公开(公告)号：US20250156652A1

公开(公告)日：2025-05-15

申请号：US18508428

申请日：2023-11-14

Applicant: SAP SE

Inventor： Yi Quan Zhou ,  Prawira Putra Fadjar ,  Bee Huang Tan ,  Kham Sian Mung ,  Jing Li

IPC: G06F40/40 ,  G06F11/34

Abstract: Methods, systems, and computer-readable storage media for generating a detection prompt at least partially based on unstructured data determined from one or more of a query entity and a target entity, determining an unstructured data pattern vector that is representative of an output of a LLM that is responsive to the detection prompt, providing a data pattern metric based on the unstructured data pattern vector, generating an explanation prompt at least partially based on the inference result, determining a correctness result that is representative of a correctness of the inference result using explanation text that is generated by the LLM, in response to determining that there is a threshold decrease in accuracy at least partially based on the correctness result, automatically executing one of fine-tuning of the ML model and re-training of the ML model to provide an adapted ML model.

公开(公告)号：US11281989B2

公开(公告)日：2022-03-22

申请号：US15451428

申请日：2017-03-07

Applicant: SAP SE

Inventor： Daniel Hermann Richard Dahlmeier ,  Ruidan He ,  Wenya Wang ,  Kham Sian Mung ,  Mohamed Yusuf Abdul Gafoor ,  Yi Qing Isaac New ,  Weile Chen ,  Hang Guo ,  Haodan Yang ,  Abraham Sasmito Adibowo

IPC: G06N20/00 ,  G06Q10/06 ,  G06Q30/02

Abstract: Described herein is a machine learning framework for facilitating engagements. In accordance with one aspect of the framework, a machine learning model is trained based on the training data. A recommendation associated with an opportunity record may then be generated using the trained machine learning model. Results of one or more actions performed in response to the recommendation may be collected and fed back to the machine learning model to be used as the training data.