241 results about "Contact center" patented technology

The disclosure relates to systems, methods, and computer-readable media for an artificial intelligence (AI) conversational agent configured for enhanced user interaction in multi-channel contact centers. An example method includes receiving a query regarding a particular property of an asset during a real-time conversation, classifying an intent of the query into a predefined category, triggering, based on the classifying of the intent, a finetuned large language model for the predefined category to answer the query, generating, by the finetuned large language model, a response to the query based on at least one of an information data model and a knowledge graph data store, and outputting the response to the query.

A computerized-method for providing personalized-content for an interaction of an agent with a customer during an outbound conversational-marketing-campaign of a tenant operated via a cloud-based contact-center-platform. The computerized-method includes: (i) receiving details of the customer and details of the outbound conversational-marketing-campaign of the tenant; (ii) creating a prompt-text based on the received details of the customer and the details of the outbound conversational-marketing-campaign; (iii) generating the personalized content for the interaction with the customer in text-format by executing an LLM AI engine with a trained model with the created prompt-text; (iv) storing a text-file with the generated personalized content in text-format in a contents-database; (v) initiating the interaction of the agent by dialing to the customer; (vi) retrieving the text-file for the interaction from the contents-database; and (vii) sending the text-file to a computerized-device of the agent to be presented via a display-unit that is associated to the computerized-device.

A method, system, and article of manufacture for modifying a queue assignment for a contact center are provided. At least one computing device determines, by solving for constraints, at least one staffing change for at least one of the first queue or the second queue, using as inputs (a) first time-based service metrics, (b) second time-based service metrics, (c) data describing eligible staffing changes, and (d) at least one predetermined constraint. The at least one staffing change is a modification to the queue assignment of a subset of the computing device instances that is predicted to improve net staffing relating to service targets selected from (a) an average speed of answer (ASA) specifying an average time for one of the computing device instances to initiate handling of a particular task after the particular task has been assigned to the relevant queue and (b) a service level specifying a percentage of tasks for which handling is initiated within a specified time frame after the tasks are assigned to the queue. The at least one staffing change can be implemented by modifying the queue assignment of the subset of the computing device instances.

A system and method for outbound call campaign management model in a contact center using a generative artificial intelligence which processes prompts such as “Schedule a follow-up call with client X,” understanding intent and context. Leveraging pre-trained language understanding, it interfaces with campaign components, scheduling calls or updating client information. The model dynamically adapts to varying scenarios, enhancing efficiency and personalization. The system employs secure interfaces, integrates with contact center tools, and undergoes continuous improvement through periodic retraining, ensuring optimal performance and compliance with evolving campaign requirements. Overall, it streamlines outbound call operations, automating actions and facilitating smoother interactions for a more productive and customer-centric contact center environment.

A method for efficiently encoding a trie data structure for transmission according to an embodiment includes receiving an application programming interface (API) request pertaining to the trie data structure that is indicative of flows of customer interactions with automated agents of a contact center, obtaining the trie data structure in which each of multiple nodes has an associated prefix key that defines a path from a root to the corresponding node, and encoding the nodes in a transmission format having a dictionary data structure. The nodes in the transmission format do not have the prefix key that defines the path from the root to the corresponding node. The method also includes transmitting a response to the API request based on the trie data structure encoded in the transmission format.

A method in a contact center for generating an action classifier model and use thereof in selectively initiating turn set queries of a knowledge base to assist agents in real time during ongoing conversations with customers. The method includes: generating an action classifier model; receiving classification data that classifies a first plurality of the customer actions found in training samples as belonging to a first action category for which a knowledge base search is deemed needed, and a second plurality of the customer actions as belonging to a second action category for which a knowledge base search is deemed not needed; and using the action classifier model and the received classification data to perform a query filtering routine for selectively initiating a turn set query for a present turn set occurring in an ongoing conversation between an agent and customer.

Systems and methods for orchestrating interaction with an artificial intelligence (AI) application in a contact center environment receive, via an AI agent, a voice message from a user; convert the message from voice to text; generate an initial computational inference process based on the text message; determine whether or not all information required to execute the initial computational inference process is available to the processor; when a determination is made that all information required is available: execute the initial computational inference process; generate a text reply based on the initial computational inference process; convert the text reply to a voice reply; and send the voice reply to the user via the AI agent; when a determination is made that information is unavailable: generate a text query requesting the information; convert the text query to a voice query; and send the voice query to the user via the AI agent.

An example operation may include one or more of implementing a trained artificial intelligence (AI) model using a neural network training capability with at least one of call log data of calls determined to have an activity risk, activity risk data, activity context, and model feedback data, capturing audio from an ongoing telephone call, converting the audio from the ongoing telephone call into text, obtaining context of an activity from a computing device, executing the trained AI model to generate an activity risk profile based on the text and the context of the ongoing telephone call, and executing an action during the ongoing telephone call based on the activity risk profile.

Methods and systems for creating and using a knowledge base in a contact center. Templates, including responses to specific issues, are made available to agents in dynamic manner to allow agents to be more efficient while performing their daily job. A centralized database of templates is created in a novel manner to be used for multiple digital channels. The templates can be used and reused by multiple systems such as an agent assistant system or a virtual agent system, providing an integrated and consistent experience for responding to communications in a contact center.

A computerized-method for predicting a staffing-shrinkage percentage in a time-slot during a future staffing plan in a contact center, The computerized-method includes: (i) receiving via a User Interface that is associated to a Workforce Management (WFM) application, skills for the future staffing plan and the time-slot; (ii) calculating a historic-shrinkage percentage during a preconfigured period based on agents time-offs and understaffing-levels during the preconfigured period; (iii) determining the staffing-shrinkage percentage in the time-slot during the future staffing plan based on the calculated historic-shrinkage percentage; and (iv) configuring the WFM application to update staffing level in the future staffing plan, based on the determined staffing-shrinkage percentage.

A device, system and method for analyzing audio speech signals to detect fraudulent calls to a contact center comprising splitting an audio recording of a call in real-time into a foreground speech signal attributed to a main speaker and a background audio signal, extracting audio features from the foreground speech signal and background audio signal, inputting the extracted audio features into an ensemble model comprising multiple different machine learning models co-trained to cumulatively detect fraud, wherein the multiple different machine learning models include: a speaker audio model to detect audio speech anomalies, a speaker intent model to classify intent of the main speaker, a synthetic voice detection model to identify a non-human entity, and a prosody model to detect voice intonation of the main speaker. A prediction may be output, by the ensemble model, indicating whether the call is fraudulent.

A method in a contact center for generating insights from conversation data derived from interactions and storing the insights in an index. The method may include: determining an insight type; based on the insight type, determining inputs including a question prompt, answer prefix, and relevant portion of the conversation data; inputting the inputs into a LLM configured to receive the inputs and generate output text answering a question contained in the question prompt pursuant to an answer form suggested by the answer prefix given content contained in the relevant portion of the conversation data; generating the output text via operation of the LLM; transforming the output text of the first insight via a sentence transformer into vector embedding representative of a semantic meaning of the output text; and storing the computed vector embedding of the first insight in the index.

A computerized-method for generating a text-summary of a multiple-sections text-document that was created via an application that is running in a cloud-based CC for a tenant. The computerized-method includes: (i) operating a prompt-generator module to yield a prompt-text, the prompt-generator module includes: a. retrieving a rule of configuration of the text-summary of the multiple-sections text-document; b. fetching data related to the multiple-sections text-document, the data related to the multiple-sections text-document includes sections, and each section of the sections comprising questions and each question of the questions has a corresponding answer, and c. generating the prompt-text based on the rule of configuration and the data related to the multiple-sections text-document and the multiple-sections text-document; (ii) generating the text-summary by operating a GenAI with LLMs service to execute the prompt-text; and (iii) storing the text-summary in a summary-database to be used to operate actions for the tenant.

A system, device, and method to reconnect a terminated communication to the original queue and provide queue status over a different communication channel. The method includes receiving a first communication over a first communication channel and placing the first communication in a contact center queue. The method also includes providing a user with an option to terminate the first communication over the first communication channel and receive queue status information over a second communication channel, and in response to the user selecting the option: terminating the first communication while maintaining a queue status in the contact center queue for the first communication; providing the queue status information; in response to the queue status of the first communication being within a threshold, notifying the user to initiate a second communication over the first communication channel; and replacing the first communication in the contact center queue with the second communication.

A method for efficient identification of knowledge base data to support interactions in a contact center may include identifying a query associated with a contemporaneous interaction between a client and an agent of a contact center and performing a search of a knowledge base to determine a set of one or more relevant documents responsive to the identified query, including ranking a set of resultant documents from the knowledge base as a function of a vector-based similarity determination in which each resultant document and the identified query is represented with a corresponding embedding. Additionally, the method may include identifying, with a transformer-based artificial intelligence model, a subset of content within each relevant document as being most pertinent to the identified query and visually demarcating the identified subset of each relevant document from other content of the relevant document in a user interface as the interaction occurs.

A method for tracking and analyzing signals associated with metrics and providing actionable insights according to an embodiment includes receiving metric data, including workload metric data, for a contact center during a predefined time interval, analyzing the metric data to generate analysis data, wherein the metric data is analyzed separately for each agent planning group, processing the analysis data using at least one large language model to generate a set of insights associated with the metric data of the contact center and at least one possible action to improve a condition associated with the set of insights, displaying the metric data, the set of insights, and an indicator of the at least one possible action on a graphical user interface accessible to a user, and automatically executing a possible action in response to the user's selection of the possible action via the graphical user interface.

A system for carbon emission reduction according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to determine whether an application for providing one or more services in a contact center is hosted in an on-premises system or a cloud-based system. The instructions may also cause the system to determine, in response to a determination that the application is hosted in a cloud-based system and as a function of one or more cloud hosting implementation properties, a score indicative of a carbon emission efficiency and provide data indicative of a potential carbon emission reduction for the application as a function of the determined score and at least one modification to the cloud hosting implementation properties.

A server accesses, during a contact center engagement performed by a software agent configured to generate and output automated responses to prompts, a prompt provided by a contact center user device. The server determines, using a natural language processing engine of the software agent, to use an application programming interface call based on the prompt, the natural language processing engine comprising a generative pre-trained transformer trained to generate natural language responses to natural language prompts. The server transmits an access request representing the application programming interface call to a governance engine configured to generate data structures responsive to application programming interface calls in a format readable by the software agent. The server receives a data structure responsive to the access request from the governance engine. The server generates, using the natural language processing engine, a natural language response based on the data structure.

A contact center controller is provided to automatically manage a large volume of audio and / or video electronic communications in a contact center. The controller routes electronic communications to available agents, and monitors the interactions between the agents and users participating in the electronic communications. The controller determines a state associated with each agent based on the interactions the agent has with one or more users in the same electronic communication, and routes new electronic communications away from a first agent in response to determining a first state for the first agent that indicates a specific level of fatigue. The controller performs different actions for different agents and / or electronic communications based on different or changing levels of fatigue associated with the agents.

A method for providing efficient trie data structure processing according to an embodiment includes splitting, based on organization identifiers and sequence identifiers, a data frame indicative of a set of events associated with customer interactions with automated agents of a contact center to produce a set of multiple partitions, and producing a set of multiple trie data structures, including generating a trie data structure for each partition. Each trie data structure represents aggregate counts of a corresponding subset of event sequences associated with a corresponding organization. The method also includes merging multiple trie data structures of the set of trie data structures to produce a combined organization trie data structure and storing the combined organization trie data structure to enable generation of a visualization of the combined organization trie data structure.

A method of routing interactions to contact center agents according to an embodiment includes identifying an interaction to be routed to a contact center agent, determining a predictive routing score for each prospective contact center agent to which the interaction can be routed based on a historical performance of each prospective agent, determining a relative gain for each prospective agent based on an interaction class of the interaction, an agent class performance of the prospective agent, and an agent value of the prospective agent, wherein the relative gain of a respective agent is indicative of a relative optimization improvement of routing the interaction to the respective agent relative to another of the prospective agents, ranking the prospective agents based on the associated predictive routing score and the associated relative gain for each prospective agent, and routing the interaction to an agent selected based on the ranking of the prospective agents.

Computer-implemented systems and methods are disclosed for simulating contact-agent pairings and analyzing contact center performance based on the simulated contact-agent pairings. An exemplary method includes obtaining a first set of available contacts and available agents; determining a first contact-agent pairing based on the first set of available contacts and available agents and a first pairing strategy; and establishing a first connection between a first agent device and a first contact device for the first contact-agent pairing. The exemplary method further includes storing a first set of pairing data corresponding to the first contact-agent pairing; generating, by a simulation model implementing a simulated pairing algorithm, a second contact-agent pairing based on the first set of available contacts and available agents and a second pairing strategy; and storing a second pairing data corresponding to the second contact-agent pairing.

A method of leveraging machine learning to predict empathy for improved contact center interactions according to an embodiment includes receiving, by a computing system, at least one user message from a real-time contact center interaction with a user, generating, by an artificial intelligence system of the computing system, at least one empathy score based on the at least one message using the machine learning, wherein each of the at least one empathy score is indicative of a real-time empathy of the user, generating, by the artificial intelligence system of the computing system, an empathetic text response to the at least one user message based on the at least one empathy score, and responding to the at least one user message in the real-time contact center interaction based on the empathetic text response generated by the artificial intelligence system of the computing system.

Systems and methods for assessing the feasibility of a proposed contact center work plan are disclosed. The plan may include a proposed workload and a proposed performance metric and the method may include: generating, based on the proposed contact center work plan and data indicative of previous feasible contact center work plans, a feasibility for the proposed contact center work plan; and where the feasibility is below a threshold, generating, using a large language model, a modified contact center work plan for a user with a feasibility above the threshold, the modified contact center work plan comprising a modification to one or more aspects of the contact center work plan.

A computer-implemented method for managing a contact center one or more processors in a management network (a) receiving, from an end-user network, data associated with a plurality of agent instances servicing incoming communications for the contact center, wherein the contact center, the end-user network, and the management network are associated with the enterprise; (b) determining, based on a specification of a logical directive, an operation to be performed in relation to the plurality of agent instances, the specification of the logical directive having at least one condition that, if satisfied by the received data associated with the plurality of agent instances servicing the incoming communications for the contact center, defines the operation to be performed; and (c) providing, to one or more servers, the determined operation to be performed, wherein the operation includes making a modification relating to (i) at least one of the plurality of agent instances and / or (ii) the servicing of the incoming communications. A computing system and article of manufacture are also provided.

A method for filtering a Trie data structure for real-time bot flow visualization according to an embodiment includes receiving data associated with the Trie data structure, wherein the Trie data structure includes data for a plurality of contact center bot flows of an organization, and wherein each bot flow of the plurality of contact center bot flows includes at least one event, receiving a user selection associated with filtering the Trie data structure for modified visualization of the Trie data structure, performing a search of the Trie data structure to identify events of the Trie data structure to be deleted, deleting the identified events to generate an updated Trie data structure, updating event attributes of remaining events of the updated Trie data structure in response to deleting the identified events, and providing the updated Trie data structure for real-time bot flow visualization.

A contact center server provides as part of a voice conversation with a customer device a voice prompt indicating the unavailability of any voice agent the agent devices and an option to route the voice conversation to any available chat agent at one of the agent devices. The contact center server receives a confirmation from the customer device to route the voice conversation to any available chat agent. In response to the confirmation, a multimodal communication session between the customer device and an available chat agent is established. Subsequently, the contact center server orchestrates a multimodal conversation in the multimodal communication session by speech-to-text conversion of customer messages received from the customer device, and text-to-speech conversion of agent messages received from the available chat agent with whom the multimodal communication session is established.

A method that includes an automated modeling process having the steps of: receiving shift data describing evaluation shifts worked by the agent and determining therefrom values for shift parameters; monitoring performance of the agent during each of the evaluation shifts in relation to an adherence metric and determining therefrom a score associated with the adherence metric for each; creating a training dataset that includes training samples for respective ones of the evaluation shifts, each training sample including the determined values of the shift parameters paired with the score achieved in relation to the adherence metric; and using the training dataset to train a work attributes model for the agent, the work attributes model configured to identify a key value for a key shift parameter that statistically correlates with the agent achieving a better score in relation to the adherence metric.

A contact center request is received from a user device. Respective sets of characteristics associated with respective agent devices are determined. The contact center request is routed to an agent device of the respective agent devices based on the respective sets of characteristics. In an example, respective environment scores for the respective agent devices are obtained based on the respective sets of characteristics. The respective agent devices can be ranked based on the respective environment scores.