Construction of intelligent decision support systems through integration of retrieval-augmented generation and knowledge graphs

计算机科学 决策支持系统 编配 智能决策支持系统 背景(考古学) 相关性(法律) 知识管理 生成语法 领域(数学分析) 人工智能 领域知识 数据科学 基于案例的推理 建筑 知识整合 基于模型的推理 订单(交换) 基于知识的系统 信息系统 供应链 推理系统 知识表示与推理 临床决策支持系统 语境意识 R型铸件 知识工程 机器学习 主题专家 图层(电子) 知识库 人机交互
作者
Sili Wang,Heng Yang,Guangzu Bai
出处
期刊:Scientific Reports [Nature Portfolio]
卷期号:15 (1): 35462-35462 被引量:3
标识
DOI:10.1038/s41598-025-19257-3
摘要

This article proposes a novel framework for intelligent decision support systems based on retrieval augmented generation models and knowledge graphs, in order to overcome the shortcomings of current approaches. Systems Like Mistral 7B, LLaMA-2, and others tend to fail at contextual understanding, transparency, and reasoning over many steps involving many domains. Our proposed architecture combines the strengths of generative models, enhanced by external knowledge retrieval, with structured, linked representations of domain knowledge. With this synergy, we show improvement in decision accuracy, reasoning transparency, and context relevance compared to using either technology alone. The structure has a flexible knowledge orchestration layer that optimizes information exchange between structured representations and generative capabilities. Research conducted on three areas, namely, financial services, healthcare management, and the supply chain has shown that our method performs particularly well when it comes to cross-domain reasoning and ambiguous queries. This study deepens our understanding of knowledge-enhancing artificial intelligence systems as well as offers a roadmap for a next-generation decision support system. The framework is designed to tackle some of the most challenging issues faced by enterprises in making decisions. In particular, it draws from both context and expertise to provide explainable recommendations.
最长约 10秒,即可获得该文献文件

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
FashionBoy应助科研通管家采纳,获得10
刚刚
HD完成签到 ,获得积分10
1秒前
香蕉觅云应助科研通管家采纳,获得10
1秒前
ff应助科研通管家采纳,获得10
1秒前
1秒前
Jasper应助科研通管家采纳,获得10
1秒前
跳跳糖应助科研通管家采纳,获得20
1秒前
小蘑菇应助科研通管家采纳,获得10
1秒前
能干智宸完成签到,获得积分10
1秒前
CAY发布了新的文献求助10
1秒前
1秒前
Hustch完成签到,获得积分10
2秒前
molihuakai应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
2秒前
22336应助科研通管家采纳,获得20
2秒前
CodeCraft应助科研通管家采纳,获得10
2秒前
简单海露应助科研通管家采纳,获得10
3秒前
v0id应助科研通管家采纳,获得10
3秒前
我是老大应助科研通管家采纳,获得10
3秒前
天天快乐应助科研通管家采纳,获得10
3秒前
SN发布了新的文献求助10
3秒前
科目三应助科研通管家采纳,获得10
3秒前
3秒前
无花果应助yyyys采纳,获得10
4秒前
JamesPei应助Benhnhk21采纳,获得10
5秒前
嘿嘿发布了新的文献求助10
5秒前
loko发布了新的文献求助10
5秒前
自然以冬完成签到,获得积分10
5秒前
totoro完成签到,获得积分10
5秒前
hh完成签到 ,获得积分10
6秒前
6秒前
情怀应助蔡航采纳,获得10
6秒前
星辰大海应助想听水星记采纳,获得30
6秒前
认真生活完成签到,获得积分10
6秒前
7秒前
AA关注了科研通微信公众号
7秒前
YANYAN发布了新的文献求助10
7秒前
桐桐应助xushengyang采纳,获得10
7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
Navigating Normative Orders. Interdisciplinary Perspectives 800
Organizational Behavior 510
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
CLSI VET01S-2024 Performance Standards for Antimicrobial Disk and Dilution Susceptibility Tests for Bacteria Isolated From Animals (7th Ed) 500
A Case Study on Hotels as Noncongregate Emergency Living Accommodations for Returning Citizens 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7757433
求助须知:如何正确求助?哪些是违规求助? 9303891
关于积分的说明 20276846
捐赠科研通 7341055
什么是DOI,文献DOI怎么找? 3311919
关于科研通互助平台的介绍 2462633
邀请新用户注册赠送积分活动 2325630