Chongjun Xi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chongjun Xi has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Dongmei Ye
School of Information Management, Wuhan University , Wuhan 430072 , China
1 shared publication - Lucheng Lyu
National Science Library, Chinese Academy of Sciences, Beijing, China
1 shared publication Qingxin Guo
1 shared publication- Wenjun Sun
National Science Library, Chinese Academy of Sciences
1 shared publication Xiaojia Yang
1 shared publication- Xiaoting Chen
CNRS, Groupe d’Étude des Méthodes de l’Analyse Sociologique de la Sorbonne, GEMASS , Sorbonne Université , Paris 75017 , France
1 shared publication
Latest Publications
- 16 November 2026
- Published by Elsevier in World Patent Information
- Vol. 87
Quantity expansion or quality advantage? A reassessment of the technological structure of major global nations
- 16 November 2026
- Published by Elsevier in World Patent Information
- Vol. 87
Quantity expansion or quality advantage? A reassessment of the technological structure of major global nations
- Open Access
- 28 May 2026
- Published by Walter de Gruyter GmbH in Journal of Data and Information Science
Perception to Cognition: Patent Value Assessment Based on Large Language Model Semantic Enhancement and Ensemble Learning
Purpose: To address the limitations of traditional patent metrics in capturing technical substance and the high cost of expert review, this study proposes a hybrid evaluation framework integrating Large Language Models (LLMs) with machine learning to achieve automated, highly accurate identification of high-value patents. Design/methodology/approach: Adopting a “Virtual Assessor” paradigm, we constructed a dataset based on the China Patent Gold Awards. The study integrated semantic scores from three diverse LLMs (DeepSeek, Qwen, GLM) under zero-shot and few-shot prompt strategies into a Stacking ensemble learning model (combining XGBoost, Random Forest, and SVM) to predict patent value across nine comparative experimental setups. Findings: Direct LLM evaluation revealed a “Knowledge Injection Paradox,” where explicit expert prior knowledge caused negative transfer and reduced accuracy due to over-conditioning. However, the Stacking model successfully rectified these biases, transforming subjective LLM evaluations into robust predictive features. The hybrid model achieved over 97 % accuracy in identifying high-value patents, demonstrating strong robustness even in high-noise environments. Research limitations: The study relies on a binary classification of extreme samples (Gold Award vs. non-awarded), potentially oversimplifying the continuous distribution of patent value. Furthermore, the interpretability of the “black box” feature fusion mechanism requires further exploration. Practical implications: The proposed framework offers IP managers and policymakers a scalable, cost-effective tool for automated patent screening, effectively bridging the gap between qualitative expert intuition and quantitative data precision. Originality/value: This research introduces a “Semantic Enhancement + Algorithmic Rectification” paradigm. It empirically demonstrates how machine learning can correct LLM hallucinations and biases, marking a significant shift from data-driven perception to AI-driven cognitive decision-making in patent valuation.
- 28 May 2026
- Published by Walter de Gruyter GmbH in Journal of Data and Information Science
Open AccessPerception to Cognition: Patent Value Assessment Based on Large Language Model Semantic Enhancement and Ensemble Learning
Purpose: To address the limitations of traditional patent metrics in capturing technical substance and the high cost of expert review, this study proposes a hybrid evaluation framework integrating Large Language Models (LLMs) with machine learning to achieve automated, highly accurate identification of high-value patents. Design/methodology/approach: Adopting a “Virtual Assessor” paradigm, we constructed a dataset based on the China Patent Gold Awards. The study integrated semantic scores from three diverse LLMs (DeepSeek, Qwen, GLM) under zero-shot and few-shot prompt strategies into a Stacking ensemble learning model (combining XGBoost, Random Forest, and SVM) to predict patent value across nine comparative experimental setups. Findings: Direct LLM evaluation revealed a “Knowledge Injection Paradox,” where explicit expert prior knowledge caused negative transfer and reduced accuracy due to over-conditioning. However, the Stacking model successfully rectified these biases, transforming subjective LLM evaluations into robust predictive features. The hybrid model achieved over 97 % accuracy in identifying high-value patents, demonstrating strong robustness even in high-noise environments. Research limitations: The study relies on a binary classification of extreme samples (Gold Award vs. non-awarded), potentially oversimplifying the continuous distribution of patent value. Furthermore, the interpretability of the “black box” feature fusion mechanism requires further exploration. Practical implications: The proposed framework offers IP managers and policymakers a scalable, cost-effective tool for automated patent screening, effectively bridging the gap between qualitative expert intuition and quantitative data precision. Originality/value: This research introduces a “Semantic Enhancement + Algorithmic Rectification” paradigm. It empirically demonstrates how machine learning can correct LLM hallucinations and biases, marking a significant shift from data-driven perception to AI-driven cognitive decision-making in patent valuation.
- 29 October 2025
- Published by Springer Nature
- p. 308-322
Technical Contradiction Extraction Based on Two-Stage Knowledge Fusion Mechanism
- 29 October 2025
- Published by Springer Nature
- p. 308-322
Technical Contradiction Extraction Based on Two-Stage Knowledge Fusion Mechanism