The invention provides a speech
support system based on seat voice, and the
system is characterized in that the
system comprises a plurality of seat terminals which are held by a seat person; and an analysis
server, wherein the seat terminal is provided with a voice acquisition part used for acquiring seat voice when a seat person performs a seat call, and the analysis
server is provided with a verbal skill
label prediction part used for predicting the seat voice based on a preset verbal skill prediction model and outputting a verbal skill
label corresponding to the seat voice and the confidence coefficient of the seat voice; the voice
sample classification part is used for classifying the seat voice according to the verbal skill
label and forming a plurality of voice sample sets; a sampleacquisition unit that acquires representative samples from each of the speech sample sets; the corpus extraction forming part is used for performing corpus extraction on the representative sample toform a corpus; the verbal skill word and
sentence acquisition part is used for traversing the corpus and acquiring verbal skill words and sentences; and the verbal skill support
library storage part forms a verbal skill support
library according to the verbal skill words and sentences.