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: Machine learning technology can analyze in real-time the data from a call between a person and a customer service representative. Based on this analysis, a server can determine a sentiment score that describes a sentiment expressed by the person or the customer service representative. If the server determines that the sentiment score is less than or equal to a pre-determined value, the server can inform the customer service representative's manager so that the manager can take further action to help the person and/or the customer service representative.

Abstract: A method for synchronizing agent staffing and customer call volume within a contact center estimates the number of agents to staff the contact center during a future time and uses historical data to estimate the number of customer calls anticipated during the future time. The method performs a first comparison of the number of agents with the anticipated customer calls volume for the future time and then determines at least one preferred contact-center callback window. The method communicates with the customer to request at least one preferred customer-selected callback time and performs a second comparison to provide the customer with a suggested callback time that is selected to synchronize the customer call volume with the number of agents, the preferred contact-center callback window, and the preferred customer-selected callback time to improve the customer's experience and efficiency of the contact center.

Abstract: A server receives a request for communication with a contact center agent device from a user device. The server determines a number of devices preceding the user device in a user queue of devices for communicating with the contact center agent device. The server determines a number of contact center agent devices available for the communication. The server periodically calculates an estimated wait time for the user device as a mathematical combination based on the number of devices preceding the user device, the number of agent devices, and previous wait times of other user devices requesting communications with the contact center agent device. The server transmits, to the user device, an output associated with the estimated wait time.

Abstract: There are provided a method for behavioral pairing in a task assignment system with an external pairing system. The method includes transmitting, to the external pairing system over an application programming interface, a control flag and a benchmark flag and receiving, from the external pairing system, a task-agent pairing based on one of a first pairing strategy and a second pairing strategy. The task-agent pairing is based at least in part on the control flag and the benchmark flag.

Abstract: A client application is specified by a target tenant and represented in an OAuth provider, along with a corresponding secret. A source tenant consents to permissions to be executed by the client application on a resource of the source tenant. A target service uses the secret to obtain an access token from an authorization server coupled to the source tenant and uses the access token to obtain access, specified by the permissions, to the resource served by a source service acting on behalf of the source tenant.

Abstract: Systems and methods for predictive cross-platform customer service include receiving first data about a service provider system that includes a plurality of customer service platforms. First user interaction rules are determined based on the first data received. A first condition is then determined to exist in the service provider system based on the first data and the first user interaction rules. First instructions for the service provider system are then determined based on the first condition to achieve a customized user response. The first instructions are provided for the service provider system such that the plurality of customer service platforms has access to the first instructions. Second data of a user interaction with at least one customer service platform is received when the first instructions have been executed. The first instructions are updated to second instructions based on the second data received.

Abstract: A computerized-method using a cloud-based computing environment for improving client service, in a contact center is provided herein. The computerized-method includes: retrieving a context of a query and a time-limit from a CTI event and attempting to retrieve data to evaluate average resolution time for the received context. When the data is found, comparing the evaluated average resolution time with the received time-limit and when the received time-limit is below the evaluated average resolution time, sending a delay notice and providing the client a menu of options for querying through other channels. When the data is not found, or when the received time-limit is above the evaluated average resolution time, presenting on an agent dashboard, the time-limit of the client and accordingly updating parameters in the agent dashboard during the inbound call, thus, improving client service, by considering the time-limit of the client before the agent addresses a query.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums described herein are configured to transfer call context between different call center systems. For example, a first call center system that establishes a communication session between a user and an agent of the first system provides context determined during the session to a call context service. The service stores the context and provides it to other requesting call center systems. For instance, during a call transfer to an agent of a second system, the first system requests the service to provide a transfer number of the second system to which the user is to be transferred. The service determines the transfer number and provides it to the first system. The first system performs the call transfer using the number. After the transfer is complete, the second system provides a request for the context, and the service provides the context to the second system.

Abstract: A network device including a first data structure storing a set of buffer profile types. Each buffer profile type is associated with one or more configuration parameters. The network device further includes a second data structure storing a set of peer device identifiers, wherein each peer device identifier of the set of peer device identifiers is associated with a buffer profile type. The network device includes a buffer management application to receive first data associated with a first peer network device coupled via a first link to an interface component of the network device, determine the first data matches a first peer device identifier stored in the second data structure, and assign a first buffer profile type to the interface component of the network device, wherein the first buffer profile type is associated with the first peer device identifier in the second data structure.

Abstract: Methods for voice authentication include receiving a plurality of mono telephonic interactions between customers and agents; creating a mapping of the plurality of mono telephonic interactions that illustrates which agent interacted with which customer in each of the interactions; determining how many agents each customer interacted with; identifying one or more customers an agent has interacted with that have the fewest interactions with other agents; and selecting a predetermined number of interactions of the agent with each of the identified customers. In some embodiments, the methods further include creating a voice print from first and second speaker components of each interaction; comparing the voice prints of a first selected interaction to the voice prints from a second selected interaction; calculating a similarity score between the voice prints; aggregating scores; and identifying the voice prints that are associated with the agent.

Abstract: Techniques for sharing control of assigning tasks between an external pairing system and a task assignment system with an internal pairing system are disclosed. In one embodiment, the techniques may be realized as a method for sharing control of assigning tasks between an external pairing system and a task assignment system with an internal pairing system comprising receiving, from the task assignment system, a plurality of task pairing requests and an agent pairing request, wherein each task request of the plurality of task pairing requests is assigned to one of a first pairing strategy and a second pairing strategy. The agent pairing request may indicate an agent that is available for pairing. The method may further comprise transmitting, to the task assignment system, a pairing recommendation being based in part on the plurality of task pairing requests, the first pairing strategy, the second pairing strategy, and the agent pairing request.

Abstract: A computerized-method for operating an Omni Session Handling (OSH) engine for proactive OSH to determine that an outreach is required, according to one or more predefined requirements, to maximize capacity of an agent in a contact center by omni session handling, is provided herein. The computerized-method may retrieve one or more interactions from a Customer-Relations-Management database based on a requirement for an outreach to be stored in a queue of proactive contacts. The computer-implemented method may further allocate a queue of one or more interactions to an agent or to a team of agents and then present the agent with a digital preview of an interaction from the queue of one or more interactions for consideration via a display unit, while the agent is handling one or more interactions. The computer-implemented method may further receive from the agent a decision upon review of the presented digital preview of the interaction.

Abstract: Consolidating events to execute objects to extract, transform, and load data from source systems to a structured data store. An event manager process executing on a server runtime utilizes one or more event properties to determine which events can be consolidated to reduce unnecessary processor utilization.

Abstract: A determination is made that a real-time communication session (e.g., a voice call) between a first agent terminal and a customer communication endpoint has been placed on hold by a first contact center agent. An estimated hold time for the real-time communication is determined, based on a rule, in response to determining that the real-time communication session has been placed on hold. It is determined that the estimated hold time for the real-time communication session has expired. In response to determining that the estimated hold time for the real-time communication session has expired, one or more actions occur. For example, the real-time communication session is automatically transferred to a second agent terminal.

Abstract: A client application is specified by a target tenant and represented in an OAuth provider, along with a corresponding secret. A source tenant consents to permissions to be executed by the client application on a resource of the source tenant. A target service uses the secret to obtain an access token from an authorization server coupled to the source tenant and uses the access token to obtain access, specified by the permissions, to the resource served by a source service acting on behalf of the source tenant.

Abstract: A computer system includes a client-side presentation layer processor; a server-side service layer component including at least one application programming interface (API) controller, at least one repository pattern processor, and a data layer processor; and a back-end layer component comprising at least one structured query language (SQL) server and a cache, wherein the client-side presentation layer processor interprets conversational modes directed to dialogues programmed in the computer system.

Abstract: An example operation may include one or more of identifying an expiration date associated with an asset, creating a blockchain transaction identifying the asset and the expiration date, storing the blockchain transaction on a blockchain, identifying a requesting entity with a certificate permitting access to the asset, and providing the requesting entity with access to the asset provided the expiration date is still pending.

Abstract: A system includes a router to route an interaction by a customer to a contact center. A journey patience value is determined for the customer, where the journey patience value is based on a current journey stage of the customer. An action by the contact center is determined based on the determined journey patience value for the customer. The action is performed by the contact center based on the determined action.

Abstract: Methods and systems for automatically implementing contact center administration updates based on acceptance of a broadcast request are provided. In particular, a request can be broadcast to a target audience. Acceptance of the request by members of the target audience automatically implements changes defined in connection with the request for accepting agents. The broadcast request can be recalled under certain conditions. In addition, the action or actions implemented in response to the acceptance of the request can be undone under various conditions.

Abstract: Methods of predicting a change of users of a network enabled device and a network and network device configured to perform the methods. A present device category and a present device demographic profile are associated with the network enabled device. The present device category is one of a plurality of predefined categories each having a demographic profile associated therewith. The method includes: detecting a network event corresponding to the network enabled device; determining an event category corresponding to the detected network event, the event category being one of the plurality of predefined categories; and comparing the event category with the present device category. When the event category differs from the present device category, determining a new demographic profile based on the present device demographic profile and the demographic profile associated with the event category; and comparing the new demographic profile with the present device demographic profile.

Abstract: In one embodiment, systems and methods are disclosed for processing telemarketing calls to determine an abandonment rate (“AR”). An abandoned call exists if a telemarketing call is answered by a live person and an agent is not connected to the called party within two seconds of the called party completing their greeting. In order to comply with various federal regulations, a feedback mechanism allows feedback of the measured AR to be used by the predictive dialer to manage the AR for future calls to maximize efficiency and avoid exceeding an AR limit. In one embodiment, a speech analytics system processes audio recordings of previously made telemarketing calls and provides feedback to the predictive dialer so as to adjust a target AR rate for future calls.

Abstract: System and method to select a contact handling mode in a contact center, the method including: receiving, by a communication interface, a contact from a customer; calculating, by a processor of the contact center, an expected wait time by the customer based upon historical contact information stored in a memory of the contact center; calculating an expected cost of queueing the customer for the expected wait time; and selecting the contact handling mode based upon the expected cost of queueing the customer.

Abstract: The present disclosure includes a system and method for blended telephone network and computer network customer support interactions. The system may include a web server, one or more controllers, a telephone exchange, a monitoring server, and one or more client devices. The method may include receiving a multimedia support request, establishing a multimedia communications session, instructing a telephony application associated with the multimedia communications session to place a telephone call, routing and connecting the telephone call to an available endpoint, identifying the available endpoint when the telephone call is connected to the available endpoint, and transmitting an invitation to participate in the multimedia communications session to the available endpoint.

Abstract: Systems and methods for managing customer communications over communication channels are disclosed. According to one embodiment, a method for receiving consent from a customer to be contacted on the customer's cellular phone may include (1) communicating, over a first communication channel, with a customer; (2) using at least one computer processor, prompting the customer for customer consent to be contacted on the customer's cellular phone; (3) receiving, from the customer, a response to the prompt for customer consent; and (4) storing the response in a database.

Abstract: A system and method for managing customer communications over communication channels are disclosed. A method may include (1) at least one of a plurality of computer processors determining a communication channel for contacting a customer; (2) at least one of the plurality of computer processors determining contact information for the customer to be used with the determined communication channel; (3) presenting the contact information to an agent; (4) receiving, at an electronic device, authorization to initiate contact with the customer using the contact information; and (5) at least one of a plurality of computer processors automatically initiating contact with the customer using the communication channel.

Abstract: The present invention discloses a call center system and a call service implementation method thereof, wherein in the system, a Web access device is used for logging on an instant messaging server based on an instant messaging access of a user and sending instant messaging queuing information to a Computer Telephony Integration (CTI), and initiating an instant messaging request to a seat after receiving queuing result information returned by the CTI; the CTI is used for returning the queuing result information to the Web access device according to the received instant messaging queuing information and sending a Web access service beginning message to the seat; and the seat is used for accepting the instant messaging request initiated by the Web access device according to the received Web access service beginning message and performing an instant messaging.

Abstract: A method to shorten hold time experienced by callers to call centers by placing predictive calls into call centers in advance to obtain favorable queue positions, and release the most favorable queue positions to callers when they indicate desires to speak with call center agents by bridging their inbound calls to the favorable positions. Most favorable positions are usually the earliest predictive calls placed that are still in the queue. The method also includes other proactive tasks that may be required to navigate automated ACD or IVR call tree, maintain the active status of call queues to ACD or IVR, detect and treat possible improper disconnection, and detect and remediate premature disconnection between callers and agents.

Abstract: A contact center is provided that has (a) a database 114 operable to contain customer records; (b) a plurality of agent communication devices 134-1 to -N corresponding to a plurality of agents; (c) a switching fabric 110, 130 to connect incoming contacts with agent communication devices; (d) a plurality of contact queues 208a-n to enqueue contacts awaiting servicing by an agent; and (e) a queue bypass module that receives, from a first agent of a contact center, a queue bypass request for a specified first customer and updates a set of data structures associated with the specified first customer to indicate that the first customer is entitled to bypass queue positions when the first customer again contacts the contact center.

Abstract: An apparatus for controlling lifespan of interaction requests includes a processor and a memory, the memory storing instructions that when executed by the processor cause the processor to detect when an interaction request is being initiated for send from a communications appliance, server, or system, activate an interface on the appliance, server, or system for configuring a time to live (TTL) for the interaction request, cause, via the configuration, the interaction request to expire if not answered within the TTL life span, and cause, via the configuration, the TTL constraint applied to the interaction request to be lifted if the interaction is answered within the TTL life span.

Abstract: The solution described herein provides an innovative use of remote services technology integrated with service personnel onsite at the point of service, such as a consumer repair outlet, to provide a pool of technical support resources to service a widely distributed resource need, such as support and repair resource needs of a chain of consumer outlets or an aggregated group of single proprietor consumer outlets. With this solution, qualified technical resources are provided from a central location to service a widely distributed retail environment. This is on-demand online remote support service is called or referred to as “support from a spigot.” The distribution method enables the delivery of higher quality, more reliable and overall lower cost services. Instead of requiring dedicated technical resources at each location, lower skilled labor may be deployed at the location to enable the remote technical support services process.

Abstract: Systems and methods are described for processing calls. A call is received at a softswitch or other call processing system from a caller intended for a first subscriber. The first call is associated with signaling information, the signaling information including a phone number associated with the caller. A determination is made as to whether the first subscriber has previously received a call associated with the caller phone number at the softswitch. If the first subscriber has not previously received a call associated with the caller phone number at the softswitch, a first message is played to the caller. An indication that the first message was played to the caller is stored in association with an account record associated with the first subscriber.

Abstract: A web-based hosted solution through which business entities create and manage communications campaigns is described. To reduce latency of customer-to-agent connections, the system implements an agent stay-on-line function by which a persistent telephony connection is established and maintained between the system infrastructure and an available agent. In this manner, the agent may handle multiple customers while avoiding an ACD hold queue. In addition, preferably a service-side hold queue also is established and maintained on the service-side of the infrastructure. This hold queue maintains calls that are waiting to be connected to available agents. It ensures that any customer abandons do not impair the connections being established and maintained to the agents.

Abstract: In one embodiment, systems and methods are disclosed for processing telemarketing calls to determine an abandonment rate (“AR”). An abandoned call exists if a telemarketing call is answered by a live person and an agent is not connected to the called party within two seconds of the called party completing their greeting. In order to comply with various federal regulations, a feedback mechanism allows feedback of the measured AR to be used by the predictive dialer to manage the AR for future calls to maximize efficiency and avoid exceeding an AR limit. In one embodiment, a speech analytics system processes audio recordings of previously made telemarketing calls and provides feedback to the predictive dialer so as to adjust a target AR rate for future calls.

Abstract: Systems and methods that employ contact escalation periods as criterion for managing routing procedures of a contact center. A prediction component can predict when a customer is likely to escalate a contact that is forwarded to a contact center, and hence facilitate resource matching based on such prediction. Accordingly, proactive and anticipatory contact interaction is enabled, wherein routing of contacts occur in-part based on predicted likelihood of escalations.

Abstract: A web-based hosted solution through which business entities create and manage communications campaigns is described. To reduce latency of customer-to-agent connections, the system implements an agent stay-on-line function by which a persistent telephony connection is established and maintained between the system infrastructure and an available agent. In this manner, the agent may handle multiple customers while avoiding an ACD hold queue. In addition, preferably a service-side hold queue also is established and maintained on the service-side of the infrastructure. This hold queue maintains calls that are waiting to be connected to available agents. It ensures that any customer abandons do not impair the connections being established and maintained to the agents.

Abstract: A method may include receiving, at a first call center, a call from a caller, forwarding the call to an agent workstation and determining that the call must be transferred. The method may also include providing, at the agent workstation, a user interface identifying a number of items associated with possible reasons for the call and receiving, via the user interface, input selecting one of the items. The method may further include appending information to the call based on the received input and forwarding the call with the appended information to a network device associated with a number of call centers.

Abstract: The present disclosure includes a system and method for blended telephone network and computer network customer support interactions. The system may include a web server, one or more controllers, a telephone exchange, a monitoring server, and one or more client devices. The method may include receiving a multimedia support request, establishing a multimedia communications session, instructing a telephony application associated with the multimedia communications session to place a telephone call, routing and connecting the telephone call to an available endpoint, identifying the available endpoint when the telephone call is connected to the available endpoint, and transmitting an invitation to participate in the multimedia communications session to the available endpoint.

Abstract: This disclosure relates to using agent queues for a contact center. An agent queue profile includes parameters to configure an agent queue for each agent that is assigned to the agent queue profile. An agent queue profile manager is programmed to assign a given agent to the agent queue profile to define a corresponding agent queue for the given agent. The agent queue profile manager can also define parameters for the agent queue profile. A distribution module can control distribution of a transaction in the corresponding agent queue based on rules and can control handling of the transaction in the corresponding agent queue based on the agent queue profile.

Abstract: A method of managing incoming calls is disclosed and includes receiving a telephone call. Further, the method includes offering a caller a bypass option to bypass an automated help application and placing the telephone call in a queue for a next available customer service agent. The method can also include prompting the caller for payment when the caller selects the bypass option. Further, the method can include indicating a current wait time when the bypass option is declined. Moreover, the method can include offering the caller an instant service option to directly connect the caller to a customer service agent. The method can also include prompting the caller for payment when the caller selects the instant service option and directly connecting the telephone call to a customer service agent.

Abstract: The problem of an automated telephony system having only a single way to measure a caller's difficulty in processing a transaction when using the system is solved by selecting from multiple thresholds for measuring the caller's difficulty. Having a choice of alternative thresholds to measure the caller's difficulty, referred to as inefficiency thresholds, allows for a more responsive approach to managing an automated telephony system. This choice of inefficiency thresholds overcomes multiple problems of systems only using one inefficiency threshold, such as: (1) transferring a call to a live agent too quickly, (2) transferring a call to a live agent too slowly, and (3) giving a caller a feeling that the automated telephony system is unresponsive to his or her needs. Having multiple inefficiency thresholds allows for a more dynamic response to a diverse audience of callers and serves different needs of a caller during various parts of a call.

Abstract: Methods for enabling call center agents to adapt their servicing of incoming calls based on the estimated value of the calls are disclosed. In accordance with the first illustrative embodiment, when there is a “high-value” call waiting in the queue while one or more agents are currently servicing lower-value calls, an agent who is servicing a lower-value call is informed that there is a higher-value call waiting in the queue, and is prompted to provide an estimate of how much longer he or she will be servicing his or her current call. The call center system selects which agent the high-value call will be routed to based on: (i) the agents' responses to the prompts, and (ii) for each of the responding agents, a measure of how closely prior responses from the agent compared to the actual amount of time taken by the agent to complete servicing the call.

Abstract: Systems and methods for providing adaptive estimated wait time predictions for work items are provided. More particularly, a processor-enabled module may select a best estimated wait time algorithm from among a plurality of estimated wait time algorithms that meets the accuracy and calculation resource conditions of a contact center based on rules. Furthermore, the conditions of a contact center may change at times and as a result the selection of which estimated wait time algorithm is considered best will adapt to suit the contact center change. In addition, the selected best estimated wait time prediction can be provided to client communication devices.

Abstract: A system and method for balancing call session assignments on an agent console is provided. Incoming call sessions and one or more agent consoles, each managed by an agent, are monitored. An absolute upper limit on a number of the call sessions allowed at each agent console at any given time is assigned. A load of call session assignments is balanced on each agent console. Objective conditions regarding call sessions already assigned to each agent are collected. Subjective conditions regarding the agent's opinion of a current call session are also collected. The objective and subjective conditions are evaluated against the absolute upper limit to determine a load factor. Each incoming call session is assigned to one such agent console based on the load factor.

Abstract: Embodiments of the invention are directed to a system and method for routing interactions. A method may include receiving a message related to the interaction. Text included in the message may be analyzed. A destination may be selected for the message based on analysis of the text. The message may be routed to the selected destination.

Abstract: The present invention is directed to a method for servicing a transaction in a contact center. When an instant message communication associated with a transaction is suspended prematurely, special treatment may be provided to the transaction initiator. The special treatment includes: (a) maintaining the assigned service priority for the transaction for assignment to a subsequent communication; (b) scheduling a subsequent outbound instant message to an external endpoint associated with the transaction initiator; (c) assigning to the transaction initiator a favored service priority when the subsequent inbound instant message is received by the contact center; and (d) maintaining previously selected item(s) in memory and providing the item(s) to the transaction initiator in a subsequent communication.

Abstract: A method of exchanging messages, which are intended for streaming connection with a source device, in a sink device of a wireless network comprises transmitting a connect request message for data streaming to the source device; receiving a connect response message from the source device, the connect response message including connection information indicating the possibility of connection with the source device; and outputting a user interface indicating at least one of the connection information included in the connect response message and wait time information required for connection with the source device, on a display module.

Abstract: The present invention, in one embodiment, is directed to an agent available notifier 250 that (a) receives a request from the first customer, but not from the second customer, to be notified when the first contact is eligible for servicing by a selected resource so that the first customer is free to perform a desired activity and (b) in response to the first customer's request, provides the first customer with a selected notification that the first contact is eligible for servicing, wherein the second customer is not provided with the selected notification when the second contact is eligible for servicing.

Abstract: A certain embodiment of the invention discloses a processing method and device for timeout of a queuing request. The method comprises the steps of: after a first queuing request in a waiting queue is timeout, setting the first queuing request to be in a queuing-paused state, and prompting a timeout (S302); obtaining a second queuing request (S304); determining that a call requested, by the second queuing request, to be accessed is the same as a call requested, by the first queuing request, to be accessed (S306); and inserting the second queuing request into the waiting queue (S308). Through a certain embodiment of the invention, the original queuing position advantage of a user can be effectively maintained, and the user experience and the system performance can be improved.

Abstract: A routing system includes a router, a statistics server (Stat Server) coupled to the router, receiving, processing and storing statistics related to event handling, and providing information regarding the statistics for use by routing intelligence in the router, and a first proxy data server coupled to the Stat Server and to a second proxy data server at a remote contact center over a network. The system is characterized in that the Stat Server receives event statistics regarding the local queue, and through the coupled first and second proxy data servers, event statistics regarding the remote queue, provides information related to the statistics to the router, and the router determines to route incoming events to local queue or to the remote queue based on the information provided.