AI models don't have a memory: When you converse with a chatbot one day, it won't remember what you said the next day. Chatbots (and Language Models) typically work by looking at "context", which, for you, basically means a few sentences in the past. The limit will vary from model to model, but it's typically up to 1000 words or something (not sure what is it these days with super huge models, but there's always a limit). Even if a chatbot uses "RNN", it's still very limited (usually even more) as RNNs struggle with long-term memory where long [a few hundred words]. The point is that AI models have no idea what you said a few sentences back. Also, don't be confused by models like Neural Turing Machine, which have a "working memory" (like RAM) but still no permanent memory (like a hard disk).

A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recommendation system still suffer from the long-term dependency and the interest drifts. To resolve these challenges, we suggest HCRNN with three hierarchical contexts of the global, the local, and the temporary interests. This structure is designed to withhold the global long-term interest of users, to reflect the local sub-sequence interests, and to attend the temporary interests of each transition. Besides, we propose a hierarchical context-based gate structure to incorporate our \textit{interest drift assumption}. As we suggest a new RNN structure, we support HCRNN with a complementary \textit{bi-channel attention} structure to utilize hierarchical context. We experimented the suggested structure on the sequential recommendation tasks with CiteULike, MovieLens, and LastFM, and our model showed the best performances in the sequential recommendations.