Tremendous academic articles face serious information overload problems while supporting literature searches. Finding a research article in a relevant domain that meets researchers’ requirements is challenging. Hence, different paper recommendation models have been proposed to address this issue. However, these models lack a more comprehensive analysis of the connections between the literature, the domain knowledge provided, and the hotspot information expressed in the literature. Previous models make it impossible to locate the appropriate documents for domain literature. Additionally, these models encounter problems such as cold start papers and data sparsity. To overcome these problems, this paper presents a recommendation model termed PRHN. Inputs of the model are the hotspot information network and the domain knowledge graph, which both were developed during the preceding research phase. After the query terms are extracted and the associated heterogeneous literature networks are formed, they are aggregated in a uniform hidden space. Similarity with the candidate set is determined to transform the search problem into a TOP N recommendation problem. Compared to state-of-the-art models, results generated by PRHN on public available datasets show improvement in HR and NDCG. Concretely, results on the metallurgical literature dataset are more conspicuous, with more remarkable improvement in HR and NGCC by approximately 4.5% and 4.2%.
Extracting keywords from a text set is an important task. Most of the previous studies extract keywords from a single text. Using the key topics in the text collection, the association relationship between the topic and the topic in the cross-text, and the association relationship between the words and the words in the cross-text has not played an important role in the previous method of extracting keywords from the text collection. In order to improve the accuracy of extracting keywords from text collections, using the semantic relationship between topics and topics in texts and highlighting the semantic relationship between words and words under the key topics, this article proposes an unsupervised method for mining keywords from short text collections. In this method, a two level semantic association model is used to link the semantic relations between topics and the semantic relations between words, and extract the key words based on the combined action. First, the text is represented with LDA; the authors used word2vec to calculate the semantic association between topic and topic, and build a semantic relation graph between topics, that is the upper level graph, and use a graph ranking algorithm to calculate each topic score. In the lower layer, the semantic association between words and words is calculated by using the topic scores and the relationship between topics in the upper network allow a graph to be constructed. Using a graph sorting algorithm sorts the words in short text sets to determine the keywords. The experimental results show that the method is better for extracting keywords from the text set, especially in short articles. In the text, the important topics, the relationship between topics and the correlation between words can improve the accuracy of extracting keywords from the text set.
With the rapid advancement of advanced manufacturing and smart logistics, the collaborative optimization and integrated scheduling of production, transportation, and assembly have emerged as a core competency for modern manufacturing enterprises. This article studies a significant transportation-assembly collaborative optimization problem (TACOP), which aims primarily to minimize cycle time, with secondary objectives of minimizing both transportation cost and inventory levels. Since TACOP comprises two coupled sub-problems, namely, the vehicle routing problem (VRP) and the simple assembly line balancing problem (SALBP), a decomposition-based Q-learning evolutionary algorithm (DQEA) is proposed to deal with the TACOP. First, the assembly agent solves the SALBP to acquire an assembly scheme with a minimized cycle time. Subsequently, this assembly scheme is extended into a diverse set of assembly solutions that share the same cycle time but differ in task arrangements. Next, these assembly solutions are decomposed by a slicing method of load balancing to generate specific subproblems, which also facilitates the reduction of inventory levels. Furthermore, given the independence of these VRPs, the transportation agent can solve them in parallel, enabling the efficient derivation of corresponding transportation solutions. To tackle the SALBP and VRPs, the agent utilizes an off-policy approach to adaptively perform global and local search, thereby extracting valuable insights from high-quality actions and rapidly guiding the search direction toward promising regions. Extensive experiments and computational comparisons are carried out to demonstrate the effectiveness and efficiency of DQEA in solving TACOP.
Named entity recognition (NER) in few-shot scenarios plays a critical role in entity annotation for low-resource domains. However, existing methods are often limited to learning semantic features and intermediate representations specific to the source domain, which restricts their generalization capability when applied to unseen target domains and leads to prominent performance degradation. To address this issue, we propose a novel few-shot NER model based on contrastive learning. Specifically, the model enhances token representations through Gaussian distribution embedding and a self-attention mechanism, while adaptively optimizing the weighting parameters of the contrastive loss to achieve performance improvement. This design effectively mitigates overfitting and enhances the model’s generalization ability. Experiments on multiple datasets (including CoNLL2003, GUM, and Few-NERD) demonstrate that our approach achieves performance gains of 2.05% to 15.89% compared to state-of-the-art methods. These results confirm the effectiveness of our model in few-shot NER tasks and suggest its potential for broader application in low-resource information extraction scenarios.