The Framework of Multi-agent Text Chance Discovery System Based on Immune

Text chance discovery is the process of extracting author´s potential hidden issue from a large number of texts. For the main question keyword (i.e. Chance) extracting, we propose a framework of text chance discovery system based on immune and multi-agent in this paper. By immunization and agent self-learning, this system reduces the person´s subjective consciousness impact on the results, and enhances the process of decision-making. It can more accurate and more effectively to achieve recognition and automatic keyword extraction.