判斷兩個文本之間的語義相似性。
文法
AI_AI_SIMILARITY([<resource_name>], <text_1>, <text_2>)參數
|
參數 |
說明 |
|
|
指定的資源名稱 |
|
|
文本 |
|
|
文本 |
傳回值
-
返回一個 0 - 10 之間的浮點數。0 表示無相似性，10 表示強相似性；數值越高，則說明相似性越高。
-
當輸入有值為 NULL 時返回 NULL。
-
結果為大模型產生，所以返回內容並不固定。
樣本
假設我有如下表，代表某家快遞公司收到的評論：
CREATE TABLE user_comments (
id INT,
comment VARCHAR(500)
) DUPLICATE KEY(id)
DISTRIBUTED BY HASH(id) BUCKETS 10
PROPERTIES (
"replication_num" = "1"
);當我想按顧客語氣情緒對評論進行排行時可以：
SELECT comment,
AI_SIMILARITY('resource_name', 'I am extremely dissatisfied with their service.', comment) AS score
FROM user_comments ORDER BY score DESC LIMIT 5;
查詢結果大致如下：
+-------------------------------------------------+-------+
| comment | score |
+-------------------------------------------------+-------+
| It arrived broken and I am really disappointed. | 7.5 |
| Delivery was very slow and frustrating. | 6.5 |
| Not bad, but the packaging could be better. | 3.5 |
| It is fine, nothing special to mention. | 3 |
| Absolutely fantastic, highly recommend it. | 1 |
+-------------------------------------------------+-------+