-
公开(公告)号：US20250111161A1
公开(公告)日：2025-04-03
申请号：US18978233
申请日：2024-12-12
Applicant: Google LLC
Inventor： Abhinav Rastogi , Mihir Sanjay Kale
Abstract: Systems and methods for guided text generation in task-based dialogue. In some aspects of the technology, an automated assistant system is configured to receive a user request, call multiple APIs, generate dialogue acts based on data received from each API, replace any slot names in the dialogue acts with natural language descriptions of the slots, concatenate the modified dialogue acts, and pass the concatenated result to an NLG model for generation of a natural language response. In some aspects of the technology, the automated assistant may be configured to generate simple templated responses based on the data received from each API, concatenate the simple templated responses, and pass the concatenated sequence to an NLG model trained as a sequence-to-sequence transformer for generation of a final natural language response.
-
公开(公告)号：US20250110962A1
公开(公告)日：2025-04-03
申请号：US18774775
申请日：2024-07-16
Applicant: Google LLC
Inventor： Abhinav Khandelwal , Aravindan Raghuveer , Snehal Sunilkumar Motarwar , Rishi Saket
IPC: G06F16/2457 , G06F16/9538
Abstract: Methods, computing systems, and technology for generating keywords using machine-learned techniques. The system can receive, from a user device, a first keyword associated with a content item of a first content provider. Additionally, the system can access from a keyword database, a plurality of keywords. Moreover, the system can select, using the machine-learned model, a subset of keywords from the plurality of keywords based on the content item. Furthermore, the system can process, using a machine-learned model, the first keyword and a subset of keywords to calculate a similarity score for each keyword in the subset of keywords and the first keyword. The system can determine a suggested keyword from the subset of keywords based on the similarity score for each keyword in the subset of keywords and the first keyword. Subsequently, the system can cause, on a display of the user device, a presentation of the suggested keyword.
-
公开(公告)号：US20250110591A1
公开(公告)日：2025-04-03
申请号：US18397466
申请日：2023-12-27
Applicant: Google LLC
Inventor： Leonardo Blanger , Chiayun Kuan , Stephen Mathew Pfetsch
IPC: G06F3/041 , G06F3/044 , G06F18/2415
Abstract: This document describes systems and techniques for false-input suppression at touch-sensitive displays. In aspects, an electronic device with a touch-sensitive display generates a touch frame having a heatmap matrix based on touch input received at the touch-sensitive display. The electronic device further obtains contextual data to determine if the contextual data satisfies contextual conditions. If the contextual conditions are satisfied, a machine-learned model analyzes the touch frame to generate a confidence score for a likelihood that one or more hotspots within the heatmap matrix are indicative of touch inputs from machine-learned entities. Based on the confidence score being above a threshold, the electronic device suppresses touch inputs to prevent user interface interactions.
-
公开(公告)号：US12266347B2
公开(公告)日：2025-04-01
申请号：US18055553
申请日：2022-11-15
Applicant: Google LLC
Inventor： Anshuman Tripathi , Han Lu , Hasim Sak
Abstract: A method for training a speech recognition model with a loss function includes receiving an audio signal including a first segment corresponding to audio spoken by a first speaker, a second segment corresponding to audio spoken by a second speaker, and an overlapping region where the first segment overlaps the second segment. The overlapping region includes a known start time and a known end time. The method also includes generating a respective masked audio embedding for each of the first and second speakers. The method also includes applying a masking loss after the known end time to the respective masked audio embedding for the first speaker when the first speaker was speaking prior to the known start time, or applying the masking loss prior to the known start time when the first speaker was speaking after the known end time.
-
公开(公告)号：US12265903B2
公开(公告)日：2025-04-01
申请号：US17063034
申请日：2020-10-05
Applicant: Google LLC
Inventor： Noam M. Shazeer
IPC: G06N3/063 , G06F16/901 , G06F18/214 , G06N3/04 , G06N3/08 , G06F17/11
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing tensor computations across computing devices. One of the methods includes: receiving specification data that specifies a distribution of tensor computations among a plurality of computing devices, wherein each tensor computation (i) is defined to receive, as input, one or more respective input tensors each having one or more respective input dimensions, (ii) is defined to generate, as output, one or more respective output tensors each having one or more respective output dimensions, or both, wherein the specification data specifies a respective layout for each input and output tensor that assigns each dimension of the input or output tensor to one or more of the plurality of computing devices; assigning, based on the layouts for the input and output tensors, respective device-local operations to each of the computing devices; and causing the tensor computations to be executed.
-
Patent Agency Ranking
公开(公告)号：US12265784B2
公开(公告)日：2025-04-01
申请号：US18389707
申请日：2023-12-19
Applicant: GOOGLE LLC
Inventor： Behnoosh Hariri , Ali Abdelhadi , Zifan Xiang , Timothy Chen
IPC: G06F40/166 , G06F16/176 , G06F40/134 , G06F40/169
Abstract: Techniques are described herein for providing people suggestions in collaborative online text editors. A method includes: receiving user interface input that corresponds to a document in a document editing application; automatically parsing the received user interface input to identify a name included in the user interface input; in response to identifying the name included in the user interface input, providing an option to create a link in the document between the name and a corresponding contact in a contact store; receiving additional user interface input that indicates acceptance of the option to create the link in the document; and in response to receiving the additional user interface input, automatically creating the link in the document between the name and the corresponding contact in the contact store.
-
公开(公告)号：US12265702B2
公开(公告)日：2025-04-01
申请号：US18546531
申请日：2021-04-28
Applicant: Google LLC
Inventor： Donald A. Barnett , Corbin Alexander Cunningham
IPC: G06F3/0488 , G06F21/32
Abstract: Systems and methods are provided for multimodal input collection. More particularly, the present disclosure relates to efficient and intuitive multimodal input collection for mobile devices. As an example, a mobile computing system (e.g., a smartphone, a tablet, a wearable device, etc.) can display a lock screen interface at a display device associated with the mobile computing system (e.g., an initial interface that requests interaction and/or authentication from the user before granting access to applications, etc.).
-
108.发明授权公开(公告)号：US12263910B2
公开(公告)日：2025-04-01
申请号：US18378080
申请日：2023-10-09
Applicant: GOOGLE LLC
Inventor： Sandro Feuz , Thomas Deselaers
Abstract: Implementations set forth herein relate to generating a pre-call analysis for one or more users that are receiving and/or initializing a call with one or more other users, and/or prioritizing pre-call content according to whether security-related value was gleaned from provisioning certain pre-call content. One or more machine learning models can be employed for determining the pre-call content to be cached and/or presented prior to a user accepting a call from another user. Feedback provided before, during, and/or after the call can be used as a basis from which to prioritize certain content and/or sources of content when generating pre-call content for a subsequent call. Other information, such as contextual data (e.g., calendar entries, available peripheral devices, location, etc.) corresponding to the previous call and/or the subsequent call, can also be used as a basis from which to provide a pre-call analysis.
-
公开(公告)号：US20250105940A1
公开(公告)日：2025-03-27
申请号：US18371145
申请日：2023-09-21
Applicant: Google LLC
Inventor： Rene Marcel Schmogrow
Abstract: Wavelength division multiplexing technology in which a layer of arrayed waveguides is used to extend the number of ports of wavelength selective switches used in multiplexing and/or demultiplexing the optical signals transported over the optical network. In some examples, the wavelength division multiplexing technology is used as part of an optical signal communication system, such as between data centers or as part of a larger network.
-
公开(公告)号：US20250103939A1
公开(公告)日：2025-03-27
申请号：US18725611
申请日：2022-12-29
Applicant: Google LLC
Inventor： Jürgen LISENFELD , Alexander BILMES , Alexey USTINOV , Johannes ROTZINGER
Abstract: Methods for enhancing the coherence of superconducting quantum bits with electric fields are disclosed comprising providing at least one qubit electrode comprising detrimental defects and intrinsic qubit resonance; and applying an intrinsic parameter of an electric field to the qubit electrode in order to tune the defects away from the qubit resonance, so that the energy relaxation time T1 of the qubit increases.
-
-
-
-
-
-
-
-
-
Search Results
24021
records
(took 0.054 seconds)
