Extended　belief　rule-based　(EBRB)　system　has　a　better　ability　to　model　complex　problems　than　belief　rule-based　(BRB)　system.　However,　the　storage　of　rules　in　EBRB　system　is　out　of　order,　which　leads　to　the　low　efficiency　of　rule　retrieval　during　the　reasoning　process.　Therefore,　to　improve　the　efficiency　of　rule　retrieval,　this　study　introduces　K-means　clustering　tree　algorithm　into　the　construction　of　rule　base,　then　proposes　a　multi-layer　weighted　reasoning　approach　based　on　K-means　clustering　tree.　The　proposed　approach　seeks　out　a　path　on　the　tree　during　the　rule　retrieval　process,　and　then　figures　out　several　reasoning　results　according　to　the　nodes　on　the　path.　These　results　are　weighted　and　aggregated　to　obtain　the　final　conclusion　of　the　system,　thus　ensure　both　the　efficiency　of　reasoning　and　the　sufficient　utilization　of　information.　In　addition,　the　differential　evolution　(DE)　algorithm　is　used　to　train　the　parameters　of　EBRB　system　in　this　study.　Several　experiments　are　conducted　on　commonly　used　classification　datasets　from　UCI,　and　the　results　are　compared　with　some　existing　works　of　EBRB　system　and　conventional　machine　learning　methods.　The　comparison　results　illustrate　that　the　proposed　method　can　make　an　obvious　improvement　in　the　performance　of　EBRB　system.