公开(公告)号：US11222033B2

公开(公告)日：2022-01-11

申请号：US16197937

申请日：2018-11-21

Applicant: SAP SE

Inventor： Rahul Tiwari ,  Krishnan Raghupathi ,  Hari Prasada Reddy

IPC: G06F16/00 ,  G06F16/248 ,  G06T11/20 ,  G06F16/242 ,  G06F16/245 ,  G06F16/28

Abstract: A process for providing a plurality of exploration mode charts to supplement a base chart is provided herein. A request for exploration mode charts may be received. The request may include a data set definition. A total number of data points for the request may be determined based on the data set definition. A total number of exploration mode charts may be determined based at least in part on the total number of data points for the request. Chart data may be obtained for a plurality of exploration mode charts based on the data set definition. The plurality of exploration mode charts may include a number of charts less than or equal to the total number of exploration mode charts. The plurality of exploration mode charts may be rendered via the chart data. The rendered exploration mode charts may be provided.

公开(公告)号：US20250028789A1

公开(公告)日：2025-01-23

申请号：US18356870

申请日：2023-07-21

Applicant: SAP SE

Inventor： Krishnan Raghupathi

IPC: G06F18/2415 ,  G06F16/55

Abstract: Generating Notifications Through Chart Pattern Detection Embodiments utilize pattern recognition to generate notifications in connection with analytical applications. A dashboard of the analytical dashboard is scanned to intake charts of data therefrom. Images of the charts are created, and then matched with repository patterns of a trained deep transfer model (such as a Convolutional Neural Network model). Upon matching of a pattern by the model, an alert is generated and communicated to a user to indicate a trend in the analytical data. In this manner, embodiments automatically detect data trends based upon their visual appearance when plotted in a chart, rather than through resource-intensive analysis of individual data point values. In specific embodiments, the pattern recognition may be implemented by an in-memory database engine of an in-memory database responsible for storing charts and/or chart images and/or the repository. In some embodiments, recognition of patterns in chart images may be implemented by a service.

公开(公告)号：US12164523B2

公开(公告)日：2024-12-10

申请号：US18058087

申请日：2022-11-22

Applicant: SAP SE

Inventor： Krishnan Raghupathi

IPC: G06F16/2455 ,  G06F16/28

Abstract: Embodiments store attributes extracted from incoming media data (e.g., image, audio, video), in a media store residing in a data lake together with other, non-media attributes. In response to incoming media data (e.g., an image), an engine references an unpopulated media attribute schema resulting from processing a trained deep learning model (e.g., a Convolutional Neural Network—CNN model). The engine applies the deep learning model to extract from the incoming media data, a media attribute (e.g., a cloudy spot dimension) comprising a prediction value and a confidence. The engine populates the media attribute schema with the attribute (value; confidence) and an identifier, and stores the populated media attribute schema in the data lake. The data lake also includes a non-media attribute (e.g., patient info) sharing the identifier. Now, the data lake may be queried for both the non-media (patient info) attribute and the media (image) attribute extracted by the model.

公开(公告)号：US20240168959A1

公开(公告)日：2024-05-23

申请号：US18058087

申请日：2022-11-22

Applicant: SAP SE

Inventor： Krishnan Raghupathi

IPC: G06F16/2455 ,  G06F16/28

CPC classification number: G06F16/24568 ,  G06F16/24552 ,  G06F16/283

Abstract: Embodiments store attributes extracted from incoming media data (e.g., image, audio, video), in a media store residing in a data lake together with other, non-media attributes. In response to incoming media data (e.g., an image), an engine references an unpopulated media attribute schema resulting from processing a trained deep learning model (e.g., a Convolutional Neural Network—CNN model). The engine applies the deep learning model to extract from the incoming media data, a media attribute (e.g., a cloudy spot dimension) comprising a prediction value and a confidence. The engine populates the media attribute schema with the attribute (value; confidence) and an identifier, and stores the populated media attribute schema in the data lake. The data lake also includes a non-media attribute (e.g., patient info) sharing the identifier. Now, the data lake may be queried for both the non-media (patient info) attribute and the media (image) attribute extracted by the model.

公开(公告)号：US20200159849A1

公开(公告)日：2020-05-21

申请号：US16197937

申请日：2018-11-21

Applicant: SAP SE

Inventor： Rahul Tiwari ,  Krishnan Raghupathi ,  Hari Prasada Reddy

IPC: G06F17/30 ,  G06T11/20

Abstract: A process for providing a plurality of exploration mode charts to supplement a base chart is provided herein. A request for exploration mode charts may be received. The request may include a data set definition. A total number of data points for the request may be determined based on the data set definition. A total number of exploration mode charts may be determined based at least in part on the total number of data points for the request. Chart data may be obtained for a plurality of exploration mode charts based on the data set definition. The plurality of exploration mode charts may include a number of charts less than or equal to the total number of exploration mode charts. The plurality of exploration mode charts may be rendered via the chart data. The rendered exploration mode charts may be provided.