Toward storytelling from personal informative lifelogging

• Published in: Multimedia tools and applications 2021-05, Vol.80 (13), p.19649-19673
• Main Authors: Liu, Guoqi, Rehman, Mujeeb Ur, Wu, Yuhou
• Format: Article
• Language: English
• Subjects: Algorithms; Computer Communication Networks; Computer Science; Data collection; Data Structures and Information Theory; Datasets; Multimedia; Multimedia Information Systems; Natural language; Special Purpose and Application-Based Systems; Unstructured data
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-020-10453-z

The authors began collecting personal informative lifelogging data in 2011. The data collected in this article is a discontinuous data set, each of which includes one or more images, a GPS message, a description of a location, and a description of the text, we call this informative lifelogging. However, for the purposes automatically building a story from a huge collection of unstructured egocentric data presents major challenges. This paper first introduces the structure and characteristics of the collected data and uses the DB-scan algorithm to classify the data. Then a model for generating a story is proposed, and a model of story generation based on a story template is proposed in the model. The author implemented a complete software system through code, described a story generation model, and gave the key algorithm to generate stories. Through this system, 418 stories were generated automatically, of which 62% of the stories were particularly accurate. The experimental results verify that it is feasible to automatically generate stories based on personal Informative lifelogging data.