amz_review_analyse/prompts/extraction/examples.yaml
OnesvmWhoops 2441c9119c Initial commit: VOC LLM 结构化分析流水线
包含七步编排入口、结构化/向量化/聚类/词频/报告模块与 prompts 配置;忽略原始 CSV 与本地密钥。

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-03 15:40:13 +08:00

69 lines
3.2 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Few-shot 示例:output 为 YAML 对象,程序自动转为 JSON 字符串
- instruction: "示例 1 教学:展示正常长评论如何标准提取,如何准确分类产品优点、缺陷以及物流问题。"
review: "Bought this for my 12yo lab who struggles with stairs. It is very soft and helps her get onto the bed easily. But the zipper broke after a week and the shipping box was damaged."
output:
audience: "12yo lab"
pain_points:
- "struggles with stairs"
- "difficulty getting onto bed"
product_feedback:
- aspect: "fabric"
opinion: "very soft"
sentiment: Positive
category: Quality
- aspect: "zipper"
opinion: "broke after a week"
sentiment: Negative
category: Quality
- aspect: "shipping box"
opinion: "damaged"
sentiment: Negative
category: Logistics
- instruction: "示例 2 教学:防混淆与隐性属性提炼。什么是「产品缺陷(如讲太快)」,它属于 product_feedback,绝不是 pain_points(用户需求)!并提炼出 teaching speed 这个隐性反馈对象。"
review: "The course content is good, the teacher speaks too fast, can't keep up."
output:
audience: "student"
pain_points: []
product_feedback:
- aspect: "course content"
opinion: "good"
sentiment: Positive
category: Quality
- aspect: "teaching speed"
opinion: "too fast to keep up"
sentiment: Negative
category: Function
- instruction: "示例 3 教学:深度上下文推理。如何通过动作(抓跳蚤)推理出使用者(pet),如何通过「全家能睡觉」推理出用户需求(失眠),以及如何将「Worth every penny」准确归类为对 Price(价格)的产品反馈。"
review: "Finally found something that stops the midnight flea scratching! The chemical smell is a bit strong initially, but it fades. Worth every penny since our family can finally sleep."
output:
audience: "pet"
pain_points:
- "midnight flea scratching"
- "sleep deprivation"
product_feedback:
- aspect: "chemical smell"
opinion: "strong initially but fades"
sentiment: Neutral
category: Quality
- aspect: "price"
opinion: "worth every penny"
sentiment: Positive
category: Price
- instruction: "示例 4 教学:保留关键成分与症状等核心具体词汇。绝不能将带有具体成分/病症的词泛化提取。例如遇到「chicken flavor」(鸡肉风味)或「joint pain」(关节疼痛)时,必须保留核心修饰词,绝不能错误缩减提取为「flavor」或「pain」。"
review: "My elderly cat suffers from severe joint pain. But he is very attracted by the chicken flavor of this supplement! It really helps him walk better."
output:
audience: "elderly cat"
pain_points:
- "severe joint pain"
product_feedback:
- aspect: "chicken flavor"
opinion: "very attracted"
sentiment: Positive
category: Quality
- aspect: "mobility improvement"
opinion: "helps walk better"
sentiment: Positive
category: Function