摘要
提供个性化定制服务是"工业4.0"时代服装生产的一大特色,准确理解顾客的个性化需求是保证个性化定制服务质量的前提。但是由于个性化需求有提供形式多样化(语音、文字、图片等)、内容复杂且具有歧义性等特点,给个性化需求提取工作带来了困难,从而制约了对个性化需求的理解。本文针对服装个性化定制需求提取的问题,根据服装设计过程和需求提取流程的特性,为服装个性化定制需求提取问题提供了一套解决方法。该方法首先对需求文本进行分词和词性标注的预处理工作,然后应用有限状态自动机以及模式匹配等理论,通过构建有限自动机,识别由关键词组成的正则语言,从而提取相关的服装属性。
Providing personalized customized service is a major feature of garment production in the era of industry 4.0.Accurate understanding of customer’s personalized needs is the premise to ensure the quality of personalized customized service.However,due to the diversity of forms(voice,text,picture,etc.),complexity and ambiguity of the content,personalized needs extraction work is difficult,which restricts the understanding of personalized needs.According to the characteristics of the process of clothing design and demand extraction,this paper provides a set of solutions for the problem of demand extraction of clothing personalized customization.This method first preprocesses the word segmentation and part of speech tagging of the demand text,then applies the theory of finite state automata and pattern matching to construct the finite automata,recognize the regular language composed of keywords,and extract the related clothing attributes.
作者
唐豪杰
刘国华
TANG Haojie;LIU Guohua(School of Computer Science and Technology,Donghua University,Shanghai 201620,China)
出处
《智能计算机与应用》
2020年第7期61-63,66,共4页
Intelligent Computer and Applications
基金
科技部国家重点研发计划(2017YFB0309800)
上海市工业互联网创新发展专项项目(2019-GYHLW-004)
