Method and device for building prediction model of voice quality MOS (Mean Opinion Score) value

The embodiment of the invention provides a method and device for building a prediction model of a voice quality MOS (Mean Opinion Score) value. The method comprises the following steps of obtaining afirst preset number of original sample data sets, wherein the original sample data sets include an original MOS value and a preset number of original feature values; performing preset data processingon the original sample data sets to obtain a standard sample data set, wherein the standard sample data set comprises a standard MOS value corresponding to the original MOS value and standard featurevalues corresponding to the original feature values; and building the prediction model of the MOS value according to the standard MOS value, the standard feature values and a preset algorithm, whereinthe prediction model is a random forest model. A random forest model algorithm is used for building the prediction model; a method for performing voice quality evaluation by drive tests and MOS box sets can be replaced; during