公开(公告)号：US20200248920A1

公开(公告)日：2020-08-06

申请号：US16264443

申请日：2019-01-31

Applicant: SAP SE

Inventor： Ninad Kulkarni ,  Xuening Wu ,  Sangeetha Krishnamoorthy ,  Mario Ponce ,  Jun Meng ,  Rui Jin ,  Wafaa Sabil ,  Sivakumar N.

IPC: F24F11/47 ,  G01W1/10 ,  F24F11/64 ,  F24F11/65 ,  F24F11/77 ,  G05B13/04

Abstract: Systems and methods are provided for determining a weather forecast corresponding to a location of an air handling unit for a building, generating a foot traffic forecast for a specified time period in the building, and generating a predicted energy consumption curve based on the weather forecast and generated foot traffic forecast for the specified time period. Based on the predicted energy consumption curve, the systems and methods further provide for generating settings for controllable energy devices of the air handling unit to control the air handling unit for the specified time period.

公开(公告)号：US11875368B2

公开(公告)日：2024-01-16

申请号：US16810465

申请日：2020-03-05

Applicant: SAP SE

Inventor： Pankti Jayesh Kansara ,  James Rapp ,  John Seeburger ,  Sangeetha Krishnamoorthy ,  Mario Ponce Midence

IPC: G06Q30/0202 ,  G06Q30/0601 ,  G06N20/00 ,  G06Q10/047 ,  G06Q10/1093 ,  G06N7/01

CPC classification number: G06Q30/0202 ,  G06N7/01 ,  G06N20/00 ,  G06Q10/047 ,  G06Q10/1093 ,  G06Q30/0605

Abstract: The present disclosure involves systems, software, and computer implemented methods for proactively predicting demand based on sparse transaction data. One example method includes receiving a request to predict transaction quantities for a plurality of transaction entities for a future time period. Historical transaction data for the transaction entities is identified for a plurality of categories of transacted items. The plurality of categories are organized using a hierarchy of levels. Multiple levels of the hierarchy are iterated over starting at a lowest level. For each current level in the iteration, features to include in a quantity forecasting model for the current level are identified. The quantity forecasting model is trained using the identified features.
Predicted transaction dates are predicted for the current level by a transaction date prediction model. The quantity forecasting model is used to generate predicted quantity information for the current level for the predicted transaction dates.

公开(公告)号：US20210117995A1

公开(公告)日：2021-04-22

申请号：US16810465

申请日：2020-03-05

Applicant: SAP SE

Inventor： Pankti Jayesh Kansara ,  James Rapp ,  John Seeburger ,  Sangeetha Krishnamoorthy ,  Mario Ponce Midence

IPC: G06Q30/02 ,  G06F17/18 ,  G06Q30/06

Abstract: The present disclosure involves systems, software, and computer implemented methods for proactively predicting demand based on sparse transaction data. One example method includes receiving a request to predict transaction quantities for a plurality of transaction entities for a future time period. Historical transaction data for the transaction entities is identified for a plurality of categories of transacted items. The plurality of categories are organized using a hierarchy of levels. Multiple levels of the hierarchy are iterated over starting at a lowest level. For each current level in the iteration, features to include in a quantity forecasting model for the current level are identified. The quantity forecasting model is trained using the identified features.
Predicted transaction dates are predicted for the current level by a transaction date prediction model. The quantity forecasting model is used to generate predicted quantity information for the current level for the predicted transaction dates.

公开(公告)号：US10955161B2

公开(公告)日：2021-03-23

申请号：US16264443

申请日：2019-01-31

Applicant: SAP SE

Inventor： Ninad Kulkarni ,  Xuening Wu ,  Sangeetha Krishnamoorthy ,  Mario Ponce ,  Jun Meng ,  Rui Jin ,  Wafaa Sabil ,  Sivakumar N

IPC: F24F11/47 ,  G01W1/10 ,  F24F11/64 ,  F24F11/65 ,  F24F11/77 ,  G05B13/04 ,  F24F140/60 ,  F24F110/10 ,  F24F110/12 ,  F24F120/10 ,  F24F130/10 ,  F24F140/50 ,  F24F11/46

Abstract: Systems and methods are provided for determining a weather forecast corresponding to a location of an air handling unit for a building, generating a foot traffic forecast for a specified time period in the building, and generating a predicted energy consumption curve based on the weather forecast and generated foot traffic forecast for the specified time period. Based on the predicted energy consumption curve, the systems and methods further provide for generating settings for controllable energy devices of the air handling unit to control the air handling unit for the specified time period.