多源自媒体资源知识组织模型构建研究

Research on the Construction of Knowledge Organization Model for Multi source Self Media Resources

[目的/意义]多源自媒体资源已成为获取信息的重要途径,其多源异构特性使有效知识组织面临挑战。鉴于当前缺乏统一的媒体资源元数据标准,本研究通过文本化、知识元抽取和语义关联等技术路径,旨在构建和实现针对多源自媒体资源的知识组织模型。[方法/过程]研究首先复用和自定义DC元数据,构建多源自媒体资源的元数据描述框架,并据此构建多源自媒体资源本体和语义网络。借助计算机算法实现多源自媒体资源的文本构建标准化,使知识组织研究可以深入到多源自媒体资源的具体内容中。此外,还实现了多源自媒体资源的命名实体、关键词和知识摘要的抽取,并设计了语义关联实验,以上研究都以B站、抖音、知乎等平台数据为基础。[结果/结论]通过算法在多源自媒体资源和给定虚拟馆藏资源进行关联,达成了虚拟馆藏资源到多源自媒体资源的语义关联映射,旨在发掘多源自媒体资源的多元价值,为图书馆的知识服务提供新思路。

[Purpose/Significance]Self-media resources have become an important means of accessing information.Their multi-source and heterogeneous characteristics pose a challenge to effective knowledge organization..This study aims to construct and implement a knowledge organization model for multi-source media resources.The technical paths of textualization,knowledge meta-extraction,and semantic association will be used to achieve this goal.The lack of a unified metadata standard for media resources is the motivation behind this study.[Methodology/Process]The study began by repurposing and adapting DC metadata to create a metadata description framework for self-produced media resources.It then developed a multi-origin media resource ontology and semantic network.Computer algorithms were used to standardize the text structure of multi-origin media resources,allowing for knowledge organization research to delve into the specific content of self-produced media resources.Furthermore,named entities,keywords,and knowledge summaries from self-media resources were extracted.We also conducted semantic association experiments based on data from platforms such as Bilibili,Tiktok and Zhihu.[Results/Conclusions]The algorithmic association between self-media resources and virtual collection resources enables a semantic mapping,which aims to explore the multifaceted value of self-media resources and provide new ideas for knowledge services in libraries.