公开(公告)号：US20190310891A1

公开(公告)日：2019-10-10

申请号：US16177289

申请日：2018-10-31

Applicant: SAS Institute Inc.

Inventor： Ruth Ellen Baldasaro ,  Jennifer Lee Hargrove ,  Edward Lew Rowe ,  Emily Louise Chapman-McQuiston

IPC: G06F9/50 ,  G06N3/08 ,  G06F16/906

Abstract: Exemplary embodiments relate to systems for building a model of changes to data items when information the data items is limited or not directly observed. Exemplary embodiments allow properties of the data items to be inferred using a single data structure and creates a highly granular log of changes to the data item. Using this data structure, the time-varying nature of changes to the data item can be determined. The data structure may be used to identify characteristics associated with a regularly-performed action, to examine how adherence to the action affects a system, and to identify outcomes of non-adherence. Fungible data items may be mapped to a remediable condition or remedy class. This may be accomplished by automatically deriving conditions and remedial information from available information, matching the conditions to remedial classes or types via a customizable mapping, and then calculating adherence for the condition on the available information.

公开(公告)号：US10761894B2

公开(公告)日：2020-09-01

申请号：US16177289

申请日：2018-10-31

Applicant: SAS Institute Inc.

Inventor： Ruth Ellen Baldasaro ,  Jennifer Lee Hargrove ,  Edward Lew Rowe ,  Emily Louise Chapman-McQuiston

IPC: G06F9/50 ,  G06N3/08 ,  G06F16/906 ,  G06F16/9038 ,  G06F16/9035

Abstract: Exemplary embodiments relate to systems for building a model of changes to data items when information the data items is limited or not directly observed. Exemplary embodiments allow properties of the data items to be inferred using a single data structure and creates a highly granular log of changes to the data item. Using this data structure, the time-varying nature of changes to the data item can be determined. The data structure may be used to identify characteristics associated with a regularly-performed action, to examine how adherence to the action affects a system, and to identify outcomes of non-adherence. Fungible data items may be mapped to a remediable condition or remedy class. This may be accomplished by automatically deriving conditions and remedial information from available information, matching the conditions to remedial classes or types via a customizable mapping, and then calculating adherence for the condition on the available information.

公开(公告)号：US10929193B2

公开(公告)日：2021-02-23

申请号：US16531506

申请日：2019-08-05

Applicant: SAS Institute Inc.

Inventor： Ruth Ellen Baldasaro ,  Jennifer Lee Hargrove ,  Edward Lew Rowe ,  Emily Louise Chapman-McQuiston

IPC: G06N3/08 ,  G06F9/50 ,  G06F16/906 ,  G06F16/9038 ,  G06F16/9035

Abstract: Exemplary embodiments relate to systems for building a model of changes to data items when information the data items is limited or not directly observed. Exemplary embodiments allow properties of the data items to be inferred using a single data structure and creates a highly granular log of changes to the data item. Using this data structure, the time-varying nature of changes to the data item can be determined. The data structure may be used to identify characteristics associated with a regularly-performed action, to examine how adherence to the action affects a system, and to identify outcomes of non-adherence. Fungible data items may be mapped to a remediable condition or remedy class. This may be accomplished by automatically deriving conditions and remedial information from available information, matching the conditions to remedial classes or types via a customizable mapping, and then calculating adherence for the condition on the available information.

公开(公告)号：US20190354410A1

公开(公告)日：2019-11-21

申请号：US16531506

申请日：2019-08-05

Applicant: SAS Institute Inc.

Inventor： Ruth Ellen Baldasaro ,  Jennifer Lee Hargrove ,  Edward Lew Rowe ,  Emily Louise Chapman-McQuiston

IPC: G06F9/50 ,  G06F16/906 ,  G06N3/08

Abstract: Exemplary embodiments relate to systems for building a model of changes to data items when information the data items is limited or not directly observed. Exemplary embodiments allow properties of the data items to be inferred using a single data structure and creates a highly granular log of changes to the data item. Using this data structure, the time-varying nature of changes to the data item can be determined. The data structure may be used to identify characteristics associated with a regularly-performed action, to examine how adherence to the action affects a system, and to identify outcomes of non-adherence. Fungible data items may be mapped to a remediable condition or remedy class. This may be accomplished by automatically deriving conditions and remedial information from available information, matching the conditions to remedial classes or types via a customizable mapping, and then calculating adherence for the condition on the available information.