As　one　of　the　most　prevalent　we-media,　short　video　has　exponentially　grown　and　gradually　fallen　into　the　disaster　area　of　infringement.　Video　fingerprint　extraction　technology　is　conducive　to　the　intelligent　identification　of　short　video.　In　view　of　various　tampering　attacks,　a　short　video　fingerprint　extraction　method　from　audio-visual　fingerprint　fusion　to　multi-index　hashing　is　proposed,　including:　(1)　the　shot-level　fingerprint　of　short　video　is　extracted　by　audio-visual　fingerprint　fusion　after　analyzing　the　consistency　to　eliminate　the　uncertainty　at　the　decision-making　layer,　in　which　the　visual　fingerprint　is　generated　by　R(2　+　1)D　network,　and　the　audio　fingerprint　is　combined　by　extracting　audio　features　with　masked　audio　spectral　keypoints　(MASK)　and　convolutional　recurrent　neural　network　(CRNN);　(2)　the　shot-level　fingerprints　are　assembled　into　the　data-level　fingerprint　of　short　video　by　constructing　the　data-shot-key　frame　relationship　model　of　data　structure;　(3)　the　short　video　fingerprint　is　matched　by　measuring　the　weighted　Hamming　distance　by　creating　the　multi-index　hashing　of　the　data-level　fingerprint.　Five　experiments　are　conducted　on　the　CC_Web_Video　dataset　and　the　Moments_in_Time_Raw_v2　dataset,　and　the　results　show　that　our　method　can　effectively　raise　the　overall　performance　of　short　video　fingerprint.