Avaya Management L.p.

Avaya Inc.

Manish Negi

Valentine C Matula

Divakar Kumar Ray

David L Chavez

Saumabha Pal

Sujata Anand Gole

Rajashri Bhor

John H Meiners

A communication between parties over a network may be performed to complete a specific workflow and thereby complete a task. Portions of the workflow may be performed during the communication and others performed after the communication has ended. However, a standardized workflow may have variations, such as when portions to complete after the call has ended may have been completed during the communication or when an agent provides additional or alternative tasks. By analyzing the conversation, such as with a neural network or other artificial intelligent system, the portion of the second workflow to be completed after the communication has ended may be produced that accurately reflects the tasks to be completed.

Dynamic generation of custom post-call workflow

Contact centers often encounter situations where a group of customers have a common issue to be addressed. Connecting each customer to an agent for one-on-one communication may be effective, but it is resource intensive both in terms of networking and computer requirements and the time an agent spends repeating the same information. By performing an initial assessment of customers' issues, a common issue may be discovered that a common issue exists that can be handled in a group lecture pod, wherein a number of customer connect to interact with an agent and optionally to each other. Provided confidential information is not required, and any other required consent given, customers may be connected to the group lecture pod for more immediate resolution of a common issue and not have to stay in queue to wait for an agent to become available for a one-on-one interaction.

Selective aggregation of enqueued nodes into a subnetwork for simultaneous communication

Customer-agent interactions are often essential to provide services, such as to resolve issues. Methods and systems are provided to enable an artificially intelligent (AI) agent, such as a neural network to annotate a communication, such as a communication comprising a video stream. The AI may determine the subject of an issue and/or an issue to be resolved as a candidate resolution, which may further comprise annotations provided to the video stream. As a benefit the resolution, with annotations may be provided to the agent for subsequent processing and/or the customer.

Automated video stream annotation

The present disclosure provides, among other things, methods and systems of managing a first channel, including: receiving a request for a communication session on the first channel; determining that a monitored attribute of the communication session has met a first threshold; comparing, by a channel change analysis, a first performance measure of the first channel with a second performance measure of a second channel; and managing a channel change based on the determining and the channel change analysis.

Context based channel switchover

Co-browsing allows a providing party to access visual content on a computing device for sharing with one or more other parties. The parties receiving the shared image may have dissimilar security authorizations. Accordingly, systems and methods are provided that enable shared content, such as a document, web page viewed in a browser, etc., to automatically be redacted to block those parties who are not authorized to view the content. For example, a neural network may be utilized to scan the document and provide specific redacted copies to the parties so each can view the image of the content with unauthorized content redacted.

Selective content sharing

In order to provide effective communications, the individuals engaged in the communication should have appropriately matched language proficiencies. By ensuring that a customer of a contact center is matched with an agent having, or presenting, content of a communication utilizing language proficiency appropriate for the customer, effective communications may be provided. Should an agent deviate and provide communication content having language proficiency that is misaligned with the customer, automatic corrective action may be taken to realign the language proficiency presented to the customer.

Detecting vocabulary skill level and correcting misalignment in remote interactions

A co-browsing session between a customer communication endpoint and an agent terminal is established. User input is received, via at least one of the customer communication endpoint and the agent terminal, in the co-browsing session, which identifies a field that is difficult to understand. For example, the contact center agent may provide input that the customer does not understand a terms of use field. Information associated with the identified field that is difficult to understand is stored in a memory. The stored information is used to generate a report for the identified field. The report is then used to identify ways that may make the field more understandable by future customers. In one embodiment, the customer may also be able to mask one or more fields so that the contact center agent cannot view information in the field. For example, the customer may mask a social security number field.

Growing community of inventors

Pune, India

Manish Negi