International Business Machines Corporation

Yin Xi Guo

Su Liu

Ming Lei Zhang

Dong Chen

Cheng Xu

Ting Ting Zhan

Kuo-Liang Chou

Shun Xian Wu

Yuan Jie Zhang

A computer-implemented method, according to one embodiment, includes: receiving copies of notes that were originally recorded by participants, the notes corresponding to a source document. Note fragments in the received copies of notes are identified and one or more machine learning models are used to compare the identified note fragments to pages and paragraphs in the source document that the respective note fragments are located in. Based at least in part on the comparison, the identified note fragments are merged with a copy of the source document to form a pseudo-source document. Furthermore, the pseudo-source document is output.

Merging supplemental information with the content of source material

A computer-implemented method for fording depth estimation based on a real-time image recognition is provided according an embodiment of the present disclosure. In the method, a first image of a low-lying road being submerged under a bridge can be acquired. At least one second image of the low-lying road without being submerged can be determined. A fording depth of the low-lying road can be estimated based on the first image and the at least one second image.

Fording depth estimation

Growing community of inventors

Beijing, China

Yin Xi Guo