| CPC G06F 40/35 (2020.01) [G06F 3/167 (2013.01); H04L 51/02 (2013.01)] | 30 Claims |
|
1. A computer-implemented method for disambiguating user utterances, the computer-implemented method comprising:
performing, by a computer comprising one or more processors, a comparison of a first plurality of user intents in a user intent file of a chatbot with a second plurality of user intents in a user intent mapping table;
generating, by the computer, based on the comparison, a list of user intents present in the first plurality of user intents that are not present in the second plurality of user intents of the user intent mapping table;
storing, by the computer, the list of user intents in the user intent mapping table;
performing, by the computer, disambiguation of a user utterance of a user based on a defined number of user intents in a set of possible user intents having highest confidence scores between a first confidence score threshold level and a second confidence score threshold level, wherein the disambiguation is performed in response to a determination that each user intent in the set of possible user intents has a corresponding confidence score less than the second confidence score threshold level;
determining, by the computer, a first user intent of the defined number of user intents is missing from the user intent mapping table, wherein a confidence score corresponding to the first user intent is greater than or equal to the first confidence score threshold level and less than or equal to the second confidence score threshold level;
generating, by the computer responsive to the determination of the first user intent, a human interpretable label for the first user intent by modifying a user intent of the user intent file of the chatbot by replacing one or more portions of the user intent with a predetermined character;
updating, by the computer, the user intent mapping table to include the human interpretable label for the user intent generated responsive to the determination that the first user intent is missing from the user intent mapping table;
locating, by the computer, each user intent of the defined number of user intents in the user intent mapping table;
extracting, by the computer, the human interpretable label corresponding to each of the defined number of user intents located in the user intent mapping table;
assembling, by the computer, a set of human interpretable labels comprising the human interpretable label corresponding to each of the defined number of user intents into a set of user intent options; and
sending, by the computer, the set of user intent options to a client device of the user.
|