Named Entity Recognition （NER） aims to identify predefined entity types from unstructured text. Span-based NER methods recognize entities through enumerating all the spans. However， adjacent spans in the text share contextual semantics， which leads to semantic information ambiguity among span boundaries， thus making it difficult for models to capture dependency information among spans. To address the issue of semantic information ambiguity among span boundaries， a multi-objective learning NER model combined with boundary generation was proposed. The model was trained through a multi-objective learning approach jointly through combining NER task with boundary generation task. Among which， the boundary generation task was used as an auxiliary task to guide the model network to focus on boundary information of the spans， thus improving the performance of NER. Tests conducted on the ACE2004， ACE2005， and GENIA datasets show that the proposed model achieves F1 scores of 87.83%， 86.90%， and 81.65%， respectively. Experimental results fully validate the effectiveness of the model on different datasets and also further confirm its superior performance in named entity recognition tasks.

Facial features contain a lot of information and hold significant value in facial attribute and expression analysis tasks， but the diversity and complexity of facial features make facial analysis tasks difficult. Aiming at the above issue， a model of Facial Attribute estimation and Expression Recognition based on contextual channel attention mechanism （FAER） was proposed from the perspective of fine-grained facial features. Firstly， a local feature encoding backbone network based on ConvNext was constructed， and by utilizing the effectiveness of the backbone network in encoding local features， the differences among facial local features were represented adequately. Secondly， a Contextual Channel Attention （CC Attention） mechanism was introduced. By adjusting the weight information on feature channels dynamically and adaptively， both global and local features of deep features were represented， so as to address the limitations of the backbone network ability in encoding global features. Finally， different classification strategies were designed. For Facial Attribute Estimation （FAE） and Facial Expression Recognition （FER） tasks， different combinations of loss functions were employed to encourage the model to learn more fine-grained facial features. Experimental results show that the proposed model achieves an average accuracy of 91.87% on facial attribute dataset CelebA （CelebFaces Attributes）， surpassing the suboptimal model SwinFace （Swin transformer for Face） by 0.55 percentage points， and the proposed model achieves accuracies of 91.75% and 66.66% respectively on facial expression datasets RAF-DB and AffectNet， surpassing the suboptimal model TransFER （Transformers for Facial Expression Recognition） by 0.84 and 0.43 percentage points respectively.

To improve the accuracy of semantic segmentation for remote sensing images and address the loss problem of small-sized target information during feature extraction by Deep Convolutional Neural Network （DCNN）， a semantic segmentation method based on multi-scale feature fusion named FuseSwin was proposed. Firstly， an Attention Enhancement Module （AEM） was introduced in the Swin Transformer to highlight the target area and suppress background noise. Secondly， the Feature Pyramid Network （FPN） was used to fuse the detailed information and high-level semantic information of the multi-scale features to complement the features of the target. Finally， the Atrous Spatial Pyramid Pooling （ASPP） module was used to capture the contextual information of the target from the fused feature map and further improve the model segmentation accuracy. Experimental results demonstrate that the proposed method outperforms current mainstream segmentation methods.The mean Pixel Accuracy （mPA） and mean Intersection over Union （mIoU） of the proposed method on Potsdam remote sensing dataset are 2.34 and 3.23 percentage points higher than those of DeepLabV3 method， and 1.28 and 1.75 percentage points higher than those of SegFormer method. Additionally， the proposed method was applied to identify and segment oyster rafts in high-resolution remote sensing images of the Maowei Sea in Qinzhou， Guangxi， and achieved Pixel Accuracy （PA） and Intersection over Union （IoU） of 96.21% and 91.70%， respectively.

As a multi-task meta learning algorithm， Model Agnostic Meta Learning （MAML） can use different models and adapt quickly to different tasks， but it still needs to be improved in terms of training speed and accuracy. The principle of MAML was analyzed from the perspective of Gaussian stochastic process， and a new Model Agnostic Meta Learning algorithm based on Bayesian Weight function （BW-MAML） was proposed， in which the weight was assigned by Bayesian analysis. In the training process of BW-MAML， each sampling task was regarded as following a Gaussian distribution， and the importance of the task was determined according to the probability of the task in the distribution， and then the weight was assigned according to the importance， thus improving the utilization of information in each gradient descent. The small sample image learning experimental results on Omniglot and Mini-ImageNet datasets show that by adding Bayesian weight function， for training effect of BW-MAML after 2500 step with 6 tasks， the accuracy of BW-MAML is at most 1.9 percentage points higher than that of MAML， and the final accuracy is 0.907 percentage points higher than that of MAML on Mini-ImageNet averagely； the accuracy of BW-MAML on Omniglot is also improved by up to 0.199 percentage points averagely.

To improve the capacity and invisibility of image steganography, the article analyzed the advantage and application fields between Nonsubsampled Contourlet Transform (NSCT) and Contourlet transform. Afterwards, an image steganography was put forward, which was based on Human Visual System (HVS) and NSCT. Through modeling the human visual masking effect, different secret massages were inserted to different coefficient separately in the high-frequency subband of NSCT. The experimental results show that, in comparison with the steganography of wavelet, the proposed algorithm can improve the capacity of steganography at least 70000b，and Peak Signal-to-Noise Ratio (PSNR) increases about 4dB. Therefore, the invisibility and embedding capacity are both considered preferably, which has a better application outlook than the wavelet project.

This paper discussed the architecture of parallel Web crawler system. Incremental crawling method was used to the system to improve the efficiency of massive information updating. Meanwhile, considering the difference of crawler in the system and with the aim of fully usage of crawler in cluster system, Cosine vector parallel crawling model was introduced to solve this problem. After giving the definitions of crawling task vector and crawler vector, relevant parallel crawling algorithms were designed. The results confirm that the system is effective in distribution adaptability and runs well in maintaining the "freshness" of the Web repository.