Named Entity Recognition （NER） aims to identify predefined entity types from unstructured text. Span-based NER methods recognize entities through enumerating all the spans. However， adjacent spans in the text share contextual semantics， which leads to semantic information ambiguity among span boundaries， thus making it difficult for models to capture dependency information among spans. To address the issue of semantic information ambiguity among span boundaries， a multi-objective learning NER model combined with boundary generation was proposed. The model was trained through a multi-objective learning approach jointly through combining NER task with boundary generation task. Among which， the boundary generation task was used as an auxiliary task to guide the model network to focus on boundary information of the spans， thus improving the performance of NER. Tests conducted on the ACE2004， ACE2005， and GENIA datasets show that the proposed model achieves F1 scores of 87.83%， 86.90%， and 81.65%， respectively. Experimental results fully validate the effectiveness of the model on different datasets and also further confirm its superior performance in named entity recognition tasks.