User Model of Personalized Search Engine for Product Design Based on Machine Learning

Abstract:

With the rapid development of internet technology, focusing on the product design of individual users, emphasizing the interaction design for Web and improving the user experience have become an inevitable trend of Web design, and also the hot spot of the design of personalized search engine. This paper proposed an optimized algorithm for building user models for product design websites. In order to show the design dimensions of Web pages presented by a browser, a concept of freshness is presented in this algorithm. By analyzing the user behavior of browsing Web pages, the model was updated using methods of machine learning. At last, the performance and effectiveness of this algorithm was analyzed and estimated through the simulation experiment.

• Periodical: Key Engineering Materials (Volumes 460-461)
• Pages: 747-753
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.460-461.747
• Online since: January 2011
• Authors: Ying Shi Kang, Hai Ning Wang
• Keywords: Machine Learning (ML), Personalized Search Engine, Product Design, User Experience, User Model

References

[1] Colorni A, Dorigo M. Heuristicsfrom nature for hard combinatorial optimization problems[J]. International Trans Operational Research, 1996, 3 (1): 1-21.

[2] Li Quanyong. Structure Optimization Review and Prospects [J]. Guilin University of Electronic Technology, 2000, (4).

[3] Stutzle T, Hoos H H. Max-min Ant system [J]. Journal of Future Generation Computer Systems, 2000, (16): 889-914.

DOI: 10.1016/s0167-739x(00)00043-1

[4] Talbi E G, Roux O, Fonlupt , et al. Parallel ant colonies for the quadratic assignment problem [J]. Future Generatio Computer Systems, 2001, 17(4): 441-449.

DOI: 10.1016/s0167-739x(99)00124-7

[5] Yang C X, Zhou PL , et al. Evolvement complexity in an artificial stock market[J]. Chin. Phys. Lett, 2005, (23): 1014-1017.

[6] Von Andries P. Engelbrecht. Fundamentals of Computational Swarm intelligence [M]. Wiley, (2006).

[7] Huang Wenpei, Wang Jinnuo, the blue peak. Chaos Powell hybrid algorithm in mechanical optimization design study [J]. Sichuan University, 2001, (5).

[8] Fan Hui-Yuan, Xi Guang, Wang Shang-Jin. Application of genetic algorithms to improve on the Cascade study design [J]. Mechanical Science and Technology, 2001, (1).

[9] SUN Tie li; YANG Feng qin. An approach of building and updating user model according to the implicit feedback. Journal of Northeast Normal University (Natural Science Edition). 2003, 9: 99-103.

[10] Micro Speretta, Susan Gauch. Personalized Search Based on User Search Histories, IEEE International Conference on Web intelligence, (2005).

DOI: 10.1109/wi.2005.114

[11] Ugur Cetintemel, Michael J. Franklin, C. Lee Giles. Self-Adaptive User Models for Large-Scale Data Delivery, IEEE International computing, (2005).

DOI: 10.1109/icde.2000.839477

[12] Di Caro G, Dorigo M. AntNet : Distributed stigmergetic control for communications networks [J]. Journal of Artificial Intelligence Research, 1998, (9): 317-365.

DOI: 10.1613/jair.530

[13] Reynolds CW. Flocks, herds, and schools: A distributed behavioral model [J]. Computer Graphics, 1987, 21: 25-34.

DOI: 10.1145/37402.37406

[14] JIANG Ping; CUI Zhi-ming Analysis and Research on the User Model in Intelligent Search Engine Microelectronics & Computer. 2004, 11: 24-26.

[15] Zhao Zhongmeng, Yuan Wei, He Shili, Shen Junyi. Research on the Intelligent Adjustive Algorithm for User Model in Personalized Search Engine. Computer Engineering and Applications. 2005, 9: 184-187.

[16] Zhuang Yue Ting, Pan yun He, Wu Fei. Multimedia Information Analysis and Retrieval online. Tsinghua University Press. BeiJin. (2002).

[17] Xu Bao Wen, Zhang Wei Feng. Search engine and information retrieve technology. Tsinghua University Press. BeiJin. 2003: 112-116.