US 11,907,673 B1
Enhancing chatbot recognition of user intent through graph analysis
Hua Hao, Dalian (CN); Chen Bi, Dalian (CN); Tieyi Guo, Frisco, TX (US); Byung Chun, Kingston, MA (US); Wenbin Ren, Dalian (CN); Hao Fu, Dalian (CN); and Pengrui Sun, Dalian (CN)
Assigned to FMR, LLC, Boston, MA (US)
Filed by FMR LLC, Boston, MA (US)
Filed on Feb. 28, 2023, as Appl. No. 18/115,496.
Int. Cl. G06F 15/16 (2006.01); G06F 40/40 (2020.01); H04L 51/02 (2022.01); G06F 16/35 (2019.01)
CPC G06F 40/40 (2020.01) [G06F 16/35 (2019.01); H04L 51/02 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A computer system for enhancing chatbot recognition of user intent through graph analysis, the system comprising a computing device having a memory that stores computer-executable instructions and a processor that executes the computer-executable instructions to:
classify each of a plurality of user messages associated with a chat session between a user of a remote computing device and a chatbot application as either comprehensible user messages that are mapped to a user intent or incomprehensible utterances that are not mapped to a user intent;
arrange the comprehensible user messages into a first plurality of clusters and arrange the incomprehensible user messages into a second plurality of clusters;
generate a first sub-graph data structure for each cluster in the first plurality of clusters and generate a second sub-graph data structure for each cluster in the second plurality of clusters;
calculate a graph kernel matrix using the first sub-graph data structures and the second sub-graph data structures;
train a classification model using the graph kernel matrix, the trained classification model configured to predict an intent identifier for an input graph kernel matrix; and
execute the trained classification model using the graph kernel matrix as input to generate a predicted intent identifier for one or more of the incomprehensible user messages.