Abstract

The study of international laws on energy cooperation between Eurasian Economic Union countries and China is helpful to maintain China's initiative and fairness in the cooperation. In this paper, parallel SVM algorithms are incorporated into the study based on big data fusion to construct global parallel SVM algorithms. Two algorithms, IW-BNAM and BBT-SVM, are used to test the classification accuracy and recognition efficiency of international laws, so as to judge the rationality of the algorithm constructed in this paper. The results show that: BBT-SVM has higher accuracy than MR-C-SVM, MR-NPP-SVM, and MR-CS-SVM in international law classification recognition overall. The average accuracy of MR-C-SVM is 87%, MR-NPP-SVM is 89%, MR-CS-SVM is 87.75%, and BBT- SVM is at the level of 90.25% overall. In terms of recognition efficiency, the IW-BNAW algorithms proposed in this paper all have the highest speedup ratios, which increase with the increase of the number of nodes. It can be seen that the algorithm in this paper has high accuracy, and it is of positive significance to be applied in international cooperation to identify international legal class clauses, etc.