US 2025/0232124 A1Published application

Updating A Sentiment Analysis Model

AssigneeOracle International Corporation

InventorMichael Patrick Rodgers

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques for updating a sentiment analysis model in response to feedback for operations that are executed based on an output of the sentiment analysis model are disclosed. The sentiment analysis model analyzes a chat conversation to determine user sentiment. The system executes an operation based on the user sentiment determined by the sentiment analysis model. The operation may be the transfer of the chat conversation from a chatbot to a human agent or the generation of an outbound message by the chatbot. The system receives positive or negative feedback regarding the appropriateness and/or timeliness of the operation. The positive or negative feedback is attributed to the sentiment analysis model. The system generates training data using the feedback. The system then retrains the sentiment analysis model based on the training data.

Claims20

Dependent claims

One or more non-transitory computer readable media comprising instructions which, when executed by one or more hardware processors, cause performance of operations comprising:

obtaining training datasets, wherein a first training dataset of the training datasets comprises:
a first chat conversation;
a first user sentiment of a first user in the first chat conversation;
training a sentiment analysis model based on the training datasets to predict user sentiments based on chat conversations;
executing a chatbot for engaging in a target chat conversation with a second user at least by transmitting outbound messages to a client device associated with the second user;
applying the sentiment analysis model to the target chat conversation to predict a second user sentiment of the second user in the target chat conversation;
based at least on the second user sentiment, detecting that one or more transfer criteria has been met to transfer the target chat conversation from the chatbot to a human agent;
transferring the chat conversation with the second user, from the chatbot to the human agent;
receiving feedback corresponding to the transfer of the target chat conversation with the second user, from the chatbot to the human agent;
based on the feedback, generating an additional training dataset for updating the sentiment analysis model;
and
retraining the sentiment analysis model based on the additional training dataset.

9 more elements

A method comprising:

obtaining training datasets, wherein a first training dataset of the training datasets comprises:
a first chat conversation;
a first user sentiment of a first user in the first chat conversation;
training a sentiment analysis model based on the training datasets to predict user sentiments based on chat conversations;
executing a chatbot for engaging in a target chat conversation with a second user at least by transmitting outbound messages to a client device associated with the second user;
applying the sentiment analysis model to the target chat conversation to predict a second user sentiment of the second user in the target chat conversation;
based at least on the second user sentiment, detecting that one or more transfer criteria has been met to transfer the target chat conversation from the chatbot to a human agent;
transferring the chat conversation with the second user, from the chatbot to the human agent;
receiving feedback corresponding to the transfer of the target chat conversation with the second user, from the chatbot to the human agent;
based on the feedback, generating an additional training dataset for updating the sentiment analysis model;
and
retraining the sentiment analysis model based on the additional training dataset, wherein the method is performed by at least one device including a hardware processor.

9 more elements

A system comprising:

at least one device including a hardware processor;
the system being configured to perform operations comprising:
obtaining training datasets, wherein a first training dataset of the training datasets comprises:
a first chat conversation;
a first user sentiment of a first user in the first chat conversation;
training a sentiment analysis model based on the training datasets to predict user sentiments based on chat conversations;
executing a chatbot for engaging in a target chat conversation with a second user at least by transmitting outbound messages to a client device associated with the second user;
applying the sentiment analysis model to the target chat conversation to predict a second user sentiment of the second user in the target chat conversation;
based at least on the second user sentiment, detecting that one or more transfer criteria has been met to transfer the target chat conversation from the chatbot to a human agent;
transferring the chat conversation with the second user, from the chatbot to the human agent;
receiving feedback corresponding to the transfer of the target chat conversation with the second user, from the chatbot to the human agent;
based on the feedback, generating an additional training dataset for updating the sentiment analysis model;
and
retraining the sentiment analysis model based on the additional training dataset.

11 more elements

Dependencies are inferred from the claim text.