# US 2026/0228411 A1 · Automated document integration

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

- Number: US 2026/0228411 A1
- Document ID: US20260228411A1
- Status: Published application
- Kind: A1
- Application number: 19/042,694
- Filed: 2025-01-31
- Published: 2026-08-06
- Earliest claimed: 2025-01-31
- Assignees: Intuit Inc.
- Applicants: Intuit Inc.
- Inventors: Vignesh Thirukazhukundram SUBRAHMANIAM; Nhung HO; Ashok SRIVASTAVA; Sricharan Kallur Palli KUMAR
- Web page: https://patentgrep.com/patent/US20260228411A1

## CPC

- G06F 16/93: Document management systems
- G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191)
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06Q 10/10: Office automation; Time management
- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- G06V 30/10: Character recognition
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Aspects of the present disclosure relate to automated document integration. Embodiments include receiving one or more documents from a user. Embodiments further include extracting, using a computer vision machine learning model, a first data item from the one or more documents. Embodiments further include generating a prompt based on a second data item not being present in the one or more documents, wherein the prompt comprises a request for the user to provide the second data item. Embodiments further include receiving, based on the prompt, an additional document from the user. Embodiments further extracting, using the computer vision machine learning model, the second data item from the additional document. Embodiments further include generating, via a particular machine learning model based on the first data item and the second data item, an electronic document that corresponds to a particular format.

## Claims

### Claim 1

A method of automated document integration, comprising:
receiving one or more documents from a user;
extracting, using a computer vision machine learning model, a first data item from the one or more documents;
generating a prompt based on a second data item not being present in the one or more documents, wherein the prompt comprises a request for the user to provide the second data item;
receiving, based on the prompt, an additional document from the user;
extracting, using the computer vision machine learning model, the second data item from the additional document; and
generating, via a particular machine learning model based on the first data item and the second data item, an electronic document that corresponds to a particular format.

### Claim 2 (depends on 1)

The method of claim 1, wherein the computer vision machine learning model is further configured to generate a respective confidence score with respect to each data item in the one or more documents.

### Claim 3 (depends on 2)

The method of claim 2, wherein the prompt is generated based on the respective confidence score generated with respect to the second data item failing to meet a particular threshold.

### Claim 4 (depends on 2)

The method of claim 2, wherein the user is prompted to confirm that the second data item has been correctly extracted based on a confidence score for the extracted second data item failing to meet a given threshold.

### Claim 5 (depends on 1)

The method of claim 1, further comprising using an additional computer vision machine learning model that is configured to extract an additional type of information to extract a third data item, wherein generating the electronic document is further based on the third data item.

### Claim 6 (depends on 1)

The method of claim 1, further comprising retraining the computer vision machine learning model based on feedback received from the user based on the electronic document.

### Claim 7 (depends on 1)

The method of claim 1, further comprising retraining the particular machine learning model based on feedback received from the user based on the electronic document.

### Claim 8 (depends on 1)

The method of claim 1, wherein the first data item comprises a classification for a given document of the one or more documents.

### Claim 9 (depends on 1)

The method of claim 1, wherein the prompt is generated by a given machine learning model.

### Claim 10

A method of automated document integration, comprising:
receiving one or more documents from a user;
classifying, using a first computer vision machine learning model that is configured to classify documents, each of the one or more documents;
identifying, based on the classifying, using a second computer vision machine learning model that is configured to identify entities, a given entity that is referenced in a given document;
extracting, from the one or more documents, based on the classifying, using a third computer vision machine learning model that is configured to extract information associated with particular entities, a first item of information associated with the given entity;
generating, based on a determination that a second item of information associated with the given entity is not present in the one or more documents, a prompt comprising a request for the user to provide the second item of information;
receiving, based on the prompt, an additional document from the user;
extracting, using a given computer vision machine learning model, the second item of information from the additional document; and
generating, via a generative machine learning model based on the identified given entity, the first item of information, and the second item of information, an electronic document that corresponds to a particular format.

### Claim 11 (depends on 10)

The method of claim 10, wherein the third computer vision machine learning model is configured to generate a respective confidence score with respect to each data item in a given document.

### Claim 12 (depends on 11)

The method of claim 11, wherein the prompt is generated based on the respective confidence score generated with respect to the second item of data failing to meet a particular threshold.

### Claim 13 (depends on 11)

The method of claim 11, wherein the user is prompted to confirm that the second item of information has been correctly extracted based on a confidence score for the extracted second item of information failing to meet a given threshold.

### Claim 14 (depends on 11)

The method of claim 11, further comprising retraining one or more of the first computer vision machine learning model or the second computer vision machine learning model based on feedback received from the user based on the electronic document.

### Claim 15 (depends on 11)

The method of claim 11, further comprising retraining the generative machine learning model based on feedback received from the user based on the electronic document.

### Claim 16

A system for automated document integration, comprising:
one or more processors; and
a memory comprising instructions that, when executed by the one or more processors, cause the system to:
receive one or more documents from a user;
extract, using a computer vision machine learning model, a first data item from the one or more documents;
generate a prompt based on a second data item not being present in the one or more documents, wherein the prompt comprises a request for the user to provide the second data item;
receive, based on the prompt, an additional document from the user;
extract, using the computer vision machine learning model, the second data item from the additional document; and
generate, via a particular machine learning model based on the first data item and the second data item, an electronic document that corresponds to a particular format.

### Claim 17 (depends on 16)

The system of claim 16, wherein the computer vision machine learning model is configured to generate a respective confidence score with respect to each data item in the one or more documents.

### Claim 18 (depends on 17)

The system of claim 17, wherein the prompt is generated based on the respective confidence score generated with respect to the second data item failing to meet a particular threshold.

### Claim 19 (depends on 16)

The system of claim 16, wherein the instructions further cause the system to retrain the computer vision machine learning model based on feedback received from the user based on the electronic document.

### Claim 20 (depends on 16)

The system of claim 16, wherein the instructions further cause the system to retrain the particular machine learning model based on feedback received from the user based on the electronic document.
