This　article　focuses　on　employing　the　dynamic　programming　algorithm　to　solve　the　large-scale　group　decision-making　problems,　where　the　preference　information　takes　the　form　of　linguistic　variables.　Specifically,　considering　the　linguistic　variables　cannot　be　directly　computed,　the　interval　type-2　fuzzy　sets　are　employed　to　encode　them.　Then,　new　distance　model　and　similarity　model　are　respectively　developed　to　measure　the　relationships　between　the　interval　type-2　fuzzy　sets.　After　that,　a　dynamic　programming　algorithm-based　clustering　model　is　proposed　to　cluster　the　decision-makers　from　the　overall　perspective.　Moreover,　by　taking　both　the　cluster　center　and　the　group　size　into　consideration,　a　new　model　is　introduced　to　determine　the　weights　of　clusters　and　decision-makers,　respectively.　Finally,　a　centroid-based　ranking　method　is　developed　to　compare　and　rank　the　alternatives,　and　two　illustrative　experiments　are　provided　to　illustrate　the　effectiveness　of　the　proposed　method.　Comparisons　and　discussions　are　also　conducted　to　verify　its　superiority.　©　1993-2012　IEEE.