The　emergence　of　ridesharing　services　is　poised　to　significantly　reshape　the　urban　sustainability　paradigm.　With　ever-growing　demand,　the　adoption　of　high-capacity　vehicles　in　shared　mobility　is　becoming　increasingly　feasible.　In　this　study,　we　present　a　high-capacity　vehicle　strategy　to　improve　the　economic,　social,　and　environmental　sustainability　of　the　ridesharing　system.　To　optimize　the　initial　solution,　deep　reinforcement　learning　(DRL)　is　introduced　into　the　framework　of　the　NSGA-II　algorithm.　Based　on　the　priority　order,　we　apply　lexicographic　optimization　to　achieve　the　final　solution.　Ultimately,　a　case　study　is　investigated　to　simulate　the　system　performance　on　a　realistic　network　of　Chicago　area.　The　results　suggest　that　the　high-capacity　strategy　with　an　incentive　mechanism　can　substantially　benefit　all　the　stakeholders.　Per-vehicle　profit　has　drastically　promoted　from　$82.50　to　$95.00,　meanwhile　regret　utility　and　carbon　emissions　decline　to　some　extent.　The　best　incentive　discount　for　the　high-capacity　vehicle　strategy　is　approximately　0.2.　Overall,　this　study　is　significantly　conducive　to　providing　a　new　strategy　to　promote　economic-social-environmental　sustainability.