Auto-sync: 2026-04-22 20:55

This commit is contained in:
2026-04-22 20:55:52 +08:00
parent e8ad058cdd
commit 087e05cf73
27 changed files with 1567 additions and 9 deletions

View File

@@ -0,0 +1,42 @@
---
title: "Intent Classification"
type: concept
tags: []
sources: []
---
# Intent Classification
## Definition
AI 自动识别客户消息的意图Purpose / Goal将非结构化自然语言映射为预定义的分类标签从而触发对应的处理策略和回复逻辑。
## Common Intent Categories
| Intent | Trigger Keywords | Handling Strategy |
|--------|-----------------|-------------------|
| **FAQ** | "how much", "do you offer", "what is" | 从知识库检索答案并回复 |
| **Appointment** | "book", "schedule", "available", "reservation" | 检查可用性并确认预约 |
| **Complaint** | "frustrated", "refund", "terrible", "problem" | 标记人工审核 + 确认收到 |
| **Review** | "google review", "rating", "stars" | 感谢反馈 + 回应问题 |
| **Order Status** | "where is my order", "tracking", "delivery" | 查询系统返回状态 |
## Implementation
Intent Classification 通常通过 LLM 的 Function Calling 或 Prompt Engineering 实现:
```
User Message → LLM Intent Classification → Match Intent to Handler → Generate Response
```
在 [[OpenClaw]] 中通过 AGENTS.md 配置 `Classify intent` 步骤实现。
## Related Concepts
- [[Unified-Inbox]]:意图分类应用于统一收件箱中的每条消息
- [[Business-Knowledge-Base]]FAQ 意图依赖知识库检索
- [[Human-Handoff]]:投诉意图触发人工升级
## Sources
- [[multi-channel-customer-service]]