Sap Se

Konrad Schenk

Johannes Hoehne

Ying Jiang

Olga Cherepanova

Janet Dorothy Salmon

Steffen Vollmert

Luca Toldo

Luisa Karl

Ralf Ille

Tunahan Atilgan

Thomas Zuerker

Martin Hoecker

Bettina Lieske

The disclosure generally describes methods, software, and systems for estimating cost allocations, including a method for the following steps. Using a machine learning system, transactions are consolidated into estimated sender-receiver totals for costs transmitted by senders to receivers in an organization. A sender-receiver percentage matrix is determined from the estimated sender-receiver totals of a given sender and for each receiver of the transactions from the given sender. The sender-receiver percentage matrix includes, for each sender, estimated sender-receiver percentages. Current actual costs are determined for each sender to receivers for a given time period. Estimated cost allocations are determined for given time period using the sender-receiver percentage matrix. The estimated cost allocations are determined for each receiver in the organization based on a function of the current actual costs for each sender. A report that includes the estimated cost allocations is provided for presentation to a user.

Cost allocation estimation using direct cost vectors and machine learning

In some embodiments, there is provided a system. The system may include at least one data processor and at least one memory storing instructions which, when executed by the at least one data processor, cause the apparatus to at least: determine, for a received document including at least one item, that the received document likely includes at least one missing item, the determination based on at least a machine learning model and the at least one item; and provide an indication of the at least one missing item. Related systems and articles of manufacture are also provided.

Predicting missing items

Disclosed herein are various embodiments for an augmented reality interaction, modeling, and annotation system. An embodiment operates by receiving an image including unknown data in an unknown format, including pixels. Each of the pixels is classified as one of a background pixel, a key pixel, or a value pixel representing the unknown data. For a plurality of the pixels classified as key pixels or value pixels, a plurality of locational data values associated with the unknown format are generated. Based on the locational data values, a key image and a corresponding value image from the received image are identified. The key image and the corresponding value image are output.

Form processing and analysis system

Growing community of inventors

Potsdam, Germany

Konrad Schenk