Objective To provide precise,effective,and intuitive nutritional and dietary recommendations for different population groups,a multi-modal nutritional knowledge graph was constructed,which includes entities such as food,nutrition,population,and diseases.Methods Data sets in the field of nutrition were obtained using web crawling and other technical means.The OneRel model was referenced to complete the joint extraction of Chinese entity relationships and construct a text library.The RoBERTa-ResNet model were used to learn the features of text and image data separately,to align images with text,and to construct a multi-modal knowledge graph.Results The F1 value of the joint entity relationship extraction model was 0.703.The constructed multi-modal knowledge graph contains 3312 textual entities,11 259 relationships,and 1000 image entities.Conclusion The algorithms used in this study to construct the multi-modal nutritional knowledge graph achieve good results.This knowledge graph not only systematically integrates multi-modal knowledge in the field of nutrition and enables good visual query capabilities,but also serves as the underlying support for downstream tasks such as intelligent question answering and nutritional recommendation systems.

Parkinson's disease（PD） is the second most common neurodegenerative disease in the world， which seriously affects the lives of patients. With the acceleration of aging process， the number of patients continues to rise. Its main pathological features are aggregation of α-synuclein and degenerative death of dopaminergic neurons in the substantia nigra. However， the pathogenesis of PD is still unclear. According to reports， the brain-derived neurotrophic factor（BDNF）/tyrosine kinase receptor B（TrkB） signaling pathway is highly expressed and activated in dopaminergic neurons in the substantia nigra， which is closely related to neurophysiological processes such as neurogenesis， synaptic plasticity， neuroinflammation， and oxidative stress. It plays an important role in the occurrence and development of PD. At present， the treatment methods of Western medicine for PD are mainly based on drugs such as levodopa and dopamine agonists to alleviate motor symptoms， but with the increase of dose， the adverse reactions are significantly enhanced. Traditional Chinese medicine（TCM） has attracted people to explore its therapeutic effects on PD due to its characteristics of homology of medicine and food， economy， minor adverse reactions and multi-target action. Therefore， this paper systematically reviews the role of BNDF/TrkB pathway in the pathogenesis of PD and the mechanism of TCM formulas， extracts and monomers in the treatment of PD by regulating the BNDF/TrkB pathway according to retrieving the latest research reports at home and abroad， so as to provide a reference for the clinical application of related TCM and the development of new drugs for PD.

Objective To provide precise,effective,and intuitive nutritional and dietary recommendations for different population groups,a multi-modal nutritional knowledge graph was constructed,which includes entities such as food,nutrition,population,and diseases.Methods Data sets in the field of nutrition were obtained using web crawling and other technical means.The OneRel model was referenced to complete the joint extraction of Chinese entity relationships and construct a text library.The RoBERTa-ResNet model were used to learn the features of text and image data separately,to align images with text,and to construct a multi-modal knowledge graph.Results The F1 value of the joint entity relationship extraction model was 0.703.The constructed multi-modal knowledge graph contains 3312 textual entities,11 259 relationships,and 1000 image entities.Conclusion The algorithms used in this study to construct the multi-modal nutritional knowledge graph achieve good results.This knowledge graph not only systematically integrates multi-modal knowledge in the field of nutrition and enables good visual query capabilities,but also serves as the underlying support for downstream tasks such as intelligent question answering and nutritional recommendation systems.