In artificial breeding of forest musk deer (Moschus berezovskii), common diseases such as abscess, enteritis, pneumonia, and parasitic infections exhibit persistently high morbidity rates. The early symptoms of certain diseases are often insidious and difficult to discern. Conventional manual inspection routines not only fail to achieve accurate diagnosis but also frequently disturb the animals, induce stress responses, and consequently delay optimal treatment windows. To address this practical challenge, this study employs an improved BRW-GPLinker joint entity-relationship extraction approach to perform integrated extraction and structural organization of disease entities, symptom manifestations, etiological associations, and preventive and therapeutic measures from farming literature and clinical records, thereby constructing a disease knowledge graph for forest musk deer. Through the introduction of a Boundary-Aware Module for refined entity boundary detection, a Relative Distance Bias Module to mitigate pairing errors in dense contexts, and a Weighted Sparse Multi-label Cross-Entropy loss function to enhance recall for infrequent relations, the proposed model achieves an F1 score of 0.887 on a self-constructed dataset and demonstrates favorable generalization capability on medical-domain datasets. By transforming fragmented clinical logs and manuals into structured medical associations, this knowledge graph facilitates rapid retrieval of forest musk deer disease information, thereby enhancing veterinary decision-making efficiency and assisting forest musk deer health management.

Non-contact behavioral monitoring is essential for the low-disturbance husbandry of captive forest musk deer, yet environmental factors such as variable illumination, shadows, and occlusion often hinder automatic recognition accuracy. To address these challenges, this study develops and evaluates a lightweight real-time detector, called HGS-YOLO26n, for behavior recording under practical captive breeding conditions. The model, which integrates visibility adaptation and geometric localization optimiza-tion, is trained on 6,760 field images from 30 enclosures. Results indicate that HGS-YOLO26n achieves an mAP50-95 of 0.8409, outperforming the baseline YO-LO26n by 3.74% while maintaining high efficiency with 2.84M parameters and an in-ference speed of 176.8 frames per second. Validation on continuous video segments demonstrate that the behavioral metrics of the system aligned closely with blinded manual assessments, yielding a consistency score of 96.0 compared to 89.9 for the baseline model. Consequently, this technology effectively converts ordinary surveil-lance footage into quantitative behavioral datasets. These experiments suggest that the proposed HGS-YOLO26n offers a robust, simple and efficient solution for wildlife daily management and welfare monitoring, facilitating standardized veterinary evaluation without imposing additional stress on captive forest musk deer.

The expansion of captive breeding of the forest musk deer (Moschus berezovskii)—a first-class protected species in China with significant economic and medicinal value—has led to escalating disease threats, underscoring the need for intelligent disease management based on knowledge graphs. However, the unstructured nature of veterinary texts, characterized by nested entities, ambiguous boundaries, and sparse relations, poses substantial challenges to accurate joint entity-relation extraction. To address these issues, this study proposes BRW-GPLinker, an enhanced joint extraction model built upon the GPLinker framework. This model integrates a Boundary-Aware Module (BAM) for precise entity boundary detection, a Relative Distance Bias Module (RDBM) to minimize pairing errors in dense contexts, and a Weighted Sparse Multi-label Cross-Entropy (WSMCE) loss function to improve recall for infrequent relations. Experimental results on the constructed MS-Data dataset demonstrate that BRW-GPLinker achieves an F1 score of 0.887, outperforming the baseline GPLinker by 2.0 percentage points. It also exhibits strong generalization, with an F1 score of 0.590 on the general-domain CMeIE-V2 dataset. These findings confirm that the proposed model provides reliable support for constructing disease knowledge graphs in forest musk deer farming.

Non-contact behavioral monitoring is important for low-disturbance husbandry of captive forest musk deer, but variable illumination, shadows, partial occlusion, and low target-background contrast can reduce recognition reliability. This study developed HGS-YOLO26n, a lightweight real-time detector for continuous behavior recording under practical captive breeding conditions. HVIEnhanceStem was used to preserve shallow visual cues under weak illumination and low contrast, AdaGFB adapted feature extraction to posture-related shifts in local discriminative regions, and SDIoU improved bounding-box localization under occlusion and target-scale variation. The model was trained and evaluated using 6760 field images collected from 30 enclosures. HGS-YOLO26n achieved an mAP50–95 of 0.8409, exceeding the YOLO26n baseline by 3.74 percentage points, with 2.84 M parameters and an inference speed of 176.8 frames per second. Validation on continuous videos showed that its behavior-duration and event-count estimates were closer overall to blinded manual observations than those of the comparison models. By converting routine surveillance footage into longitudinal, individual-level records of behavior duration, event frequency, and temporal distribution, the system enables efficient review of behavioral activity across extended monitoring periods. Husbandry and veterinary staff can use these records to compare behavioral patterns across observation periods and return to corresponding video segments when specific changes require verification. This provides a low-disturbance source of quantitative behavioral information for routine husbandry, longitudinal observation, and conservation breeding of captive forest musk deer.