Customs Commodity Classification Method Based on the Fusion of Text Sequence and Graph Information

Abstract

In today's prevalent international trade, the customs clearance and flow of massive import and export commodities bring enormous audit and regulatory pressure to ports of entry. With the rise of artificial intelligence, many researchers have explored deep learning technology to assist import and export commodity classification and audit. However, the text of the commodity declaration needs to be structured and arranged according to the customs audit rules, resulting in its lack of continuous context, and the elements in the text present complex joint discriminative relationships; it is difficult for existing algorithms to classify commodities accurately based on the unprocessed commodity declaration text. In order to solve the above problems, this paper proposes a fusing text sequence and graph information (FTSGI) neural network. The model comprises the following components: (a) The sequence learning module identifies sequential features and filters out irrelevant details. (b) The key element identification mechanism (KEIM) distinguishes between ordinary and key declaration elements. (c) The graph learning module introduces graph features by modeling the relationships between crucial declaration elements, capturing the interdependencies between textual elements. Compared to other models that have achieved state-of-the-art performance on text classification tasks, FTSGI demonstrates superior performance on real customs datasets.