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

Table 7

Results of training the network using only Chinese patent data.

Category	Training set				Test set
	Precision	Recall	-score	Support	Precision	Recall	-score	Support
1	0.92	1.00	0.96	61	0.55	0.66	0.60	35
2	0.79	0.70	0.74	33	0.41	0.39	0.40	18
3	0.80	0.82	0.81	49	0.18	0.19	0.19	21
4	0.61	0.69	0.65	29	0.30	0.30	0.30	10
5	0.42	0.65	0.51	17	0.33	0.38	0.35	8
6	1.00	0.80	0.89	5	0.00	0.00	0.00	3
7	0.00	0.00	0.00	9	0.00	0.00	0.00	3
8	0.00	0.00	0.00	5	0.00	0.00	0.00	2
Microavg	0.76	0.76	0.76	208	0.40	0.40	0.40	100
Macroavg	0.57	0.58	0.57	208	0.22	0.24	0.23	100