基于深度迁移学习的业务流程实例剩余执行时间预测方法*
|
刘彤,倪维健,孙宇健,曾庆田
|
Predicting Remaining Business Time with Deep Transfer Learning
|
Tong Liu,Weijian Ni,Yujian Sun,Qingtian Zeng
|
|
表2 对比实验结果
|
Table 2 Experiment Results
|
|
方法 | BPIC2012_A | BPIC2012_O | BPIC2012_W | Helpdesk | Hospital_Billing | TS-set | 7.505 | 8.429 | 7.392 | 6.283 | 51.456 | TS-multiset | 7.488 | 8.691 | 7.203 | 6.167 | 51.507 | TS-sequence | 7.488 | 8.619 | 9.612 | 6.192 | 51.504 | SPN | 8.880 | 8.516 | 6.385 | 6.337 | 78.018 | LSTM | 3.588 | 8.021 | 7.993 | 3.542 | 42.050 | GRU | 3.895 | 7.324 | 6.153 | 3.303 | 36.691 | 本文方法(LSTM) | 3.489 | 5.858 | 5.826 | 3.357 | 33.201 | 本文方法(GRU) | 3.512 | 7.306 | 6.338 | 2.677 | 32.227 |
|
|
|