Elasticsearch的高价玩法--拼音、同义词、自动补全、多字段按权重综合排序

爱埋珊瑚海～～2024-12-13 12:25

介绍

基于 Elasticsearch 自定义扩展功能。我们将在其基础上构建拼音支持、同义词和自动更正。

安装扩展插件

cd elasticsearch-7.17.9/bin

./elasticsearch-plugin install https://get.infini.cloud/elasticsearch/analysis-pinyin/7.17.9

创建索引

使用curl命令操作elasticsearch 建立索引

markup 复制代码 
curl -X PUT "http://localhost:9200/test_index" -H 'Content-Type: application/json' -d '
{
    "settings":{
        "analysis":{
            "analyzer":{
                "pinyin_analyzer":{
                    "tokenizer":"my_pinyin"
                },
                "ik_max_syno":{
                    "tokenizer":"ik_max_word",
                    "filter":"my_synonym"
                },
                "ik_smart_syno":{
                    "tokenizer":"ik_smart",
                    "filter":"my_synonym"
                }
            },
            "tokenizer":{
                "my_pinyin":{
                    "type":"pinyin",
                    "keep_first_letter":true,
                    "keep_separate_first_letter":false,
                    "keep_full_pinyin":true,
                    "keep_original":false,
                    "limit_first_letter_length":16,
                    "lowercase":true,
                    "remove_duplicated_term":true
                }
            },
            "filter":{
                "my_synonym":{
                    "type":"synonym_graph",
                    "synonyms_path":"analysis/synonyms.txt"
                    // ,"updateable": true
                }
            }
        }
    },
    "mappings":{
        "properties":{
            "name":{
                "type":"text",
                "analyzer":"standard",
                "fields":{
                    "keyword":{
                        "type":"keyword",
                        "ignore_above":256,
                        "doc_values":false
                    },
                    "pinyin":{
                        "type":"text",
                        "analyzer":"pinyin_analyzer"
                    },
                    "ik":{
                        "type":"text",
                        "analyzer":"ik_max_syno",
                        "search_analyzer":"ik_smart_syno"
                    },
                    "suggest":{
                        "type":"completion",
                        "analyzer":"ik_max_syno",
                        "search_analyzer":"ik_smart_syno",
                        "preserve_separators": "false",
                        "preserve_position_increments": "true",
                        "max_input_length": 50
                    }
                }
            },
            "remark":{
                "type":"text",
                "analyzer":"standard",
                "fields":{
                    "keyword":{
                        "type":"keyword",
                        "ignore_above":256,
                        "doc_values":false
                    },
                    "pinyin":{
                        "type":"text",
                        "analyzer":"pinyin_analyzer"
                    },
                    "ik":{
                        "type":"text",
                        "analyzer":"ik_max_syno",
                        "search_analyzer":"ik_smart_syno"
                    },
                    "suggest":{
                        "type":"completion",
                        "analyzer":"ik_max_syno",
                        "search_analyzer":"ik_smart_syno",
                        "preserve_separators": "false",
                        "preserve_position_increments": "true",
                        "max_input_length": 50
                    }
                }
            },
            "category":{
                "type":"keyword",
                "doc_values":false
            },
            "tag":{"type":"keyword"},
            "rating":{
              "type":"scaled_float",
              "scaling_factor": 10
            },
            "times":{
              "type":"integer"
            }
        }
    }
}'

插入示例数据

markup 复制代码 
curl -X POST "http://localhost:9200/test_index/_bulk" -H 'Content-Type: application/json' -d'
{ "index": { "_id": 1 } }
{ "name": "番茄炒蛋", "remark": "番茄, 鸡蛋", "category": "家常菜", "tag": ["简单", "营养"] , "rating": 2.0,"times":100}
{ "index": { "_id": 2 } }
{ "name": "宫保鸡丁", "remark": "鸡胸肉, 干辣椒, 花生", "category": "川菜", "tag": ["辣", "下饭"], "rating": 3.4,"times":80 }
{ "index": { "_id": 3 } }
{ "name": "蒸蛋羹", "remark": "水,盐,蛋,麻油,生抽", "category": "川菜", "tag": ["辣", "下饭"] , "rating": 4.8,"times":20}
{ "index": { "_id": 4 } }
{ "name": "水煮蛋", "remark": "水,蛋", "category": "川菜", "tag": ["下饭"] , "rating": 4.9,"times":30}
{ "index": { "_id": 5 } }
{ "name": "酒酿蛋花年糕", "remark": "水,糖,蛋白,酒酿", "category": "家常菜", "tag": [ "简单","营养", "快手菜"] , "rating": 5.0,"times":50}
'

拼音搜索示例

markup 复制代码 
curl -X GET "http://localhost:9200/test_index/_search" -H 'Content-Type: application/json' -d'
{
  "query": {
    "multi_match": {
      "query": "fanqie",
      "fields": [
        "name.pinyin^4",
        "name.ik^5",
        "remark.pinyin^2",
        "remark.ik^3"
      ],
      "operator": "or"
    }
  },
  "size": 15, 
  "sort": [
    {
      "_score": {
        "order": "desc"
      },
      "times": {
        "order": "desc"
      }
    }
  ]
  ,
  "highlight": {
    "fields": {
      "name": {}
    },
    "highlight_query": {
      "match_phrase": {
        "name": {
          "query": "fanqie"
        }
      }
    }
  }
}'

匹配结果：

{
  "took": 3,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 1,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "1",
        "_score": 13.421699,
        "_source": {
          "name": "番茄炒蛋",
          "remark": "番茄, 鸡蛋",
          "category": "家常菜",
          "tag": [
            "简单",
            "营养"
          ],
          "rating": 3.0,
          "times": 100
        },
        "sort": [
          13.421699,
          100
        ]
      }
    ]
  }
}

同义词搜索示例

markup 复制代码 
curl -X GET "http://localhost:9200/test_index/_search" -H 'Content-Type: application/json' -d'
{
  "query": {
    "multi_match": {
      "query": "西红柿",
      "fields": [
        "name.pinyin^4",
        "name.ik^5",
        "remark.pinyin^2",
        "remark.ik^3"
      ],
      "operator": "or"
    }
  },
  "size": 15, 
  "sort": [
    {
      "_score": {
        "order": "desc"
      },
      "times": {
        "order": "desc"
      }
    }
  ]
  ,
  "highlight": {
    "fields": {
      "name": {}
    },
    "highlight_query": {
      "match_phrase": {
        "name": {
          "query": "西红柿"
        }
      }
    }
  }
}'


匹配结果：
{
  "took": 3,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 1,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "1",
        "_score": 8.388562,
        "_source": {
          "name": "番茄炒蛋",
          "remark": "番茄, 鸡蛋",
          "category": "家常菜",
          "tag": [
            "简单",
            "营养"
          ],
          "rating": 3.0,
          "times": 100
        },
        "sort": [
          8.388562,
          100
        ]
      }
    ]
  }
}

自动补全搜索示例

根据输入的关键字给出关联的建议词

如下是根据输入的关键字匹配两个字段进行自动给出建议词汇

markup 复制代码 
curl -X GET "http://localhost:9200/test_index/_search" -H 'Content-Type: application/json' -d'
{
  "suggest": {
    "nameSuggest": {
      "text": "鸡",
      "completion": {
        "field": "name.suggest"
      }
    },
    "remarkSuggest": {
      "text": "鸡",
      "completion": {
        "field": "remark.suggest"
      }
    }
  }
}'
匹配的结果：
{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 0,
      "relation": "eq"
    },
    "max_score": null,
    "hits": []
  },
  "suggest": {
    "remarkSuggest": [
      {
        "text": "鸡",
        "offset": 0,
        "length": 1,
        "options": [
          {
            "text": "鸡胸肉, 干辣椒, 花生",
            "_index": "test_index",
            "_type": "_doc",
            "_id": "2",
            "_score": 1.0,
            "_source": {
              "name": "宫保鸡丁",
              "remark": "鸡胸肉, 干辣椒, 花生",
              "category": "川菜",
              "tag": [
                "辣",
                "下饭"
              ],
              "rating": 3.4,
              "times": 80
            }
          }
        ]
      }
    ],
    "nameSuggest": [
      {
        "text": "鸡",
        "offset": 0,
        "length": 1,
        "options": []
      }
    ]
  }
}

多字段按照权重综合排序

markup 复制代码 
curl -X GET "http://localhost:9200/test_index/_search" -H 'Content-Type: application/json' -d'
{
  "query": {
    "function_score": {
     
      "functions": [
        {
          "field_value_factor": {
            "field": "rating",
            "factor": 5,  // name 字段的权重最大
            "modifier": "none",
            "missing": 1  // 如果字段为空，则使用默认值 1
          }
        },
        {
          "field_value_factor": {
            "field": "times",
            "factor": 3,  // title 字段的权重次之
            "modifier": "none",
            "missing": 1
          }
        }
      ],
      "score_mode": "sum",  // 将所有字段的得分加总
      "boost_mode": "multiply"  // 将查询得分与函数得分相乘
    }
  
  },
  "size": 10, 
  "sort": [
    {
      "_score": {
        "order": "desc"
      }
    }
  ]
}'

匹配结果：
{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 6,
      "relation": "eq"
    },
    "max_score": null,
    "hits": [
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "1",
        "_score": 315.0,
        "_source": {
          "name": "番茄炒蛋",
          "remark": "番茄, 鸡蛋",
          "category": "家常菜",
          "tag": [
            "简单",
            "营养"
          ],
          "rating": 3.0,
          "times": 100
        },
        "sort": [
          315.0
        ]
      },
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "2",
        "_score": 257.0,
        "_source": {
          "name": "宫保鸡丁",
          "remark": "鸡胸肉, 干辣椒, 花生",
          "category": "川菜",
          "tag": [
            "辣",
            "下饭"
          ],
          "rating": 3.4,
          "times": 80
        },
        "sort": [
          257.0
        ]
      },
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "5",
        "_score": 174.0,
        "_source": {
          "name": "酒酿蛋花年糕",
          "remark": "水,糖,蛋白,酒酿",
          "category": "家常菜",
          "tag": [
            "简单",
            "营养",
            "快手菜"
          ],
          "rating": 4.8,
          "times": 50
        },
        "sort": [
          174.0
        ]
      },
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "4",
        "_score": 114.5,
        "_source": {
          "name": "水煮蛋",
          "remark": "水,蛋",
          "category": "家常菜",
          "tag": [
            "简单",
            "营养",
            "快手菜"
          ],
          "rating": 4.9,
          "times": 30
        },
        "sort": [
          114.5
        ]
      },
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "3",
        "_score": 84.0,
        "_source": {
          "name": "蒸蛋羹",
          "remark": "水,盐,蛋,麻油,生抽",
          "category": "川菜",
          "tag": [
            "辣",
            "下饭"
          ],
          "rating": 4.8,
          "times": 20
        },
        "sort": [
          84.0
        ]
      },
      {
        "_index": "test_index",
        "_type": "_doc",
        "_id": "6",
        "_score": 83.0,
        "_source": {
          "name": "牛奶麵包",
          "remark": "奶油,牛奶,糖,3颗蛋",
          "category": "家常菜",
          "tag": [
            "简单",
            "营养",
            "快手菜"
          ],
          "rating": 4.6,
          "times": 20
        },
        "sort": [
          83.0
        ]
      }
    ]
  }
}
相关推荐
TDengine （老段）5 分钟前
TDengine 中的关联查询
大数据·javascript·网络·物联网·时序数据库·tdengine·iotdb
这个懒人2 小时前
深入解析Translog机制：Elasticsearch的数据守护者
数据库·elasticsearch·nosql·translog
直裾4 小时前
Mapreduce的使用
大数据·数据库·mapreduce
愿你天黑有灯下雨有伞6 小时前
Docker 安装 Elasticsearch 教程
运维·elasticsearch·docker
麻芝汤圆7 小时前
使用 MapReduce 进行高效数据清洗：从理论到实践
大数据·linux·服务器·网络·数据库·windows·mapreduce
树莓集团7 小时前
树莓集团海南落子：自贸港布局的底层逻辑
大数据
不剪发的Tony老师7 小时前
Hue：一个大数据查询工具
大数据
靠近彗星7 小时前
如何检查 HBase Master 是否已完成初始化？| 详细排查指南
大数据·数据库·分布式·hbase
墨染丶eye8 小时前
数据仓库项目启动与管理
大数据·数据仓库·spark
SelectDB8 小时前
Apache Doris 2025 Roadmap：构建 GenAI 时代实时高效统一的数据底座
大数据·数据库·aigc
热门推荐
01我决定放弃搞 Java 了02DeepSeek各版本说明与优缺点分析03如何在WPS和Word/Excel中直接使用DeepSeek功能04RAG 实践- Ollama+RagFlow 部署本地知识库05本地化部署AI知识库：基于Ollama+DeepSeek+AnythingLLM保姆级教程06从零安装 LLaMA-Factory 微调 Qwen 大模型成功及所有的坑07如何本地部署AI智能体平台，带你手搓一个AI Agent08苍穹外卖面试总结09DeepSeek RAGFlow构建本地知识库系统10【芯片封测学习专栏 -- D2D 和 C2C 之间的区别】