当前位置:首页 >英文主页 >中英对照 > 中译版报告详情

GTI:2024 面向人工智能(AI)设备的度量指标与测试方法白皮书(中译版)(45页).pdf

上传人: Kell****reet 编号:617564 2024-12-30 45页 3.16MB

下载:

1、GTI Metrics and TestMethods Towards AIdevice White Paperhttp:/gtigroup.org/group.orgGTI Metrics and Test Methods Towards AI device White Paper2GTI Metrics and Test MethodsTowards AI device White PaperVersion:v_1.0.0Deliverable Type Procedural Document Working DocumentConfidential Level Open to GTI O

2、perator MembersOpen to GTI Partners Open to PublicProgram5G Technology and ProductProjectTechnology EvolutionTask5G-A TechnologySource membersChina Mobile,Qualcomm,Xiaomi,MTK,OPPO,vivoSupport membersHuawei,Unisoc,Keysight,R&SEditorHang Ruan(CMCC),Jing Gao(CMCC),Jiachen Zhang(CMCC),Lei Cao(CMCC),Tian

3、ming Jiang(CMCC),Ting Wang(Qualcomm),Shuping Chen(Qualcomm),Yan Li(Qualcomm),Xiangkuo Xiao(Xiaomi),Daliang Sun(Xiaomi),YingjunLi(Xiaomi),Mingyu Chen(MTK),Yuanyuan Zhang(MTK),HanXiao(OPPO),Wendong Liu(OPPO),Sihao Shi(vivo),BuleSun(vivo)Last Edit Date2024-11-23Approval DateConfidentiality:This documen

4、t may contain information that is confidential and access to thisdocument is restricted to the persons listed in the Confidential Level.This document may not beused,disclosed or reproduced,in whole or in part,without the prior written authorization of GTI,and those so authorized may only use this do

5、cument for the purpose consistent with theauthorization.GTI disclaims any liability for the accuracy or completeness or timeliness of theinformation contained in this document.The information contained in this document may besubject to change without prior notice.GTI Metrics and Test Methods Towards

6、 AI device White Paper3Document HistoryDateMeeting#Version#Revision Contents2024.11.25GTI#41V1.0Initial VersionGTI Metrics and Test Methods Towards AI device White Paper4TableTable ofof ContentsContentsIntroduction.6Executive Summary.7Abbreviations.81 5G-A AI Device Evaluation System.91.1 Evaluation

word格式文档无特别注明外均可编辑修改,预览文件经过压缩,下载原文更清晰!
三个皮匠报告文库所有资源均是客户上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作商用。
本文主要介绍了AI设备评估体系,包括AI设备评估系统、通信AI设备评估解决方案和生成式AI设备评估解决方案。 1. AI设备评估系统:提出了“1-4-1”评估体系架构,包括评估环境、评估工具、评估指标和测试接口四个方面。 2. 通信AI设备评估解决方案:包括AI基线预测和管理、AI基线CSI预测、AI弱信号预测和AI数据停滞预测。 3. 生成式AI设备评估解决方案:包括AI文本和图像生成、AI多模态人机交互。 本文还介绍了AI设备评估的发展趋势,包括AI代理评估、零开销叠加导频设计和评估、信道和无线环境语义通信和评估。 总体来说,本文旨在推动形成客观统一的AI设备评估体系,为行业提供评估方案参考。
5G-A AI设备评估体系如何构建? 通信AI设备评估方案有哪些? 生成式AI设备评估指标有哪些?
客服
商务合作
小程序
服务号
折叠