Research On Method Of Tourism Route Recommendation Combining Event Graph And Knowledge Graph

With the development of information technology,the importance of intelligent recommendation systems is increasing day by day.The function of the recommendation system is to infer items that the user may be interested in based on the user's historical behavior,so as to save the user's time and improve the user experience.Both traditional content-based recommendation and collaborative filtering-based recommendation methods have some shortcomings,including data sparseness and cold start.Recommendation methods based on knowledge graphs have received widespread attention.The event graph is developed on the basis of the knowledge graph,which contains events and the logical relationships between them.Starting from the perspective of management,this paper constructs a theoretical model of recommendation methods based on event graphs and knowledge graphs,which can enrich the research in the field of personalized recommendation algorithms based on knowledge graphs.In addition,in the tourism route recommendation method constructed in this paper that integrates the event graph and the knowledge graph,the main use is the logical relationship of succession,which can make the recommendation result.First,we constructed the theoretical model of the recommendation system,which is divided into three modules,knowledge graph module,event graph module and recommendation module.Based on the theoretical model,we constructed an event graph of the tourism field by collecting travel travel strategy data of major tourism platforms.Different from the traditional method,we add time parameters and transition probability to the path.And then we constructed the knowledge graph of tourism field based on ontology model.Through the steps of ontology model construction,information extraction,entity filling and knowledge processing,the knowledge graph with a certain scale is formed.Then,we designed a recommendation method combining knowledge graph and event graph.In the path-based recommendation method,not only the items favored by users are considered,but also the items disliked by users are considered.Finally,using the method of example verification,the route is represented on the actual map to verify the rationality and effectiveness of the recommended method.Given an application example,and the recommendation results are evaluated by HR and MRR.The results show that the recommendation method proposed in this paper has a good recommendation effect.