公开(公告)号：US20250086402A1

公开(公告)日：2025-03-13

申请号：US18415308

申请日：2024-01-17

Applicant: Salesforce, Inc.

Inventor： Ran Xu ,  Zeyuan Chen ,  Yihao Feng ,  Krithika Ramakrishnan ,  Congying Xia ,  Juan Carlos Niebles Duque ,  Vetter Serdikova ,  Huan Wang ,  Yuxi Zhang ,  Kexin Xie ,  Donglin Hu ,  Bo Wang ,  Ajaay Ravi ,  Matthew David Trepina ,  Sam Bailey ,  Abhishek Das ,  Yuliya Feldman ,  Pawan Agarwal

IPC: G06F40/40 ,  G06F9/451 ,  G06F9/50 ,  G06T11/00

Abstract: Methods, systems, apparatuses, devices, and computer program products are described. A flow generation service may receive a natural language input that indicates instructions for automating a task according to a first process flow. Using a large language model (LLM), the flow generation service may decompose the natural language input into a set of elements (e.g., logical actions) and connectors, where the LLM may be trained on first metadata corresponding to a second process flow that is created manually by a user. In addition, using the LLM, the flow generation service may generate second metadata corresponding to each of the set of elements based on decomposing the natural language input. The flow generation service may sequence and merge the set of elements to generate the first process flow. In some examples, the flow generation service may send, for display to a user interface of a user device, the first process flow.

公开(公告)号：US20240046115A1

公开(公告)日：2024-02-08

申请号：US17883503

申请日：2022-08-08

Applicant: Salesforce, Inc.

Inventor： Donglin Hu ,  Yuxi Zhang ,  Kexin Xie ,  Chen Xu

IPC: G06N5/02 ,  G06Q30/02

CPC classification number: G06N5/022 ,  G06Q30/0241

Abstract: A prediction system of an online system deploys one or more machine-learned architectures to generate predictions. In one embodiment, the machine-learned architecture is a stacked ensemble model. The stacked ensemble model includes a plurality of base models, where a base model is coupled to receive input data and generate a base prediction for the input data. The stacked ensemble model includes a meta model that combines the base predictions to generate a meta prediction for the input data. The prediction system also generates a reliability measure that takes advantage of the base predictions to evaluate the reliability of the meta prediction. In this manner, while the quality of individual predictions may differ from one another depending on the values of the input data, the prediction system can dynamically generate the reliability measure to account for this variation.

公开(公告)号：US12051008B2

公开(公告)日：2024-07-30

申请号：US17883503

申请日：2022-08-08

Applicant: Salesforce, Inc.

Inventor： Donglin Hu ,  Yuxi Zhang ,  Kexin Xie ,  Chen Xu

IPC: G06N5/022 ,  G06Q30/0241

CPC classification number: G06N5/022 ,  G06Q30/0241

Abstract: A prediction system of an online system deploys one or more machine-learned architectures to generate predictions. In one embodiment, the machine-learned architecture is a stacked ensemble model. The stacked ensemble model includes a plurality of base models, where a base model is coupled to receive input data and generate a base prediction for the input data. The stacked ensemble model includes a meta model that combines the base predictions to generate a meta prediction for the input data. The prediction system also generates a reliability measure that takes advantage of the base predictions to evaluate the reliability of the meta prediction. In this manner, while the quality of individual predictions may differ from one another depending on the values of the input data, the prediction system can dynamically generate the reliability measure to account for this variation.