绿色AI效率评价模型的构建与应用  

Construction and application of a quantitative efficiency assessment model for green AI in intelligent customer service systems

作　　者：马晓亮 刘英[2,3] 赵汝强 杨邦兴 高洁 邓从健 MA Xiaoliang;LIU Ying;ZHAO Ruqiang;YANG Bangxing;GAO Jie;DENG Congjian(Xidian University,Xi’an 710071,China;China Telecom Corporation Guangzhou Branch,Guangzhou 510620,China;Ma Xiaoliang Innovation Studio for Model Workers and Creative Talents,Guangzhou 510620,China;Guangzhou Yunqu Information Technology Co.,Ltd.,Guangzhou 510665,China;China DataCom Co.,Ltd.,Guangzhou 510630,China)

机构地区：[1]西安电子科技大学,陕西西安710071 [2]中国电信股份有限公司广州分公司,广东广州510620 [3]马晓亮劳模与工匠人才创新工作室,广东广州510620 [4]广州云趣信息科技有限公司,广东广州510665 [5]中数通信息有限公司,广东广州510630

出　　处：《电信科学》2024年第8期130-137,共8页Telecommunications Science

摘　　要：随着人工智能(artificial intelligence,AI)的兴起,大模型(large language model,LLM)日益成为知识推介和多轮对话的核心技术。伴随而来,AI大模型在数据处理、模型训练和部署过程中的高能耗问题亟须有效评估,以便在模型优化后进行前后量化对比。提出一种AI大模型能耗的评估方法,旨在量化评估AI模型的服务效率(efficiency,E)。该模型使用训练收敛时间(time,T)、模型参数规模(parameter,P)和浮点运算量(floating-point operations,F)等多维度因素,通过构建能源消耗函数C(T,P,F)实现量化分析;同时,运用非线性最小二乘法,得出模型参数。该分析方法不仅适用于电信运营商客服AI模型的运行效率分析,也可泛化于其他行业的AI模型能耗评估。The rise of AI and the increasing prominence of LLM are positioned as core technologies for knowledge dissemination and multiturn dialogues.Alongside their growth,the high energy consumption associated with data processing,model training,and deployment in AI large models is necessitating effective evaluation to facilitate quantitative comparisons before and after model optimization.An assessment method for the energy consumption of AI large models was introduced,aimed at quantitatively evaluating the service efficiency(E)of AI models.This model was incorporated with multiple dimensions such as training convergence time(T),model parameter size(P),and floating-point operations(F),and quantitative analysis was achieved through the construction of an energy consumption function C(T,P,F).Furthermore,by employing the nonlinear least squares method,model parameters were derived.This analysis method was not only applicable to the operational efficiency analysis of AI models used by tele‐communications operators but can also be generalized for energy consumption assessment of AI models across various industries.

关 键 词：绿色AI 智能客服 能源效率评估 大语言模型 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]