a genetic algorithm approachto document assembly（遗传算法日常文档组装）（6页）.docVIP

A Genetic Algorithm Approach to Automated Custom Document Assembly Lisa Purvis Xerox Corporation 800 Phillips Road, 128-27E Webster, NY 14580 Abstract The digital networked world is enabling and requiring a new emphasis on personalized document creation. Traditional methods of producing document layout and style have become insufficient, since most are aimed at producing static results. Also, as new untrained users start producing documents for a wide audience, the old publishing tools prove too demanding. The new, more dynamic digital environment demands tools that can reproduce both the contents and the layout automatically, tailored to personal needs and transformed for the presentation device, and can enable novices to easily create such documents. In order to achieve such automated document assembly and transformation, we have formalized custom document creation as a constrained optimization problem, and use a genetic algorithm to assemble and transform compound personalized documents. We have found that using this approach provides advantages over existing custom document creation methods. Introduction The digital networked world is a sea of information. Individuals need this information in different forms, at different times, on different devices. While there is lot of information, only a portion of it is relevant to each individual at a particular time, and the information needs of an individual change over time. Businesses are also finding that personalized information is more effective in keeping customers, both in e-commerce and traditional settings. The new, more dynamic digital environment demands tools that can automatically create documents, tailored to personal needs and transformed for the presentation device. We have formalized the custom document creation problem as a constrained-optimization problem, and use a genetic algorithm to assemble and transform compound documents to meet individual needs. We begin in Section 2 by