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

WO2019126721A1 SYSTEMS AND METHODS FOR PREDICTING PATIENT HEALTH STATUS 审中-公开
公开(公告)号：WO2019126721A1
公开(公告)日：2019-06-27
申请号：PCT/US2018/067240
申请日：2018-12-21
申请人： ABIOMED, INC.
发明人： LIU, Chen , KATERJI, Admad El , CORBETT, Scott
IPC分类号： G16H20/40 , A61M5/14 , G16H20/17 , G16H50/00 , A61M1/10
CPC分类号： A61M1/1086 , A61B5/00 , A61M1/101 , A61M1/1031 , A61M1/122 , A61M1/125 , A61M2205/04 , A61M2205/18 , A61M2205/3303 , A61M2205/3365 , A61M2205/50 , A61M2205/502 , A61M2205/52 , A61M2205/584 , A61M2230/06 , A61M2230/20 , A61M2230/208 , A61M2230/30 , A61M2230/43 , G06N5/045 , G06N20/00 , G16H20/17 , G16H20/40 , G16H50/00 , G16H50/20
摘要： Systems and methods are provided herein for treating a patient in cardiogenic shock. An intravascular heart pump system is inserted into vasculature of the patient. The heart pump system has a cannula, pump outlet, pump inlet, and rotor. The heart pump system is positioned within the patient such that the cannula extends across the patient's aortic valve, the pump inlet is located within the patient's left ventricle, and the pump outlet is located within the patient's aorta. Data related to time-varying parameters of the heart pump system is acquired from the heart pump system. A plurality of features are extracted from the data. A probability of survival of the patient is determined based on the plurality of features and using a prediction model. The heart pump system is operated to treat the patient.

2. 发明申请

WO2018061249A1 マーケティング支援システム审中-公开
标题翻译：营销支持系统
公开(公告)号：WO2018061249A1
公开(公告)日：2018-04-05
申请号：PCT/JP2017/010294
申请日：2017-03-15
申请人：株式会社日立製作所
发明人：相薗　敏子 , 魏　文鵬 , 茂川　拓矢 , 徳永　和朗 , 難波　康晴
IPC分类号： G06Q30/02
CPC分类号： G06Q30/0202 , G06N5/00 , G06N5/045 , G06Q30/02 , G06Q30/0201
摘要：多数の説明変数を自動で生成した際に、出力される示唆の量が膨大であるため、示唆の選別の負担が大きい。　マーケティング支援システムを、購買データを受け付け、前記購買データ間の相関を分析することで、複合変数を出力する示唆抽出部と、前記複合変数および制限テーブルを受け付け、前記制限テーブルで定義される制限条件に基づいて、前記複合変数を排除する制限フィルタリング部と、過去に定義した施策の実績を用いて、前記複合変数に基づいた施策を行った場合の予想効果を推定し、前記複数の説明変数を選別する実績フィルタリング部と、を有する構成とする。
摘要翻译：
当自动生成很多解释变量时，要输出的建议量很大，因此选择建议的负担很重。营销支持系统接收购买数据，通过分析购买数据之间的相关性，用于输出复合变量，限制条件所建议的提取单元，其中，接收的复合变量和限制表被限制表中定义，通过使用过去定义的度量的过去记录来估计当执行基于复变量的度量时的预测效果，并且估计多个解释变量并有一个实际结果过滤单元用于对结果进行排序。

3. 发明申请

WO2017165019A1 INVARIANT MODELING AND DETECTION FOR HETEROGENEOUS LOGS 审中-公开
标题翻译：非均匀原木的不变模型与检测
公开(公告)号：WO2017165019A1
公开(公告)日：2017-09-28
申请号：PCT/US2017/017874
申请日：2017-02-15
申请人： NEC LABORATORIES AMERICA, INC.
发明人： ZONG, Bo , XU, Jianwu , JIANG, Guofei
IPC分类号： G06F11/34 , G06F17/30
CPC分类号： G06F16/2477 , G06F11/3072 , G06F16/35 , G06N5/045
摘要： A method is provided that is performed in a network having nodes that generate heterogeneous logs including performance logs and text logs. The method includes performing, during a heterogeneous log training stage, (i) a log-to-time sequence conversion process for transforming clustered ones of training logs, from among the heterogeneous logs, into a set of time sequences that are each formed as a plurality of data pairs of a first configuration and a second configuration based on cluster type, (ii) a time series generation process for synchronizing particular ones of the time sequences in the set based on a set of criteria to output a set of fused time series, and (iii) an invariant model generation process for building invariant models for each time series data pair in the set of fused time series. The method includes controlling an anomaly-initiating one of the plurality of nodes based on the invariant models.
摘要翻译：提供一种在具有生成包括性能日志和文本日志的异构日志的节点的网络中执行的方法。该方法包括在异构日志训练阶段期间执行（i）日志到时间序列转换过程，用于将群集中的多个训练日志从异构日志中转换成一组时间序列，每个时间序列形成为（ii）时间序列生成过程，用于基于一组准则同步该组中的特定时间序列，以输出一组融合时间序列（iii）不变模型生成过程，用于为该组融合时间序列中的每个时间序列数据对构建不变模型。该方法包括基于不变模型控制多个节点中异常发起的一个节点。

4. 发明申请

WO2017150230A1 DIAGNOSIS SUPPORT APPARATUS, CONTROL METHOD FOR DIAGNOSIS SUPPORT APPARATUS, AND COMPUTER-READABLE STORAGE MEDIUM 审中-公开
标题翻译：诊断支持装置，用于诊断支持装置的控制方法以及计算机可读存储介质
公开(公告)号：WO2017150230A1
公开(公告)日：2017-09-08
申请号：PCT/JP2017/006032
申请日：2017-02-20
申请人： CANON KABUSHIKI KAISHA
发明人： KAWAGISHI, Masami
IPC分类号： G06F19/00 , G06N5/04
CPC分类号： G06N5/046 , G06N5/045 , G06N7/005 , G06N20/00 , G06N20/10 , G16H50/20
摘要： A diagnosis support apparatus comprising: first inference means for performing inference concerning diagnosis using data collected under a first condition; second inference means for performing inference concerning the diagnosis using the data collected under the first condition and data collected under a second condition different from the first condition; third inference means for performing inference concerning the diagnosis using the data collected under the second condition; and integration means for integrating inference results of the first inference means, the second inference means, and the third inference means using a first weight, a second weight, and a third weight respectively corresponding to the first inference means, the second inference means, and the third inference means.
摘要翻译：一种诊断支持设备，包括：第一推断装置，用于使用在第一条件下收集的数据执行关于诊断的推理; 第二推理装置，用于使用在第一条件下采集的数据和在不同于第一条件的第二条件下采集的数据进行关于诊断的推理; 第三推理装置，用于使用在第二条件下收集的数据执行关于诊断的推理; 以及整合装置，用于使用分别对应于第一推断装置，第二推断装置和第二推理装置的第一权重，第二权重和第三权重来整合第一推理装置，第二推理装置和第三推理装置的推理结果，第三个推断的意思是。

5. 发明申请

WO2016076878A1 SATISFACTION METRIC FOR CUSTOMER TICKETS 审中-公开
标题翻译：满意客户门票价格
公开(公告)号：WO2016076878A1
公开(公告)日：2016-05-19
申请号：PCT/US2014/065586
申请日：2014-11-14
申请人： HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
发明人： AGRANONIK, Arie , COHEN, Ira
IPC分类号： G06Q10/04 , G06Q10/02
CPC分类号： G06Q30/016 , G06N5/045 , G06Q10/04 , G06Q10/06393
摘要： A computing device includes at least one processor and a satisfaction prediction module. The satisfaction prediction module is to generate a pruned decision tree using historical ticket data for a plurality of customer tickets, where the historical ticket data for each customer ticket includes a satisfaction metric and attribute values of the customer ticket. The satisfaction prediction module is also to generate a plurality of business rules based on the pruned decision tree, obtain at least one attribute value of an active customer ticket, and determine, based on the plurality of business rules and the at least one attribute value, a projected satisfaction metric for the active customer ticket.
摘要翻译：计算设备包括至少一个处理器和满意度预测模块。所述满意度预测模块是使用历史票据数据生成多个客户票据的修剪决策树，其中每个客户票据的历史票据数据包括客户票证的满意度度量和属性值。所述满意度预测模块还基于所述修剪决策树生成多个业务规则，获取活动客户票证的至少一个属性值，并且基于所述多个业务规则和所述至少一个属性值，活动客户票据的预期满意度指标。

6. 发明申请

WO2016067070A1 SYSTEM AND METHOD FOR SOLVING SPATIOTEMPORAL-BASED PROBLEMS 审中-公开
标题翻译：用于解决基于空间问题的系统和方法
公开(公告)号：WO2016067070A1
公开(公告)日：2016-05-06
申请号：PCT/IB2014/002302
申请日：2014-10-30
申请人： UMM AL-QURA UNIVERSITY
发明人： ALMARAASHI, Majid, Saeed , KHORMI, Hassan, M. , IBRAHIM, Mohammad, Kasim
IPC分类号： G06N5/04 , G06N99/00 , G06N7/02
CPC分类号： G06N5/045 , G06N5/04 , G06N7/005 , G06N99/005
摘要： A system for adaptive intelligent decision making includes circuitry that receives a spatiotemporal problem that includes at least one of a spatial dimension and a temporal dimension. Problem data is assigned to a relative problem space that affects decisions to the spatiotemporal problem. Weighting factors are assigned to the problem data that indicate an effect of the problem data on the decisions to the spatiotemporal problem in order to control relationships between the problem data in the relative problem space. Decisions are determined to the spatiotemporal problem based on decisions between the problem data. Feedback is provided that is related to the decisions and an associated decision confidence factor.
摘要翻译：用于自适应智能决策的系统包括接收包括空间维度和时间维度中的至少一个的时空问题的电路。问题数据被分配给影响对时空问题的决定的相对问题空间。加权因子被分配给问题数据，其指示问题数据对于时空问题的决定的影响，以便控制相对问题空间中的问题数据之间的关系。根据问题数据之间的决策，决定时空问题。提供与决策有关的反馈和相关的决策置信因子。

7. 发明申请

WO2014127433A1 A CONTROL SYSTEM 审中-公开
标题翻译：控制系统
公开(公告)号：WO2014127433A1
公开(公告)日：2014-08-28
申请号：PCT/AU2014000177
申请日：2014-02-25
申请人： STUBBS MARGOT
发明人： STUBBS MARGOT
IPC分类号： G06Q50/18
CPC分类号： G05B15/02 , G06N5/045 , G06Q10/10 , G06Q50/18
摘要： This invention concerns a control system that makes use of a computer user interface to control a process having a plurality of different stages of operation, in particular a multi-stage legal process. The system comprises a computer memory that stores a decision tree having a network of interconnected nodes, each of which represents a stage of the multi-stage process. The system further includes historical patterns of entries made by users and a plurality of different types of resource information for each stage of the multi-stage process. In use, each node requires an input to satisfy specified criterion, in response to which, one of the downstream nodes is automatically selected and the computer screen is updated. Input is made by a user either directly or automatically as determined by a selected historical pattern of entries.
摘要翻译：本发明涉及一种利用计算机用户界面来控制具有多个不同操作阶段，特别是多阶段合法过程的过程的控制系统。该系统包括存储具有互连节点网络的决策树的计算机存储器，每个节点代表多级过程的一个阶段。该系统还包括用户进行的条目的历史模式以及多级处理的每个阶段的多种不同类型的资源信息。在使用中，每个节点需要输入以满足指定的准则，响应于此，自动选择一个下游节点并更新计算机屏幕。输入由用户直接或自动进行，由选定的条目历史模式决定。

8. 发明申请

WO2014007943A2 METHOD AND APPARATUS FOR OBFUSCATING USER DEMOGRAPHICS 审中-公开
标题翻译：用于混淆用户人口统计的方法和设备
公开(公告)号：WO2014007943A2
公开(公告)日：2014-01-09
申请号：PCT/US2013/044890
申请日：2013-06-10
申请人： THOMSON LICENSING , BHAGAT, Smriti , WEINSBERG, Udi , IOANNIDIS, Stratis , TAFT, Nina
发明人： BHAGAT, Smriti , WEINSBERG, Udi , IOANNIDIS, Stratis , TAFT, Nina
IPC分类号： G06F21/50
CPC分类号： G06N5/022 , G06F21/6254 , G06N5/045 , G06N7/005
摘要： A method to obfuscate the accurate detection of demographic information of a new user who provides ratings to a digital content service having a recommender system includes training an inference engine to detect the 5 demographic information. The training set includes movie ratings and demographic information from a plurality of other users. The new user inputs ratings, such as movie ratings, and the inference engine determines the demographic information of the new user. An obfuscation engine then adds movie ratings to the recommender system which cause an inference engine in the recommender system to fail to accurately detect the demographic information of the new user.
摘要翻译：混淆精确检测向具有推荐系统的数字内容服务提供评级的新用户的人口统计信息的方法包括训练推理引擎以检测人口统计信息。训练集包括来自多个其他用户的电影评级和人口统计信息。新用户输入评级，如电影评级，推理引擎确定新用户的人口统计信息。迷惑引擎然后将电影评级添加到推荐者系统，这导致推荐者系统中的推理引擎不能准确地检测到新用户的人口统计信息。

9. 发明申请

WO2011106308A2 CONFIGURABLE CIRCUITRY FOR SOLVING STOCHASTIC PROBLEMS 审中-公开
标题翻译：用于解决故障问题的可配置电路
公开(公告)号：WO2011106308A2
公开(公告)日：2011-09-01
申请号：PCT/US2011/025678
申请日：2011-02-22
申请人： NAVIA SYSTEMS, INC. , JONAS, Eric, M. , MANSINGHKA, Vikash, K.
发明人： JONAS, Eric, M. , MANSINGHKA, Vikash, K.
CPC分类号： G06N7/005 , G06N5/04 , G06N5/043 , G06N5/045 , G06N5/048 , G06N99/005
摘要： Techniques described herein may be used to solve a stochastic problem by dividing the stochastic problem into multiple fragments. In some cases, each fragment may be related to a random variable that forms a part of the problem, such that each fragment may produce samples from a probability distribution for that variable. Each fragment of the stochastic problem may then be assigned to a configurable circuit to solve the stochastic fragment. Configurable circuits may be implemented using any suitable combination of hardware and/or software, including using stochastic circuitry. In some embodiments, stochastic circuitry may include a stochastic tile and/or a stochastic memory.
摘要翻译：本文描述的技术可以用于通过将随机问题划分成多个片段来解决随机问题。在某些情况下，每个片段可能与形成问题的一部分的随机变量相关，使得每个片段可以从该变量的概率分布产生样本。然后将随机问题的每个片段分配给可配置电路以解决随机片段。可以使用硬件和/或软件的任何合适的组合来实现可配置电路，包括使用随机电路。在一些实施例中，随机电路可以包括随机瓦片和/或随机存储器。

10. 发明申请

WO2009111252A2 SYSTEM AND METHOD FOR EXPLAINING A RECOMMENDATION PRODUCED BY A DECISION SUPPORT TOOL 审中-公开
标题翻译：用于解释由决策支持工具生成的建议的系统和方法
公开(公告)号：WO2009111252A2
公开(公告)日：2009-09-11
申请号：PCT/US2009/035211
申请日：2009-02-26
申请人： RAYTHEON COMPANY , ALLEN, David, L. , SEIDA, Steven, B. , PRZYTULA, Krzysztof, W.
发明人： ALLEN, David, L. , SEIDA, Steven, B. , PRZYTULA, Krzysztof, W.
IPC分类号： G06N5/00
CPC分类号： G06N5/045
摘要： In accordance with a particular embodiment of the invention, a method for explaining a recommendation produced by a decision support tool is disclosed. The method comprises submitting a list of observation inputs to the decision support tool and producing a recommendation. The list of inputs is then reordered according to an observation metric. The method further comprises quantifying how each input impacts the probability of the recommendation produced. The inputs may then be ranked by comparing the associated changes in probability of the recommendation produced.
摘要翻译：根据本发明的具体实施例，公开了一种用于解释由决策支持工具产生的推荐的方法。该方法包括向决策支持工具提交观察投入清单并提出建议。然后根据观测指标重新排列输入列表。该方法还包括量化每个输入如何影响产生的推荐概率。然后可以通过比较所产生的推荐概率的相关变化来对输入进行排名。

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