電商客服自動工單分類助手

首頁

AI 提示詞列表

電商客服工單分類

${:__('collect %s',電商客服工單分類)}$

基於自然語言處理技術，自動識別並分類電商客服收到的用戶諮詢與投訴工單，提升響應效率。

提示內容

複製

Analyze the following customer service message received by an e-commerce platform and determine its business category. The categories include: Logistics Inquiry, Return/Exchange Request, Product Quality Complaint, Price Dispute, Account Issue, and Others. Output only the category name without explanation. For instance, if the user says 'My package hasn't moved for three days', classify it as Logistics Inquiry; if the user says 'The clothes faded after washing', classify it as Product Quality Complaint. Accurately categorize the input text.

複製

請分析以下電商客服收到的用戶消息，判斷其所屬的業務類別。業務類別包括：物流查詢、退換貨申請、產品質量投訴、價格爭議、帳戶問題及其他。請僅輸出分類結果，無需解釋原因。例如，若用戶說「我的包裹三天沒動了」，應歸類為物流查詢；若用戶說「衣服洗後褪色」，應歸類為產品質量投訴。請對輸入文本進行準確分類。

複製

分享點擊複製鏈接

評論 (0)

0/300

提交

推薦

電商客服工單分類

Analyze the provided customer inquiry text and categorize it into one of four predefined classes: pre-sales consultation, after-sales service, logistics inquiry, or complaint/suggestion based on business semantics. If an order number is mentioned, extract it; if emotional expression is present, label the sentiment as positive, neutral, or negative. The output must include the classification result, key entity extraction, and sentiment label, ensuring the logic aligns with standard e-commerce customer service protocols without additional explanatory reasoning.

電商工單分類

Act as an intelligent customer service assistant for an e-commerce platform. Receive raw user inquiry text, analyze its core intent and emotional tone, and categorize it into standard classes such as pre-sales consultation, after-sales rights protection, logistics inquiry, or complaint suggestion. Extract key entities like order numbers, product names, and problem descriptions, and finally output structured classification results and handling suggestions for quick human agent intervention.

電商工單分類

Act as a senior e-commerce customer service operations expert. Analyze the provided customer inquiry text and categorize it into one of four types: 'Logistics Inquiry', 'Return/Exchange Request', 'Product Quality Complaint', or 'Other Inquiry'. Briefly explain the reasoning behind your classification based on the key intent of the message.

電商客服智能回覆

Act as a senior e-commerce customer service expert. Draft a response to a customer complaining about a minor scratch on their received item, who is visibly upset. Your reply must start with a sincere apology acknowledging the issue, then offer two specific solutions (e.g., partial refund or free replacement) for the customer to choose from. Conclude with gratitude and a commitment to improvement. Maintain a professional, gentle, yet firm tone, avoiding robotic phrases, ensuring the customer feels valued and respected to effectively resolve the conflict and protect the brand image.

電商客服智能回覆

Act as a senior e-commerce customer service expert. Based on the customer inquiry: 'My order #12345 shows shipped but logistics info hasn't updated for three days, I'm anxious,' and considering the order status is 'In Transit,' estimated delivery is '2023-10-15,' and current logistics node is 'East China Distribution Center,' generate a professional, reassuring, and solution-oriented reply. The response must include an apology for the delay, an explanation of the current logistics status, a specific estimated time for the next update, and proactively offer a compensation plan if delivery is not met, maintaining a friendly yet professional tone without using robotic template language.

電商客服工單分類

Please analyze the following customer message received by an e-commerce support team and determine its business category. The categories include: Logistics Inquiry, Return/Exchange Request, Product Quality Complaint, Price Dispute, and General Consultation. Read the user's input carefully, extract key information such as order numbers, product names, and problem descriptions, and then classify the message into one of the five predefined categories based on established standards. If the message involves multiple issues, select the most urgent or core issue for classification. Finally, output the result in JSON format, including the original message, the predicted category, and a confidence score, ensuring the classification is accurate and meets actual business needs.