US 12,354,026 B2
Utilizing large language model responses to train an inference pattern engine
Shuhao Zhang, Cupertino, CA (US); Qi Zhai, Hillsborough, CA (US); Pavlo Dudka, Mountain View, CA (US); Mark Yi Chien Peng, Belmont, CA (US); and FNU Taha Junaid, Mountain View, CA (US)
Assigned to Tiny Fish Inc., Cupertino, CA (US)
Filed by Tiny Fish Inc., Cupertino, CA (US)
Filed on Jul. 30, 2024, as Appl. No. 18/789,437.
Application 18/789,437 is a continuation in part of application No. 18/415,431, filed on Jan. 17, 2024, granted, now 12,174,906.
Claims priority of provisional application 63/534,541, filed on Aug. 24, 2023.
Prior Publication US 2025/0068942 A1, Feb. 27, 2025
Int. Cl. G06F 16/00 (2019.01); G06N 5/04 (2023.01)
CPC G06N 5/04 (2013.01) 21 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor configured to:
generate a plurality of prompts based on a plurality of inputs and processed content associated with a tree data structure;
provide the plurality of prompts to a large language model;
based on a response received from the large language model that maps one or more variables associated with the input to one or more elements associated with the processed content associated with the tree data structure received from the large language model, derive corresponding patterns mapping the one or more variables associated with the plurality of inputs to the one or more elements associated with the processed content associated with the tree data structure;
store the derived pattern mappings and a corresponding correctness associated with the derived pattern mappings based on the large language model response;
receive a subsequent input and subsequent processed content associated with the tree data structure;
determine that a correctness associated with a stored derived pattern mapping from the derived pattern mappings is greater than a confidence threshold; and
utilize the stored derived pattern mapping to generate a response for the subsequent input; and
a memory coupled to the processor and configured to provide the processor with one or more instructions.