In　the　text　clustering,　the　traditional　clustering　algorithm　is　easy　to　fall　into　the　local　optimal　for　exploring　the　clustering　center,　which　will　affect　the　results　of　text　clustering.　This　paper　proposes　a　text　clustering　method　based　on　the　improved　heuristic　three-parent　genetic　algorithm.　In　this　paper,　the　heuristic　three-parent　genetic　algorithm　is　improved.　Furthermore,　by　enhancing　the　crossover　strategy　and　introducing　the　unequal　crossover,　the　genetic　algorithm＇s　convergence　speed　and　global　search　ability　are　improved.　In　text　clustering,　three-parent　with　the　improved　heuristic　genetic　algorithm　to　find　the　optimal　clustering　center.　Through　the　change　of　fitness　function,　the　clustering　center　is　more　suitable　for　text　clustering　results.　Using　the　clustering　center　guide　text　embedded　to　lower-dimensional　coding　of　high-dimensional　text,　finally　use　the　Deep　Embedded　Clustering　(DEC)　to　improve　the　effect　of　clustering.　The　clustering　results　are　evaluated　in　terms　of　Accuracy　and　Mutual　Information.　The　experimental　results　show　that　the　algorithm　performs　well　in　selecting　clustering　centers　and　clustering　results.　©　2021　IEEE