Paper current collection and diversion system based on Contrimetric plug-in

Abstract

The invention provides a paper current collection and diversion system based on a Contrimetric plug-in, and relates to the field of paper diversion systems. The thesis current collection and diversion system based on the Contrimetric plug-in comprises the following steps: a, data acquisition, which is mainly responsible for collecting thesis data from various academic resources; according to the thesis current collection and diversion system based on the Contrimetric plug-in, firstly, the visibility and the reference rate of a thesis can be remarkably improved, which has great benefits for an author because the author is helped to improve the academic influence of the author in the academic circle, so that the author can obtain more acknowledgement and attention in the academic field; and secondly, through a unique recommendation mechanism, a more accurate paper recommendation service can be provided for the readers, so that the readers can be helped to save a large amount of retrieval time, the research efficiency of the readers can be remarkably improved, and the readers can quickly find high-quality papers related to the research field of the readers.

Description

Technical Field

[0001] The present invention relates to the technical field of paper diversion systems, and in particular to a paper diversion system based on a Contrimetric plug-in. Background Art

[0002] In the field of academic research, the frequency of citations and the number of readers of a paper are key indicators of its academic influence. However, due to the dispersion of academic information and the inconvenience of the retrieval mechanism, many high-quality academic papers have failed to receive corresponding academic attention. Currently, there is no efficient tool in the market that can promote a more direct communication channel between academic paper authors and readers, thereby increasing the exposure and citation rate of academic papers. Summary of the invention

[0003] The purpose of the present invention is to provide a paper flow receiving and diversion system based on Contrimetric plug-in, which solves the problems raised in the above background technology.

[0004] Technical Solution

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: A paper flow receiving and diversion system based on Contrimetric plug-in, including: a. Data acquisition, which is mainly responsible for collecting paper data from various academic resources, including but not limited to various academic databases, professional journal websites, and records and reports of academic conferences. Through this process, the system can accumulate a large amount of paper information, laying a solid foundation for subsequent processing and analysis.

[0006] b. Data processing: The paper data collected during the data collection phase needs to be carefully classified, sorted and analyzed. This process involves processing the paper's subject, field, author information, citation status and other information to ensure the accuracy and availability of the data and provide high-quality data support for the paper recommendation system. In order to more accurately extract and analyze the key information of the paper, the system uses a variety of data processing algorithms such as natural language processing technology to improve the accuracy and efficiency of data processing.

[0007] c. The system can intelligently recommend relevant papers to potential readers based on the content characteristics of the papers and the user's interest preferences. Through accurate recommendation and matching algorithms, the system can improve the reading rate and influence of papers, while also providing users with more personalized and valuable academic resources. When designing the recommendation algorithm, the system uses technologies such as long-term memory network models, heterogeneous information construction, attention mechanisms, and graph neural networks. In addition to using diversified recommendation technologies such as content-based recommendations and collaborative filtering, the system also uses user behavior data for personalized recommendations to improve the accuracy of recommendations.

[0008] d. Traffic diversion. In addition to recommending papers, the system is also responsible for guiding readers to visit the original source of the paper. It provides users with download links for papers, ensuring that users can easily and quickly obtain the complete content of the paper. This function not only improves the user experience, but also promotes the sharing and dissemination of academic resources. The system provides one-click access and download functions, as well as integration with academic social networks, allowing users to share and discuss papers more conveniently, thereby increasing the dissemination and influence of papers.

[0009] e. User feedback: Establish a user feedback system to allow users to evaluate the recommendation results. The system further optimizes the recommendation algorithm based on the feedback to improve the system's adaptability and user satisfaction. So far, nearly 200 journals have used the system and received some valuable feedback.

[0010] Furthermore, the real-time citation calling and display allows authors to track the citation changes of their achievements in real time.

[0011] Furthermore, the recommended readings change in real time: each paper is kept up to date with the latest research.

[0012] Furthermore, the recommended papers are collected, subsequently read and cited by target readers: increasing exposure and citations.

[0013] Furthermore, each document is classified into: included in Scopus, included in WoS, etc.

[0014] Furthermore, the measurement functions include: total number of publications, total citations, Scopus total citations, WoS total citations, and visitor geographic information measurement. It is used as the basis for journals to apply for inclusion in Scopus+WoS.

[0015] Furthermore, the link is connected to the ecosystem of this publisher and the ecosystem of other publishers: each paper is activated, and the algorithm is fully utilized to interconnect the published content, so as not to waste any visitor's reading and visit.

[0016] The present invention provides a paper flow receiving and diversion system based on Contrimetric plug-in. It has the following beneficial effects:

[0017] The paper flow diversion system based on Contrimetric plug-in, first of all, the present invention can significantly improve the visibility and citation rate of the paper, which is of great benefit to the author, because it helps the author to improve his academic influence in the academic community, so as to gain more recognition and attention in the academic field; secondly, the present invention can provide readers with more accurate paper recommendation services through its unique recommendation mechanism, which can not only help readers save a lot of search time, but also significantly improve their research efficiency, so that they can find high-quality papers related to their research fields more quickly; finally, the implementation of the present invention can also help promote the rational circulation of academic resources, and through the optimized recommendation and retrieval mechanism, it can enhance the activity of academic exchanges, create a more open and shared environment for the academic community, and promote the progress and development of the entire academic community. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of the data flow for importing the present invention;

[0019] Figure 2 A schematic diagram of a data flow for obtaining the present invention;

[0020] Figure 3 It is a schematic diagram of data analysis of the present invention;

[0021] Figure 4 The following is a flowchart of the algorithm recommended by the present invention. DETAILED DESCRIPTION

[0022] like Figure 1-4 As shown, the embodiment of the present invention provides a paper flow receiving and diversion system based on Contrimetric plug-in, including: a. Data collection, which is mainly responsible for collecting paper data from various academic resources, including but not limited to various academic databases, professional journal websites, and records and reports of academic conferences. Through this process, the system can accumulate a large amount of paper information, laying a solid foundation for subsequent processing and analysis.

[0023] b. Data processing: The paper data collected during the data collection phase needs to be carefully classified, sorted and analyzed. This process involves processing the paper's subject, field, author information, citation status and other information to ensure the accuracy and availability of the data and provide high-quality data support for the paper recommendation system. In order to more accurately extract and analyze the key information of the paper, the system uses a variety of data processing algorithms such as natural language processing technology to improve the accuracy and efficiency of data processing.

[0024] c. The system can intelligently recommend relevant papers to potential readers based on the content characteristics of the papers and the user's interest preferences. Through accurate recommendation and matching algorithms, the system can improve the reading rate and influence of papers, while also providing users with more personalized and valuable academic resources. When designing the recommendation algorithm, the system uses technologies such as long-term memory network models, heterogeneous information construction, attention mechanisms, and graph neural networks. In addition to using diversified recommendation technologies such as content-based recommendations and collaborative filtering, the system also uses user behavior data for personalized recommendations to improve the accuracy of recommendations.

[0025] d. Traffic diversion. In addition to recommending papers, the system is also responsible for guiding readers to visit the original source of the paper. It provides users with download links for papers, ensuring that users can easily and quickly obtain the complete content of the paper. This function not only improves the user experience, but also promotes the sharing and dissemination of academic resources. The system provides one-click access and download functions, as well as integration with academic social networks, allowing users to share and discuss papers more conveniently, thereby increasing the dissemination and influence of papers.

[0026] e. User feedback: Establish a user feedback system to allow users to evaluate the recommendation results. The system further optimizes the recommendation algorithm based on the feedback to improve the system's adaptability and user satisfaction. So far, nearly 200 journals have used the system and received some valuable feedback.

[0027] Flowchart of the system's recommended algorithm:

[0028] Start: The starting point of the process.

[0029] Data collection: Collect paper data, user behavior data, citation network, etc.

[0030] Feature extraction: Extract useful features from the collected data, such as text features, user behavior features, etc.

[0031] Multi-feature fusion: The extracted features are fused to form a comprehensive feature representation.

[0032] Deep learning model training: The system uses a long-term memory network training model to extract deep features.

[0033] Heterogeneous information network construction: Construct a heterogeneous information network containing entities such as papers, authors, and citations.

[0034] Application of attention mechanism: Introduce the attention mechanism to weight the importance of different features.

[0035] Graph Neural Network Applications: Use graph neural networks to learn complex interactions and reference relationships between entities.

[0036] Personalization and quality optimization: Optimize the objective function to balance the needs of personalization and document quality.

[0037] Adaptive user model update: Dynamically update the user's interest preference model.

[0038] Combination of collaborative filtering and content recommendation: Combine collaborative filtering technology and content-based recommendation methods for recommendation.

[0039] Recommendation result output: Output the final recommendation result.

[0040] End: The end of the process.

Claims

1. A paper flow diversion system based on Contrimetric plug-in, including: a. Data collection: This part is mainly responsible for collecting paper data from various academic resources, including but not limited to various academic databases, professional journal websites, and records and reports of academic conferences. Through this process, the system can accumulate a large amount of paper information, laying a solid foundation for subsequent processing and analysis; b. Data processing: The paper data collected during the data collection phase needs to be carefully classified, sorted and analyzed. This process involves processing the paper's subject, field, author information, citation status and other information to ensure the accuracy and availability of the data and provide high-quality data support for the paper recommendation system. In order to more accurately extract and analyze the key information of the paper, the system uses a variety of data processing algorithms such as natural language processing technology to improve the accuracy and efficiency of data processing; c. The system can intelligently recommend relevant papers to potential readers based on the content characteristics of the papers and the user's interest preferences. Through precise recommendation and matching algorithms, the system can improve the reading rate and influence of papers, while also providing users with more personalized and valuable academic resources. When designing recommendation algorithms, the system uses technologies such as long-term memory network models, heterogeneous information construction, attention mechanisms, and graph neural networks. In addition to using diversified recommendation technologies such as content-based recommendations and collaborative filtering, the system also uses user behavior data for personalized recommendations to improve the accuracy of recommendations; d. Traffic diversion. In addition to recommending papers, the system is also responsible for guiding readers to visit the original source of the paper. It provides users with download links for papers, ensuring that users can easily and quickly obtain the complete paper content. This function not only improves the user experience, but also promotes the sharing and dissemination of academic resources. The system provides one-click access and download functions, as well as integration with academic social networks, allowing users to share and discuss papers more conveniently, thereby increasing the dissemination and influence of papers; e. User feedback: Establish a user feedback system to allow users to evaluate the recommendation results. The system further optimizes the recommendation algorithm based on the feedback to improve the system's adaptability and user satisfaction. So far, nearly 200 journals have used the system and received some valuable feedback.

Images