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
The disclosure is directed to modeling 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 embodiments generate 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.
Claims41
A computer-implemented method for modeling a conversation between a participant and a user, the computer-implemented method comprising:
- analyzing, by a computer system, a set of call data between multiple users and multiple participants to extract multiple features of conversations between the users and the participants, the multiple features indicating characteristics of any of (a) at least one of the users, (b) at least one of the participants, (c) the conversations;
- extracting, by the computer system, the multiple features of the conversation based on the analysis;
- generating, by the computer system, multiple classifiers based on the multiple features, wherein each of the multiple classifiers indicates one of multiple outcomes of a conversation and includes a subset of the multiple features that contributed to the one of the multiple outcomes, wherein different classifiers have distinct features;
- receiving, by the computer system, real-time call data of an ongoing call between the user and the participant;
- extracting, by the computer system, a set of features from the real-time call data;
- and
- analyzing, by the computer system, the set of features using the multiple classifiers;
- and
- generating, by the computer system, probabilities for potential outcomes of the call based on the analyzing of the set of features.
A computer-readable storage medium storing computer-readable instructions, comprising:
- instructions for receiving real-time call data of a call between a user and a participant of multiple participants;
- instructions for extracting a set of features from the real time call data, wherein the set of features includes characteristics of the user and characteristics associated with a conversation of the call;
- instructions for analyzing the set of features using multiple classifiers, wherein the multiple classifiers are generated based on multiple features extracted from a set of historical call data, wherein each of the multiple classifiers indicates one of multiple outcomes of a conversation, includes a subset of the multiple features that contributed to the one of the multiple outcomes, and includes a probability value for the corresponding outcome;
- and
- instructions for generating probabilities for potential outcomes of the call based on the analyzing of the set of features using the multiple classifiers.
A system for determining a first participant of multiple participants to whom a call from a user is to be routed, the system comprising:
- a first component that is configured to receive real-time call data of a call between the user and a participant of multiple participants;
- a second component that is configured to extract a set of features from the real time call data, wherein the set of features includes characteristics of the user and characteristics associated with a conversation of the call;
- a third component that is configured to analyze the set of features using multiple classifiers, wherein the multiple classifiers are generated based on multiple features extracted from a set of historical call data, wherein each of the multiple classifiers indicates one of multiple outcomes of a conversation, includes a subset of the multiple features that contributed to the one of the multiple outcomes, and includes a probability value for the corresponding outcome;
- and
- a fourth component that is configured to generate probabilities for potential outcomes of the call based on the analyzing of the set of features using the multiple classifiers.
A system for modeling calls between representatives and customers in real time, comprising:
- a first component that is configured to receive audio recordings and/or call streams of conversations between the representatives and the customers;
- a second component that is configured to extract features from the audio recordings and/or the call streams;
- a third component that is configured to generate multiple classifiers based on the extracted features for different temporal intervals, the classifiers including probabilities for possible outcomes of a conversation of the conversations;
- and
- a fourth component that is configured to apply, in real-time, the classifiers to a conversation in progress between a customer and a representative to generate instructions for the representative for improving an outcome of the conversation, wherein the instructions include one or more features and values of those features that, when adopted by the representative, increases the probability of the outcome.
Dependencies are inferred from the claim text.