The　traveling　salesman　problem　(TSP)　is　one　of　the　classic　combinatorial　optimization　problems,　which　can　be　widely　used　in　intelligent　transportation　and　logistics　field.　Neural　network　has　shown　great　potential　in　combinatorial　optimization　tasks.　However,　it　faces　privacy　leakage　when　a　TSP　neural　combinatorial　optimization　network　and　user's　data　are　directly　outsourced　to　a　cloud　platform　to　provide　and　request　service.　In　order　to　address　the　issue,　this　paper　proposes　a　privacy-preserving　service　framework　for　a　TSP-based　neural　combinatorial　optimization　network　called　PPSF.　We　first　protect　the　service　provider's　model　parameters　and　users'　data　by　different　split　methods　in　multiple　cloud　servers,　providing　a　secure　outsourced　mode　for　the　participators　in　the　PPSF　framework.　Then,　in　the　secure　outsourced　mode,　a　series　of　secure　computation　protocols　are　designed　for　the　cloud　servers　to　support　performing　the　secure　computing　in　each　service　task.　Moreover,　it　can　also　protect　the　process　that　the　cloud　servers　respond　to　users　after　data　processing　and　achieve　private　service　result　recovery.　Finally,　we　prove　that　the　proposed　framework　can　realize　privacy　protection　for　TSP-based　combinatorial　optimization　service　and　verify　its　utility　and　efficiency　by　experiments.　IEEE