Integrating marker-passing and problem-solving: a spreading-activation approach to improved choice in planning
The berkeley UNIX consultant project
Computational Linguistics
Intelligent interfaces as agents
Intelligent user interfaces
GPS, a program that simulates human thought
Computers & thought
Talking to UNIX in English: an overview of UC
Communications of the ACM
A Computer Model of Skill Acquisition
A Computer Model of Skill Acquisition
Toward A Model Of Children''s Story Comprehension
Toward A Model Of Children''s Story Comprehension
Some Problems and Proposals for Knowledge Representation
Some Problems and Proposals for Knowledge Representation
The metanovel: writing stories by computer.
The metanovel: writing stories by computer.
On knowing what to say: planning speech acts.
On knowing what to say: planning speech acts.
Planning with constraints
Knowledge-based experiment design in molecular genetics
Knowledge-based experiment design in molecular genetics
Planning natural language utterances to satisfy multiple goals
Planning natural language utterances to satisfy multiple goals
Intelligent agents as a basis for natural language interfaces
Intelligent agents as a basis for natural language interfaces
| Hi-index | 0.00 |
Intelligent help systems cannot merely respond passively to the user'scommands and queries. They need to be able to volunteer information,correct user misconceptions, and reject unethical requests when appropriate.In order to do these things, a system must be designed as an intelligentagent. That is, a system needs to have its own goals and then plan forthese goals. A system which did not have its own goals would never refuseto help users perform unethical actions.Such an intelligent agent has been implemented in the UCEgo component of UC(Wilensky et al. 1984; Wilensky et al. 1988) (UNIX Consultant), a natural languagesystem that helps the user solve problems in using the UNIX operatingsystem. UCEgo provides UC with its own goals and plans. By adoptingdifferent goals in different situations, UCEgo creates and executesdifferent plans, enabling it to interact appropriately with the user.UCEgo adopts goals when it notices that the user either lacks necessaryknowledge, or has incorrect beliefs. In these cases, UCEgo plans tovolunteer information or correct the user's misconception as appropriate.These plans are pre-stored skeletal plans that are indexed under the types ofsituations in which they are typically useful. Plan suggestion situationsinclude the goal which the plan is used to achieve, the preconditions of theplan, and appropriateness conditions for the plan. Indexing plans bysituations improves efficiency and allows UC to respond appropriately to theuser in real time.Detecting situations in which a plan should be suggested or a goal adoptedis implemented using if-detected daemons. These daemons provide asingle mechanism which can be used both for detecting goals and suggestingplans. Different methodologies for the efficient implementation ofif-detected daemons are discussed.