你是反馈分析师，一位把用户的抱怨、吐槽、建议变成产品金矿的翻译官。你知道用户的原话往往不是他们真正的需求，你的工作是透过表面找到根因，给团队可执行的洞察。
from dataclasses import dataclass, field
from collections import Counter
from datetime import datetime
from enum import Enum
from typing import List, Optional
class Severity(Enum):
CRITICAL = "critical"
HIGH = "high"
MEDIUM = "medium"
LOW = "low"
class Category(Enum):
BUG = "bug"
FEATURE_REQUEST = "feature_request"
UX_ISSUE = "ux_issue"
PERFORMANCE = "performance"
PRAISE = "praise"
@dataclass
class Feedback:
id: str
source: str # appstore / zendesk / social / survey
content: str
category: Category
severity: Severity
sentiment: float # -1.0 到 1.0
user_tier: str # free / pro / enterprise
created_at: datetime
tags: List[str] = field(default_factory=list)
class FeedbackAnalyzer:
"""用户反馈分析器"""
def __init__(self, feedbacks: List[Feedback]):
self.feedbacks = feedbacks
def top_issues(self, n: int = 10) -> list:
"""按标签统计 Top N 问题"""
tag_counts = Counter()
for fb in self.feedbacks:
if fb.category != Category.PRAISE:
for tag in fb.tags:
tag_counts[tag] += 1
return tag_counts.most_common(n)
def severity_distribution(self) -> dict:
"""严重程度分布"""
dist = Counter(fb.severity.value for fb in self.feedbacks)
total = len(self.feedbacks)
return {k: {"count": v, "pct": f"{v/total:.1%}"}
for k, v in dist.items()}
def sentiment_by_tier(self) -> dict:
"""各用户层级的情感得分"""
tier_scores = {}
for fb in self.feedbacks:
tier_scores.setdefault(fb.tier, []).append(fb.sentiment)
return {tier: sum(s)/len(s)
for tier, s in tier_scores.items()}
def weekly_report(self) -> str:
"""生成周报摘要"""
total = len(self.feedbacks)
top = self.top_issues(5)
critical = sum(
1 for fb in self.feedbacks
if fb.severity == Severity.CRITICAL
)
return (
f"本周收到 {total} 条反馈，"
f"其中 {critical} 条严重问题。\n"
f"Top 5 问题：{', '.join(t[0] for t in top)}"
)