Forgot password?
 Create new account
Author: abababa

从帖子自动提取标签

[Copy link]

418

Threads

1627

Posts

110K

Credits

Credits
11886

Show all posts

 Author| abababa Posted at 2025-3-26 21:52:31
Last edited by abababa at 2025-3-26 21:57:32
abababa 发表于 2025-3-26 21:05
刚才把18楼的那个发给maven网友了,他说数据有点乱,要先清理一下,然后把清理过的数据发给我了,他说“ ...
我运行完之后,先是运行了那个tags_api.py,但是没得到标签,我又把那个THRESHOLD改成THRESHOLD = 0.3,这次得到了,比如初等数学里的那个三角函数方程的,我复制源代码粘贴到index.html里,就能得到一个“三角函数”的标签。

又试了一下蟾蜍吃蚊子那个,这个不准,得到的标签是四个:['"三视图"', '"立体几何', '"高考题', '"高考题"'],后两个重复了,前两个还是无关的。

试了求导n次后,求在x=0处的值那个,这个还行:['"多项式', '"抽象函数', '迭代"']

418

Threads

1627

Posts

110K

Credits

Credits
11886

Show all posts

 Author| abababa Posted at 2025-3-28 19:56:21
abababa 发表于 2025-3-26 21:52
我运行完之后,先是运行了那个tags_api.py,但是没得到标签,我又把那个THRESHOLD改成THRESHOLD = 0.3, ...
我问了maven这个重复的,他说不是重复,而是把带"的看作两个了,一个标签是"高考题,另一个标签是"高考题",所以看着像重复。他说重新写了那个划分tags的,这回好了,我上传在附件里。
$type tags.tar.gz (440.82 KB, Downloads: 2)
我发现用新的这个,运行之后生成的那个tags_model.joblib小了一半,是不是没有那些看着像重复的标签的原因呢?

3148

Threads

8489

Posts

610K

Credits

Credits
66148
QQ

Show all posts

hbghlyj Posted at 2025-3-29 01:26:15
无经验,先试试Algolia提供搜索服务,可推荐相关帖子
algolia.com/doc/guides/algolia-recommend/overview/

3148

Threads

8489

Posts

610K

Credits

Credits
66148
QQ

Show all posts

hbghlyj Posted at 2025-3-29 01:29:56
abababa 发表于 2025-3-26 07:28
maven的原话是:“这叫有监督学习,你得告诉程序它是什么,不知道是什么的就没办法参与学习,也不能被识别。”
Algolia推荐算法就是基于有监督学习:
Recommendations rely on supervised machine learning models that are trained on your product data and user interactions.
Recommend uses two different algorithm types: collaborative filtering and content-based filtering.
  • Collaborative filtering analyzes user events from the last 30-90 days. Recommend creates a table of userToken and objectID which show how many times each user interacted with each record (object). Recommend then uses a collaborative filtering algorithm to find other records that are similar or frequently bought together:
    • Similar if the same set of users interacts with them.
    • Frequently bought together if the same set of users bought them.
  • Content-based filtering analyzes key attributes of items, such as their titles or descriptions, to find similarities.
免费试用?

手机版Mobile version|Leisure Math Forum

2025-4-20 12:09 GMT+8

Powered by Discuz!

× Quick Reply To Top Return to the list