The　generalized　Pareto　distribution　(GPD)　is　one　of　the　most　important　distribution　in　statistics　analysis.　This　paper　is　based　on　sample　quantiles　of　the　GPD.　First,　the　shape　parameter　estimator　that　has　high　estimated　precision　is　solved,　then　the　approximated　generalized　least　squares　estimation　expressions　of　the　location　and　scale　parameters　are　obtained　for　the　GPD.　The　proposed　method　is　easy　and　has　no　limitation　for　the　shape　parameter.　In　addition,　it　has　high　estimation　accuracy　under　Monte-Carlo　simulation　tests.