公开(公告)号：US20240378392A1

公开(公告)日：2024-11-14

申请号：US18661235

申请日：2024-05-10

Applicant: GENESYS CLOUD SERVICES, INC.

Inventor： BASIL GEORGE ,  RAMASUBRAMANIAN SUNDARAM ,  SARNENDU RAHA ,  SUDHANSHU SHEKHAR ,  SANKET SINGH

IPC: G06F40/35 ,  G06F3/0484 ,  G06N3/006 ,  G06Q30/015 ,  H04L51/02

Abstract: A method for enhancing intent health of a conversational bot. The conversational bot include a machine learning model trained for natural language understanding (NLU) within a NLU domain that is defined by a collection of intents and sets of associated utterances. The method includes: retrieving the collection of intents and associated utterances; generating an utterance embedding for each of the retrieved utterances; calculating scores for utterance-level health indicators for each intent of the collection of intents; and calculating an overall intent health score for each intent of the collection of intents. The overall intent health score may be based on a weighted combination of the calculated scores for the utterance-level health indicators. The utterance-level health indicators may include an utterance in conflict indicator based on a computed semantic similarity and an utterance outlier indicator based on local density.

公开(公告)号：US20230315998A1

公开(公告)日：2023-10-05

申请号：US17708679

申请日：2022-03-30

Applicant: GENESYS CLOUD SERVICES, INC.

Inventor： RAMASUBRAMANIAN SUNDARAM ,  BASIL GEORGE

IPC: G06F40/35 ,  G06F40/117 ,  G06F40/253 ,  G06F40/289 ,  G06F16/2458

CPC classification number: G06F40/35 ,  G06F40/117 ,  G06F40/253 ,  G06F40/289 ,  G06F16/2465

Abstract: A method for mining topics discussed in conversations that includes: receiving conversation data; and using a topic mining algorithm to mine topics from the conversation data. The topic mining algorithm includes identifying candidate topics in each of the conversations. The topic mining algorithm further includes identifying the topics of the conversations by: compiling a list of the candidate topics; pruning the list of candidate topics by discarding certain of the candidate topics per a cross-conversation factor that factors usage across all conversations; and identifying the candidate topics remaining on the pruned list of candidate topics as the topics. The topic mining algorithm further includes determining topic groups by grouping the topics according to a degree of semantic similarity between the topics; and associating a list of utterances with the topic groups.