Zoom Communications, Inc.

Zoom Video Communications, Inc.

Maikl Adly Abdel-Malek Eskander

Kristin Renae Bosch

Wei Dai

Fengcai Sun

A server receives a query for connecting a user device to an agent device at a contact center server. The server determines, based on the query, a set of features of an agent associated with the agent device. The server determines that the agent having the set of features is available. The server calculates a priority score for the user device based on an elapsed time since the user device initiated a contact center engagement and additional stored data associated with the user device. The server connects the user device to the agent device based on the agent being available and based on the priority score for the user device exceeding a priority score for at least one other user device.

Connecting a user device to an agent device at a contact center

A contact center server receives indicia of user devices accessing the server. The contact center server determines that a contact center agent device is available for communicating with a user device of the user devices. The contact center server calculates, for at least a subset of the user devices, a priority score based on an elapsed time since the user device initiated a contact center engagement and a priority level of an account associated with the user device. The contact center server selects, based on the calculated priority scores, a first user device for communicating with the available agent device. The contact center server connects the first user device to the available agent device via the contact center server.

Priority score-based connection of user device to agent device

A server accesses, during a contact center engagement performed by a software agent configured to generate and output automated responses to prompts, a prompt provided by a contact center user device. The server determines, using a natural language processing engine of the software agent, to use an application programming interface call based on the prompt, the natural language processing engine comprising a generative pre-trained transformer trained to generate natural language responses to natural language prompts. The server transmits an access request representing the application programming interface call to a governance engine configured to generate data structures responsive to application programming interface calls in a format readable by the software agent. The server receives a data structure responsive to the access request from the governance engine. The server generates, using the natural language processing engine, a natural language response based on the data structure.

Integrating an application programming interface with a contact center

A server determines a number of devices preceding a user device in a user queue of devices for communication with a contact center agent device. The server determines a number of contact center agent devices available for the communication. The server calculates an estimated wait time for the user device based on the number of devices preceding the user device, the number of contact center agent devices, and wait times of user devices, distinct from the user device, requesting communications with the contact center agent device.

Calculating an estimated wait time

A contact center server accesses queries provided by user devices. The contact center server determines a confidence score representing a likelihood that a query of the queries matches an intent using an intent matching engine. The contact center server matches, via the intent matching engine based on the confidence score exceeding a threshold, the query to the intent. The contact center server provides, to a client device, a subset of the queries that are not matched to any intent. The subset is identified based on confidence scores. The contact center server receives, from the client device, data representing an intent that matches at least one query in the subset. The contact center server trains the intent matching engine based on the received data.

Training an intent matching engine of a contact center

A server receives a request for communication with a contact center agent device from a user device. The server determines a number of devices preceding the user device in a user queue of devices for communicating with the contact center agent device. The server determines a number of contact center agent devices available for the communication. The server periodically calculates an estimated wait time for the user device as a mathematical combination based on the number of devices preceding the user device, the number of agent devices, and previous wait times of other user devices requesting communications with the contact center agent device. The server transmits, to the user device, an output associated with the estimated wait time.

Growing community of inventors

Seattle, WA, United States of America

Maikl Adly Abdel-Malek Eskander