Modeling voice calls to improve an outcome of a call between a representative and a customer
AssigneeAffectLayer, Inc.
InventorsRoy Raanani, Russell Levy, Micha Yochanan Breakstone
Life of this patent
Estimating the term…
Abstract
A call-modeling system models calls in real-time, with the goal of helping users, e.g., a sales representative and/or their managers, improve and/or guide the outcome of the calls. The call-modeling system generates real-time probabilities for possible outcomes of the conversation, as well as highlight specific on-call patterns, which may be either conducive or detrimental to a desired conversation outcome. The generated probabilities and highlighted patterns may be used by the sales representatives and/or their managers to either increase the probability of a desired outcome and/or optimize for call duration with a specific outcome.
Claims26
1-29. (canceled)
A computer-implemented method comprising:
- receiving, by a processor, a stream of data related to a call in which a conversation occurs between multiple participants;
- extracting, by the processor, a set of features from the stream of data,
- wherein the set of features includes at least one characteristic of a given participant of the multiple participants and at least one characteristic of the conversation;
- analyzing, by the processor, the set of features using multiple classifiers to determine multiple potential outcomes of the call;
- and
- generating, by the processor based on said analyzing, an on-call guidance to increase a probability of a given outcome of the multiple potential outcomes.
The computer-implemented method of 33, further comprising:
- determining, by the processor, that the set of features has changed as the call progressed;
- and
- adjusting, by the processor, the on-call guidance to reflect the change in the set of features.
A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
- receiving a stream of data related to a call in which a conversation occurs between a customer and a representative;
- extracting a set of features from the stream of data,
- wherein the set of features includes at least one characteristic of the representative and at least one characteristic of the conversation;
- analyzing the set of features to determine multiple potential outcomes of the call;
- and
- generating an on-call guidance to increase a probability of a given outcome of the multiple potential outcomes.
A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:
- acquiring data related to past calls in which conversations occurred between customers and representatives of an enterprise;
- extracting multiple features of the conversations by analyzing the data;
- and
- generating multiple classifiers based on the multiple features,
- wherein each classifier of the multiple classifiers is associated with an outcome and at least one feature of the multiple features determined to have contributed to the outcome.
Dependencies are inferred from the claim text.