Employee experience score
Techniques for monitoring and improving emotional well-being of an employee are described. Stream of audio data corresponding to a call between an employee and a customer may be received. One or more acoustic features and/or audio feature data may be generated from the audio data. Word embedding data corresponding to the audio data may be generated. An employee experience score may be generated using a machine learning (ML) model, word embedding data, and the one or more acoustic features, where the score corresponds to an experience level of the first speaker during the call with the second speaker. Based on the score, an action may be caused to be performed. In some embodiments, one or more notifications may be generated based on data related to the audio data, where at least notification is configured to improve an experience level for the first speaker.
1 . A computer-implemented method comprising:
receiving first audio data corresponding to a call between first speaker using a first device and a second speaker using a second device, wherein the first speaker is communicating with the second speaker as part of employment of the first speaker, wherein the first audio data is received during the call;
generating, using a first machine learning (ML) model and based on first data related to the first audio data, one or more notifications, wherein at least one notification of the one or more notifications is configured to improve an experience level for the first speaker;
generating, using the first audio data, a first call score, wherein the first call score corresponds to an experience level of the first speaker during the call; and
causing the one or more notifications and the first call score to be displayed in a graphical user interface (GUI) of a computing device.
2 . The computer-implemented method of claim 1 , wherein the experience level for the first speaker corresponds to an experience of the first speaker over an entirety of the call.
3 . The computer-implemented method of claim 2 , further comprising:
determining, based on at least the first call score, an aggregated call score for the first speaker, wherein the aggregated call score representing a cumulative experience level of the first speaker corresponding to multiple calls with multiple customers.
4 . The computer-implemented method of claim 3 , wherein:
the first data related to the first audio data indicates a difference between the first call score and the aggregated call score satisfies a threshold difference; and
the at least one notification indicates data representing the first call score and a follow-up discussion with the first speaker.
5 . The computer-implemented method of claim 1 , wherein:
the first call score is generated using a second ML model and the first audio data.
6 . The computer-implemented method of claim 3 , further comprising:
determining whether the aggregated call score satisfies a threshold aggregated call score; and
in response to the aggregated call score satisfying the threshold aggregated call score, modifying a call schedule for the first speaker.
7 . The computer-implemented method of claim 6 , wherein modifying the call schedule for the first speaker comprises:
removing the first speaker from a call queue.
8 . The computer-implemented method of claim 1 , further comprising:
determining, based in part on the first audio data, one or more topics discussed during the call; and
identifying one or more portions of the first audio data corresponding to the one or more topics,
wherein the one or more notifications may indicate the one or more portions of the first audio data.
9 . The computer-implemented method of claim 1 , wherein the computing device is associated with a supervisor of the first speaker.
10 . The computer-implemented method of claim 1 , wherein the at least one notification is generated during the call.
11 . The computer-implemented method of claim 10 , wherein the first data comprises a first call score corresponding to an experience level of the first speaker during the call, and wherein the at least one notification indicates that the first speaker requires assistance of a supervisor of the first speaker during the call.
12 . The computer-implemented method of claim 1 , further comprising:
determining a call type corresponding to the call,
wherein a first notification of the one or more notifications indicates the call type.
13 . The computer-implemented method of claim 1 , further comprising:
determining, based on the first audio data, a first intent of the second speaker;
determining an average call score representing an average experience of an employee during a call related to the first intent;
determining the first call score is below the average call score; and
in response to determining that the first call score is below the average call score, determining one or more topics associated with the first intent, wherein a first notification of the one or more notifications indicates additional training in the one or more topics.
14 . The computer-implemented method of claim 1 , further comprising:
determining a group associated with the first speaker;
determining, based on a plurality of call scores corresponding to a plurality of calls over a first time period, an average call score for the group;
and
determining the first call score is below the average call score, wherein a first notification of the one or more notifications indicates that the experience level of the first speaker is worse than an average experience level of the group.
15 . A system comprising:
at least one processor; and
at least one memory including instructions that, when executed by the at least one processor, cause the system to:
receive first audio data corresponding to a call between first speaker using a first device and a second speaker using a second device, wherein the first speaker is communicating with the second speaker as part of employment of the first speaker, wherein the first audio data is received during the call;
generate, using a first machine learning (ML) model and based on first data related to the first audio data, one or more notifications, wherein at least one notification of the one or more notifications is configured to improve an experience level for the first speaker;
generate, using the first audio data, a first call score, wherein the first call score corresponds to an experience level of the first speaker during the call; and
cause the one or more notifications and the first call score to be displayed in a graphical user interface (GUI) of a computing device.
16 . The system of claim 15 , wherein the experience level for the first speaker corresponds to an experience of the first speaker over an entirety of the call.
17 . The system of claim 16 , wherein the at least one memory includes further instructions that, when executed by the at least one processor, further cause the system to:
determine, based on at least the first call score, an aggregated call score for the first speaker, wherein the aggregated call score representing a cumulative experience level of the first speaker corresponding to multiple calls with multiple customers.
18 . The system of claim 15 , wherein the at least one memory includes further instructions that, when executed by the at least one processor, further cause the system to:
determine, based in part on the first audio data, one or more topics discussed during the call; and
identify one or more portions of the first audio data corresponding to the one or more topics,
wherein the one or more notifications may indicate the one or more portions of the first audio data.
19 . The system of claim 15 , wherein the computing device is associated with a supervisor of the first speaker.
20 . The system of claim 15 , wherein the at least one notification is generated during the call.