Elektrotehniški vestnik Electrotechnical Review, Ljubljana, Slovenija Accepted

Elektrotehniški vestnik Electrotechnical Review, Ljubljana, Slovenija Accepted Aproved Intelligent Agents in E-commerce Aleksander Pivk, Matjaž Gams Jozef Stefan Institute, Department of Intelligent Systems, Jamova 39, 1000 Ljubljana E-mail: aleksander.pivk@ijs.si, matjaz.gams@ijs.si Abstract. Intelligent agents represent a new breed of software with significant potential for a wide range of Internet applications. They have been successfully used for personal assistants, intelligent user interfaces, and managing electronic mail. Recently, agents have been applied to electronic commerce, promising a revolution in the way we conduct business, whether business-to-business, business-to-customer or customer-to-customer. This article gives a brief introduction to intelligent agents and electronic commerce, followed by a review of agent technologies involved in buying and selling. Typology, taxonomy, and classification of agents are presented. Several agent-mediated electronic commerce systems are analyzed in the context of a general model of the buying process. Several lists of related Internet links should help readers to gather additional relevant information. Key words: agent, intelligent agent, and electronic commerce Inteligentni agenti v elektronskem poslovanju Povzetek. Inteligentni agenti predstavljajo novo zvrst programske opreme z visokim potencialom pri razširjenih internetnih aplikacijah. V preteklosti so jih uspešno uporabljali pri upravljanju z elektronsko pošto, kot osebne pomoènike in inteligentne uporabniške vmesnike. V zadnjem èasu pa so se le-ti zaèeli uveljavljati pri elektronskem poslovanju, kjer obljubljajo revolucionarne spremembe pri opravljanju poslovanja, pa èe tu opazujemo poslovanje med podjetji, med podjetjem in konèno stranko ali celo med samimi konènimi strankami. V èlanku sva najprej predstavila inteligentne agente in elektronsko poslovanje, temu pa sledi pregled tehnologij, ki se uporabljajo pri nakupovanju in prodaji. Predstavljeni so tudi tipologija, sistematika in klasifikacija agentov. V kontekstu splošnega modela nakupovalnega procesa je analiziranih nekaj elektronsko-poslovnih sistemov v povezavi z agenti. Pri zbiranju dodatnih pomembnih informacij pa je bralcu v pomoè spisek sorodnih internetnih povezav. Kljuène besede: agent, inteligentni agent, elektronsko poslovanje 1 Introduction In recent years the Internet (World Wide Web) due to its exponential growth enabled substantial progress in new information society functions [17, 23] such as online commerce. Latest studies of online spending habits of consumers by Forrester have shown that the growth has been explosive, increasing from $2.4 billion in 1997 to $8.0 billion in 1998 and $20.2 billion in 1999 and still growing at a rapid pace. Electronic commerce entails business-to- business, business-to-customer and customer-to-customer transactions. It encompasses a wide range of issues including security, trust, reputation, law, payment mechanisms, advertising, ontologies, electronic product catalogs, intermediaries, multimedia shopping 2 Pivk, Gams experiences, and back office management. Agent technologies can be applied to any of these areas [1]. Still, the potential of the Internet for truly transforming commerce is largely unrealized to date. Electronic purchases remain mostly non-automated. While information about different products and vendors is easily accessible and orders and payments can be dealt with electronically, a human is still in the loop in all stages of the buying process. Traditional shopping activities require a large effort from a human buyer collecting and interpreting information on merchants, products and services, making an optimal purchase decisions and finally entering appropriate purchase and payment information [2]. Software agents help automate a variety of activities, mostly time consuming ones, and thus lower the transaction costs. Software agents differ from “traditional” software in that they are personalized, social, continuously running and semi-autonomous [1]. In this way, e-commerce is becoming more user-friendly, semi-intelligent and human-like. These qualities are conducive for optimizing the whole buying experience and revolutionizing commerce, as we know it today [2]. 2 Intelligent Agents 2.1 Description There are many definitions of what the term “agent” denotes based on different approaches, expectations and visions. As pointed out by Bradshaw [3], one person’s “intelligent agent” is another’s person “smart object”. Shoham [4] describes a software agent as a software entity which functions continuously and autonomously in a particular environment often inhabited by other agents and processes. The requirement for continuity and autonomy derives from human desire that an agent be able to perform activities in a flexible and intelligent manner responsive to changes in the environment without constant human supervision. An agent that functions over a long period of time should be able to adopt from its experience. Further, we expect an agent to inhabit an environment with other agents and processes, to be able to communicate and cooperate with them, and perhaps move from one place to another in doing so [3]. Consistent with the requirements of a particular problem, each agent might possess to a greater or lesser degree the following attributes [3,5,6]: • Reactivity: the ability to selectively sense and act. • Autonomy: goal-directedness, proactive and self-starting behavior. • Collaborative behavior: can work in collaboration with other agent to achieve a common goal. • “Knowledge-level” communication ability: the ability to communicate with human and other agents with language more resembling human-like speech than symbol-level protocols. • Inferential capability: can act on abstract task specification using prior knowledge of general goals and preferred methods to achieve flexibility. • Temporal continuity: persistence of identity and state over long periods of time. • Personality: the capability of manifesting the attributes of a believable character such as emotion. • Adaptivity: being able to learn and improve with experience. Intelligent Agents in E-commerce 3 • Mobility: being able to migrate in a self- directed way from one host platform to another. Agents may be classified according to [3]: • Mobility (static, mobile) – the ability to move around. • Presence of symbolic reasoning model a) Deliberative – from the deliberative thinking paradigm, which holds that agent posses symbolic reasoning models, they engage in planning and negotiation with other agents in order to achieve their goals. b) Reactive – do not have any internal, symbolic models of their environment; instead they respond in a stimulus- response manner to the present state of the environment in which they are embedded. • Exhibition of primary attributes a) Autonomy – agents can operate without human interference. A key element of autonomy is proactiveness, i.e., the ability to “take the initiative” [7]. b) Cooperation – paramount with other agents. The communication required to ensure cooperation generally involves high-level messages. c) Learning – intelligent agents should learn as they react and interact with the external environment. Over time their performance should increase. • Tasks (information, Internet) – such agents help manage the vast amount of information in wide area networks. • Hybrid properties – two or more different agent approaches (philosophies) are combined in a single agent, and • Secondary attributes – these attributes provide a stronger definition of agent- hood. Some of them are: versatility, benevolence, veracity, trustworthiness, temporal continuity, mentalistic and emotional qualities etc. Four types of agents can be derived from the characteristics of primary attributes [3,8]: collaborative, collaborative learning, interface and smart (see Figure 1). According to Jennigns and Wooldridge, and Nwana [7,8], more common classification of agents entails eight categories (see Figure 2): • Collaborative agents: emphasize autonomy and cooperation with other agents (see Figure 1) in order to perform Learn Cooperate Autonomous Collaborative Learning Agents Smart Agents Interface Agents Collaborative Agents Figure 1: Typology based on Nwana’s primary attribute dimension 4 Pivk, Gams • tasks for their owners in open and time- constraint multi-agent environments. Collaborative agents tend to be static, large and coarse-grained agents [7]. In order to reach mutually acceptable agreements they may have to negotiate. • Interface agents: emphasize autonomy and learning in order to perform tasks for their owners (see Figure 1). Essentially, interface agents support and provide proactive assistance, typically to a user learning to use a particular application (spreadsheet, word processor, operating system) [7]. The agent observes and monitors the action taken by the user in the interface, learns new shortcuts, and in future suggests better ways for completing a task. These agents learn to assist their users in the following four ways [7]: (a) by observing and imitating the user, (b) through receiving positive and negative feedback from the user, (c) by receiving explicit instructions from the user, and (d) by asking other agents for advice. Their cooperation with other agents is limited to asking for advice. The general benefits of interface agents are threefold. Firstly, they reduce user’s efforts in repetitive work. Secondly, agent can adapt to its user’s preferences and habits, and finally know-how among different users in a community may be shared [7]. • Mobile agents: software processes capable of roaming wide area networks (such as WWW), interacting with foreign hosts, performing tasks on behalf of their owners and returning home having performed duties been set. • Information/Internet agents: they perform the role of managing, manipulating, or collating information from many distributes sources. The motivation for developing information agents is at least twofold. Firstly, there is an increasing need for tools that manage the information explosion of the WWW, where anyone would benefit from them. Secondly, there are also vast financial opportunities to be gained. • Reactive agents: there are three key ideas underpinning these agents. Firstly, emergent functionality: reactive agents are relatively simple and they interact with other agents in basic ways. There uploads/Geographie/ iain-ec 1 .pdf

  • 28
  • 0
  • 0
Afficher les détails des licences
Licence et utilisation
Gratuit pour un usage personnel Attribution requise
Partager