二十八、Elasticsearch用function_score

我们可以让score不走默认的，让他与我们某个field进行计算（加减乘除自己定义）得到一个结果作为score值

数据准备
follower_num：帖子阅读量

POST /forum/article/_bulk
{ "update": { "_id": "1"} }
{ "doc" : {"follower_num" : 5} }
{ "update": { "_id": "2"} }
{ "doc" : {"follower_num" : 10} }
{ "update": { "_id": "3"} }
{ "doc" : {"follower_num" : 25} }
{ "update": { "_id": "4"} }
{ "doc" : {"follower_num" : 3} }
{ "update": { "_id": "5"} }
{ "doc" : {"follower_num" : 60} }

将对帖子搜索得到的分数，跟follower_num进行运算，由follower_num在一定程度上增强帖子的分数
看帖子的人越多，那么帖子的分数就越高

GET /forum/article/_search
{
  "query": {
    "function_score": {
      "query": {
        "multi_match": {
          "query": "java spark",
          "fields": ["title", "content"]
        }
      },
      "field_value_factor": {
        "field": "follower_num"
      }
    }
  }
}

结果：

{
  "took": 124,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 40.994698,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "5",
        "_score": 40.994698,
        "_source": {
          "articleID": "DHJK-B-1395-#Ky5",
          "userID": 3,
          "hidden": false,
          "postDate": "2017-03-01",
          "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 spark",
          "sub_title": "haha, hello world",
          "author_first_name": "Tonny",
          "author_last_name": "Peter Smith",
          "new_author_last_name": "Peter Smith",
          "new_author_first_name": "Tonny",
          "follower_num": 60
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 6.8640785,
        "_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",
          "sub_title": "learned a lot of course",
          "author_first_name": "Smith",
          "author_last_name": "Williams",
          "new_author_last_name": "Williams",
          "new_author_first_name": "Smith",
          "follower_num": 10
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 1.3371139,
        "_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",
          "sub_title": "learning more courses",
          "author_first_name": "Peter",
          "author_last_name": "Smith",
          "new_author_last_name": "Smith",
          "new_author_first_name": "Peter",
          "follower_num": 5
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "4",
        "_score": 0.46640402,
        "_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",
          "sub_title": "both of them are good",
          "author_first_name": "Robbin",
          "author_last_name": "Li",
          "new_author_last_name": "Li",
          "new_author_first_name": "Robbin",
          "follower_num": 3
        }
      }
    ]
  }
}

可以发现分数都特别的大，都在好几十。是因为它与我们的follower_num进行了乘法运算。

我们想让分数不要相差的这么离谱怎么办？ modifier

GET /forum/article/_search
{
  "query": {
    "function_score": {
      "query": {
        "multi_match": {
          "query": "java spark",
          "fields": ["title", "content"]
        }
      },
      "field_value_factor": {
        "field": "follower_num",
        "modifier": "log1p"
      }
    }
  }
}

结果

{
  "took": 5,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 1.0189654,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "5",
        "_score": 1.0189654,
        "_source": {
          "articleID": "DHJK-B-1395-#Ky5",
          "userID": 3,
          "hidden": false,
          "postDate": "2017-03-01",
          "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 spark",
          "sub_title": "haha, hello world",
          "author_first_name": "Tonny",
          "author_last_name": "Peter Smith",
          "new_author_last_name": "Peter Smith",
          "new_author_first_name": "Tonny",
          "follower_num": 60
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 0.53412914,
        "_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",
          "sub_title": "learned a lot of course",
          "author_first_name": "Smith",
          "author_last_name": "Williams",
          "new_author_last_name": "Williams",
          "new_author_first_name": "Smith",
          "follower_num": 10
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 0.14549617,
        "_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",
          "sub_title": "learning more courses",
          "author_first_name": "Peter",
          "author_last_name": "Smith",
          "new_author_last_name": "Smith",
          "new_author_first_name": "Peter",
          "follower_num": 5
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "4",
        "_score": 0.06186694,
        "_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",
          "sub_title": "both of them are good",
          "author_first_name": "Robbin",
          "author_last_name": "Li",
          "new_author_last_name": "Li",
          "new_author_first_name": "Robbin",
          "follower_num": 3
        }
      }
    ]
  }
}

公式会变为，new_score = old_score * log(1 + number_of_votes)，这样出来的分数会比较合理

再加个factor，可以进一步影响分数，new_score = old_score * log(1 + factor * number_of_votes)

GET /forum/article/_search
{
  "query": {
    "function_score": {
      "query": {
        "multi_match": {
          "query": "java spark",
          "fields": ["title", "content"]
        }
      },
      "field_value_factor": {
        "field": "follower_num",
        "modifier": "log1p",
        "factor": 0.5
      }
    }
  }
}

结果

{
  "took": 10,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 1.0189654,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "5",
        "_score": 1.0189654,
        "_source": {
          "articleID": "DHJK-B-1395-#Ky5",
          "userID": 3,
          "hidden": false,
          "postDate": "2017-03-01",
          "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 spark",
          "sub_title": "haha, hello world",
          "author_first_name": "Tonny",
          "author_last_name": "Peter Smith",
          "new_author_last_name": "Peter Smith",
          "new_author_first_name": "Tonny",
          "follower_num": 60
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 0.53412914,
        "_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",
          "sub_title": "learned a lot of course",
          "author_first_name": "Smith",
          "author_last_name": "Williams",
          "new_author_last_name": "Williams",
          "new_author_first_name": "Smith",
          "follower_num": 10
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 0.14549617,
        "_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",
          "sub_title": "learning more courses",
          "author_first_name": "Peter",
          "author_last_name": "Smith",
          "new_author_last_name": "Smith",
          "new_author_first_name": "Peter",
          "follower_num": 5
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "4",
        "_score": 0.06186694,
        "_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",
          "sub_title": "both of them are good",
          "author_first_name": "Robbin",
          "author_last_name": "Li",
          "new_author_last_name": "Li",
          "new_author_first_name": "Robbin",
          "follower_num": 3
        }
      }
    ]
  }
}

我们不想乘法，想加上follower_num

GET /forum/article/_search
{
  "query": {
    "function_score": {
      "query": {
        "multi_match": {
          "query": "java spark",
          "fields": ["title", "content"]
        }
      },
      "field_value_factor": {
        "field": "follower_num",
        "modifier": "log1p",
        "factor": 0.5
      },
      "boost_mode": "sum"
    }
  }
}

结果

{
  "took": 3,
  "timed_out": false,
  "_shards": {
    "total": 5,
    "successful": 5,
    "failed": 0
  },
  "hits": {
    "total": 4,
    "max_score": 2.1746066,
    "hits": [
      {
        "_index": "forum",
        "_type": "article",
        "_id": "5",
        "_score": 2.1746066,
        "_source": {
          "articleID": "DHJK-B-1395-#Ky5",
          "userID": 3,
          "hidden": false,
          "postDate": "2017-03-01",
          "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 spark",
          "sub_title": "haha, hello world",
          "author_first_name": "Tonny",
          "author_last_name": "Peter Smith",
          "new_author_last_name": "Peter Smith",
          "new_author_first_name": "Tonny",
          "follower_num": 60
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "2",
        "_score": 1.4645591,
        "_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",
          "sub_title": "learned a lot of course",
          "author_first_name": "Smith",
          "author_last_name": "Williams",
          "new_author_last_name": "Williams",
          "new_author_first_name": "Smith",
          "follower_num": 10
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "1",
        "_score": 0.81149083,
        "_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",
          "sub_title": "learning more courses",
          "author_first_name": "Peter",
          "author_last_name": "Smith",
          "new_author_last_name": "Smith",
          "new_author_first_name": "Peter",
          "follower_num": 5
        }
      },
      {
        "_index": "forum",
        "_type": "article",
        "_id": "4",
        "_score": 0.553408,
        "_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",
          "sub_title": "both of them are good",
          "author_first_name": "Robbin",
          "author_last_name": "Li",
          "new_author_last_name": "Li",
          "new_author_first_name": "Robbin",
          "follower_num": 3
        }
      }
    ]
  }
}

boost_mode，可以决定分数与指定字段的值如何计算，multiply，sum，min，max，replace

max_boost，限制计算出来的分数不要超过max_boost指定的值

GET /forum/article/_search
{
  "query": {
    "function_score": {
      "query": {
        "multi_match": {
          "query": "java spark",
          "fields": ["title", "content"]
        }
      },
      "field_value_factor": {
        "field": "follower_num",
        "modifier": "log1p",
        "factor": 0.5
      },
      "boost_mode": "sum",
      "max_boost": 2
    }
  }
}

若有兴趣，欢迎来加入群，【Java初学者学习交流群】：458430385，此群有Java开发人员、UI设计人员和前端工程师。有问必答，共同探讨学习，一起进步！
欢迎关注我的微信公众号【Java码农社区】，会定时推送各种干货：

qrcode_for_gh_577b64e73701_258.jpg