Law question and answer method and device based on large model and knowledge guidance

The invention provides a legal question answering method based on a large model and knowledge guidance, and relates to the technical field of laws, and the method comprises the steps: obtaining a question input by a user, and carrying out the preprocessing of the question, and obtaining a question semantic vector; performing matching from the legal database by taking the question and the question semantic vector as indexes to obtain matched data, and performing similarity sorting on the matched data to obtain target data; and performing text generation on the target data through the large language model to obtain a target text. By adopting the scheme, diversified and complex legal question and answer requirements can be met. 本申请提出了一种基于大模型和知识指导的法律问答方法，涉及法律技术领域，其中，该方法包括：获取用户输入的问题，并对问题进行预处理，得到问题语义向量；以问题和问题语义向量为索引从法律数据库中进行匹配，得到匹配数据，并对匹配数据进行相似度排序，得到目标数据；通过大语言模型对目标数据进行文本生成，得到目标文本。采用上述方案的本发明能够满足多样化和复杂的法律问答需求。