Intelligent Search Agents Research Articles

Evaluating Intelligent Search Agents in a Controlled Environment Using Complex Queries: An Empirical Study

Evaluating Intelligent Search Agents in a Controlled Environment Using Complex Queries: An Empirical Study

Modeling knowledge resource selection in expert librarian search.

Providing knowledge at the point of care offers the possibility for reducing error and improving patient outcomes. However, the vast majority of the physician's information needs are not met in a timely fashion. The research presented in this paper characterizes an expert librarian's search strategies as it pertains to the selection and use of various electronic information resources. The 10 searches conducted by the librarian to address the physician's information needs varied in terms of complexity and question type. The librarian employed a total of 10 resources and used as many as 7 in a single search. The longer term objective is to model the sequential process in sufficient detail as to be able to contribute to the development of intelligent automated search agents.

Humans versus computers

Information overload is a very common problem in the business information industry. However, the root of this problem is not too much information; rather it is the fact that humans have limited attention spans to handle this information. Humans possess more processing power than computers but computers score over us in having almost unlimited attention spans. We must allocate our attention span in such a way as to maximize the information we obtain, given the constraint of our mental abilities. We have adopted a number of strategies to cope, like using intelligent search agents or spreading what attention we have thinly across as many information sources as possible (in other words skimming). The financial services industry, however, has adopted a radical approach: cut the human out of key parts of information acquisition and processing and use computers instead. This article argues that this approach could well spread to the wider business information market in the next few years. Far from being a threat, this could prove liberating for information professionals, allowing them to become more expert in specific industry sectors. The new breed of industry information portals, or community sites, will greatly aid in this transition and will build professional skills and efficiency.

E-비즈니스 컴포넌트 시스템 설계 및 구현

오늘날의 컴퓨팅 시스템은 인터넷을 사용하여 비즈니스 거래와 분산 업무 처리로 확대되어가고 있으며 정보 기술은 점차적으로 재사용성과 독립성 그리고 이식성을 가진 컴포넌트를 기반으로 한 응용 개발이 확산되고 있다. 컴포넌트 개발 형태는 코드의 재사용이나 클래스 라이브러리보다 좀 더 발전된 형태의 부품개발 형태로서, CBD(Component Based Development)를 기초로 한다. 그러나, CBD를 이용하여 새로운 컴포넌트를 구축하는 비용의 증가와 함께 비즈니스 요구사항에 맞는 컴포넌트 개발을 위한 노력이 필요하며, 빠르게 정확한 컴포넌트 정보를 웹 상에서 지원할 수 있도록 시스템 측면에서 정규화 형태의 컴포넌트 모델이 요구되고 있다. 본 논문에서는 사용자의 요구사항에 접근하고 웹 상에서 빠르고 신속하게 애플리케이션이 개발되는데 목적을 두고 있으며, 네트워크 상에서 비즈니스 도메인을 기반한 가장 소규모 단위의 분산 컴포넌트를 대상으로 인터페이스 명세를 제공하고자 한다. 분산 컴포넌트 내부와 외부 관계를 담고 있는 명세는 사용자 중심의 컴포넌트를 제공하기 위해서 웹 상에서 요구사항을 작성하고 결국 이들은 조합되어 e-비즈니스 컴포넌트 명세 제공이 요구된다. 따라서 본 논문에서는 사용자가 분산 컴포넌트를 등록하고, 이에 대한 컴포넌트 정보를 검색말 수 있는 e-BCOS(e-Busines Component System)을 설계 구현한다. e-BCOS는 컴포넌트 등록. 검색을 위한 에이전트 시스템으로, 비즈니스 도메인에서의 분산 컴포넌트의 e-비즈니스 컴포넌트 개발을 통해 재사용성을 증대시키고, 웹 상에서 애플리케이션 구축을 빠르고 신속하게 처리될 수 있도록 하며, 사용자가 쉽게 컴포넌트에 관한 정보를 얻고 이해할 수 있도록 해준다. 또한 명세의 공유와 유통을 원활히 하기 위해서 XML(extensible Markup Language)로 명세를 표현하여 사용자의 다양한 욕구를 충족시키도록 한다. 따라서, e-BCOS는 에이전트에 의해서 효율성 증대와 시간 절약 및 신뢰성과 유지보수성을 증대할 수 있는 잇점을 가진다. Today's computing system has expanded its application to business trade and distributed work transactions using the Internet. As the demand for more flexible, adaptable, extensible, and robust web-based enterprise, these application development has been gradually expanded based on reusable, independent, and portable components. Component Based Development (CBD) works by developing and evolving software from selected reusable software components and then assembling them within appropriate software architecture. However, it requires an increase in cost to build new components as well as the necessary effort to develop of the business requirement these components. Standardized component models are required as well from the perspective of systems in order to support rapid and exact component information transmission on the web. In this paper, we describe the e-Business Component Development with agent for rapid application development on the web that correspond to the demands of users in the business domain. We design and implement the specifications of e-business components by combining these demands. In order to improve the agent register and retrieval, we propose the intelligent search and register agents, which can conduct more precise searching and specializing for components. The system enables the locating of user's frequently used components through an agent involving register and retrieval, as well as rapid procedures for registers The e-BCOS (e-Business Component System) is the agent system for the user to register distributed components and to search for components Information. The e-BCOS increases reusability through the e-business component development of distributed components in the business domain. For the share and delivery, specification with XML is acceptable to user's variable order e-BCOS Includes the effective investment, timeliness, reliability, efficiency, and maintenance effort by with agent.

Complementing search engines with online web mining agents

While search engines have become the major decision support tools for the Internet, there is a growing disparity between the image of the World Wide Web stored in search engine repositories and the actual dynamic, distributed nature of Web data. We propose to attack this problem using an adaptive population of intelligent agents mining the Web online at query time. We discuss the benefits and shortcomings of using dynamic search strategies versus the traditional static methods in which search and retrieval are disjoint. This paper presents a public Web intelligence tool called MySpiders, a threaded multiagent system designed for information discovery. The performance of the system is evaluated by comparing its effectiveness in locating recent, relevant documents with that of search engines. We present results suggesting that augmenting search engines with adaptive populations of intelligent search agents can lead to a significant competitive advantage. We also discuss some of the challenges of evaluating such a system on current Web data, introduce three novel metrics for this purpose, and outline some of the lessons learned in the process.

A human-centered agent-based architecture for electronic brokerage

Electronic brokerage, envisioning brokers acting on customers' behalf to locate required products and services at the best available price, is a promising technique to solve a specific problem of electronic commerce business relations, i.e. the identification of the goods and services satisfying the user requirements to the highest possible degree. In this paper we describe a electronic brokerage system based on a human-centered layered architecture that allows the broker to proceed seamlessly from the user's vision of the market, based on a nominal scale, to ordinal and interval based representations suitable for intelligent search agents exploiting fuzzy techniques.

Radiological information searching on the Internet: data banks, search machines and intelligent agents

The Internet plays an important role in a growing number of medical applications. Finding relevant information is not always easy as the amount of available information on the Web is rising quickly. Even the best search engines can only collect links to a fraction of all existing Web pages. In addition, many of these indexed documents have been changed or deleted. The vast majority of information on the Web is not searchable with conventional methods. New search strategies, technologies and standards are combined in intelligent search agents (ISA) and robots, which can retrieve desired information in a specific approach. The article describes differences between ISAs and conventional search engines and how communication between agents improves their ability to find information. Examples of existing ISAs are given and the possible influences on the current and future work in radiology is discussed.

Will technology kill the healthcare library?

Will technology kill the healthcare library?

MY KINGDOM FOR AN AGENT? EVALUATION OF AUTONOMY, AN INTELLIGENT SEARCH AGENT FOR THE INTERNET

This paper presents an evaluation of a commercially available intelligent search agent for the Internet. Search robots and search engines can be of great help in finding information on the Internet, but their different features and sometimes their unfriendly interfaces can be confusing. Some expect that intelligent search agents could solve these problems. But most of these applications are not yet on the market, and the few that are: do they really perform? One of the few commercially available search agents is Autonomy, from Autonomy Corporation. Its concept is promising to professional users: the natural language processing of the query, the take‐over of repetitive jobs, an integrated interface for searching and managing information, and the sharing of knowledge with other users. The test in this article, however, reveals that the product is not yet ready to challenge the Internet search indexes which, in the test cases, perform better than Autonomy does with regard to recall and precision of information retrieval. Moreover, Autonomy does not give enough feedback to control the search action.