Context-aware and Click Session-based Graph Pattern Mining with Recommendations for Smart EMS through AI

In the field of Artificial Intelligence (AI), Smart Enterprise Management Systems (Smart EMS) and big data analytics are most prominent computing technologies. A key component EMS system is E-commerce, especially Session-based Recommender systems (SRS), which typically utilized to enhance user experience by providing recommendations analyzing behavior encoded in browser sessions. Also work recommender predict users’ next actions (click on an item) using sequence current session. Current developments session-based recommendation have primarily focused mining more information accessible within On other hand, those approaches ignored sessions with identical context for session that includes a wealth collaborative data. Therefore this paper proposed Context-aware Click graph pattern through AI. It employs novel Triple Attentive Neural Network (TANN) SRS. Specifically, TANN contains three main components, i.e., Enhanced Sqrt-Cosine Similarity based Neighborhood Sessions Discovery (NSD), Frequent Subgraph Mining (FSM) Top-K possible Next-clicked Items (TNID). The NSD module uses session-level attention mechanism find m similar query session, FSM also extracts frequent subgraphs from already discovered via item-level attention. Then, TNID used discover top-K next-clicked items target-level Finally, we perform comprehensive experiments one dataset, DIGINETICA, verify effectiveness model, results experiment clearly illustrate performance TANN.