☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 多模态理解力帮你轻松跨越从0到1的创作门槛☜☜☜
{\"type\":\"doc\",\"content\":[{\"type\":\"heading\",\"attrs\":{\"id\":\"98fa0704-90d0-464c-9e2d-8f412ad66dbc\",\"textalign\":\"inherit\",\"indent\":0,\"level\":1,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"textstyle\",\"attrs\":{\"color\":\"\",\"background\":\"\"}}],\"text\":\"前言：团队现有通用评测平台能力\"}]},{\"type\":\"bulletlist\",\"attrs\":{\"id\":\"abd5823a-a43e-4aa8-ba07-620a108499a6\",\"ishoverdraghandle\":false},\"content\":[{\"type\":\"listitem\",\"attrs\":{\"id\":\"0a7fcce1-dadd-457a-a7a9-20007aaedb69\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"0279b3e1-9555-486b-b8a5-03a20d45cc48\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"支持单轮\u0026多轮对话评测\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"a050ce6e-8873-4bcf-a6c6-ccf933dcad01\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"a3518301-dfe7-44a2-840a-9884a0d1b360\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"支持对于评测结果打标\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"866e0e5f-7e05-40d1-9a87-f0037e7d9c09\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"ed59b903-dd13-47dd-860a-6d687afd55a7\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"支持llm根据用户的对话目标和对话计划生成自定义轮数的评测用例。\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"93288528-861c-4e68-92d3-5eabd843d7a1\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"2fa7f348-8e0f-4fc5-bb8a-1834ed01d49e\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"支持评测指标和标准的自定义\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"646b04ed-d30c-4cec-824c-ea6fec448a04\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"bc10c514-218d-4d7b-af36-5a421f50842c\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"指标可以设置权重和复用\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"1905fe0c-082a-43f8-b316-24283dd0b846\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"eccd1f37-620b-430c-a7aa-2bdb2a1e31f7\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"评测提示词支持ape自主评估和优\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"c95fd413-8ee7-4260-9b4f-f2d63647fb47\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"ef6b8356-baa4-49a5-83cc-c92a84e90193\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"化评测用例支持复用以及任务可重复执行\"}]}]},{\"type\":\"listitem\",\"attrs\":{\"id\":\"2c1db500-44bd-4c9a-b2e1-bf5c567c4fcf\"},\"content\":[{\"type\":\"paragraph\",\"attrs\":{\"id\":\"cace63ae-dec0-4099-917b-3018a5f85e04\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"text\":\"以下是部分平台截图：\"}]}]}]},{\"type\":\"image\",\"attrs\":{\"id\":\"d6ac564d-f787-4cb8-bf89-06f06a0cd5ac\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/070633186b3407d1e547c537c32fb254.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":\"\",\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"paragraph\",\"attrs\":{\"id\":\"60b4d515-957a-418f-b6ff-a734a664ddee\",\"textalign\":\"center\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false}},{\"type\":\"image\",\"attrs\":{\"id\":\"103ba2f4-f6af-4006-abd2-91250cbed78d\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/99069f6250b96196d76792515520289d.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":\"\",\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"image\",\"attrs\":{\"id\":\"f43df6c2-64fa-4ee4-b204-2f3457757f57\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/e496174adb4899fc9cde8886b5c3a406.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":\"\",\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"image\",\"attrs\":{\"id\":\"4fa818f2-5455-4a85-ae70-588471c6b373\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/24b13fdf0e63c27363c63878b2f3a67a.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":\"\",\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"image\",\"attrs\":{\"id\":\"85468229-0618-43d2-8cc4-154ccbaa7c95\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/e0371b233956f6b66e9ba4b8bc62ffc3.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":\"\",\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"heading\",\"attrs\":{\"id\":\"930bb283-27bc-4cfb-a1de-6858b06fc8a0\",\"textalign\":\"inherit\",\"indent\":0,\"level\":1,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"bold\"}],\"text\":\"『\"},{\"type\":\"text\",\"marks\":[{\"type\":\"textstyle\",\"attrs\":{\"color\":\"\",\"background\":\"\"}}],\"text\":\"业务实践过程中的认知和系统能力迭代需求\"},{\"type\":\"text\",\"marks\":[{\"type\":\"bold\"}],\"text\":\"』\"}]},{\"type\":\"paragraph\",\"attrs\":{\"id\":\"e55b52b0-a919-48aa-a4fd-8849f9f29b3b\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"textstyle\",\"attrs\":{\"color\":\"\",\"background\":\"\"}}],\"text\":\"背景：本次输出的ai评测的认知迭代和平台能力迭代规划，以bc双端ai企微场景的业务专项为背景，沟通收集qa同学，产品同学在整个过程中对于现有工具和平台的使用反馈和建议，结合过程中各角色协作过程中沟通讨论的主要问题，思考总结而成。\"}]},{\"type\":\"heading\",\"attrs\":{\"id\":\"2eb98375-9aae-4a21-bc45-388f95dc6c98\",\"textalign\":\"inherit\",\"indent\":0,\"level\":2,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"bold\"}],\"text\":\"问题一：如何做通用的评测用例集（可用来做agent验证的基线case）在模型优化后做快速验证评估。\"}]},{\"type\":\"image\",\"attrs\":{\"id\":\"78a899bb-2092-47ed-ba28-88a987a0e96c\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/ffc41016c1f9719e393f838e4be1e5be.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":790,\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"heading\",\"attrs\":{\"id\":\"c3c936d3-f08b-49e2-a92e-b3fe87b6c62f\",\"textalign\":\"inherit\",\"indent\":0,\"level\":2,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"bold\"}],\"text\":\"问题二：通用的llm评测规则是不是足够？评测逻辑是否业务认可？\"}]},{\"type\":\"image\",\"attrs\":{\"id\":\"c288ccf9-5ef8-404f-84c6-650740b0f5db\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/74f9b937a34067dbfbb83e5cb8ee49e9.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":718,\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"heading\",\"attrs\":{\"id\":\"4dfd1b39-6e9f-4b2b-b918-899d778fa486\",\"textalign\":\"inherit\",\"indent\":0,\"level\":3,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"bold\"}],\"text\":\"问题三：针对单条用例一个最终的评测通过结果+评测说明是否足够？\"}]},{\"type\":\"image\",\"attrs\":{\"id\":\"af599661-ffc7-4470-9aec-878cb6ca7c78\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/a82a75b5a39f5a828a35259c5cfa331d.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":764,\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"heading\",\"attrs\":{\"id\":\"becd3c51-3c31-4557-a380-10872b15c5f2\",\"textalign\":\"inherit\",\"indent\":0,\"level\":2,\"ishoverdraghandle\":false},\"content\":[{\"type\":\"text\",\"marks\":[{\"type\":\"bold\"}],\"text\":\"问题四：团队协作上目前缺少什么？造成开发和测试过程中才陆续发现一些隐藏的问题？\"}]},{\"type\":\"image\",\"attrs\":{\"id\":\"89de1f6b-4ee8-4d8b-a9e9-bc64d83a7b24\",\"src\":\"https://developer.qcloudimg.com/http-save/audit-12512212/591b4891ec98525b5a604e89e0b1a8f6.webp\",\"extension\":\"\",\"align\":\"center\",\"alt\":\"\",\"showalt\":false,\"href\":\"\",\"boxshadow\":\"\",\"width\":751,\"aspectratio\":0,\"status\":\"success\",\"showtext\":true,\"ispercentage\":false,\"percentage\":0,\"ishoverdraghandle\":false}},{\"type\":\"paragraph\",\"attrs\":{\"id\":\"df4b0260-8489-4f1c-b782-aa38655a27ae\",\"textalign\":\"inherit\",\"indent\":0,\"color\":null,\"background\":null,\"ishoverdraghandle\":false}}]}
