With　the　rapid　development　of　information　technology,　the　name　ambiguity　problem　has　become　one　of　the　primary　issues　in　the　fields　of　information　retrieval,　data　mining,　and　scientific　measurement.　Name　disambiguation　is　used　to　promote　computer　technology　and　big　data　information,　which　maps　virtual　relational　networks　to　real　social　networks　to　solve　the　problem　that　the　same　name　points　to　multiple　entities.　At　present　many　literature　search　platforms　launched　their　respective　scholar　system,　name　ambiguity　problem　will　inevitably　affect　the　precision　of　other　information　calculations,　reduce　the　credibility　of　the　system,　and　affect　the　information　quality　and　content　quality.　Most　work　deals　with　this　issue　by　using　graph　theory　and　clustering.　However,　the　name　disambiguation　problem　is　still　not　well　resolved.　In　this　paper,　we　propose　a　multi-level　name　disambiguation　algorithm.　This　algorithm　is　mainly　based　on　the　unsupervised　algorithm,　which　combines　hierarchical　agglomerative　clustering　(HAC)　and　graph　theory　for　disambiguating.　The　experimental　results　show　that　the　proposed　solution　achieves　clearly　better　performance　(+17　similar　to　25%　in　terms　of　F1-Measure)　than　several　methods,　including　HAC　and　Graph.