Microsoft Technology Licensing, LLC

Other

Robert Alexander Sim

Ryen William White

Elnaz Nouri

Russell Allen Herring, Jr

Scott Laufer

David Steeves

Pui-Yin Winfred Wong

Anthony Paul Penta

Adam Fourney

Mark A Nikiel

Nirupama Chandrasekaran

Bernd Ingo Plontsch

Luke Abrams

Laurentiu Bogdan Cristofor

Sagi Hilleli

Harry Simon Katz

Chad W Mills

Tomer Hermelin

Dana Scott Kaufman

Omar Shaya

Aaron Small

Adrian Kreuziger

Alexa Lynn Keizur

Marcello Mendes Hasegawa

Collin Tibbetts

Charles Hayden

Mudit Jain

Adi Gerzi Rosenthal

Sung Chung

William B Dolan

Ji Li

Christopher Brian Quirk

Christopher John Brockett

David Alexander Molnar

Jisheng Liang

Dimitrios Basile Dimitriadis

Nikrouz Ghotbi

Dolly Sobhani

Girish Kumar

Christian Seifert

Vikram Reddy Dendi

Pallavi Choudhury

Elliott Jeb Haber

Dhruv Joshi

Akash Atul Shah

Tomasz Kasperkiewicz

Vanessa Graham Murdock

Milad Shokouhi

Christopher Ian Charla

Noelle Mallory Sophy

David Benjamin Levitan

Sumithra Bhakthavatsalam

John Christian Leone

Nicole Beaudry

Thomas E Woolsey

Hosein Azarbonyad

Vaishnavi Shrivastava

Fatemehsadat Mireshghallah

Julia S McANALLEN

Huseyin Atahan Inan

Xiang Yue

Antonio Andre Monteiro Manoel

Anthony Penta

A system for development of an Artificial Intelligence (AI) model while protecting sensitive user information includes: a confidential computing environment in which original prompts to the AI model written by users are collected; a trained synthetic prompt generator to generate synthetic prompts based on the original prompts, wherein the synthetic prompt generator generates anonymized synthetic prompts without sensitive user information identifiable from the original prompts; and a developer computing environment in which the synthetic prompts are submitted to the AI model under development to generate a dataset that includes the synthetic prompts and corresponding AI model output for analysis to determine updates for the AI model while protecting the sensitive user information of actual users.

Protecting sensitive user information in developing artificial intelligence models

Systems and methods are directed to building annotated models based on eyes-off data. Specifically, a synthetic data generation model is trained and used to further train a target model. The synthetic data generation model is trained within an eyes-off environment using an anonymity technique on confidential data. The synthetic data generation model is then used to create synthetic data that closely represents the confidential data but without any specific details that can be linked back to the confidential data. The synthetic data is then annotated and used to train the target model within an eyes-on environment. Subsequently, the target model is deployed back within the eyes-off environment to classify the confidential data.

Building annotated models based on eyes-off data

A personalized natural language processing system tokenizes a plurality of sets of raw text data to generate a plurality of sets of tokenized text data for the plurality of users, respectively. The tokenized text data includes a sequence of tokens corresponding to the raw text data, the tokens at least identifying distinct words or portions of words in the raw text. The system appends predetermined user-specific tokens to the sets of tokenized text data from the users, respectively. Each predetermined user-specific token corresponds to one of the users. The system processes the sets of tokenized text data using the NLP model in accordance with the appended predetermined user-specific tokens to predict a personalized classification for the sets of tokenized text data from each of the users, and outputs the personalized classifications of the tokenized text data for each of the users.

Personalized natural language processing system

The present disclosure relates to systems and methods for an interactive, intelligent hub built around the completion of a task. This hub brings together resources, information, suggested steps, and other automated assistance to facilitate the completion of the task. AI-based assistance may indicate which steps can be completed by automated processes, and dispatch those processes, or suggest resources to assist in the completion of other steps. The hub displays the current status of the task, and lives until the completion of the task, or abandonment by the user.

Semi-autonomous intelligent task hub

A system and method to provide computer support for a meeting of invitees comprises accessing one or more sensory data streams providing digitized sensory data responsive to an activity of one or more of the invitees during the meeting, the one or more sensory data streams including at least one audio stream. The method also comprises subjecting the at least one audio stream to phonetic and situational computer modeling to recognize a sequence of words in the audio stream and to assign each word to an invitee, subjecting the sequence of words to semantic computer modeling to recognize a sequence of directives in the sequence of words, and releasing one or more output data streams based on the sequence of directives, the one or more output data streams including one or more notifications.

Computer support for meetings

The present disclosure provides systems and methods for user interaction and task completion using multiple devices. A set of devices may be used to perform a task, such that different devices may perform different steps of the task. A device management service may update state information at each device of the set, thereby enabling a user to interact with any of the computing devices to perform the task. A device management service may also automatically determine which device should be used by the user, based on task or step requirements, device characteristics, and device capabilities, among other examples. Thus, rather than being required to continue a task on the same device (even when the device is not well-suited for the current step or task), the user is provided with the option to use and, in some instances, is automatically transitioned to use, different devices within the set.

User interaction and task management using multiple devices

Systems and methods can be implemented to provide suggestions to a user device to execute user tasks in a variety of applications. In various embodiments, a set of tasks of a user from a number of task sources are identified for possible consolidation. The tasks in the set can be analyzed to identify a location to accomplish the tasks, estimate times to complete the tasks at the identified locations, and compute routes to the locations from a starting location or compute routes with respect to a route to another location of another task of the set of tasks. The identified locations, the estimated times, and the computed routes can be used to determine which tasks of the set of tasks are available for consolidation. One or more suggestions of task consolidations can be generated to or within the user device. Additional systems and methods are disclosed.

Location-based task suggestions

Generally discussed herein are devices, systems, and methods for task classification. A method can include modifying a representation of a source sentence of a source sample from a source corpus to more closely resemble a representation of target sentences of target samples from a target corpus, operating, using a machine learning model trained using the modified representation of the source sentence, with the target sample to generate a task label, the task label indicating whether the target sample includes a task, and causing a personal information manager (PIM) to generate a reminder, based on whether the target sample includes the task.

Task detection in communications using domain adaptation

Embodiments described herein are implemented in authentication brokering systems where an authentication broker issues security tokens that represent its authentications of users. Client devices operated by the users store the security tokens and send them to resource providers. The resource providers authenticate and grant access to the users based on validation of the security tokens. Authentication related messages exchanged between the resource providers and the authentication broker are used to exchange authentication risk data that is obtained or derived by the resource providers and the authentication broker. The resource providers obtain authentication risk data directly from the authentication broker and indirectly, via the authentication broker, from each other. As security tokens are used or managed, authentication risk data is shared among the participants in the authentication brokering system. The participants are able to modify their authentication procedures or make authentication decisions based on shared authentication risk data.

Brokered authentication with risk sharing

A Personal Virtual Assistant (PVA) system takes existing inputs and processes them to understand the user's personality, intent, etc., through analysis of features such as the user's tone, language use, vocal volume, facial expressions, and context from device use and surroundings. As a result of the processing, the PVA system augments how it responds and interacts with the user. Such augmented responses may include simple things like changing the assistant's tone to complimenting the user's mood, as well as changing her use of language, volume, and the way she shares information, like giving good news when the user might be down, or suppressing bad news when the time is not right for the user to optimally process it.

Empathetic personal virtual digital assistant

In one embodiment, a human interactive proof portalmay use a biometric input to determine whether a user is a standard user or a malicious actor. The human interactive proof portalmay receive an access requestfor an online data servicefrom a user device. The human interactive proof portalmay send a proof challengeto the user devicefor presentation to a user. The human interactive proof portalmay receive from the user devicea proof responsehaving a biometric metadata descriptionbased on a biometric input from the user.

Using the ability to speak as a human interactive proof

One or more techniques and/or systems are provided for risk assessment. Historical authentication data and/or compromised user account data may be evaluated to identify a set of authentication context properties associated with user authentication sessions and/or a set of malicious account context properties associated with compromised user accounts (e.g., properties indicative of whether a user recently visited a malicious site, created a fake social network profile, logged in from unknown locations, etc.). The set of authentication context properties and/or the set of malicious account context properties may be annotated to create an annotated context property training set that may be used to train a risk assessment machine learning model to generate a risk assessment model. The risk assessment model may be used to evaluate user context properties of a user account event to generate a risk analysis metric indicative of a likelihood the user account event is malicious or safe.

Risk assessment modeling

Growing community of inventors

Bellevue, WA, United States of America

Robert Alexander Sim