US 11,455,547 B1Granted

Distributed industrial virtual assistant platform

AssigneeTeamsolve Pte. Ltd

InventorsAmitsur Preis, Michael Peter Allen, Muhammad Mudasser Iqbal, Wong Loo Ping Robin

Life of this patent

Estimating the term…

Loading patent…

Abstract

A distributed Industrial Virtual Assistant (IVA) platform and method that that allows operational staff at industrial facilities to have natural language conversations with an IVA to obtain information about, and to control operations of, industrial facilities. For each facility, the IVA platform contains a facilities asset database, one or more domain-specific knowledge databases, a natural language processing engine, and machine learning algorithms for both knowledge domains and context which update the domain-specific knowledge databases based on continuing interactions with operational staff over time. The IVA platform is capable of generating user-specific and device-specific IVA instances that can be queried by voice or text independently of the platform but can connect to the platform to update the databases based on new knowledge, exceptions, and incidents.

Claims10

Dependent claims

A distributed industrial virtual assistant platform, comprising:

a first computing device comprising a memory, a processor, and a non-volatile data storage device;
a facilities database stored on the non-volatile data storage device and comprising a list of equipment at an industrial facility;
a domain-specific knowledge database stored on the non-volatile data storage device and comprising terminology and a plurality of rules for a plurality of knowledge domains related to the industrial facility;
a communications manager comprising a second plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive a query from a user in voice or text form related to the industrial facility;
if in voice form, convert the communication to text form using a speech-to-text algorithm of a natural language processing engine;
parse the text of the communication using the natural language processing algorithm to identify key words and phrases;
send the parsed text to an industrial virtual assistant manager;
receive a notification from the industrial virtual assistant manager that a trigger has been met;
and
formulate a voice or text response to the second computing device using the natural language processing algorithm;
and
communicate the response to the user;
an industrial virtual assistant manager comprising a second plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive the parsed text from the communications manager;
request identification of a piece of equipment and a rule from a domain expertise manager;
set a threshold or trigger for the piece of equipment based on the rule;
monitor data from the piece of equipment;
and
notify the communications manager when the threshold or trigger is met;
and
a domain expertise manager comprising a third plurality of programming instructions stored in the memory which, when operating on the processor, causes the computer system to:
receive the request for identification from the industrial virtual assistant manager;
search the facilities database for the piece of equipment responsive to the request;
search the domain-specific knowledge database for the rule responsive to the request;
and
send the piece of equipment identification and the rule to the industrial virtual assistant manager.

24 more elements

A method for operating a distributed industrial virtual assistant, comprising the steps of:

a facilities database stored on the non-volatile data storage device and comprising a list of equipment at an industrial facility;
a domain-specific knowledge database stored on the non-volatile data storage device and comprising terminology and a plurality of rules for a plurality of knowledge domains related to the industrial facility;
using a communications manager operating on a computing device comprising a memory, a processor, and a non-volatile data storage device to:
receive a query from a user in voice or text form related to an industrial facility;
if in voice form, convert the communication to text form using a speech-to-text algorithm of a natural language processing engine;
parse the text of the communication using the natural language processing algorithm to identify key words and phrases;
send the parsed text to an industrial virtual assistant manager operating on the computing device;
receive a notification from the industrial virtual assistant manager that a trigger has been met;
and
formulate a voice or text response to the second computing device using the natural language processing algorithm;
and
communicate the response to the user;
using the industrial virtual assistant manager to:
receive the parsed text from the communications manager;
request identification of a piece of equipment and a rule from a domain expertise manager operating on the computing device;
set a threshold or trigger for the piece of equipment based on the rule;
monitor data from the piece of equipment;
and
notify the communications manager when the threshold or trigger is met;
and
using the domain expertise manager to:
receive the request for identification from the industrial virtual assistant manager;
search a facilities database stored on the non-volatile data storage device and comprising a list of equipment at an industrial facility for the piece of equipment responsive to the request;
search a domain-specific knowledge database stored on the non-volatile data storage device and comprising terminology and a plurality of rules for a plurality of knowledge domains related to the industrial facility for the rule responsive to the request;
and
send the piece of equipment identification and the rule to the industrial virtual assistant manager.

23 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/700,407Filed 21 Mar 2022 · us provisional application
Priority: 7 Feb 2022
Granted: 27 Sep 2022
Term ends: Not estimatedThe source records don’t support an estimate.

Classification15 codes

G06N 5/022
Knowledge representation; Symbolic representation: knowledge engineering; Knowledge acquisition
G06N 20/00
Machine learning
G05B 19/418
Electric: total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible…
G06F 9/453
Execution arrangements for user interfaces: help systems