{"title":"基于自然语言处理技术的电力客服工单文本挖掘策略","authors":"Houen Li, Zhicheng Li, Zhuyi Rao","doi":"10.1109/ICICAS48597.2019.00078","DOIUrl":null,"url":null,"abstract":"In order to improve the level of power customer service, we need to start with natural language processing technology, and conduct in-depth text mining of power customer complaint work order. Combined with the format and characteristics of power customer service work order, this paper proposed a text mining strategy of power customer service work order based on natural language processing technology which includes the following processes: work order data cleaning, text segmentation, information characterization, model training and model evaluation is proposed. The TF-IDF algorithm and the model optimization method based on accuracy calculation are applied in this strategy, which greatly improves the level of power customer service.","PeriodicalId":409693,"journal":{"name":"2019 International Conference on Intelligent Computing, Automation and Systems (ICICAS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Text Mining Strategy of Power Customer Service Work Order Based on Natural Language Processing Technology\",\"authors\":\"Houen Li, Zhicheng Li, Zhuyi Rao\",\"doi\":\"10.1109/ICICAS48597.2019.00078\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In order to improve the level of power customer service, we need to start with natural language processing technology, and conduct in-depth text mining of power customer complaint work order. Combined with the format and characteristics of power customer service work order, this paper proposed a text mining strategy of power customer service work order based on natural language processing technology which includes the following processes: work order data cleaning, text segmentation, information characterization, model training and model evaluation is proposed. The TF-IDF algorithm and the model optimization method based on accuracy calculation are applied in this strategy, which greatly improves the level of power customer service.\",\"PeriodicalId\":409693,\"journal\":{\"name\":\"2019 International Conference on Intelligent Computing, Automation and Systems (ICICAS)\",\"volume\":\"44 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 International Conference on Intelligent Computing, Automation and Systems (ICICAS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICICAS48597.2019.00078\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference on Intelligent Computing, Automation and Systems (ICICAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICICAS48597.2019.00078","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Text Mining Strategy of Power Customer Service Work Order Based on Natural Language Processing Technology
In order to improve the level of power customer service, we need to start with natural language processing technology, and conduct in-depth text mining of power customer complaint work order. Combined with the format and characteristics of power customer service work order, this paper proposed a text mining strategy of power customer service work order based on natural language processing technology which includes the following processes: work order data cleaning, text segmentation, information characterization, model training and model evaluation is proposed. The TF-IDF algorithm and the model optimization method based on accuracy calculation are applied in this strategy, which greatly improves the level of power customer service.