International Journal of Information Technology and Applications, Vol. 2, No. 2, pp. 27-35, June 2025.
Abstract: In view of the high dimensionality, dynamics and noise interference of tourism network search data, this paper proposes a method for mining tourism popular search behaviors based on immune clonal algorithm. By simulating the clonal selection mechanism of biological immune system, the search behavior pattern is abstracted as an antigen-antibody matching problem, and a multi-dimensional affinity function, dynamic parameter adjustment strategy and hybrid model enhancement mechanism are designed. By optimizing the number of algorithm antibodies and classifiers, the model can be effectively used for mining tourism data. Experimental data show that the rule extraction rate of the model reaches 99.6%, far exceeding the effect of the comparison algorithm. It also performs well in terms of computing time, which is 34.25s, lower than other comparison models. It is further proved that the algorithm is particularly suitable for deep mining of association rules in low support scenarios.