Traditional knowledge reasoning methods based on representation learning can only be used for closed-world knowledge reasoning. Conducting open-world knowledge reasoning effectively is a hot issue currently. Therefore， a knowledge reasoning model based on path and enhanced triplet text， named PEOR （Path and Enhanced triplet text for Open world knowledge Reasoning）， was proposed. First， multiple paths generated by structures between entity pairs and enhanced triplets generated by individual entity neighborhood structures were utilized. Among then， the path text was obtained by concatenating the text of triplets in the path， and the enhanced triplet text was obtained by concatenating the text of head entity neighborhood， relation， and tail entity neighborhood. Then， BERT （Bidirectional Encoder Representations from Transformers） was employed to encode the path text and enhanced triplet text separately. Finally， semantic matching attention calculation was performed using path vectors and triplet vectors， followed by aggregation of semantic information from multiple paths using semantic matching attention. Comparison experimental results on three open-world knowledge graph datasets： WN18RR， FB15k-237， and NELL-995 show that compared with suboptimal model BERTRL （BERT-based Relational Learning）， the proposed model has Hits@10 （Hit ratio） metric improved by 2.6， 2.3 and 8.5 percentage points， respectively， validating the effectiveness of the proposed model.

Utilizing contextual information of scene graphs can help models understand the correlation effect among targets. However， a large number of unrelated targets may introduce additional noise， affecting information interaction and causing prediction biases. In noisy and diverse scenes， even a few simple associated targets are sufficient to infer environmental information of the target and eliminate ambiguity information of other targets. In addition， Scene Graph Generation （SGG） faces challenges when dealing with long-tailed biased data in real-world scenarios. To address the problems of contextual information optimization and prediction biases， an association Information Enhancement and Relationship Balance based SGG （IERB） method was proposed. In IERB method， a secondary reasoning structure was employed according to biased scene graph prediction results， to reconstruct association information under different prediction angles of view and balance the prediction biases. Firstly， strongly correlated targets from different angles of view were focused on to construct the contextual association information. Secondly， the prediction capability for tail relationships was enhanced using a balancing strategy of tree structure. Finally， a prediction-guided approach was used to optimize predictions based on the existing scene graph. Experimental results on Visual Genome dataset show that compared with three baseline models Visual Translation Embedding network （VTransE）， Motif， and Visual Context Tree （VCTree）， the proposed method improves the mean Recall mR@100 in the Predicate Classification （PredCls） task by 11.66， 13.77 and 13.62 percentage points， respectively， demonstrating the effectiveness of the proposed method.

Panoptic Scene Graph Generation （PSGG） aims to identify all objects within an image and capture the intricate semantic association among them automatically. Semantic association modeling depends on feature description of target objects and subject-object pair. However， current methods have several limitations： object features extracted through bounding box extraction are ambiguous； the methods only focus on the semantic and spatial position features of objects， while ignoring the semantic joint features and relative position features of subject-object pair， which are equally essential for accurate relation predictions； current methods fail to extract features of different types of subject-object pair （e.g.， foreground-foreground， foreground-background， background-background） differentially， ignoring their inherent differences. To address these challenges， a PSGG method based on Relation Feature Enhancement （RFE） was proposed. Firstly， by introducing pixel-level mask regional features， the detailed information of object features was enriched， and the joint visual features， semantic joint features， and relative position features of subject-objects were integrated effectively. Secondly， depending on the specific type of subject-object， the most suitable feature extraction method was selected adaptively. Finally， more accurate relation features after enhancement were obtained for relation prediction. Experimental results on the PSG dataset demonstrate that with VCTree （Visual Contexts Tree）， Motifs， IMP （Iterative Message Passing）， and GPSNet as baseline methods， and ResNet-101 as the backbone network， RFE achieves increases of 4.37， 3.68， 2.08， and 1.80 percentage points， respectively， in R@20 index for challenging SGGen tasks. The above validates the effectiveness of the proposed method in PSGG.

Multi-view clustering has recently been a hot topic in graph data mining. However， due to the limitations of data collection technology or human factors， multi-view data often has the problem of missing views or samples. Reducing the impact of incomplete views on clustering performance is a major challenge currently faced by multi-view clustering. In order to better understand the development of Incomplete Multi-view Clustering （IMC） in recent years， a comprehensive review is of great theoretical significance and practical value. Firstly， the missing types of incomplete multi-view data were summarized and analyzed. Secondly， four types of IMC methods， based on Multiple Kernel Learning （MKL）， Matrix Factorization （MF） learning， deep learning， and graph learning were compared， and the technical characteristics and differences among the methods were analyzed. Thirdly， from the perspectives of dataset types， the numbers of views and categories， and application fields， twenty-two public incomplete multi-view datasets were summarized. Then， the evaluation metrics were outlined， and the performance of existing incomplete multi-view clustering methods on homogeneous and heterogeneous datasets were evaluated. Finally， the existing problems， future research directions， and existing application fields of incomplete multi-view clustering were discussed.

To address the problem that relevant models typically only model characters and relevant vocabulary without fully utilizing the unique glyph structure information and entity type information of Chinese characters， a model that integrates prior knowledge and glyph features for Named Entity Recognition （NER） task was proposed. Firstly， the input sequence was encoded using a Transformer combined with Gaussian attention mechanism， and the Chinese definitions of entity types were obtained from Chinese Wikipedia. Bidirectional Gated Recurrent Unit （BiGRU） was used to encode the entity type information as prior knowledge， which was combined with the character representation using an attention mechanism. Secondly， Bidirectional Long Short-Term Memory （BiLSTM） network was used to encode the long-distance dependency relationship of the input sequence， and a glyph encoding table was used to obtain traditional Chinese characters’ Cangjie codes and simplified Chinese characters’ modern Wubi codes. Then， Convolutional Neural Network （CNN） was used to extract glyph feature representations， and the traditional and simplified glyph feature representations were combined with different weights， which were then combined with the character representation encoded by BiLSTM using a gating mechanism. Finally， decoding was performed using Conditional Random Field （CRF） to obtain a sequence of named entity annotations. Experiment results on the colloquial dataset Weibo， the small dataset Boson， and the large dataset PeopleDaily show that， compared with the baseline model MECT （Multi-metadata Embedding based Cross-Transformer）， the proposed model has the F1 value increased by 2.47， 1.20， and 0.98 percentage points， respectively， proving the effectiveness of the proposed model.

Currently， Graph ATtention network （GAT） assigns different weights to entities in the neighbourhood of the target entity and performs information aggregation by introducing an attention mechanism， which makes it pay more attention to the local neighbourhood of the entity and ignore the topology between entities and relations in the graph structure. Moreover， the output embedding vectors are simply spliced or averaged after the multi-head attention， resulting in the independence of attention heads， and fails to capture important semantic information of different attention heads. Aiming at the problems that GAT does not fully mine entity structural information and semantic information when it is applied to knowledge graph reasoning task， a Fusing Entity Semantic and Structural Information for knowledge graph reasoning （FESSI） model was proposed. Firstly， TransE was used to represent entities and relationships as embedding vectors in the same space. Secondly， an interactive attention mechanism was proposed to reintegrate the multi-head attention in GAT into multiple hybrid attentions， which enhanced the interaction between the attention heads to extract richer semantic information of the target entity. At the same time， the structural information of the entity was extracted by utilizing the Relational Graph Convolutional Network （R-GCN）， and the output feature vectors of GAT and R-GCN were learned through weight matrices. Finally， ConvKB was used as a decoder for scoring. Experimental results on the knowledge graph datasets Kinship， NELL-995 and FB15K-237 show that the FESSI model outperforms most comparison models， with the Mean Reciprocal Rank （MRR） index on the three datasets of 0.964， 0.565 and 0.562， respectively.

In response to the problems that Knowledge Tracing （KT） models do not consider differences between students and explore the high matching between knowledge states and exercises， a two-layer network architecture was proposed — Knowledge Tracing based on Personalized Learning and Deep Refinement （PLDRKT）. Firstly， the attention enhancement mechanism was used to obtain a deep refined representation of the exercises. Then， personalized modeling of the initial knowledge state was conducted from the perspectives of different students’ perceptions of difficulty and learning benefits of the exercises. Finally， the initial knowledge states and the deep exercise representations were used to obtain the students’ deep knowledge states and predict their future answering conditions. Comparative experiments were conducted on Statics2011， ASSIST09， ASSIST15， and ASSIST17 datasets among PLDRKT model and seven models such as enhancing Adversarial Training based Knowledge Tracing （ATKT） and ENsemble Knowledge Tracing （ENKT）. Experimental results show that the Area Under the Curve （AUC） of PLDRKT model is increased by 0.61， 1.32， 5.29， and 0.19 percentage points， respectively， compared to the optimal baseline models without considering exercise embedding on four datasets. It can be seen that PLDRKT model can model students’ knowledge states and predict answers effectively.

In recent years， more and more schools tend to use online education widely. However， learners are hard to search for their needs from the massive learning resources in the Internet. Therefore， it is very important to research the online learning resource recommendation and perform personalized recommendations for learners， so as to help learners obtain the high-quality learning resources they need quickly. The research status of online learning resource recommendation was analyzed and summarized from the following five aspects. Firstly， the current work of domestic and international online education platforms in learning resource recommendation was summed up. Secondly， four types of algorithms were analyzed and discussed： using knowledge point exercises， learning paths， learning videos and learning courses as learning resource recommendation targets respectively. Thirdly， from the perspectives of learners and learning resources， using the specific algorithms as examples， three learning resource recommendation algorithms based on learners’ portraits， learners’ behaviors and learning resource ontologies were introduced in detail respectively. Moreover， the public online learning resource datasets were listed. Finally， the current challenges and future research directions were analyzed.

Aiming at the problems of the slow model convergence and low diagnosis accuracy due to the time-series fault diagnosis data with strong noise in the industrial field， an improved one-Dimensional Convolutional and Bidirectional Long Short-Term Memory（1DCNN-BiLSTM） Neural Network fault diagnosis method was proposed. The method includes preprocessing of fault vibration signals， automatic feature extraction and vibration signal classification. Firstly， Complete Ensemble Empirical Mode Decomposition with Adaptive Noise （CEEMDAN） technology was used to preprocess the original vibration signal. Secondly， the 1DCNN-BiLSTM dual channel model was constructed， and the processed signal was input into the Bidirectional Long Short-Term Memory （BiLSTM） model channel and the One-dimensional Convolution Neural Network （1DCNN） model channel to fully extract the timing correlation characteristics， the non-correlation characteristics of the local space and the weak periodic laws of the signal. Thirdly， in response to the problem of strong noise in the signal， the Squeeze and Excitation Network （SENet） module was improved and applied to the two different channels. Finally， the features extracted from the two channels were fused by putting them into the fully connected layer， and the accurate identification of equipment faults was realized by the help of the Softmax classifier. The bearing dataset of Case Western Reserve University was used for experimental comparison and verification. The results show that after applying the improved SENet module to the 1DCNN channel and the stacked BiLSTM channel at the same time， the 1DCNN-BiLSTM dual channel model performs the highest diagnosis accuracy 96.87% with fast convergence， which is better than traditional one-channel models， thereby effectively improving the efficiency of equipment fault diagnosis.

Clustering is a technique to find the internal structure between data， which is a basic problem in many data-driven applications. Clustering performance depends largely on the quality of data representation. In recent years， deep learning is widely used in clustering tasks due to its powerful feature extraction ability， in order to learn better feature representation and improve clustering performance significantly. Firstly， the traditional clustering tasks were introduced. Then， the representative clustering methods based on deep learning were introduced according to the network structure， the existing problems were pointed out， and the applications of deep learning based clustering in different fields were presented. At last， the development of deep learning based clustering was summarized and prospected.

In order to solve the problem that the algorithms of publication venue recommendation always consider the text topics or the author’s history of publications separately， which leads to the low accuracy of publication venue recommendation results， a contribution recommendation algorithm of academic journal based on author preferences was proposed. In this algorithm， not only the text topics and the author’s history of publications were used together， but also the potential relationship between the academic focuses of publication venues and time were explored. Firstly， the Latent Dirichlet Allocation （LDA） topic model was used to extract the topic information of the paper title. Then， the topic-journal and time-journal model diagrams were established， and the Large-scale Information Network Embedding （LINE） model was used to learn the embedding of graph nodes. Finally， the author’s subject preferences and history of publication records were fused to calculate the journal composite scores， and the publication venue recommendation for author to contribute was realized. Experimental results on two public datasets， DBLP and PubMed， show that the proposed algorithm has better recall under different list lengths of recommended publication venues compared to six algorithms such as Singular Value Decomposition （SVD）， DeepWalk and Non-negative Matrix Factorization （NMF）. The proposed algorithm maintains high accuracy while requiring less information from papers and knowledge bases， and can effectively improve the robustness of publication venue recommendation algorithm.