ExpertClerk: A conversational case-based reasoning tool for developing salesclerk agents in e-commerce webshops. Shimazu, H. Artificial Intelligence Review, 18(3-4):223-244, 2002.
abstract   bibtex   
Conversational Case-based Reasoning (CCBR) has been used successfully to improve knowledge management in corporate activities as a problem solver. In our past research, we developed CCBR systems in customer support domains where CCBR systems played the role of customer support agents. Based on these experiences, we have applied the same CCBR technologies to design the user-interface of e-commerce websites. ExpertClerk was designed as a tool for developing dialogue-based front-end systems for product databases. We first analyzed 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 between asking questions, proposing sample products, and observing the customer’s responses. ExpertClerk imitates a human salesclerk. It consolidates the human shopper’s requests by narrowing down a list of many products through a process of asking effective questions using entropy (navigation-by-asking) and showing contrasting samples with an explanation of their selling points (navigation-by-proposing). This request elaboration cycle is repeated until the shopper finds an appropriate product. In this article, we present the system architecture, algorithms as well as empirical evaluations.
@article{
 title = {ExpertClerk: A conversational case-based reasoning tool for developing salesclerk agents in e-commerce webshops},
 type = {article},
 year = {2002},
 identifiers = {[object Object]},
 keywords = {Agent,Conversational case-based reasoning,Dialogue management,E-commerce},
 pages = {223-244},
 volume = {18},
 id = {8b577177-9ddc-30db-bed0-ae96245ecf35},
 created = {2018-09-05T07:25:06.079Z},
 file_attached = {false},
 profile_id = {2ed0fe69-06a2-3e8b-9bc9-5bdb197f1120},
 group_id = {e795dbfa-5576-3499-9c01-6574f19bf7aa},
 last_modified = {2018-12-14T12:16:31.072Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Shimazu2002},
 private_publication = {false},
 abstract = {Conversational Case-based Reasoning (CCBR) has been used successfully to improve knowledge management in corporate activities as a problem solver. In our past research, we developed CCBR systems in customer support domains where CCBR systems played the role of customer support agents. Based on these experiences, we have applied the same CCBR technologies to design the user-interface of e-commerce websites. ExpertClerk was designed as a tool for developing dialogue-based front-end systems for product databases. We first analyzed 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 between asking questions, proposing sample products, and observing the customer’s responses. ExpertClerk imitates a human salesclerk. It consolidates the human shopper’s requests by narrowing down a list of many products through a process of asking effective questions using entropy (navigation-by-asking) and showing contrasting samples with an explanation of their selling points (navigation-by-proposing). This request elaboration cycle is repeated until the shopper finds an appropriate product. In this article, we present the system architecture, algorithms as well as empirical evaluations. },
 bibtype = {article},
 author = {Shimazu, Hideo},
 journal = {Artificial Intelligence Review},
 number = {3-4}
}
Downloads: 0