Google Inc.

Dropbox, Inc.

Timo Mertens

Bradley Neuberg

Okan Kolak

Vinh Quoc Ly

Ahmet Onur Tekdas

Christine Nguyen

Jin Lu

Charles Randell Sievert

Robin Dua

Maxim Gubin

Michael Wu

Sam Jau

David Stinnette

Kavitha Radhakrishnan

Neil Sethi

Justin Hileman

Adam LaFave

Mariana Stepp

The disclosed embodiments include computerized methods, systems, and devices, including computer programs encoded on a computer storage medium, for generating terms of a search query based on a user's spoken utterances, identifying multiple cross-platform messages based on the generated terms, and to generating, via a presentation device, a single interface that enables the user to interact with identified messages. Based on a spoken utterance, the disclosed embodiments may determine user-specified search terms and/or criteria, and based on the user-specified search terms and/or criteria, may obtain cross-platform message data that corresponds to the search query. The communications device may generate one or more interface elements that describe corresponding ones of the cross-platform messages, which may be presented within a unified graphical user interface or voice-user interface by a communications device.

Unified message search

A collaborative content management system allows multiple users to access and modify collaborative documents. When audio data is recorded by or uploaded to the system, the audio data may be transcribed or summarized to improve accessibility and user efficiency. Text transcriptions are associated with portions of the audio data representative of the text, and users can search the text transcription and access the portions of the audio data corresponding to search queries for playback. An outline can be automatically generated based on a text transcription of audio data and embedded as a modifiable object within a collaborative document. The system associates hot words with actions to modify the collaborative document upon identifying the hot words in the audio data. Collaborative content management systems can also generate custom lexicons for users based on documents associated with the user for use in transcribing audio data, ensuring that text transcription is more accurate.

Meeting transcription using custom lexicons based on document history

Methods, systems, and apparatus, including computer programs encoded on a computer-storage medium, for using a search engine implemented on a user device to identify topics or tasks associated with native application content. The method may include actions of receiving a set of data that is generated by the native application and that includes (i) native application content, and (ii) context information associated with the native application content, indexing the data on the user device, and then identifying one or more tasks based on the indexed data.

Search engine

Automated outline generation of captured meeting audio in a collaborative document context

The present disclosure relates to generating and utilizing digital associations between digital documents and digital calendar events based on determined content connections. For example, one or more embodiments suggest a digital document to a user for association with a digital calendar event based on content connections between the digital document and the digital calendar event. In particular, one or more embodiments determine a content connection based on document characteristics (e.g., document content and access characteristics) and calendar event characteristics (e.g., calendar content and historical meeting information). For example, the system can train a machine learning model to determine content connections based on document characteristics and calendar event characteristics. By associating digital documents with digital calendar events, the system can efficiently manage digital documents for participants, automatically generate new digital documents for calendar events, generate snippets for insertion within digital documents, and generate calendar event summaries and action items.

Generating digital associations between documents and digital calendar events based on content connections

From the content of a document, a factual entity that relates to the content of the document is determined. Content for a knowledge panel is requested. A knowledge panel is a user interface element that provides a collection of content related to the factual entity. The contents of the knowledge panel is received for contemporaneous display on the user device with the content of the document.

Contextually relevant knowledge panels in an application environment

The disclosed technology relates to a system configured to receive a first input into a search interface and perform a first search based on the first input, wherein the first search is performed on a first set of content items managed by a content management system. The system further receives a second input into the search interface and performs, in response to receiving the second input, a second search based on the first input, wherein the second search is performed on a second set of content items managed by the content management system.

Hybrid search interface

Meeting audio capture and transcription in a collaborative document context

Methods, systems, and apparatus, including computer programs encoded on a computer-storage medium, for using a search engine implemented on a user device to identify topics or tasks associated with native application content. The method may include actions of receiving a set of data that is generated by the native application and that includes (i) native application content, and (ii) context information associated with the native application content, generating a cluster feature-vector representation based on the set of data, storing the cluster feature-vector representations in a search engine index on the user device, identifying a set of cluster feature-vector representations that are associated with a particular feature-vector representation, identifying one or more tasks that are associated with the set of cluster feature-vector representations, and providing, for output, a user interface including a selectable control that identifies one or more of the tasks.

Growing community of inventors

Millbrae, CA, United States of America

Timo Mertens