X Development LLC

Snowflake Inc.

Google Inc.

Yale University

Thiago Teixeira

Charles Chen

Daniel Rodriguez Magana

Istvan Cseri

Chun Yat Frank Li

William A Pugh

Anand Agarawala

Jeffrey Shaw

Michael Joseph Papale

Yifung Lin

Annissa Al-Alusi

Wei Song

Jue Liu

Jeffrey P Bigham

Adrien Treuille

Thomas Finsterbusch

Andreas Savvides

Walter Lasecki

Jason Samuel Soll

A data platform for running a subset of cells in a notebook is provided. The data platform receives a run cells message from a notebook user interface (UI) application specifying the subset of cells to run. For each cell in the subset, the data platform runs the cell to generate a set of results, generates a cell execution stream using the results, stores the stream, and transmits the stream to the notebook UI application. The notebook UI application generates a display for the user using the cell execution stream. The data platform provides an efficient way to run specific cells in a notebook and display the results to the user.

Notebooks with cached results

Notebooks with predictable behavior

A multimodal sensor network is designed to extract a plurality of fundamental properties associated with subject sensing. In one aspect, such network can combine cameras distributed in an environment with inertial sensors available in subjects' wearable devices. The network can permit anonymous detection, counting, and localization of one or more subjects utilizing the cameras. In one aspect, by fusing such information with positional data from the inertial sensors contained or coupled to wearable devices associated with the one or more subjects, the network can track and can identify each subject carrying a wearable device functionally coupled to inertial sensor(s). In one aspect, the problem of subject sensing can be divided into two parts: (1) a detection, counting, and localization (DCL) layer and (2) a tracking and identification (TI) layer, wherein such layers can be implemented via simulations and a real sensor network deployment.

Subject sensing in an environment

Embodiments may relate to intuitive user-interface features for a head-mountable device (HMD), in the context of a hybrid human and computer-automated response system. An illustrative method may involve a head-mountable device (HMD) that comprises a touchpad: (a) sending a speech-segment message to a hybrid response system, wherein the speech-segment message is indicative of a speech segment that is detected in audio data captured at the HMD, and wherein the speech-segment is associated with a first user-account with the hybrid response system, (b) receiving a response message that includes a response to the speech-segment message and an indication of a next action corresponding to the response to the speech-segment message, (c) displaying a screen interface that includes an indication of the response, and (d) while displaying the response, detecting a singular touch gesture and responsively initiating the at least one next action.

Tap to initiate a next action for user requests

Example systems and methods may facilitate processing of voice commands using a hybrid system with automated processing and human guide assistance. An example method includes receiving a speech segment, determining a textual representation of the speech segment, causing one or more guide computing devices to display one or more portions of the textual representation, receiving input data from the one or more guide computing devices that identifies a plurality of chunks of the textual representation, determining an association between the identified chunks of the textual representation and corresponding semantic labels, and determining a digital representation of a task based on the identified chunks of the textual representation and the corresponding semantic labels.

Transcription and tagging system

Methods are described herein related to providing a workspace that is associated with a voice-request account workspace and that is capable of establishing a session for a user-account. An example method may involve: (a) providing, by a computing system, a workspace on a virtual machine, where the workspace is associated with a voice-request account, where the workspace is accessible to one or more guide computing systems, (b) receiving, at the computing system, authentication information for a user-account, (c) receiving, at the computing system, a request to establish a session for the user-account in the workspace associated with the voice-request account and responsively establishing the session, and (d) providing, by the computing system, the one or more guide accounts with access via the workspace to the session for the user-account.

Shared workspace associated with a voice-request account

Embodiments may relate to intuitive user-interface features for a head-mountable device (HMD), in the context of a hybrid human and computer-automated response system. An illustrative method may involve a head-mountable device (HMD) that comprises a touchpad: (a) sending a speech-segment message to a hybrid response system, wherein the speech-segment message is indicative of a speech segment that is detected in audio data captured at the HMD, and wherein the speech-segment is associated with a first user-account with the hybrid response system, (b) receiving a response message that includes a response to the speech-segment message and an indication of a next action corresponding to the response to the speech-segment message, (c) displaying a card interface that includes an indication of the response, and (d) while displaying the response, detecting a singular touch gesture and responsively initiating the at least one next action.

Growing community of inventors

San Francisco, CA, United States of America

Thiago Teixeira