Abstract: A method for summarizing dialogs may include obtaining an agent text stream and a customer text stream, segmenting the agent text stream and customer text stream into sentences, and labeling sentences associated with the segmented agent text stream and the segmented customer text stream. The method may further include extracting sentences from the agent text stream and the customer text stream based upon frequencies of appearance of words and terms of interest; generating an agent summary paragraph based on the extracted sentences from the agent text stream, and generating a customer summary paragraph based on the extracted sentences from the customer text stream. The method may identify keywords associated with each of the agent summary paragraph and the customer summary paragraph.

Abstract: The distribution of incoming queries to a customer interaction center agent group is parallel processed amongst agents of that group to improve queue wait times. A threshold number of queries that may be processed by agent devices associated with the agent group at a given time are defined based on a number of agents of the agent group that are available at the given time. In response to determining that the number of queries is satisfies the threshold number of queries based on the number of agents that are available at a current time, a number of queries awaiting processing are distributed to one or more agent devices of the agent group. The threshold number of queries may be based on half of the number of agents that are available at the given time.

Abstract: Apparatuses and methods concerning routing and processing of calls in a server are disclosed, and involving a processing circuit communicatively coupled to a server that routes calls (e.g., data communications) for a plurality of end-users and generates call event messages for the routed calls. The processing circuit generates call summary data and evaluates the call summary data to identify a set of incoming calls to the server that were missed and have not been returned by the end-users. Certain of the calls are checked relative to a secondary data source and respective priorities for the set of incoming calls are ascribed for further processing, and some having a higher priority.

Abstract: A system may separate a transcript of a conversation into a first section corresponding to a first speaker in the conversation, and a second section corresponding to a second speaker in the conversation. The system may process, based on delimiters and punctuation marks, the first section and the second section to form a first speaker transcript and a second speaker transcript; determine, based on one or more topic models, a first set of key terms associated with the first speaker transcript and a second set of key terms associated with the second speaker transcript. The system may generate, based on a common set of key terms associated with the first set and the second of key terms, a first transcript summary of the first speaker transcript and a second transcript summary of the second speaker transcript; and generate a summary based on the first and the second transcript summaries.

Abstract: A system includes a router to route a call to agent stations, processor and a memory. The memory stores instructions, which when executed by the processor, causes the processor to identify the call as a callback, identify an available agent station at a same site as the router if the call is a callback, and establish the callback with the available agent station at the same site as the router where the callback is initiated.

Abstract: A centralized and robust threat assessment tool is disclosed to perform comprehensive analysis of previously-stored and subsequent communication data, activity data, and other relevant information relating to inmates within a controlled environment facility. As part of the analysis, the system detects certain keywords and key interactions with the dataset in order to identify particular criminal proclivities of the inmate. Based on the identified proclivities, the system assigns threat scores to inmate that represents a relative likelihood that the inmate will carry out or be drawn to certain threats and/or criminal activities. This analysis provides a predictive tool for assessing an inmate's ability to rehabilitate. Based on the analysis, remedial measures can be taken in order to correct an inmate's trajectory within the controlled environment and increase the likelihood of successful rehabilitation, as well as to prevent potential criminal acts.

Abstract: An architecture and process flow for a system that processes event notifications from a speech analytics system for the purpose of controlling the recording of calls in a contact center for various contexts. Based on the regulatory context of the call, call recording may require requesting and receiving consent from the remote party to record the call. A speech analytics system operating in conjunction with an event handler module and a call recording application specific module can facilitate automatically recording the call and minimize agent intervention. The application specific module may provide icons and text on the agent's display to remind or inform the agent of the context and various conditions. The application specific module may also control various recording equipment.

Abstract: Disclosed are a system and methods to enable the interactive management of incoming and outgoing communications in an automated or manual fashion.

Abstract: An architecture and process flow for a contact center that receives payments prevents the agent from hearing sensitive financial information during the payment transaction. During a call with a remote party, the agent determines an appropriate time to bridge on a bank card payment processing system to receive and process a payment. Audio of the call to the agent is then interrupted so as to avoid the agent hearing any sensitive financial information provided by the remote party. A speech analytics system (“SAS”) is bridged onto the call and monitors the payment transaction. The SAS provides status indications displayed to the agent so that the agent is able to monitor the progression of the payment transaction without hearing the contents of the call. The SAS determines when the payment transaction has completed and causes the agent audio to be restored.

Abstract: An electronic device displays a first row in a multitasking user interface that includes a plurality of representations of open applications. The device concurrently displays a second row that is spaced apart from the first row and includes application icons for the open applications. While concurrently displaying the first row and the second row, the device detects a first input that corresponds to movement in a second direction. In response, the device moves the respective representation out of the first row in the second direction in accordance with a progression of the first input without moving the application icon for the respective application in the second direction. When application-close criteria have been met for the respective application by the first input, the device closes the respective application, ceases to display the respective representation in the first row and ceases to display the application icon in the second row.

Abstract: The present invention provides systems and methods for controlling signaling data transmitted over a communication system between a first party and a second party. The system comprises a first communication channel configured to carry communication data, wherein the communication data comprises the content of the communication between the first party and the second party; a second communication channel configured to carry signaling data, wherein the signaling data comprises data relating to the first communication channel and sensitive data transmitted by the first party; a signaling processor configured to receive the signaling data from the first party via the second communication channel, modify the signaling data to remove or replace at least some of the sensitive data in the signaling data, and transmit the modified signaling data via the second communication channel to the second party.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for identifying an occurrence during a conversation being conducted between a first party and a second party where sensitive information is conveyed by the first party or the second party. In particular embodiments, speech analytics is used to monitor audio of the conversation and a first speech characteristic is detected indicating a start event identifying a start of an occurrence where sensitive information is conveyed by the first party or the second party. Following the detection of first speech characteristic, a second speech characteristic is detected in the audio indicating an end event identifying an end of the occurrence. Accordingly, identifiers for the start and end events are then recorded in various embodiments as metadata along with a recording of the audio of the conversation to identify where in the recording the occurrence takes place.

Abstract: A method for tracking at least recent contacts and favorite contacts across multiple communications services may include collecting, by a processor, information associated with a plurality of contact interactions of a user from each of a set of different communications services utilized by the user. The method may also include storing, by a storage device, the information associated with each of the plurality of contact interactions. The method may additionally include analyzing the information associated with each of the plurality of contact interactions. The method may further include determining at least one of a list of most recent contacts and a list of favorite contacts from analyzing the information associated with each of the plurality of contact interactions.

Abstract: A method for tracking at least recent contacts and favorite contacts across multiple communications services may include collecting, by a processor, information associated with a plurality of contact interactions of a user from each of a set of different communications services utilized by the user. The method may also include storing, by a storage device, the information associated with each of the plurality of contact interactions. The method may additionally include analyzing the information associated with each of the plurality of contact interactions. The method may further include determining at least one of a list of most recent contacts and a list of favorite contacts from analyzing the information associated with each of the plurality of contact interactions.

Abstract: A mixed workload management system and associated operating method modify a shortest job first (SJF) by service levels. The workload management system comprises a scheduler configured for scheduling mixed workloads. The scheduler comprises an analyzer that determines query execution time, assigns scheduling priority to a query in order inverse to the query execution time, weights the assigned scheduling priority by service level of the query, and sorts a list of queries in order of weighted scheduling priority. A schedule controller selects a query for execution from head of the sorted list of queries.

Abstract: A contact center dialing a telephone number to a destination party, such as a debtor, may discover that the number is subject to a prohibition of being autodialed. In other embodiments, a number that was subject to the prohibition of being autodialed is now discovered to no longer be subject to such prohibition. Various mechanisms may be defined to indicate how such a prohibition associated with the number may be indicated in a dialing list and how various contact center architectures may be used to process the dialing list. In one embodiment, separate sub-systems are used to dial separate dialing lists based on whether the number is to be manually dialed or dialed using an autodialer. In another embodiment, another architecture is used to process an integrated dialing list to determine whether a number is to be manually dialed or autodialed.

Abstract: A contact center dialing a telephone number to a destination party, such as a debtor, may discover that the number is obsolete, e.g., the number has been reassigned to a new subscriber. A purportedly current number (called a ‘skip-trace’ number) may be obtained for the debtor, which may be a wireless number. Until the wireless skip-trace number has been confirmed as being associated with the debtor, an agent manually dials that number to minimize liability to the contact center. Once the agent has verbally confirmed the skip-trace number is associated with the debtor, a record for this number in a dialing list is updated allowing future dialing attempts to occur automatically, by using a predictive dialer. In one embodiment, a dialing list module processes the dialing list so as to detect when a number is obsolete and update the corresponding record when the number is confirmed.

Abstract: Systems and methods for recording a communication session between a customer and an agent of a customer center communication system are provided. In this regard, a representative method comprises: configuring a communication component of the customer center communication system to enable recording of a media stream associated with the communication session; transmitting the media stream over a network based on the configuration of the communication component; receiving the media stream over the network; and recording the received media stream.

Abstract: An apparatus and methods for a call routing system is disclosed whereby the call routing service provider is associated with a series of partners. By providing a system supporting not only the main user, but also the partners, efficiencies are gained through cost-spreading. Agents can be qualified to field calls for multiple business entities. Cross-selling and proactive servicing based on caller demographic and profile data can be effectuated. The system employs a centralized or global bank of shared Interactive Voice Response (IVR) units so that unnecessary post-routing and call site interflow are reduced. The system comprises a central server system that interfaces with a long distance provider so that route requests are received, caller data is retrieved from one or more databases, routing and handling strategies are developed, load balancing is effectuated, and calls are appropriately routed to one of a plurality of geographically separated call center systems with queues staffed by agents.

Abstract: A system and method for maximizing efficiency of call transfer from being between a customer and a dialing agent, to being between the customer and a talker is provided. The method contains the steps of: entering a dialing agent and a talker into a campaign to maintain direct communication with the dialing agent and with the talker; calling a customer via use of a dialing agent device; receiving from the dialing agent a request to transfer a connected customer from communicating with the dialing agent to communicating with a talker; and after receiving the request to transfer, transmitting an identification of a customer record associated with the connected customer to a talker computer for identifying the customer record, where the customer record has been previously stored on the talker computer prior to receiving the request to transfer.

Abstract: Methods, systems, and computer-readable media consistent with the present invention manage multiple telephone calls by managing a session record associated with the call, amending the session record according to a plurality of rules to reflect a plurality of instructed actions, evaluating an amended session record to derive at least one of the plurality of instructed actions, and implementing a derived instructed action on the call under the control of an automated apparatus.

Abstract: An automated call center that stores state information for callers. When a caller contacts the call center, an identification is determined for that caller. The caller's number may be used as the identification. A database if checked to determine whether a data record exists for that caller. If so, data record is pulled and a caller asset receives the call along with information in the data record. If this is the caller's first call, or first call after a predetermined time period, the a new data record may be created in the database. The caller may be prompted with a series of menu choices that enable the caller to select a caller asset. The call center may record all entries and inputs by the caller and caller asset in the data record.

Abstract: System and method for recording communication sessions in a peer-to-peer communication networks. A conference call may be established between an external end-device, a target agent end-device of a call center and a recorder over a peer-to-peer communication network. After the conference call is established, the recorder may receive media transferred between the external end-device and the target agent end-device and record that media.

Abstract: Various embodiments of the invention provide methods, systems, and computer-program products for determining whether and how to record voice calls, or portions thereof, for calls processed by a contact center. Calls can be classified as being in a context that is either single-party consent or dual-party consent depending on whether the call is inter-state or intra-state and which state(s) are involved. In one embodiment, the contact center may access tables that indicate for a telephone number whether the call involves a state that adheres to a single-party consent regime or a dual-party consent regime. A speech analytics system may further be used to ascertain whether aural consent is provided by the remote party, or whether the agent properly requested and responded to the remote party's response. Depending on the context, all parties, one party, or no parties may be recorded.

Abstract: The present invention provides a system, method, and computer program product for automatically detecting any unnecessary repetition by customers of specific types of information in a multi-channel (e.g., self-service application, IVR system, live agent center) customer service session. For each channel used in the customer service session, the information provided by the customer in the channel is recorded in a log, transcription, or other record. The record(s) for the customer service session are subsequently parsed for specific types of information provided by the customer. From the parsed records, specific types of information provided by the customer in two or more channels during the customer service session are identified. In one embodiment, the results are analyzed to determine if providing such information in two or more channels is redundant, and, if so, this is counted as a redundancy.

Abstract: A system and method for recording and distributing calls are provided. A call may be associated with an information record. Parameters in the information record may be used to determine if the call is to be recorded. Parameters in the information record may be used to determine a method of providing a recording of the call. Other embodiments are described and claimed.

Abstract: A system and method for processing interaction requests includes a computer system that receives over a data channel from an end user device accessible to the customer, a request for an interaction. The request includes data from an application running on the end user device. The data is stored by the computer system upon receipt. When a voice call from a telephony device accessible to the customer is received, a voice media session is established with the telephony device over a voice channel. The data is identified based on information associated with the voice call. A contact center resource is further identified for routing the voice call. The data is attached to a request to route the call to the identified contact center resource.

Abstract: A computing device may receive a record order from a client device. The record order may include recording instructions for a communication session involving an interactive voice response recording system. The computing device may provide the record order to the interactive voice response recording system and, in response to providing the record order to the interactive voice response recording system, receive record metadata corresponding to the communication session and store the record metadata locally. The record metadata may include a storage location of record data corresponding to the communication session, and the record data may include a recording of the communication session.

Abstract: In a method for recording telephone conversations between a subscriber to a service provider and a telephone conversation partner, the subscriber dials the number of the service provider and interacts with a menu-driven IVR user interface, entering his subscriber number as well as a corresponding PIN-number to authenticate himself. After the verification, the subscriber can chose one or more of the following options: (a) listen to one or more of his previously recorded telephone conversations, (b) delete one or more of his previously recorded telephone conversations, (c) arrange that all incoming and outgoing calls are to be automatically recorded, (d) deactivate the setting that all incoming and outgoing calls are automatically recorded, and/or (e) record the next telephone conversation. At the beginning of each conversation to be recorded, the service provider informs the telephone conversation partner, via a warning voice message, that the telephone conversation will be recorded.

Abstract: A system and method is provided for automatically generating an interactive voice response (IVR) application flow from recorded audio files of calls to or from an IVR system. The method includes identifying an IVR state sequence for each of a plurality of calls from recorded audio files of the calls. The N most common state sequences are identified for the IVR system for the plurality of calls. An application flow is then displayed for the IVR application using the N most common state sequences.

Abstract: A device may receive a history of call volumes and statistics for a call queue. The device may also receive, for each of a number of agents that are associated with the call queue, a work schedule. The device may determine a projected call occupancy for the call queue based on the history of call volumes for the call queue and the work schedules; select a subset of agents, among the number of agents that are associated with the call queue, that are not needed to handle calls in the call queue during a time for which projected call occupancy is below a first threshold; and assign tasks, for the time, to the subset of agents.

Abstract: A system and method for handling a call made to a contact center after a prior call from the same caller was disconnected. In exemplary embodiments, a caller who was connected to an agent during the previous call may be placed in a routing path for the same agent, a caller who had provided information to the system during the previous call may not be required to provide the information again, and a caller who was in a routing path waiting for an agent may be placed ahead of other callers who have spent less time in the routing path.

Abstract: A system and method for automatic call segmentation including steps and means for automatically detecting boundaries between utterances in the call transcripts; automatically classifying utterances into target call sections; automatically partitioning the call transcript into call segments; and outputting a segmented call transcript. A training method and apparatus for training the system to perform automatic call segmentation includes steps and means for providing at least one training transcript with annotated call sections; normalizing the at least one training transcript; and performing statistical analysis on the at least one training transcript.

Abstract: A method may include receiving a call from a caller and determining whether the caller has previously called a call center. The method may also include identifying, in response to determining that the caller has previously called the call center, an agent that handled the previous call from the caller, and forwarding the call to the agent that handled the previous call.

Abstract: Systems and methods for recording a communication session between a customer and an agent are provided. In this regard, a representative method comprises: routing a media stream associated with the communication session based on information corresponding to routing criteria, wherein the routing criteria include call control protocols or policies; receiving the media stream associated with the communication session from the customer center communication system; and recording the received media stream.

Abstract: A contact center is described along with various methods and mechanisms for administering the same. The contact center proposed herein provides the ability to, among other things, determine performance efficiencies/metric associated with one or more multi-tasking agents and provide relief to agents based on rules. This multi-tasking relief may be provided to the one or more agents via reducing an amount of multi-tasking work, inserting breaks into the agent's work flow, and/or directing work items to other resources.

Abstract: An apparatus and methods for a call routing system is disclosed whereby the call routing service provider is associated with a series of partners. By providing a system supporting not only the main user, but also the partners, efficiencies are gained through cost-spreading. Agents can be qualified to field calls for multiple business entities. Cross-selling and proactive servicing based on caller demographic and profile data can be effectuated. The system employs a centralized or global bank of shared Interactive Voice Response (IVR) units so that unnecessary post-routing and call site interflow are reduced. The system comprises a central server system that interfaces with a long distance provider so that route requests are received, caller data is retrieved from one or more databases, routing and handling strategies are developed, load balancing is effectuated, and calls are appropriately routed to one of a plurality of geographically separated call center systems with queues staffed by agents.

Abstract: A system and method for processing a call between a caller and a live agent is provided. A stream of verbal speech utterances is received from the caller and converted into text. Text messages are received from the agent in response to the stream of verbal speech utterances and converted into synthesized speech utterances. The synthesized speech utterances are provided to the caller. A record of the call is processed and presented to a further live agent for manipulation. The manipulated record is stored.

Abstract: A system and method are provided for allowing a user to consent to call recording. A user is prompted to make a recording preference. The recording preference is stored in a table indexed by UCID (universal call ID) or as part of a UUI (user-to-user information) field of the call. A recording module and/or a compliance manager, both associated with a call center, are configured to record or not record the call based on the recording preference. The recording preference can be enforced on incoming and outgoing calls to and from the call center. Advantageously, the user's recording preference is enforced throughout the call, regardless of how the call is routed/transferred within the call center.

Abstract: Embodiments of the present invention provide systems and methods for recording media communication. An exemplary method comprises the steps of: receiving an incoming call from a calling phone; routing the incoming call to a called phone in a contact center; transmitting voice communications associated with the incoming call via the calling phone; duplicating the voice communications via the called phone; transmitting the duplicated voice communications via the called phone; and recording the duplicated voice communications.

Abstract: A system and method for maximizing efficiency of call transfer from being between a customer and a dialing agent, to being between the customer and a talker is provided. The method contains the steps of: entering a dialing agent and a talker into a campaign to maintain direct communication with the dialing agent and with the talker; calling a customer via use of a dialing agent device; receiving from the dialing agent a request to transfer a connected customer from communicating with the dialing agent to communicating with a talker; and after receiving the request to transfer, transmitting an identification of a customer record associated with the connected customer to a talker computer for identifying the customer record, where the customer record has been previously stored on the talker computer prior to receiving the request to transfer.

Abstract: Embodiments described herein provide a system, method and technique for operating a communication device. According to an embodiment, information contained in a contact record is displayed, where the information includes a plurality of entries. Each entry is associated with one of a plurality of communication types and includes an identifier for use with an application of the associated communication type. An input is detected corresponding to a user's selection of one of the plurality of entries. In response to the user's selection, the application of the communication type associated with the selected entry is automatically executed by initiating a communication using the identifier included in the selected entry.

Abstract: A hosted list service provider (“HLSP”) provides list management services for compliance purposes. The HLSP receives electronic consent information from an enterprise that may comprise a telephone number and stores the same in at least one database, to facilitate retrieving the electronic consent information for a particular telephone number. A telephone number list is provided to a call center, which can originate calls for a calling campaign using the telephone numbers on behalf of the enterprise. After the campaign is completed, the call center may provide data to the HLSP indicating which callers have requested to opt-out, and the HLSP updates its databases appropriately. The HLSP may process the telephone number data against other databases, and may inform the enterprise of called parties that have requested a change of status. Follow up communication can occur to the called party to confirm or re-establish consent for subsequent calls.

Abstract: Methods and systems implemented in an information handling system are provided for managing call event data between agents and callers for calls completed through a carrier. Functionality provided by certain embodiments includes, but is not limited to, one or more of the following features: the ability to automatically update customer information databases according to call event data in real-time, dual-tone multi-frequency (DTMF) activity of the caller and/or agent, do-not-call (DNC) verification and updating, agent identification, lead source and content identification, the recording of calls, the automatic translation of voice communications to textual transcripts, key word detection, communication of customer demographic data to an agent before or during phone calls, audio file management, agent call tracking, and other functions and advantages as will be apparent with the benefit of this disclosure. Methods and systems are also included for data associated with managing broadcast campaigns.

Abstract: A user of a personal computing device may identify an item of interest provided by a network-based service for which additional information is desired. Customer service agents (CSAs) of the network-based service may be contacted by the user to respond to queries. To assess the quality of a contact, a contact review service may record the contact between the CSA and the user and edit the contact to reduce its length for ease of review. The edited contact may be submitted to one or more reviewers to obtain reviews characterizing the contact quality. Reviewers may include CSAs not participating in the contact or other human reviewers. The reviewers may return their reviews to the contact review service, which generates a composite review from the returned reviews. The composite review may be employed for CSA evaluation and/or training purposes, amongst others.

Abstract: A system and method for enhanced tracking of calls resulting from referrals to a website from third party servers includes the steps of identifying a tracking parameter, dynamically allocating a phone number to the tracking parameter, displaying the dynamically allocated number on a web page, and tracking calls received on the number. The dynamically allocated number may replace an existing number on the web page. The tracking parameter can be a keyword used in a search, an identifier of the referring website, or any other parameter, including combinations thereof. The tracking parameter may be included in the referring URL, the URL of the website, or in the body of a web page. In some embodiments, the call tracking capability is provided by a service provider other than an operator of the merchant website and JavaScript is used so that the process is easy to implement by the merchant website.

Abstract: Methods, systems, and computer-readable media consistent with the present invention manage multiple telephone calls by managing a session record associated with the call, amending the session record according to a plurality of rules to reflect a plurality of instructed actions, evaluating an amended session record to derive at least one of the plurality of instructed actions, and implementing a derived instructed action on the call under the control of an automated attendant apparatus.

Abstract: A method for recording automatic call distributor calls includes receiving from a caller a call for distribution to one of a plurality of agents and distributing the call to a first agent of the plurality of agents for handling. The method includes creating a call signature associated with the call for recording verification and recording communications of the call to a recording file. The method also includes embedding the call signature in the recording file.

Abstract: A unified session detail records of a multi-hop session is provided. The multi-hop session may be established through multiple nodes in a VoIP network. Each node may generate session detail records for the legs of the multi-hop session that are connected to the node. The nodes on the path of the multi-hop call may send the record to a single node to consolidate the session detail records of the legs of the multi-hop call in the single node so that the single node can provide unified session detail records of the multi-hop session. By providing unified session detail records, the user does not need to track down the nodes that are on the path of the multi-hop call to obtain the session detail records of the multi-hop session.

Abstract: A predictive call routing system that includes a real-time decision engine to receive information about a customer and identify a skill that is useful for providing service to the caller. The decision engine identifies the skill by generating scores for a plurality of statistical models using the statistical models and parameters associated with the caller, each statistical model representing a correlation between a subset of parameters and an action that may be performed or requested to be performed by the caller, the score for each statistical model being generated using the statistical model and the subset of parameters associated with the statistical model, and identifies a skill based on the scores. The system includes a call router to route a call from the customer to a representative who has the skill.