This study presents a knowledge graph construction scheme leveraging large language models (LLMs) for task-oriented semantic communication systems. The proposed methodology systematically addresses four critical stages: corpus collection, entity extraction and relationship analysis, knowledge base generation, and dynamic updating mechanisms. It is worth noting that prompt engineering is combined with few-shot learning to enhance reliability and accuracy in this methodology. Experimental demonstration showed that this methodology had superior entity extraction performance, achieving 89.7% precision and 92.3% recall rate. This scheme overcomes the demand for domain knowledge and the labor cost of traditional knowledge base construction schemes. It greatly improves the construction efficiency of knowledge graphs. This paper provides an efficient and reliable task knowledge base construction scheme for task-oriented semantic communication, which is expected to promote its wider application.

With the development of artificial intelligence and computer hardware, semantic communication has been attracting great interest. As an emerging communication paradigm, semantic communication can reduce the requirement for channel bandwidth by extracting semantic information. This is an effective method that can be applied to image acquisition of unmanned aerial vehicles, which can transmit high-data-volume images within the constraints of limited available bandwidth. However, the existing semantic communication schemes fail to adequately incorporate the guidance of task requirements into the semantic communication process and are difficult to adapt to the dynamic changes of tasks. A task-oriented image semantic communication scheme driven by knowledge base is proposed, aiming at achieving high compression ratio and high quality image reconstruction, and effectively solving the bandwidth limitation. This scheme segments the input image into several semantic information unit under the guidance of task requirements by Yolo-World and Segment Anything Model. The assigned bandwidth for each unit is according to the task relevance scores, which enables high-quality transmission of task-related information with lower communication overheads. An improved metric weighted learned perceptual image patch similarity (LPIPS) is proposed to evaluate the transmission accuracy of the novel scheme. Experimental results show that our scheme achieves a notable performance improvement on weighted LPIPS while the same compression ratio compared with traditional image compression schemes. Our scheme has a higher target capture ratio than traditional image compression schemes under the task of target detection.

As an emerging communication paradigm, semantic communications (SC) focuses on the semantic content of information transmission, aiming to achieve more efficient and accurate information interaction. However, SC requires an in-depth analysis of information semantics and accurate adaptation to application scenarios. With the substantial growth in information volume, richness, and application diversity, the resources, constraints, and requirements associated with SC systems have also increased. Optimal resource allocation (ORA) of SC can effectively deal with these practical problems, a key technology for improving communication efficiency. In complex network environments and special scenarios, communication resources are limited. Increasing transmission efficiency, ensuring accuracy and quality of information, and reducing energy consumption can be achieved by rationally allocating bandwidth, power, and related resources. Since SC technology is still in its early stages of development, there is a lack of a comprehensive review of ORA for SC in the existing literature. This paper provides a comprehensive review of ORA for SC. First, the basic concepts, characteristics and development motivations for SC and ORA are reviewed. Then, a comprehensive analysis of the key technologies for ORA in SC is presented, covering end-to-end and semantic network multi-link ORA. These technologies include technology for predicting resource demand based on semantic understanding, resource optimization technology for semantic information (SI) processing and transmission, and technology for dynamic resource adjustment. Then, a conceptual ORA framework is synthesized from the reviewed technologies to unify key design principles and provide a foundation for future research. In addition, this paper provides research prospects in future trends of ORA for SC, comprising emerging artificial intelligence (AI) and machine learning, laying the foundation for next-generation intelligent communication networks. Finally, this paper points out the main application direction of ORA in SC, which reflects the practical significance of this study.

In dealing with emergency events, it is very important when making scientific and correct decisions. As an important premise, the creation of information needs is quite essential. Taking earthquakes as a type of unexpected event, this paper constructs a large and model-driven system for automating the generating process of information requirements for earthquake response. This research explores how the different departments interact during an earthquake emergency response, how the information interacts with each other, and how the information requirement process operates. The system is designed from three points of view, building a knowledge base, designing and developing prompts, and designing the system structure. It talks about how computers automatically make info needs for sudden emergencies. During the experimental process, the backbone architectures used were four Large Language Models (LLMs): chatGLM (GLM-4.6), Spark (SparkX1.5), ERNIE Bot (4.5 Turbo), and DeepSeek (V3.2). According to the desired system process, information needs is generated by real-word cases and then they are compared to the gathered information needs by experts. In the comparison process, the “keyword weighted matching + text structure feature fusion” method was used to calculate the semantic similarity. Like true positives, false positives, and false negatives can be used to find differences and calculate metrics like precision and recal. And the F1-score is also computed. The experimental results show that all four LLMs achieved a precision and recall of over 90% in earthquake information extraction, with their F1-scores all exceeding 85%. This verifies the feasibility of the analytical method a chatGLM dopted in this research. Through comparative analysis, it was found that chatGLM exhibited the best performance, with an F1-score of 93.2%. Eventually, Python is used to script these aforementioned processes, which then create complete comparison charts for visual and test result checking. In the course of researching we also use Protege to create the knowledge requirements ontology, so it is easy for us to show and look at it. This research is particularly useful for emergency management departments, earthquake emergency response teams, and those working on intelligent emergency information systems or those focusing on the automated information requirement generation using technologies such as LLMs. It provides practical support for optimizing rapid decision-making in earthquake emergency response.