Implementing text generation
    41.
    发明授权

    公开(公告)号:US11675983B2

    公开(公告)日:2023-06-13

    申请号:US17331526

    申请日:2021-05-26

    CPC classification number: G06F40/56 G06F40/117 G06F40/126 G06N20/00

    Abstract: A method for implementing text generation, a device and a medium are provided. The method includes: determining a target task type of a target text generation task from multiple task types supported by a pre-trained general text generation model; determining, based on a requirement of the target text generation task for a target output text, a first target output text attribute for the target text generation task from multiple output text attributes supported by the general text generation model; and fine tuning the general text generation model based on a target training data set associated with the target text generation task to obtain a task-specific text generation model, by taking task indication information for the target task type and first attribute indication information for the first target output text attribute as at least part of an input of the general text generation model.

    PROCESSOR AND IMPLEMENTATION METHOD, ELECTRONIC DEVICE, AND STORAGE MEDIUM

    公开(公告)号:US20230179546A1

    公开(公告)日:2023-06-08

    申请号:US17792867

    申请日:2021-08-05

    Inventor: Xiaoping YAN

    CPC classification number: H04L49/9057 H04L45/74 H04L49/9063 G06N3/063

    Abstract: A processor includes a system controller configured to send predetermined packet information to a data packing and unpacking module; the data packing and unpacking module configured to acquire corresponding packet data from a storage array module according to the packet information, pack the packet data with the packet information, send a first packet obtained from packing to an operation module for operation processing, acquire a second packet returned by the operation module, unpack the second packet to obtain operation result data, and store the operation result data in the storage array module; the storage array module configured to store data; and the operation module configured to perform operation processing on the acquired first packet, generate the second packet according to the operation result data, and return the second packet to the data packing and unpacking module.

    Method and apparatus for querying shortest path of graph, and storage medium

    公开(公告)号:US11657091B2

    公开(公告)日:2023-05-23

    申请号:US16986120

    申请日:2020-08-05

    CPC classification number: G06F16/9024 G06F16/24558 G06F16/288

    Abstract: The present disclosure provides a method and an apparatus for querying the shortest path of a graph, and a storage medium. The method includes: performing a breadth-first search in a distributed graph database with a start entity to be searched and an end entity to be searched as root nodes respectively, and obtaining a layer of new entities for each search; performing an intersection checking on the new entities and entities of the highest layer from a search set on an opposite side, so as to determine whether an intersection between the new entities and the entities of the highest layer exists; and when the intersection exists, determining intersection points, and performing path backtracking through the intersection points to find the shortest path from the start entity to the end entity.

    Method and apparatus for updating deep learning model

    公开(公告)号:US11640550B2

    公开(公告)日:2023-05-02

    申请号:US16026976

    申请日:2018-07-03

    Abstract: The disclosure discloses a method and apparatus for updating a deep learning model. An embodiment of the method comprises: executing following updating: acquiring a training dataset under a preset path, training a preset deep learning model based on the training dataset to obtain a new deep learning model; updating the preset deep learning model to the new deep learning model; increasing training iterations; determining whether a number of training iterations reaches a threshold of training iterations; stopping executing the updating if the number of training iterations reaches the threshold of training iterations; and continuing to execute the updating after an interval of a preset time length if the number of training iterations fails to reach the threshold of training iterations. This embodiment has improved the model updating efficiency.

    Method and apparatus for operating database

    公开(公告)号:US11640474B2

    公开(公告)日:2023-05-02

    申请号:US16455394

    申请日:2019-06-27

    Inventor: Hao Song Baohua Lai

    Abstract: Enclosed are a method and apparatus for operating a database. The method includes: performing, in response to determining a user indicated by a user identifier having a permission to operate on data targeted by a database operation statement, a digital signature on the database operation statement using a user private key to obtain signature information, generating transaction information according to the database operation statement, the signature information and the user identifier, and storing the generated transaction information into a local transaction information buffer pool; and selecting, in response to competing for a transaction information block recording permission using a preset consensus algorithm, transaction information in the local transaction information buffer pool to generate a block, parsing and executing a database operation statement in each piece of selected transaction information, concatenating the generated block to a local blockchain, and broadcasting the generated block to other database servers.

Patent Agency Ranking