公开(公告)号：US20190130069A1

公开(公告)日：2019-05-02

申请号：US15797295

申请日：2017-10-30

Applicant: International Business Machines Corporation

Inventor： Xiang Li ,  Hai Feng Liu ,  Guo Tong Xie ,  Yi Qin Yu ,  Ping Zhang

IPC: G06F19/00 ,  G06N99/00

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate providing treatment suggestions are described herein. In one example, a computer-implemented method comprises: generating, by a system operatively coupled to a processor, treatment directed graphs associated with a plurality of treatment regimens, wherein, in connection with generating respective treatment directed graphs, penalties are applied during weighting of respective regimens as a function of an associated confidence level; identifying a treatment directed graph that corresponds to the patient directed graph; and outputting a set of treatment suggestions associated with the treatment directed graph that corresponds to the patient directed graph.

公开(公告)号：US20180203426A1

公开(公告)日：2018-07-19

申请号：US15898983

申请日：2018-02-19

Applicant: International Business Machines Corporation

Inventor： Bing Li ,  Xiang Li ,  Xiao Jian Lian ,  Dan Liu ,  Haifeng Liu ,  Jing Mei ,  Guo Tong Xie ,  Yi Qin Yu ,  Jing Zhang

IPC: G05B17/02

CPC classification number: G05B17/02

Abstract: Disclosed are a computer-implemented method for converting a procedural process model for a process to a hybrid process model, a system and a computer program product. In this method, a plurality of steps of the process which are included in the procedural process model may be clustered selectively according to historical execution information of the plurality of steps, to generate a plurality of candidate cluster set. One candidate cluster set satisfying a first condition may be selected from the plurality of candidate cluster sets. Then, the procedural process model may be converted into the hybrid process model according to the selected candidate cluster set.

公开(公告)号：US20170161634A1

公开(公告)日：2017-06-08

申请号：US14962078

申请日：2015-12-08

Applicant: International Business Machines Corporation

Inventor： Xiang Li ,  Haifeng Liu ,  Jing Mei ,  Guo Tong Xie ,  Yi Qin Yu

IPC: G06N99/00 ,  G06N5/02

CPC classification number: G06N99/005 ,  G06F19/00 ,  G06F19/30 ,  G06N5/04

Abstract: A method for using a plurality of decision engines to produce a single decision comprises: receiving heterogeneous data from the plurality of decision engines comprising a set of class labels from each of the plurality of decision engines, wherein the set of class labels from at least a first decision engine differs from the set of class labels from at least a second decision engine; generating a single set of unified class labels from the heterogeneous data; calculating at least one value corresponding to each of at least a subset of the unified class labels; and performing decision fusion on at least the subset of the unified class labels and corresponding values to produce the single decision.

公开(公告)号：US20150294232A1

公开(公告)日：2015-10-15

申请号：US14748850

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.