This paper analyzes conversation models of human salesclerks interacting with customers. The goal of a salesclerk is to effectively match a customer's buying points and a product's selling points. To achieve this, the salesclerk alternates among asking questions, proposing sample goods, and observing the customer's responses. Based on this analysis, we developed ExpertClerk, an agent system that imitates a human salesclerk and navigates Web shoppers in merchandise databases. In the system, a character agent talks with a shopper in a natural language and consolidates the shopper's request by narrowing down a list of many matching goods by asking effective questions using entropy (Navigation by Asking). Then, it shows three contrasting samples with explanations of their selling points (Navigation by Proposing). This cycle is repeated until the shopper finds an appropriate good. Evaluations show that the combination of Navigation by asking and Navigation by proposing works as most effectively as human salesclerks.
展开▼
