Open access

A Synergistic Knowledge Graph and LLM-Driven Framework for Intelligent Process Decision-Making Systems

Deguo Yao Zhaoze Sun Jie Gao Hao-Yu Cao Xiao-Yue Li

Aug 2026 · Applied System Innovation · Vol 9, pp. 171 · 0 citations · 30 references

TL;DR

The proposed knowledge graph construction method for the workpiece machining distortion domain is proposed, together with an intelligent decision-making framework driven by the collaboration of knowledge graphs and large language models, providing a feasible pathway for the structured organization, intelligent retrieval, and decision support of workpiece machining distortion knowledge.

Abstract

To address the problems of complex process knowledge sources, heterogeneous representations, dispersed semantic associations, and limited reusability in the domain of machining distortion of thin-walled parts, this study proposes a knowledge graph construction method for the workpiece machining distortion domain, together with an intelligent decision-making framework driven by the collaboration of knowledge graphs and large language models. First, a domain ontology model is established around core concepts, including workpiece objects, deformation-driving factors, analytical resources, analytical methods, and optimization knowledge, thereby providing a unified semantic foundation for domain knowledge organization. Second, considering the characteristics of domain texts, such as dense technical terminology, ambiguous entity boundaries, and complex relation expressions, a dual-channel knowledge extraction method integrating BERT-BiLSTM-CRF and Universal Information Extraction (UIE) is developed to achieve high-precision extraction of entities and relations from unstructured texts. Knowledge fusion is further carried out through cross-validation, entity disambiguation, coreference resolution, and semantic alignment, and the extracted knowledge is ultimately stored and organized in Neo4j. Furthermore, an intelligent decision-making framework based on the collaboration of knowledge graphs and large language models is constructed. In this framework, a LoRA-tuned Qwen model is employed for user intent recognition and key information extraction, RapidFuzz WRatio is adopted for similar-node retrieval, and local subgraph construction, Label Propagation-based community detection, Betweenness Centrality-based key-node analysis, and evidence fusion are integrated to support process recommendation and intelligent question answering. Based on the proposed framework, an intelligent decision-making system is further developed for process recommendation and intelligent question answering in machining distortion scenarios. Experimental results show that the proposed dual-channel knowledge extraction model achieves an F1-score of 0.88, demonstrating its effectiveness in knowledge acquisition for the machining distortion domain. The constructed knowledge graph contains 4639 entities and 5822 relations, enabling a systematic representation of machining distortion knowledge. Case studies further demonstrate that the proposed method can generate interpretable recommendation results under complex process constraints in real industrial query scenarios. Overall, the proposed approach provides a feasible pathway for the structured organization, intelligent retrieval, and decision support of workpiece machining distortion knowledge.

DOI Semantic Scholar

Read PDF

Similar papers

Open access 2026

Intelligent Mining and Reasoning for Shipbuilding Process Rules Based on LLM-KG

To address three key challenges in the knowledge-based process of domain process design—heavy manual dependence, the difficulty of updating traditional knowledge rules, and the reliance of knowledge graph construction on manual effort with limited contextual understanding—this paper proposes an LLM-KG-based domain rule reasoning framework termed RCKG-DRB. First, this paper introduces RCKG—a knowledge graph structure tailored for process reasoning—and develops its ontology schema. Subsequently, integrating Prompt Engineering with Workflow techniques, an LLM-based automatic RCKG rule chain construction method is proposed for efficient rule mining. Finally, an RCKG-based dynamic reasoning base approach is adopted, which retrieves similar rule chains via retrieval-augmented generation (RAG) and applies multi-level weight-based conflict resolution, enabling dynamic organization and rapid reasoning. Experiments demonstrate that RCKG-DRB achieves an F1 score of 87.31% in domain-specific knowledge graph construction, showing promising improvements on the evaluated dataset in both reasoning accuracy and explainability, thereby enhancing rule-based knowledge management.

Jingjing Wu, Yifei Zhu, Qichang He · IEEE Access · 0 citations

Review Open access Jul 2026

LLM-driven materials knowledge extraction: multimodal parsing, ontology, and agentic systems

Extracting reliable knowledge from unstructured materials literature remains a central bottleneck for data-driven and AI-enabled materials discovery. Large language models (LLMs) are reshaping this task by integrating multimodal document parsing, ontology-guided semantic grounding, structured extraction, and agentic verification into increasingly unified workflows. This review analyzes these developments through a Perception–Cognition–Action lens. At the perception layer, we examine how scientific document parsers, multimodal LLMs, table and chart readers, and optical chemical-structure-recognition systems convert visually rich papers into computable evidence. At the cognition layer, we discuss how ontologies and knowledge graphs constrain LLM outputs, support entity alignment, and reduce semantic ambiguity. At the action layer, we compare schema-based extraction, schema-free discovery, and agentic extraction as a control–coverage–autonomy spectrum rather than a simple succession of tools. We further argue that reliability is the decisive criterion for large-scale deployment, and synthesize failure modes, layered defenses, and evaluation protocols that connect source grounding, ontology constraints, physical verification, and human-in-the-loop review. By distinguishing demonstrated extraction capabilities from more speculative AI-scientist and self-driving-laboratory visions, this review provides a comparative and risk-aware account of how LLM-driven systems can produce evidence-linked, physically meaningful, and reusable materials knowledge.

Shuai Yang, Yi-Meng Wang, Qiong Tu et al. · Journal of Materials Informa... · 0 citations

Aug 2026

A knowledge graph and large language model integration framework for intelligent oil and gas geological exploration

The digitization process in oil and gas exploration and production necessitates intelligent approaches to integrating various types of geological, geophysical, engineering, and production information. The current information systems generally lack a unified approach to knowledge representation, semantic interoperability, and reasoning capability to perform complex operations in the domain of E&P. This study presents a novel framework for an intelligent approach to oil and gas geological exploration using knowledge graphs and large language models (LLMs). The proposed architecture utilizes both the structured representation and reasoning power of knowledge graphs as well as the semantic comprehension and task planning capabilities of LLMs. A seven-layer architecture is proposed, which includes hierarchical storage, computing resource management, sampling management and model training, data management, service interface integration, industrial agents, and virtual expert groups. The main components of integration, as well as the workflow for implementation, are described to aid in geological knowledge management, target assessment, risk detection during drilling operations, and reservoir development. The proposed framework offers an actionable path to transform traditional oil and gas information systems into intelligence systems based on knowledge and reasoning rather than data-centric systems.

Jie Yang, Huaye Huang, Na Zhang et al. · Smart Oil and Gas and Sustai... · 0 citations

Jul 2026

An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents

A production extraction layer that converts a live document stream into a validated knowledge graph aligned to a formal ontology, and improved search recall from roughly 70 to 95 percent with no false merges, and corrected seven classes of silent quality defect.

Vaibhav Dangaich, Kevin Lewis, Kundeshwar Pundalik · arXiv.org · 0 citations

Open access 2024

AI-Based Knowledge Graphs for Intelligent Decision Support

Experimental results show that AI-driven knowledge graphs significantly enhance decision accuracy, reduce ambiguity, and improve interpretability, achieving up to 85–92% higher decision efficiency compared to traditional methods.

Venkatesh Iyer, Nandhini Ravi · International Journal of Art... · 0 citations

Open access Aug 2026

Towards Building a Multi-Source Heterogeneous Knowledge Graph for Complex Material Question Answering

Results indicate that integrating multi-source domain knowledge with relation-preserved retrieval and attribute-supported filtering provides more focused and inspectable evidence, thereby supporting more accurate complex material question answering.

Peize Li, Xi Guo, Nan Yin et al. · Electronics · 0 citations