Date of Publication :13th February 2018
Abstract: Human-computer support desk plays an important role in dynamic trading online, especially in B2C ecommerce. Further scientific investigations about designing the software agent that can deal with the human’s random and inconsistent offer are in need, which is crucially useful for the online merchants to achieve better trading outcomes and save vast trading cost. The lack of such studies has decelerated the process of applying automated support desk to real world applications. To address the critical issue, this paper develops a strategy model. To demonstrate the effectiveness of this model, we develop a prototype and conduct human-computer support desk experiments over 121 participants. The experimental result shows that the agent with our newly designed strategy model can significantly increase the agreement rate and joint outcome of the both sides, and even can outperform human negotiators. In order to develop a negotiating agent that has the ability to negotiate with human, it is of vital importance to elucidate how to design a negotiation strategy model to guide the agent’s concession in the process of negotiation. A negotiation strategy is a decision-making model used by the participants to persuade the opponent towards the outcome they desire. There are two major approaches to design the strategy, the heuristic-based approach and the machine learning approach. However, several important dimensions have received limited attention in existing research of negotiation strategies. Firstly, past studies primarily focus on computer-computer automated negotiation, while relatively few studies have been carried out in assessing the potential of human-computer support desk. None can ignore the fact that the computer simulating negotiation environment is quite different with the negotiation that has human participating in, but systematic design and evaluation of agent strategies that incorporate a human counterpart’s perspective is lacking. Secondly, a negotiation strategy is essentially a concession model that defines the utility decreasing sequence of offers
Reference :
-
- Md. Shahriare Satu; Md. Hasnat Parvez; Shamim-AlMamun (2015). "Review of integrated applications with AIML based chatbot".2015 International Conference on Computer and Information Engineering (ICCIE), 87 - 90, DOI: 10.1109/CCIE.2015.7399324
- Abu Shawar B and Atwell E, “Machine learning from dialogue corpora to generate chatbots “, 2003.
- A.L.I.C.E Artificial Intelligence Foundation”[Online].http://alice.pandorabots.com
- Philip C Jackson - Introduction to Artificial Intelligence
- Ray Kurzweil - How to Create a Mind: The Secret of Human Thought Revealed
- Microsoft.com-https: //www.microsoft.com/en-us /AI /references-for-developers