Instrument Landing System （ILS） is a critical navigation device for ensuring flight safety， whose signal quality affects the accuracy and safety of aircraft landing accuracy and safety directly. However， the increasingly complex electromagnetic environment around airports leads to more and more multipath effects， thereby impacting the reliability and precision of ILS signals significantly. Therefore， taking LOCalizer （LOC） as the research object， a signal propagation path analysis method based on backward ray-tracing method was proposed. In the method， by establishing an electromagnetic propagation model of the airport environment and incorporating ray-tracing and path validity determination rules， the propagation characteristics of ILS signals in multipath environments were investigated systematically. And the influence of signal reflection and diffraction effects caused by obstacles on the Difference in Depth of Modulation （DDM） of the airborne LOC receiving signals were particularly analyzed. Simulation results demonstrate that when obstacles are near the runway centerline， DDM experiences significant fluctuations， with the maximum jitter reached 283.4% of the value specified by the International Civil Aviation Organization （ICAO） approximately. And after adjusting the obstacle positions appropriately， occlusions between obstacles and the increased distance between obstacles and the runway centerline lead to a reduction in multipath interference. As a result， the fluctuation of DDM decreases significantly and meets the ICAO’s prescribed limit， with the maximum jitter reached 99.0% of the specified value approximately. The above verifies that this method can assess the impact of multipath propagation on ILS performance in complex airport environments effectively.

To address the problem that the existing methods based on attention mechanism are difficult to capture complex dependencies among texts， a multi-label text classification method based on contrastive learning enhanced dual-attention mechanism was proposed. Firstly， text representations based on self-attention and label attention were learned respectively， and the two were fused to obtain a more comprehensive text representation for capturing structural features of the text and semantic associations among the text and labels. Then， a multi-label contrastive learning objective was given to supervise the learning of text representations by label-guided text similarity， thereby capturing complex dependencies among the texts at topic， content， and structural levels. Finally， a feedforward neural network was used as a classifier for text classification. Experimental results demonstrate that compared with LDGN （Label-specific Dual Graph neural Network）， the proposed method improves the normalized Discounted Cumulative Gain at top-5 （nDCG@5） value by 1.81 and 0.86 percentage points， respectively， on EUR-Lex （European Union Law Document） dataset and Reuters-21578 dataset， and achieves competitive results on AAPD （Arxiv Academic Paper Dataset） dataset and RCV1 （Reuters Corpus Volume Ⅰ） dataset. It can be seen that this method can capture the complex dependencies among texts at topic， content， and structural levels effectively， resulting in good performance in multi-label text classification tasks.

To address the following two major drawbacks of existing Contrastive Learning （CL） methods for the nested Named Entity Recognition （NER） tasks： 1） candidate entities by greedily enumerating in contrastive learning lack contextual semantics and boundary information， 2） unnecessary noise and invalid information increases computational burden and weakens contrastive learning performance， a two-stage NER framework was proposed. In the first stage， candidate entity boundaries were generated by the boundary recognition model， and candidate entities were integrated by the boundary integration module to minimize unnecessary negative candidates. Attention cues were inserted on both sides of the candidate entities to generate corresponding candidate entity texts， allowing the model to perceive contextual semantics and boundary information. In the second stage， a bi-encoder framework mapped candidate entity texts and entity label annotations into the same vector representation space through contrastive learning， with the comparison objects being sentences with attention cues rather than candidate entities. In addition， a classification parameter matrix with label semantics was designed to enrich the model’s understanding of candidate entities.Experimental results show that compared with Binder method， the proposed method improves the F1 values of 1.22， 3.42 and 2.31 percentage points， respectively， on three nested datasets： GENIA， ACE2005 and ACE2004， which verifies the effectiveness of the proposed method for tasks of nested NER.

The development of hot news events is very rich， and each stage of the development has its own unique narrative. With the development of events， a trend of hierarchical storyline evolution is presented. Aiming at the problem of poor interpretability and insufficient hierarchy of storyline in the existing storyline generation methods， a Hierarchical Storyline Generation Method （HSGM） for hot news events was proposed. First， an improved hotword algorithm was used to select the main seed events to construct the trunk. Second， the hotwords of branch events were selected to enhance the branch interpretability. Third， in the branch， a storyline coherence selection strategy fusing hotword relevance and dynamic time penalty was used to enhance the connection of parent-child events， so as to build hierarchical hotwords， and then a multi-level storyline was built. In addition， considering the incubation period of hot news events， a hatchery was added during the storyline construction process to solve the problem of neglecting the initial events due to insufficient hotness. Experimental results on two real self-constructed datasets show that in the event tracking process， compared with the methods based on singlePass and k-means respectively， HSGM has the F score increased by 4.51% and 6.41%， 20.71% and 13.01% respectively； in the storyline construction process， HSGM performs well in accuracy， comprehensibility and integrity on two self-constructed datasets compared with Story Forest and Story Graph.

The rapid development of Internet leads to the explosive growth of news data. How to capture the topic evolution process of current popular events from massive news data has become a hot research topic in the field of document analysis. However， the commonly used traditional dynamic clustering models are inflexible and inefficient when dealing with large-scale datasets， while the existing deep document clustering models lack a general method to capture the topic evolution process of time series data. To address these problems， a Deep Dynamic Document Clustering （DDDC） model was designed. In this model， based on the existing deep variational inference algorithms， the topic distributions incorporating the content of previous time slices on different time slices were captured， and the evolution process of event topics was captured from these distributions through clustering. Experimental results on real news datasets show that compared with Dynamic Topic Model （DTM）， Variational Deep Embedding （VaDE） and other algorithms， DDDC model has the clustering accuracy and Normalized Mutual Information （NMI） improved by at least 4 percentage points averagely and at least 3 percentage points respectively in each time slice on different datasets， verifying the effectiveness of DDDC model.

In recent years， due to the advantages of the structural information of Graph Neural Network （GNN） in machine learning， people have begun to combine GNN into deep text clustering. The current deep text clustering algorithm combined with GNN ignores the important role of the decoder on semantic complementation in the fusion of text semantic information， resulting in the lack of semantic information in the data generation part. In response to the above problem， a Structured Deep text Clustering Model based on multi-layer Semantic fusion （SDCMS） was proposed. In this model， a GNN was utilized to integrate structural information into the decoder， the representation of text data was enhanced through layer-by-layer semantic complement， and better network parameters were obtained through triple self-supervision mechanism.Results of experiments carried out on 5 real datasets Citeseer， Acm， Reutuers， Dblp and Abstract show that compared with the current optimal Attention-driven Graph Clustering Network （AGCN） model， SDCMS in accuracy， Normalized Mutual Information （NMI ） and Average Rand Index （ARI） has increased by at most 5.853%， 9.922% and 8.142%.