Files
nexus/wiki/concepts/Quality-Scoring.md
2026-04-27 20:02:52 +08:00

31 lines
1.0 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"
type: concept
tags: [Ranking, Filtering, AI-Processing]
sources: [multi-source-tech-news-digest.md]
last_updated: 2026-04-27
---
# Quality-Scoring
质量评分——对聚合内容按多维度指标打分,以优先级排序的机制,解决信息过载下的内容筛选问题。
## Definition
通过预设规则或 AI 辅助,对每条内容从多个维度赋予分值(如权威性、时效性、相关性、互动量),综合计算后决定内容的展示优先级。
## Scoring Dimensions
| 维度 | 示例 | 分值范围 |
|------|------|----------|
| 优先级来源 | 权威媒体/KOL/官方账号 | +1 ~ +5 |
| 多来源交叉 | 同一内容被多个来源报道 | +3 ~ +5 |
| 时效性 | 距发布时间越近分数越高 | +1 ~ +3 |
| 互动量 | 点赞/评论/分享数 | +1 ~ +2 |
## Related Concepts
- [[Content-Aggregation]]:质量评分作用于聚合后的内容
- [[Content-Deduplication]]:去重是评分的前置步骤
- [[RAG]]RAG 中的 reranking 与质量评分思路类似