Abstract: A system and method of automatically discovering unigrams in a speech data element may include receiving a language model that includes a plurality of n-grams, where each n-gram includes one or more unigrams; applying an acoustic machine-learning (ML) model on one or more speech data elements to obtain a character distribution function; applying a greedy decoder on the character distribution function, to predict an initial corpus of unigrams; filtering out one or more unigrams of the initial corpus to obtain a corpus of candidate unigrams, where the candidate unigrams are not included in the language model; analyzing the one or more first speech data elements, to extract at least one n-gram that comprises a candidate unigram; and updating the language model to include the extracted at least one n-gram.

Abstract: A method for conducting a data transaction between an on-chain enterprise and an off-chain enterprise according to one embodiment includes receiving at the on-chain enterprise a request for data from an end user; determining that the off-chain enterprise possesses the requested data; transmitting the request for data to an oracle system; transmitting the request for data to the off-chain enterprise; providing the requested data to the oracle system; providing the requested data to the on-chain enterprise by (i) generating a block representing the data transaction in the blockchain infrastructure, (ii) publishing the block to one or more nodes in the blockchain infrastructure, (iii) validating the data transaction at the one or more nodes in the blockchain infrastructure, (iv) adding the block to a blockchain based on a consensus reached among the one or more nodes in the blockchain infrastructure, (v) updating the one or more nodes in the blockchain infrastructure with the block, and (vi) labeling the data tr

Abstract: A method for executing hyper-personalized interactions across enterprises using interactions added to blockchains as transactions according to one embodiment includes determining, by a first enterprise system, an intent from a first interaction added to a blockchain via a blockchain transaction, determining, by the first enterprise system, a correlation between the intent and a set of subsequent related interactions with one or more enterprise systems different from the first enterprise system, and generating, by the first enterprise system, a second interaction with a second enterprise system of the one or more enterprise systems different from the first enterprise system, wherein the second interaction is within the set of subsequent related interactions.

Abstract: A method for routing incoming interactions in a contact center. The incoming interactions are instigated by customers for communicating with the contact center, and the contact center includes agents between which the incoming interactions are routed. The method includes: determining a routing interval; identifying received incoming interactions for inclusion in a received interactions batch, each of the received incoming interactions being identified as ones of the incoming interactions that are received within the routing interval; identifying candidate agents for inclusion in a candidate agent group, the candidate agents being identified as available ones of the agents to whom the received incoming interactions of the received interaction batch can be routed; and subsequent to the end of the routing interval, routing the received incoming interactions included in the received interaction batch to the candidate agents included in the candidate agent group.

Abstract: A method for measuring experience quality. The method including: receiving key experience aspects (“KEAs”); administering pre-surveys to a representative subset of the experience audience, including an importance pre-survey requesting relative importance between the KEAs; and perception pre-survey requesting how closely perceptions align with each KEAs; calculating importance weights and perception weights based on the pre-surveys; performing a general survey process that includes surveying the experience audience to provide a quality rating indicating how well each of the KEAs was delivered based on their own experience; and calculating an Experience Index score as a measure of the quality of the experience that is an aggregation of the received quality ratings weighted by at least one of the importance weights or the perception weights.

Abstract: A method of neural network-based pattern analysis for real-time threat detection according to an embodiment includes receiving a real-time request for a system resource from a user of the system, determining a user identifier associated with the user of the system, retrieving a set of recent requests associated with the user identifier from a short-term buffer, analyzing, using machine learning, the real-time request based on the set of recent requests and a neural network model to determine whether the real-time request is suspicious, and flagging the real-time request as a suspicious request in response to a determination that the real-time request is suspicious.

Abstract: The journeys and/or timelines of multiple customers may be used in escalation management and/or journey mining. An event of interest, pertaining to an issue or an incident, on a timeline may be used in the escalation management and/or journey mining. Escalation management is directed to addressing and resolving incidents, problems, and customer situations which could result in a high level of customer dissatisfaction or damage to a service provider's reputation, using the appropriate response and/or resources. Journey mining is directed to using patterns across customers and their journeys to determine where things in the journey went differently than what was expected.

Abstract: A method for implementing chats that includes: providing a chat feature and chat interface on a webpage; providing two types of the chat resources for generating the text inputs of the chats, an automated chat resource type and a human chat resource type; providing a routing function that selectively routes incoming chats between the two types of the chat resources; providing a first selectable portion on the chat interface that, when selected by a customer, indicates a customer chat preference as to whether the customer prefers to chat with chat resources of the automated chat resource type or human chat resource type; receiving input from the customer device indicating that the customer selected the first selectable portion; determining from the received input the customer chat preference; and routing in accordance with the determined preference.

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.

Abstract: A method and system for automatic topic detection in text may include receiving a text document of a corpus of documents and extracting one or more phrases from the document, based on one or more syntactic patterns. For each phrase, embodiments of the invention may: apply a word embedding neural network on one or more words of the phrase, to obtain one or more respective word embedding vectors; calculate a weighted phrase embedding vector, and compute a phrase saliency score, based on the weighted phrase embedding vector. Embodiments of the invention may subsequently produce one or more topic labels, representing one or more respective topics in the document, based on the computed phrase saliency scores, and may select one or more topic labels according to their relevance to the business domain of the corpus.

Abstract: A method and system for finetuning automated sentiment classification by at least one processor may include: receiving a first machine learning (ML) model M0, pretrained to perform automated sentiment classification of utterances, based on a first annotated training dataset; associating one or more instances of model M0 to one or more corresponding sites; and for one or more (e.g., each) ML model M0 instance and/or site: receiving at least one utterance via the corresponding site; obtaining at least one data element of annotated feedback, corresponding to the at least one utterance; retraining the ML model M0, to produce a second ML model Mi, based on a second annotated training dataset, wherein the second annotated training dataset may include the first annotated training dataset and the at least one annotated feedback data element; and using the second ML model Mi, to classify utterances according to one or more sentiment classes.

Abstract: An on-premises system for pre-processing data for forecasting according to an embodiment includes at least one processor and at least one memory having a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the on-premises system to receive a request to forecast contact center data using a cloud system, determine a first number of interactions per unit of time for a source interval, determine a second number of units of time in a destination interval, and determine a third number of interactions in the destination interval based on the first number of interactions per unit of time for the source interval and the second number of units of time in the destination interval.