Entity　relation　classification　is　one　of　the　basic　tasks　in　natural　language　processing.　The　performance　of　the　existing　relational　classification　in　Chinese　literature　text　is　not　ideal.　To　address　the　issues,　we　propose　a　entity　attention-based　model　for　entity　relation　classification　for　Chinese　literature　text.　Our　proposed　model　extracts　key　information　from　entity　by　using　attention　mechanism,　and　filters　out　redundant　information.　In　addition,　we　integrate　entity　type　information　into　the　model　to　help　the　model　classify　relation　more　reasonably.　Experimental　results　show　that　the　proposed　model　outperforms　the　state-of-the-art　methods　on　Chinese　literature　text.　©　2021　IEEE.