Software agents for information retrieval

1994

Abstract sources that are available to it. Given an information request, an agent identifies an appropriate set of With the vast number of information resources information sources, generates a plan to retrieve and available today, a critical problem is how to loprocess the data, uses knowledge about the data to recate, retrieve and process information. It would formulate the plan, and then executes it.

Information Retrieval, 2005

The heterogeneous, distributed and voluminous nature of many government and corporate data sources impose severe constraints on meeting the diverse requirements of users who analyze the data. Additionally, communication bandwidth limitations, time constraints, and multiple data formats impose further restrictions on users of these distributed data sources. In this paper, we present an Agent-based Complex QUerying and Information Retrieval Engine (ACQUIRE) for large, heterogeneous, and distributed data sources. ACQUIRE acts as a softbot or interface agent by presenting users with a view of a single, unified, homogenous data source, against which users can pose high-level declarative queries. ACQUIRE translates each such user query into a set of sub-queries by employing a combination of planning and traditional database query optimization techniques. ACQUIRE then spawns a set of mobile agents corresponding to these sub-queries, which in turn retrieve the data from various distributed data sources by dynamically optimizing the retrieval strategy as it is carried out. These mobile agents carry with them data-processing code that can be executed at the remote site, thus reducing the size of data returned by the agent. When all mobile agents have returned, ACQUIRE filters and merges the retrieved data and presents the results to the user. While the system is still very much a work in progress, current validation experiments on simulated NASA Distributed Active Archive Centers (DAACs) have demonstrated that complex queries can be effectively decomposed and retrieved by this approach.

International Journal of Product Lifecycle Management, 2007

In this paper, we present a multi-agent system for searching the internet. The search for interesting documents on the internet is becoming more and more difficult. The main problem is not that we do not have the needed information to build or use knowledge, the problem is that we have too much information, mostly irrelevant. A proof of this is that inference engines are largely outperformed by the expansion of the internet and the results of queries are often of very poor quality. To improve the search process, intelligent individual agents were developed. We believe that multi-agent systems can give more accurate results than the individual agents because in a multi-agent system, agents can be specialised in different tasks and can share information. We implemented such an approach using an open multi-agent system containing personal assistants, library agents, filter agents, and search agents. In this paper, we study the models of internet multi-agent systems and propose an architecture to do intelligent web search. The application is based on an AUML protocol (slightly extended) to allow interoperability and yields more accurate results than standard search engines.

International Journal of Intelligent Systems Technologies and Applications, 2010

This paper proposes a new approach using a multi-agents system for personalising the distributed information retrieval (DIR). Most prior research in DIR focused on selecting and merging information that has the most relevant content according to the query, but ignored the user's specific needs. Our approach extends the state-of-the-art in a DIR. Firstly, it develops an agent called user-agent for managing the user profile. Secondly, it develops an agent called source-agent for each information source in order to manage its information source. Finally, it develops an agent called agent-broker for cooperating between user-agent and each source-agent in order to select the best source and merge their best documents in response to the user's query. The approach has been experimented with several known information sources. The experimental results show that the approach: (1) improve the relevance of the result, (2) reduce the response times and (3) improve the system extensibility.

2000

Searching for information on the Web is a time consuming task. To help users and to speed up searching for relevant documents efficient retrieval and filtering techniques are needed. To increase the efficiency of information retrieval and filtering tasks, intelligent agents have been widely studied and deployed. In this paper, we present a general agent framework for retrieving and filtering relevant/irrelevant documents.

1999

The expansion of information available on the Web has been explosive. The initial approach of collecting all Web pages into a single location and indexing them is limited in its ability to deal with this explosion. Different search engines provide access to different collections, requiring users to access multiple information sources to meet their needs. A scalable approach to information gathering from multiple sources is described which is based on the use of distributed information agents to route queries to the most appropriate sources and fuse information they provide. This paper describes an intelligent, adaptive Web search tool that can not only locate relevant information sources for the user, but also adapt to the frequent changes of the dynamic Web environment. We employ a multiple agent architecture to intelligently categorize and broker queries to remote search engines, learn and continuously update confidence factors for the quality of results provided by each search engine, and automatically detect and adapt to changes in the syntax used by the search engines. Our work is an extension of ProFusion thtto://www.orofusion.com) [Ganch 96b], a Web rectasearch engine developed at the University of Kansas which can currently broker information from nine remote search engines.

2005

The Web offers a huge amount of valuable information, but it is very hard and time consuming to retrieve thousands of web pages related to a concept, filter the relevant ones, analyse this information and integrate it in a knowledge repository. This paper describes one component of a knowledge management platform (h-TechSight project) that performs these tasks, the multi-agent search module (MASH). MASH employs a domain ontology to search for web pages that contain relevant information to each concept in the domain of interest. The search is then constrained to a specific domain to avoid as much as possible the analysis of irrelevant information.

2003

With the consolidation of the Internet and other computer networks, the need of sophisticated systems to retrieve information increased enormously. In these networks, information is distributed on several machines and sometimes in different formats. In this context, we propose an architecture that besides retrieving information can classify it according to some criteria. To implement the proposed architecture, we used some existing technologies such as mobile agents to transport information between data sources; the Naive Bayes model for classification; the Java language and the XML model for development and storage of the required information.

Proceedings of the …, 2007

The technology of search engines is evolving from indexing and classification of web resources based on keywords to more sophisticated techniques which take into account the meaning and the context of textual information and usage. Replying to query, commercial search engines face the user requests with a large amount of results, mostly useless or only partially related to the request; the subsequent refinement, operated downloading and examining as much pages as possible and simply ignoring whatever stays behind the first few pages, is left up to the user. Furthermore, architectures based on centralized indexes, allow commercial search engines to control the advertisement of online information, in contrast to P2P architectures that focus the attention on user requirements involving the end user in search engine maintenance and operation. To address such wishes, new search engines should focus on three key aspects: semantics, geo-referencing, collaboration/distribution. Semantic analysis lets to increase the results relevance. The geo-referencing of catalogued resources allows contextualisation based on user position. Collaboration distributes storage, processing, and trust on a world-wide network of nodes running on users' computers, getting rid of bottlenecks and central points of failures. In this paper, we describe the studies, the concepts and the solutions developed in the DART project to introduce these three key features in a novel search engine architecture.

2003

One of the major problems in information technologies nowadays is the growing amounts of information accu-mulated in large weakly-structured repositories such as the Internet. Thus a lot of research is going on in the area of information retrieval and search, and in most of ...