Abstract: A system and method for classification of voice samples to genuine voice samples or spoofing voice samples may include: extracting a set of features from each of a plurality of voice samples, each voice sample labeled as genuine or spoof; training a neural network having a plurality of nodes organized into layers, with links between the nodes, wherein each link comprises a weight, with the sets of features, by adjusting at least one of the weights using a loss function that comprises a regulation factor, wherein the regulation factor is set to zero for voice samples labeled as genuine and is proportional to the prediction of the neural network for data samples labeled as spoofing.

Abstract: A system automatically prioritizes and resumes disconnected customer interactions. The system includes a processor to perform operations that include: receiving a list of disconnected customer interactions, including their metadata; using a prioritization module and the metadata, assigning a priority score to each disconnected interaction; with a queuing module and the respective priority scores, with an agent assignment module, arranging the disconnected interactions in a priority order; assigning an available agent to each disconnected interaction in the priority order; selecting a channel for each disconnected interaction in the priority order, based on a channel recommendation module and the metadata; and re-connecting a disconnected customer with the respective agent via the respective channel for each respective disconnected customer interaction in the priority order.

Abstract: Agent evaluation systems and methods, and non-transitory computer readable media, include receiving a recorded interaction between a customer and a contact center agent; retrieving or determining an interaction divergence range for each of a plurality of interaction parameters for the recorded interaction; calculating a form divergence determinant (FDD) score for each of a plurality of evaluation forms, wherein the lower the FDD score, the more suitable an evaluation form is for the recorded interaction; filtering out evaluation forms having an FDD score greater than a predefined threshold; ranking evaluation forms having an FDD score lower than the predefined threshold based on their FDD score; and providing a list of the ranked evaluation forms to a supervisor of the contact center agent.

Abstract: A computerized system and method may provide automated clustering procedures where each clustered entity or node may be included in a plurality of clusters (e.g., more than a single cluster). Clustering procedures provided by some embodiments of the invention may involve measuring and/or quantifying degrees of relevance and/or generality for a plurality of entities or nodes. In some embodiments, a clustering procedure may be used, e.g., to generate a hierarchical, multi-tiered taxonomy of such entities. A computerized system comprising a processor, and a memory, may be used for ranking a plurality of nodes; select nodes based on the ranking; cluster selected nodes into intermediate clusters; calculate distances between unselected nodes and intermediate clusters; and cluster unselected nodes and intermediate clusters into final clusters based on the calculated distances.

Abstract: A computerized system and method may detect potentially fraudulent events where agent access credentials are used by an unauthorized party, based on calculations, comparisons, and analyses performed using recorded audio data, and execute corrective actions based on calculated results. A computerized system including a processor or a plurality of processors, a communication interface to communicate via a communication network with one or more remote computing devices, and a memory including a data store of a plurality of data items—which may, e.g., describe the remote computing devices and/or interactions involving the remote computing devices—may compare a plurality of voice signatures, which may describe calls from a plurality of remote computers, to a plurality of corresponding voice models—and, if the comparison results in a mismatch, perform a plurality of corrective actions (which may include, e.g., terminating one or more calls involving one or more remote computers).

Abstract: A method of managing interaction recordings of an interaction between agent devices and customer devices, the method comprising: initiating an interaction recording of the interaction between an agent device and a customer device, wherein the interaction recording comprises metadata items; storing one or more parts of the interaction recording in a local storage; identifying parts of the interaction recording whose metadata items fulfill archiving criteria; and archiving parts of the interaction recording stored in the local storage whose metadata items fulfill the archiving criteria and deleting parts of the interaction recording from the local storage whose metadata items do not fulfill the archiving criteria.

Abstract: A machine learning (ML) system and methods are provided that are configured to correlate text data with corresponding image data for image sentiment analysis. The system includes a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform image processing operations which include receiving image data for an image posted on a social networking platform, determining whether there is text data, performing image data extraction operations, analyzing the text data, determining and combining a score for the image and text data, determining an image sentiment or a text sentiment, calculating weighted metrics based on the image sentiment or the text sentiment, determining historical customer data interactions of the customer, and recommending one or more actions based on the weighted metrics.

Abstract: A computer-implemented method for dynamically prioritizing inbound interactions in a digital multi-channel contact center. The computer-implemented method includes for each inbound interaction via a digital channel: (i) operating an interaction analyzer module to extract one or more metadata parameters from the inbound interaction; (ii) operating a prioritization module to calculate a Digital Interaction Priority Score (DIPS) of the inbound interaction based on the one or more metadata parameters; and (iii) forwarding the DIPS to an interaction distribution module to route the inbound interaction to an agent based on the DIPS. The DIPS is periodically updated until the interaction is assigned to the agent.

Abstract: Systems and methods for digital scheduling, include periodically checking a data storage for queued schedule trade requests; identifying two corresponding queued schedule trade requests; else, if two corresponding queued schedule trade requests are not identified: identifying a set of cyclic queued schedule trade requests; else, if a set of cyclic queued schedule trade requests are not identified: repeating the step of periodically checking; approving or rejecting the identified schedule trade requests based on one or more approval criteria; and if the identified schedule trade requests were approved, outputting one or more updated schedules reflecting the approved schedule trade requests.

Abstract: Methods and systems for digital scheduling include periodically determining, from a datastore of agent profiles, a set of agents which satisfy a predefined time-off criterion; and notifying, via a digital message, one or more agents of the determined set of agents of a recommended list of dates on which to take a time-off, wherein the recommended list of dates is generated in accordance with staffing prediction data for the dates.

Abstract: A computerized system and method may calculate or update task or job execution schedules for a plurality of resources and perform automated actions based on the calculated or updated schedules. A computerized system including one or more processors, a memory, and a communication interface to communicate via a communication network with remote computing devices, may be used for forecasting or reforecasting task properties for relevant time intervals, where the properties may describe future tasks to be handled by a plurality of resources; calculating an allocation matrix for the time intervals based on the predicted properties; and calculating or updating a schedule based on the calculated allocation matrix—for example to automatically extend a break for one or more resources, where resources are not to handle tasks during the break. Some embodiments of the invention may perform, e.g., computer automated actions based on calculated or updated schedules.

Abstract: A computerized system and method may provide automated clustering procedures where each clustered entity or node may be included in a plurality of clusters (e.g., more than a single cluster). Clustering procedures provided by some embodiments of the invention may involve measuring and/or quantifying degrees of relevance and/or generality for a plurality of entities or nodes. In some embodiments, a clustering procedure may be used, e.g., to generate a hierarchical, multi-tiered taxonomy of such entities. A computerized system comprising a processor, and a memory, may be used for ranking a plurality of nodes; select nodes based on the ranking; cluster selected nodes into intermediate clusters; calculate distances between unselected nodes and intermediate clusters; and cluster unselected nodes and intermediate clusters into final clusters based on the calculated distances.

Abstract: A system and a method for managing interactions between agent devices and customer devices, the system comprising: a computing device; a local storage; a memory; and a processor, the processor configured to: identify interaction data in interactions between an agent device and a customer device that show a transition from a first connection type to a second connection type; and when a transition in connection types is identified, initiating one or more remedial measures.

Abstract: A system and a method of managing data transfer for a plurality of data centers may include identifying data transfer capacity and data transfer demand for each server of a plurality of data centers; calculating a data transfer distribution for the plurality of data centers that prioritizes data transfer between servers of a first data center of the plurality of data centers over data transfer between servers of the first data center and servers of the remaining data centers of the plurality of data centers based on the identified data transfer capacity and the data transfer demand; and allocating data transfers to the servers of the plurality of data centers.

Abstract: A system and method for real-time fraud detection with a social engineering phoneme (SEP) watchlist of phoneme sequences may perform real-time fraud prevention operations including receiving incoming call interactions and grouping the call interactions into one or more clusters, each cluster associated with a speaker's voice based on voiceprints. For a pair of voiceprints in a cluster, a phoneme sequence is extracted for each voice print. From the extracted phoneme sequences, a similarity score is then calculated to determine if a match exists between the extracted phoneme sequences based on a threshold. If determined a match exists, the phoneme sequence may be added to a SEP watchlist.

Abstract: A method for allocating resources for a plurality of time intervals, including: receiving a forecasted workload and at least one required service metric value; applying a search algorithm to identify an initial allocation assignment; inputting the assignment to a machine learning algorithm, the machine learning algorithm trained on historic data of past intervals; predicting an expected service metric value provided by the initial allocation assignment; adjusting the initial allocation assignment based on a difference between the expected service metric value and the corresponding required service metric value; iteratively repeating the applying, inputting, predicting, and adjusting operations until one of: the expected service metric value predicted for an adjusted allocation assignment is within a predetermined distance of the corresponding at least one required service metric value for the interval; or a predetermined time has elapsed.

Abstract: A method of managing interaction recordings of an interaction between agent devices and customer devices, the method comprising: initiating an interaction recording of the interaction between an agent device and a customer device, wherein the interaction recording comprises metadata items; storing one or more parts of the interaction recording in a local storage; identifying parts of the interaction recording whose metadata items fulfill archiving criteria; and archiving parts of the interaction recording stored in the local storage whose metadata items fulfill the archiving criteria and deleting parts of the interaction recording from the local storage whose metadata items do not fulfill the archiving criteria.

Abstract: Embodiments are disclosed for securing internet-based transfer of voice call data. Embodiments may include: sending a primary-protocol-encoded communication, by a forwarding unit (FU), to a session border controller (SBC), when an indication is received at the FU that a secondary-protocol-encoded communication has been received at a gateway component, from a voice call data source, to propose transferring voice call data to the SBC; outputting by the SBC, in response to the primary-protocol-encoded communication an IP address encoded with the primary protocol; converting, by a gateway component, the IP address encoded with the primary protocol into an IP address encoded with the secondary protocol; and sending, by a gateway component, the IP address encoded with the secondary protocol to the voice call data source that is proposing to transfer the voice call data.

Abstract: Methods and systems for digital scheduling include, using a processor: identifying a set of target agents associated with a corresponding set of shift parameters that satisfy a set of preferences of a multi-day trade request initiated by a source agent; sending the multi-day trade request to a sub-set of the identified target agents selected by the source agent; and if a first target agent of the sub-set accepts the multi-day trade request, and if the multi-day trade request satisfies a pre-defined set of approval criteria, then automatically approving the multi-day trade request between the source agent and said first target agent, and automatically adjusting a schedule of the source agent and the first target agent to reflect the approved multi-day trade request; else: automatically rejecting the multi-day trade request.

Abstract: A computerized system and method may provide a robust, automated clustering procedure, including handling of outlier points, which may involve measuring and/or quantifying degrees of relevance and/or generality for a plurality of input entities. In some embodiments, a clustering procedure may be used, e.g., to generate a hierarchical, multi-tiered taxonomy of such entities. In some embodiments, a computerized system comprising a processor, and a memory, may be used for calculating a distance between nodes for each of a plurality of pairs of nodes, where the pairs may comprise a plurality of input entities and/or initial clusters; selecting one or more of the pairs based on the calculated distances; and merging one or more of the selected pairs, which may include a common node, into one or more final clusters. Some embodiments of the invention may allow routing interactions between remotely connected computer systems based on an automatically generated taxonomy.