专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20220206999A1 OPTIMIZATION OF WORKFLOWS WITH DYNAMIC FILE CACHING 有权
公开(公告)号：US20220206999A1
公开(公告)日：2022-06-30
申请号：US17137187
申请日：2020-12-29
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Vasileios Vasileiadis , Christian Pinto , Michael Johnston , Ioannis Gkoufas , Srikumar Venugopal
IPC分类号： G06F16/182 , G06F9/48 , G06F16/901 , G06F16/17 , G06F16/14 , G06F9/50
摘要： A computer implemented method for optimizing performance of workflow includes associating each of a plurality of workflow nodes in a workflow with a data cache and managing the data cache on a local storage device on one of one or more compute nodes. A scheduler can request execution of the tasks of a given one of the plurality of workflow nodes on one of the one of more compute nodes that hosts the data cache associated with the given one of the plurality of workflow nodes. Each of the plurality of workflow nodes is permitted to access a distributed filesystem that is visible to each of the plurality of compute nodes. The data cache stores data produced by the tasks of the given one of the plurality of workflow nodes.

2. 发明申请

US20180276688A1 SYSTEM AND METHOD FOR A SCALABLE RECOMMENDER SYSTEM USING MASSIVELY PARALLEL PROCESSORS 审中-公开
公开(公告)号：US20180276688A1
公开(公告)日：2018-09-27
申请号：US15468308
申请日：2017-03-24
申请人： International Business Machines Corporation
发明人： Celestine Duenner , Thomas Parnell , Charalampos Pozidis , Vasileios Vasileiadis , Michail Vlachos
IPC分类号： G06Q30/02 , H04L29/08 , G06F13/16 , G06N3/04 , G06F9/30 , G06F9/52
CPC分类号： G06Q30/0201 , G06F9/30036 , G06F9/3009 , G06F9/528 , G06F13/1663 , G06N3/0472 , G06Q50/01 , H04L47/127 , H04L67/22
摘要： Methods and apparatus are provided to determine entities and attributes dependencies for creating recommendations of items or entities using a highly scalable architecture. For example, a user may be recommended an item if a probability model of the method determines that the user relates to the item although the user has no contact to the item before the method is performed. The methods and apparatus provide a data structure representing a matrix having rows representing entities and columns representing attributes of the entities. Each entity of the entities of the data structure may include a user and each attribute of the attributes of the data structure may include an item. A cell of the matrix may be formed by a component pair including an entity and an attribute. In this manner, the methods and apparatus provide an efficient way for processing the probability model.

3. 发明授权

US09524468B2 Method and system for identifying dependent components 有权
公开(公告)号：US09524468B2
公开(公告)日：2016-12-20
申请号：US14935476
申请日：2015-11-09
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Reinhard Wolfram Heckel , Vasileios Vasileiadis , Michail Vlachos
IPC分类号： G06N5/02 , G06N7/00
CPC分类号： G06N7/005 , G06N5/022 , G06N5/04
摘要： Embodiments include processing a data structure representing a dependency matrix having columns representing respective first components and rows representing respective second components. Aspects include assigning each cell of the matrix a value indicative of the level of dependency or indicative of an unknown dependency of a pair of first and second components forming the cell and assigning each component of the first and second components an affiliation vector indicative of the strength of affiliation of the component to N predefined initial clusters of cells of the matrix. Aspects also include determining a probability model using the affiliations vectors parameters and estimating the parameters of the probability model for a plurality of different numbers of clusters starting from the initial number N of clusters. Aspects further include computing a score for the parameters of the probability model estimated and selecting the parameters of the probability model with the highest computed score.

4. 发明申请

US20160063392A1 METHOD AND SYSTEM FOR IDENTIFYING DEPENDENT COMPONENTS 有权
标题翻译：识别相关组件的方法和系统
公开(公告)号：US20160063392A1
公开(公告)日：2016-03-03
申请号：US14935476
申请日：2015-11-09
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Reinhard Wolfram Heckel , Vasileios Vasileiadis , Michail Vlachos
IPC分类号： G06N7/00
CPC分类号： G06N7/005 , G06N5/022 , G06N5/04
摘要： Embodiments include processing a data structure representing a dependency matrix having columns representing respective first components and rows representing respective second components. Aspects include assigning each cell of the matrix a value indicative of the level of dependency or indicative of an unknown dependency of a pair of first and second components forming the cell and assigning each component of the first and second components an affiliation vector indicative of the strength of affiliation of the component to N predefined initial clusters of cells of the matrix. Aspects also include determining a probability model using the affiliations vectors parameters and estimating the parameters of the probability model for a plurality of different numbers of clusters starting from the initial number N of clusters. Aspects further include computing a score for the parameters of the probability model estimated and selecting the parameters of the probability model with the highest computed score.
摘要翻译：实施例包括处理表示依赖矩阵的数据结构，该依赖矩阵具有表示相应的第一分量的列和表示相应的第二分量的行。方面包括将矩阵的每个单元分配成指示依赖性水平的值或指示构成单元的一对第一和第二分量的未知依赖性，并且将第一和第二分量的每个分量分配给表示强度的附属矢量将组件与N个预定义的矩阵单元格的初始聚类相关联。方面还包括使用关联向量参数来确定概率模型，并从群集的初始数目N开始估计多个不同数量的群集的概率模型的参数。方面还包括计算估计的概率模型的参数的得分，并且选择具有最高计算得分的概率模型的参数。

5. 发明授权

US10147103B2 System and method for a scalable recommender system using massively parallel processors 有权
公开(公告)号：US10147103B2
公开(公告)日：2018-12-04
申请号：US15468308
申请日：2017-03-24
申请人： International Business Machines Corporation
发明人： Celestine Duenner , Thomas Parnell , Charalampos Pozidis , Vasileios Vasileiadis , Michail Vlachos
IPC分类号： G06F12/00 , G06Q30/02 , H04L29/08 , G06F13/16 , G06N3/04 , G06F9/30 , G06F9/52 , H04L12/801 , G06Q50/00
摘要： Methods and apparatus are provided to determine entities and attributes dependencies for creating recommendations of items or entities using a highly scalable architecture. For example, a user may be recommended an item if a probability model of the method determines that the user relates to the item although the user has no contact to the item before the method is performed. The methods and apparatus provide a data structure representing a matrix having rows representing entities and columns representing attributes of the entities. Each entity of the entities of the data structure may include a user and each attribute of the attributes of the data structure may include an item. A cell of the matrix may be formed by a component pair including an entity and an attribute. In this manner, the methods and apparatus provide an efficient way for processing the probability model.

6. 发明授权

US09519864B1 Method and system for identifying dependent components 有权
标题翻译：用于识别依赖组件的方法和系统
公开(公告)号：US09519864B1
公开(公告)日：2016-12-13
申请号：US14967678
申请日：2015-12-14
申请人： International Business Machines Corporation
发明人： Reinhard Wolfram Heckel , Vasileios Vasileiadis , Michail Vlachos
IPC分类号： G06F17/00 , G06N5/04
CPC分类号： G06N7/005 , G06N5/022 , G06N5/04
摘要： Embodiments include processing a data structure representing a dependency matrix having columns representing respective first components and rows representing respective second components. Aspects include assigning each cell of the matrix a value indicative of the level of dependency or indicative of an unknown dependency of a pair of first and second components forming the cell and assigning each component of the first and second components an affiliation vector indicative of the strength of affiliation of the component to N predefined initial clusters of cells of the matrix. Aspects also include determining a probability model using the affiliations vectors parameters and estimating the parameters of the probability model for a plurality of different numbers of clusters starting from the initial number N of clusters. Aspects further include computing a score for the parameters of the probability model estimated and selecting the parameters of the probability model with the highest computed score.
摘要翻译：实施例包括处理表示依赖矩阵的数据结构，该依赖矩阵具有表示相应的第一分量的列和表示相应的第二分量的行。方面包括将矩阵的每个单元分配成指示依赖性水平的值或指示构成单元的一对第一和第二分量的未知依赖性，并且将第一和第二分量的每个分量分配给表示强度的附属矢量将组件与N个预定义的矩阵单元格的初始聚类相关联。方面还包括使用关联向量参数来确定概率模型，并从群集的初始数目N开始估计多个不同数量的群集的概率模型的参数。方面还包括计算估计的概率模型的参数的得分，并且选择具有最高计算得分的概率模型的参数。

7. 发明申请

US20220291964A1 WORKFLOW MEMOIZATION 有权
公开(公告)号：US20220291964A1
公开(公告)日：2022-09-15
申请号：US17199608
申请日：2021-03-12
申请人： International Business Machines Corporation
发明人： Vasileios Vasileiadis , Michael Johnston
IPC分类号： G06F9/50 , G06N5/04
摘要： Workflow memoization can include generating an embedding associated with a node in a workflow. The embedding can be generated by encoding at least the node's executable and input data to the node. A matching embedding can be retrieved from a database of embeddings, which matches the generated embedding according to a match criterion. The database of embeddings can store embeddings associated with previously run nodes. Output data associated with the matching embedding can be retrieved. The output data can be used as the node's output without having to run the node in the workflow.

8. 发明申请

US20220207438A1 AUTOMATIC CREATION AND EXECUTION OF A TEST HARNESS FOR WORKFLOWS 有权
公开(公告)号：US20220207438A1
公开(公告)日：2022-06-30
申请号：US17138843
申请日：2020-12-30
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Michael Johnston , Vasileios Vasileiadis
IPC分类号： G06Q10/06 , G06Q10/10 , G06F8/65 , G06F11/36
摘要： A computer implemented method for automatically creating and executing a test harness for a workflow includes creating a workflow package including a version identification and a workflow graph definition and creating a workflow instance as a copy of the workflow package. The workflow instance is executed to generate output data and the output data is saved into the workflow instance. The workflow instance is saved, with the output data, as a test archive. One or more components of an updated workflow package are tested with the test archive; and an indication of pass or fail of the testing of the updated workflow package is outputted.

9. 发明授权

US11222054B2 Low-complexity methods for assessing distances between pairs of documents 有权
公开(公告)号：US11222054B2
公开(公告)日：2022-01-11
申请号：US15918963
申请日：2018-03-12
申请人： International Business Machines Corporation
发明人： Kubilay Atasu , Cesar Berrospi Ramis , Nikolas Ioannou , Thomas Patrick Parnell , Charalampos Pozidis , Vasileios Vasileiadis
IPC分类号： G06F16/33 , G06F17/16 , G06K9/00 , G06K9/62 , G06F16/31
摘要： Two sets X2 and X1 of histograms of words, and a vocabulary V are accessed. Each of the two sets is representable as a sparse matrix, each row of which corresponds to a histogram. Each histogram is representable as a sparse vector, whose dimension is determined by a dimension of the vocabulary. Two phases compute distances between pairs of histograms. The first phase includes computations performed for each histogram and for each word in the vocabulary to obtain a dense, floating-point vector y. The second phase includes computing, for each histogram, a sparse-matrix, dense-vector multiplication between a matrix-representation of the set X1 of histograms and the vector y. The multiplication is performed to obtain distances between all histograms of the set X1 and each histogram X2[j]. Distances between all pairs of histograms are obtained, based on which distances between documents can subsequently be assessed.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式