Method For Predicting Research Citation Growth Using Queueing Theory And Machine Learning With A Computer Implemented System

Sandeep Kumar
Awaiting Request for Examination App No 202511050137 Computer Science

Patent information

IP India · live record
Application number
202511050137
Filing date
25 May 2025
Status
Awaiting Request for Examination
Publication number
24/2025
Publication type
INA
Invention field
Computer Science

Abstract

ABSTRACT The present invention relates to a computer-implemented system and method for predicting research citation growth using queueing theory and machine learning. The system comprises a data acquisition module for collecting bibliometric data, a queueing-based modeling engine for classifying citation growth patterns, a machine learning processor for predicting future citations, a database storage unit for maintaining research metrics, and a user interface module for visualizing citation trends. The method involves acquiring citation data, applying a queueing-based model, using machine learning for enhanced accuracy, storing processed data, and generating citation trend reports. By integrating queueing theory with AI-driven analytics, the invention provides an accurate and dynamic approach to forecasting research impact, benefiting universities, funding agencies, and researchers in evaluating scholarly influence and optimizing funding decisions.

Applicants

9
India
Sandeep Kumar Department of Management, JB Institute of Technology, Dehradun
India
Mr. Suraj Sinha JB Institute of Technology, Dehradun Pincode - 248197
India
Dr. Surjan Singh Department of Mathematics, Eternal University Baru Sahib HP, PIN 173101
India
Anil Kumar Gupta GD Goenka University, Sohna, Gurugram, Haryana, India
India
Mrs. Kokil Bhatia Department of Management, JB Institute of Technology,Dehradun
India
Dr Md Heshamuddin GLOCAL UNIVERSITY, Mirzapur pole, Saharanpur Uttar Pradesh, India
India
Mr Ravi Shankar Department of Mechanical Engineering, JB Institute of Technology, Dehradun
India
Dr. Sandeep Kumar Yadav Department of AIML, JB Institute of Technology Dehradun.
India
Prem Kumar Department of ECE, JB Institute of Technology, Dehradun

Inventors

9
India
Sandeep KumarDepartment of Management, JB Institute of Technology, Dehradun
India
Mr. Suraj SinhaJB Institute of Technology, Dehradun Pincode - 248197
India
Dr. Surjan SinghDepartment of Mathematics, Eternal University Baru Sahib HP, PIN 173101
India
Anil Kumar GuptaGD Goenka University, Sohna, Gurugram, Haryana, India
India
Mrs. Kokil BhatiaDepartment of Management, JB Institute of Technology,Dehradun
India
Dr Md HeshamuddinGLOCAL UNIVERSITY, Mirzapur pole, Saharanpur Uttar Pradesh, India
India
Mr Ravi ShankarDepartment of Mechanical Engineering, JB Institute of Technology, Dehradun
India
Dr. Sandeep Kumar YadavDepartment of AIML, JB Institute of Technology Dehradun.
India
Prem KumarDepartment of ECE, JB Institute of Technology, Dehradun

Claims

8
1 A computer-implemented system for predicting research citation growth, comprising: o a data acquisition module configured to collect bibliometric data from digital repositories, journals, and academic citation databases; o a queueing-based modeling engine configured to classify research articles into citation growth categories based on historical trends and real-time citation accumulation; o a machine learning processor configured to analyze historical citation patterns, predict future citation trajectories, and update predictive models dynamically; o a database storage unit for storing citation records, author metrics, and journal impact factors; and o a user interface module configured to display citation predictions, trend analysis, and impact factor estimations for researchers, universities, and funding agencies.
2 The system of claim 1, wherein the queueing-based modeling engine applies an M/M/8 queueing model to predict the citation rate of a research publication based on arrival patterns of citations over time.
3 The system of claim 1, wherein the machine learning processor employs supervised and unsupervised learning algorithms to refine citation predictions based on evolving citation trends, co-authorship networks, and interdisciplinary impact.
4 The system of claim 1, wherein the database storage unit integrates citation data with h index, i10-index, and journal impact factor scores to provide comprehensive research performance insights.
5 The system of claim 1, wherein the user interface module is configured to generate real time citation trajectory graphs, heat maps, and comparative analysis reports for researchers and institutions.
6 The system of claim 1, wherein the data acquisition module retrieves citation data from open-access platforms, proprietary research databases, and government-funded repositories using API integration and web scraping techniques.
7 A method for predicting research citation growth, comprising: o collecting citation data from multiple academic sources; o processing the data using a queueing-based citation prediction model; o applying machine learning techniques to improve the accuracy of predictions; o storing processed data in a structured bibliometric database; and o displaying real-time citation growth trends through an interactive user interface.
8 The method of claim 7, wherein the citation prediction accuracy is enhanced using reinforcement learning techniques, allowing the system to self-improve based on real time citation feedback.

Specification

Show full textCollapse

Description:DETAILED DESCRIPTION For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the following description. Specific language will be used to describe the system and method, but it will be understood that no limitation of the scope of the invention is thereby intended. Alterations, modifications, and variations in the illustrated system, and further applications of the principles of the invention as illustrated, are contemplated and would normally occur to one skilled in the art to which the invention relates. It will be understood by those skilled in the art that the general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive. Reference throughout this specification to “an embodiment,” “another embodiment,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrases “in an embodiment,” “in another embodiment,” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment. The terms "comprises," "comprising," or any other variations thereof are intended to cover a non exclusive inclusion. This means that a process or method comprising a list of steps does not exclude other steps that are not explicitly listed but may be inherent to such processes or methods. Similarly, when one or more devices, sub-systems, structures, components, or elements are described as "comprising... a," this does not, without more constraints, preclude the inclusion of additional devices, sub-systems, structures, components, or elements that may be part of the system or method. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative and should not be construed as limiting. The present invention provides a computer-implemented system and method for predicting research citation growth by integrating queueing theory and machine learning techniques. The invention is designed to analyze citation trends, predict future research impact, and assist researchers, universities, and funding agencies in making data-driven decisions. The system comprises multiple components, each performing a critical function in citation prediction. The data acquisition module is responsible for collecting bibliometric data from digital repositories, research databases, and academic journals. It integrates with APIs and web crawling techniques to ensure comprehensive data collection. The queueing-based modeling engine classifies research articles based on citation growth patterns using M/M/8 queueing models or other probabilistic techniques, enabling accurate categorization of research impact. The machine learning processor refines citation predictions by applying supervised and unsupervised learning algorithms, analyzing co-authorship networks, interdisciplinary influence, and time-series trends. A database storage unit is employed to store structured bibliometric data, including citation records, impact factors, h-index, and i10-index. The user interface module provides real-time citation trajectory visualizations, predictive insights, and comparative analysis dashboards, allowing researchers and institutions to monitor research impact effectively. , Claims:CLAIMS I/We claim: 1. A computer-implemented system for predicting research citation growth, comprising: o a data acquisition module configured to collect bibliometric data from digital repositories, journals, and academic citation databases; o a queueing-based modeling engine configured to classify research articles into citation growth categories based on historical trends and real-time citation accumulation; o a machine learning processor configured to analyze historical citation patterns, predict future citation trajectories, and update predictive models dynamically; o a database storage unit for storing citation records, author metrics, and journal impact factors; and o a user interface module configured to display citation predictions, trend analysis, and impact factor estimations for researchers, universities, and funding agencies. 2. The system of claim 1, wherein the queueing-based modeling engine applies an M/M/8 queueing model to predict the citation rate of a research publication based on arrival patterns of citations over time. 3. The system of claim 1, wherein the machine learning processor employs supervised and unsupervised learning algorithms to refine citation predictions based on evolving citation trends, co-authorship networks, and interdisciplinary impact. 4. The system of claim 1, wherein the database storage unit integrates citation data with h index, i10-index, and journal impact factor scores to provide comprehensive research performance insights. 5. The system of claim 1, wherein the user interface module is configured to generate real time citation trajectory graphs, heat maps, and comparative analysis reports for researchers and institutions. 6. The system of claim 1, wherein the data acquisition module retrieves citation data from open-access platforms, proprietary research databases, and government-funded repositories using API integration and web scraping techniques. 7. A method for predicting research citation growth, comprising: o collecting citation data from multiple academic sources; o processing the data using a queueing-based citation prediction model; o applying machine learning techniques to improve the accuracy of predictions; o storing processed data in a structured bibliometric database; and o displaying real-time citation growth trends through an interactive user interface. 8. The method of claim 7, wherein the citation prediction accuracy is enhanced using reinforcement learning techniques, allowing the system to self-improve based on real time citation feedback.

Documents

Sign in to open
Application documents
1 202511050137-FORM-9 [25-05-2025(online)].pdf 25 May 2025
2 202511050137-FORM-5 [25-05-2025(online)].pdf 25 May 2025
3 202511050137-FORM 3 [25-05-2025(online)].pdf 25 May 2025
4 202511050137-FORM 1 [25-05-2025(online)].pdf 25 May 2025
5 202511050137-FIGURE OF ABSTRACT [25-05-2025(online)].pdf 25 May 2025
6 202511050137-DRAWINGS [25-05-2025(online)].pdf 25 May 2025
7 202511050137-COMPLETE SPECIFICATION [25-05-2025(online)].pdf 25 May 2025