中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

18 records (took 0.025 seconds)

    Predicting wildfires on the basis of biophysical indicators and spatiotemporal properties using a long short term memory network
    2.
    发明授权
    Predicting wildfires on the basis of biophysical indicators and spatiotemporal properties using a long short term memory network 有权

    公开(公告)号：US11275989B2

    公开(公告)日：2022-03-15

    申请号：US15601739

    申请日：2017-05-22

    Applicant: SAP SE

    Inventor： Vadim Tschernezki ,  Oliver Blum ,  Hinnerk Gildhoff ,  Michèle Wyss ,  Bjoern Deiseroth ,  Wenzel Svojanovsky

    IPC: G06N3/04 ,  G06N3/08

    Abstract: The present disclosure involves systems, software, and computer implemented methods for predicting wildfires on the basis of biophysical indicators and spatiotemporal properties. A method includes receiving a request for a wildfire prediction for at least one geographical area. At least one biophysical indicator is identified. Each biophysical indicator provides biophysical data for the at least one geographical area. The at least one biophysical indicator is provided to a long short term memory (LSTM) network. The LSTM network includes a convolutional neural network (CNN) for each of multiple LSTM units. Each LSTM unit and each CNN are associated with a historical time period in a time series. The LSTM is used to generate at least one prediction for wildfire risk for the at least one geographical area for an upcoming time period. The at least one prediction is provided responsive to the request.

    Adjacency structures for executing graph algorithms in a relational database
    3.
    发明授权
    Adjacency structures for executing graph algorithms in a relational database 有权

    公开(公告)号：US10546021B2

    公开(公告)日：2020-01-28

    申请号：US15419866

    申请日：2017-01-30

    Applicant: SAP SE

    Inventor： Thomas Fischer ,  Hinnerk Gildhoff ,  Romans Kasperovics ,  Cornelia Kinder ,  Marcus Paradies

    IPC: G06F16/901

    Abstract: A system for processing graph-modeled data in a relational database is provided. The system can include at least one data processor and at least one memory storing instructions that are executed by the at least one data processor. Executing the instructions can result in operations comprising: receiving a request to execute a graph algorithm operating on graph-modeled data stored at a relational database; and executing the graph algorithm within the relational database, the executing comprising use of an adjacency structure within the relational database. Related methods and articles of manufacture, including computer program products, are also provided.

    Graph-modeled data processing in a relational database
    4.
    发明授权
    Graph-modeled data processing in a relational database 有权

    公开(公告)号：US10394855B2

    公开(公告)日：2019-08-27

    申请号：US15419875

    申请日：2017-01-30

    Applicant: SAP SE

    Inventor： Thomas Fischer ,  Hinnerk Gildhoff ,  Romans Kasperovics ,  Cornelia Kinder ,  Marcus Paradies

    IPC: H04L29/06 ,  G06F16/28 ,  G06F16/901 ,  G06F21/62

    Abstract: A system for processing graph-modeled data in a relational database is provided. In some implementations, the system performs operations comprising: receiving, from a first user, a request to define a graph algorithm operating on a graph workspace, the graph workspace comprising at least a portion of graph-modeled data stored at a relational database; applying a first security rule associated with the relational database, the applying comprising determining whether the first user has a privilege to define the graph algorithm operating on the graph workspace; and storing the graph algorithm at the relational database, when the first user is determined to have the privilege to define the graph algorithm operating on the graph workspace. Related methods and articles of manufacture, including computer program products, are also provided.

    PREDICTING WILDFIRES ON THE BASIS OF BIOPHYSICAL INDICATORS AND SPATIOTEMPORAL PROPERTIES USING A CONVOLUTIONAL NEURAL NETWORK
    5.
    发明申请
    PREDICTING WILDFIRES ON THE BASIS OF BIOPHYSICAL INDICATORS AND SPATIOTEMPORAL PROPERTIES USING A CONVOLUTIONAL NEURAL NETWORK 审中-公开

    公开(公告)号：US20180336460A1

    公开(公告)日：2018-11-22

    申请号：US15601704

    申请日：2017-05-22

    Applicant: SAP SE

    Inventor： Vadim Tschemezki ,  Oliver Blum ,  Hinnerk Gildhoff ,  Michèle Wyss ,  Bjoern Deiseroth ,  Wenzel Svojanovsky

    IPC: G06N3/08 ,  G06N3/04

    Abstract: The present disclosure involves systems, software, and computer implemented methods for predicting wildfires on the basis of biophysical indicators and spatiotemporal properties. A method includes receiving a request for a wildfire prediction for at least one geographical area. At least one biophysical indicator is identified. Each biophysical indicator provides biophysical data for the at least one geographical area. The at least one biophysical indicator is provided to a convolutional neural network (CNN). The CNN is trained using ground truth data that includes historical information about wildfires for at least one ground truth geographical area. The CNN is used to generate at least one prediction for wildfire risk for the at least one geographical area. The at least one prediction is provided responsive to the request.

    SYSTEM AND METHOD FOR DETERMINING ALPHA VALUES FOR ALPHA SHAPES
    7.
    发明申请
    SYSTEM AND METHOD FOR DETERMINING ALPHA VALUES FOR ALPHA SHAPES 审中-公开

    公开(公告)号：US20190304176A1

    公开(公告)日：2019-10-03

    申请号：US15944520

    申请日：2018-04-03

    Applicant: SAP SE

    Inventor： Kai-Niklas Bastian ,  Hinnerk Gildhoff ,  Tim Grouisborn ,  Michael Jung

    IPC: G06T17/10 ,  G06F7/08

    Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program receives, from a client device, a percentage value for a set of points. The program further determines a triangulation based on the set of points. The program also determines an alpha value based on the triangulation and the percentage value. The program further determines an alpha shape based on the alpha value. The program also provides the client device the alpha shape.

    PREDICTING WILDFIRES ON THE BASIS OF BIOPHYSICAL INDICATORS AND SPATIOTEMPORAL PROPERTIES USING A LONG SHORT TERM MEMORY NETWORK
    10.
    发明申请
    PREDICTING WILDFIRES ON THE BASIS OF BIOPHYSICAL INDICATORS AND SPATIOTEMPORAL PROPERTIES USING A LONG SHORT TERM MEMORY NETWORK 审中-公开

    公开(公告)号：US20180336452A1

    公开(公告)日：2018-11-22

    申请号：US15601739

    申请日：2017-05-22

    Applicant: SAP SE

    Inventor： Vadim Tschernezki ,  Oliver Blum ,  Hinnerk Gildhoff ,  Michèle Wyss ,  Bjoern Deiseroth ,  Wenzel Svojanovsky

    IPC: G06N3/04 ,  G06N3/08

    Abstract: The present disclosure involves systems, software, and computer implemented methods for predicting wildfires on the basis of biophysical indicators and spatiotemporal properties. A method includes receiving a request for a wildfire prediction for at least one geographical area. At least one biophysical indicator is identified. Each biophysical indicator provides biophysical data for the at least one geographical area. The at least one biophysical indicator is provided to a long short term memory (LSTM) network. The LSTM network includes a convolutional neural network (CNN) for each of multiple LSTM units. Each LSTM unit and each CNN are associated with a historical time period in a time series. The LSTM is used to generate at least one prediction for wildfire risk for the at least one geographical area for an upcoming time period. The at least one prediction is provided responsive to the request.

Patent Agency Ranking