-
公开(公告)号：US20170255874A1
公开(公告)日：2017-09-07
申请号：US15059594
申请日：2016-03-03
Applicant: International Business Machines Corporation
Inventor： Girish B. Chafle , Peng Fei Chen , Fan Jing Meng , Hai Shan Wu , Jing Min Xu , Lin Yang
CPC classification number: G06N20/00 , G06F11/3006 , G06F11/3414 , G06F11/3452
Abstract: Embodiments are directed to a computer implemented method for generating a drift detector. The method includes generating, using a processor system, drift cases based at least in part on known drift set data of a computer system. The method further includes injecting, using the processor system, the drift cases into the computer system to generate a first data set. The method further includes applying, using the processor system, cleaning rules to the first data set to reduce a size of the first data set and generate a cleaned data set. The method further includes extracting one or more features of the cleaned data set. The method further includes normalizing the extracted one or more features of the cleaned data set. The method further includes training a machine learning system using the extracted and normalized one or more features of the cleaned data, wherein an output of the machine learning system comprises the drift detector.
-
公开(公告)号：US09674029B2
公开(公告)日：2017-06-06
申请号：US14967639
申请日：2015-12-14
Applicant: International Business Machines Corporation
Inventor： Fan Jing Meng , Yuan Wang , Jing Min Xu , Bo Yang , Yang Zhao
CPC classification number: G06F9/45558 , G06F9/4856 , G06F2009/4557 , H04L41/046 , H04L41/0846 , H04L67/32
Abstract: Embodiments include methods and devices for migrating virtual assets over networks that have a first manager connected to a physical host a virtual machine run. Aspects include registering the physical host to a second manager in the network, creating the mapping relationship of the physical host between a database of the first manager and a database of the second manager and importing instance data and status data of the virtual machine of the physical host from the database of the first manager into the database of the second manager. Aspects also include switching the management for the physical host from the first manager to the second manager.
-
43.发明申请DETERMINING A PERFORMANCE PREDICTION MODEL FOR A TARGET DATA ANALYTICS APPLICATION 审中-公开确定目标数据分析应用的性能预测模型公开(公告)号：US20150310335A1
公开(公告)日：2015-10-29
申请号：US14689073
申请日：2015-04-17
Applicant: International Business Machines Corporation
Inventor： Liya Fan , Chang Sheng Li , Jing Min Xu , Lin Yang
CPC classification number: G06N20/00
Abstract: A performance prediction model for a target data analytics application, where: (i) a reference data analytics application similar to the target data analytics application is determined; (ii) a configuration-performance data pair of the target data analytics application are acquired; and (iii) the performance prediction model for the target data analytics application is determined based on the configuration-performance data pair of the target data analytics application and a configuration-performance data pair of the at least one reference data analytics application. This can reduce the time required to accumulate the configuration-performance data pairs for determining the performance prediction model by combining the configuration-performance data pairs of the existing data analytics applications, thereby accelerating determination of the performance prediction model.
Abstract translation: 用于目标数据分析应用的性能预测模型，其中：（i）确定与目标数据分析应用程序类似的参考数据分析应用程序; （ii）获取目标数据分析应用的配置性能数据对; 以及（iii）基于所述目标数据分析应用的配置性能数据对和所述至少一个参考数据分析应用的配置性能数据对来确定所述目标数据分析应用的性能预测模型。 这可以通过组合现有数据分析应用的配置性能数据对来减少累积用于确定性能预测模型的配置性能数据对所需的时间，从而加速性能预测模型的确定。
-
公开(公告)号：US11269714B2
公开(公告)日：2022-03-08
申请号：US17136974
申请日：2020-12-29
Applicant: International Business Machines Corporation
Inventor： Xiao Zhang , Fan Jing Meng , Lin Yang , Jing Min Xu
Abstract: Embodiments facilitating performance anomaly detection are described. A computer-implemented method comprises: detecting, by a device operatively coupled to one or more processing units, based on monitoring data of a plurality of performance metrics of a monitored device, at least one trend within the monitoring data of the respective performance metrics; removing, by the device, the at least one trend from the monitoring data of the respective performance metrics to generate modified data of the respective performance metrics; and detecting, by the device, a performance anomaly based on the modified data of the respective performance metrics and a behavior clustering model comprising at least one steady state.
-
公开(公告)号：US20210286828A1
公开(公告)日：2021-09-16
申请号：US16819144
申请日：2020-03-15
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Jia Qi Li , Fan Jing Meng , Jing Min Xu , Pei Ni Liu , Zi Xiao Zhu
IPC: G06F16/28 , G06F16/17 , G06F16/182 , G06N5/02
Abstract: A method and system for relation discovery from operation data includes classifying categories of extracted entities from operation data into three or more classes identified in a knowledge base. A log affiliation of the extracted entities is determined, and relations of the extracted entities are identified according to a log affiliation. The identified relations information of the extracted entities is associated with operation objects of the operation data.
-
Patent Agency Ranking
公开(公告)号：US10977005B2
公开(公告)日：2021-04-13
申请号：US15622558
申请日：2017-06-14
Applicant: International Business Machines Corporation
Inventor： Xiao Xi Liu , Jing Min Xu , Yuan Wang , Jian Ming Zhang
Abstract: A service running on a server for developing software collaboratively. The service includes accessing at least one repository of code for software applications. A code tree structure is extracted from the repository which represents a plurality of preexisting pipeline requirements to be used with a tree kernel similarity algorithm. At least one development repository of code is accessed. A code tree structure is extracted from the development repository of code which represents a new pipeline requirement to be used with a tree kernel similarity algorithm. A tree kernel similarity algorithm is used that includes a specified similarity function to create feature map between the new pipeline requirements with the preexisting pipeline requirements. One or more features of the new pipe line requirements are clustered. Different requirements are extracted to different definitions based upon the features that have been clustered. A preexisting pipeline requirement is selected for a highest similarity.
-
公开(公告)号：US10901954B2
公开(公告)日：2021-01-26
申请号：US16180630
申请日：2018-11-05
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Jian Ma , Guang Cheng Li , Jing Min Xu , Xiao Xi Liu , Yuan Wang , Lin Yang
IPC: G06F17/00 , G06F16/178 , G06F16/182
Abstract: Methods and systems for managing persistent volumes include receiving a request from a container on a processing node to access a local mount point. A distributed filesystem located outside the processing node is mounted to a local mount point. Access to the local mount point is provided to the container.
-
公开(公告)号：US20210021456A1
公开(公告)日：2021-01-21
申请号：US16515333
申请日：2019-07-18
Applicant: International Business Machines Corporation
Inventor： Dian Qi , Fan Jing Meng , Jing Min Xu , Lin Yang
IPC: H04L12/24
Abstract: Techniques for Bayesian-based event grouping are provided. One technique includes determining a group of alarm events from received alarm events; in response to the group of alarm events matching a group of historical alarm events, determining a first correlation, wherein the group of historical alarm events comprises correlated events associated with a same entity; and determining a root cause of the group of alarm events based on the first correlation.
-
公开(公告)号：US20200233735A1
公开(公告)日：2020-07-23
申请号：US16253262
申请日：2019-01-22
Applicant: International Business Machines Corporation
Inventor： Xiao Zhang , Fan Jing Meng , Lin Yang , Jing Min Xu
IPC: G06F11/07
Abstract: Embodiments facilitating performance anomaly detection are described. A computer-implemented method comprises: detecting, by a device operatively coupled to one or more processing units, based on monitoring data of a plurality of performance metrics of a monitored device, at least one trend within the monitoring data of the respective performance metrics; removing, by the device, the at least one trend from the monitoring data of the respective performance metrics to generate modified data of the respective performance metrics; and detecting, by the device, a performance anomaly based on the modified data of the respective performance metrics and a behavior clustering model comprising at least one steady state.
-
50.发明申请公开(公告)号：US20200160230A1
公开(公告)日：2020-05-21
申请号：US16195070
申请日：2018-11-19
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Yuan Wang , Lin Yang , Xiao Xi Liu , Fan Jing Meng , Jing Min Xu , William V. Da Palma , Sandhya Kapoor , Takayuki Kushida , Hiroki Nakano
Abstract: A computer-implemented method is presented for automatically generating alerting rules. The method includes identifying, via offline analytics, abnormal patterns and normal patterns from history logs based on machine learning, statistical analysis and deep learning, the history logs stored in a history log database, automatically generating the alerting rules based on the identified abnormal and normal patterns, and transmitting the alerting rules to an alerting engine for evaluation. The method further includes receiving a plurality of online log messages from a plurality of computing devices connected to a network, augmenting the plurality of online log messages, and extracting information from the plurality of augmented online log messages to be provided to the alerting engine, the alerting engine configured to approve and enforce the alerting rules automatically generated by the offline analytics processing.
-
-
-
-
-
-
-
-
-
Search Results
75
records
(took 0.024 seconds)
