Artificial　intelligence　(AI)-enabled　Internet　of　Things　(IoT)　has　attracted　great　interests.　The　accuracy　of　data　training　model　in　AI　is　vital　for　further　development　of　IoT.　In　addition,　with　the　increasing　number　of　intelligent　IoT　devices,　the　amounts　of　data　available　for　transmission,　learning　and　training　can　lead　to　serious　communication　burdens　and　data　reliability　issues.　In　order　to　address　these　issues,　we　study　novel　network　architectures　in　future　6G　networks　to　support　the　intelligent　IoT.　Moreover,　inspired　by　the　collective　learning　of　humans,　we　introduce　and　adopt　a　novel　method　named　as　collective　reinforcement　learning　(CRL)　in　the　intelligent　IoT　to　realize　the　sharing　of　learning　and　training　results.　To　ensure　security　and　privacy,　as　well　as　improve　computing　efficiency,　blockchain,　mobile　edge　computing　(MEC)　and　cloud　computing　are　applied　to　protect　data　security　and　enrich　computing　resources.　On　this　basis,　we　formulate　an　optimization　problem　in　the　intelligent　IoT　based　on　the　proposed　framework　to　optimize　transmission　latency　and　energy　consumption.　Simulation　results　demonstrate　that　the　system　performance　has　improved　significantly.　At　last,　some　research　challenges　and　open　issues　are　pointed　out　to　the　intelligent　IoT　in　future　networks.