In the domain of machine translation (MT) processing, end-to-end neural machine translation (NMT) has emerged as a remarkable breakthrough, surpassing the conventional statistical MT approaches. Inspired by the Internet of Things (IoT) technology, some researchers are exploring how to integrate device-to-device communication patterns into NMT to enhance translation efficiency. However, the current state-of-the-art NMT models predominantly adopt sequence-based representations for both the source language and target language sentences. The lack of natural language sentence structure attributes leads to problems such as unfaithful translation in NMT. To enhance lexical alignment in NMT, the paper proposes a new transformer MT model that incorporates vocabulary alignment structure. The model receives external lexical alignment information during each step of the decoding process in the decoder design to alleviate the problem of missing lexical alignment structures. During the decoding phase of the model, the statistical MT system plays a crucial role by supplying relevant lexical alignment information derived from the decoding information obtained from the NMT. Additionally, the model suggests vocabulary recommendations based on this lexical alignment information. The experimental results provide evidence that this approach successfully integrates the vocabulary knowledge derived from statistical MT, leading to improved translation performance.