Intelligent Negotiation Technology

Technologies For Supporting Reasoning Communities and Collaborative Decision Making Cooperative Approaches, 2010

One of the major concerns raised by people using negotiation processes is about the fairness or justice of the process. Individuals undertake negotiation to derive better outcomes than would otherwise occur, which requires them to engage in interest-based negotiation. But interest-based negotiation focuses upon the interests of the disputants rather than any objective legal measures of "fairness" -that is, legal justness, not the more commonly accepted negotiation concept of meeting the interests of all parties equally. It is vital to investigate how to develop measures, or at the very least principles, for the construction of legally just negotiation support systems. This article discusses processes that, when applied, will encourage fairness and justice in the development of negotiation support systems. Such processes include providing enhanced transparency, supporting bargaining in the shadow of the law, and allowing for limited discovery.

2009

Electronic business negotiations are enabled by different electronic negotiation models: automated negotiation models for software agents, negotiation support models for human negotiators, and auction models for both. To date, there is no electronic negotiation model that enables bilateral multi-issue negotiations between a human negotiator and a negotiation agent-an important task in electronic negotiation research. In this thesis, a model is presented that integrates the automated negotiation model and the negotiation support model. The resulting hybrid negotiation model paves the way for human-agent business negotiations. The integration of two models is realised at the levels of negotiation process, communication support and decision making. To this end, the negotiation design, negotiation process, negotiation decision making, and negotiation communication in negotiation support systems (NSSs) and agent negotiation systems (ANSs) are studied and analysed. The analyses on these points help in strengthening the motivation behind hybrid negotiation model and setting aims for the integration of an NSS and an ANS in hybrid negotiation model. We mainly propose a human-agent negotiation design, negotiation process protocols to support the design, a hybrid communication model for human-agent interaction, an agent decision-making model for negotiation with human, and a component for interoperability between NSS and ANS. The agent decision-making model is composed of heuristic and argumentationbased negotiation techniques. It is proposed after analysing different automated negotiation models for different human negotiation strategies. The proposed communication model supports human negotiator and negotiation agent to understand and process negotiation messages from each other. This communication model consists of negotiation ontology, a wrapper agent, and a proper selection of an agent communication language (ACL) and a content language. The wrapper agent plays a role for interoperability between agent system and NSS by providing a communication interface along with the negotiation ontology. The negotiation ontology, ACL and agent content language make the communication model of negotiation agent in ANS. The proposed hybrid model is realised by integrating an ANS into NSS Negoisst. The research aim is to 1.2.2 Hybrid Communication Model and Agent Communication Model Communication is an essential part of a negotiation process and it is about exchanging negotiation messages between negotiators. With a hybrid (human-agent) communication model for human-agent negotiation, our aim is to bridge the gap between the communication models of Negoisst and ANS in order to enable two different communicatory entities to communicate their negotiation stance to each other. A communication model in any negotiation system normally defines the structure of negotiation messages and the representation and semantics of contents in messages. The hybrid communication model must thus be based on a thorough analysis of the negotiation communication behaviour and the structure of negotiation messages in NSSs and ANSs. A communication behaviour in a negotiation message can be represented through an offer containing negotiation issues' values with or without text representing the arguments, queries about product or service, clarifications about some negotiation matter, greetings etc. The structure of a negotiation message in NSSs and ANSs is

2002

This paper presents a novel approach to automated negotiation that is particularly suitable to open environments, such as the Internet. In this approach agents can negotiate in any type of marketplace regardless of the negotiation mechanism in use. In order to support a wide variety of negotiation mechanisms, protocols are no longer hardcoded in the agents participating to negotiations, but are now expressed in terms of a shared ontology, thus making this approach particularly suitable for applications such as electronic commerce. The paper describes the negotiation ontology and provides a walkthrough example describing how the approach based on the negotiation ontology could be applied to the trading agent competition scenario.

Artificial Intelligence and Law, 2005

Negotiation Support Systems have traditionally modelled the process of negotiation. They often rely on mathematical optimisation techniques and ignore heuristics and other methods derived from practice. Our goal is to develop systems capable of decision support to help resolve a given dispute. A system we have constructed, Family_Winner, uses empirical evidence to dynamically modify initial preferences throughout the negotiation process. It sequentially allocates issues using trade-offs and compensation opportunities inherent in the dispute.

2008

Argumentation theory is often used in multi agent-systems to facilitate autonomous agent reasoning and multi-agent interaction. The technology can also be used to develop online negotiation and mediation services by providing argument structures that assist parties involved in a dispute to resolve outstanding issues or avoid future disputes. While Alternative Dispute Resolution (ADR) represents a move from a fixed and formal process to a more flexible one, Online Dispute Resolution (ODR) moves ADR from a physical to a virtual place. The research aims to capitalise on the recent trend towards ODR by creating a JADE based multi-agent ODR environment. The utility functions and argument structures of two existing ODR applications are being redeployed as Web based intelligent agents capable of intuitively coordinating during a negotiation. One agent uses expert knowledge of the Australian Family Law domain to recommend a percentage property split, while another uses heuristics and game theory and combines this split with a significance rating of items provided by each party, to allocate issues and advise upon possible trade-offs. The ultimate aim is to provide disputants with an integrated ODR environment offering a range of services to assist them in achieving fairer outcomes.

Software Agent-Based Applications, Platforms and Development Kits, 2005

This paper presents a System for Analysis of Multi-Issue Negotiation (SAMIN). The agents in this system conduct one-to-one negotiations, in which the values across multiple issues are negotiated on simultaneously. It is demonstrated how the system supports both automated negotiation (i.e., conducted by a software agent) and human negotiation (where humans specify their bids). To analyse such negotiation processes, the user can enter any formal property deemed useful into the system and use the system to automatically check this property in given negotiation traces. Furthermore, it is shown how, compared to fully closed negotiation, the efficiency of the reached agreements may be improved, either by using incomplete preference information revealed by the negotiation partner or by incorporating a heuristic, through which an agent uses the history of the opponent's bids in order to guess his preferences.

Negotiation Journal, 1995

An increasing number of researchers have turned their attention in recent years to the development of computer programs designed to aid participants in complex negotiations.' Notwithstanding their assorted differences, these programs typically rely on "expert systems" and use both specific and general knowledge bases to provide advice on various aspects of negotiations. While the immediate goal of any of these programs is to make the decision maker a better negotiator, expert systems have an even more fundamental advantage: The logic of an expert negotiation system (as summarized by its knowledge base and action rules) is, by design, straightforward and open for all to see. In comparison, the negotiation behavior of a human expert, no matter how experienced and astute, obeys a less transparent logic. Typically, a negotiator's actions depend on a subtle sequence of judgments. And frequently, a negotiator's reasoning is not fully communicated and is apt to vary even across similar circumstances. In short, the value of an expert negotiation system is that it codifies the logic underlying a given decision task. By rendering this knowledge and reasoning transferable, a decision maker can pursue expert strategies without needing the "expert" itself. As this article's title suggests, the main question I shall address here is: What kind of economic analyses might a computer-based expert system deliver to negotiators? My aim is to present a rough blueprint of a useful and feasible negotiation support system. Though facsimiles of such a system do not yet exist, they could well be built. At the same time, the discussion will not dwell on the technical aspects of expert systems. Rather, I describe the negotiation

Negotiation is considered in general very context sensitive. Since our research laboratory has successfully developed decision support systems in Australian Family Law, we have used our domain expertise to construct a variety of Family Law negotiation support systems. Family_Winner uses point allocation and heuristics to advise upon structuring the mediation process and provides solutions based on trade-off and compensation strategies. Heuristic utility functions were developed from cases supplied to us by the Australian Institute of Family Studies. Family_Winner operates best when it is possible to allocate points to issues, and creative decision-making is not required. Whilst conducting an evaluation of the Family_Winner system, we observed that Family_Winner, in focusing upon providing advice with regard to bargaining, had neglected considering issues of justice. In a domain such as Family Law, issues of justice are of paramount concern. This indicates that use of negotiation support systems should be limited to domains in which principles of equity do not conflict with user satisfaction. When Family_Winner was used in a variety of other negotiation domains (international disputes, enterprise bargaining and company mergers) the advice offered strongly resembled the eventual negotiated outcome.

Lecture Notes in Computer Science, 2006

The negotiation in general sense, as one of the most fundamental and powerful interaction of human beings, represents the dynamic process of exchanging information and perspectives towards mutual understanding and agreements. Interest based negotiation allows negotiators to discuss the concerns behind the negotiation issues so that a mutually acceptable win-win solution is more likely to be reached. This paper, for the first time, proposes a computational model for interest based negotiation automation which enables the automation of the fundamental elements of negotiation. Based on the model, algorithms are designated to automate the fundamental elements with practical computational complexity. This model provides not only a theoretical foundation for software agent based negotiation automation, but also a practical approach.

ArXiv, 2017

In this work we propose an ontology to support automated negotiation in multiagent systems. The ontology can be connected with some domain-specific ontologies to facilitate the negotiation in different domains, such as Intelligent Transportation Systems (ITS), e-commerce, etc. The specific negotiation rules for each type of negotiation strategy can also be defined as part of the ontology, reducing the amount of knowledge hardcoded in the agents and ensuring the interoperability. The expressiveness of the ontology was proved in a multiagent architecture for the automatic traffic light setting application on ITS.

Lecture Notes in Computer Science

Negotiation is an important and pervasive form of social interaction. The design of autonomous negotiating agents involves the consideration of insights from multiple relevant research areas to integrate different perspectives on negotiation. As a starting point for an interdisciplinary research effort, this paper presents a model that handles bilateral multi-issue negotiation, employs game-theoretic techniques to define equilibrium strategies for the bargaining game of alternating offers, and formalizes a set of negotiation strategies and tactics studied in the social sciences. Autonomous agents equipped with the model are currently being developed using the Jade framework. The agents are able to negotiate under both complete and incomplete information, thereby making the model in particular and the agents in general very compelling for automated negotiation.

2011 5th International Symposium on Computational Intelligence and Intelligent Informatics (ISCIII), 2011

Automated negotiation has become the core of many intelligent applications. Common research in automated negotiation is focused on investigations on negotiation protocol and strategy. However, the applications of automated negotiation systems depend on other components as preferences. This paper discusses the utility of these negotiation components among others and proposes a negotiation guiding framework using web services technology and describes the process of the whole system. This proposition was tested on our negotiation framework.

Studies in Computational Intelligence, 2010

Automated negotiation has become increasingly important and pervasive since the advent of e-Business. It frees people from tedious interactions, improves the efficiency of e-business and ensures the accuracy of complex service composition. However, there are limitations of the existing negotiation models. Firstly, the majority of existing negotiation models are "price" bargain type of negotiation. It does not consider the reasons lead to the bargain position. Secondly, a few interest based negotiation models proposed in recent years are able to consider the underlying reasons of the counter party's position, therefore, have more chance to reach an agreement. However, they focus on individual's alternative solution seeking. None of these models promote the most productive human negotiation approach, especially in the global economic context, to constructively cooperate and seek for possible win-win situations. In an e-business environment, it would be more powerful if new services could be built on multiple parties' existing services to form a cooperative solution. This paper proposes a negotiation model to enable negotiation parties to exchange preferences and knowledge, develop optimal cooperative solutions for mutual benefits. It is a cooperative-competitive win-win strategy.

Group Decision and Negotiation, 1994

In June of 1992 the Systems Research Institute of the Polish Academy of Sciences organized a Workshop on Support Systems for Decisions and Negotiation. More than eighty presented papers dealt with the design and application of decision support systems, modeling and support for group decision making, negotiation, mediation, and bargaining. Many of the papers introduced novel and interesting concepts. Other papers presented applications from a variety of areas, for exampie, environmental planning, water resource management, petroleum exploration, and engineering design.

2004

Current research in developing negotiation support systems focuses upon argumentation, artificial intelligence and game theory. These techniques are rarely used in tandem. We argue that truly intelligent negotiation support systems require the integration of such techniques.