Google Inc.

Michael Andrew Goodman

Yuval Baror

Praveen Krishnakumar

Vikram Aggarwal

Yoav Tzur

Wei Yu

Ágoston Weisz

Thang Minh Luong

Bibo Xu

Golnaz Ghiasi

Yifeng Lu

Sanil Jain

Amin Ghafouri

Igor Petrovski

Evgeny Sluzhaev

Oscar Akerlund

Rakesh Shivanna

Vikas Peswani

Trevor D Strohman

Jaclyn Konzelmann

Valerie Nygaard

Diana Avram

Dekel Auster

Dan Rasin

Rafael Goldfarb

Lior Alon

Nino Tasca

Nevzat Topcu

Komal Singh

Khyatti Gupta

Yaguang Li

Yu Qing Du

Apoorv Kulshreshtha

Dustin Tran

A method of providing a personalized audio briefing to a user is performed at an electronic device. The device receives identification of information sources associated with the user. Each of the information sources is associated with a content type. The device receives an authorization to access the identified information sources and a preferred order of content types for presentation within the audio briefing. It transmits to a remote system the identification, the authorization, and the preferred order. Following the transmitting, the device receives a verbal input from the user requesting the audio briefing. In response to the verbal input, the device receives a response generated by the remote system, including content from the information sources and information inserted by the remote system based on the authorization to access received from the user. The device outputs an audible response according to the preferred order.

Personalized and contextualized audio briefing

A method includes determining, by an assistant executing at one or more processors, a default group of actions that the assistant is configured to execute in response to receiving a particular audible command. The method includes determining, by the assistant, based on the default group of actions and a user profile associated with a particular user, a custom group of actions that the assistant is configured to execute in response to receiving the particular audible command from the particular user. The method also includes receiving, by the assistant, an indication of the particular audible command, and determining, by the assistant, whether the indication of particular audible command originated from the particular user. The method further includes, responsive to determining that the indication of particular audible command originated from the particular user, executing, by the assistant, each action from the custom group of actions.

Virtual assistant configured to automatically customize groups of actions

Implementations are directed to utilizing an assistant to automatically navigate an interactive voice response (IVR) tree to arrive at a target state during an assisted telephone call. The assistant can receive input to initiate the assisted telephone call, identify an entity to engage with, on behalf of the user, and during the assisted telephone call, based on the input, and identify an IVR tree stored in association with the entity. In various implementations, navigation of the IVR tree can be modified based on interaction(s) detected at a client device subsequent to initiating the assisted telephone call. In various implementations, the assisted telephone call can be initiated from a search interface, and the target state can be associated with a given search result. In various implementations, the IVR tree can be dynamic in that only a subset of candidate state(s) of the IVR tree may be available as the target state.

Automatic navigation of an interactive voice response (IVR) tree on behalf of human user(s)

Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.

Multimedia content management for large language model(s) and/or other generative model(s)

Implementations are directed to using an assistant to initiate automated telephone calls with entities. Some implementations identify an item of interest, identify a group of entities associated with the item, and initiate the calls with the entities. During a given call with a given entity, the assistant can request a status update regarding the item, and determine a temporal delay before initiating another call with the given entity to request a further status update regarding the item based on information received responsive to the request. Other implementations receive a request to perform an action on behalf of a user, identify a group of entities that can perform the action, and initiate a given call with a given entity. During the given call, the assistant can initiate an additional call with an additional entity, and generate notification(s), for the user, based on result(s) of the given call and/or the additional call.

Selective performance of automated telephone calls to reduce latency and/or duration of assistant interaction

Recommending an automated assistant action for inclusion in an existing automated assistant routine of a user, where the existing automated assistant routine includes a plurality of preexisting automated assistant actions. If the user confirms the recommendation through affirmative user interface input, the automated assistant action can be automatically added to the existing automated assistant routine. Thereafter, when the automated assistant routine is initialized, the preexisting automated assistant actions of the routine will be performed, as well as the automated assistant action that was automatically added to the routine in response to affirmative user interface input received in response to the recommendation.

Recommending automated assistant action for inclusion in automated assistant routine

Implementations described herein relate to reducing latency in automated assistant interactions. In some implementations, a client device can receive audio data that captures a spoken utterance of a user. The audio data can be processed to determine an assistant command to be performed by an automated assistant. The assistant command can be processed, using a latency prediction model, to generate a predicted latency to fulfill the assistant command. Further, the client device (or the automated assistant) can determine, based on the predicted latency, whether to audibly render pre-cached content for presentation to the user prior to audibly rendering content that is responsive to the spoken utterance. The pre-cached content can be tailored to the assistant command and audibly rendered for presentation to the user while the content is being obtained, and the content can be audibly rendered for presentation to the user subsequent to the pre-cached content.

Methods and systems for reducing latency in automated assistant interactions

Implementations relate to generating multi-modal response(s) through utilization of large language model(s) (LLM(s)). Processor(s) of a system can: receive natural language (NL) based input, generate a multi-modal response that is responsive to the NL based output, and cause the multi-modal response to be rendered. In some implementations, and in generating the multi-modal response, the processor(s) can process, using a LLM, LLM input (e.g., that includes at least the NL based input) to generate LLM output, and determine, based on the LLM output, textual content for inclusion in the multi-modal response and multimedia content for inclusion in the multi-modal response. In some implementations, the multimedia content can be obtained based on a multimedia content tag that is included in the LLM output and that is indicative of the multimedia content. In various implementations, the multimedia content can be interleaved between segments of the textual content.

Generating multi-modal response(s) through utilization of large language model(s)

Growing community of inventors

Oakland, CA, United States of America

Michael Andrew Goodman