华南理工大学学报（自然科学版）2025，Vol.53Issue(3)：40-49,10.DOI:10.12141/j.issn.1000-565X.240191
基于意图理解驱动的客服知识推荐大模型构建
Customer Service Knowledge Recommendation Large Model Construction Driven by Intent Understanding
摘要
Abstract
With the deepening application of artificial intelligence technology in the field of customer service,tele-communications operators have raised higher standards for the accuracy of AI service knowledge recommendations.To enhance the efficiency and accuracy of knowledge recommendation in telecommunications operators'AI cus-tomer service systems,this paper proposed a large-scale customer service knowledge recommendation model driven by intent understanding.Firstly,the synonym and dialogue sequence keyword extraction model was employed to identify key terms in user queries.These keywords were then matched with questions in a standard question bank using semantic similarity comparison techniques to generate the most relevant standard questions.Additionally,a generative agent technology framework was utilized to construct and enrich the standard question bank,enabling the automatic generation of knowledge questions.The extracted standard questions were input into the ChatGLM2-6B large language model,which has been pre-trained and aligned with human preferences,further improving the accu-racy of knowledge recommendations.The experimental results show that after the introduction of the standard ques-tion bank,the accuracy of the intelligent recommendation system in specific industry knowledge domains signifi-cantly increased from 74.8%to 85.9%.Multiple sets of comparative experimental results further validate the effec-tiveness of the strategy of establishing a standard question bank in improving accuracy.The large model discussed in this paper optimized the intelligent knowledge recommendation for operator AI customer service,providing new ideas and technical support for the knowledge recommendation in telecommunications operators'AI customer ser-vice systems.With this model,operators can more effectively understand and respond to customer inquiries,signifi-cantly enhancing the customer service experience.关键词
意图理解/AI客服/生成式大语言模型/关键词提问/提示示例Key words
intent understanding/AI customer service/large language model/keyword-based questioning/prompt example分类
信息技术与安全科学引用本文复制引用
马晓亮,高洁,刘英,裴庆祺,赵汝强,杨邦兴,邓从健..基于意图理解驱动的客服知识推荐大模型构建[J].华南理工大学学报（自然科学版）,2025,53(3):40-49,10.基金项目
国家重点研发计划项目(2021YFB2700600) Supported by the National Key R&D Program of China(2021YFB2700600) （2021YFB2700600）
