公开(公告)号：US20250094798A1

公开(公告)日：2025-03-20

申请号：US18727800

申请日：2022-02-03

Applicant: Google LLC

Inventor： Li Zhang ,  Matthew Sharifi ,  David Petrou ,  Blaise Aguera y Arcas

IPC: G06N3/08

Abstract: Systems and methods for partitioning a large model that has been configured to use a model-synthesis approach in which multiple basis models are combined to generate a final output. The present technology provides systems and methods for identifying a device-specific or subject-specific subset of those basis models to be used on a given device, such that it need not store the weight matrices for the entire set of basis models, and may perform inference using only the weight matrices of the identified subset of basis models. In some examples, the subset of basis models used by a given device may be updated based on actual usage and feedback. Likewise, in some examples, the model may be trained in a federated setting in which multiple devices each utilize different subsets of the basis models, and share training signals with a full copy of the model.

公开(公告)号：US20250093173A1

公开(公告)日：2025-03-20

申请号：US18559638

申请日：2023-01-04

Applicant: GOOGLE LLC

Inventor： Matthew Sharifi ,  Jyrki Alakuijala

IPC: G01C21/36 ,  G01C21/34

Abstract: To provide navigation directions to one or more points of interest (POIs) for accomplishing a user's goals, a computing device receives an indication of N goals for a user to accomplish, and identifies M POIs for accomplishing the N goals. N is greater than M. The computing device then generates a set of navigation directions for navigating to each of the M POIs, and provides the set of navigation directions for display to the user.

公开(公告)号：US20250069617A1

公开(公告)日：2025-02-27

申请号：US18454031

申请日：2023-08-22

Applicant: Google LLC

Inventor： Victor Carbune ,  Matthew Sharifi

IPC: G10L25/48 ,  G10L15/183 ,  G10L15/22

Abstract: A method includes receiving a natural language query specifying an action for an assistant interface to perform and selecting one or more business large language models (LLMs) for the assistant interface to interact with to fulfill performance of the action. For each business LLM, method also includes accessing an adapter module to structure the natural language query into a respective prompt specifically formulated for the corresponding business LLM, issuing, for input to the corresponding business LLM, the respective prompt, and receiving corresponding response content from the corresponding business LLM that conveys details regarding performance of a corresponding portion of the action. The method also includes presenting, for output from the user device, presentation content based on the corresponding response content received from each corresponding business LLM.

公开(公告)号：US12223960B2

公开(公告)日：2025-02-11

申请号：US18608559

申请日：2024-03-18

Applicant: GOOGLE LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G10L21/00 ,  G06F16/9032 ,  G06F16/9035 ,  G06F21/12 ,  G10L15/22 ,  G10L15/26 ,  G10L25/00 ,  G06F3/04812

Abstract: Implementations relate to generating a proficiency measure, and utilizing the proficiency measure to adapt one or more automated assistant functionalities. The generated proficiency measure is for a particular class of automated assistant actions, and is specific to an assistant device and/or is specific to a particular user. A generated proficiency measure for a class can reflect a degree of proficiency, of a user and/or of an assistant device, for that class. Various automated assistant functionalities can be adapted, for a particular class, responsive to determining the proficiency measure satisfies a threshold, or fails to satisfy the threshold (or an alternate threshold). The adaptation(s) can make automated assistant processing more efficient and/or improve (e.g., shorten the duration of) user-assistant interaction(s).

公开(公告)号：US20250028744A1

公开(公告)日：2025-01-23

申请号：US18714673

申请日：2022-01-07

Applicant: Google LLC

Inventor： Matthew Sharifi ,  Maryam Karimzadehgan ,  Lukas Zilka ,  Julian Odell ,  Jesper Andersen

IPC: G06F16/332 ,  G06F16/33 ,  G06F40/40 ,  G06N3/006 ,  G06N20/00

Abstract: Systems and methods for generating a domain-specific conversational automated assistant. In some examples, a conversational language model is used to generate a target answer and a target action recommendation in response to each of a set of in-domain training questions. In some examples, the conversational language model is further used to generate follow-up questions to one or more of its generated target answers, and to then generate a target answer and target action recommendation to each generated follow-up question. In some examples, the processing system also generates a set of out-of-domain training examples including an out-of-domain question, a predetermined target answer, and a predetermined target action recommendation. The automated assistant may then be trained to predict the generated target answers and target action recommendations based on the associated training question or generated follow-up question, as well as any prior questions and answers in the conversation.

公开(公告)号：US20250024237A1

公开(公告)日：2025-01-16

申请号：US18900067

申请日：2024-09-27

Applicant: GOOGLE LLC

Inventor： Matthew Sharifi ,  Jorge Pereira ,  Dominik Roblek ,  Julian Odell ,  Cong Li ,  David Petrou

IPC: H04W4/60 ,  G06F16/23 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/587 ,  G06F16/907 ,  G06F16/9535 ,  G06V20/62 ,  H04L67/50 ,  H04W4/029 ,  H04W4/18

Abstract: Systems and methods are provided for a personalized entity repository. For example, a computing device comprises a personalized entity repository having fixed sets of entities from an entity repository stored at a server, a processor, and memory storing instructions that cause the computing device to identify fixed sets of entities that are relevant to a user based on context associated with the computing device, rank the fixed sets by relevancy, and update the personalized entity repository using selected sets determined based on the rank and on set usage parameters applicable to the user. In another example, a method includes generating fixed sets of entities from an entity repository, including location-based sets and topic-based sets, and providing a subset of the fixed sets to a client, the client requesting the subset based on the client's location and on items identified in content generated for display on the client.

公开(公告)号：US20250022464A1

公开(公告)日：2025-01-16

申请号：US18900099

申请日：2024-09-27

Applicant: GOOGLE LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G10L15/22 ,  G10L15/30 ,  G10L15/32

Abstract: Techniques are described herein for warm word arbitration between automated assistant devices. A method includes: determining that warm word arbitration is to be initiated between a first assistant device and one or more additional assistant devices, including a second assistant device; broadcasting, by the first assistant device, to the one or more additional assistant devices, an active set of warm words for the first assistant device; for each of the one or more additional assistant devices, receiving, from the additional assistant device, an active set of warm words for the additional assistant device; identifying a matching warm word included in the active set of warm words for the first assistant device and included in the active set of warm words for the second assistant device; and enabling or disabling detection of the matching warm word by the first assistant device, in response to identifying the matching warm word.

公开(公告)号：US12198671B2

公开(公告)日：2025-01-14

申请号：US18309754

申请日：2023-04-28

Applicant: Google LLC

Inventor： Matthew Sharifi ,  Jakob Nicolaus Foerster

IPC: G10L13/00 ,  G06F40/253 ,  G06F40/289 ,  G10L13/08

Abstract: In some implementations, a language proficiency of a user of a client device is determined by one or more computers. The one or more computers then determines a text segment for output by a text-to-speech module based on the determined language proficiency of the user. After determining the text segment for output, the one or more computers generates audio data including a synthesized utterance of the text segment. The audio data including the synthesized utterance of the text segment is then provided to the client device for output.

公开(公告)号：US20250006207A1

公开(公告)日：2025-01-02

申请号：US18697860

申请日：2021-10-12

Applicant: Google LLC

Inventor： Matthew Sharifi

IPC: G10L19/00 ,  G06F40/289 ,  G10L13/08

Abstract: Systems and methods for steganographic embedding of metadata in media, and improved generation of synthetic media files. In some examples, a steganography encoder may be trained to encode a media file with data such that it will be more likely to be accurately decoded, and/or less likely to be perceptible to a user or other applications. In some examples, the media file may be a synthetically generated media file, and the data may be some or all of the data used to generate the synthetically generated media file. In some examples, a generative model may be trained to create synthetically generated media files that are more likely to be accurately interpreted by an interpretive model. In some examples, data encoded into a synthetically generated media file may be used to output an indication that the file was synthetically generated.

公开(公告)号：US20240420698A1

公开(公告)日：2024-12-19

申请号：US18820381

申请日：2024-08-30

Applicant: GOOGLE LLC

Inventor： Matthew Sharifi ,  Victor Carbune

IPC: G10L15/22 ,  G06F16/245 ,  G06F16/248 ,  G10L15/26 ,  G10L15/30 ,  G10L15/32

Abstract: Systems and methods for determining whether to combine responses from multiple automated assistants. An automated assistant may be invoked by a user utterance, followed by a query, which is provided to a plurality of automated assistants. A first response is received from a first automated assistant and a second response is received from a second automated assistant. Based on similarity between the responses, a primary automated assistant determines whether to combine the responses into a combined response. Once the combined response has been generated, one or more actions are performed in response to the combined response.