Microsoft Technology Licensing, LLC

Google Inc.

Hen Fitoussi

Benny Schlesinger

Eran Yariv

Blaise Aguera Y Arcas

William Ramsey

Yuval Pinchas Borsutsky

Avichai Cohen

John Daniell Hebert

Eldar Cohen

Delia Koren

Shira Weinberg

Erez Altus

Haim Somech

Adi L Miller

Guy Kashtan

Ori Barak

Nir Nice

Gabriel Taubman

Christian Liensberger

Henrik Frystyk Nielsen

Kfir Karmon

Ron Jack Karidi

Harris Syed

Keith Coleman Herold

Daniel Sitton

Roy Varshavsky

Oded Elyada

Jonathan E Hamaker

John DiMartile

Benjamin Schlesinger

Noam Etzion-Rosenberg

Limor Lahiani

Matt Dyor

Elinor Axelrod

Anatoly Efros

Sahil Goel

Sapir Caduri

Liat Segal

Tair Barkay

Noga Amit

Pauline Chao

Morgan Venable

Nikita Edward Dubrovsky

Paul S Bloom

Methods, systems, and apparatus for filtering content at the operating system level. In one aspect, a method includes accessing, at a user device, data that includes content items that are to be presented by an application executing on the user device; prior to the content being presented by the application: for each content item, determining, at the user device and by a filtering model, whether the content item is to be presented by the application or filtered, for each content item that is determined to be presented by the application, allowing the application to present the content item, and for each content item that is determined to be filtered, precluding, by the filtering model by a system level filtering operation performed at an operating system level and separate from an application level at which the application is executing, presentation of the content item by the application.

System for filtering displayed content at the OS level

Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.

Virtual assistant for generating personalized responses within a communication session

Aspects of the technology described herein can provide assisted-communication with an intelligent personal assistant. An exemplary computing device may use a profile handler to receive a user profile of a user and a system profile of an interactive communications system. Moreover, a context handler in the exemplary computing device may receive an indication of a communication event related to the user, such as a call or message, and context information associated with the event. Further, a communication handler in the exemplary computing device may use the context information, the user profile, and/or the system profile to navigate the interactive system for the user. In some instances, where a user is unavailable to address a communication event, the intelligent personal assistant may utilize the communication handler to intercept the communication and negotiate the session on behalf of the user.

Assisted-communication with intelligent personal assistant

A computer system can conduct corresponding natural language dialogs with multiple computer-readable profiles using a computer proxy messaging bot. For example, a first set of natural language instructions can be received via a computer messaging proxy bot from a first computer-readable profile. The first set of natural language instructions can be analyzed via the proxy bot. Also, first and second natural language dialog scripts can be generated via the proxy bot using results of the analyzing of the first set of natural language instructions, with the second natural language dialog script including natural language data derived from the first set of natural language instructions. The first natural language dialog script can be sent to the first profile via the proxy bot and the second natural language dialog script can be sent to a second computer-readable profile via the proxy bot, both in response to the first set of instructions.

Computer proxy messaging bot

Techniques are described herein that are capable of providing extensibility with regard to a context-aware digital personal assistant. For instance, a description of a capability of a target (e.g., a software target) may be received. Examples of a target include but are not limited to an application (e.g., a software application), a service, a bot, and a website. In a first example, a digital personal assistant may be caused to perform operation(s) based at least in part on a context of a user. In a second example, whether the digital personal assistant performs operation(s) that are configured to be triggered by first aspect(s) of the context of the user is controlled based at least in part on second aspect(s) of the context of the user. The operation(s) include notifying the user of the capability and/or implementing the capability on behalf of the user.

Extensibility for context-aware digital personal assistant

A computer system may communicate metadata that identifies a current speaker. The computer system may receive audio data that represents speech of the current speaker, generate an audio fingerprint of the current speaker based on the audio data, and perform automated speaker recognition by comparing the audio fingerprint of the current speaker against stored audio fingerprints contained in a speaker fingerprint repository. The computer system may communicate data indicating that the current speaker is unrecognized to a client device of an observer and receive tagging information that identifies the current speaker from the client device of the observer. The computer system may store the audio fingerprint of the current speaker and metadata that identifies the current speaker in the speaker fingerprint repository and communicate the metadata that identifies the current speaker to at least one of the client device of the observer or a client device of a different observer.

Communicating metadata that identifies a current speaker

In the field of computing, many scenarios involve the execution of an application within a virtual environment of a device (e.g., web applications executing within a web browser). Interactions between applications and device components are often enabled through hardware abstractions or component application programming interfaces (API), but such interactions may provide more limited and/or inconsistent access to component capabilities for virtually executing applications than for native applications. Instead, the device may provide hardware interaction as a service to the virtual environment utilizing a callback model, wherein applications within the virtual environment initiate component request specifying a callback, and the device initiates the component requests with the components and invokes associated callbacks upon completion of a component request. This model may enable the applications to interact with the full capability set of the components, and may reduce blocked execution of the application within the virtual application in furtherance of application performance.

Inversion-of-control component service models for virtual environments

Creation data can be received from a computer-readable developer profile, with the creation data including instructions to create a messaging bot. A messaging bot definition can be generated using the instructions, and a messaging bot may be executed using the definition. The instructions may include natural language instructions defining one or more messaging bot characteristics. The natural language instructions can be matched with one or more commands to include one or more characteristics in the messaging bot, and instructions for those characteristic(s) can be included in the messaging bot definition. The instructions can be instructions that are not in a computer programming language, and they can be instructions to create one or more general messaging bot characteristics configured to be implemented with a specific dialog structure that defines one or more specific natural language dialog scripts.

Computer messaging bot creation

One or more techniques and/or systems are provided for cloud service hosting on a client device. For example, a cloud service may comprise data and/or functionality that may be consumed by apps on client devices. The cloud service may be hosted within a cloud computing environment because a client device may not comprise processing resources capable of hosting the entire cloud service. Accordingly, a local service may be deployed on a client device as a local instantiation of the cloud service. For example, the local service may be a local instantiation of at least a portion of the data and/or functionality of the cloud service. In this way, the local service may utilize fewer resources than the cloud service, and may locally process requests from apps on the client device. For example, a map local service may process requests using map data locally cached from a map cloud service.

Cloud service hosting on client device

Growing community of inventors

Ramat Hasharon, Israel

Hen Fitoussi