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
图片ai拒绝帮用户ps修改带公章类的拍照图片如何解决?
视频大模型和最强文本大模型通过代码生成视频哪个性价比更高?
seedream5.5为啥无法将图白色背景修改成透明?
seedance2如何通过2张不同角度平视图来识别场景进行人物定位?
有没有免费的浏览器中离线运行的语音识别ai模型?
微信小程序个人版不交钱认证就不让你用二维码,报错"errcode":85411?
美丽国为啥要限制ai发展?
seedance2如何参考白模视频使用真实场景和人物生成新视频?
如何设定小孩看电视的时候每隔10分钟弹出一个题目,答对才能继续,答错继续下一题?
直播数字人根据公屏互动评论实时做出不用动作技术是什么?


