US 12,236,194 B2
Wireframe generation
Zhaoqi Wu, Shanghai (CN); Yi Fang Chen, DaLian (CN); Zhi Wang, Shanghai (CN); Yi Qun Zhang, Shanghai (CN); Yan Du, Beijing (CN); and Li Na Yuan, Beijing (CN)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Oct. 20, 2022, as Appl. No. 18/048,064.
Prior Publication US 2024/0135102 A1, Apr. 25, 2024
Prior Publication US 2024/0232533 A9, Jul. 11, 2024
Int. Cl. G06F 40/295 (2020.01); G06F 40/216 (2020.01); G06N 3/08 (2023.01)
CPC G06F 40/295 (2020.01) [G06F 40/216 (2020.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for wireframe generation, comprising:
performing, by one or more processing units, a named entity recognition on text information related to requirements for a wireframe by a first artificial intelligence (AI) model, to extract a set of entities and relationships between each of the entities of the set of entities from the text information; and
inputting, by the one or more processing units, the set of entities and relationships between each of the entities of the set of entities to a second AI model to generate the wireframe, wherein the second AI model is trained so that a difference between resultant relations of the set of entities of the generated wireframe and the relationships between each of the entities of the set of entities from the first AI model is decreased.