IP Library › Granted Patent US 10,685,655
Granted Patent B2
US 10,685,655 · App. 15/913,977 · Granted Jun 16, 2020

Leveraging natural language processing

Inventors: Allen Ginsberg (St. Petersburg, FL); Charles E. Beller (Baltimore, MD); Chengmin Ding (Chantilly, VA); Elinna Shek (Herndon, VA)
Assignee: International Business Machines Corporation
G10L15/24G06F40/35G06N5/02G10L15/10G10L15/12G10L15/22G10L25/48
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 10,685,655
App. No.
15/913,977
Granted
Jun 16, 2020
Kind
B2
Abstract

A system, computer program product, and method are provided to automate a natural language processing system to facilitate an artificial intelligence platform defining a relationship between dialogue and post dialogue activity. Dialogue is detected and analyzed, including identification of key words and phrases within the dialogue. Post dialogue actions, including physical actuation of a hardware device and an associated temporal proximity of the action and the dialogue, are monitored. The hardware device receives an instruction from a processing unit that relates to the analyzed dialogue and the hardware device changes states and/or actuates another hardware device. The system constructs a hypothesis, i.e., a relationship from the identified key phrase drawn from the analyzed dialogue and the monitored post action dialogue. A dialogue tree containing identified terms and associated post dialogue actions is dynamically modified with one or more new identified terms and the associated post dialogue actions.

Claims (35)

1. A computer system comprising:

a processing unit operatively coupled to memory;

an artificial intelligence (AI) platform, in communication with the processing unit and memory, the AI platform comprising:

a natural language processing (NLP) dialogue monitor to detect dialogue data and analyze the detected dialogue data, including identification of a term within the detected dialogue data;

a dialogue engine operatively coupled to the NLP dialogue monitor, the dialogue engine to monitor a post dialogue action, including physical actuation of a hardware device and proximity of the actuation to the detected dialogue data;

an analysis engine operatively coupled to the dialogue engine and the NLP dialogue monitor, the analysis engine to construct a relationship from an identified key phrase drawn from the analyzed dialogue data and the monitored post dialogue action;

the analysis engine to evaluate a re-occurrence of the identified term in a first dialogue and a second dialogue, and to apply a weight to the identified term, wherein the weight reflects prominence of the identified term; and

a search engine, operatively coupled to the analysis engine, to dynamically modify a dialogue tree responsive to the applied weight, including addition of a new entry into the dialogue tree, the new entry including the identified term and the post dialogue action; and

the hardware device operatively coupled to the dialogue engine, the hardware device to receive an instruction related to the analyzed dialogue data, wherein receipt of the instruction causes a physical action comprising the hardware device to change states, actuation of a second hardware device, or combinations thereof.

2. The system of claim 1 , further comprising the dialogue engine to detect non-verbal data and apply the detected non-verbal data to the identified term and post dialogue action.

3. The system of claim 2 , further comprising the NLP dialogue monitor to evaluate proximity of occurrence of the identified term to the detected non-verbal data.

4. The system of claim 2 , further comprising the dialogue engine to detect a response to the post dialogue action, and to classify the detected response with the new entry in the dialogue tree.

5. The system of claim 1 , wherein the dynamic modification of the dialogue tree is a confirmation of an association between the identified term and the post dialogue action.

6. A computer program product to process natural language (NL), the computer program product comprising a computer readable storage device having program code embodied therewith, the program code executable by a processing unit to:

leverage a natural language processing (NLP) dialogue monitor to detect dialogue data and analyze the detected dialogue data, including identification of a term within the detected dialogue data;

monitor a post dialogue action, including physical actuation of a hardware device and proximity of the actuation to the detected dialogue data;

construct a hypothesis from an identified key phrase drawn from the analyzed dialogue data and the monitored post dialogue action;

evaluate a re-occurrence of the identified term in a first dialogue and a second dialogue, and apply a weight to the identified term, wherein the weight reflects prominence of the identified term;

dynamically modify a dialogue tree responsive to the applied weight, including addition of a new entry into the dialogue tree, the new entry including the identified term and the post dialogue action; and

the hardware device operatively coupled to the processing unit, the hardware device to receive an instruction related to the analyzed dialogue data, wherein receipt of the instruction causes a physical action comprising the hardware device to change states, actuation of a second hardware device, or combinations thereof.

7. The computer program product of claim 6 , further comprising program code to detect non-verbal data and apply the detected non-verbal data to the identified term and post dialogue action.

8. The computer program product of claim 7 , further comprising program code to evaluate proximity of occurrence of the identified term to the detected non-verbal data.

9. The computer program product of claim 7 , further comprising program code to detect a response to the post dialogue action, and to classify the detected response with the new entry in the dialogue tree.

10. The computer program product of claim 6 , wherein the dynamic modification of the dialogue tree is a confirmation of an association between the identified term and the post dialogue action.

11. A method for processing natural language (NL), comprising:

detecting dialogue data and analyzing the detected dialogue data, including identification of a term within the detected dialogue data;

monitoring a post dialogue action, including physical actuation of a hardware device and proximity of the actuation to the detected dialogue data;

constructing a hypothesis from an identified key phrase drawn from the analyzed dialogue and the monitored post dialogue action;

evaluating a re-occurrence of the identified term in a first dialogue and a second dialogue, and applying a weight to the identified term, wherein the weight reflects prominence of the identified term;

dynamically modifying a dialogue tree responsive to the applied weight, including addition of a new entry into the dialogue tree, the new entry including the identified term and the post dialogue action; and

a hardware device operatively coupled to the processing unit, the hardware device to receiving an instruction related to the analyzed dialogue data, wherein receipt of the instruction causing a physical action comprising the hardware device to change states, actuation of a second hardware device, or combinations thereof.

12. The method of claim 11 , further comprising detecting non-verbal data and applying the detected non-verbal data to the identified term and post dialogue action.

13. The method of claim 12 , further comprising evaluating proximity of occurrence of the identified term to the detected non-verbal data.

14. The method of claim 12 , further comprising detecting a response to the post dialogue action, and classifying the detected response with the new entry in the dialogue tree.

15. The method of claim 11 , wherein the dynamic modification of the dialogue tree is a confirmation of an association between the identified term and the post dialogue action.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 7, 2018
From: GINSBERG, ALLEN; BELLER, CHARLES E.; DING, CHENGMIN; SHEK, ELINNA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 045128/0168 →
Continuity (1)
Related Publication 20190279639A1 · Sep 12, 2019
Cited By (1)
US 12,651,595