Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for analyzing an audio to capture semantic and non-semantic characteristics of the audio and corresponding relationships between the semantic and non-semantic characteristics. In particular embodiments, the audio is segmented into a set of utterance segments containing a party speaking on the audio and a set of noise segments containing the party not speaking on the audio. The semantic and non-semantic characteristics are then captured for each of the utterance segments. Specifically, speech analytics is performed on each segment to identify the words spoken by the party in the segment as semantic characteristics. Further, laughter, emotion, and sentence boundary detection is performed on each segment to identify occurrences of such in the segment as non-semantic characteristics.

Abstract: A secure payment agent assist (“SPAA”) feature provides assistance to a contact center agent during a transaction involving sensitive information, where the sensitive information provided by the remote party is maintained in secure manner, so that the agent is not exposed to it. The agent is assisted by being provided with a pop-up window that allows the agent to invoke a “recollect” and “cancel” function during the transaction. The pop-up window also provides information to the agent making the agent aware of the progress of the transaction as the remote party interacts with an interactive voice response (“IVR”) unit. In other embodiments, a configuration parameter allows the prompts for the payment information to be provided by the agent or the IVR.

Abstract: A call handler is configured to originate calls using records stored in a contact list by using various campaign call data comprising a set of calling party numbers or “ANIs” that are to be used when originating calls. Each ANI is associated with a status, which reflects whether a terminating voice service provider has blocked a prior call using that ANI. The call handler is configured to recognize when a call is blocked by examining SIP protocol-based error codes and/or intercept announcements provided by the carrier when the call is blocked. Upon detecting the call is blocked, the call handler will update the status of that ANI and select another ANI value from the campaign call data to use for subsequent call originations of that campaign. A set of ANIs that a carrier has blocked may be stored to facilitate subsequent redress with that carrier.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for handling a call reaching a party's voicemail. A predictive model is used to generate a first probability of an outcome occurring as a result of leaving a voicemail message and a second probability of the outcome occurring as a result of sending a text message. If the first probability is greater, an IVR uses DTMF tone(s) to bypass a greeting on the voicemail so that a message can be recorded with minimal time. If the second probability is greater, the call is ended and an email is sent to the party's service provider using an email address comprising a mobile number for the party and a domain portion specific to the provider. As a result, the provider delivers a text message to the party with the body of the message including the content of the email.

Abstract: A dialing list comprising call records can be processed by a call handling component(s) in a contact center in various dialing modes. A call record may be processed to originate a voice call, where the agent manually dials the call as a voice telephone call. In another embodiment, one or more call records can be processed to originate a SMS text call or group text call, where the agent also determines when the call(s) originates. The agent is presented with a graphical user interface tailored to the dialing mode. The dialing mode used may be defined by the dialing list the call record is retrieved from, information from within the call record itself, application of a rule, or input from the agent. The dialing mode may be altered under certain conditions. When the call is originated, various compliance oriented tests, including calling windows and call attempts, are performed.

Abstract: An enhanced abandoned call recovery (“E-ACR”) process allows certain abandoned calls to be eligible for a callback call. An E-ACR assignment point defines which abandoned calls in an inbound campaign or interactive voice response (“IVR”) menu are eligible to be processed to determine whether the E-ACR callback should occur. The determination of whether a callback occurs involves various compliance tests, such as ensuring calling window, call attempts, and other regulatory concerns are addressed. Once a callback is determined to occur, it is associated with a specific campaign to ensure the called party is provided with agents having the skill set as defined for that assignment point. In this manner, only eligible callers receive an E-ACR callback, and further receive the callback in a compliant manner and handled by the same skill set of agents as would have been allocated to the caller had they not abandoned their call.

Abstract: A call blocking module in a smartphone is configured to generate a whitelist stored in the smartphone, the whitelist comprising a calling party number (“CPN”) using various number sources, such as a contact list, outgoing call list, or incoming call list. As each number source is modified with a new CPN, the whitelist may also be augmented automatically, or based upon a confirmation from a user of the smartphone. A contact center originating voice calls to the smartphone may be configured to generate a text call to the smartphone in order to populate the whitelist with the CPN that will be used when originating a subsequent voice call to the smartphone. Thus, the contact center can originate a text call to the smartphone to potentially increase the likelihood that a subsequent voice call will be passed by the whitelist.

Abstract: A dialer in a contact center is managed by a Communication Attempt Management System (“CAMS”) for tracking the total number of communications attempts, including voice calls, originated to an individual within a period of time. A list comprising account data of a plurality individuals may be processed by the CAMS to identify those accounts exceeding a weekly limit on the number of allowable communication attempts and are not authorized to receive further communications in that period of time. The list is modified to reflect those accounts which have not exceeded their corresponding limit and are authorized to be contacted. The modified list is provided to the dialer, which then originates a call to each account. The CAMS may then update each account to reflect each communication attempt made by the dialer and whether the communication is considered exempt or non-exempt with respect to the communication limits.

Abstract: A call handler in a contact center is configured to temporarily derogate the skill level of one or more agents in a group having a common skill. During the time period of derogation, incoming calls will be routed to agents with the highest skill level, such that the normally lower skill level agents will be selected to receive calls. If there are more than one agent meeting this criteria, then the agent that has been waiting the longest to receive a call is selected. This allows the lower skill level agents to gain experience in handling calls and improving their call handling capabilities. After a set threshold, the derogation of the agents is terminated, and their skill level is restored to the pre-derogation level. In this manner the lower skill level agents are given limited opportunities for improvement by handling calls.

Abstract: Various embodiments of the invention provide methods, systems, and computer program products for sending an outbound communication to a party to generate an inbound communication from the party for a contact center. An expected response time is derived identifying a time the inbound communication is expected to be received from the party after sending the outbound communication to the party. In particular instances, an agent is identified who is expected to be available at the expected response time to handle the inbound communication when it is received by the party at the contact center. In addition, the content of the outbound communication may be composed to identify the agent to the party. Accordingly, the outbound communication is sent to the party so that the inbound communication can be routed to the agent upon being received.

Abstract: Various processes are defined associated with customer-initiated text messages to a contact center to delineate various sessions between the customer and an agent. The sessions are defined in part using various timers, including a customer response timer that is stopped upon receipt of a customer text and started typically started when the agent response is sent. The session is initiated upon the initial customer text and the expiry of the customer response timer defines the end of a particular session with the customer. Various data structures are created or updated upon the beginning of a session, including tables which may define which sessions a customer previously had and the messages associated with each session. The agent may be able to review prior sessions for a given customer and can review the specific messages of a prior session.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for converting a connection string configured to use a first API to connect to a data source of a data source type to using a second, different API to connect to the data source. The data source type is identified as being associated with the string and the string is parsed and stored in a key-value dictionary. An object is instantiated for a subclass designed for the data source type. This subclass inherits from a base class that includes an abstract version of a method defined for the second API and the subclass includes a non-abstract version of this method. A string is generated by calling the method associated with the object, causing the non-abstract version to be executed, which uses the dictionary to generate the string configured to use the second API to connect to the data source.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for analyzing an audio to capture semantic and non-semantic characteristics of the audio and corresponding relationships between the semantic and non-semantic characteristics. In particular embodiments, the audio is segmented into a set of utterance segments containing a party speaking on the audio and a set of noise segments containing the party not speaking on the audio. The semantic and non-semantic characteristics are then captured for each of the utterance segments. Specifically, speech analytics is performed on each segment to identify the words spoken by the party in the segment as semantic characteristics. Further, laughter, emotion, and sentence boundary detection is performed on each segment to identify occurrences of such in the segment as non-semantic characteristics.

Abstract: Technologies are disclosed for determining a best time to send a text message to a party over a plurality of contact periods of time to achieve having the party respond to the message with a desired outcome and/or result. Various embodiments of the invention involve determining, for each period of time, an amount of time the party is expected to take to respond to the text message, a cost of sending the message, and a probability of the party responding with the desired outcome and/or result as a result of sending the message during the period of time. A contact attempt value is determined for each period of time based on these variables along with a desirability of sending the message to the party during the period of time. Accordingly, the best time to send the message is identified as the period of time having the highest contact attempt value.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for handling a call reaching a party's voicemail. A predictive model is used to generate a first probability of an outcome occurring as a result of leaving a voicemail message and a second probability of the outcome occurring as a result of sending a text message. If the first probability is greater, an IVR uses DTMF tone(s) to bypass a greeting on the voicemail so that a message can be recorded with minimal time. If the second probability is greater, the call is ended and an email is sent to the party's service provider using an email address comprising a mobile number for the party and a domain portion specific to the provider. As a result, the provider delivers a text message to the party with the body of the message including the content of the email.

Abstract: Agents are coached to improve their performance by participation in a speech coaching campaign. In one embodiment, an administrator identifies top and bottom performing agents, and retrieves their voice call recordings that are processed by a speech analytics system to produce word clouds corresponding to desirable and undesirable phrases. After reviewing and potentially editing the word clouds, a set of desirable and undesirable operational phrases are created, which the agent should use, or not use, during a call. A speech analytics system is configured to detect the presence of these operational phrases for an agent when the agent is on a call. The agent may review information depicting how well they are utilizing the desirable phrases and avoiding the undesirable phrases, and points may be allocated reflecting the agent's usage. The points may be processed by a gamification system to incentivize the agent to improve their performance.

Abstract: A dialing list comprising call records can be processed by a call handling component(s) in a contact center in various dialing modes. A call record may be processed to originate a voice call, where the agent manually dials the call as a voice telephone call. In another embodiment, one or more call records can be processed to originate a SMS text call or group text call, where the agent also determines when the call(s) originates. The agent is presented with a graphical user interface tailored to the dialing mode. The dialing mode used may be defined by the dialing list the call record is retrieved from, information from within the call record itself, application of a rule, or input from the agent. The dialing mode may be altered under certain conditions. When the call is originated, various compliance oriented tests, including calling windows and call attempts, are performed.

Abstract: A communications handler receiving incoming communications determines an appropriate contact center agent to receive the communication and modifies a graphical user interface (“GUI”) to notify the agent of the incoming communication. A plurality of communication session indicators provide status information for various communication sessions, and allow the agent to select one of several simultaneous communication sessions, which in turn alters the GUI to present information about that selected communication session. By selecting the corresponding communication session indicator, the agent can replace information for one communication session with another. The communication session indicators are updated to reflect the corresponding status of the communication session. The communication sessions include voice and non-voice channel types, wherein the non-voice channel types may include chat sessions, text sessions, and email sessions.

Abstract: Various embodiments of the invention provide methods, systems, and computer program products for handling poor voice quality being experienced by a remote party on a call. In various embodiments, an assessment is received from the party at an IVR on the voice quality of the call. Accordingly, data is collected for one or more parameters associated with at least one of audio of the call and a network used to carry the audio of the call in response to the party experiencing poor voice quality. At this point, a predictive model is used to predict at least one cause for the poor voice quality. Here, the data collected for the one or more parameters is provided as input to the predictive model. Accordingly, one or more actions are taken to attempt to address the at least one cause and improve the voice quality on the call for the remote party.

Abstract: A communications handler receiving incoming communications determines an appropriate contact center agent to receive the communication and modifies a graphical user interface (“GUI”) to notify the agent of the incoming communication. A plurality of communication session indicators provide status information for various communication sessions, and allow the agent to select one of several simultaneous communication sessions, which in turn alters the GUI to present information about that selected communication session. By selecting the corresponding communication session identifier, the agent can replace information for one communication session with another. The communication session indicators are updated to reflect the corresponding status of the communication session. The communication sessions include voice and non-voice channel types, wherein the non-voice channel types may include chat sessions, text sessions, and email sessions.