Research on Literature Clustering Algorithm for Massive Scientific and Technical Literature Query Service

Area of Science:

• Information Science
• Computer Science
• Data Science

Background:

• Traditional scientific and technical literature search methods are challenged by the exponential growth of digital information resources.
• Existing approaches struggle to meet user information needs within large-scale datasets due to limitations in traditional technical methods and service models.

Purpose of the Study:

• To propose an effective model for large-scale scientific and technical literature search services in the big data era.
• To address the limitations of traditional search methods for handling diverse and voluminous scientific literature data.

Main Methods:

• Developed a fast literature retrieval method combining R-tree indexing, optimized for diverse data types and large volumes.
• Utilized an improved k-means clustering algorithm to construct an R-tree clustering model for enhanced retrieval.
• Implemented R-tree indexing to improve the efficiency of searching scientific and technical literature data.

Main Results:

• Experimental results on university science and technology literature datasets demonstrate significant improvements.
• The proposed method shows enhanced efficiency in literature searching.
• The method also achieves improved precision in retrieving relevant scientific literature.

Conclusions:

• The R-tree indexing method offers a viable solution for efficient and precise large-scale scientific literature retrieval.
• This approach effectively addresses the challenges posed by big data in scientific information services.
• The study highlights the potential of advanced indexing techniques for modern knowledge discovery.