-
公开(公告)号：US20190129819A1
公开(公告)日：2019-05-02
申请号：US15794988
申请日：2017-10-26
Applicant: International Business Machines Corporation
Inventor： Shi Jing Guo , Xiang Li , Hai Feng Liu , Jing Mei , Zhi Qiao , Guo Tong Xie , Shi Wan Zhao
IPC: G06F11/22 , G06F11/263 , G06N3/04 , G06N3/08
CPC classification number: G06F11/2263 , G06F11/263 , G06N3/0445 , G06N3/0454 , G06N3/08
Abstract: A method and system of imputing corrupted sequential data is provided. A plurality of input data vectors of a sequential data is received. For each input data vector of the sequential data, the input data vector is corrupted. The corrupted input data vector is mapped to a staging hidden layer to create a staging vector. The input data vector is reconstructed based on the staging vector, to provide an output data vector. adjusted parameter of the staging hidden layer is iteratively trained until it is within a predetermined tolerance of a loss function. A next input data vector of the sequential data is predicted based on the staging vector. The predicted next input data vector is stored.
-
12.发明申请公开(公告)号：US20190042691A1
公开(公告)日：2019-02-07
申请号：US15667237
申请日：2017-08-02
Applicant: International Business Machines Corporation
Inventor： Gang Hu , Xiang Li , Haifeng Liu , Guo Tong Xie , Ping Zhang
CPC classification number: G16B20/00 , G06F19/3456 , G16B25/00 , G16B40/00 , G16H20/10 , G16H50/30 , G16H50/50 , G16H50/70
Abstract: Combination therapies are automatically discovered that provide statistically significantly greater protection against a specific outcome, compared to therapies with fewer treatments. A dataset is received that associates each of a plurality of respective individual treatments with a corresponding outcome and a corresponding set of confounding factors. A plurality of new potential combination therapies are combined iteratively. The received dataset is used to automatically identify at least one candidate combination therapy of the new potential combination therapies that provides a statistically significantly greater protection against an outcome with reference to each of the plurality of respective individual treatments.
-
公开(公告)号：US10068668B2
公开(公告)日：2018-09-04
申请号：US14186079
申请日：2014-02-21
Applicant: International Business Machines Corporation
Abstract: Method and apparatus for processing medical data. The method for processing indication conditions includes obtaining a plurality of predetermined indication conditions which relate to a plurality of parameters and forming a plurality of conditional segments based on respective values of the plurality of parameters, which respectively correspond to a plurality of combinations of value ranges of the plurality of parameters. The method for processing patient data includes obtaining distribution information of the patient data in the plurality of conditional segments formed above and determining a matching relationship of patient data with at least one indication condition. The apparatuses correspond to the methods. Based on this, a matching relation of patient data with the plurality of indication conditions is determined directly based on distribution of patient data in respective conditional segments, which reduces/avoids chances of inefficiency caused by multiple data acquisitions, conversions, and analysis and improves processing efficiency of patient data.
-
公开(公告)号：US11189380B2
公开(公告)日：2021-11-30
申请号：US15825156
申请日：2017-11-29
Applicant: International Business Machines Corporation
Inventor： Shi Jing Guo , Xiang Li , Hai Feng Liu , Shi Wan Zhao , Zhi Qiao , Guo Tong Xie
Abstract: A dataset regarding a plurality of applications is obtained. A set of parameters is determined from the dataset, comprising at least a sample performance trajectory, a risk factor, and a performance outcome. A maximum likelihood of each performance outcome is determined using a likelihood function, the likelihood function being a mixture model of a trajectory model and an outcome model. The set of parameters is updated according to the maximum likelihood of each performance outcome. A performance trajectory model is built according to the updated set of parameters. The plurality of applications is then grouped into subgroups according to the performance trajectory model, each subgroup containing one or more applications, and each of the one or more applications in a given subgroup having a same or similar trajectory to each other. An alert associated with the applications in at least one of subgroups may be generated.
-
公开(公告)号：US11004564B2
公开(公告)日：2021-05-11
申请号：US16053086
申请日：2018-08-02
Applicant: International Business Machines Corporation
Abstract: A computer implemented method for processing a plurality of medical indication conditions on a computer that includes a processor communicatively coupled to a memory includes obtaining a plurality of predetermined indication conditions which relate to a plurality of parameters, and forming a plurality of conditional segments based on respective values of the plurality of parameters defined in the plurality of predetermined indication conditions. Each conditional segment of the plurality of conditional segments corresponds to a combination of different value ranges of respective parameters of the plurality of parameters. The plurality of predetermined indication conditions includes a measurement item, a reference standard, a time period, a measurement condition, and a measurement manner.
-
Patent Agency Ranking
公开(公告)号：US10452987B2
公开(公告)日：2019-10-22
申请号：US14748867
申请日：2015-06-24
Applicant: International Business Machines Corporation
Inventor： Jing Li , Xiang Li , Haifeng Liu , Guo Tong Xie , Yi Qin Yu , Shi Lei Zhang
IPC: G06N7/00
Abstract: A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.
-
公开(公告)号：US10417569B2
公开(公告)日：2019-09-17
申请号：US14598655
申请日：2015-01-16
Applicant: International Business Machines Corporation
Inventor： Jing Li , Xiang Li , Haifeng Liu , Guo Tong Xie , Yi Qin Yu , Shi Lei Zhang
Abstract: A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.
-
公开(公告)号：US20150302314A1
公开(公告)日：2015-10-22
申请号：US14748867
申请日：2015-06-24
Applicant: International Business Machines Corporation
Inventor： Jing Li , Xiang Li , Haifeng Liu , Guo Tong Xie , Yi Qin Yu , Shi Lei Zhang
IPC: G06N7/00
Abstract: A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.
-
公开(公告)号：US11514348B2
公开(公告)日：2022-11-29
申请号：US16563070
申请日：2019-09-06
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Jing Li , Xiang Li , Haifeng Liu , Guo Tong Xie , Yi Qin Yu , Shi Lei Zhang
IPC: G06N7/00
Abstract: A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.
-
公开(公告)号：US11354588B2
公开(公告)日：2022-06-07
申请号：US16563076
申请日：2019-09-06
Applicant: International Business Machines Corporation
Inventor： Jing Li , Xiang Li , Haifeng Liu , Guo Tong Xie , Yi Qin Yu , Shi Lei Zhang
IPC: G06N7/00
Abstract: A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.
-
-
-
-
-
-
-
-
-
Search Results
39
records
(took 0.024 seconds)
