利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

818 records (took 0.016 seconds)

    Agent environment co-creation using reinforcement learning
    2.
    发明授权
    Agent environment co-creation using reinforcement learning 有权

    公开(公告)号：US12229223B2

    公开(公告)日：2025-02-18

    申请号：US16919388

    申请日：2020-07-02

    Applicant: Accenture Global Solutions Limited

    Inventor： Robert P. Dooley ,  Dylan James Snow

    IPC: G06F9/451 ,  G06F18/21 ,  G06F18/214 ,  G06F18/2413

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for agent environment co-creation. The methods, systems, and apparatus include actions of determining a success rate of an agent in an environment with a first complexity, determining that the success rate satisfies a complexity change criteria, in response to determining that the success rate satisfies the complexity change criteria, determining a second complexity that has a greater complexity than the first complexity, training the agent in the environment with the second complexity, and providing the agent trained in the environment with the second complexity.

    Generative artificial intelligence for generating predicted effects in response to a synthetic stimulus
    5.
    发明授权
    Generative artificial intelligence for generating predicted effects in response to a synthetic stimulus 有权

    公开(公告)号：US12216742B2

    公开(公告)日：2025-02-04

    申请号：US18330896

    申请日：2023-06-07

    Applicant: Wells Fargo Bank, N.A.

    Inventor： Naveen Gururaja Yeri

    IPC: G06F18/23 ,  G06F18/2413

    Abstract: Systems, apparatuses, methods, and computer program products are disclosed for generating a predicted effect for a target cluster in response to a synthetic stimulus. An example method includes receiving a synthetic behavior prediction request and generating a plurality of clusters, wherein each cluster is associated with a corresponding centroid position. The method further includes selecting the target cluster from the plurality of clusters and generating the predicted effect for the target cluster in response to the synthetic stimulus based on the centroid position corresponding to the target cluster. The method further includes providing a predicted effect notification.

    METHOD AND SYSTEM FOR REAL-TIME GEO REFERENCING STABILIZATION
    6.
    发明申请
    METHOD AND SYSTEM FOR REAL-TIME GEO REFERENCING STABILIZATION 有权

    公开(公告)号：US20250039545A1

    公开(公告)日：2025-01-30

    申请号：US18915994

    申请日：2024-10-15

    Applicant: PALANTIR TECHNOLOGIES INC.

    Inventor： Jay Harshadbhai Patel

    IPC: H04N23/68 ,  B64C39/02 ,  B64U101/30 ,  G06F18/2413 ,  G06T7/35 ,  G06T7/38 ,  G06T15/06 ,  G06V20/17 ,  G06V20/40

    Abstract: A computing system and methods are provided for georeferencing stabilization. An exemplary method includes: obtaining a video stream capturing an area from a camera of a drone, where the video stream includes a plurality of frames, each including a field of view of the image capturing device and metadata of the image capturing device when the frame is captured; constructing a geographic (geo) lattice for the field of view in each of the plurality of frames, the geo lattice comprises a plurality of points, each being associated with raw coordinates determined based on the corresponding metadata; and building a lattice map with stabilized geo coordinates by (1) aligning the frames, (2) averaging the raw geo coordinates for given intersection points, and (3) building the lattice map based on the averaged geo coordinates of the intersection points.

    Classification with segmentation neural network for image-based content capture
    7.
    发明授权
    Classification with segmentation neural network for image-based content capture 有权

    公开(公告)号：US12211244B2

    公开(公告)日：2025-01-28

    申请号：US18325127

    申请日：2023-05-30

    Applicant: Open Text SA ULC

    Inventor： Sreelatha Reddy Samala

    IPC: G06T5/00 ,  G06F18/21 ,  G06F18/2413 ,  G06T5/20 ,  G06T7/11 ,  G06V10/26 ,  G06V10/82 ,  G06V30/19 ,  G06V30/413

    Abstract: A segmentation neural network is extended to provide classification at the segment level. An input image of a document is received and processed, utilizing a segmentation neural network, to detect pixels having a signature feature type. A signature heatmap of the input image can be generated based on the pixels in the input image having the signature feature type. The segmentation neural network is extended from here to further process the signature heatmap by morphing it to include noise surrounding an object of interest. This creates a signature region that can have no defined shape or size. The morphed heatmap acts as a mask so that each signature region or object in the input image can be detected as a segment. Based on this segment-level detection, the input image is classified. The classification result can be provided as feedback to a machine learning framework to refine training.

    Method for functional classification of luminaires
    8.
    发明授权
    Method for functional classification of luminaires 有权

    公开(公告)号：US12207371B2

    公开(公告)日：2025-01-21

    申请号：US17909772

    申请日：2021-02-23

    Applicant: Tridonic GmbH & Co KG

    Inventor： Istvan Bakk ,  Christian Fragner ,  Anna Werkovits

    IPC: H05B47/12 ,  G06F18/2411 ,  G06F18/2413 ,  H05B47/155 ,  H05B47/19

    Abstract: A method (20) for functional classification of luminaires (101a-d) arranged as a grid (100) has luminaires (101a-d) with at least two different sensors (103, 105, 107), such as at least two of a light sensor (103), an acoustic sensor (105) and a motion sensor (107). Output signals of the sensors (103, 105, 107) are supplied to a controller (109), and are wirelessly forwarded (23) along with timestamps and luminaire IDs to a gateway and then transmitted to a central database (403). The timestamps are used to correlate the sensor information signals (130) over a defined period of time, and to generate (27) functional classification information based on the correlations found. The functional classification information indicates a likelihood function of a certain usage of each luminaire, out of a given set of usage functions.

    Deep mapping for imputing nulls
    10.
    发明授权
    Deep mapping for imputing nulls 有权

    公开(公告)号：US12189723B2

    公开(公告)日：2025-01-07

    申请号：US18468235

    申请日：2023-09-15

    Applicant: PAYPAL, INC.

    Inventor： Itay Margolin ,  Tomer Handelman

    IPC: G06F16/18 ,  G06F18/213 ,  G06F18/214 ,  G06F18/2413 ,  G06N5/04 ,  G06N20/20

    Abstract: Methods and systems are presented for imputing missing data items within a first dataset based on data associated with a second dataset that is the nearest neighbor of the first dataset. A first mapping model is configured to map data subsets corresponding to a first data source to first positions in a multi-dimensional space. A second mapping model is configured to map data subsets corresponding to a second data source to second positions in the multi-dimensional space. The first and second mapping models are trained together to reduce a distance between positions mapped by the first and second mapping models based on corresponding data subsets that belong to the same entity. A nearest neighbor dataset to the first dataset is identified based on the first and second mapping models. Data associated with the nearest neighbor dataset is used to impute the missing data items of the first dataset.

Patent Agency Ranking