TEXT-BASED SEARCH OPTIMIZATION VIA IMPLICIT IMAGE SEARCH AUGMENTATION

    公开(公告)号:US20240362267A1

    公开(公告)日:2024-10-31

    申请号:US18139514

    申请日:2023-04-26

    申请人: eBay Inc,

    发明人: Fei DONG Wei LIU Bin LI

    摘要: A text-based search optimization via implicit image search augmentation eliminates or reduces the need for providing an image query input, performing multiple search queries, displaying multiple user interfaces, and the like by enabling a search engine to return a single set of search results comprising an aggregated and ranked set of text-based results and a set of image-based results based on one or more text-based keywords of a search query. Initially, a search query comprising one or more text-based keywords is received at a search engine. A machine learning model is utilized to generate an image based on a first portion of the one or more text-based keywords. Image-based results are generated based on the image. Text-based results are generated based on a second portion of the one or more text-based keywords. The image-based results and the text-based results are aggregated and ranked in a single set of search results.

    IMAGE SEARCHING USING A FULL-TEXT SEARCH ENGINE

    公开(公告)号:US20240362266A1

    公开(公告)日:2024-10-31

    申请号:US18766361

    申请日:2024-07-08

    摘要: A method including pre-screening one or more second images from a database for a search result based on one or more substring distances between one or more first binary substrings for a first image and one or more second binary substrings for the one or more second images, comprises: determining the one or more substring distances between one or more substring pairs of the one or more first binary substrings and the one or more second binary substrings of the one or more second images, and upon determining that the one or more substring distances and the one or more second binary substrings are not greater than one or more substring distance thresholds, including the one or more second images in the search result. The method further can include after pre-screening, determining one or more image distances for one or more third images of the search result. The method can also include when the one or more image distances for the one or more third images are greater than a predetermined image distance threshold, removing the one or more third images from the search result. Other embodiments are disclosed.

    Reducing false positives in entity matching based on image-linking graphs

    公开(公告)号:US12132727B2

    公开(公告)日:2024-10-29

    申请号:US17824539

    申请日:2022-05-25

    申请人: PAYPAL, INC.

    IPC分类号: H04L9/40 G06F16/532 G06V40/16

    摘要: Methods and systems are presented for performing comprehensive and accurate matching of user accounts with one or more known entities based on image-linking graphs. Images related to each known entity are retrieved from one or more online sources. Faces are extracted from the images. Based on attributes of the faces in the images, an image-linking graph is generated for the entity. When a user account is determined to be a potential match for the entity based on text-based attributes, an image associated with the account may be obtained. If the image matches with any one of the faces in the image-linking graph, an action is performed to the user account based on a position of the matched face in the image-linking graph.

    Face picture information display method and terminal device

    公开(公告)号:US12118199B2

    公开(公告)日:2024-10-15

    申请号:US17355158

    申请日:2021-06-22

    发明人: Yubing Zhang

    摘要: The embodiments of the present disclosure provide an information display method and a terminal device. The information display method includes: receiving a first input that is performed by a user on a first picture; displaying M face pictures and icons of K messaging programs in response to the first input, where the first picture includes the M face pictures; receiving a second input that is performed by the user; and displaying N face pictures and T pieces of first information in response to the second input, where the N face pictures are face pictures that are of the M face pictures and that correspond to the second input, each piece of first information corresponds to at least one face picture, one piece of first information is information of a user indicated by at least one face picture corresponding to the first information, and each piece of first information includes information in at least one first messaging program of the K messaging programs.

    Intelligent Systems and Methods for Visual Search Queries

    公开(公告)号:US20240330357A1

    公开(公告)日:2024-10-03

    申请号:US18743754

    申请日:2024-06-14

    申请人: Google LLC

    摘要: A user can submit a visual query that includes one or more images. Various processing techniques such as optical character recognition (OCR) techniques can be used to recognize text (e.g. in the image, surrounding image(s), etc.) and/or various object detection techniques (e.g., machine-learned object detection models, etc.) may be used to detect objects (e.g., products, landmarks, animals, humans, etc.) within or related to the visual query. Content related to the detected text or object(s) can be identified and potentially provided to a user as search results or a proactive content feed. As such, aspects of the present disclosure enable the visual search system to more intelligently process a visual query to provide improved search results and content feeds, including those search results which are more personalized and/or consider contextual signals to account for implicit characteristics of the visual query and/or user's search intent.

    Iterative Image Generation From Text
    6.
    发明公开

    公开(公告)号:US20240320867A1

    公开(公告)日:2024-09-26

    申请号:US18186752

    申请日:2023-03-20

    发明人: Celeste M.B. Bean

    IPC分类号: G06T11/00 G06F16/532

    CPC分类号: G06T11/00 G06F16/532

    摘要: Methods and systems are presented for automatically identifying additional descriptors of an image generated by a text-to-image generator from an initial prompt. The additional descriptors are either incorporated into the initial prompt or made into a new prompt in order to produce another image from the text-to-image generator. The initial prompt and additional descriptors can describe visual features represented in images including content, artistic styles, visual perspectives, and other visible attributes of images. The additional descriptors can be incorporated into the initial prompt by replacing or supplementing existing descriptors. Subsequent images generated by the text-to-image generator can be used to iteratively produce additional descriptors.

    Systems and methods for identifying a design template matching a search query

    公开(公告)号:US20240311422A1

    公开(公告)日:2024-09-19

    申请号:US18600121

    申请日:2024-03-08

    申请人: Canva Pty Ltd

    IPC分类号: G06F16/532 G06F16/2457

    CPC分类号: G06F16/532 G06F16/24578

    摘要: Methods and systems for identifying design templates that match an input query are disclosed. The method includes: receiving a design search query; performing a template search based on the design search query, the template search returning a first template design, the first template design including a target image; processing the design search query to generate an image search query; performing an image search based on the image search query, the image search returning a candidate image; and generating a new design. The new design is based on the first template design and includes the candidate image instead of the target image.

    Probabilistic procedure planning for instructional videos

    公开(公告)号:US12050640B2

    公开(公告)日:2024-07-30

    申请号:US17984685

    申请日:2022-11-10

    IPC分类号: G06F16/00 G06F16/532 G06N7/01

    CPC分类号: G06F16/532 G06N7/01

    摘要: The present disclosure provides methods and apparatuses for probabilistic procedure planning for generating a plan based on a goal relating to an end state. In some embodiments, a method includes receiving a request from a user to generate an action plan comprising T intermediate actions between a start state and the end state. The method further includes constructing an input query matrix based on T, the start state, the end state, positional encodings, and pseudo-random noise information. The method further includes generating, using a machine learning transformer decoder, the action plan based on the input query matrix and a plurality of learnable vectors. The method further includes providing the action plan to the user. The action plan indicates a probability distribution of a plurality of distinct action sequences, to be performed by the user, that transform the start state to the end state.