IP Library Granted Patent US 10,474,703
Granted Patent B2
US 10,474,703 · App. 15/629,203 · Granted Nov 12, 2019

Method and apparatus for natural language query in a workspace analytics system

Inventors: Edward S. Wegryn (Ann Arbor, MI); Lawrence J. Birk (Ann Arbor, MI); Christopher Dyer (Ann Arbor, MI); Kenneth M. Schumacher (Orchard Lake, MI)
Assignee: Lakeside Software, Inc.
G06F16/3338G06F16/243G06F16/3323G06F16/3329G06F16/3344G06F16/90344G06F16/951G06F17/278G06F17/2795
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,474,703
App. No.
15/629,203
Granted
Nov 12, 2019
Kind
B2
Abstract

A method includes associating, for each one of a plurality of answer definitions, at least one or more pattern-form questions, wherein each answer definition has an associated jump target that defines a respective entry point into the workspace analytics system to provide information responsive to the associated one or more pattern-form questions. The method further includes receiving a user input including capturing input text defining a natural language user query, matching the received input text to one of the pattern-form questions thereby selecting the jump target associated with the matched pattern-form question, and generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link based on the selected jump target and zero or more parameters values.

Claims (27)

1. A computer-implemented method for providing a natural language interface to process user queries for information managed in a workspace analytics system, comprising:

receiving a user input from a user including capturing input text, wherein the input text defines a natural language user query;

matching the received input text to one of a plurality of predefined pattern-form questions defined in and using a first, local entity matcher executing in a first computer at a first location, wherein the matching is further performed in and using a second, cloud entity matcher executing in a second computer at a second location when the first local entity matcher does not find a match having a confidence level exceeding a predetermined threshold, wherein said matching step is performed by using a third, external entity matcher when neither the first, local entity matcher nor the second, cloud entity matcher finds a match having a confidence level exceeding the predetermined threshold, and wherein before using either the second entity matcher or third entity matcher, detecting an entity contained in the user input text and replacing the text corresponding to the detected entity with a neutralized, generic marker;

selecting a jump target that is associated with the matched pattern-form question;

generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link that is based on at least the selected jump target.

2. The method of claim 1 wherein the workspace analytics system has associated therewith a first extent of known entities, said method further comprising identifying, in the captured user input text, at least one entity in the first extent of known entities, using the first, local entity matcher.

3. The method of claim 2 further comprising

providing a graphical user interface (GUI) on a first portion of a display visible to the user where the graphical user interface is configured to acquire a speech input from the user which is converted to the user input text;

correcting the converted user input text based on, at least in part, the first extent of known entities associated with the workspace analytics system.

4. The method of claim 1 wherein one or more matches provided by said second, cloud entity matcher pertain to upgrade features available for said workspace analytics system.

5. The method of claim 4 wherein said second, cloud entity matcher is configured with at least one of a matcher definition and an answer definition associated with said upgrade features.

6. The method of claim 4 wherein providing one or more matches by said second, cloud entity matcher further comprises providing a link to information associated with said upgrade feature.

7. The method of claim 6 wherein said information comprises a mechanism for allowing a user to purchase said upgrade feature.

8. The method of claim 1 further comprising associating, for each one of a plurality of answer definitions, at least one or more of the pattern-form questions, wherein each answer definition has an associated jump target that defines a respective entry point into the workspace analytics system to provide information responsive to the associated one or more pattern-form questions.

9. The method of claim 1 wherein said first location and said second location are the same.

10. The method of claim 1 wherein said first location and said second location are different, said second location being remote from said first location.

11. A computer-implemented method for providing a natural language interface to process user queries for information managed in a workspace analytics system, comprising:

receiving a user input from a user including capturing input text, wherein the input text defines a natural language user query;

matching the received input text to one of a plurality of predefined pattern-form questions defined in and using a first, local entity matcher executing in a first computer at a first location, wherein the matching is further performed in and using a second, cloud entity matcher executing in a second computer at a second location when the first local entity matcher does not find a match having a confidence level exceeding a predetermined threshold;

selecting a jump target that is associated with the matched pattern-form question;

generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link that is based on at least the selected jump target, wherein the workspace analytics system has associated therewith a first extent of known entities, said method further comprising identifying, in the captured user input text, at least one entity in the first extent of known entities, using the first, local entity matcher, said method further comprising establishing the first extent of known entities in the workspace analytics system includes defining one or more matcher definitions wherein each matcher definition is associated with an entity type, and retrieving from the workspace analytics system, for each matcher definition, a respective set of values for the entity type.

12. The method of claim 11 further comprising providing a configuration file containing the one or more matcher definitions.

13. A computer-implemented method for providing a natural language interface to process user queries for information managed in a workspace analytics system, comprising:

receiving a user input from a user including capturing input text, wherein the input text defines a natural language user query;

matching the received input text to one of a plurality of predefined pattern-form questions defined in and using a first, local entity matcher executing in a first computer at a first location, wherein the matching is further performed in and using a second, cloud entity matcher executing in a second computer at a second location when the first local entity matcher does not find a match having a confidence level exceeding a predetermined threshold;

selecting a jump target that is associated with the matched pattern-form question;

generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link that is based on at least the selected jump target said method further comprising detecting an entity contained in the user input text and replacing the text corresponding to the detected entity with a neutralized, generic marker.

Assignments (3)
SECURITY INTEREST Recorded Feb 28, 2025
From: LAKESIDE SOFTWARE
To: FIRST-CITIZENS BANK & TRUST COMPANY
Reel/Frame 070363/0243 →
CERTIFICATE OF CONVERSION Recorded Sep 3, 2020
From: LAKESIDE SOFTWARE, INC.
To: LAKESIDE SOFTWARE, LLC
Reel/Frame 053688/0373 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 21, 2017
From: WEGRYN, EDWARD S.; BIRK, LAWRENCE J.; DYER, CHRISTOPHER; SCHUMACHER, KENNETH M.
To: LAKESIDE SOFTWARE, INC.
Reel/Frame 042938/0894 →
Continuity (2)
Provisional Application 62379708 · Aug 25, 2016
Related Publication 20180060420A1 · Mar 1, 2018