QUERY ANSWERING METHOD BASED ON LARGE MODEL, ELECTRONIC DEVICE, STORAGE MEDIUM, AND INTELLIGENT AGENT

    公开(公告)号:US20250094460A1

    公开(公告)日:2025-03-20

    申请号:US18969597

    申请日:2024-12-05

    Abstract: A query answering method, an electronic device, a storage medium, and an intelligent agent are provided, which relate to a field of artificial intelligence technology, and in particular to fields of large model, intelligent search and information processing technology. The method includes: inputting, in response to a retrieval content set retrieved based on a query, the query, the retrieval content set and prompt information for answer generation into the large model, so that the large model performs operations of: processing, based on a current task in the prompt information and the query, a current text corresponding to the retrieval content set to obtain a processed text, where the current task is determined based on a task execution order in the prompt information; and obtaining, in a case of determining that the processed text meets a preset condition, an answer to the query based on the processed text.

    TRAINING METHOD FOR A DEEP LEARNING MODEL

    公开(公告)号:US20250061305A1

    公开(公告)日:2025-02-20

    申请号:US18936686

    申请日:2024-11-04

    Abstract: A training method, an inference method, a device, an apparatus, and a medium for a deep learning model are provided. A first model includes a plurality of first parameters, a second model comprises a plurality of second parameters, which is initialized to parameter values of a plurality of target parameters selected from the plurality of first parameters. The training method includes: determining a target loss for both the first model and the second model; adjusting parameter values, including: in response to determining that the target loss indicates that the parameter values of at least part of the target parameters need to be adjusted, synchronously adjusting the parameter values of the corresponding second parameters; and in response to determining that the target loss indicates that the parameter values of at least part of the second parameters need to be adjusted, synchronously adjusting the parameter values of the corresponding target parameters.

    METHOD AND SYSTEM OF TRAINING DEEP LEARNING MODEL, DEVICE, AND MEDIUM

    公开(公告)号:US20240394190A1

    公开(公告)日:2024-11-28

    申请号:US18696757

    申请日:2022-09-27

    Abstract: The present application provides a method of training a deep learning model. A specific implementation solution of the method of training the deep learning model includes: determining, according to first training data for a current training round, a first target parameter required to be written into a target memory in a first network parameter required by an embedding of the first training data, wherein the target memory is a memory contained in a target processor; determining a remaining storage slot in the target memory according to a first mapping relationship between a storage slot of the target memory and a network parameter; and writing, in response to the remaining storage slot meeting a storage requirement of the first target parameter, the first target parameter into the target memory so that a computing core contained in the target processor adjusts the first network parameter according to the first training data.

    METHOD FOR GENERATING HIGH DEFINITION MAP, DEVICE AND COMPUTER STORAGE MEDIUM

    公开(公告)号:US20240185379A1

    公开(公告)日:2024-06-06

    申请号:US17758692

    申请日:2021-11-17

    CPC classification number: G06T3/14 G06T5/80 G06T7/38 G06T7/70

    Abstract: A method and an apparatus for generation a high definition map, a device and a computer storage medium, which relate to automatic driving and deep learning technologies in the field of artificial intelligence technologies, are disclosed. An implementation includes: acquiring point cloud data and front-view image data which are collected respectively by a plurality of collecting devices at a plurality of location points to obtain a sequence of point clouds and a sequence of front-view images; performing registration of the front-view images and the point clouds on the sequence of point clouds and the sequence of front-view images; transforming the sequence of front-view images into a top-view image based on the result of the registration and determining coordinate information of each pixel in the top-view image; and identifying map elements of the top-view image to obtain the high definition map.

    METHOD FOR AUTOMATICALLY PRODUCING MAP DATA, AND RELATED APPARATUS

    公开(公告)号:US20230041943A1

    公开(公告)日:2023-02-09

    申请号:US17961930

    申请日:2022-10-07

    Abstract: The present disclosure provides a method and apparatus for automatically producing map data. The method includes: performing track rectification on crowdsourcing tracks based on corresponding standard tracks, and locating each map element included, based on depth information of track point images included in the rectified crowdsourcing tracks; comparing a latest map element obtained based on the rectified crowdsourcing tracks locating and an old map element at a corresponding locating position using a pre-built entity semantic map; determining, in response to a change in the latest map element compared to the old map element, a target processing method according to a processing standard of a changed map element pre-abstracted from a map element update specification; and processing the latest map element according to the target processing method to obtain a processed latest map.

    METHOD FOR TRAINING DECISION-MAKING MODEL PARAMETER, DECISION DETERMINATION METHOD, ELECTRONIC DEVICE, AND STORAGE MEDIUM

    公开(公告)号:US20230032324A1

    公开(公告)日:2023-02-02

    申请号:US17966127

    申请日:2022-10-14

    Abstract: A method for training a decision-making model parameter, a decision determination method, an electronic device, and a non-transitory computer-readable storage medium are provided. In the method, a perturbation parameter is generated according to a meta-parameter, and first observation information of a primary training environment is acquired based on the perturbation parameter. According to the first observation information, an evaluation parameter of the perturbation parameter is determined. According to the perturbation parameter and the evaluation parameter thereof, an updated meta-parameter is generated. The updated meta-parameter is determined as a target meta-parameter, when it is determined, according to the meta-parameter and the updated meta-parameter, that a condition for stopping primary training is met. According to the target meta-parameter, a target memory parameter corresponding to a secondary training task is determined, where the target memory parameter and the target meta-parameter are used to make a decision corresponding to a prediction task.

    AFFINITY PREDICTION METHOD AND APPARATUS, METHOD AND APPARATUS FOR TRAINING AFFINITY PREDICTION MODEL, DEVICE AND MEDIUM

    公开(公告)号:US20220215899A1

    公开(公告)日:2022-07-07

    申请号:US17557691

    申请日:2021-12-21

    Abstract: The present disclosure discloses an affinity prediction method and apparatus, a method and apparatus for training an affinity prediction model, a device and a medium, and relates to the field of artificial intelligence technologies, such as machine learning technologies, smart medical technologies, or the like. An implementation includes: collecting a plurality of training samples, each training sample including information of a training target, information of a training drug and a test data set corresponding to the training target; and training an affinity prediction model using the plurality of training samples. In addition, there is further disclosed the affinity prediction method. The technology in the present disclosure may effectively improve accuracy and a training effect of the trained affinity prediction model. During an affinity prediction, accuracy of a predicted affinity of a target to be detected with a drug to be detected may be higher by acquiring a test data set corresponding to the target to be detected to participate in the prediction.

Patent Agency Ranking