Sparse intent clustering through deep context encoders

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.

2. The method of claim 1 , wherein encoding the features of each user report comprises one-hot encoding a number of fields in the user report.

3. The method of claim 1 , wherein encoding the features of each user report comprises:

decomposing equations of a number of filters in the user report to produce decomposed filters; and

one-hot encoding the decomposed filters.

4. The method of claim 1 , wherein encoding the features of each user report comprises:

decomposing equations of a number of custom fields in the user report to produce decomposed custom fields; and

one-hot encoding the decomposed custom fields.

5. The method of claim 1 , wherein encoding the features of each user report comprises encoding the title and description with embeddings from language models.

6. The method of claim 1 , wherein vectors within each cluster have cosine similarities above 0.5.

7. A system for sparse intent clustering, the system comprising:

a storage device configured to store program instructions; and

one or more processors operably connected to the storage device and configured to execute the program instructions to cause the system to:

identify 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;

encode the features of each user report 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 feature of the features for the user report;

feed 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;

project the float vectors representing the user reports into a N-dimensional space;

cluster the float vectors into vector clusters according to cosine similarities, wherein each vector cluster represents an intent of the user in creating the reports;

label the intent of each vector cluster

receive input from the user to create a new user report, wherein the input includes a title and description for the new user report;

determine an intent of the new user report according to the input;

identify a vector cluster labeled with an intent that matches the intent of the new user report; and

provide the user with suggested features for the new user report according to features in the vector cluster identified with the matching intent.

8. The system of claim 7 , wherein encoding the features of each user report comprises one-hot encoding a number of fields in the user report.

9. The system of claim 7 , wherein encoding the features of each user report comprises:

decomposing equations of a number of filters in the user report to produce decomposed filters; and

one-hot encoding the decomposed filters.

10. The system of claim 7 , wherein encoding the features of each user report comprises:

decomposing equations of a number of custom fields in the user report to produce decomposed custom fields; and

one-hot encoding the decomposed custom fields.

11. The system of claim 7 , wherein encoding the features of each user report comprises encoding the title and description with embeddings from language models.

12. A computer program product for sparse intent clustering, the computer program product comprising:

a computer-readable storage medium having program instructions embodied thereon 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 report 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 feature 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; and

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.

13. The computer program product of claim 12 , wherein encoding the features of each user report comprises one-hot encoding a number of fields in the user report.

14. The computer program product of claim 12 , wherein encoding the features of each user report comprises:

decomposing equations of a number of filters in the user report to produce decomposed filters; and

one-hot encoding the decomposed filters.

15. The computer program product of claim 12 , wherein encoding the features of each user report comprises:

decomposing equations of a number of custom fields in the user report to produce decomposed custom fields; and

one-hot encoding the decomposed custom fields.

16. The computer program product of claim 12 , wherein encoding the features of each user report comprises encoding the title and description with embeddings from language models.

17. The computer program product of claim 12 , wherein vectors within each cluster have cosine similarities above 0.5.