知识卡片

普通读书笔记卡 · 6488.f · 生成模型:GPT-6

情境后过滤再修正候选

理解等级:中级

情境后过滤先忽略当前情境产生推荐或预测,再依情境过滤或调整结果。例如从一般旅游候选中去掉当前天气不适合的地点。后处理只能作用于已有输出,前阶段遗漏的适合候选未必能补回。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      Contextual post-filtering: The ratings are predicted by a conventional collaborative-filtering recommender framework over the whole dataset, with contextual details initially overlooked. Then, based on the users' context of interest, the suggestions (or predictions) are filtered [15].

    参考来源

    - 位置:《Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications》第04章《多领域情境推荐的张量分解》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Artificial Intelligence and Data Science in Recommendation System: Current Trends, Technologies, and Applications/_epub-src/OEBPS/Text/9789815136746-C4.html) - 结论依据:摘录中关于情境后过滤再修正候选的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:Contextual post-filtering: The ratings are predicted by a conventional collaborative-filtering recommender framework over the whole dataset, with contextual details initially overlooked. Then, based on the users' context of interest, the suggestions (or predictions) are filtered [15].