Amazon Technologies, Inc.

Jon R Jay

Joseph Daniel Sullivan

Yung-Chun Lin

Jeremy A Dashe

Donald Lloyd Kaufman

Raymond P Sharpe, Jr

Pasquale DeMaio

Eric Samuel Stone

Kenneth C Macfarlane

Nathan Brent Glissmeyer

Zachary Lee Yeager

Brock Aaron Judkins

Donald Loyd Kaufman

Thomas J Weiland

Ajit Kumar

Saket Agarwal

Nihal Chand Jain

Jaswinder Singh Randhawa

Tauseef Kidwai

Jeffrey C Pratt

Adrian Inglis

Lorraine A Nicholson

Raymond P Sharpe

John Elias Darrow

Juliana Saussy

Thomas Boyd Johnston

Wei Niu

Tak Chung Lung

Adrian Paul Inglis

Jeffrey Pratt

Phillip H Keung

A Lorraine Nicholson

Vamsi Polapragada

Sonu Kumar Mishra

Saket Agarwa

Yiwei Li

Preetham Gowda

Paul Sharpe

Nate Glissmeyer

Richard Julian Rodriguez

Manjeshwar Donthi

Joseph D Sullivan

Systems and methods are described relating to distributing agents to different queues provided by a call or contact center. A contact service may define a number of different queues for processing different customer requests, such as may be routed to different agents, with each queue associated with a priority value (higher priority get assigned agents first) and a visibility threshold (how long a request will sit before it is picked up by an agent). The described techniques add a time-to-service level (SL) goal, per queue to determine when queues are over and underperforming. In the case queues are overperforming, various techniques, including control systems approaches may be used to determine adjustments to the visibility threshold (e.g., at least one of increasing the thresholds for overperforming queues and decreasing the thresholds for underperforming queues) to increase performance in meeting the customer SL goals.

Service level based routing using visibility thresholds

Methods, systems, and computer-readable media for accurate usage forecasting for virtual contact centers are disclosed. A contact center management system configures a contact center instance associated with a client. The contact center instance comprises a plurality of queues configured to store contacts. At least a portion of the contacts are routed to a plurality of agents. The contact center management system determines, using one or more machine learning models associated with the contact center instance, a plurality of predictions for a plurality of metrics for the contact center instance for a plurality of time horizons. At least a portion of the predictions are generated for individual queues of the contact center instance.

Accurate individual queue level metric forecasting for virtual contact center queues with insufficient data, using models trained at higher granularity level

A technology is described for configurable contact flows implemented using a contact flow service. An example method may include activating a contact flow in response to a request to establish a contact center session. The contact flow may be used to provide automated contact service communications to end users using computing resources hosted within a computing service provider environment. A starting prompt specified by the contact flow may be output using a communication channel. Input data may be received via the communication channel in response to the starting prompt. The input data may be analyzed to identify an intent identifier included in the input data and a contact flow action linked to the intent identifier may be executed.

Configurable natural language contact flow

A user of a personal computing device may identify an item of interest displayed in a user interface provided by a network-based service and would like to obtain more information. The user may submit one or more electronic contact requests to a contact service in communication with a contact distribution system in order to obtain more information. The contact distribution system determines accurate, real-time availability of service agents and enables communications between the customer and an agent to be established in accordance with user contact information provided by the user.

Systems and methods for customer contact

Aspects of systems and methods for maintaining and operating agent nodes are provided. In some embodiments, calls, contacts, and other work units may be routed to individual customer service agents via a centralized queue based on a variety of factors. Some embodiments may provide market-based call pricing and customer service agent compensation.

System and method for automated call distribution

Disclosed are various embodiments for a call routing application. Routes are evaluated according to selection scores of call routes. The selection scores are calculated based on weighted call quality data corresponding to past calls on the call routes. A call route is selected according to an evaluation including call costs or other criteria. A call is then routed via the selected call route to the call endpoint.

Quality-based phone routing

Technologies are disclosed for providing an onboarding service within a service provider network for on-demand creation of a contact center. Information associated with an account of a user at the service provider network is utilized to begin creating the contact center. Based upon input from the user, a directory of authorized users and storage for the contact center are created using services available within the service provider network. Encryption keys are created for encrypting customer call recordings and customer phone numbers in the storage. An initial user for handling calls is specified and a call queue is created. A routing profile is created to route calls from the call queue to the initial user. Available phone numbers are provided to the user for the selection of a phone number for accessing the contact center. One this data has been specified, the contact center can be activated for use.

On-demand generation of a contact center

Disclosed are various embodiments for a call routing application. Routes are evaluated according to aggregated call quality data with respect to a call endpoint. A route is selected according to the evaluation, call costs, or other criteria. A call is then routed via the route to the call endpoint.

This disclosure describes a system for associating user accounts with source identifiers included in communication requests received from users of those user accounts and using that information to later identify potential user accounts. For example, when a user contacts a support network, such as a call center, the source identifier (e.g., telephone number) may be identified. Once the user initiating the communication request is verified and the corresponding user account identified, the source identifier may be associated with the identified user account. By establishing and storing a relationship between the source identifier and the verified user account, if the user later again initiates a communication request that includes the same source identifier, that user's user account may be quickly identified to the agent, thereby simplifying verification.

Associating user accounts with source identifiers

Growing community of inventors

Seattle, WA, United States of America

Jon R Jay