KI-gestützte Weiterleitung von E-Commerce-Support-Tickets

Heim

KI-Prompt-Liste

E-Commerce-Ticket-Klassifizierung

${:__('collect %s',E-Commerce-Ticket-Klassifizierung)}$

Nutzung von Natural Language Processing zur Analyse von Kundensupport-Tickets, Identifizierung der Absicht und Weiterleitung an Logistik-, Qualitäts- oder Rückerstattungsabteilungen zur Verbesserung der Effizienz.

Prompt-Inhalt

Kopieren

Analyze the following e-commerce customer support ticket text to identify the core issue and determine its business category. The content involves common scenarios such as damaged goods, delayed shipping, or refund requests. Extract key entities like order numbers, product names, and problem descriptions. Map the ticket to the most appropriate category based on predefined standards including logistics issues, product quality, after-sales service, and others. If the user expresses strong emotions or uses sensitive language, flag it as high priority. The final output should include the classification result, confidence score, and brief handling suggestions, ensuring clear logic that aligns with actual business operations to help the customer service team quickly triage and prioritize urgent cases.

Kopieren

Analysieren Sie den folgenden Text des E-Commerce-Kundensupport-Tickets, um das Kernproblem zu identifizieren und seine Geschäftskategorie zu bestimmen. Der Inhalt umfasst gängige Szenarien wie beschädigte Waren, Versandverzögerungen oder Rückerstattungsanfragen. Extrahieren Sie Schlüsselentitäten wie Bestellnummern, Produktnamen und Problembeschreibungen. Ordnen Sie das Ticket basierend auf vordefinierten Standards, einschließlich Logistikproblemen, Produktqualität, After-Sales-Service und anderen, der am besten passenden Kategorie zu. Wenn der Benutzer starke Emotionen ausdrückt oder sensible Sprache verwendet, markieren Sie ihn als hohe Priorität. Die endgültige Ausgabe sollte das Klassifizierungsergebnis, den Konfidenzwert und kurze Behandlungsvorschläge enthalten, um eine klare Logik zu gewährleisten, die mit den tatsächlichen Geschäftsvorgängen übereinstimmt, um dem Kundenserviceteam zu helfen, schnell zu sortieren und dringende Fälle zu priorisieren.

Kopieren

Teilen Klicken Sie, um den Link zu kopieren

Kommentare (0)

0/300

Einreichen

Empfehlung

E-Commerce-Ticket-Klassifizierer

Analyze the following raw customer inquiry text submitted via e-commerce channels and classify it into one of four categories: 'Logistics Inquiry', 'Return/Exchange Request', 'Product Quality Complaint', or 'Other Inquiry'. If the text does not clearly indicate a specific business scenario, assign it to 'Other Inquiry'. Output only the category label name without explaining the reasoning process or providing additional suggestions.

E-Commerce-Ticket-Klassifizierer

Act as an intelligent customer service assistant for an e-commerce platform. Receive the raw text of a user's inquiry, analyze its core intent and sentiment, and categorize it into specific business scenarios such as pre-sales consultation, after-sales complaint, logistics inquiry, or return/exchange application. Extract key entities like order numbers, product names, and problem descriptions, then output a structured ticket summary to facilitate quick handling by human agents.

E-Commerce-Support-Ticket-Klassifizierung

Analyze the following e-commerce support ticket text to identify the user's core request and emotional tone, then automatically categorize it into specific business modules such as logistics delay, product quality issue, return/refund application, or general inquiry, while extracting key entities like order ID, product name, and problem description for subsequent manual agent intervention.

E-Commerce Ticket-Klassifizierung

Please read the following customer service message submitted by the user, analyze its core request, and categorize it into one of the predefined ticket types: Logistics Inquiry, Return/Exchange Request, Product Quality Issue, Account Anomaly, or Other. Output only the classification label without explaining the reasoning process, ensuring accurate classification to assist subsequent manual handling.

EC-Kundenservice-QA

Act as a senior e-commerce customer service quality monitoring expert to analyze the provided customer-service dialogue records. Focus on checking if the customer service accurately understood the customer's needs, used standard polite language, effectively resolved complaints or inquiries, and avoided shirking responsibility or emotional responses. Identify key risk points in the dialogue, such as unfulfilled promises, incorrect information, or poor attitude, and provide specific improvement suggestions. The final output should include a dialogue quality score, a description of main issues, and an optimized reply example to ensure improved customer satisfaction and compliance.

E-Commerce CS Antwort

Act as a senior e-commerce customer service expert. Based on the provided order details and common after-sales issues, generate a professional, friendly, and efficient reply text. The reply must include confirmation of the order status, proactive answers to potential issues, and specific solution suggestions. Maintain a polite and empathetic tone, avoiding mechanical template language, ensuring the content is natural, fluent, and effectively resolves customer concerns.