistant systems

In one embodiment, a method includes receiving a user query associated with dialog-intents at a client system, executing tasks corresponding to the dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the tasks, wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and presenting the multi-perspective response at the client system.

In one embodiment, a method includes, by a client system, receiving, at the client system, a first user input, processing by the client system, the first user input to provide an initial response by identifying one or more entities referenced by the first user input and providing, by the client system, the initial response, where the initial response includes a conversational filler referencing at least one of the one or more identified entities, processing the first user input to provide a complete response by identifying, by the client system, one or more intents and one or more slots associated with the first user input based on a semantic analysis by a natural-language understanding module, and providing, by the client system, the complete response subsequent to the initial response, where the complete response is based on the one or more intents and the one or more slots.

Predictive injection of conversation fillers for assistant systems

In one embodiment, a method includes receiving an indication of a trigger action by a first user at a client system, wherein the trigger action is associated with a priming content object, identifying related content objects associated with the priming content object, selecting recommended content objects based on the priming content object, the related content objects, and profile information of the first user, wherein each of the selected recommended content objects comprises entity information of entities associated with the priming content object, and presenting content suggestions at the client system, wherein each content suggestion comprises one of the selected recommended content objects.

Engaging users by personalized composing-content recommendation

Aspects of the present disclosure provide systems and methods for detecting memorable events of a user, storing those memorable events in a user profile, and leveraging those events to the user. In so doing, memorable events with positive emotional weight may be recalled to encourage delightful experiences. Alternatively or additionally, memorable events with negative emotional weight may be recalled to increase user engagement for conversational systems.

Memorable event detection, recording, and exploitation

In one embodiment, a method includes receiving a user query from a client system associated with a first user, determining a plurality of dialog-intents, each being associated with a particular agent of a plurality of agents, executing a plurality of tasks corresponding to the user query via the plurality of agents corresponding to the plurality of dialog-intents, receiving a plurality of execution results corresponding to the plurality of tasks from the plurality of agents, respectively, selecting two or more of the plurality of execution results for combination, generating a multi-perspective response based on the selected execution results by a stitching model, wherein the multi-perspective response comprises a natural-language response combining the selected execution results, and sending instructions for presenting the multi-perspective response to the first user to the client system in response to the user query.

In one embodiment, a method includes receiving a user input by a user from a client system associated with the user, parsing the user input to identify a subject and intent of the user input, determining whether one or more agents associated with the identified intent are able to resolve the user input, identifying one or more entities related to the identified subject of the user input responsive to determining that the one or more agents are not able to resolve the user input, calculating a subject-association score for each of the one or more entities, ranking the one or more entities based on their respective subject-association scores, and sending, to the client system, instructions for presenting one or more recommendations to the user corresponding to one or more of the entities having a ranking greater than a threshold ranking.

In one embodiment, a method includes, by one or more computing systems, receiving, from a client system associated with a first user, a first user input from the first user, identifying one or more entities referenced by the first user input, determining a classification of the first user input based on a machine-learning classifier model, generating several candidate conversational fillers based on the classification of the first user input and the one or more identified entities, wherein each candidate conversational filler references at least one of the one or more identified entities, ranking the candidate conversational fillers based on a relevancy of the candidate conversational filler to the first user input and a decay model hysteresis, and sending instructions for presenting a top-ranked candidate conversational filler as an initial response to the first user.

In one embodiment, a method includes, by one or more computing systems, receiving, from a client system associated with a user, an initial portion of a user input, wherein the initial portion comprises a partial request, and wherein the initial portion is received while the user is continuing to provide further input, generating, responsive to receiving the initial portion of the user input, one or more speculative queries based on the partial request and a machine-learning predictive model, wherein each speculative query is a predicted complete request based on the partial request, calculating a confidence score for each speculative query based on the predictive model, ranking the one or more speculative queries based on their respective confidence scores and associated costs, executing one or more of the speculative queries based on their ranks, and caching one or more results of the executed one or more speculative queries.

Context-based utterance prediction for assistant systems

In one embodiment, a method includes, by one or more computing devices, receiving, from a client system associated with a first user of an online social network, an indication of a trigger action by the first user, wherein the trigger action is associated with a user activity, determining a first user context based on the trigger action, accessing one or more recommended content objects associated with the first user context, calculating a recommendation score for each recommended content object, generating one or more content suggestions comprising one of the one or more recommended content objects, respectively, each content suggestion corresponding to a recommended content object having a recommendation score above a threshold recommendation score, and sending, to the client system in response to the trigger action, instructions for presenting one or more of the content suggestions to the first user.

Recommending content with assistant systems

In one embodiment, a method includes receiving an indication of a trigger action by a first user, wherein the trigger action is associated with a priming content object, identifying one or more related content objects associated with the priming content object, generating a first feature vector representing the priming content object, the one or more related content objects, and profile information of the first user, accessing a plurality of second feature vectors representing a plurality of recommended content objects, respectively, selecting one or more of the recommended content objects based on comparisons between the first feature vector and the respective second feature vectors representing the recommended content objects, and sending, to a client system in response to the trigger action, instructions for presenting one or more content suggestions to the first user, wherein each content suggestion comprises one of the selected recommended content objects.

Systems and methods for receiving various input data, processing said input data, and utilizing artificial emotional intelligence to analyze said input data to return calculated response stimuli are provided. Various electronic devices may be utilized to acquire input data related to a specific user, a group of users, or environments. This input data, which may comprise tone of voice, facial expressions, social media profiles, and surrounding environmental data, may be compared with past data related to a certain user, group of users, or environment. The systems and methods herein may employ artificial emotional intelligence to evaluate the aggregated data and provide a response stimulus to a user or group of users. The response stimulus may be in the form of uplifting/encouraging music, quotes, pictures, jokes, suggestions, etc. The purpose of providing the response stimuli is to significantly increase the productivity of meetings, conversations, and other interactions across electronic devices.

EQ-digital conversation assistant

Systems and methods are disclosed for conversationally-relevant content requests. In one implementation, a first communication is processed to identify a first content element within the communication. The first content element is stored within a first content repository. A content request is generated based on the first content repository. The content request is provided to the user. A second communication is received from the user in response to the content request. An action is initiated based on the second communication.

Conversationally-relevant content requests

Growing community of inventors

Kirkland, WA, United States of America

Emmanouil Koukoumidis