The　rapid　development　of　the　Internet　of　Things　makes　it　possible　to　analyze　and　make　decisions　on　complex　tasks　in　human　society　based　on　big　data　and　artificial　intelligence　technologies.　Intelligent　healthcare　is　a　part　of　it　that　is　closely　related　to　human　beings.　Traditional　intelligent　healthcare　lacks　mental　health　diagnosis　and　monitoring.　The　mental　health　diagnosis　method　relies　on　subjective　decision-making　and　cannot　achieve　mental　health　diagnosis　and　early　warning　on　a　large　scale.　This　paper　combines　artificial　intelligence　and　low　communication　cost　edge　cloud　solutions　with　intelligent　healthcare.　Also,　the　paper　proposed　an　IoT-based　mental　health　diagnosis　solution　with　the　help　of　sentiment　analysis　technology.　The　scheme　targets　current　speech　in　various　scenarios　and　relies　on　sentiment　analysis　technology　to　quantify　emotions.　Then,　it　cooperates　with　algorithms　to　achieve　real-time　monitoring　and　early　warning　of　mental　health　conditions.　The　experimental　part　uses　self-collected　data　as　well　as　publicly　available　data.　The　experimental　results　show　that　the　framework　proposed　in　this　paper　accomplishes　the　tasks　on　multiple　data　sets.　©　2023　IEEE.