Files
nexus/wiki/concepts/Quality-Scoring-Algorithm.md

30 lines
1.1 KiB
Markdown
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.
---
title: "Quality Scoring Algorithm"
type: concept
tags: []
---
## Definition
多维度加权评分算法——通过 priority source优先级来源、multi-source多源交叉验证、recency时效性和 engagement互动量四个维度对内容进行加权评分过滤噪音提升信息价值。
## Formula
```
score = priority_source(×3) + multi_source(×5) + recency(×2) + engagement(×1)
```
## Dimensions
| 维度 | 权重 | 说明 |
|------|------|------|
| priority_source | +3 | 高质量来源(如 OpenAI Blog、Hacker News |
| multi_source | +5 | 多源同时报道同一事件 |
| recency | +2 | 发布时间距现在越近分数越高 |
| engagement | +1 | 社交媒体互动量(点赞/转发/评论) |
## Use Cases
- [[multi-source-tech-news-digest]] — 科技新闻质量评分
- 任何需要从大量来源中筛选高价值内容的场景
## Related Concepts
- [[Semantic-Deduplication]] — 与评分算法配合,先去重再评分
- [[Daily-Digest]] — 评分结果最终投递为每日简报