Abstract: A computerized-method for resolving a query posted on an online-discussion-board of a social-media-platform and awaiting in a queue of a digital-communication-channel.

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 method for generating a list of tasks from an interaction recording may include a computing device; a memory; and a processor, the processor configured to: identify, for each sentence of one or more sentences of an interaction recording, whether the sentence comprises at least two nouns and at least one verb; generate a set of actionable items using a long short-term memory (LSTM) model by: when the sentence does not comprise at least two nouns and at least one verb, deleting the sentence; and when the sentence comprises at least two nouns and at least one verb, generating an actionable item; input the actionable items to a language model to generate a list of tasks. Computer systems may use a generated list of tasks to automatically allocate work to agents of a contact center or to automatically update a status of a completed task.

Abstract: A system and method are provided to predict media playback requests of media files to decrease response times to the media playback requests. The system includes a processor and a computer readable medium operably coupled thereto, to perform predictive caching operations which include receiving metadata from an interaction stream after recording a media file of an interaction, determining contacts corresponding to users identified in the metadata that are recorded in the media file from the metadata, accessing an ML model for predictive caching of media files, determining, using the ML model and a plurality of model features for the ML model, a first prediction for a first playback of the media file, predicting the first playback of the media file by at least one of the contacts based on the first prediction, caching the media file in the data cache for a time period based on the predicting.

Abstract: A computerized-method for managing skills in an ACD-application due to a request of change to a scheduled-shift of an agent. The computerized-method includes: (i) receiving the request; (ii) retrieving all skills associated to the agent; (iii) for each skill, retrieving mapped ACD-skills and a corresponding SLA-threshold; for each ACD-skill: a. predicting an impact-level on the corresponding SLA-threshold; b.

Abstract: A computerized-method for identifying and addressing a real-time conversational conflict in a contact center. The computerized-method includes: (i) monitoring by one or more processors an interaction between an agent and a customer; (ii) continuously updating a conflict-score during the interaction when a conversational-cut is detected, by operating by the one or more processors a conflict-detector module. The conversational-cut is a point in the interaction that the agent speech is interrupted by the customer and the agent stops speaking, and (iii) addressing the real-time conversational conflict when the updated conflict-score is above a preconfigured conflict-threshold by routing the interaction to a queue of Subject Matter Experts (SME)s of an Automatic Calls Distributor (ACD) application.

Abstract: A computerized-method for matching customer queries across diverse digital channels with a response in a multichannel contact center.

Abstract: A computerized system and method may process and predict stress levels for audio data using a machine learning based framework. A computerized system including a processor and a memory may calculate a buffer length based on a plurality of audio attributes (e.g., of a given audio input or data item), extract an audio buffer from an audio data item based on the calculated length, and predict, using a machine learning model, a stress level for the audio buffer or data item. Some embodiments of the invention may include extracting a buffer of a length determined dynamically for different audio inputs, e.g., to ensure coherency between audio attributes or features extracted from different audio inputs having different audio characteristics. In some embodiments, audio features which may be considered by the model may include, e.g., a plurality of gradients between mel-frequency cepstrum coefficients computed for relevant audio buffers or inputs.

Abstract: In general, systems and methods are provided for training a neural network based on sample screen recordings wherein the neural network learns to minimize a reconstruction error between an original image input to the VAE, and an image reconstructed by the VAE. The systems and methods can provide determining and displaying significant points in time of the frame based on a similarity between compressed frames of a screen recording based on the trained VAE.

Abstract: Screen recording systems and methods, and non-transitory computer readable media, include receiving, from an applications server, a recording configuration including a local recording trigger, wherein the local recording trigger includes a start screen recording event and a stop screen recording event; monitoring activity on a device of a contact center agent; initiating recording of a screen of the device when the start screen recording event is detected; transmitting data captured in the recording to a recorder; and stopping transmission of the data captured in the recording to the recorder.

Abstract: Systems and methods for detecting stamps include if at least one regular shape in an image of a document is detected then outputting said at least one regular shape as a stamp; else: removing at least one of text, lines, and noise in the image of the document; and if at least one closed shape is remaining in the image of the document, then inscribing said at least one closed shape and outputting said at least one inscribed closed shape as a stamp; else if at least one open shape is remaining in the image of the document, then enclosing said at least one open shape and outputting said at least one enclosed shape as a stamp.

Abstract: A method and system for evaluating bot performance, including collecting, by a processor, bot performance data items, wherein the collecting includes directly collecting bot performance data items; and calculating bot performance data items based on collected bot performance metrics; producing a bot performance output including bot performance data items; and assessing the bot performance output. Assessment of the bot performance output may initiate bot quality management, wherein the bot quality management includes, assessing the bot update recommendations. Assessment of the bot update recommendations may result in initiating bot update.

Abstract: Systems and methods for providing interaction recordings with removed personally identifiable information (PII) are disclosed, the systems and methods involving: extracting, from an interaction recording, using an automatic speech recognition engine, a timestamped recording transcript; identifying, using an artificial intelligence (AI) engine, time periods of the timestamped recording transcript which disclose PII; and removing, from the interaction recording, data present during the time periods which disclose PII, to produce a secure interaction recording.

Abstract: Systems and methods for evaluating and determining a root cause of a change in performance in a workforce management system are provided. Graphs can be created based on key performance indicators, behaviors and metrics to determined a root cause for agents who have a decrease in performance. The root cause can be transmitted to other computing systems which can select which interactions to record, selects a coaching program to run, or any combination.

Abstract: A computerized-system for converting a time-off request of an agent to a shift-trade with another agent or to a self-swap schedule, in a contact center is provided here in. Upon receiving a time-off request from a source-agent, operating a Time-off Convertor (TC) module. The TC module includes (i) searching open trade requests in dates where the source-agent doesn't have a scheduled-shift, to yield a list-of-trading-agents; (ii) retrieving from the yielded list-of-trading-agents, compatible-agents who do not have a scheduled-shift in the specified date; (iii) presenting the compatible-agents, via a display unit; (iv) enabling the source-agent a selection of an agent from the presented compatible-agents and upon selection of the agent by the source-agent, sending an approval request to the agent; and (v) upon acceptance of the agent, sending to the source-agent and to the agent a trade-success-notification, and operating change of scheduled shifts in one or more WFM MSs.

Abstract: A system and method for managing interaction distribution, for example in a contact center, may, for a digital skill relating to interaction handling and impacted by a lack of resources during an interval, determine an agent having the digital skill; raise the identified agent's concurrency setting for the digital skill for the interval; and distribute interactions according to the concurrency setting. The concurrency setting may determine how many interactions relating to the digital skill the agent can handle concurrently.

Abstract: A system and method for intelligent computerized task scheduling and execution, including: optimizing a time off rule including a quota of time off units for a time period—by changing the quota of time off units based on calculating a time off utilization indicator; updating a computerized task schedule based on the optimized time off rule; and executing tasks based on the updated schedule. In some embodiments, time off optimization may include identifying, by a machine learning model (such as, e.g., a generative artificial intelligence or large language model), rules matching a given time off rule, and deleting/merging rules based on similar rule names or activity codes. The machine learning model may generate rule names for merged rules. Optimized time off rules may be used to accept or reject time off requests transmitted and/or received, e.g. over a data or communication network.

Abstract: A system and method for automatically identifying and masking information, including: identifying, using a machine learning model, one or more tokens in an image file using one or more data items extracted from the image file and including one or more strings, and masking one or more of the identified tokens in the image file. In some embodiments, masking includes coloring locations in the image file based on extracted location information—describing boxes or polygons bounding or surrounding of the strings in the image file. Tokens identified and/or masked by some embodiments may include personally identifiable information (PII) or data, and some embodiments may determine the type of PII data for tokens or texts identified as including PII. In some embodiments, rows of text extracted from the image file may be provided to the machine learning model in a sequential manner (e.g., one row after another).

Abstract: A computerized-method for detecting market sentiment manipulation that is related to financial-instruments trading. The computerized-method includes: (i) monitoring incoming alerts in an analytics-engine. (ii) retrieving data from each alert, by operating a context-extraction module; (iii) for each alert: a. collecting feeds from social-media servers based on the retrieved data by operating a social-media feeds-extraction module; b. for each feed, generating a summary by using Gen AI; and c. analyzing a social-media sentiment by providing the generated summary of each feed to the Gen-AI; (iv) for each financial instrument that has been traded in the preconfigured period, searching an anomaly between a sentiment from traditional news source and the analyzed social-media sentiment; (v) storing each anomaly in an anomalies database; and (vi) pausing each financial-transaction that has been processed and related to the financial-instrument in the anomalies database.

Abstract: A device, system and method for accelerated compliance testing for real-time detection of suspicious transactions in a transaction stream. A machine learning model may determine a global trend of cumulative transaction behavior based on all, a majority or a representative subset, of the stream of transactions. For each transaction in the stream, a skip rule engine may sort each security compliance test to be skipped or not skipped based on the test's relevance to the global trend of the cumulative transaction behavior. The not skipped security compliance tests may be executed in real-time for each transaction in the stream to generate real-time partial security assessments therefore comprising real-time suspicious transaction alerts. The remaining tests may be skipped in real-time and executed, at a time delay after transaction times, to generate time delayed supplemental security assessments therefore comprising time delayed suspicious transaction alerts to complete all compliance testing.