公开(公告)号：WO2021254413A1

公开(公告)日：2021-12-23

申请号：PCT/CN2021/100478

申请日：2021-06-17

Applicant: 南京大学

Inventor： 陈开明 ,  徐碧村 ,  鷲尾隆 ,  周志华

IPC: G06F16/2458 ,  G06K9/62 ,  G06F16/2465 ,  G06F2216/03 ,  G06K9/6215

Abstract: 一种隔离分布核构建方法、异常数据检测方法及装置，属于机器学习和数据挖掘技术领域。采用新的隔离分布核，给定一个数据集，将输入空间划分为隔离分区，每个分区将一个点与训练集中的其余点隔离。在执行点异常检测时，隔离分布核被用于测量点与给定数据集之间的相似性，相似度最低的点被视为点异常；为了检测群数据集中的群异常，在两个层级使用隔离分布核，在第一级将输入空间中数据集中的每个群都映射到希尔伯特空间一个点，在第二级使用IDK测量希尔伯特空间映射后的点和点集之间的相似性，希尔伯特空间点异常为对应输入空间中群异常，隔离分布核实现有限维度的特征映射，从而加快运行效率，并且利用数据分布提高相似性精度。

公开(公告)号：WO2023059358A1

公开(公告)日：2023-04-13

申请号：PCT/US2021/072163

申请日：2021-11-01

Applicant: UIPATH, INC.

Inventor： VANDERZEE, Matthew ,  HATZIDIMITRIS, Kosmas Wilhelmus ,  BEGO, Sven Cornelius Hubertus ,  VERHOEF, Céline ,  SELMAN, Johannes Wilhelmus Maria ,  WIJFFELAARS, Martijn Wilhelmus Henricus

IPC: G06Q10/06 ,  G06F9/451 ,  G06F9/448 ,  G06F11/36 ,  G06F16/2465 ,  G06F16/248 ,  G06F16/254 ,  G06F2216/03 ,  G06F8/65

Abstract: Systems and methods for performing process mining are provided. Data from one or more source systems is extracted by a data connector of a process app. The extracted data is transformed into a normalized data model by transforms of the process app. One or more process mining algorithms of the process app are applied to the normalized data. Results of the one or more process mining algorithms are presented to a user via a user interface of the process app.

公开(公告)号：WO2021202088A1

公开(公告)日：2021-10-07

申请号：PCT/US2021/022265

申请日：2021-03-15

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： BIRD, Christian Alma ,  FU, Shengyu ,  SUNDARESAN, Neelakantan ,  WANG, Nina ,  ZHANG, Shuo

IPC: G06F8/75 ,  G06F8/33 ,  G06F16/2246 ,  G06F16/2465 ,  G06F2216/03 ,  G06F8/315 ,  G06F8/36 ,  G06F8/751

Abstract: A data mining technique is used to find large frequently-occurring source code patterns from methods/APIs that can be used in code development. Simplified trees that represent the syntactic structure and type and method usage of a source code fragment, such as a method, are mined to find closed and maximal frequent subtrees which represent the largest frequently-occurring source code patterns or idioms associated with a particular type and method usage. These idioms are then used in an idiom web service and/or a code completion system to assist users in the development of source code programs.

公开(公告)号：WO2022208174A1

公开(公告)日：2022-10-06

申请号：PCT/IB2022/050747

申请日：2022-01-28

Applicant: METACLUSTER LT, UAB

Inventor： JURAVIČIUS, Martynas ,  KŪKŠTA, Andrius

IPC: G06F16/957 ,  G06F16/951 ,  G06F21/577 ,  G06F2216/03 ,  G06K9/6256 ,  G06K9/6269 ,  G06K9/6278 ,  G06K9/6282 ,  G06N20/00 ,  G06N3/0445 ,  G06N5/025 ,  H04L63/1433 ,  H04L67/02

Abstract: Systems and methods that allow examination of response data collected from content providers and provide for classification and routing according to the classification. The process of classification employs an unsupervised, or partially unsupervised, Machine Learning classifier model for identifying data collection responses that contains no data, mangled data, or a block, for assigning a classification correspondingly and for feeding the classification decision back to a data collection platform.

公开(公告)号：WO2021248201A1

公开(公告)日：2021-12-16

申请号：PCT/AU2021/050596

申请日：2021-06-10

Applicant: COMMONWEALTH SCIENTIFIC AND INDUSTRIAL RESEARCH ORGANISATION ,  UNIVERSITY OF GRONINGEN

Inventor： GOVERNATORI, Guido ,  VAN BEEST, Nick ,  CRYER, Adrian ,  GROEFSEMA, Heerko

IPC: G06F17/40 ,  G06F11/34 ,  G06Q10/06 ,  G06F11/302 ,  G06F11/3476 ,  G06F2216/03 ,  G06Q10/0635 ,  G06Q10/0639 ,  G06Q10/10

Abstract: This disclosure relates to a computer analysing log data. The computer receives log data comprising traces having log events from respective process executions. The computer creates a stream of log events, wherein the stream is sorted by the event time. The computer iterates over the stream of log events, and for each log event, executes update functions that define updates of a set of variables based on the log events. The set of variables comprises at least one cross-trace variable to calculate an updated value of the set of variables. The update functions define updates of the cross-trace variable in response to the log events of the traces. The computer further executes evaluation functions on the set of variables to determine compliance in relation to the log data based on the updated value. The evaluation functions represent compliance rules based on the set of variables including the cross-trace variable.