Non-contact monitoring in precision livestock farming (PLF) needs reliable individual identification and face-anchored analytics to link animals with longitudinal health and behavior signals in variable barns. Evidence is fragmented across pipeline modules and deployment readiness is difficult to assess because robustness and operational KPIs are inconsistently reported. We map research evolution and synthesize deployment-oriented evidence and design principles. A two-stage review was conducted: CiteSpace bibliometric mapping of Web of Science Core Collection records (2005–2025; pre-2005 relevant records were sporadic), followed by a scoping synthesis of peer-reviewed empirical studies (2022–2025) searched mainly in ScienceDirect and supplemented by Web of Science, Scopus, IEEE Xplore, and CNKI. We included studies using livestock facial imagery (RGB and/or thermal/IR) for identity functions or face-coupled ROI analytics with quantitative cohort evaluation. Following QRD screening, 24 studies were retained. We consolidate deployment factors and reporting gaps and propose “Digital Individuals” as persistent identity anchors for multimodal longitudinal records and closed-loop decision support.

Unstructured Chinese medical texts are rich sources of entity and relational information. The extraction of entity relationships from medical texts is pivotal for the construction of medical knowledge graphs and aiding healthcare professionals in making swift and informed decisions. However, the extraction of entity relationships from these texts presents a formidable challenge, notably due to the issue of overlapping entity relationships. This study introduces a novel extraction model that leverages RoFormer’s rotational position encoding (RoPE) technique for an efficient implementation of relative position encoding. This approach not only optimizes positional information utilization but also captures syntactic dependency information by constructing a weighted adjacency matrix. During the feature fusion phase, the model employs an entity attention mechanism for a deeper integration of features, effectively addressing the challenge of overlapping entity relationships. Experimental outcomes demonstrate that our model achieves an F1 score of 83.42 on datasets featuring overlapping entity relations, significantly outperforming other baseline models.

Unmanned swarm systems must achieve real-time, secure, and intelligent coordination to respond to dynamic environments and realize emergent swarm-scale capabilities. Current research predominantly focuses on static coordination tasks such as formation control, path planning, and task allocation, where task models are predefined to improve execution accuracy. Researchers have paid comparatively little attention to security requirements for adapting to environmental changes and resisting attacks. This survey categorizes collaborative security mechanisms into three dimensions: (1) fault tolerance, ensuring system resilience against communication or node failures; (2) consistency, maintaining unified perception, decisions, and actions across the swarm; and (3) attack resistance, defending against intrusion, spoofing, and data leakage. We review the state of the art across architecture security, network communication security, collaborative perception security, task security, and data privacy security, and identify open challenges and future directions. A capability-layer mapping matrix systematically reveals coverage patterns and research gaps across these dimensions.