公开(公告)号：US20180357556A1

公开(公告)日：2018-12-13

申请号：US15617498

申请日：2017-06-08

Applicant: SAP SE

Inventor： Ramprasad Rai ,  Timo Hoyer ,  Dirk Wodtke ,  Ramshankar Venkatasubramanian

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06F3/0484

Abstract: The disclosure generally describes methods, software, and systems, including a method for machine learning anomaly detection for a set of assets. Assets are analyzed using anomaly-detection analysis and a set of anomaly-detection rules. Each asset is associated with correlated records comprising characteristics of the particular asset and characteristic of non-asset-specific signals. Each anomaly-detection rule is associated with conditions determined to be indicative of a potential anomaly. At least a subset of the assets are provided for presentation in a user interface. Each asset is identified as being in a potential anomalous or non-anomalous state based on the anomaly-detection analysis. Input is received from a user identifying at least one asset as anomalous as a non-anomalous asset. Based on the received input, at least one anomaly-detection rule is modified that was applied to identify the asset as anomalous. The modified rule is stored for future analyses.

公开(公告)号：US20180239804A1

公开(公告)日：2018-08-23

申请号：US15437831

申请日：2017-02-21

Applicant: SAP SE

Inventor： Ramshankar Venkatasubramanian ,  Dirk Wodtke ,  Ramprasad Rai ,  Brendan Bowles

IPC: G06F17/30

CPC classification number: G06F16/254 ,  G06F16/288 ,  G06Q10/00 ,  G06Q10/063 ,  G06Q10/0833

Abstract: A system includes determination of a first measure value associated with a first physical space and a first time period within the analytical data, dynamic determination of a time-dependent association between a first entity or event and the first physical, dynamic mapping of the first measure value to the first entity or event based on the time-dependent association, and presentation of the first measure value in association with the first entity or event.

公开(公告)号：US11250343B2

公开(公告)日：2022-02-15

申请号：US15617498

申请日：2017-06-08

Applicant: SAP SE

Inventor： Ramprasad Rai ,  Timo Hoyer ,  Dirk Wodtke ,  Ramshankar Venkatasubramanian

IPC: G06N20/00 ,  G06N20/10 ,  G06N5/02 ,  G06Q10/08 ,  G06F21/57 ,  G06Q10/10 ,  G06Q50/06 ,  G06F21/55 ,  G06F3/0484

Abstract: The disclosure generally describes methods, software, and systems, including a method for machine learning anomaly detection for a set of assets. Assets are analyzed using anomaly-detection analysis and a set of anomaly-detection rules. Each asset is associated with correlated records comprising characteristics of the particular asset and characteristic of non-asset-specific signals. Each anomaly-detection rule is associated with conditions determined to be indicative of a potential anomaly. At least a subset of the assets are provided for presentation in a user interface. Each asset is identified as being in a potential anomalous or non-anomalous state based on the anomaly-detection analysis. Input is received from a user identifying at least one asset as anomalous as a non-anomalous asset. Based on the received input, at least one anomaly-detection rule is modified that was applied to identify the asset as anomalous. The modified rule is stored for future analyses.

公开(公告)号：US20180357595A1

公开(公告)日：2018-12-13

申请号：US15617447

申请日：2017-06-08

Applicant: SAP SE

Inventor： Ramprasad Rai ,  Brendan Bowles ,  Dirk Wodtke ,  Ramshankar Venkatasubramanian

IPC: G06Q10/08 ,  G06N99/00 ,  G06Q30/02

CPC classification number: G06Q10/087 ,  G06F3/0481 ,  G06N99/005 ,  G06Q30/0205

Abstract: The disclosure generally describes methods, software, and systems, including a method for data collection and correlation of information for a set of assets. A set of asset-specific signals is obtained for a plurality of assets. Each asset has a set of characteristics defining the asset. A set of non-asset-specific signals is obtained. At least a portion of the set of non-asset-specific signals is correlated to at least some of the plurality of assets based on a determined correlation between at least one characteristic of a particular asset and a characteristic of the non-asset-specific signals. For each asset, a correlated record of the particular asset comprising the correlated characteristics is stored.

公开(公告)号：US10929421B2

公开(公告)日：2021-02-23

申请号：US15617408

申请日：2017-06-08

Applicant: SAP SE

Inventor： Ramprasad Rai ,  Timo Hoyer ,  Shridhar Nayak ,  Dirk Wodtke ,  Ramshankar Venkatasubramanian ,  Riccardo Spina

IPC: G06F16/245 ,  G06F16/26 ,  G06N20/00 ,  G06F16/2455

Abstract: The disclosure generally describes methods, software, and systems, including a method for providing a suggested view of asset information for presentation. A set of correlated records is identified for a plurality of assets. The set of correlated records includes a correlated set of at least one characteristic of a particular asset and a characteristic of the non-asset-specific signals. The set of correlated records is analyzed to identify a set of anomaly-detection rules. In a presentation of at least a subset of the assets, an indication of assets associated with a potential anomaly identified. A suggested view is identified based on the potential anomaly and at least one characteristic/signal associated with the determination that the potential anomaly exists. The suggested view is provided for presentation in a user interface.

公开(公告)号：US10387442B2

公开(公告)日：2019-08-20

申请号：US15437831

申请日：2017-02-21

Applicant: SAP SE

Inventor： Ramshankar Venkatasubramanian ,  Dirk Wodtke ,  Ramprasad Rai ,  Brendan Bowles

IPC: G06F7/00 ,  G06F17/00 ,  G06F16/25 ,  G06F16/28 ,  G06Q10/00 ,  G06Q10/06 ,  G06Q10/08

Abstract: A system includes determination of a first measure value associated with a first physical space and a first time period within the analytical data, dynamic determination of a time-dependent association between a first entity or event and the first physical, dynamic mapping of the first measure value to the first entity or event based on the time-dependent association, and presentation of the first measure value in association with the first entity or event.

公开(公告)号：US20180357292A1

公开(公告)日：2018-12-13

申请号：US15617408

申请日：2017-06-08

Applicant: SAP SE

Inventor： Ramprasad Rai ,  Timo Hoyer ,  Shridhar Nayak ,  Dirk Wodtke ,  Ramshankar Venkatasubramanian ,  Riccardo Spina

IPC: G06F17/30 ,  G06N99/00 ,  G06F3/0484

CPC classification number: G06F17/30572 ,  G06F3/0484 ,  G06F17/30477 ,  G06N99/005

Abstract: The disclosure generally describes methods, software, and systems, including a method for providing a suggested view of asset information for presentation. A set of correlated records is identified for a plurality of assets. The set of correlated records includes a correlated set of at least one characteristic of a particular asset and a characteristic of the non-asset-specific signals. The set of correlated records is analyzed to identify a set of anomaly-detection rules. In a presentation of at least a subset of the assets, an indication of assets associated with a potential anomaly identified. A suggested view is identified based on the potential anomaly and at least one characteristic/signal associated with the determination that the potential anomaly exists. The suggested view is provided for presentation in a user interface.