Entity relation extraction model training method and system based on dynamic labels

The invention relates to an entity relation extraction model training method and system based on dynamic tags, belongs to the technical field of data processing, and solves the problem of low accuracy of a relation extraction model when samples are unbalanced in the prior art. Comprising the following steps: preprocessing a historical quality problem analysis report, constructing a sample set, and dividing the sample set into a training set and a test set; constructing a PCNN model, training the PCNN model based on the training set, and dynamically updating each relationship category label value corresponding to each training sample according to a current training result until the training is finished, thereby obtaining a trained PCNN model; verifying the PCNN model based on the test set, updating the sample weight of each relation category according to a verification result when the model accuracy is smaller than a threshold value, expanding the training set according to the updated sample weight of each rel