US 11,782,961 B2
Device, system and method for providing descriptions to communication devices using machine learning generated templates
Christophe Blaya, La Roquette sur Siagne (FR); Xavier Callens, Cagnes sur Mer (FR); Ilias Driouich, Nice (FR); Bernard Jean Marie Rannou, Le Cannet (FR); Yazid Goghrod, Nice (FR); Ranganath Vaikuntham, Nice (FR); and Benoit Lacoue, Peymeinade (FR)
Assigned to AMADEUS S.A.S., Biot (FR)
Filed by AMADEUS S.A.S., Biot (FR)
Filed on Apr. 16, 2021, as Appl. No. 17/232,714.
Prior Publication US 2022/0335072 A1, Oct. 20, 2022
Int. Cl. G06F 16/332 (2019.01); G06N 20/00 (2019.01); G06F 16/335 (2019.01); G06F 40/205 (2020.01); G06F 40/51 (2020.01); G06F 18/214 (2023.01); G06F 18/2113 (2023.01)
CPC G06F 16/3326 (2019.01) [G06F 16/335 (2019.01); G06F 16/3329 (2019.01); G06F 18/214 (2023.01); G06F 18/2113 (2023.01); G06F 40/205 (2020.01); G06F 40/51 (2020.01); G06N 20/00 (2019.01)] 16 Claims
OG exemplary drawing
 
1. A method comprising:
replacing, by a computing device, given word types in provided text files with corresponding tags to generate corresponding intermediate templates, the provided text files associated with a given topic, the corresponding tags of the corresponding intermediate templates respective tag names that identify respective given word types that were replaced in the provided text files;
generating for the given topic, by the computing device, one or more textual templates that include at least a portion of the corresponding tags, including the respective tag names that identify the respective given word types that were replaced in the provided text files, the one or more textual templates in natural language sentences, the generating of the one or more textual templates at least partially based on the corresponding intermediate templates, wherein the corresponding intermediate templates are generated using at least a first machine learning algorithm, and the corresponding intermediate templates are used to train at least a second machine learning algorithm to generate the one or more textual templates;
replacing, by the computing device, respective tags of the corresponding tags in a textual template, of the one or more textual templates, with corresponding words of a given data file associated with the given topic that correspond to the given word types identified by the respective tag names, to generate a respective description of a given item associated with the given topic, the given data file being specific to the given item;
providing, by the computing device and a communication interface, the respective description to a communication device; and
prior to providing the respective description to the communication device, translating the respective description from a first language into a second language selected based on one or more of: a location of the communication device; and an indication of the second language as received from the communication device.