Personal Information Assistant (PIA) in companies
PIA Enterprise is an enterprise search engine that has the goal to assist employees to fulfill their daily information gathering tasks. PIA provides access to content from multiple sources within the enterprise such as intranet, web, databases, mails and user desktops whilst taking into account privacy and user rights. PIA offers a semantic search, computes personalized recommendations, and continually supplies new information that fits the user’s information need. Users may also assign ratings and tags to individual search results, thus allowing the underlying personalization component to learn a user’s interests and preferences for future searches.
The system provides quick access to information and offers personalized continuous information supply to inform users once new content is available. PIAs unique features are the distributed indices, which allow adding new sources to a running system and managing rights for different sources individually. PIA transfers latest research results directly to real world enterprise applications.
Information discovery matching the needs and interests of individual users is a challenging task and plays a central role in the daily life. Unfortunately, most of the time a lot of irrelevant information hides the relevant information, search results are sometimes redundant or contradictory, often distributed over multiple sources, thus resulting in difficult and costly retrieval. In order to counteract this information overload, personalized services that collect, filter, prepare and present information from different sources are required.
The goal of the Personal Information Assistant project is to provide a comprehensive agent-based solution for the personalized and device-independent supply of information. The user receives information that is relevant to his personal needs and interests. This includes daily news, background knowledge on work issues, or information on leisure time plans and activities. The architecture of the PIA system is designed to allow information sources to be flexibly integrated into the system. Information is analyzed and filtered using advanced filtering methods, e.g. content-based or collaborative filtering techniques. The use of multiple filtering techniques, which are guided by integrating user feedback from a learning and user modelling component, guarantees a high accuracy of search results.