US 12,475,112 B2
Generating hierarchical queries from natural language
Yeuk-Yin Chan, San Jose, CA (US); Victor S. Bursztyn, Mountain View, CA (US); Eunyee Koh, Sunnyvale, CA (US); Nathan Ross, Highland, UT (US); and Vasanthi Holtcamp, Fremont, CA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Oct. 13, 2023, as Appl. No. 18/486,603.
Prior Publication US 2025/0124023 A1, Apr. 17, 2025
Int. Cl. G06F 16/20 (2019.01); G06F 16/242 (2019.01)
CPC G06F 16/243 (2019.01) [G06F 16/2423 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by a computing device including at least one processor, the method comprising:
encoding, using a text encoder, a text query to obtain a text embedding, wherein the text query comprises a natural language text query;
selecting, using a key phrase mapping component, a field of a data schema by comparing the text embedding to a field embedding corresponding to the field, wherein the data schema comprises one or more hierarchical rules constraining the use of the field for querying data based on a hierarchy of attributes; and
generating, using a query composer, a hierarchical query including a value corresponding to the selected field by predicting a next word in a sequence of words based on a positional encoding for the next word, wherein the hierarchical query comprises a hierarchy of nested descriptors corresponding to the hierarchy of attributes in a database.