公开(公告)号：US10402740B2

公开(公告)日：2019-09-03

申请号：US15223991

申请日：2016-07-29

Applicant: SAP SE

Inventor： Judith Hoetzer ,  Philip Miseldine

IPC: H03M7/30 ,  H04N1/00 ,  G06N7/00 ,  G06N20/00 ,  G06F3/00 ,  G06F17/27 ,  G06Q40/08 ,  G06Q10/10 ,  G06F16/33 ,  G06F3/0484 ,  G06F17/22 ,  G06F3/0482 ,  G06F17/24 ,  G06F3/0488 ,  G06F17/21 ,  G06F3/0483

Abstract: In an example embodiment, first user input including handwriting input and non-alphanumeric symbolic input is detected. The non-alphanumeric symbolic input is input into a first machine learning model trained to output a set of possible actions corresponding to the non-alphanumeric symbolic input and a probability score assigned to each action in the set of possible actions. A combination of the action having the highest probability score and textual input from the handwriting input is input into a second machine learning model trained to select a service from a plurality of services based on the textual input and the selected action by referencing a service model corresponding to each service in the plurality of services. The combination of the textual input and the selected action is transformed into a native request for the selected service based on the service model for the selected service.

公开(公告)号：US20180032505A1

公开(公告)日：2018-02-01

申请号：US15223991

申请日：2016-07-29

Applicant: SAP SE

Inventor： Judith Hoetzer ,  Philip Miseldine

IPC: G06F17/27 ,  G06F3/0488 ,  G06F17/24 ,  G06N99/00 ,  G06N7/00

CPC classification number: G06N7/005 ,  G06F3/00 ,  G06F3/0482 ,  G06F3/0483 ,  G06F3/0484 ,  G06F3/04842 ,  G06F3/04883 ,  G06F3/04886 ,  G06F16/3338 ,  G06F17/211 ,  G06F17/22 ,  G06F17/242 ,  G06F17/243 ,  G06F17/2765 ,  G06F17/277 ,  G06F17/2785 ,  G06N3/0472 ,  G06N20/00 ,  G06Q10/10 ,  G06Q40/08

Abstract: In an example embodiment, first user input including handwriting input and non-alphanumeric symbolic input is detected. The non-alphanumeric symbolic input is input into a first machine learning model trained to output a set of possible actions corresponding to the non-alphanumeric symbolic input and a probability score assigned to each action in the set of possible actions. A combination of the action having the highest probability score and textual input from the handwriting input is input into a second machine learning model trained to select a service from a plurality of services based on the textual input and the selected action by referencing a service model corresponding to each service in the plurality of services. The combination of the textual input and the selected action is transformed into a native request for the selected service based on the service model for the selected service.