Applying Deep Learning Technologies to Evaluate the Patent Quality with the Collaborative Training

Table 6

Final results of different migration parts.

Migration layer	Training set (microavg/macroavg)						Test set (microavg/macroavg)
	Precision		Recall		-score		Precision		Recall		-score
0-14	0.85	0.70	0.85	0.68	0.85	0.69	0.61	0.38	0.60	0.44	0.60	0.41
2-14	0.83	0.70	0.83	0.63	0.83	0.66	0.66	0.43	0.65	0.46	0.65	0.44
3-14	0.82	0.66	0.82	0.65	0.82	0.65	0.66	0.61	0.66	0.54	0.66	0.57
7-14	0.78	0.66	0.77	0.60	0.77	0.63	0.60	0.44	0.60	0.38	0.60	0.41
9-14	0.60	0.43	0.60	0.39	0.60	0.41	0.58	0.44	0.58	0.36	0.58	0.40
11-14	0.53	0.37	0.53	0.34	0.53	0.35	0.52	0.42	0.52	0.35	0.52	0.38