公开(公告)号：US20230096720A1

公开(公告)日：2023-03-30

申请号：US17486126

申请日：2021-09-27

Applicant: SAP SE

Inventor： Martin Wezowski ,  Hans-Martin Will ,  Rohit Jalagadugula ,  Kavitha Krishnan ,  Sai Hareesh Anamandra ,  Vinay George Roy ,  Parthasarathy Menon ,  Alexander Schaefer

IPC: G06Q10/06

Abstract: A method may include collecting data from a variety of data sources associated with a user. The data sources may include personal data sources, corporate data sources, and public data source. The data collected from the variety of data sources may be enriched through categorization and aggregation. For example, browser history may be categorized based on types of website and aggregated to reflect the quantity of interactions with each category of website. A multi-dimensional digital profile may be generated based on the enriched data. For instance, the digital profile may include a social, emotional, spiritual, environmental, occupational, intellectual, and physical dimension. One or more recommendation corresponding to one or more of a burnout prediction, wellness recommendation, learning plan, skill gap, and personality type may be generated based on the digital profile. Related systems and computer program products are also provided.

公开(公告)号：US11853950B2

公开(公告)日：2023-12-26

申请号：US17486126

申请日：2021-09-27

Applicant: SAP SE

Inventor： Martin Wezowski ,  Hans-Martin Will ,  Rohit Jalagadugula ,  Kavitha Krishnan ,  Sai Hareesh Anamandra ,  Vinay George Roy ,  Parthasarathy Menon ,  Alexander Schaefer

IPC: G06Q10/0639 ,  G06Q10/067 ,  G06Q10/0633 ,  H04L67/50

CPC classification number: G06Q10/06398 ,  G06Q10/067 ,  G06Q10/0633 ,  H04L67/535

Abstract: A method may include collecting data from a variety of data sources associated with a user. The data sources may include personal data sources, corporate data sources, and public data source. The data collected from the variety of data sources may be enriched through categorization and aggregation. For example, browser history may be categorized based on types of website and aggregated to reflect the quantity of interactions with each category of website. A multi-dimensional digital profile may be generated based on the enriched data. For instance, the digital profile may include a social, emotional, spiritual, environmental, occupational, intellectual, and physical dimension. One or more recommendation corresponding to one or more of a burnout prediction, wellness recommendation, learning plan, skill gap, and personality type may be generated based on the digital profile. Related systems and computer program products are also provided.

公开(公告)号：US20230131099A1

公开(公告)日：2023-04-27

申请号：US17508699

申请日：2021-10-22

Applicant: SAP SE

Inventor： Sai Hareesh Anamandra ,  Kavitha Krishnan ,  Rohit Jalagadugula ,  Parthasarathy Menon ,  Aditi D'Souza ,  Shrusti Mohanty ,  Lingyun Bu ,  Vinay George Roy

IPC: G06Q10/06 ,  G06N5/04 ,  G16H50/70 ,  G16H50/20 ,  G06Q10/10 ,  A61B5/11 ,  A61B5/0205 ,  A61B5/024 ,  A61B5/00

Abstract: A method may include training one or more machine learning models to predict a decline in employee performance. The machine learning models may be trained in a federated manner to avoid the exchange of personal data. The trained machine learning models may be applied to data associated with an employee that corresponds to one or more leading indicators of employee burnout. In response to the trained machine learning models predicting a decline in the performance of the employee, the root causes of the predicted decline in the performance of the employee may be identified by applying an explainability algorithm such as Shapley Additive Explanations (SHAP). A report including a corrective action for the predicted decline in employee performance may be generated based on the root causes. Related systems and computer program products are also provided.

公开(公告)号：US20240078495A1

公开(公告)日：2024-03-07

申请号：US17897664

申请日：2022-08-29

Applicant: SAP SE

Inventor： Sai Hareesh Anamandra ,  Gopi Kishan ,  Rohit Jalagadugula ,  Akash Srivastava ,  Kavitha Krishnan ,  Vinay George Roy

IPC: G06Q10/06 ,  G06Q10/10

CPC classification number: G06Q10/06398 ,  G06Q10/06395 ,  G06Q10/103

Abstract: Systems, methods, and computer media for determining compatible users through machine learning are provided herein. Previous interactions between some users in a group can be used to determine a first set of user-to-user compatibility scores. Both the first set of compatibility scores and attributes for the users in the group can be provided as inputs to a machine learning model that can be used to determine a second set of user-to-user compatibility scores for user pairs who do not have an interaction history. Along with input constraints, the first and second sets of user-to-user compatibility scores can be used to select compatible user groups.