Learning Plans for an Intelligent Assistant by Observing User Behavior

Keith R. Levi; Valerie L. Shalin; David L. Perschbacher

doi:10.1016/S0020-7373(05)80049-5

Learning Plans for an Intelligent Assistant by Observing User Behavior

Keith R. Levi
, Valerie L. Shalin
, David L. Perschbacher

Psychology

Research output: Contribution to journal › Article › peer-review

Abstract

A critical requirement of intelligent automated assistants is a representation of actions and goals that is common to both the user and the automated assistant. Updating the intelligent system's knowledge base by observing user behavior is a convenient method for acquiring this common representation. We are developing an explanation based learning system to automate the acquisition of new plans for a large pilot-aiding expert system. We have developed a planning/learning shell that is based on the TWEAK planning system and DeJong's explanation based learning system. We are applying this shell to the pilot-aiding problem in a joint industry/university research effort involving Honeywell, Lockheed, ISX, Search Technology, and the Universities of Illinois and Michigan.

Original language	English
Pages (from-to)	489-503
Number of pages	15
Journal	International Journal of Man-Machine Studies
Volume	33
Issue number	5
DOIs	https://doi.org/10.1016/S0020-7373(05)80049-5 https://doi.org/10.1016/S0020-7373(05)80049-5
State	Published - Nov 1990

ASJC Scopus Subject Areas

General Engineering

Disciplines

Psychology
Social and Behavioral Sciences

Access to Document

Cite this

@article{9df3250d6b484bfe92176d34fc3f428a,

title = "Learning Plans for an Intelligent Assistant by Observing User Behavior",

abstract = " A critical requirement of intelligent automated assistants is a representation of actions and goals that is common to both the user and the automated assistant. Updating the intelligent system's knowledge base by observing user behavior is a convenient method for acquiring this common representation. We are developing an explanation based learning system to automate the acquisition of new plans for a large pilot-aiding expert system. We have developed a planning/learning shell that is based on the TWEAK planning system and DeJong's explanation based learning system. We are applying this shell to the pilot-aiding problem in a joint industry/university research effort involving Honeywell, Lockheed, ISX, Search Technology, and the Universities of Illinois and Michigan.",

author = "Levi, \{Keith R.\} and Shalin, \{Valerie L.\} and Perschbacher, \{David L.\}",

year = "1990",

month = nov,

doi = "10.1016/S0020-7373(05)80049-5",

language = "English",

volume = "33",

pages = "489--503",

journal = "International Journal of Man-Machine Studies",

issn = "0020-7373",

number = "5",

}

TY - JOUR

T1 - Learning Plans for an Intelligent Assistant by Observing User Behavior

AU - Levi, Keith R.

AU - Shalin, Valerie L.

AU - Perschbacher, David L.

PY - 1990/11

Y1 - 1990/11

N2 - A critical requirement of intelligent automated assistants is a representation of actions and goals that is common to both the user and the automated assistant. Updating the intelligent system's knowledge base by observing user behavior is a convenient method for acquiring this common representation. We are developing an explanation based learning system to automate the acquisition of new plans for a large pilot-aiding expert system. We have developed a planning/learning shell that is based on the TWEAK planning system and DeJong's explanation based learning system. We are applying this shell to the pilot-aiding problem in a joint industry/university research effort involving Honeywell, Lockheed, ISX, Search Technology, and the Universities of Illinois and Michigan.

AB - A critical requirement of intelligent automated assistants is a representation of actions and goals that is common to both the user and the automated assistant. Updating the intelligent system's knowledge base by observing user behavior is a convenient method for acquiring this common representation. We are developing an explanation based learning system to automate the acquisition of new plans for a large pilot-aiding expert system. We have developed a planning/learning shell that is based on the TWEAK planning system and DeJong's explanation based learning system. We are applying this shell to the pilot-aiding problem in a joint industry/university research effort involving Honeywell, Lockheed, ISX, Search Technology, and the Universities of Illinois and Michigan.

UR - https://www.scopus.com/pages/publications/0013150376

UR - https://www.scopus.com/pages/publications/0013150376#tab=citedBy

UR - https://corescholar.libraries.wright.edu/psychology/462

U2 - 10.1016/S0020-7373(05)80049-5

DO - 10.1016/S0020-7373(05)80049-5

M3 - Article

SN - 0020-7373

VL - 33

SP - 489

EP - 503

JO - International Journal of Man-Machine Studies

JF - International Journal of Man-Machine Studies

IS - 5

ER -

Learning Plans for an Intelligent Assistant by Observing User Behavior

Abstract

ASJC Scopus Subject Areas

Disciplines

Access to Document

Other files and links

Cite this