Development of a Technological Solution for Automated Reintroducing of Mixed Lot Goods in the Trading Process

Today, the amount of orders made via internet shops is increasing continuously. From books, over clothes, up to technology and media, each consumer group can be served. Major enterprises such as Amazon, Zalando SE, etc. are offering their customers the possibility to receive a perfect shopping experience. Whereas during a personal shopping experience, the customer can inspect their products directly in the store, this is not possible when ordering via online marketplaces. Products, which are not sufficient to the customers attitude, like and taste, are returned to the seller. Not all of the returned goods can be sold again, as some are damaged or the value for reselling is too low. These products are packed on pallets and sold blind as mixed lot goods. Reintroducing these goods is currently still done manually. This paper is focusing on the development of a technological solution to reintroduce these mixed lot goods into the economic traffic in an automated way. To fulfill this task, a technological model has been developed. This model is using text processing aspects as well as Artificial Intelligence based algorithms such as Deep Learning and Big Data aspects, combined with simple digital workflows to reintroduce and digitalize the goods part by part. Applying the planned algorithms, the concept model is using a scanner device (e.g. a smartphone camera). Pictures of the products of the mixed lot goods, will be analyzed with neural networks and compared with similar goods in the internet, by using automated robots.


  • English

Media Info

  • Media Type: Web
  • Features: References;
  • Pagination: pp 32-44
  • Monograph Title: Reliability and Statistics in Transportation and Communication: Selected Papers from the 20th International Conference on Reliability and Statistics in Transportation and Communication, RelStat2020, 14-17 October 2020, Riga, Latvia
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 01878795
  • Record Type: Publication
  • ISBN: 9783030684754
  • Files: TRIS
  • Created Date: Apr 10 2023 11:45AM