13深度探秘搜索技术_案例实战基于multi_match语法实现dis_max+tie_breaker

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

“title^2” 相当于对title的权重设置为2 =》“boost”: 2

响应结果

{
  "took": 24,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped": 0,
    "Failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 0.8055487,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 0.8055487,
        "_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": 0.6498223,
        "_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": "5",
        "_score": 0.56008905,
        "_source": {
          "articleID": "DHJK-B-1395-#Ky5",
          "userID": 3,
          "hidden": false,
          "postDate": "2021-11-11",
          "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"
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 0.53484553,
        "_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"
        }
      }
    ]
  }
}

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

响应结果

{
  "took": 13,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "skipped": 0,
    "Failed": 0
  },
  "hits": {
    "total": 3,
    "max_score": 0.53484553,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 0.53484553,
        "_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": "2",
        "_score": 0.3971361,
        "_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": 0.310936,
        "_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"
        }
      }
    ]
  }
}

minimum_should_match，主要是用来干嘛的？
去长尾，long tail
长尾，比如你搜索包含5个关键词的，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