-
公开(公告)号：US11798539B2
公开(公告)日：2023-10-24
申请号：US17218456
申请日：2021-03-31
Inventor： Basil George , Ramasubramanian Sundaram
IPC: G10L15/18 , G06F16/2458 , G06N5/02 , G06Q30/016 , G10L15/19 , G06F16/35 , G06F16/332 , G06F40/30 , G06F40/289 , G06F40/284 , G06F40/205 , G06F40/216 , G06F40/35 , G06F40/295
CPC classification number: G10L15/1822 , G06F16/2465 , G06F16/3329 , G06F16/353 , G06F40/30 , G06N5/02 , G06Q30/016 , G10L15/1815 , G10L15/19 , G06F40/205 , G06F40/216 , G06F40/284 , G06F40/289 , G06F40/295 , G06F40/35 , G06F2216/03
Abstract: A method for authoring a conversational bot including: receiving conversation data; receiving seed intent data that comprises seed intents having a seed intent label and sample intent-bearing utterances; using an intent mining algorithm to mine the conversation data to determine new utterances to associate with the seed intent; augmenting the seed intent data to include the mined new utterances associated with the seed intents; and uploading the augmented seed intent data into the conversation bot. The intent mining algorithm may include: identifying intent-bearing utterances; identifying candidate intents; for each of the seed intents, identifying seed intent alternatives from the sample intent-bearing utterances; associating the intent-bearing utterances from the conversation data with the seed intents via determining a degree of semantic similarity between the candidate intents of the intent-bearing utterances and the seed intent alternatives.
-
Patent Agency Ranking
2.发明授权公开(公告)号：US11514897B2
公开(公告)日：2022-11-29
申请号：US17218426
申请日：2021-03-31
Inventor： Basil George , Ramasubramanian Sundaram
IPC: G06F40/30 , G10L15/08 , G10L15/18 , G06F16/2458 , G06N5/02 , G06Q30/00 , G10L15/19 , G06F16/35 , G06F16/332 , G06F40/289 , G06F40/284 , G06F40/205 , G06F40/216 , G06F40/35 , G06F40/295
Abstract: A method for intent mining that includes: receiving conversation data; using an intent mining algorithm to automatically mine intents from the conversation data; and uploading the mined intents into the conversational bot. The intent mining algorithm may include: analyzing utterances of the conversation data to identify intent-bearing utterances; analyzing the identified intent-bearing utterances to identify candidate intents; selecting salient intents from the candidate intents; grouping the selected salient intents into salient intent groups in accordance with a degree of semantic similarity; for each of the salient intent groups, selecting one of the salient intents as the intent label and designating the others as the intent alternatives; and associating the intent-bearing utterances with the salient intent groups via determining a degree of semantic similarity between the candidate intents present in the intent-bearing utterance and the intent alternatives within each group.
-
3.发明申请公开(公告)号：US20190355348A1
公开(公告)日：2019-11-21
申请号：US16414885
申请日：2019-05-17
Inventor： Ramasubramanian Sundaram , Aravind Ganapathiraju , Yingyi Tan
Abstract: A system and method are presented for a multiclass approach for confidence modeling in automatic speech recognition systems. A confidence model may be trained offline using supervised learning. A decoding module is utilized within the system that generates features for audio files in audio data. The features are used to generate a hypothesized segment of speech which is compared to a known segment of speech using edit distances. Comparisons are labeled from one of a plurality of output classes. The labels correspond to the degree to which speech is converted to text correctly or not. The trained confidence models can be applied in a variety of systems, including interactive voice response systems, keyword spotters, and open-ended dialog systems.
-
公开(公告)号：US20220208178A1
公开(公告)日：2022-06-30
申请号：US17135114
申请日：2020-12-28
Inventor： Ramasubramanian Sundaram , Pavan Buduguppa
Abstract: A method of applying a confidence classifier for intent classification in association with an automated chat bot according to an embodiment includes processing, by a computing system, an utterance with an intent classifier to determine a probability distribution of possible intents associated with the utterance, generating, by the computing system, a plurality of measures of peakedness of the probability distribution, and applying, by the computing system, a trained confidence classifier to determine a single normalized probability of a most likely intent associated with the utterance based on the plurality of measures of peakedness of the probability distribution.
-
公开(公告)号：US11195514B2
公开(公告)日：2021-12-07
申请号：US16414885
申请日：2019-05-17
Inventor： Ramasubramanian Sundaram , Aravind Ganapathiraju , Yingyi Tan
Abstract: A system and method are presented for a multiclass approach for confidence modeling in automatic speech recognition systems. A confidence model may be trained offline using supervised learning. A decoding module is utilized within the system that generates features for audio files in audio data. The features are used to generate a hypothesized segment of speech which is compared to a known segment of speech using edit distances. Comparisons are labeled from one of a plurality of output classes. The labels correspond to the degree to which speech is converted to text correctly or not. The trained confidence models can be applied in a variety of systems, including interactive voice response systems, keyword spotters, and open-ended dialog systems.
-
公开(公告)号：US11134155B1
公开(公告)日：2021-09-28
申请号：US17139033
申请日：2020-12-31
Inventor： Felix Immanuel Wyss , Ramasubramanian Sundaram , Aravind Ganapathiraju
Abstract: A method for automated generation of contact center system embeddings according to one embodiment includes determining, by a computing system, contact center system agents, contact center system agent skills, and/or contact center system virtual queue experiences; generating, by the computing system, a matrix representation based on the contact center system agents, the contact center system agent skills, and/or the contact center system virtual queue experiences; generating, by the computing system and based on the matrix representation, contact center system agent identifiers, contact center system agent skills identifiers, and/or contact center system virtual queue identifiers; transforming, by the computing system, the contact center system agent identifiers, the contact center system agent skills identifiers, and/or the contact center system virtual queue identifiers into the contact center system agent embeddings, contact center system agent skills embeddings, and/or contact center system virtual queue embeddings, wherein weights of the contact center system agent embeddings, the contact center system agent skills embeddings, and/or the contact center system virtual queue embeddings are randomly initialized; and training, by the computing system, the contact center system agent embeddings, the contact center system agent skills embeddings, and/or the contact center system virtual queue embeddings by applying machine learning to obtain final weights of the contact center system agent embeddings, the contact center system agent skills embeddings, and/or the contact center system virtual queue embeddings.
-
-
-
-
-
Search Results
6
records
(took 0.01 seconds)
