arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03633cs.CL
收藏

CARE:一个引导客服代表阅读用户手册的线索辅助助手

CARE: A Clue-guided Assistant for CSRs to Read User Manuals

College of Computer Science, Sichuan University(四川大学计算机学院);Dalian University of Technology(大连理工大学);University of Electronic Science and Technology(电子科技大学)

Weihong Du, Jia Liu, Zujie Wen, Dingnan Jin, Hongru Liang, Wenqiang Lei

AI总结:

提出CARE阅读助手,通过显式线索链和自监督策略帮助客服代表从用户手册中快速找到准确回复,实验证明其能显著减少阅读时间并保持高服务质量。

摘要:

为客服代表(CSRs)构建一个阅读用户手册的阅读助手非常节省时间,尤其是信息丰富的手册。当前的解决方案由于缺乏对用户问题和可能回复的关注,不太适合在线客服场景。因此,我们提出为 CSRs 开发一个省时且细致的阅读助手,名为 CARE。它可以通过显式的线索链帮助 CSRs 从用户手册中快速找到合适的回复。具体而言,每条线索链都是通过对用户手册进行推理形成的,从与用户问题对齐的问题线索开始,到可能的回复结束。为了克服监督数据的短缺,我们采用自监督策略进行模型学习。离线实验表明,CARE 能够高效地从用户手册中自动推断出准确的回复。在线实验进一步证明了 CARE 的优越性,能够减轻 CSRs 的阅读负担并保持高服务质量,特别是耗时减少了 >35%,并保持 >0.75 的 ICC 得分。

英文摘要:

It is time-saving to build a reading assistant for customer service representations (CSRs) when reading user manuals, especially information-rich ones. Current solutions don't fit the online custom service scenarios well due to the lack of attention to user questions and possible responses. Hence, we propose to develop a time-saving and careful reading assistant for CSRs, named CARE. It can help the CSRs quickly find proper responses from the user manuals via explicit clue chains. Specifically, each of the clue chains is formed by inferring over the user manuals, starting from the question clue aligned with the user question and ending at a possible response. To overcome the shortage of supervised data, we adopt the self-supervised strategy for model learning. The offline experiment shows that CARE is efficient in automatically inferring accurate responses from the user manual. The online experiment further demonstrates the superiority of CARE to reduce CSRs' reading burden and keep high service quality, in particular with >35% decrease in time spent and keeping a >0.75 ICC score.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑