The　rapid　growth　in　the　scale　of　distributed　databases　has　led　to　a　deeper　impact　of　the　multi-join　query　optimization　problem　on　data　query　efficiency.　The　increase　in　the　number　of　relations　causes　a　significant　increase　in　the　search　space　complexity　of　distributed　database　multi-join　optimization,　which　greatly　affects　the　efficiency　of　finding　the　optimal　execution　plan,　thus　hindering　the　further　optimization　of　multi-join　queries.　In　this　regard,　a　genetic　multiple　bee　colony　algorithm　combined　with　fuzzy　logic　is　proposed　to　solve　the　problem　of　further　optimizing　multi-join　queries　of　distributed　databases.　Firstly,　the　fast　convergence　property　of　the　genetic　algorithm　is　utilized　to　obtain　a　set　of　relatively　optimal　solutions　in　order　to　overcome　the　blindness　of　the　artificial　bee　algorithm＇s　pre-search,　and　then　the　parallel　multiple　bee　algorithm　is　introduced,　which　makes　use　of　the　information　interaction　between　multiple　bee　colonies　to　better　prevent　the　algorithm　from　falling　into　the　local　optimal　situation　as　well　as　the　parallelization　of　the　execution　of　the　multiple　bee　colonies　to　improve　the　search　efficiency　and　convergence　speed　of　the　algorithm.　Secondly,　the　fuzzy　logic　system　is　also　used　to　optimize　the　parameters　of　the　algorithm　and　set　the　corresponding　algorithmic　control　parameters　for　different　dimensional　queries.　Finally,　a　comparison　experiment　is　conducted　to　test　the　average　execution　cost　and　algorithm　execution　time　of　the　Top-K　query　plans　output　by　the　algorithm　in　the　case　of　six　query　statements　involving　different　lengths,　and　the　experimental　results　show　that　the　K　optimal　query　plans　generated　by　the　method　proposed　in　this　paper　have　lower　query　excution　cost　and　algorithm　execution　time,　and　can　effectively　improve　the　query　efficiency.　©　2024　IEEE.