中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

1343 records (took 0.022 seconds)

    数据处理装置及方法
    1.
    发明申请
    数据处理装置及方法 审中-公开

    公开(公告)号：WO2023087227A1

    公开(公告)日：2023-05-25

    申请号：PCT/CN2021/131571

    申请日：2021-11-18

    Applicant: 华为技术有限公司

    Inventor： 张琳坚 ,  范团宝 ,  李忠逵 ,  郑明

    IPC: G06N3/00

    Abstract: 本公开提供了数据处理装置及方法。该数据处理装置包括调度器，被配置为将至少一个处理任务调度到第一处理单元和/或第二处理单元；第一处理单元被配置为使用在处理至少第一部分之前被配置的第一卷积参数处理至少一个处理任务的至少第一部分；第二处理单元被配置为使用第二卷积参数处理至少一个处理任务的至少第二部分，第二卷积参数是在处理至少第二部分过程中从存储单元读取的；以及存储单元被配置为存储与至少一个处理任务相关的数据。以此方式，第一处理单元所使用的第一卷积参数在处理任务之前被配置，从而在任务处理过程中，无需从存储单元再次读取或更新该第一卷积参数，能够减少数据的传输，进而能够减少功耗开销，提升处理能效。

    DETECTING VARYING CONDUCTANCE INDICATIVE OF SEQUENTIAL INTERACTIONS BETWEEN NUCLEOBASES
    2.
    发明申请
    DETECTING VARYING CONDUCTANCE INDICATIVE OF SEQUENTIAL INTERACTIONS BETWEEN NUCLEOBASES 审中-公开

    公开(公告)号：WO2023086416A1

    公开(公告)日：2023-05-19

    申请号：PCT/US2022/049451

    申请日：2022-11-09

    Applicant: ADAPTIVE BIOTECHNOLOGIES CORPORATION

    Inventor： BIELAS, Jason H. ,  ROBINS, Harlan S.

    IPC: C12Q1/6869 ,  G06F3/00 ,  G06N3/00 ,  G06N20/00

    Abstract: Provided are methods comprising causing relative movement of a first nucleic acid through an opening formed at least in part by an electrolyzed second nucleic acid. Such methods comprise, during the relative movement, detecting a varying conductance along the first nucleic acid, or a varying conductance between the first nucleic acid and an electrode proximate to the first nucleic acid, wherein the varying conductance is indicative of sequential interactions between nucleobases of the first nucleic acid and one or more nucleobases of the electrolyzed second nucleic acid. The varying conductance comprises conductance fingerprints for the different nucleobases in the first nucleic acid. In certain embodiments, the methods comprise determining the identity of one or more nucleotide, optionally determining a sequence, of the first nucleic acid based on the varying conductance. Computer-readable media and systems that find use, e.g., in practicing the methods of the present disclosure, are also provided.

    APPARATUS AND METHOD FOR REINFORCEMENT LEARNING BASED POST-TRAINING SPARSIFICATION
    3.
    发明申请
    APPARATUS AND METHOD FOR REINFORCEMENT LEARNING BASED POST-TRAINING SPARSIFICATION 审中-公开

    公开(公告)号：WO2023082278A1

    公开(公告)日：2023-05-19

    申请号：PCT/CN2021/130746

    申请日：2021-11-15

    Applicant: INTEL CORPORATION ,  QIAN, Xu ,  CREWS, Darren ,  LI, Yuanyuan

    Inventor： QIAN, Xu ,  CREWS, Darren ,  LI, Yuanyuan

    IPC: G06N3/00

    Abstract: Provided herein are apparatus and methods for reinforcement learning based post-training sparsification. An apparatus includes: a memory; and processor circuitry coupled with the memory, wherein the processor circuitry is to: obtain a first correction parameter indicating a mean shift of a set of weights after sparsification of a model with respect to that before the sparsification of the model; obtain a second correction parameter indicating a variance shift of the set of weights after the sparsification of the model with respect to that before the sparsification of the model; and correct the set of weights at least partially based on the first correction parameter and the second correction parameter, and wherein the memory is to store the corrected set of weights. Other embodiments may also be disclosed and claimed.

    METHOD AND SYSTEM FOR DETERMINING A TARGET RECIPE OF A COMPOUND
    5.
    发明申请
    METHOD AND SYSTEM FOR DETERMINING A TARGET RECIPE OF A COMPOUND 审中-公开

    公开(公告)号：WO2023072993A1

    公开(公告)日：2023-05-04

    申请号：PCT/EP2022/079888

    申请日：2022-10-26

    Applicant: COVESTRO DEUTSCHLAND AG

    Inventor： GAO, Han ,  LIU, Hao ,  GUO, Ruijing ,  ZHANG, Mengyang ,  THOMPSON-COLÓN, Jim A.

    IPC: G16C20/10 ,  G06N3/00 ,  G16C20/70

    Abstract: A method and system for determining a target recipe of a compound with desired attributes are provided in the invention, characterized in that the method comprises: a) performing simulation synthesis for each of a plurality of recipes, and calculating on the simulation synthesis one or more descriptors of each recipe, wherein the descriptors are used to characterize the simulated product of a corresponding recipe; b) performing synthesis for each of a plurality of recipes, and measuring one or more properties of each recipe, wherein the properties are used to describe the attributes of a corresponding recipe; c) training one or more machine learning models by using the values of the descriptors and the properties obtained by step a) and step b) as training samples, wherein the machine learning models correlates the descriptors of the recipes with the properties of the recipes; and d) generating a plurality of candidate recipes, performing simulation synthesis for each of the plurality of candidate recipes, and, using the trained machine learning model obtained by step c), to predict one or more properties of each candidate recipe, thus determining one or more target recipes from the plurality of candidate recipes.

    ENDOLUMINAL VALVE PLACEMENT PATIENT OUTCOME PREDICTION
    6.
    发明申请
    ENDOLUMINAL VALVE PLACEMENT PATIENT OUTCOME PREDICTION 审中-公开

    公开(公告)号：WO2023069978A1

    公开(公告)日：2023-04-27

    申请号：PCT/US2022/078343

    申请日：2022-10-19

    Applicant: GYRUS ACMI, INC. D/B/A OLYMPUS SURGICAL TECHNOLOGIES AMERICA

    Inventor： NICKESON, Matthew E. ,  LYON, Torsten M.

    IPC: G16H50/20 ,  G16H20/40 ,  G06N3/00

    Abstract: Various aspects of methods, systems, and use cases may be used to train a model to determine whether a patient is a candidate for receiving an endoluminal valve based on collateral ventilation data. A method may include receiving sensor data based on pressure or airflow at a target portion of a lung of a patient that is occluded from receiving air via a breathing airway of the lung. The method may include training a machine learning model, based at least in part on training data (e.g., based on the sensor data), to predict patient breathing outcomes via an indication of whether collateral ventilation is present in a particular patient target lung portion.

    一种提高配电网可靠性的储能容量优化配置方法
    7.
    发明申请
    一种提高配电网可靠性的储能容量优化配置方法 审中-公开

    公开(公告)号：WO2023060815A1

    公开(公告)日：2023-04-20

    申请号：PCT/CN2022/077253

    申请日：2022-02-22

    Applicant: 广西电网有限责任公司电力科学研究院

    Inventor： 周柯 ,  丘晓茵 ,  秦丽文 ,  莫枝阅 ,  李珊 ,  周杨珺

    IPC: G06Q10/04 ,  G06N3/00

    Abstract: 一种提高配电网可靠性的储能容量优化配置方法，包括以下步骤：(1)定义储能系统的"收益-投入比"：式（I）其中，Ctotal为储能系统的建设成本，f1为配置储能系统的经济性收益，f2为配置储能系统的可靠性收益；(2)选择储能系统的功率区间，根据储能系统的功率区间选择容量区间；(3)估计供电网络中配置不同容量的储能系统的"收益-投入比"；(4)根据当前容量下储能系统的"收益-投入比"，搜索储能系统最佳的配置容量，即储能系统最大的"收益-投入比"下的配置容量为储能系统最佳的配置容量。本发明能够智能高效地规划储能功率与容量的配置，实现储能配置的可靠性收益与经济性收益的综合最优，具有智能化程度高的优点。

    A SYSTEM AND METHOD FOR PREDICTING RISK FOR A FLIGHT OF AN UNMANNED AERIAL VEHICLE
    8.
    发明申请
    A SYSTEM AND METHOD FOR PREDICTING RISK FOR A FLIGHT OF AN UNMANNED AERIAL VEHICLE 审中-公开

    公开(公告)号：WO2023041973A1

    公开(公告)日：2023-03-23

    申请号：PCT/IB2021/059295

    申请日：2021-10-11

    Applicant: TROPOGO LIMITED

    Inventor： BANERJEE, Sayan ,  GHOSH, Shreya ,  PAL, Saptarshi ,  SEN, Sandipan

    IPC: G08G5/00 ,  G06Q40/08 ,  G06Q50/30 ,  G06N3/00

    Abstract: The present disclosure provides a system and method for predicting risk for a flight of an unmanned aerial vehicle (UAV). The system includes a user device (101) including a user interface (102), connected to a risk prediction system (105). The risk prediction system (105) including a computing module (106), an artificial intelligence module (120), a risk evaluation module (121), a prediction module (123), a dynamic pricing unit (125) and a user recommendation unit (127). The method includes providing (201) details of flying the unmanned aerial vehicle, by a user using the user interface, computing (202) parameters affecting flight of the unmanned aerial vehicle based on the details, by the computing module (106), determining risks based on the computed parameters, by the risk evaluation module (121) and predicting a total risk of the flight of the UAV based on the determined risks, by the prediction module (123).

Patent Agency Ranking