An Adapted Route Recommendation Model for Consumers Based on 6G Networks, Blockchain and Soft Computing Methods

The route preference of a consumer plays a vital role in deciding the effectiveness of route recommendations. Accurately analyzing the user’s travel preferences and demands can enhance the personalization and accuracy of travel route recommendations. Hence, an adapted route recommendation model id designed which is utilizing 6G communications for exchanging of data, Blockchain for collection of data at distributed nodes through smart sensors and soft computing methods that make decision for suggesting optimal route. The soft computing method begins by utilizing a Bayesian decision tree structure to obtain classification rules for attribute nodes through case reasoning that is unordered and rule less. These classification rules are then used to determine the busiest routes and demand of the consumers for respective routes. Additionally, the travel route preferences are also determined based on time considerations, and an adaptive route recommendation model is also constructed that emphasis on minimizing the travel costs and consumption of time to reach at the destination. To further enhance the recommendation process, the leapfrog algorithm is devised by adjusting the controllable precision, by incorporating the screening criteria, and by handling abnormal situations on the routes. The improved leapfrog algorithm is applied to solve the recommendation model, which is resulting in the generation of personalized route recommendations. The results prove that the proposed methodology significantly reduces the travel cost by attaining the recommendation accuracy up to 98.6% and outperforms the existing route recommendation models.