公开(公告)号：US11163850B2

公开(公告)日：2021-11-02

申请号：US16841088

申请日：2020-04-06

Applicant: International Business Machines Corporation

Inventor： Robert H. Bell, Jr. ,  Louis B. Capps, Jr. ,  Daniel M. Dreps ,  Luis A. Lastras-Montano ,  Michael J. Shapiro

IPC: G06F12/00 ,  G06F16/957 ,  G06F3/06 ,  G06K9/62 ,  G06F16/583

Abstract: According to one aspect of the present disclosure a method and technique for managing data transfer includes receiving and storing a plurality of different data patterns anticipated to be encountered by a processor unit of a data processing system corresponding to a particular application being processed. Responsive to receiving a read request for data, the requested data is read from a memory subsystem, and the read data is compared by the memory subsystem to the stored data patterns. Responsive to determining that the read data matches at least one of the stored data patterns, the memory subsystem replaces the matching read data with a pattern tag corresponding to the matching data pattern. The pattern tag is transmitted over a communication link in response to the request.

公开(公告)号：US09336497B2

公开(公告)日：2016-05-10

申请号：US14148261

申请日：2014-01-06

Applicant: International Business Machines Corporation

Inventor： Aaron K. Baughman ,  Louis B. Capps, Jr. ,  Barry M. Graham ,  Jennifer R. Mahle

IPC: G06N5/04 ,  G06N99/00

CPC classification number: G06N99/005 ,  G06F17/30371 ,  G06F17/30401 ,  G06F17/30528 ,  G06F17/3053 ,  G06N5/04

Abstract: Various embodiments provide systems, computer program products and computer implemented methods. Some embodiments include a method of updating an expert corpus set, including obtaining a query from a user, obtaining a raw data source, determining a relevance score for the raw data source with respect to the query, by performing actions including creating a first vector of statistical variables for the query using at least one natural language processing (NLP) socket, the statistical variables having category types, creating a second vector for the first raw data source, having category types that are the same as those for the query and generating a hypothesis regarding the relevance of the raw data source, testing the hypothesis by comparing relative statistical variables, calculating a gradient between the vectors to determine the relevance score and updating the expert corpus set with the raw data in response to the relevance score exceeds a threshold.

Abstract translation: 各种实施例提供系统，计算机程序产品和计算机实现的方法。 一些实施例包括更新专家语料库集合的方法，包括从用户获得查询，获得原始数据源，通过执行动作来确定原始数据源相对于查询的相关性得分，包括创建第一向量 使用至少一个自然语言处理（NLP）套接字的所述查询的统计变量，所述统计变量具有类别类型，为所述第一原始数据源创建第二向量，具有与所述查询的类别类型相同的类别类型 关于原始数据源的相关性的假设，通过比较相对统计变量来测试假设，计算向量之间的梯度以确定相关性得分并且响应于相关性得分用原始数据更新专家语料库超过阈值。

公开(公告)号：US10025590B2

公开(公告)日：2018-07-17

申请号：US15359764

申请日：2016-11-23

Applicant: International Business Machines Corporation

Inventor： Louis B. Capps, Jr. ,  Ronald E. Newhart ,  Thomas E. Cook ,  Robert H. Bell, Jr. ,  Michael J. Shapiro

IPC: G06F9/46 ,  G06F9/30 ,  G06F11/34 ,  G06F9/50 ,  G06F9/38 ,  G06F11/30 ,  G06F15/80

Abstract: A multiprocessor system having plural heterogeneous processing units schedules instruction sets for execution on a selected of the processing units by matching workload processing characteristics of processing units and the instruction sets. To establish an instruction set's processing characteristics, the homogeneous instruction set is executed on each of the plural processing units with one or more performance metrics tracked at each of the processing units to determine which processing unit most efficiently executes the instruction set. Instruction set workload processing characteristics are stored for reference in scheduling subsequent execution of the instruction set.

公开(公告)号：US09830557B2

公开(公告)日：2017-11-28

申请号：US14946336

申请日：2015-11-19

Applicant: International Business Machines Corporation

Inventor： Aaron K. Baughman ,  Louis B. Capps, Jr. ,  Barry M. Graham ,  Jennifer R. Mahle

IPC: G06N5/04 ,  G06N99/00 ,  G06F17/30

CPC classification number: G06N99/005 ,  G06F17/30371 ,  G06F17/30401 ,  G06F17/30528 ,  G06F17/3053 ,  G06N5/04

Abstract: Various embodiments provide systems, computer program products and computer implemented methods. Some embodiments include a method of updating an expert corpus set, including obtaining a query from a user, obtaining a raw data source, determining a relevance score for the raw data source with respect to the query, by performing actions including creating a first vector of statistical variables for the query using at least one natural language processing (NLP) socket, the statistical variables having category types, creating a second vector for the first raw data source, having category types that are the same as those for the query and generating a hypothesis regarding the relevance of the raw data source, testing the hypothesis by comparing relative statistical variables, calculating a gradient between the vectors to determine the relevance score and updating the expert corpus set with the raw data in response to the relevance score exceeds a threshold.