Intelligent dialog re-elicitation of information

Patent metadata

Field	Value
Publication number	US-11275902-B2
Application number	US-201916659216-A
Country	US
Kind code	B2
Filing date	Oct 21, 2019
Priority date	Oct 21, 2019
Publication date	Mar 15, 2022
Grant date	Mar 15, 2022

Abstract

Various embodiments are provided for providing intelligent dialog re-elicitation in a dialog system in a computing environment by a processor. Information, provided during a dialog using the dialog system, may be detected that has been subsequently revised. One or more variables impacted by the revised information provided during the dialog may be dynamically re-elicited.

First claim

What is claimed is:

1. A method, by a processor, for providing intelligent dialog re-elicitation in a dialog system, comprising:
detecting information provided during a dialog using the dialog system has been subsequently revised; and
dynamically re-eliciting one or more variables impacted by the revised information provided during the dialog, wherein dynamically re-eliciting the one or more variables includes estimating an expected number of dialog turns, of at least one communication each between the dialog system and a user, are remaining in the dialog according to the revised information, and estimating a selected number of previous decisions that remain unchanged based on the revised information.

2. The method of claim 1 , further including maintaining a dialog plan or goal of the dialog while dynamically re-eliciting the one or more variables.

3. The method of claim 1 , further including identifying and learning a plurality of dependencies between the one or more variables impacted by the revised information relating to the dialog, a plurality of historical dialogs, or a combination thereof.

4. The method of claim 1 , further including identifying those of the one or more variables impacted by the revised information.

5. The method of claim 1 , further including:
determining a degree of impact upon the one or more variables caused by the revised information; and
confirming or rejecting one or more changes to the one or more variables having the degree of impact less than a defined threshold.

6. The method of claim 1 , further including initializing a machine learning mechanism to learn the one or more variables impacted by the revised information, learn those of the one or more variables to re-elicit, suggest one or more alternative action steps, task, or event to maintain dialog plan or goal of the dialog, or providing one or more simulated dialog turns remaining in the dialog according the revised information.

7. A system, for providing intelligent dialog re-elicitation in a dialog system in a computing environment, comprising:
one or more processors with executable instructions that when executed cause the system to:
detect information provided during a dialog using the dialog system has been subsequently revised; and
dynamically re-elicit one or more variables impacted by the revised information provided during the dialog, wherein dynamically re-eliciting the one or more variables includes estimating an expected number of dialog turns, of at least one communication each between the dialog system and a user, are remaining in the dialog according to the revised information, and estimating a selected number of previous decisions that remain unchanged based on the revised information.

8. The system of claim 7 , wherein the executable instructions maintain a dialog plan or goal of the dialog while dynamically re-eliciting the one or more variables.

9. The system of claim 7 , wherein the executable instructions identify and learn a plurality of dependencies between the one or more variables impacted by the revised information relating to the dialog, a plurality of historical dialogs, or a combination thereof.

10. The system of claim 7 , wherein the executable instructions identify those of the one or more variables impacted by the revised information.

11. The system of claim 7 , wherein the executable instructions:
determine a degree of impact upon the one or more variables caused by the revised information; and
confirm or reject one or more changes to the one or more variables having the degree of impact less than a defined threshold.

12. The system of claim 7 , wherein the executable instructions initialize a machine learning mechanism to learn the one or more variables impacted by the revised information, learn those of the one or more variables to re-elicit, suggest one or more alternative action steps, task, or event to maintain dialog plan or goal of the dialog, or providing one or more simulated dialog turns remaining in the dialog according the revised information.

13. A computer program product for, by one or more processors, providing intelligent dialog re-elicitation in a dialog system in a computing environment, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that detects information provided during a dialog using the dialog system has been subsequently revised; and
an executable portion that dynamically re-elicits one or more variables impacted by the revised information provided during the dialog, wherein dynamically re-eliciting the one or more variables includes estimating an expected number of dialog turns, of at least one communication each between the dialog system and a user, are remaining in the dialog according to the revised information, and estimating a selected number of previous decisions that remain unchanged based on the revised information.

14. The computer program product of claim 13 , further including an executable that maintains a dialog plan or goal of the dialog while dynamically re-eliciting the one or more variables.

15. The computer program product of claim 13 , further including an executable that:
identifies those of the one or more variables impacted by the revised information; and
identifies and learns a plurality of dependencies between the one or more variables impacted by the revised information relating to the dialog, a plurality of historical dialogs, or a combination thereof.

16. The computer program product of claim 13 , further including an executable that:
determines a degree of impact upon the one or more variables caused by the revised information; and
confirms or rejects one or more changes to the one or more variables having the degree of impact less than a defined threshold.

17. The computer program product of claim 13 , further including an executable that initialize a machine learning mechanism to learn the one or more variables impacted by the revised information, learn those of the one or more variables to re-elicit, suggest one or more alternative action steps, task, or event to maintain dialog plan or goal of the dialog, or providing one or more simulated dialog turns remaining in the dialog according the revised information.

Assignees

• IBM

Inventors

• Botea Adi
• Alkan Oznur
• Daly Elizabeth
• Mattetti Massimiliano
• Pedemonte Pablo
• Valente Abel Nicolas
• Vejsbjerg Inge

Classifications

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06F40/35 Primary

  Discourse or dialogue representation · CPC title