直接告诉ai,让他输出有效的json格式,例如我直接告诉ai规则,对评论进行分类,返回json数据,一定告诉ai,json数据外不要添加其他信息:Don't add explanation beyond the JSON
You’re a Customer Insights AI. Analyze this feedback and output in JSON format with keys: “sentiment” (positive/negative/neutral), “key_issues” (list), and “action_items” (list of dicts with “team” and “task”), Don't add explanation beyond the JSON. “I’ve been a loyal user for 3 years, but the recent UI update is a disaster. Finding basic features is now a scavenger hunt. Plus, the new ‘premium’ pricing is outrageous. I’m considering switching unless this is fixed ASAP.”返回
{ “sentiment”: “negative”, “key_issues”: [ “Poor UI/UX in recent update”, “Difficulty finding basic features”, “Perceived high pricing (new ‘premium’ tier)” ], “action_items”: [ { “team”: “Product”, “task”: “Conduct usability testing and iterate on UI based on findings” }, { “team”: “UX”, “task”: “Create a feature discovery guide or onboarding flow” }, { “team”: “Marketing”, “task”: “Review pricing strategy and communicate value proposition” }, { “team”: “Customer Success”, “task”: “Reach out to user, offer concessions to prevent churn” } ] }
这是主流大模型调用结果:

网友回复
为啥所有的照片分辨率提升工具都会修改照片上的图案细节?
js如何在浏览器中将webm视频的声音分离为单独音频?
微信小程序如何播放第三方域名url的mp4视频?
ai多模态大模型能实时识别视频中的手语为文字吗?
如何远程调试别人的chrome浏览器获取调试信息?
为啥js打开新网页window.open设置窗口宽高无效?
浏览器中js的navigator.mediaDevices.getDisplayMedia屏幕录像无法录制SpeechSynthesisUtterance产生的说话声音?
js中mediaRecorder如何录制window.speechSynthesis声音音频并下载?
python如何直接获取抖音短视频的音频文件url?
js在浏览器中如何使用MediaStream与MediaRecorder实现声音音频多轨道混流?