自定义 DotProduct 在无痛脚本 ElasticSearch 中给出不准确的结果

Question

在无痛弹性搜索中使用自定义 Dotproduct 时得到不准确的结果。

索引映射。

PUT /custom_dot_product
{
  "settings": {
    "number_of_shards": 1,
    "number_of_replicas": 1
  },
  "mappings": {
    "properties": {
      "level1": {
        "type": "nested",
        "properties": {
          "level2": {
            "properties": {
              "vector_3": {
                "type": "long"
              }
            }
          }
        }
      }
    }
  }
}

文档数据 .

POST /custom_dot_product/_doc/1
{
  "level1": {
    "level2": {
      "vector_3": [
       2,
       2,
       2,
       0
      ]
    }
  }
}

搜索查询

POST custom_dot_product/_search
{
  "query": {
    "bool": {
      "must": [
        {
          "nested": {
            "path": "level1",
            "query": {
              "function_score": {
                "query": {
                  "match_all": {}
                },
                "script_score": {
                  "script": {
                    "source": " if(doc['level1.level2.vector_3'].size()>0){ double result = 0.0; for (int i = 0; i < params.user_vector.length; i++) result += params.user_vector[i] * doc['level1.level2.vector_3'][i]; return result;} ",
                    "params": {
                      "user_vector": [
                        1,
                        1,
                        1,
                        0
                      ]
                    }
                  }
                },
                "boost_mode": "replace"
              }
            },
            "inner_hits": {
              "sort": []
            }
          }
        }
      ]
    }
  }
}

输出：

    {
  "took" : 1,
  "timed_out" : false,
  "_shards" : {
    "total" : 1,
    "successful" : 1,
    "skipped" : 0,
    "failed" : 0
  },
  "hits" : {
    "total" : {
      "value" : 1,
      "relation" : "eq"
    },
    "max_score" : 4.0,
    "hits" : [
      {
        "_index" : "knn_dot_product_poc",
        "_type" : "_doc",
        "_id" : "1",
        "_score" : 4.0,
        "_source" : {
          "level1" : {
            "level2" : {
              "vector_3" : [
                2,
                2,
                2,
                0
              ]
            }
          }
        },
        "inner_hits" : {
          "level1" : {
            "hits" : {
              "total" : {
                "value" : 1,
                "relation" : "eq"
              },
              "max_score" : 4.0,
              "hits" : [
                {
                  "_index" : "knn_dot_product_poc",
                  "_type" : "_doc",
                  "_id" : "1",
                  "_nested" : {
                    "field" : "level1",
                    "offset" : 0
                  },
                  "_score" : 4.0,
                  "_source" : {
                    "level2" : {
                      "vector_3" : [
                        2,
                        2,
                        2,
                        0
                      ]
                    }
                  }
                }
              ]
            }
          }
        }
      }
    ]
  }
}

score 结果应该是 6.0，但它给出了 4.0 当我从向量中删除 0 时，它开始给出 6.0

剧本评分后面还有其他计算吗？