Do you have valuable data hidden in unstructured files such as material specifications in paper or PDF documents, making it inaccessible in your ERP system? Many organizations face the same challenge, preventing them from efficiently enriching and cleansing data as well as creating new datasets in their ERP systems. A major challenge here is the accurate mapping of documents to ERP data, such as supplier or material data, which comes along with tedious manual work that is highly time and resource-consuming. As a result, valuable resources are wasted to utilize this data. The Data Quality Navigator Reader solves this problem by automatically extracting data from unstructured documents, comparing it with data in the ERP system, and suggesting the correct values to maintain in the ERP system. It also provides a guided workflow to seamlessly integrate trusted data into an ERP system.
Documents can be uploaded or stored in pre-defined folders. Also archives can be accessed by the DQN. The DQN will match the documents against business information system records (e.g. business partner or materials) or alert if no match is found. The DQN front-end provides an overview report of the data collection status.
Data inconsistencies or missing information are identified by the DQN. Workflow management reports display these inconsistencies, and proper values are automatically suggested. Users can modify or accept suggestions in the DQN front-end.
During upload, the data is parsed and structured by AI. The DQN Reader maps the data to the required business information system format.