US 12,332,942 B2
Knowledge insight capturing system
Frank Bienewald, Ludwigshafen (DE); and Henning Schwabe, Ludwigshafen (DE)
Assigned to BASF SE, Ludwigshafen (DE)
Filed by BASF SE, Ludwigshafen (DE)
Filed on Mar. 8, 2024, as Appl. No. 18/599,962.
Application 18/599,962 is a continuation of application No. 17/483,366, filed on Sep. 23, 2021, granted, now 11,954,153.
Claims priority of application No. 20198048 (EP), filed on Sep. 24, 2020.
Prior Publication US 2024/0211517 A1, Jun. 27, 2024
Int. Cl. G06F 16/903 (2019.01); G06F 16/93 (2019.01)
CPC G06F 16/90344 (2019.01) [G06F 16/93 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for storage of digital information data via at least one processing unit operatively coupled to at least one database, the method comprising:
providing, at the processing unit, at least one portion of the digital information data;
performing, via the processing unit, at least one syntactic and/or semantic search in the at least one database based upon the portion of the digital information data;
providing, via the processing unit, one or more meta-data strings in response to the at least one syntactic and/or semantic search;
receiving, at the processing unit, at least one relevant meta-data string, wherein the at least one relevant meta-data string is selected from the one or more meta-data strings; and
storing, in any of the at least one database, the portion of digital information data and the at least one relevant meta-data string,
wherein the at least one relevant meta-data string is usable for a future syntactic and/or semantic search, and
wherein the provided portion of digital information is evaluated using semantic information extraction and linked automatically to found concepts, wherein the selection of the relevant meta-data string comprises at least one named entity recognition, wherein for selecting the at least one relevant meta-data string, the processing unit computes word and/or documents embeddings for named entities of the documents.