Abstract: A system and method are presented for creating bots for automating first party touchpoints with contact centers. Software bots created using Robotic Process Automation (RPA) are integrated with a contact center's different customer touch points (e.g. chatbots, emails and SMS, websites, IVR application, mobile applications, agent workstation). Artificial intelligence behind the touch points finds the intent of an interaction and the respective RPAs to be triggered using a fulfillment engine that finds and executes the appropriate fulfillment for each interaction intent. A REST API Request is sent to an RPA execution server, which runs the selected RPA and sends the result to the respective touch point that triggered it.

Abstract: A conversation system may dynamically control a conversation or workflow by performing multi-modal conversation monitoring, generating actions that control the conversation based on the multi-modal monitoring producing conversation elements that deviate from patterns of a selected plan for that conversation, and/or by dynamically generating and/or updating the plan for future conversations based on the pattern recognition. For instance, the conversation system may detect a pattern within completed conversations that resulted in a common outcome, may monitor an active conversation between at least an agent and a participant, may extract different sets of conversation elements from different points in the active conversation, may determine that a particular set of conversation elements deviates from the pattern, and may modify the active conversation by performing one or more actions based on the particular set of conversation elements that deviate from the pattern.

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: An interactive voice response system for interpreting sentiment of a conversation in real time is provided. The system may include a receiver. The receiver may be operable to receive a plurality of sentiment signals and a first portion of a conversation. The first portion of the conversation may include a plurality of interaction pairs. Each interaction pair may include an utterance and a system response. The system may include an utterance sentiment category determination module that may be operable to determine a sentiment category for each utterance. The system may include a sequential module. The sequential module may determine a conversation sentiment category based on the utterance sentiment categories and the order in which the utterance sentiment categories are received. The system may include an output module. The output module may output the conversation sentiment category. The conversation sentiment category may be used to determine a future system response.

Abstract: Systems and methods are provided for distributing audio. An audio system is provided that includes one or more audio interfaces, at least one of which is a wireless audio interface. An audio hub couples to the one or more audio interfaces and detects the presence of one or more headphones coupled to the wireless audio interfaces. The audio hub selectively establishes communication channel(s) to convey audio content between a plurality of devices coupled to the audio interfaces. The plurality of devices may include one or more headphones, an infotainment head unit, a microphone, and a speaker. Accordingly, headphone users may hold conversations with each other and/or other occupants of a vehicle, and various users may share audio content with headphone users and/or other occupants of a vehicle.

Abstract: Apparatuses and methods concerning providing a data-communications contact center virtual agent are disclosed. As an example, user-data-communications between client and participant stations are facilitated as follows, which may be implemented using a data communications server and associated communications circuitry. Service request data is received from users at a participant stations, and context information is identified for user-data-communications between a client station and the participant stations based on the service request data at least one communications-specific characteristic associated with the user-data-communications. The identified context information is aggregated for the client station and used for choosing a data routing option routing data with each user at the participant stations, based on the service request data and the aggregated context information.

Abstract: A method of detecting robocalls includes generating at least one of an identification (ID) spoofing score, a number similarity score, and a call length prediction request for a telephone call request. The method further includes generating a robocall predictor score based at least in part on the call length prediction score and the ID spoofing score, and rejecting the telephone call request when the robocall predictor score indicates the telephone call request is invalid.

Abstract: In one aspect, a first device includes a processor, a microphone accessible to the processor, a speaker accessible to the processor, a display accessible to the processor, and storage accessible to the processor. The storage may include instructions executable by the processor to facilitate concurrent video conferencing for first and second video conferences and to receive user input selecting the first video conference. Based on the user input, the instructions may be executable to control the speaker to output audio for the first video conference at a greater volume level than audio for the second video conference and to transmit input from the microphone to a second device associated with a participant of the first video conference but not to a third device associated with a participant of the second video conference.

Abstract: Systems and methods for intelligently routing a member of an organization to a single point-of-contact within an optimized, secure network to address all the member's healthcare needs are described. The disclosed intelligent routing configurations transform and process, in real-time, vast amounts of member data to generate aggregated diagnoses and a member score specific to each member's household. The scores, among other things, are used to determine an identification of special needs and an appropriate advocate within the organization to route the member, and its account file containing real-time member and household level data.

Abstract: Embodiments of the present disclosure include computer-implemented systems and methods for routing incoming customer requests or inquiries in a customer service center. The system may include at least one processor configured to execute instructions to perform steps. The steps may include receiving a plurality of incoming customer calls and a plurality of incoming customer chat sessions. The steps may include blending the received plurality of customer calls and the received plurality of customer chat sessions into a total queue for presentation to at least one user device. The steps may additionally include determining a respective priority for each of the blended plurality of customer calls and the blended plurality of customer chat sessions and sending, based on the determined priority, to the at least one user device at least one of the blended plurality of customer calls or the blended plurality of customer chat sessions.

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: Techniques are described that update a caller on call progress status using various effects based on a likelihood that the call will connect with the callee, and/or a likelihood that the caller will prematurely terminate the call. In some examples, a machine-learned model may determine a likelihood that a call will connect based on conditions associated with the callee. In some cases, a machine-learned model may determine a likelihood that a call will be prematurely terminated by the caller based on conditions associated with the caller. Animations, haptic outputs, sounds, and/or other content may be used to indicate likelihood of the call connecting to the caller.

Abstract: A return call routing system verifies that the telephone number of an outbound call being placed by an agent is the telephone number of a contact assigned to the agent. The outbound call is then assigned a tag identifying the contact's phone number as associated with the agent's station. When the routing system recognizes a contact's return call phone number as being tagged, the system bypasses the normal call flow at the call center and the return call is routed directly to the assigned agent's station. A time window for the return call may be set beyond which the return call is directed to the next available agent through a call flow manager.

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 from previous service sessions between service representative(s) and individual(s). Training data may include, for previous service session(s), a session record (e.g., audio record) of the session and a set of 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 is a combination of a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network.

Abstract: A system for scheduling deferred communications is provided. A workload requirement for a deferred queue for each interval of a set of intervals is determined. Each workload may indicate the amount of work predicted for the associated interval. A staffing requirement for an immediate queue is received and may indicate the number of agents needed to handle the immediate communications for the same intervals. The system, for each interval, may consider the number of agents needed for the interval in the immediate queue. Because the deferred communications do not have to be handled at any particular interval, the system may, based on the workloads, schedule agents for the deferred queue where the immediate queue is less busy (a smaller number of agents are scheduled). The goal of the system being to smooth the intervals such that the total number of agents scheduled for each interval across the immediate queue and the deferred queue remains fairly constant.

Abstract: A computer device may include a memory storing instructions and processor configured to execute the instructions to obtain a text file generated based on a communication session; select topics for classifying communication sessions; and apply one or more trained machine learning models to the obtained text file to determine one or more most likely topics for the communication session. The processor may be further configured to apply regular expression binary classifiers, each associated with a different topic, to the obtained text file to determine a likelihood the communication session is associated with a particular topic; select a topic for the communication session based on the determined one or more most likely topics and the determined likelihood the communication session is associated with the particular topic; and classify the communication session based on the selected topic.

Abstract: A processor receives inputs from a dialog between an agent and a user performed over a communication channel A knowledge base is stored, comprising entries with a subset of said entries defined as higher priority. A match is detected between an input from said dialog and a plurality of said knowledge base entries. At least one of said plurality of entries is retrieved corresponding to said match. The at least one of said plurality of entries is pushed as an output to one or more of a device operated by said user and at least one device operated by one of said user and said agent. A further match is detected between an input from said dialog and a higher priority entry in said knowledge base and pushed to said at least one device while the dialog is ongoing.

Abstract: Embodiments relate to an electronic device such a smart speaker. The electronic device may include a sensor to identify an environmental condition related to a location in which the electronic device is positioned. The electronic device may further include a processor to identify, based on a neural network, a sound-related parameter related to the environmental condition. The electronic device may further include a speaker to generate a sound based on the sound-related parameter. Other embodiments may be described or claimed.

Abstract: Systems and methods for locating a cellular phone are provided. More particularly, systems and methods for providing the location of a requested user's cellular phone from a requesting user's device (e.g., a second cellular phone) based on access rights defined by the requested user. Location descriptions may be provided at a multitude of levels. For example, if a cellular phone, or an identity associated to (e.g., logged into) a cellular phone, has been given access rights to a cell phone's exact location for an indefinite amount of time, that cell phone can receive, on command, the exact location of the approved cell phone. Other levels of location information that can be granted include, for example, proximities, states, and countries.

Abstract: A method, device, and computer-readable medium provide for receiving, via a chatbot access channel, a chat message from a user device associated with a customer chat session; determining that the chat message includes a customer intent that corresponds to a chat flow for the customer chat session; generating one or more suggested response messages based on the chat message, wherein at least one of the one or more suggested response messages includes a previously stored chat message response corresponding to the customer intent and approved by a service agent; presenting, via a display, a transcript of a messaging sequence for the customer chat session concurrently with a user interface that enables the service agent to perform an action with respect to the one or more suggested response messages; and sending, via the chatbot access channel, a selected one of the one or more suggested response messages to the user device.