The configuration design ontologies and the VT elevator domain theory
International Journal of Human-Computer Studies - Special issue: the Sisyphus-VT initiative
COLLAGEN: A Collaboration Manager for Software Interface Agents
User Modeling and User-Adapted Interaction
Interactive Critiquing forCatalog Navigation in E-Commerce
Artificial Intelligence Review
Proceedings of the IFIP TC5 WG5.2 Fourth Workshop on Knowledge Intensive CAD to Knowledge Intensive Engineering
A Unified Probabilistic Framework for Web Page Scoring Systems
IEEE Transactions on Knowledge and Data Engineering
Domain-Specific Web Search with Keyword Spices
IEEE Transactions on Knowledge and Data Engineering
Personalized Web Search For Improving Retrieval Effectiveness
IEEE Transactions on Knowledge and Data Engineering
Probabilistic Memory-Based Collaborative Filtering
IEEE Transactions on Knowledge and Data Engineering
Ontological user profiling in recommender systems
ACM Transactions on Information Systems (TOIS)
Latent semantic models for collaborative filtering
ACM Transactions on Information Systems (TOIS)
Item-based top-N recommendation algorithms
ACM Transactions on Information Systems (TOIS)
The lumière project: Bayesian user modeling for inferring the goals and needs of software users
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Hi-index | 0.00 |
This paper proposes a design work support system called "push-style guidance system". The system automatically presents some advisory information that helps designers to write technical documents. When the designer adds or revises text on word processor, the text line is immediately sent to the knowledge server with its document structure information, which indicates the location of the text in the document. The server reconstructs the current contents of the document by combining the text lines based on the document structure information. The server analyzes the reconstructed document contents, and evaluates the conformity of preserved guidance generation rules to select appropriate ones. From the selected rules, guidance information is generated and is sent back to the word processor. This enables the simultaneous presentation of information appropriate to the written contents in progress. We have developed a prototype system and evaluated the appropriateness of provided guidance information in a task of writing specifications about electric circuits. Experimental results show that the proposed system performs better than naive systems.