Academic evaluation is a process of assessing and measuring researchers, institutions, or disciplinary fields. Its goal is to evaluate their contributions and impact in the academic community, as well as to determine their reputation and status within specific disciplinary domains. Web of Science (WOS), being the most renowned global academic citation database, provides crucial data for academic evaluation. However, due to factors such as institutional changes, translation discrepancies, transcription errors in databases, and authors’ individual writing habits, there exist ambiguities in the institution names recorded in the WOS literature, which in turn affect the scientific evaluation of researchers and institutions. To address the issue of data reliability in academic evaluation, this paper proposes a WOS institution name synonym recognition framework that integrates multi-granular embeddings and multi-contextual information.
Most network attacks occur at the application layer, where many application layer protocols exist. These protocols have different structures and functionalities, posing feature extraction challenges and resulting in low identification accuracy. This significantly affects application layer protocol recognition, analysis, and detection. We propose a data protocol identification method based on a Residual Network (ResNet) to address this issue. The method involves the following steps: (1) utilizing a delimiter determination algorithm based on information entropy proposed in this paper to determine an optimal set of delimiters; (2) segmenting the original data using the optimal set of delimiters and constructing a feature data block frequency table based on the frequency of segmented data blocks; (3) employing a composite-feature-based RGB image generation algorithm proposed in this paper to generate feature images by combining feature data blocks and original data; and (4) training the ResNet model with the generated feature images to automatically learn protocol features and achieve classification recognition of application layer protocols. Experimental results demonstrate that this method achieves over 98% accuracy, precision, recall, and F1 score across these four metrics.