公开(公告)号：US20220318686A1

公开(公告)日：2022-10-06

申请号：US17223796

申请日：2021-04-06

Applicant: SAP SE

Inventor： Nithya Rajagopalan ,  Panish Ramakrishna ,  Ashutosh Patel ,  Ranjith Pavanje Raja Rao ,  Mayank Kamboj ,  Arjun Swami

IPC: G06N20/20 ,  G06N5/04

Abstract: In an example embodiment an applications (apps) intelligence framework is utilized to quickly operationalize machine learned models (of different use cases, products, or applications) and take them to production through a set of predetermined pipelines. The app server may include a model configuration component to allow an entity to configure a model for an entity's specific use case. This configuration is then passed to a model generation component in the machine learning component, which acts to generate the specific model for the entity's use case using the configuration. An intelligent scheduling component may then be used to schedule retraining of the specific model at particular intervals. Notably, the intelligent scheduling component is itself a machine learned model (in one example embodiment a neural network) that is trained to dynamically output a training interval for a particular model based on various features.

公开(公告)号：US20220237542A1

公开(公告)日：2022-07-28

申请号：US17160820

申请日：2021-01-28

Applicant: SAP SE

Inventor： Mudit Joshi ,  Kiran Prashanth Kulkarni ,  Rahul Seshagiri Srivatsa ,  Avinash Permude ,  Erik Scheithauer ,  Nithya Rajagopalan

IPC: G06Q10/06

Abstract: Various examples are directed to determining an impact of a subunit on the value of a unit. A web-based analytics system receives unit value data via a user interface page provided to a supplier computing device by a web application, the unit value data including relationship data describing a relationship between a plurality of subunit values and a unit value. Based on relationship data, the system increases a value for a first subunit while holding values for the other subunits constant until the value of the unit increases to a unit value threshold and increases a value for a second subunit while holding values for the other subunits constant until the value of the unit increases to a unit value threshold. The system compares an increase in the value of the first subunit to increase the value of the unit to the unit value threshold with an increase in the value of the second subunit to increase the value of the unit to the unit value threshold. Based on the comparing, the system determines that the first subunit is a more significant driver of the value of the unit than the second subunit.

公开(公告)号：US20220036436A1

公开(公告)日：2022-02-03

申请号：US16943304

申请日：2020-07-30

Applicant: SAP SE

Inventor： Nithya Rajagopalan ,  Vidhya Neelakantan

IPC: G06Q30/06 ,  G06N20/00 ,  H04L29/08

Abstract: Aspects of the current subject matter are directed to implementing a distribution scenario in a system. In particular, implementations of the current subject matter provide for a designating client device to create a group of distributing client devices for events among and with a plurality of second client devices. Implementations of the current subject matter further relate to automatic assignment of items among the group of distributing client devices, the assignment based on designating client device-established constraints, and to providing an aggregate view of information related to the automatic assignment of the items to allow the designating client device to manage the items.

公开(公告)号：US11176324B2

公开(公告)日：2021-11-16

申请号：US16584420

申请日：2019-09-26

Applicant: SAP SE

Inventor： Kumaraswamy Gowda ,  Nithya Rajagopalan ,  Nishant Kumar ,  Panish Ramakrishna ,  Rajendra Vuppala ,  Erica Vandenhoek

IPC: G06F40/295 ,  G06F40/177 ,  G06F40/49 ,  G06K9/62

Abstract: The present disclosure involves systems, software, and computer implemented methods for creating line item information from tabular data. One example method includes receiving event data values at a system. Column headers of columns in the event data values are identified. At least one column header is not included in standard line item terms used by the system. Column values of the columns in the event data values are identified. The identified column headers and the identified column values are processed using one or more models to map each column to a standard line item term used by the system. The processing includes using context determination and content recognition to identify standard line item terms. An event is created in the system, including the creation of line items from the identified column value. Each line item includes standard line item terms mapped to the columns.

公开(公告)号：US20210304298A1

公开(公告)日：2021-09-30

申请号：US16831430

申请日：2020-03-26

Applicant: SAP SE

Inventor： Nithya Rajagopalan ,  Panish Ramakrishna ,  Harish Dhivahar Ariharasuthan

IPC: G06Q30/08 ,  G06K9/62 ,  G06N3/08 ,  G06F9/54

Abstract: Various examples are directed to systems and methods for managing a computerized event platform. The computerized event platform may receive participant data describing a plurality of historical bids from a plurality of historical events and generate a set of recommended participants to participate in an event to provide a first item.

公开(公告)号：US10795904B2

公开(公告)日：2020-10-06

申请号：US16185872

申请日：2018-11-09

Applicant: SAP SE

Inventor： Nithya Rajagopalan ,  Abhishek Chaturvedi ,  Sunil Gornalle ,  Prasad Karani ,  Surendranath Gopinathan ,  Gurudayal Khosla

IPC: G06F16/00 ,  G06F16/25 ,  G06Q30/06 ,  G06F16/2455 ,  G06F3/0481

Abstract: In an example embodiment, a first payload in a first electronic communication is received, the first payload containing localization information regarding a first node in a taxonomy of objects, categories, and characteristics. The first payload is parsed to identify one or more dependencies. For each of the one or more dependencies, a dummy node in the taxonomy corresponding to the dependency is created, the dummy node containing information about the dependency from the first payload. A search mechanism is provided to a graphical user interface, the search mechanism designed to receive user interactions from a user and cause one or more hardware processors to retrieve and cause display of information in one or more of the dummy nodes in the taxonomy.

公开(公告)号：US20190179937A1

公开(公告)日：2019-06-13

申请号：US15838256

申请日：2017-12-11

Applicant: SAP SE

Inventor： Debashis Banerjee ,  Nithya Rajagopalan

IPC: G06F17/30 ,  G06N99/00

Abstract: A method for enriching an object in a database may include determining, by a trained machine learning model, that a first object at the database is same and/or similar to a second object at the database. The first object and the second object may be part of a schema of the database. The second object may be subordinate to the first object. In response to the determination that the first object is same and/or similar to the second object, one or more attributes associated with the second object may be added to the first object. Related systems and articles of manufacture including computer program products are also provided.