Method and system for document classification
First Claim
1. A computer-implemented method of classifying documents including executing instructions stored on a computer-readable medium, said method comprising:
- receiving a plurality of documents from at least one user, wherein each document includes at least one of unplanned information relating to a customer support issue and an indication of a sentiment;
identifying at least one customer support issue or sentiment contained within each document by parsing the plurality of documents;
classifying, using a classifier, at least a portion of the plurality of documents that satisfy a confidence threshold into one of a plurality of classes, each class associated with the identified at least one customer support issue or sentiment;
clustering a remainder of the plurality of documents that do not satisfy the confidence threshold for the identified at least one customer support issue or sentiment into a plurality of clustered groups using a clustering engine, the clustering engine applying a word analysis; and
outputting a frequency of each identified customer support issue or sentiment in each of the classes and clustered groups, the frequency based on said classifying or said clustering.
2 Assignments
0 Petitions
Accused Products
Abstract
A method and system of classifying documents is provided. The method includes receiving a plurality of documents from at least one user, wherein each document includes information relating to a customer support issue or sentiment and identifying at least one customer support issue or sentiment contained within each document. The method also includes classifying the documents satisfying a confidence threshold using a classifier, clustering the remainder of the plurality of documents into groups using a clustering engine, the clustering engine applying a word analysis, and outputting a frequency of each identified customer support issue or sentiment, the frequency based on the classifying or the clustering.
54 Citations
20 Claims
-
1. A computer-implemented method of classifying documents including executing instructions stored on a computer-readable medium, said method comprising:
-
receiving a plurality of documents from at least one user, wherein each document includes at least one of unplanned information relating to a customer support issue and an indication of a sentiment; identifying at least one customer support issue or sentiment contained within each document by parsing the plurality of documents; classifying, using a classifier, at least a portion of the plurality of documents that satisfy a confidence threshold into one of a plurality of classes, each class associated with the identified at least one customer support issue or sentiment; clustering a remainder of the plurality of documents that do not satisfy the confidence threshold for the identified at least one customer support issue or sentiment into a plurality of clustered groups using a clustering engine, the clustering engine applying a word analysis; and outputting a frequency of each identified customer support issue or sentiment in each of the classes and clustered groups, the frequency based on said classifying or said clustering. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A computer system for processing documents, said computer system comprising:
-
a memory device; a processor in communication with the memory device; a classifier configured to; receive a plurality of documents, each document includes unplanned information relating to a customer support issue or sentiment; determine if a document of the plurality of documents refers to a customer support issue or sentiment by parsing the plurality of documents; and if a confidence level of the determination meets a confidence level threshold of the customer support issue or sentiment, associate a probability to the document that the document refers to the customer support issue or sentiment; and a clustering module configured to receive a remainder of the plurality of documents that do not meet the confidence level threshold of the customer support issue or sentiment; and cluster the remainder of the plurality of documents that do not satisfy the confidence threshold for the customer support issue or sentiment into a plurality of clustered groups containing similar terms relating to the customer support issue or sentiment; and an output module configured to generate a report of a frequency of occurrence of documents associated with the customer support issue or sentiment. - View Dependent Claims (10, 11, 12, 13)
-
-
14. One or more non-transitory computer-readable storage media having computer-executable instructions embodied thereon, wherein when executed by at least one processor, the computer-executable instructions cause the processor to:
-
receive a plurality of documents from at least one user, wherein each document includes unplanned information relating to a customer support issue or sentiment; identify at least one customer support issue or sentiment contained within each document by parsing the plurality of documents; if a confidence level of the identification meets a confidence level threshold of the customer support issue or sentiment, classify the documents satisfying a confidence threshold using a classifier into one of a plurality of classes, each class associated with the identified at least one customer support issue or sentiment; cluster a remainder of the plurality of documents that do not meet the confidence level threshold into a plurality of clustered groups containing similar terms relating to the customer support issue or sentiment using a clustering engine, the clustering engine applying a word analysis; and output a frequency of each identified customer support issue or sentiment within at least one of the plurality of classes and plurality of clustered groups, the frequency based on said classification or said clustering. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
Specification