白话Elasticsearch12-深度探秘搜索技术之基于multi_match + best fields语法实现dis_max+tie_breaker

文章目录

概述

继续跟中华石杉老师学习ES，第十二篇

 ​

---

官网

https://www.elastic.co/guide/en/elasticsearch/reference/7.2/query-dsl-multi-match-query.html

---

示例

GET /forum/article/_search
{
  "query": {
    "dis_max": {
      "queries": [
        {
          "match": {
            "title": {
              "query": "java beginner",
              "minimum_should_match": "50%",
              "boost": 2
            }
          }
        },
        {
          "match": {
            "content": {
              "query": "java beginner",
              "minimum_should_match": "50%"
            }
          }
        }
      ],
      "tie_breaker": 0.3
    }
  }
}

可以简化为

GET /forum/article/_search
{
  "query": {
    "multi_match": {
      "query": "java beginner",
      "type": "best_fields",
      "fields": [
        "title^2",
        "content"
      ],
      "tie_breaker": 0.3,
      "minimum_should_match": "50%"
    }
  }
}

minimum_should_match的主要用途 ： 去长尾，long tail

长尾是什么呢，举个例子：假设你搜索5个关键词，但是很多结果是只匹配1个关键词的，其实跟你想要的结果相差甚远，这些结果就是长尾

minimum_should_match，控制搜索结果的精准度，只有匹配一定数量的关键词的数据，才能返回

---

返回结果

{
  "took": 1,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": 5,
    "max_score": 1.4387287,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 1.4387287,
        "_source": {
          "articleID": "KDKE-B-9947-#kL5",
          "userID": 1,
          "hidden": false,
          "postDate": "2017-01-02",
          "tag": [
            "java"
          ],
          "tag_cnt": 1,
          "view_cnt": 50,
          "title": "this is java blog",
          "content": "i think java is the best programming language"
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "4",
        "_score": 1.2162449,
        "_source": {
          "articleID": "QQPX-R-3956-#aD8",
          "userID": 2,
          "hidden": true,
          "postDate": "2017-01-02",
          "tag": [
            "java",
            "elasticsearch"
          ],
          "tag_cnt": 2,
          "view_cnt": 80,
          "title": "this is java, elasticsearch, hadoop blog",
          "content": "elasticsearch and hadoop are all very good solution, i am a beginner"
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "3",
        "_score": 1.0341108,
        "_source": {
          "articleID": "JODL-X-1937-#pV7",
          "userID": 2,
          "hidden": false,
          "postDate": "2017-01-01",
          "tag": [
            "hadoop"
          ],
          "tag_cnt": 1,
          "view_cnt": 100,
          "title": "this is elasticsearch blog",
          "content": "i am only an elasticsearch beginner"
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 0.977973,
        "_source": {
          "articleID": "XHDK-A-1293-#fJ3",
          "userID": 1,
          "hidden": false,
          "postDate": "2017-01-01",
          "tag": [
            "java",
            "hadoop"
          ],
          "tag_cnt": 2,
          "view_cnt": 30,
          "title": "this is java and elasticsearch blog",
          "content": "i like to write best elasticsearch article"
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "5",
        "_score": 0.7116974,
        "_source": {
          "articleID": "DHJK-B-1395-#Ky5",
          "userID": 3,
          "hidden": false,
          "postDate": "2019-05-01",
          "tag": [
            "elasticsearch"
          ],
          "tag_cnt": 1,
          "view_cnt": 10,
          "title": "this is spark blog",
          "content": "spark is best big data solution based on scala ,an programming language similar to java"
        }
      }
    ]
  }
}