├── README.md ├── SearchEngineBook.pdf └── Slides ├── 01_Basics_01.pdf ├── 01_Basics_02.pdf ├── 01_Basics_03.pdf ├── 01_Basics_04.pdf ├── 02_Rel_01.pdf ├── 02_Rel_02.pdf ├── 02_Rel_03.pdf ├── 02_Rel_04.pdf └── 02_Rel_05.pdf /README.md: -------------------------------------------------------------------------------- 1 | # 搜索引擎技术 2 | 3 | 4 | 5 | 6 | 1. **搜索引擎基础** 7 | 8 | * 搜索引擎的基本概念 9 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/01_Basics_01.pdf)] 10 | [[YouTube](https://youtu.be/ddi6_rGEIdk)] 11 | [[Bilibili](https://www.bilibili.com/video/BV1Wr421b7uP/)] 12 | 13 | * 什么决定用户满意度? 14 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/01_Basics_02.pdf)] 15 | [[YouTube](https://youtu.be/MjdAP_bqMFk)] 16 | [[Bilibili](https://www.bilibili.com/video/BV1Lm421J7Xz/)] 17 | 18 | * 搜索引擎的评价指标 19 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/01_Basics_03.pdf)] 20 | [[YouTube](https://youtu.be/_1_-dvNAMlo)] 21 | [[Bilibili](https://www.bilibili.com/video/BV1BT421m7UQ/)] 22 | 23 | * 搜索引擎的链路 24 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/01_Basics_04.pdf)] 25 | [[YouTube](https://youtu.be/V1BrdtN2d30)] 26 | [[Bilibili](https://www.bilibili.com/video/BV1UM4m1D7L3/)] 27 | 28 | 29 | 30 | 2. **相关性** 31 | 32 | * 相关性的定义与分档 33 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/02_Rel_01.pdf)] 34 | 35 | * 相关性的评价指标 36 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/02_Rel_02.pdf)] 37 | 38 | * 文本匹配分数 39 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/02_Rel_03.pdf)] 40 | 41 | * 相关性BERT模型及其推理 42 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/02_Rel_04.pdf)] 43 | 44 | * 相关性BERT模型的训练 45 | [[slides](https://github.com/wangshusen/SearchEngine/blob/main/Slides/02_Rel_05.pdf)] 46 | 47 | 48 | 3. **查询词处理** 49 | 50 | * 分词:基于字典匹配的方法 & 新词发现 51 | 52 | * 分词:基于深度学习的方法 53 | 54 | * 词权重 (Term Weight) 55 | 56 | * 类目识别 57 | 58 | * 意图识别 59 | 60 | * 查询词改写 61 | 62 | 63 | 64 | 4. **召回** 65 | 66 | * 倒排索引和文本召回 67 | 68 | * 向量召回 69 | 70 | * 缓存召回 71 | 72 | 73 | 74 | 5. **排序** 75 | 76 | * 排序的原理 77 | 78 | * 融合模型的训练方法 79 | 80 | 81 | 82 | 83 | 6. **查询词推荐** 84 | 85 | * 查询词推荐的场景 86 | 87 | * 查询词推荐的召回 88 | 89 | * 查询词推荐的排序 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | -------------------------------------------------------------------------------- /SearchEngineBook.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/SearchEngineBook.pdf -------------------------------------------------------------------------------- /Slides/01_Basics_01.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/01_Basics_01.pdf -------------------------------------------------------------------------------- /Slides/01_Basics_02.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/01_Basics_02.pdf -------------------------------------------------------------------------------- /Slides/01_Basics_03.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/01_Basics_03.pdf -------------------------------------------------------------------------------- /Slides/01_Basics_04.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/01_Basics_04.pdf -------------------------------------------------------------------------------- /Slides/02_Rel_01.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/02_Rel_01.pdf -------------------------------------------------------------------------------- /Slides/02_Rel_02.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/02_Rel_02.pdf -------------------------------------------------------------------------------- /Slides/02_Rel_03.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/02_Rel_03.pdf -------------------------------------------------------------------------------- /Slides/02_Rel_04.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/02_Rel_04.pdf -------------------------------------------------------------------------------- /Slides/02_Rel_05.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wangshusen/SearchEngine/7339c6b126e314abdb74a89adb033d39d8e3d37b/Slides/02_Rel_05.pdf --------------------------------------------------------------------------------