In　order　to　get　a　better　semantic　matching　degree　for　web　services,　in　this　paper,　we　try　to　deal　with　the　problems　of　semantic　web　services　matching　through　calculating　the　Normalized　Google　Distance　(NGD)　between　concepts,　based　on　the　semantic　description　of　web　service＇s　input　and　output.　This　technique　takes　advantage　of　the　Google　massive　terms　and　open　Google　search　engine　to　compute　the　NGD,　and　calculates　the　similarity　between　concepts.　Compared　with　the　existing　algorithm,　we　adopt　Google　terms　which　present　merits　of　more　abundance　and　updating　in　a　relatively　faster　speed.　This　method　is　simpler　and　greatly　decreases　the　complexity　of　calculation　because　there　is　no　ontology　and　taxonomy　tree,　no　need　to　judge　the　foliatory　order,　path　length,　depth　and　local　density.　The　preliminary　results　have　shown　that　our　algorithm　can　highly　improve　the　recall　and　precision　of　the　web　services.　©　2005　by　Binary　Information　Press.