US 12,326,901 B2
Method, device, and computer program product for processing workflow chart
Zijia Wang, Weifang (CN); Zhisong Liu, Shenzhen (CN); and Zhen Jia, Shanghai (CN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Nov. 7, 2023, as Appl. No. 18/503,829.
Claims priority of application No. 202311329547.1 (CN), filed on Oct. 13, 2023.
Prior Publication US 2025/0124082 A1, Apr. 17, 2025
Int. Cl. G06F 17/30 (2006.01); G06F 16/901 (2019.01); G06F 40/20 (2020.01)
CPC G06F 16/9024 (2019.01) [G06F 40/20 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method for processing a workflow chart, comprising:
encoding structural information of the workflow chart comprising a plurality of nodes and a plurality of edges by using a graph neural network to acquire a vector representation of the structural information;
acquiring textual description data about the workflow chart at the nodes;
training a language model based on the acquired textual description data and the acquired vector representation to acquire a pretrained language model, wherein the pretrained language model represents a trained language model prior to fine-tuning in one or more additional training operations to generate a fine-tuned language model; and
fine-tuning the pretrained language model through training data of a specific task to acquire the fine-tuned language model.