Manju Vijayakumar

US Patent:

20210141865, May 13, 2021

Filed:

Nov 11, 2019

Appl. No.:

16/680323

Inventors:

- San Francisco CA, US
James Douglas Harrison - Mill Valley CA, US
Caiming Xiong - Menlo Park CA, US
Xinyi Yang - San Francisco CA, US
Thomas Archie Cook - Boulder CO, US
Roojuta Lalani - Fremont CA, US
Jean-Marc Soumet - San Jose CA, US
Karl Ryszard Skucha - Los Altos CA, US
Juan Manuel Rodriguez - Mountain View CA, US
Manju Vijayakumar - Pleasanton CA, US
Vishal Motwani - Palo Alto CA, US
Tian Xie - Palo Alto CA, US
Bryan McCann - Menlo Park CA, US
Nitish Shirish Keskar - San Francisco CA, US
Armen Abrahamyan - Alameda CA, US
Zhihao Zou - Foster City CA, US
Chitra Gulabrani - Palo Alto CA, US
Minal Khodani - Foster City CA, US
Adarsha Badarinath - Fremont CA, US
Rohiniben Thakar - Newark CA, US
Srikanth Kollu - Pleasanton CA, US
Kevin Schoen - Bothell WA, US
Qiong Liu - Cupertino CA, US
Amit Hetawal - San Ramon CA, US
Kevin Zhang - San Francisco CA, US
Kevin Zhang - Alameda CA, US
Victor Brouk - San Francisco CA, US
Johnson Liu - Santa Clara CA, US
Rafael Amsili - Mountain View CA, US

International Classification:

G06F 17/27
G06N 3/08
G06N 3/04
H04L 12/58

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.

US Patent:

20200089757, Mar 19, 2020

Filed:

Sep 18, 2018

Appl. No.:

16/134956

Inventors:

- San Francisco CA, US
John BALL - San Francisco CA, US
Shashank HARINATH - San Francisco CA, US
Roojuta LALANI - Fremont CA, US
Zineb LARAKI - San Francisco CA, US
Qingqing LIU - San Francisco CA, US
Mike ROSENBAUM - San Francisco CA, US
Karl Ryszard SKUCHA - Sunnyvale CA, US
Jean-Marc SOUMET - San Jose CA, US
Manju VIJAYAKUMAR - Pleasanton CA, US

International Classification:

G06F 17/27
G06F 17/30
G10L 15/22
G10L 15/18

Abstract:

Approaches to using unstructured input to update heterogeneous data stores include receiving unstructured text input, receiving a template for interpreting the unstructured text input, identifying, using an entity classifier, entities in the unstructured text input, identifying one or more potential parent entities from the identified entities based on the template, receiving a selection of a parent entity from the one or more potential parent entities, identifying one or more potential child entities from the identified entities based on the template and the selected parent entity, receiving a selection of a child entity from the one or more potential child entities, identifying an action item in the unstructured text input based on the identified entities and the template, determining, using an intent classifier, an intent of the action item, and updating a data store based on the determined intent, the identified entities, and the selected child entity.