Granted Patent B2

US 12,598,117 · App. 18/525,523 · Granted Apr 7, 2026

Inventors: Ravi Chittari (New York, NY); Siddharth Bhaskar (New York, NY); Fady Massoud (New York, NY); Jason Farnsworth (New York, NY)

Assignee: LIVEPERSON, INC.

H04L41/5054H04L41/16

Abstract

Claims (55)

1 . A method comprising:

generating a feature vector from communications of a real-time data stream, wherein the real-time data stream is a representation of a communication session between a user of a first device and a service of a second device, wherein the communications include natural language communications provided by the user;

executing a first machine-learning model using the feature vector, wherein of first machine-learning model is configured to generate a conversation score, wherein the conversation score indicates a quality of natural language communications between the user and the service;

determining that a condition of a trigger of a set of triggers is satisfied based on the conversation score being below a threshold, wherein the conversation score being below the threshold indicates poor quality natural language communications between the user and the service;

facilitating a connection of a third device to the communication session in response to executing a function associated with the trigger, wherein a user of the third device communicates with the user of the first device using natural language communications;

generating a training vector for a second machine-learning model using natural language communications of the real-time data stream that occur after execution of the first machine-learning model, wherein the second machine-learning model is trained using supplemental training data, and wherein the training vector is configured to replace at least a portion of the supplemental training data to improve an accuracy of the second machine-learning model with respect to the communication session;

updating the second machine-learning model using the training vector, wherein the second machine-learning model is configured to manage the set of triggers; and

modifying, using the second machine-learning model, one or more triggers of the set of triggers based on the conversation score and the real-time data stream, wherein the one or more triggers are modified in response to executing the function associated with the trigger, and wherein modifying the one or more triggers reduces a probability that a condition of the one or more triggers will be satisfied during a subsequent time interval of the communication session.

2 . The method of claim 1 , wherein the service is an automated service that is configured to communicate with the user over the real-time data stream using natural language communications.

3 . The method of claim 1 , wherein the machine-learning model is further configured to generate a predicted intent of the user of the first device.

4 . The method of claim 1 , further comprising:

executing, in response to modifying the set of triggers, the machine-learning model to generate a new conversation score;

determining that a condition of a particular trigger is satisfied based on the new conversation score;

executing, in response to determining that the condition of the particular trigger is satisfied, a particular function associated with the particular trigger; and

modifying the set of triggers based on the conversation score and the real-time data stream.

5 . The method of claim 1 , wherein modifying the set of triggers includes modifying one or more conditions of a corresponding one or more triggers.

6 . The method of claim 1 , wherein modifying the set of triggers includes adding one or more new triggers or removing one or more triggers.

7 . The method of claim 1 , wherein executing the function causes the real-time data stream to connect a second service to the real-time data stream.

8 . A system comprising:

one or more processors; and

a non-transitory machine-readable storage medium storing instructions that when executed by the one or more processors, cause the one or more processors to perform operations including:

generating a feature vector from communications of a real-time data stream, wherein the real-time data stream is a representation of a communication session between a user of a first device and a service of a second device, wherein the communications include natural language communications provided by the user;

executing a first machine-learning model using the feature vector, wherein of first machine-learning model is configured to generate a conversation score, wherein the conversation score indicates a quality of natural language communications between the user and the service;

determining that a condition of a trigger of a set of triggers is satisfied based on the conversation score being below a threshold, wherein the conversation score being below the threshold indicates poor quality natural language communications between the user and the service;

facilitating a connection of a third device to the communication session in response to executing a function associated with the trigger, wherein a user of the third device communicates with the user of the first device using natural language communications;

generating a training vector for a second machine-learning model using natural language communications of the real-time data stream that occur after execution of the first machine-learning model, wherein the second machine-learning model is trained using supplemental training data, and wherein the training vector is configured to replace at least a portion of the supplemental training data to improve an accuracy of the second machine-learning model with respect to the communication session;

updating the second machine-learning model using the training vector, wherein the second machine-learning model is configured to manage the set of triggers; and

modifying, using the second machine-learning model, one or more triggers of the set of triggers based on the conversation score and the real-time data stream, wherein the one or more triggers are modified in response to executing the function associated with the trigger, and wherein modifying the one or more triggers reduces a probability that a condition of the one or more triggers will be satisfied during a subsequent time interval of the communication session.

9 . The system of claim 8 , wherein the service is an automated service that is configured to communicate with the user over the real-time data stream using natural language communications.

10 . The system of claim 8 , wherein the machine-learning model is further configured to generate a predicted intent of the user of the first device.

11 . The system of claim 8 , wherein the operations further include:

executing, in response to modifying the set of triggers, the machine-learning model to generate a new conversation score;

determining that a condition of a particular trigger is satisfied based on the new conversation score;

executing, in response to determining that the condition of the particular trigger is satisfied, a particular function associated with the particular trigger; and

modifying the set of triggers based on the conversation and the real-time data stream.

12 . The system of claim 8 , wherein modifying the set of triggers includes modifying one or more conditions of a corresponding one or more triggers.

13 . The system of claim 8 , wherein modifying the set of triggers includes adding one or more new triggers or removing one or more triggers.

14 . The system of claim 8 , wherein executing the function causes the real-time data stream to connect a second service to the real-time data stream.

15 . A non-transitory machine-readable storage medium storing instructions that when executed by one or more processors, cause the one or more processors to perform operations including:

generating a feature vector from communications of a real-time data stream, wherein the real-time data stream is a representation of a communication session between a user of a first device and a service of a second device, wherein the communications include natural language communications provided by the user;

executing a first machine-learning model using the feature vector, wherein of first machine-learning model is configured to generate a conversation score, wherein the conversation score indicates a quality of natural language communications between the user and the service;

determining that a condition of a trigger of a set of triggers is satisfied based on the conversation score being below a threshold, wherein the conversation score being below the threshold indicates poor quality natural language communications between the user and the service;

facilitating a connection of a third device to the communication session in response to executing a function associated with the trigger, wherein a user of the third device communicates with the user of the first device using natural language communications;

generating a training vector for a second machine-learning model using natural language communications of the real-time data stream that occur after execution of the first machine-learning model, wherein the second machine-learning model is trained using supplemental training data, and wherein the training vector is configured to replace at least a portion of the supplemental training data to improve an accuracy of the second machine-learning model with respect to the communication session;

updating the second machine-learning model using the training vector, wherein the second machine-learning model is configured to manage the set of triggers; and

modifying, using the second machine-learning model, one or more triggers of the set of triggers based on the conversation score and the real-time data stream, wherein the one or more triggers are modified in response to executing the function associated with the trigger, and wherein modifying the one or more triggers reduces a probability that a condition of the one or more triggers will be satisfied during a subsequent time interval of the communication session.

16 . The non-transitory machine-readable storage medium of claim 15 , wherein the service is an automated service that is configured to communicate with the user over the real-time data stream using natural language communications.

17 . The non-transitory machine-readable storage medium of claim 15 , wherein the machine-learning model is further configured to generate a predicted intent of the user of the first device.

18 . The non-transitory machine-readable storage medium of claim 15 , wherein the operations further include:

executing, in response to modifying the set of triggers, the machine-learning model to generate a new conversation score;

determining that a condition of a particular trigger is satisfied based on the new conversation score;

executing, in response to determining that the condition of the particular trigger is satisfied, a particular function associated with the particular trigger; and

modifying the set of triggers based on the conversation score and the real-time data stream.

19 . The non-transitory machine-readable storage medium of claim 15 , wherein modifying the set of triggers includes modifying one or more conditions of a corresponding one or more triggers.

20 . The non-transitory machine-readable storage medium of claim 15 , wherein modifying the set of triggers includes adding one or more new triggers or removing one or more triggers.

Assignments (3)

Continuity (2)

References Cited (10)