User Profile Sentiment Analysis

Patent metadata

Field	Value
Publication number	US-2026004155-A1
Application number	US-202418757363-A
Country	US
Kind code	A1
Filing date	Jun 27, 2024
Priority date	Jun 27, 2024
Publication date	Jan 1, 2026
Grant date	—

Abstract

A system can perform a first sentiment-based analysis based on interaction data representative of an interaction between the system and a user profile. The system can perform a second sentiment-based analysis based on publication data representative of a publication associated with the user profile. The system can generate a sentiment-based user profile for the user profile based on respective results of the first sentiment-based analysis and the second sentiment-based analysis. The system can input the sentiment-based user profile and impact data representative of an impact that the user profile has on an entity associated with the system to a trained artificial intelligence model, to produce an output that indicates a proposed action to take with respect to the user profile. The system can store an indication of the output.

First claim

What is claimed is:

1 . A system, comprising:
at least one processor; and at least one memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, comprising:
performing a first sentiment-based analysis based on interaction data representative of an interaction between the system and a user profile;
performing a second sentiment-based analysis based on publication data representative of a publication associated with the user profile;
generating a sentiment-based user profile for the user profile based on respective results of the first sentiment-based analysis and the second sentiment-based analysis;
inputting the sentiment-based user profile and impact data representative of an impact that the user profile has on an entity associated with the system to a trained artificial intelligence model, to produce an output that indicates a proposed action to take with respect to the user profile; and
storing an indication of the output.

2 . The system of claim 1 , wherein the system performs the performing of the first sentiment-based analysis, the performing of the second sentiment-based analysis, the generating, and the inputting using cloud computing service of a cloud computing platform.

3 . The system of claim 1 , wherein the operations further comprise:
generating a response to the user profile based on the output.

4 . The system of claim 3 , wherein the operations further comprise:
conveying the response to a device associated with the user profile via a chatbot.

5 . The system of claim 3 , wherein the operations further comprise:
presenting the response in a user interface that is accessible to a customer service agent associated with the system.

6 . The system of claim 1 , wherein the interaction is a previous interaction relative to a current interaction with the user profile, and wherein the publication is a previous publication relative to the current interaction.

7 . The system of claim 1 , wherein the performing of the first sentiment-based analysis is in response to the interaction occurring, or wherein the performing of the second sentiment-based analysis is in response to the publication occurring.

8 . A method, comprising:
performing, by a system comprising at least one processor, a first sentiment-based analysis with respect to an interaction between the system and a user profile; performing, by the system, a second sentiment-based analysis with respect to a publication associated with the user profile; generating, by the system, a sentiment-based user profile for the user profile based on the first sentiment-based analysis and the second sentiment-based analysis; and providing, by the system as input to a trained artificial intelligence model, the sentiment-based user profile and an impact that the user profile is determined to have on an entity associated with the system, to produce an output, from the trained artificial intelligence model, that indicates a proposed action to take with respect to the user profile.

9 . The method of claim 8 , wherein the interaction comprises at least one of an audio interaction, a text interaction, or a video interaction.

10 . The method of claim 8 , wherein the interaction comprises a voice interaction involving at least one voice, and wherein the first sentiment-based analysis is performed based on at least one tone of the at least one voice of the voice interaction, at least one speech pattern of the at least one voice of the voice interaction, or at least one vocal cue of the at least one voice of the voice interaction.

11 . The method of claim 10 , further comprising:
performing, by the system, feature engineering on the at least one voice of the voice interaction to extract features of the voice interaction, resulting in extracted features; and providing, by the system, the extracted features of the voice interaction as input to a sentiment analysis model that performs the first sentiment-based analysis.

12 . The method of claim 8 , wherein the interaction comprises a marketing interaction with marketing information associated with the user profile.

13 . The method of claim 12 , wherein the marketing information comprises at least one of importance information representative of an importance of the user profile to the entity, money information representative of an amount of money associated with the user profile that is paid to the entity, or user profile information about the user profile.

14 . The method of claim 8 , wherein the publication comprises a social media posting associated with the user profile.

15 . A non-transitory computer-readable medium comprising instructions that, in response to execution, cause a system comprising at least one processor to perform operations, comprising:
generating a sentiment-based user profile for a user profile based on a first sentiment-based analysis on an interaction between the system and the user profile, and a second sentiment-based analysis on a publication associated with the user profile; and inputting the sentiment-based user profile and an impact that the user profile has on an entity associated with the system to a trained artificial intelligence model, resulting in an output from the trained artificial intelligence model that indicates a proposed action to take with respect to the user profile.

16 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise, based on the output, triggering an alert.

17 . The non-transitory computer-readable medium of claim 15 , wherein the operations further comprise, based on the output, escalating a case associated with the user profile.

18 . The non-transitory computer-readable medium of claim 17 , wherein the escalating of the case is performed based on the trained artificial intelligence model identifying a negative sentiment associated with the user profile that satisfies a negativity criterion.

19 . The non-transitory computer-readable medium of claim 15 , wherein the output identifies an aspect of communications that modifies a first metric associated with a positive sentiment associated with the user profile or modifies a second metric associated with a negative sentiment associated with the user profile.

20 . The non-transitory computer-readable medium of claim 15 , wherein the output identifies a topic that modifies a first metric associated with a positive sentiment associated with the user profile or modifies a second metric associated with a negative sentiment associated with the user profile.

Assignees

• Dell Products Lp

Inventors

• Gehtman Yevgeni
• Shachar Tomer
• Buchman Ophir

Classifications

• G06Q30/015 Primary

  Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk · CPC title

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title