Access Range: Campus Network Only

Access Address: Online Access  | Off-Campus Access

Chaoxing Discovery is a powerful academic discovery system. Leveraging a massive metadata repository and a robust vocabulary database, it ensures comprehensive and precise literature retrieval. Its continuously optimized search engine saves researchers time, enabling rapid knowledge discovery. The system excels in resource integration, seamlessly incorporating the library's print collections and commercial database subscriptions into a normalized, systematic, and unified framework. This significantly improves the utilization rate of both physical and electronic collections, providing a single search point for all library resources.

Going beyond standard search functionality, Chaoxing Discovery utilizes big data analytics to perform personalized, accurate, and in-depth data mining and knowledge association. It helps users map knowledge structures, expand their understanding of academic fields, and enhances the system's ability to transform simple information retrieval into meaningful knowledge discovery. Chaoxing Discovery is poised to deliver an unparalleled knowledge discovery experience.

Core Features:

Multi-dimensional Faceted Clustering: Search results can be clustered by various facets, including publication year, document type, subject, discipline, author, institution, and indexing in authoritative databases (e.g., SCI, SSCI).

Intelligent Assisted Search: The system utilizes a built-in authority database and analyzes user search history to automatically refine searches towards the most relevant research areas, helping users grasp the core concepts of their topic in real-time.

Comprehensive Citation Analysis: Analyzes citation relationships across different resource types, including books-to-books, journals-to-journals, books-to-journals, and beyond, revealing the scholarly conversation.

Academic Lineage Tracking: Maps the influence and evolution of academic ideas by establishing linear and networked knowledge associations, generating relational graphs for topics, disciplines, authors, institutions, and regions.

Knowledge Association Graph: Integrates knowledge mining, association analysis, and visualization technologies to present discovery data and analytical results in an intuitive graphical format.

Research Trend Visualization: Reveals the chronological evolution of research on any given topic. It provides a macro-view of a field's development—identifying its origins, growth, fluctuations, and trends—based on large-scale data analysis.

AI-Powered Generative Search: Employs RAG (Retrieval-Augmented Generation) technology. It retrieves relevant literature based on search queries, enhances the context using predefined templates, and leverages large language models to generate accurate, synthesized text, such as aiding in the creation of literature reviews on a specific topic.