Abstract: Systems and methods for automatically assessing a quality of service for agents of a customer support system are disclosed. An example method may include retrieving historical conversations between the agents and users of the customer support system, receiving user comments for one or more of the historical conversations, identifying which of the received user comments includes keywords indicative of one or more quality of service attributes, generating transcripts of historical conversations associated with the identified user comments, training a machine learning model based at least in part on the generated transcripts and the user comments of the historical conversations associated with the identified user comments, providing a plurality of current conversations between agents and users of the customer support system to the trained machine learning model, and generating a behavioral score for each of the agents using the trained machine learning model.

Abstract: Methods of intelligent routing of work assignment includes indexing plurality of pending tasks and indexing a plurality of available employees. A first employee is retrieved from an index of available employees. A next available task assignable to the first employee is determined. A work item from the next available task is assigned to the first employee from the available employee list. The assigned work item is removed from pending task list. The first employee is removed from the available employee list. The next employee is retrieved from the index of available employees.

Abstract: Embodiments of the present disclosure may relate to an apparatus for infrastructure management with an interface to receive a plurality of telemetry signals from first one or more infrastructure components of an infrastructure; and a policy controlled semi-autonomous (PCSA) infrastructure evaluator coupled with the interface, where the PCSA infrastructure evaluator includes a machine-learning (ML) model of service level metric (SLM) deviation by second one or more application or infrastructure components of the infrastructure and the PCSA infrastructure evaluator is to: determine a deviation from a SLM of third one or more infrastructure components based at least in part the ML model and one or more of the plurality of telemetry signals; and send a message, based at least in part on the deviation from the SLM. Other embodiments may be described and/or claimed.

Abstract: Methods and devices for reducing durations of sessions (e.g., voice call sessions, chat sessions, etc.) include a mobile device that is configured to receive an instruction message from a customer service center associated with an enterprise, and in response, determine whether the mobile device user has engaged the customer service center associated with the enterprise within a proceeding duration. The mobile device may select a media element based on the received instruction message in response to determining that the mobile device user has engaged the customer service center associated with the enterprise within the proceeding duration. The mobile device may render the selected media element on a screen of the mobile device until the mobile device user interacts with the mobile device or the rendered media element.

Abstract: Failover between decentralized identity stores in the context of there being multiple decentralized identity stores that are each under the control of a single decentralized identity to store data belonging to or regarding the decentralized identity. Third parties can use the decentralized identity to at least conditionally access the data of the primary decentralized identity store. However, in response to detecting a failover event, one of the remaining decentralized identity stores is promoted as the new primary decentralized identity store. As part of this promotion, the new primary decentralized identity store replaces the old primary decentralized identity store as being the decentralized identity store that is accessed using the decentralized identity.

Abstract: Systems, methods, and computer program products include smart capacity workload routing with workload modeling. One example involves storing a workload model in memory regarding a set of different factors associated with user communications, with each factor is associated with a measurement of workload. A received request including information regarding one or more of the factors is processed and used in identifying a workload measurement for the requested user communication based on comparing the received request information to the stored workload model. An agent with capacity that is available to handle the requested user communication is identified. A communication slot for the identified agent is activated and defined by the identified workload measurement, and the request is routed to the identified agent and updating available workload capacity in the system.

Abstract: A system may include one or more processors disposed within a management network, where the management network has computing resources dedicated to an end-user network. The end-user network may include agent instances and one or more servers associated with the end-user network. The one or more servers are operable to: (i) receive communications to the end-user network, and (ii) assign agent instances to service the communications. The one or more processors may be configured to perform one or more tasks. These tasks may include receiving data associated with the processes of the one or more servers, where the processes relate to the end-user network. The tasks may also include determining, based on a specification, an operation to be performed by the one or more servers, where the specification is defined by the end-user network and comprises a logical directive including at least one condition that, if satisfied by the received data, define the operation.

Abstract: Systems and methods for generating prioritization models and predicting workflow prioritizations are disclosed. Exemplary implementations may: manage environment state information maintaining a collaboration environment; effectuate presentation of a series of questions via a first client computing platform associated with the first user; receive user input from the first client computing platform; generate a first prioritization model based on the response information; and determine one or more priorities for the first user based on the first prioritization model such that a primary first unit of work within the first set of units of work is determined to be a higher priority than a secondary first unit of work within the first set of units of work.

Abstract: A mechanism is provided for implementing a bias detection mechanism that mitigates unintended bias in a conversational agent by leveraging conversational agent definitions, a conversational agent chat logs, and user satisfaction statistics. One or more protected attributes are identified within an utterance from the conversational agent chat logs. Using the identified protected attributes, a replacement utterance with a replacement term is generated for at least one of the identified protected attributes in the utterance. A score is generated for the utterance and the replacement utterance using utterance level relative term importance for protected attributes and regular terms in the utterance and the replacement utterance. Utilizing the scoring, a determination is made as to whether unintended bias exists within the utterance. Responsive to unintended bias being detected, an action is implemented that causes a change to a machine learning model used by the conversational agent.

Abstract: Failover between decentralized identity stores in the context of there being multiple decentralized identity stores that are each under the control of a single decentralized identity to store data belonging to or regarding the decentralized identity. Third parties can use the decentralized identity to at least conditionally access the data of the primary decentralized identity store. However, in response to detecting a failover event, one of the remaining decentralized identity stores is promoted as the new primary decentralized identity store. As part of this promotion, the new primary decentralized identity store replaces the old primary decentralized identity store as being the decentralized identity store that is accessed using the decentralized identity.

Abstract: A system uses intelligent logic to determine information from a communication and to infer relevant CRM objects that may be related the communication. The system further presents a user interface with the communication information and the related CRM objects to allow an agent to review, select, and relate the communication information to one or more CRM objects. Accordingly, the embodiments described herein improve the efficiency of communication management systems and CRM systems by providing an intelligent logic and unique user interface that greatly reduces the number of steps needed to relate communication information with a CRM object.

Abstract: A technique relates to communication resource allocation. A computer system monitors a communication between a conversational entity communication channel and a user device. A type of the communication associated with the user device is determined based on the communication. A replacement communication channel to replace the conversational entity communication channel is determined, in response to the type of the communication. The replacement communication channel is coupled to the user device in place of the conversational entity communication channel.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set and a set of question and answer sets that allow prediction of a subsequent question by a customer. By improving prediction of a subsequent customer question the heuristic engine may improve the efficiency of customer service interactions. The heuristic engine may improve and learn by providing actual interaction sets with correlations associated with the predicted outcomes.

Abstract: A computerized method of managing a robotic telemarketing call includes calling, by an automated robotic telemarketing system, a customer selected from a customer list. The method includes parsing, by a real-time speech recognition module of the automated robotic telemarketing system, a customer statement received from the customer. The method includes determining, by a language intention determining module, a customer purchase intention according to the parsed customer statement. The method includes selecting a sales pitch response corresponding to the determined customer purchase intention. The method includes providing an audio signal including the selected sales pitch response to the customer.

Abstract: A computer system comprises a display system and a skill trainer in communication with the display system. The skill trainer receives a submission of content from a user relevant to a particular skill. The skill trainer publishes the content as material relevant to increasing a proficiency in the particular skill. Further, the skill trainer increases the proficiency of the user according to a policy for submission of content relevant to the particular skill, enabling performing an operation for the organization based on the skills for the people in the organization.

Abstract: A system that greatly improves contact center operations by converting inbound calls from communicating devices to outbound calls to the communicating devices. The system can include a call response agent that receives the inbound call from the communicating device, a speech-enabled automated agent that that interacts with the communicating device to receive an audio signal, a classifier that analyzes the audio signal and determines a caller request based on the audio signal, and a request package generator that creates an unallocated request package based on the caller request. The request package generator can create an unallocated request package menu, including the unallocated request package, and send the unallocated request package menu to a plurality of agent workstations.

Abstract: A system may include one or more processors disposed within a management network. An end-user network may contain agent instances and one or more servers, where the one or more servers are operable to: (i) receive communications to the end-user network, and (ii) assign agent instances to service the communications. The one or more processors may be configured to perform one or more tasks. These tasks may include receiving, from the end-user network, data associated with the processes of the one or more servers; determining, based on a specification, operations to be performed by the one or more servers, wherein the specification is defined by the end-user network and comprises logical directives, each directive containing conditions that, if satisfied by the received data, define the operations; and providing, to the one or more servers, the operations.

Abstract: Described are computer-based methods and apparatuses, including computer program products, for authenticating user service requests from a social networking site. Data representing a selected message and an originator of the selected message is stored. Data representing a reply to the originator of the selected message is transmitted for posting at the social networking server, the reply including data that causes transmission of a service request to the server when actuated. Data representing the service request and a sender of the service request is received. Data representing a user profile of the sender of the service request is retrieved from the social networking server. One or more attributes of the user profile of the sender are compared against one or more attributes of the stored data representing the originator of the selected message in order to verify the one or more attributes of the user profile.

Abstract: Non-limiting examples of the present disclosure describe insight-based routing that is used to improve processing of a service request through a help desk service. A request for support (e.g. technical support) can be received through a modality of a help desk service. The request is evaluated, where an evaluation of the request comprises analyzing an issue associated with the request as well as user-specific signal data associated with a customer and generating insights. A support agent is matched to the customer based on an evaluation of the request. The support agent is selected from a pool of support agents based on application of a model that analyzes support agent data in correlation with the generated insights. An interaction between the matched support agent and the customer may be initiated through a modality of the help desk service.

Abstract: A device obtains information concerning a plurality of customer service representatives to identify a customer service representative and a user device associated with the customer service representative. The device selects a test issue of a plurality of test issues to be presented to the customer service representative, and, based on the test issue, a virtual assistant to converse with the customer service representative. The device initiates, based on an availability of the user device, a communication session with the user device, and causes the virtual assistant to converse with the customer service representative regarding the test issue. The device obtains data concerning a performance of the customer service representative during the communication session, processes the data using a machine learning model to determine a performance score for the customer service representative, and causes, based on the performance score for the customer service representative, at least one action to be performed.

Abstract: A method for providing coachable events for agents within a call center is provided. Behavior score waveforms for interactions and behaviors can be determined. Events can be identified in the behavior score waveforms within identified durations, and a relevancy of one or more events to one or more behaviors can be determined.

Abstract: Embodiments include method, systems and computer program products for performing summarization of a recording based on biometric and business process data. Aspects include receiving a recording of a customer service representative performing a task, receiving a biometric data from a sensor configured to monitor the customer service representative during the performance of the task and obtaining a business process data relating to one or more of the task and the customer service representative. Aspects also include identifying one or more portions of interest from the recording based on one or more of the biometric data and the business process data and compiling the one or more portions of interest into a summarization of the task.

Abstract: Embodiments include method, systems and computer program products for performing summarization of a recording based on biometric and business process data. Aspects include receiving a recording of a customer service representative performing a task, receiving a biometric data from a sensor configured to monitor the customer service representative during the performance of the task and obtaining a business process data relating to one or more of the task and the customer service representative. Aspects also include identifying one or more portions of interest from the recording based on one or more of the biometric data and the business process data and compiling the one or more portions of interest into a summarization of the task.

Abstract: A worker resource management system may include a voice-directed mobile terminal that enables a dialog between a user and the voice-directed mobile terminal. At least one computer may be in communication with the mobile terminal. The computer can include a worker resource management module that receives and records user activity from the voice-directed mobile terminal. The worker resource management module can identify user productivity patterns and provide work assessment predictions based at least in part upon the user activity that is received and recorded. Management can make worker resource decisions in response to the user productivity patterns identified or the work assessment predictions provided by the worker resource management module.

Abstract: Communication events often produce a significant volume and variety of data. While such data is often useful as a teaching or configuration tool or as a source of troubleshooting information, such information often results in “information overload.” By providing a “highlight reel,” communication data comprising only relevant information, which may be further limited to a specific number of duration of events, allows for key data to be identified for presentation and avoid the need to further process, store, or otherwise maintain irrelevant or less relevant data.

Abstract: Techniques for workforce management in a contact center system are disclosed. In one particular embodiment, the techniques may be realized as a method for workforce management in a contact center system comprising generating historical workforce data regarding an agent workforce capacity of the contact center system, and initiating an increase or decrease to an agent workforce of the contact center system based at least in part on the historical workforce data to increase an amount of choice among available agents or waiting contacts.

Abstract: Techniques are described for generating metrics about an individual's experience. One of the method describes providing, by at least one processor, the session record as input to at least one computer-processable model that determines, based on the session record, at least one metric for the service session, the at least one model having been trained, using machine learning and based at least partly on survey data for previous service sessions, to provide the at least one metric associated with the individual's experience. The method includes associating, by at least one processor, the metric of the individual's experience with the individual. The method also includes communicating, by at least one processor, the at least one metric for presentation through a user interface of a computing device.

Abstract: Examples are described of smart capacity workload routing. One example involves storing a workload model in memory regarding a set of different factors associated with user communications, with each factor is associated with a measurement of workload. A received request including information regarding one or more of the factors is process and used in identifying a workload measurement for the requested user communication based on comparing the received request information to the stored workload model, and identifying an agent with capacity that is available to handle the requested user communication. A communication slot for the identified agent is activated and defined by the identified workload measurement. The request is then routed to the identified agent and updating available workload capacity in the system.

Abstract: An adaptive conversational system may simultaneously monitor multiple active calls or ongoing voice or telephone conversations, may extract a different set of conversation elements from a current point in each conversation in real-time as each conversation proceeds, may determine different rules that apply to current points of different ongoing conversations based on the extracted conversation elements satisfying different rule triggers, and may control different conversations at different times according to actions of different rules that are applied at different times to different conversations. The system may selectively control the conversations when the conversations become non-compliant, deviate from best practices, or can be controlled to more effectively reach a positive disposition than when allowing a telephone agent to independently control the conversation.

Abstract: Methods and systems for improving resource content mapping for an electronic learning system. The methods can include: receiving, by the electronic learning system, a resource for satisfying at least one learning objective of the one or more learning objectives, the resource comprising a content having a content data convertible into a text data and one or more resource property fields defining at least one characteristic of the resource; sectioning the content data into one or more content portions based on an analysis of at least one of the content data and the one or more resource property fields; and assigning at least one content portion of the one or more content portions to at least one learning objective.

Abstract: Utilizing a computing device to detect and respond to emotion in dialog systems. The computing device receives a dialog structure comprising a plurality of dialog nodes. The computing device determines a node emotion level for each of the dialog nodes in the dialog structure based on analysis of one or more intents of each of the dialog nodes in the dialog structure. The computing device determines emotional hotspot nodes in the dialog structure, the node emotion level for each of the emotional hotspot nodes exceeding an emotional threshold. The computing device generates one or more responses modifying the node emotion level of each of the emotional hotspot nodes.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data such as communications from previous service sessions between service representative(s) and individual(s), and survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that combines a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network. Individuals can be clustered according to the metric(s) and/or other factors, and the cluster(s) can be employed for routing incoming service requests.

Abstract: A system, method and non-transitory computer readable storage medium comprising instructions that when read by a processor perform receiving a list including a plurality of possible recipients of telephony network connections, the recipients identified by a telephony number, determining a status characteristic of the intended recipient based on the addressing information, based on the status characteristic, determining whether the intended recipient would successfully receive a telephony connection request if the telephony connection request was forwarded to the intended recipient, and indicating the determination of whether the intended recipient would successfully receive the telephony connection request on the list.

Abstract: The present invention allows a CEC system to automatedly, and without human intervention, identify interactions that are likely in need of supervisor intervention. The system reviews all incoming and outgoing interactions for analysis by a metadata analytics service (MAS) software module. The MAS analyzes the interactions to generate interaction metadata, which is used by an interaction analysis engine (IAE) to score the quality of the interaction. If the quality of the interaction is not sufficient, the system marks the interaction as being a problem interaction and notifies a supervisor of the interaction. This ensures the intelligent and dynamic determination of interactions that require additional assistance and assures notification to a supervisor.

Abstract: The invention relates to a method and system for analyzing an electronic communication, more particularly, to analyzing telephonic communications between customers and a contact center to determine and display the most relevant communications to an organization or business.

Abstract: Approaches presented herein enable measuring an impact on performance metrics of shifting a performance focus based on an assignment of communications to a resource based on a performance area in a customer support environment. Specifically, resources, each with several performance area attributes, are assigned performance scores. A performance focus manager selects a shifting performance area of focus and assigns communications to the resources based on the selected performance area. A history manager maintains a set of feedback performance metrics in a selected performance category, including a subset of metrics establishing a baseline for the category. The feedback performance metrics may be queried to determine how a shift in performance focus impacts a performance category and if the performance metrics of the category are within a tolerance.

Abstract: A communications handler manages incoming communications of different channel types and determines an appropriate contact center agent to receive the communication, based on which communication type and the number of sessions for each type, that an agent can handle. The performance of the agent handling the various communication sessions across the channel types is measure and monitored. If the agent's performance crosses a threshold indicating an unacceptable decrease in performance, a channel type/session may be de-assigned in order to improve the agent's performance. If the agent's performance is stellar and allows, then a further channel type or communication session of a channel type may be added. Various graphical user indications for managing the channel type performance and de-assignment are presented.

Abstract: Embodiments of the invention are related generally to systems and methods for routing and administering TTY calls on behalf of individuals who may be deaf and/or hearing-impaired and/or speech-impaired. The invention provides for systems and methods which are operable to both streamline the routing of non-TTY calls, which are often mistakenly made to TTY phone numbers, as well as to better administer TTY calls to true TTY callers. In the present invention, TTY calls are routed to an operator, who may be presented with a real-time feed of TTY calls received by themselves and/or by other operators. Further, search functionality and exportation of data from the system provide additional functionality for users. In embodiments of the invention, data associated with this system may be used to allow for more effective management of a TTY system by users and/or system administrators.

Abstract: A method, system, and a computer program product are provided for monitoring an emotional state of a conversation by monitoring a communication between first and second persons to determine an emotional state of the communication, providing a visual representation of the emotional state of the communication for display to a person having access to the communication, and performing an intervention action to improve the emotional state of the communication in response to detecting the emotional state of the communication meets one or more specified intervention criteria.

Abstract: A method and system automatically determines when to review an agent response. The method performed by an oversight device includes receiving first data including a request type of a request received by a contact center. In response to the first data, the method includes automatically determining rules corresponding to the request type, the rules indicating required steps performed by an agent for the request type. The method includes receiving second data corresponding to a response process used by the agent in generating a response to the request, the response process including performed steps performed by the agent for the request. In response to the second data, the method includes automatically determining whether the required steps are included in the performed steps of the response process. The method includes forwarding the response to a supervisor device when the required steps are absent from the performed steps of the response process.

Abstract: Devices, systems, and methods to receive and analyze biometric measurements from a customer service agent are provided. The analysis of the biometric measurements may be used to identify correlations between the biometric measurements, agent health, and agent performance. These correlations may then be used to route communications to the agent and/or modify the performance and/or increase the heath of the agent. The biometric measurements may also be correlated to an empathy level of the agent.

Abstract: The disclosed system and methods provide real-time information about how agents and customers sound as they are speaking, allowing a supervisor to continuously monitor how agents are doing. The system allows agents to visualize their own speech behavior performance during and after a conversation while viewing important comparative information about prior conversations, and gamifies conversations in real-time by providing visual comparison between the live conversations and various target metrics. The visualization in-turn enhances agent interactive skills such as active listening and mirroring, as well as decision-making skills based on observations of customer engagement and distress levels.

Abstract: An adaptive conversational system may simultaneously monitor multiple active calls or ongoing voice or telephone conversations, may extract a different set of conversation elements from a current point in each conversation in real-time as each conversation proceeds, may determine different rules that apply to current points of different ongoing conversations based on the extracted conversation elements satisfying different rule triggers, and may control different conversations at different times according to actions of different rules that are applied at different times to different conversations. The system may selectively control the conversations when the conversations become non-compliant, deviate from best practices, or can be controlled to more effectively reach a positive disposition than when allowing a telephone agent to independently control the conversation.

Abstract: A system and method obtain a recording of an interaction with a user and a screen recording related to the interaction; extract, from the screen recording, a unique identification value related to the user; resolve the identity of the user using the extracted unique identification value; and associate the user with the recorded interaction by associating the unique identification value with the interaction.

Abstract: Various example implementations are directed to circuits, apparatuses, and methods for providing voice-over-IP (VoIP) services. According to an example embodiment, an apparatus includes one or more VoIP servers configured and arranged to route VoIP calls to and from users of a plurality of customer accounts. Each customer account has a respective plurality of users and a respective settings file. For each of the customer accounts, a processing circuit communicatively coupled to the VoIP servers, records an audio portion of a VoIP call to or from a user of the customer account in response to the VoIP call satisfying a set of recording criteria specified in the settings file for the customer account. The recording criteria for at least one of the customer accounts includes account-level settings for selecting VoIP calls to be recorded and sets of user-level settings indicating criteria for preventing recording of VoIP calls of the individual users.

Abstract: Utilizing a computing device to detect and respond to emotion in dialog systems. The computing device receives a dialog structure comprising a plurality of dialog nodes. The computing device determines a node emotion level for each of the dialog nodes in the dialog structure based on analysis of one or more intents of each of the dialog nodes in the dialog structure. The computing device determines emotional hotspot nodes in the dialog structure, the node emotion level for each of the emotional hotspot nodes exceeding an emotional threshold. The computing device generates one or more responses modifying the node emotion level of each of the emotional hotspot nodes.

Abstract: A method for automatically managing a recorded interaction between a customer and an agent of a contact center includes: extracting, by a processor, features from the recorded interaction; computing, by the processor, a score of the recorded interaction by supplying the features to a prediction model; detecting, by the processor, a condition based on the score; matching, by the processor, the condition with an action; and controlling, by the processor, a workforce management server to assign a training session to the agent of the contact center.

Abstract: A computer-implemented method of handling an audio dialog between a robot and a human user comprises: during the audio dialog, receiving audio data and converting audio data into text data; in response to text data, determining a dialog topic, the dialog topic comprising a dialog content and a dialog voice skin; wherein a dialog content comprises a plurality of sentences; determining a sentence to be rendered in audio by the robot; receiving a modification request of the determined dialog sentence. Described developments for example comprise different regulation schemes (e.g. open-loop or closed-loop), the use of moderation rules (centralized or distributed) and the use of priority levels and/or parameters depending on the environment perceived by the robot.

Abstract: A system for automatically scheduling contact center agents using real-time analytics, comprising an analytics server that receives and analyzes interaction information, a scheduling server that produces scheduling events based on the analysis, and a queuing server that modifies a current state of agent workstations based on the scheduling events, and a method for system for automatically scheduling contact center agents using real-time analytics.

Abstract: A system and method for a communication analytics system comprising a communication device and a system analyzer and the system analyzer is configured to continuously monitor electronic communications over the one or more communication devices and identify one or more communication activities associated with the electronic communications. The system analyzer is further configured to translate the one or more communication activities into communication data, store the communication data in a database and identify one or more correlations from the communication data.