公开(公告)号：US12277635B1

公开(公告)日：2025-04-15

申请号：US18532470

申请日：2023-12-07

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Louis Wang ,  Christopher James Kelley ,  Jessica Lee

IPC: G06T11/60 ,  G06T13/80

Abstract: A multimodal search system is described. The system can receive image data from a user device. Additionally, the system can receive a prompt associated with the image data. Moreover, the system can determine, using a computer vision model, a first object in the image data that is associated with the prompt. Furthermore, the system can receive, from the user device, a user indication on whether the image data includes the first object. Subsequently, in response to receiving the user indication, the system can generate a response using a large language model.

公开(公告)号：US20240403362A1

公开(公告)日：2024-12-05

申请号：US18326496

申请日：2023-05-31

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Belinda Luna Zeng ,  Viviana Caso Corella ,  Aashi Jain ,  David William Hendon ,  Christopher James Kelley ,  Jessica Lee ,  Dounia Berrada ,  Kai Yu ,  Louis Wang ,  Thomas J. Duerig ,  Radu Soricut ,  Robin Dua

IPC: G06F16/735 ,  G06F16/732 ,  G06F16/783 ,  G06T7/70 ,  G06V10/62 ,  G06V10/774 ,  G06V20/40

Abstract: A multimodal search system using a video query is described. The system can receive video data captured by a camera of a user device. The video data can have a sequence of image frames. Additionally, the system can receive audio data associated with the video data captured by the user device. Moreover, the system can process, using one or more machine-learned models, the sequence of image frames to generate video embeddings related to the sequence of the image frames. The video embeddings can have a plurality of image embeddings associated with the sequence of image frames. Furthermore, the system can determine one or more video results based on the video embeddings and the audio data. Subsequently, the system can transmit, to the user device, the one or more video results.

公开(公告)号：USD1042528S1

公开(公告)日：2024-09-17

申请号：US29869039

申请日：2022-12-20

Applicant: Google LLC

Designer： Jessica Lee ,  Bálint Miklos ,  Harshit Kharbanda ,  Severin Heiniger

Abstract: FIG. 1 is a front view of a display screen or portion thereof with a transitional graphical user interface showing a first image of the claimed design; and,
FIG. 2 is a second image thereof.
The outermost evenly spaced broken lines show an electronic device that forms no part of the claimed design. The dot-dash broken lines show a display screen or portion thereof and form no part of the claimed design. The remaining broken lines and all lined-through text, show portions of the transitional graphical user interface, and form no part of the claimed design.
The appearance of the transitional image sequentially transitions between the views of FIGS. 1-2. The process or period in which an image transitions to another forms no part of the claimed design.

公开(公告)号：USD1042527S1

公开(公告)日：2024-09-17

申请号：US29869038

申请日：2022-12-20

Applicant: Google LLC

Designer： Jessica Lee ,  Alok Aggarwal ,  Ruslan Alfridovich Abdikeev ,  Jessica Katherine Turner ,  Wenjia Yuan ,  Hassan Ali Shojania ,  Viviana Caso Corella ,  Harshit Kharbanda

Abstract: FIG. 1 is a front view of a display screen or portion thereof with a transitional graphical user interface showing a first image of the claimed design;
FIG. 2 is a second image thereof; and,
FIG. 3 is a third image thereof.
The outermost evenly spaced broken lines show an electronic device that forms no part of the claimed design. The dot-dash broken lines show a display screen or portion thereof and form no part of the claimed design. The remaining broken lines and all lined-through text, show portions of the transitional graphical user interface, and form no part of the claimed design.
The appearance of the transitional image sequentially transitions between the views of FIGS. 1-3. The process or period in which an image transitions to another forms no part of the claimed design.

公开(公告)号：US20250124075A1

公开(公告)日：2025-04-17

申请号：US18999901

申请日：2024-12-23

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Christopher James Kelley ,  Pendar Yousefi

IPC: G06F16/532 ,  G06F16/538 ,  G06F16/54

Abstract: Systems and methods for textual replacement can include the determination of a visual intent, which can trigger an interface for selecting an image to replace visual descriptors. The visually descriptive terms can be identified, and an indicator can be provided to indicate the text replacement option may be initiated. An image can then be selected by a user to replace the visually descriptive terms.

公开(公告)号：US12266065B1

公开(公告)日：2025-04-01

申请号：US18409268

申请日：2024-01-10

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Louis Wang ,  Christopher James Kelley ,  Jessica Lee ,  Igor Bonaci ,  Daniel Valcarce Silva

IPC: G06T19/00 ,  G06V20/20

Abstract: Systems and methods for providing visual indications of generative model responses can include obtaining a user input and processing the user input with a generative model to generate a model-generated-response. The systems and methods can process the model-generated response and an image of an environment to generate an augmented image. The augmented image can include visual indicators of the model-generated response, which can include annotating the image based on detected features within the image. Generation of the augmented image can include object detection and annotation based on the content of the model-generated response.

公开(公告)号：USD1048064S1

公开(公告)日：2024-10-22

申请号：US29866689

申请日：2022-09-23

Applicant: Google LLC

Designer： Christopher Kelley ,  Minsang Choi ,  Pritam Singh Pebam ,  Caroline Chilton ,  Carrie Linda Bisazza ,  Matthew Roth ,  Sabrina Curry ,  Natalie Michele Salaets ,  Jongwon Yu ,  Belinda Zeng ,  Harshit Kharbanda ,  Louis Wang ,  Austin Wu ,  Nishant Ranka ,  Morgane Magali Laure Sanglier

Abstract: FIG. 1 is a front view of a display screen or portion thereof with transitional graphical user interface showing a first image of the claimed design.
FIG. 2 is a second image thereof; and,
FIG. 3 is a third image thereof.
The outermost evenly spaced broken lines in the drawings show the electronic device, which is the environment of the design and forms no part of the claimed design. The dot-dash broken lines showing the display screen or portion thereof forms no part of the claimed design. The remaining broken lines showing portions of the graphical user interface form no part of the claimed design.
The appearance of the transitional image sequentially transitions between the views of FIGS. 1-3. The process or period in which an image transitions to another forms no part of the claimed design.

公开(公告)号：US20240202795A1

公开(公告)日：2024-06-20

申请号：US18193890

申请日：2023-03-31

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Arash Sadr ,  Alice Au Quan ,  Belinda Luna Zeng ,  Christopher James Kelley ,  Jieming Yu ,  Minsang Choi

IPC: G06Q30/0601

CPC classification number: G06Q30/0627 ,  G06Q30/0621 ,  G06Q30/0643

Abstract: Systems and methods for searching using machine-learned model-generated outputs can provide a user with a medium for generating a theoretical dataset that can then be matched to a real world example. The systems and methods can include selecting a plurality of terms, which can be utilized to generate a prompt input that can be processed by a dataset generation model to generate a plurality of model-generated datasets. A selection can then be received that selects a particular model-generated database to utilize to query a database.

公开(公告)号：US20240126807A1

公开(公告)日：2024-04-18

申请号：US17968430

申请日：2022-10-18

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Christopher James Kelley ,  Pendar Yousefi

IPC: G06F16/532 ,  G06F16/538 ,  G06F16/54

CPC classification number: G06F16/532 ,  G06F16/538 ,  G06F16/54

Abstract: Systems and methods for textual replacement can include the determination of a visual intent, which can trigger an interface for selecting an image to replace visual descriptors. The visually descriptive terms can be identified, and an indicator can be provided to indicate the text replacement option may be initiated. An image can then be selected by a user to replace the visually descriptive terms.

公开(公告)号：US12271417B2

公开(公告)日：2025-04-08

申请号：US18305660

申请日：2023-04-24

Applicant: Google LLC

Inventor： Belinda Luna Zeng ,  Harshit Kharbanda ,  Christopher James Kelley ,  Erica Bjornsson ,  David William Hendon

IPC: G06F16/532 ,  G06F16/538 ,  G06F16/55 ,  G06F16/583 ,  G06V10/22 ,  G06V10/26 ,  G06V10/75 ,  G06V10/764

Abstract: Systems and methods for multi-image search can include obtaining two or more images and determining one or more search results that are based on the two or more images. The one or more search results can be determined based on determined shared attributes of the two or more images. The one or more search results may be based on feature embeddings associated with the two or more images. The two or more images may be obtained based on one or more user interactions with one or more databases.