公开(公告)号：US20210141865A1

公开(公告)日：2021-05-13

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 Manuel Rodriguez ,  Manju Vijayakumar ,  Vishal Motwani ,  Tian Xie ,  Bryan McCann ,  Nitish Shirish Keskar ,  Armen Abrahamyan ,  Zhihao Zou ,  Chitra Gulabrani ,  Minal Khodani ,  Adarsha Badarinath ,  Rohiniben Thakar ,  Srikanth Kollu ,  Kevin Schoen ,  Qiong Liu ,  Amit Hetawal ,  Kevin Zhang ,  Kevin Zhang ,  Victor Brouk ,  Johnson Liu ,  Rafael Amsili

IPC: G06F17/27 ,  G06N3/08 ,  G06N3/04 ,  H04L12/58

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：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：US10824608B2

公开(公告)日：2020-11-03

申请号：US15884318

申请日：2018-01-30

Applicant: salesforce.com, inc.

Inventor： Yan Yang ,  Karl Ryszard Skucha ,  Marco Vivero ,  Joshua Sauter ,  Kit Pang Szeto ,  Leah McGuire ,  Matvey Tovbin ,  Jean-Marc Soumet ,  Qiong Liu ,  Vlad Patryshev

IPC: G06F16/00 ,  G06F16/22 ,  G06N5/02 ,  H04L29/08 ,  H04L12/24

Abstract: A system may generate a score for a predictive model based on receiving a streaming data flow of events associated with a predictive model for a tenant. The system may receive the streaming data flow and calculate one or more feature values in real time based on the reception. The system may store each of the calculated features to a multi-tenant database server. The system may calculate a score for the predictive model based on the storage and may transmit an indication of the score (e.g., a prediction) based on the calculation. The system may transmit the score to, for example, a computing device.

公开(公告)号：US20190147076A1

公开(公告)日：2019-05-16

申请号：US15884318

申请日：2018-01-30

Applicant: salesforce.com, inc.

Inventor： Yan Yang ,  Karl Ryszard Skucha ,  Marco Vivero ,  Joshua Sauter ,  Kit Pang Szeto ,  Leah McGuire ,  Matvey Tovbin ,  Jean-Marc Soumet ,  Qiong Liu ,  Vlad Patryshev

IPC: G06F17/30 ,  H04L29/08 ,  G06N5/02

Abstract: A system may generate a score for a predictive model based on receiving a streaming data flow of events associated with a predictive model for a tenant. The system may receive the streaming data flow and calculate one or more feature values in real time based on the reception. The system may store each of the calculated features to a multi-tenant database server. The system may calculate a score for the predictive model based on the storage and may transmit an indication of the score (e.g., a prediction) based on the calculation. The system may transmit the score to, for example, a computing device.