公开(公告)号：US10467501B2

公开(公告)日：2019-11-05

申请号：US15797117

申请日：2017-10-30

Applicant: SAP SE

Inventor： Sivakumar N ,  Praveenkumar A K ,  Raghavendra D ,  Vijay G ,  Pratik Shenoy ,  Kishan Kumar Kedia

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06K9/00 ,  G06K9/32 ,  G06K9/34 ,  G06K9/46 ,  G06T7/73 ,  G06N20/00 ,  G06T7/60 ,  G06N3/02 ,  G06N5/04 ,  G06Q10/08

Abstract: In an example, a first machine learning algorithm is used to train a smart contour model to identify contours of product shapes in input images and to identify backgrounds in the input images. A second machine learning algorithm is used to train a plurality of shape-specific classification models to output identifications of products in input images. A candidate image of one or more products is obtained. The candidate image is passed to the smart contour model, obtaining output of one or more tags identifying product contours in the candidate image. The candidate image and the one or more tags are passed to an ultra-large scale multi-hierarchy classification system to identify one or more classification models for one or more individual product shapes in the candidate image. The one or more classification models are used to distinguish between one or more products and one or more unknown products in the image.

公开(公告)号：US20190057218A1

公开(公告)日：2019-02-21

申请号：US15680897

申请日：2017-08-18

Applicant: SAP SE

Inventor： Srinivas Bhaskara ,  Vinay C ,  Vijay G ,  Zainul Abidin Mulla ,  Pranjal Chugh ,  Miguel Rolando Heineken

IPC: G06F21/62 ,  H04L29/06

Abstract: A retention service registers a target system as a consumer service. A cloud platform provides services to each of multiple consumer service. Retention rule information about the target system is received and reflects a data retention requirement. A rule is created that corresponds to the data retention requirement. A configuration is defined that specifies recurring future invocations of the rule. The rule is invoked per the configuration and a query is sent to the target system, the query configured to extract data. Extracted data is received and the rule is applied thereto. An action specified by the rule is taken with regard to the data.

公开(公告)号：US10831910B2

公开(公告)日：2020-11-10

申请号：US15680897

申请日：2017-08-18

Applicant: SAP SE

Inventor： Srinivas Bhaskara ,  Vinay C ,  Vijay G ,  Zainul Abidin Mulla ,  Pranjal Chugh ,  Miguel Rolando Heineken

IPC: H04L29/00 ,  G06F21/62 ,  H04L29/06 ,  H04L29/08

Abstract: A retention service registers a target system as a consumer service. A cloud platform provides services to each of multiple consumer service. Retention rule information about the target system is received and reflects a data retention requirement. A rule is created that corresponds to the data retention requirement. A configuration is defined that specifies recurring future invocations of the rule. The rule is invoked per the configuration and a query is sent to the target system, the query configured to extract data. Extracted data is received and the rule is applied thereto. An action specified by the rule is taken with regard to the data.

公开(公告)号：US10474928B2

公开(公告)日：2019-11-12

申请号：US15812533

申请日：2017-11-14

Applicant: SAP SE

Inventor： Sivakumar N ,  Praveenkumar A K ,  Raghavendra D ,  Vijay G ,  Pratik Shenoy ,  Kishan Kumar Kedia

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06K9/32 ,  G06K9/34 ,  G06K9/46 ,  G06T7/73 ,  G06N20/00 ,  G06T7/60 ,  G06N3/02 ,  G06N5/04 ,  G06Q10/08

Abstract: In an example, a computerized neural fabric is created by representing each pattern of learned weights of one or more machine learning algorithm-trained models specifying a specific set of products as a column in the computerized neural fabric, each pattern comprising one or more clusters representing combinations of convolutional filters, each cluster learning low level features and sending output via a vertical flow up the corresponding column to a final classification within the corresponding pattern. One or more potential lateral flows between patterns in the computerized neural fabrics is dynamically determined based on resemblance of a new product in a candidate image to the specific sets of products in each of the patterns and identifying possible mutations of the patterns based on the resemblance. Then, one of the one or more potential lateral flows is selected as a new model.

公开(公告)号：US20190130292A1

公开(公告)日：2019-05-02

申请号：US15812533

申请日：2017-11-14

Applicant: SAP SE

Inventor： Sivakumar N ,  Praveenkumar A K ,  Raghavendra D ,  Vijay G ,  Pratik Shenoy ,  Kishan Kumar Kedia

IPC: G06N5/04 ,  G06N3/02 ,  G06N99/00

Abstract: In an example, a computerized neural fabric is created by representing each pattern of learned weights of one or more machine learning algorithm-trained models specifying a specific set of products as a column in the computerized neural fabric, each pattern comprising one or more clusters representing combinations of convolutional filters, each cluster learning low level features and sending output via a vertical flow up the corresponding column to a final classification within the corresponding pattern. One or more potential lateral flows between patterns in the computerized neural fabrics is dynamically determined based on resemblance of a new product in a candidate image to the specific sets of products in each of the patterns and identifying possible mutations of the patterns based on the resemblance. Then, one of the one or more potential lateral flows is selected as a new model.

公开(公告)号：US20190130214A1

公开(公告)日：2019-05-02

申请号：US15797117

申请日：2017-10-30

Applicant: SAP SE

Inventor： Sivakumar N ,  Praveenkumar A K ,  Raghavendra D ,  Vijay G ,  Pratik Shenoy ,  Kishan Kumar Kedia

IPC: G06K9/62 ,  G06N99/00 ,  G06N3/04 ,  G06T7/73 ,  G06T7/60 ,  G06K9/00

CPC classification number: G06K9/6256 ,  G06K9/00208 ,  G06K9/00771 ,  G06K9/00973 ,  G06K9/3241 ,  G06K9/34 ,  G06K9/4628 ,  G06K9/6204 ,  G06K9/6218 ,  G06K9/6268 ,  G06K9/6273 ,  G06K9/6284 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0454 ,  G06N3/084 ,  G06N5/047 ,  G06N20/00 ,  G06Q10/087 ,  G06T7/60 ,  G06T7/75 ,  G06T2200/28 ,  G06T2207/30242

Abstract: In an example, a first machine learning algorithm is used to train a smart contour model to identify contours of product shapes in input images and to identify backgrounds in the input images. A second machine learning algorithm is used to train a plurality of shape-specific classification models to output identifications of products in input images. A candidate image of one or more products is obtained. The candidate image is passed to the smart contour model, obtaining output of one or more tags identifying product contours in the candidate image. The candidate image and the one or more tags are passed to an ultra-large scale multi-hierarchy classification system to identify one or more classification models for one or more individual product shapes in the candidate image. The one or more classification models are used to distinguish between one or more products and one or more unknown products in the image.