AI agents combining natural language interaction, task planning, and business ontologies can help companies provide better-quality and more costeffective customer service. Our customer-service agents use natural language to interact with customers, enabling customers to state their intentions directly instead of searching for the places on the Web site that may address their concern. Our agents converse with customers, guaranteeing that needed information is acquired from customers and that relevant information is provided to them in order for both parties to make the right decision. The net effect is a more frictionless interaction process that improves the customer experience and makes businesses more competitive on the service front.
Human schedulers are typically overburdened by the complexity of this task, and conventional computer-based scheduling systems consider only a small fraction of the relevent knowledge. This article describes research aimed at providing a framework in which all relevant scheduling knowledge can be given consideration during schedule generation and revision. Factory scheduling is cast as a complex constraint-directed activity, driven by a rich symbolic model of the factory environment in which various influencing factors are formalized as constraints. Two knowledge-based factory scheduling systems that implement aspects of this approach are described.
Carnegie-Mellon University has established a Robotics Institute to bring its expertise in engineering, science, and industrial administration to bear upon the problem of national industrial productivity. The institute has been established to undertake advanced research and development in seeing, thinking robots and intelligent systems, and to facilitate transfer of this technology to industry. The Institute is engaged in broad programs of research in robotics, artificial intelligence, manufacturing technology, micro-electronics technology, and computer science. The Institute offers the promise of dramatic advances that will not only improve the productivity of all types of employees but also lead to improvements in the "quality of life" for all.