已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

An Agent-Driven Question-Answering Digital Human Based on a Knowledge Graph for the Agricultural Planting Domain

作者
Bing Bai,Xiaoyan Meng,Jin Xu,Chenzi Zhao,Qi Gao
出处
期刊:Applied sciences [Multidisciplinary Digital Publishing Institute]
卷期号:16 (11): 5615-5615 被引量:1
标识
DOI:10.3390/app16115615
摘要

Complex agricultural question answering often requires multi-step reasoning over domain-specific knowledge and reliable retrieval of heterogeneous evidence. However, existing retrieval-augmented generation (RAG) methods usually rely on one-shot retrieval and provide limited control over whether the retrieved evidence is sufficient, accurate, and consistent for answering complex agricultural questions. To address this limitation, this paper proposes an agent-driven question-answering framework for the agricultural planting domain based on a Planning–Execution–Feedback (PEF) closed-loop mechanism. The framework decomposes complex queries into executable subtasks, performs knowledge acquisition through a knowledge-graph-guided hybrid retrieval module, and iteratively refines the reasoning process according to retrieval-quality feedback. Specifically, in the retrieval stage, a two-stage strategy is introduced to first localize candidate entities in the knowledge graph and then conduct context-enhanced dense retrieval with entity-consistency reranking, thereby reducing semantic drift and improving domain alignment. In the feedback stage, the agent evaluates the adequacy of the retrieved evidence and determines whether to continue execution, re-retrieve evidence, or replan the workflow. Experimental results on the AgroQA dataset show that the proposed method achieves 88.9%, 79.1%, and 92.6% on the Answer-C, Answer-R, and CR metrics, respectively, outperforming traditional retrieval-augmented and general large language model baselines. In addition, a three-dimensional digital human interface is implemented as an application prototype to demonstrate the feasibility of integrating the proposed framework into interactive agricultural knowledge services.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
舒适思松完成签到 ,获得积分10
刚刚
小鱼完成签到,获得积分20
1秒前
科研通AI6.4的应助被余溪采纳,获得10
2秒前
3秒前
3秒前
奇迹发布了新的文献求助10
3秒前
NexusExplorer的应助被标致的千柳采纳,获得10
3秒前
4秒前
领导范儿的应助被大力的映天采纳,获得10
5秒前
放青松发布了新的文献求助10
5秒前
kiki完成签到,获得积分10
7秒前
7秒前
7秒前
所所的应助被科研通管家采纳,获得10
7秒前
orixero的应助被科研通管家采纳,获得10
8秒前
华仔的应助被科研通管家采纳,获得10
8秒前
打打的应助被舒南晴采纳,获得10
8秒前
汉堡包的应助被科研通管家采纳,获得10
8秒前
852的应助被质谱仪采纳,获得10
8秒前
orixero的应助被科研通管家采纳,获得10
8秒前
上官若男的应助被科研通管家采纳,获得10
8秒前
慕青的应助被烂漫代曼采纳,获得10
8秒前
传奇3的应助被科研通管家采纳,获得30
8秒前
SciGPT的应助被科研通管家采纳,获得10
8秒前
领导范儿的应助被科研通管家采纳,获得10
9秒前
完美世界的应助被科研通管家采纳,获得10
9秒前
乐乐的应助被科研通管家采纳,获得10
9秒前
9秒前
完美世界的应助被科研通管家采纳,获得10
9秒前
田様的应助被科研通管家采纳,获得10
9秒前
9秒前
英俊的铭的应助被科研通管家采纳,获得10
9秒前
10秒前
14秒前
李健的应助被木木采纳,获得10
14秒前
搜集达人的应助被凌松526采纳,获得30
14秒前
xinyuanjia的应助被ylj1170230采纳,获得20
14秒前
dd完成签到,获得积分10
18秒前
19秒前
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
Grapes 1000
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8179198
求助须知:如何正确求助?哪些是违规求助? 9569781
关于积分的说明 21806509
捐赠科研通 7774542
什么是DOI,文献DOI怎么找? 3433008
关于科研通互助平台的介绍 2556929
邀请新用户注册赠送积分活动 2478652