Recently, with the advancement of technologies such as virtual reality and the metaverse, remote 3D reconstruction has gained increasing attention. However, achieving fast and high-quality 3D reconstruction in complex communication environments remains a major challenge. To address this, we propose R-SVRSC, a semantic communication system for single-view 3D reconstruction based on 3D Gaussian Splatting (3D GS). Specifically, the transmitter extracts and transmits semantic information from a single image, instead of transmitting complex 3D data. At the receiver, a Semantic-to-Gaussian Mapper (SGM) directly maps the received deep semantic features into 3D Gaussians, which are then rapidly rendered using a Gaussian rasterizer. Furthermore, to combat the performance degradation caused by multipath fading and channel instability, we introduce a RIS-assisted enhancement to the proposed semantic communication system. A deep learning (DL)-based RIS phase shift prediction module is integrated into the transmitter and jointly trained with the entire system in an end-to-end manner, enabling intelligent reconstruction of the wireless channel. Experimental results show that the proposed system achieves efficient rendering and consistently high-quality 3D reconstruction under low signal-to-noise ratio (SNR) conditions across various real-world channel scenarios.

How to further improve clinical efficacy of acupuncture, extend its application range is a key issue in the research and promotion of acupuncture. Famous acupuncturists represent the highest academic level and treatment ability, and have an important influence on development of acupuncture and rehabilitation of patients. Therefore, how to accurately find the acupuncturist is a difficult problem for both patients and peer doctors. At the same time, Internet is also full of a large number of false information, how to accurately analyze the real acupuncturist from these information is the key issue. We can automatically acquire these tags by using information collection technology, and select acupuncture experts from them by combining artificial intelligence. However, tags of social network users is sparse, only a small number of users have tags, and the number of tags is limited. Most users only publish articles and pay attention to other interested users and blogs. They do not tag themselves. There are problems of no tags or less tags, which make it more difficult to find acupuncturists. For untagged users, we can consider predicting tags from their social relationships. In this paper, we design an intelligent tag prediction algorithms for acupuncture experts, which first predicts intimate users of users, and then predicts the users' tags through intimate users' tags. Firstly, possible close users are selected as candidates through cosine similarity. If the user doesn't have an object of interest, then replace it with his fans. Subsequently, user tags are predicted according to the tags of the target audience or fans. Finally, the effectiveness of ITPAE is verified by simulation experiments.