Skip to content

[Feature] 关于上传时选用的tag #340

@EarSum

Description

@EarSum

Is your feature request related to a problem? Please describe.

(A clear and concise description of what the problem is.)

根据discussion中讨论的结果,现在上传时将选用搜索栏中有关artist的热词来进行自动tag,但是这可能引入一个问题,热词并非一定是中性或者正面的结果,如果artist有什么瓜或者黑料也会被打入tag(如图),这样也许会对artist造成困扰或者对观众造成不适,因此我个人认为这个tag的逻辑可能需要做出修改。
Image

Describe the solution you'd like

(A clear and concise description of what you want to happen.)
我认为有两种解决方案:
1、比较简单粗暴,直接提供自动tag的开关,对于关闭自动tag的情况,使用例如artist名称,直播间号,直播时间,“直播录播”,直播标题作为默认tag上传视频,而自动tag则维持原样。如果可以的话能针对直播间进行单独的子设置更好,例如全局关闭的情况下单个直播间可选择打开自动tag
2、接入大模型的语义分析,利用大模型api进行对热词语义分析,如果是中性或者正面的词保留其余的剔除,但是这个可能比较复杂

Describe alternatives you've considered

(A clear and concise description of any alternative solutions or features you've considered.)
现在我个人的解决方案是改动了/src/upload/extract_video_info.py的代码,使用视频信息的字符串拼接成tag上传,但这样灵活性较差。

def generate_tag(video_path):
    title, artist, date = get_video_info(video_path)
    artist_text = re.sub(r"\W+", "", artist)
    title_text = re.sub(r"\W+", "", title)
    date_text = re.sub(r"\W+", "", date)
    #tags = get_bilibili_suggestions(artist_text)
    #if not tags:
    #    tags = "直播回放"
    tags = f"{artist_text},{title_text},{date_text},直播录播"
    return tags

Additional context

(Add any other context or screenshots about the feature request here.)
None

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions