[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f4nG37vd7x4KvoNhxh1bvInKfbmhaogvBGBYSFb5e6YI":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2024-10-02 11:15:07",160656949,[8,9,10,11],"幻觉","文本输入","专业知识","需要定制化场景",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},6,"536a9ad78fe4e72dd49ab2f63abff3d8","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Faa87a127d2c75fcdb3733863e9bd6e96.jpg","生成式人工智能原理及其影响和应用","6705fbe4263446aa9a79a2b23b38372f","7.1 基于大语言模型智能运维面临的挑战","下列不属于大语言模型的限制的是()",[21,32,41,50,59,68],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],160656944,[25,26,27,28],"BERT","T5","GPT","以上都不是","在《Large Language Model for RCA》研究中,主要采用了哪个模型进行根本原因分析","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],160656945,[36,37,38,39],"下游任务由简单的故障分类、问答和解析,发展到根因分析、专家诊断和解决方案评估","数据分析从日志、事件到故障单以及更多维数据","模型适配从大量数据微调到少样本训练,甚至零样本训练","大幅增加对标注数据的依赖","随着大模型规模的增长,AIOps发展趋势不包括()",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],160656946,[45,46,47,48],"谷歌","苹果","微软","IBM","课程里介绍的《Large Language Model for RCA》研究是由()团队制作.()",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],160656947,[54,55,56,57],"日志异常分类","面容解锁","自动驾驶","信息检索","华为公司的《logprompt》聚焦于()任务",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":31},[],160656948,[63,64,65,66],"严肃性问题","简单场景","多源异构数据","强领域知识","下列不属于运维领域的特点的是()",{"answer":69,"createTime":5,"id":6,"options":70,"question":19,"source":30,"type":31},[],[8,9,10,11]]