# US 2025/0156911 A1 · Ensemble of language models for improved user support

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0156911 A1
- Document ID: US20250156911A1
- Status: Published application
- Kind: A1
- Application number: 18/510,541
- Filed: 2023-11-15
- Published: 2025-05-15
- Earliest claimed: 2023-11-15
- Assignees: Intuit Inc.
- Applicants: Intuit, Inc.
- Inventors: Jineet Hiren DOSHI; Maya Vered LIVSHITS; Apurva SWARNAKAR; Jingyuan ZHANG
- Web page: https://patentgrep.com/patent/US20250156911A1

## CPC

- G06Q 30/0282: Rating or review of business operators or products
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/30: Semantic analysis
- G06Q 30/016: After-sales
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Certain aspects of the disclosure provide a method for providing user support by generating recommended response for a customer verbatim with an ensemble of machine learning models. The method includes processing a customer verbatim with a topic model trained to identify a topic associated with the customer verbatim. The method further includes processing the customer verbatim with a sentiment model trained to determine a sentiment of the customer verbatim. The method further includes processing the customer verbatim with an actionability model trained to assign an actionability score to the customer verbatim. The method includes processing the topic, the sentiment, and the actionability score with a recommendation model to generate the recommended response to the customer verbatim.

## Claims

### Claim 1

A method for providing user support, comprising:
identifying a topic associated with a customer verbatim with a topic model;
determining a sentiment associated with the customer verbatim with a sentiment model trained to determine a customer's satisfaction based on the customer verbatim;
assigning an actionability score for the customer verbatim with an actionability model, wherein the actionability score indicates an estimated redressability of the customer verbatim; and
processing the topic, the sentiment, and the actionability score with a recommendation model to generate a recommended response to the customer verbatim.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the recommended response to the customer verbatim comprises a resolution for the customer verbatim; and
the method further comprises sending to a user, the resolution for the customer verbatim.

### Claim 3 (depends on 2)

The method of claim 2, wherein the recommended response comprises a communication channel for the user to contact the customer in regards to the customer verbatim.

### Claim 4 (depends on 2)

The method of claim 2, further comprising receiving an indication of activity of the customer associated with the resolution for the customer verbatim.

### Claim 5 (depends on 4)

The method of claim 4, further comprising updating the recommendation model based on the indication of activity of the customer.

### Claim 6 (depends on 1)

The method of claim 1, wherein the topic model is a machine learning model trained to process the customer verbatim to identify the topic associated with the customer verbatim with one or more of: latent dirichlet allocation, latent semantic analysis, non-negative matrix factorization, or BERTopic modeling.

### Claim 7 (depends on 1)

The method of claim 1, wherein the actionability score further indicates a priority for responding to the customer verbatim.

### Claim 8

A method for training an ensemble of machine learning models to provide recommendations for responding to a customer verbatim, comprising:
training a topic model to identify a topic associated with the customer verbatim;
training a sentiment model to determine a sentiment, wherein the sentiment indicates a customer's satisfaction based on the customer verbatim;
training an actionability model to assign an actionability score for the customer verbatim, wherein the actionability score indicates an estimated redressability of the customer verbatim; and
training a recommendation model to generate a recommended response to the customer verbatim, based on the topic, the sentiment, and the actionability score.

### Claim 9 (depends on 8)

The method of claim 8, wherein the topic model is trained to identify the topic associated with the customer verbatim with one or more of: latent dirichlet allocation, latent semantic analysis, non-negative matrix factorization, or BERTopic modeling.

### Claim 10 (depends on 8)

The method of claim 8, wherein:
the recommended response to the customer verbatim comprises a resolution for the customer verbatim; and
the method further comprises sending to a user, the resolution for the customer verbatim.

### Claim 11 (depends on 10)

The method of claim 10, wherein the recommended response comprises a communication channel for the user to contact the customer in regards to the customer verbatim.

### Claim 12 (depends on 10)

The method of claim 10, further comprising receiving an indication of activity of the customer associated with the resolution for the customer verbatim.

### Claim 13 (depends on 12)

The method of claim 12, further comprising updating the recommendation model based on the indication of activity of the customer.

### Claim 14

A processing system, comprising: a memory comprising computer-executable instructions; and a processor configured to execute the computer-executable instructions and cause the processing system to:
identify a topic associated with a customer verbatim with a topic model;
determine a sentiment associated with the customer verbatim with a sentiment model trained to determine a customer's satisfaction;
assign an actionability score for the customer verbatim with an actionability model, wherein the actionability score indicates an estimated redressability of the customer verbatim; and
process the topic, the sentiment, and the actionability score with a recommendation model to generate a recommended response to the customer verbatim.

### Claim 15 (depends on 14)

The processing system of claim 14, wherein:
the recommended response to the customer verbatim comprises a resolution for the customer verbatim; and
the processor is further configured to cause the processing system to send to a user, the resolution for the customer verbatim.

### Claim 16 (depends on 15)

The processing system of claim 15, wherein the processor is further configured to cause the processing system to receive an indication of activity of the customer associated with the resolution for the customer verbatim.

### Claim 17 (depends on 16)

The processing system of claim 16, wherein the processor is further configured to cause the processing system to update the recommendation model based on the indication of activity of the customer.

### Claim 18 (depends on 15)

The processing system of claim 15, wherein the recommended response comprises a communication channel for the user to contact the customer in regards to the customer verbatim.

### Claim 19 (depends on 14)

The processing system of claim 14, wherein the topic model is a machine learning model trained to process the customer verbatim to identify the topic associated with the customer verbatim with one or more of: latent dirichlet allocation, latent semantic analysis, non-negative matrix factorization, or BERTopic modeling.

### Claim 20 (depends on 14)

The processing system of claim 14, wherein the actionability score further indicates a priority for responding to the customer verbatim.
