The paper introduces a novel continuous semantic occupancy mapping algorithm called Sharp-Edged and Efficient Continuous Semantic Occupancy Mapping (SEE-CSOM) for mobile robots. The main challenges addressed by SEE-CSOM are overinflation and computational inefficiency in existing continuous semantic occupancy mapping methods. To mitigate overinflation, the Redundant Voxel Filter Model (RVFM) is proposed, which uses context entropy to filter out redundant voxels, ensuring accurate and sharp-edged object boundaries. The Adaptive Kernel Length Model (AKLM) is introduced to adjust the kernel length adaptively based on class entropy, reducing the computational complexity. The multientropy kernel inference function integrates RVFM and AKLM to generate a continuous semantic occupancy map. The algorithm is validated on indoor and outdoor datasets and a real robot platform, demonstrating significant improvements in accuracy and efficiency compared to existing methods. The results show that SEE-CSOM effectively balances the trade-off between map accuracy and efficiency, making it suitable for autonomous robotics applications.The paper introduces a novel continuous semantic occupancy mapping algorithm called Sharp-Edged and Efficient Continuous Semantic Occupancy Mapping (SEE-CSOM) for mobile robots. The main challenges addressed by SEE-CSOM are overinflation and computational inefficiency in existing continuous semantic occupancy mapping methods. To mitigate overinflation, the Redundant Voxel Filter Model (RVFM) is proposed, which uses context entropy to filter out redundant voxels, ensuring accurate and sharp-edged object boundaries. The Adaptive Kernel Length Model (AKLM) is introduced to adjust the kernel length adaptively based on class entropy, reducing the computational complexity. The multientropy kernel inference function integrates RVFM and AKLM to generate a continuous semantic occupancy map. The algorithm is validated on indoor and outdoor datasets and a real robot platform, demonstrating significant improvements in accuracy and efficiency compared to existing methods. The results show that SEE-CSOM effectively balances the trade-off between map accuracy and efficiency, making it suitable for autonomous robotics applications.