H04M5/00

Analysis and classification of unstructured computer text for generation of a recommended conversation topic flow
10965812 · 2021-03-30 · ·

Methods and apparatuses are described for generating a recommended conversation topic flow. A server executes a topic modelling algorithm on voice call transcripts to determine a distribution of topics present in the transcripts. The server generates a historical topic flow for each transcript by determining topic-related words in text blocks in the transcript and assigning a score to each text block. The server categorizes each topic flow as positive or negative based upon outcomes associated with the transcript. The server trains a classification model using the categorized topic flows as input. The server captures a bitstream corresponding to a current voice call and converts the bitstream into unstructured text. The server executes the classification model on the unstructured text to determine whether a call topic flow is positive or negative. The server generates topic recommendations and transmits the recommendations to a second client device.

Dynamic voice over internet protocol proxy for network bandwidth optimization

Examples include receiving, from a VoIP server, identification information of the virtual meeting and information of a plurality of client devices participating in the virtual meeting, associating each client device of the plurality of client devices to a network device in a set of network devices based on the identification information of the virtual meeting and capabilities of the set of network devices, and creating a proxy agent in each network device in the set. The proxy agent is configured to receive, from the VoIP server, VoIP streaming data of the virtual meeting. Additionally, examples include, configuring the proxy agent to replicate and transmit the VoIP streaming data to the plurality of client devices.

Stranded asset management in customer service call centers

A method, system, and computer-readable storage medium provide for managing stranded assets of a customer service call center. The system includes an interface component that identifies an opportunity event of an established customer service session initiated by a user that is in a waiting queue for a customer service representative. The system includes an ingestion component that ingests one or more characteristics of the opportunity event that characterize at least one of: (i) the identity of the user; (ii) subject of the established customer service session; and (iii) situational context of the user. The system includes a correlation component that correlates the one or more ingested characteristics and an estimated duration of the waiting queue with at least one transaction-related content item. The system includes a publishing component that publishes a selected transaction-related content item via the established customer service session to the user while in the waiting queue.

Systems and methods for routing incoming calls to operator devices based on performance analytics
11057523 · 2021-07-06 · ·

Disclosed are systems and methods for routing inbound communications at call centers in order to enhance customer experience and call center agent efficiency. In order to effectively route communications, customer service call types and one or more agent performance rates responding to said customer service calls are analyzed in order to determine which one or more call center agents should be routed which specific customer service call type. Additionally, tools are disclosed for analyzing call center agent performance rates and assigning call center agents to service specific customer service call types.

Matching using agent/caller sensitivity to performance
11863708 · 2024-01-02 · ·

A method, system and program product, the method comprising: obtaining for each call in one set of calls a respective pattern representing multiple different respective data fields; obtaining performance data for the respective patterns of the calls; obtaining performance data for the respective agents; determining agent performance sensitivity to call pattern performance for agents in a set of agents comprising the agent performance data correlated to call performance data for the calls the agent handles; and matching a respective one of the agents from the set of agents to one of the calls based at least in part on the performance data for the respective pattern of the one call and on the agent sensitivity to call performance for the respective one agent of the set of agents.

Matching using agent/caller sensitivity to performance
11863708 · 2024-01-02 · ·

A method, system and program product, the method comprising: obtaining for each call in one set of calls a respective pattern representing multiple different respective data fields; obtaining performance data for the respective patterns of the calls; obtaining performance data for the respective agents; determining agent performance sensitivity to call pattern performance for agents in a set of agents comprising the agent performance data correlated to call performance data for the calls the agent handles; and matching a respective one of the agents from the set of agents to one of the calls based at least in part on the performance data for the respective pattern of the one call and on the agent sensitivity to call performance for the respective one agent of the set of agents.

Priority calling using cloud-based signaling for VoLTE and non-cellular calls

This Application describes mechanisms to provide priority levels for call connection requests and/or messages from a sending device to a receiving device. The receiving device is configured to allow prioritized notification alerts for incoming call connection requests and/or for incoming messages from a sending device to override a silent or do not disturb mode for one or more contacts based on i) a priority level provided with the call connection request or message and ii) a priority setting for the sending device or a set of devices associated with a user of the sending device.

System and method for a cloud callback platform with predictive multi-channel routing

A system and method for a cloud callback platform, comprising at least a profile manager, callback manager, interaction manager, media server, context analysis engine, and context aggregator mechanism, allowing users to call a business, agents in contact centers, or other users who are connected to cloud callback platform, and, failing to connect to the individual they called, or by request, allow for an automatic callback object to be created, whereby the two users may be automatically called and bridged together at a time when both users are available, and a context summary report is sent to one or more user. The system and method implement predictive logic to determine the most successful alternative communication channel to use to bridge the two parties.

Method and system for providing a seamless handoff from a voice channel to a call agent

The method and system may provide a seamless handoff of user information from a drugstore to a call agent. When a customer communicates with a drugstore device regarding a drugstore-related inquiry, the drugstore device attempts to identify an answer to the drugstore-related inquiry. When the drugstore device does not identify an answer to the drugstore-related inquiry, the drugstore device initiates communication between the customer and a contact center. A transcribed version of the communication may be stored in a database accessible by the contact center along with additional user information for the customer related to the customer's experiences with the drugstore. The user information may be provided to a call agent's contact center device for display and in this manner, the call agent may be made aware of the communication to avoid asking repeat questions and to quickly and efficiently answer the customer's drugstore-related inquiry.

Contact center authentication

A method of authenticating a service agent on behalf of a user, the method performed at a server and including: obtaining a unique identifier associated with a first communication session established over a first communication channel; storing the unique identifier in a data store; receiving, via a second communication channel, a validation request comprising verification information associated with the user; attempting authentication of the service agent by comparing the verification information with the unique identifier, and in response outputting a validation response via the second communication channel. If the verification information corresponds with the unique identifier, the validation response indicates successful authentication of the service agent, and if the verification information does not correspond with the at least one unique identifier, the validation response indicates unsuccessful authentication of the service agent.