公开(公告)号：US11769013B2

公开(公告)日：2023-09-26

申请号：US16680323

申请日：2019-11-11

Applicant: salesforce.com, inc.

Inventor： Michael Machado ,  James Douglas Harrison ,  Caiming Xiong ,  Xinyi Yang ,  Thomas Archie Cook ,  Roojuta Lalani ,  Jean-Marc Soumet ,  Karl Ryszard Skucha ,  Juan Rodriguez ,  Manju Vijayakumar ,  Vishal Motwani ,  Tian Xie ,  Bryan McCann ,  Nitish Shirish Keskar ,  Zhihao Zou ,  Chitra Gulabrani ,  Minal Khodani ,  Adarsha Badarinath ,  Rohiniben Thakar ,  Srikanth Kollu ,  Kevin Schoen ,  Qiong Liu ,  Amit Hetawal ,  Kevin Zhang ,  Kevin Zhang ,  Johnson Liu ,  Rafael Amsili

IPC: G10L15/16 ,  G06F40/30 ,  G06N3/08 ,  H04L51/02 ,  G06N3/04 ,  G06F40/295

CPC classification number: G06F40/30 ,  G06F40/295 ,  G06N3/04 ,  G06N3/08 ,  H04L51/02

Abstract: A multi-tenant system performs custom configuration of a tenant-specific chatbot to process and act upon natural language requests. The multi-tenant system configures the tenant-specific chatbots without requiring tenant-specific training. The multi-tenant system providing a user interface for configuring a tenant-specific set of permitted actions. The multi-tenant system determines a set of example phrases for each of the selected permitted actions. The multi-tenant system receives a natural language request from a user and identifies the action that the user wants to perform. The multi-tenant system uses a neural network to compare the natural language request with example phrases to identify an example phrase that matches the natural language request. The multi-tenant system performs the action corresponding to the matching example phrase.

公开(公告)号：US12057116B2

公开(公告)日：2024-08-06

申请号：US17162007

申请日：2021-01-29

Applicant: salesforce.com, inc.

Inventor： Juan Rodriguez ,  Michael Machado

IPC: G10L15/22 ,  G06F9/451 ,  G10L15/26 ,  G10L15/32

CPC classification number: G10L15/22 ,  G06F9/453 ,  G10L15/26 ,  G10L15/32 ,  G10L2015/223

Abstract: The present disclosure is directed techniques for executing a task or service using a virtual agent. A method includes: executing, using a virtual agent, one or more tiers of a plurality of tiers of machine learning analysis to identify a desired action to be performed based on a user command, the user command being received from an external computing device; responsive to the one or more tiers of the plurality of tiers of machine learning analysis identifying a plurality of actions associated with the user command, determining a series of inquiries to present via the external computing device, wherein each inquiry of the series of inquiries is selected based on a number of actions associated with each inquiry, and wherein each subsequent inquiry in the series of inquires is based on a user response to a preceding inquiry; identifying, based on responses to the series of inquiries, the desired action to be performed; and executing the desired action to be performed.