CPC G06F 11/3072 (2013.01) [G06F 16/35 (2019.01); G06N 3/045 (2023.01); G06N 3/084 (2013.01)] | 17 Claims |
1. A computer-implemented method of sparse intent clustering, the method comprising:
using a number of processors to perform the steps of:
identifying features in a number of electronic user reports created by a user and contained in a database, wherein the features include a title and description;
encoding the features of each user into a binary vector to form a matrix representing the number of electronic user reports, wherein each row of the matrix represents a vector of different user report and, each column of the matrix represents a different features of the features for the user report;
feeding the binary vector for each user report from the matrix into an autoencoder neural network, wherein the autoencoder neural network generates float vectors by generating a N-dimensional float vector representing the user report for each user report, and wherein the N-dimensional float vector comprises floating point numbers with fractional parts;
projecting the float vectors representing the user reports into a N-dimensional space;
clustering the float vectors into vector clusters according to cosine similarities, wherein each vector cluster represents an intent of the user in creating the reports;
labeling the intent of each vector cluster;
receiving input from the user to create a new user report, wherein the input includes a title and description for the new user report;
determining an intent of the new user report according to the input;
identifying a vector cluster labeled with an intent that matches the intent of the new user report; and
providing the user with suggested features for the new user report according to features in the vector cluster identified with the matching intent.
|