Precise segmentation of colon polyps in gastrointestinal endoscopy images holds significant clinical value. However， the traditional segmentation methods often struggle with capturing enough fine details and rely on large-scale data heavily， leading to poor performance when addressing complex polyp morphologies. Although Segment Anything Model （SAM） has notable progress in natural image segmentation， the ideal effect in polyp segmentation task cannot be achieved by SAM methods due to domain differences between natural and medical images. To address this issue， a lightweight fine-tuning method based on SAM architecture was proposed， named Segment Anything Model for Colon Polyps （SAMCP）. In this method， a streamlined adapter module focusing on channel-dimension information was introduced， a joint loss function was simplified using Dice and Intersection over Union （IoU）， and parameters of the original image encoder and prompt encoder were frozen during training to enhance polyp segmentation performance with low training cost. Experimental results on three public datasets comparing SAMCP with nine advanced methods demonstrate that SAMCP outperforms other SAM methods. Specifically， SAMCP improves the Dice and IoU values by 56.7% and 84.5%， respectively， on the Kvasir-SEG dataset， by 46.0% and 86.0%， respectively， on the CVC-ClinicDB， and by 95.3% and 122.2%， respectively， on the CVC-ColonDB dataset， surpassing the current best performance of SAM-based methods. With the introduction of point-based prompts， even with a single click， SAMCP can also outperform other SAM-based methods. The above validates that SAMCP performs well in handling complex shapes and local details， providing physicians with more precise segmentation guidance.

Crack segmentation is an important prerequisite for evaluating the damage degree of pavement diseases. In order to balance the effectiveness and real-time of deep neural network segmentation， a lightweight asphalt pavement crack segmentation neural network based on U?Net encoder-decoder structure was proposed， namely PIPNet （Parallel dilated convolution of Inverted Pyramid Network）. The encoding part was an inverted pyramid structure. Multi-branch parallel dilated convolution module with different dilatation rates was proposed to extract multi-scale information from the top， middle and bottom features and reduce model complexity， which combined deep separable convolutions with ordinary convolutions and gradually reduced the number of parallel convolutions. Drawing on the characteristics of GhostNet， an inverse residual lightweight module was designed， which was embedded with parallel dual pooling attention. Test results on GAPs384 dataset show that， compared with ResNet50 encoding method， PIPNet has mIoU （mean Intersection over Union） 1.10 percentage points higher with only about one-sixth of parameter quantity and MFLOPs （Million FLOating Point operations）， and its mIoU is 4.14 and 9.95 percentage points higher than those of lightweight GhostNet and SegNet， respectively. Experimental results show that PIPNet has high crack segmentation performance while reducing the model complexity， and has good adaptability to segmentation of different pavement crack images.

With the continuous development of knowledge graph technology， knowledge information management driven by knowledge graph has been widely applied in multiple domains， so the efficiency of distributed Simple Protocol and Resource description framework Query Language （SPARQL） query for knowledge graph is particularly important. Firstly， a detailed investigation on the existing Spark-based and Random Access Memory （RAM）-based distributed RDF systems was conducted. Secondly， query performance evaluation of eight representative systems selected from the above systems was performed， thereby comparing query performance differences between Spark-based and RAM-based systems with different query types， query diameters and datasets. Thirdly， the query performance of Spark-based and RAM-based systems was evaluated by analyzing the experimental results comprehensively. Finally， the future research directions of distributed SPARQL query optimization which oriented vertical application domain were pointed out aiming at problems of the existing distributed SPARQL query， such as poor query scalability， high query join complexity and long query compilation time.

Because laplace watershed segmentation on image edge is not very effective. Based on the energy regional concentration theory, the authors defined a function to measure area differences. When the difference between two regions is greater than any one of them, this is a border lie between the two regions; otherwise they belong to the same region, they should merge into one. Through the experiment under vs2008, the authors split butterfly specimens into four parts, marked different regions by using different colors. Experiment demonstrates the method has good effect, and also less time-consuming.