The　concepts　of　four　parameters　of　nominal　water-cement　ratio,　equivalent　water-cement　ratio,　average　paste　thickness,　fly　ash-binder　ratio　were　introduced.　It　was　verified　that　the　four　parameters　and　the　mix　proportion　of　mortar　can　be　transformed　each　other.　The　behaviors　(strength,　workability,　et　al.)　of　mortar　primarily　determined　by　the　mix　proportion　of　mortar　now　depend　on　the　four　parameters.　The　prediction　models　of　strength　and　workability　of　mortar　were　built　based　on　artificial　neural　networks　(ANNs).　The　calculation　models　of　average　paste　thickness　and　equivalent　water-cement　ratio　of　mortar　can　be　obtained　by　the　reversal　deduction　of　the　two　prediction　models,　respectively.　A　mortar　mix　proportion　design　algorithm　was　proposed.　The　proposed　mortar　mix　proportion　design　algorithm　is　expected　to　reduce　the　number　of　trial　and　error,　save　cost,　laborers　and　time.