評估、整合與提升客戶支援對話效能

摘要

有效的客戶支援不僅需要精確的問題解決能力，還需遵循專業標準，進行結構化且富有同理心的溝通。然而，現有的對話數據集往往缺乏策略性指導，且現實中的服務數據難以獲取與標註。為此，我們提出了客戶支援對話（Customer Support Conversation, CSC）任務，旨在培訓客服人員運用明確的支援策略進行回應。我們基於COPC指南提出了一個結構化的CSC框架，定義了五個對話階段及十二種策略，以引導高質量的互動。基於此框架，我們構建了CSConv，這是一個包含1,855條真實客戶與客服對話的評估數據集，這些對話經由大型語言模型（LLM）重寫，以體現策略的刻意運用，並進行了相應的標註。此外，我們開發了一種角色扮演方法，利用與CSC框架對齊的LLM驅動角色模擬富含策略的對話，從而產生了訓練數據集RoleCS。實驗表明，在RoleCS上對強力LLM進行微調，能顯著提升其在CSConv上生成高質量、策略對齊回應的能力。人類評估進一步證實了問題解決能力的提升。所有代碼與數據將公開於https://github.com/aliyun/qwen-dianjin。

English

Effective customer support requires not only accurate problem solving but also structured and empathetic communication aligned with professional standards. However, existing dialogue datasets often lack strategic guidance, and real-world service data is difficult to access and annotate. To address this, we introduce the task of Customer Support Conversation (CSC), aimed at training customer service agents to respond using well-defined support strategies. We propose a structured CSC framework grounded in COPC guidelines, defining five conversational stages and twelve strategies to guide high-quality interactions. Based on this, we construct CSConv, an evaluation dataset of 1,855 real-world customer-agent conversations rewritten using LLMs to reflect deliberate strategy use, and annotated accordingly. Additionally, we develop a role-playing approach that simulates strategy-rich conversations using LLM-powered roles aligned with the CSC framework, resulting in the training dataset RoleCS. Experiments show that fine-tuning strong LLMs on RoleCS significantly improves their ability to generate high-quality, strategy-aligned responses on CSConv. Human evaluations further confirm gains in problem resolution. All code and data will be made publicly available at https://github.com/aliyun/qwen-dianjin.