# US 2025/0148020 A1 · Automated document analysis

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

- Number: US 2025/0148020 A1
- Document ID: US20250148020A1
- Status: Published application
- Kind: A1
- Application number: 18/939,956
- Filed: 2024-11-07
- Published: 2025-05-08
- Earliest claimed: 2023-11-08
- Assignees: LegalZoom.com, Inc.
- Applicants: LegalZoom.com, Inc.
- Inventors: Vivek Kumar Padmashali; Gaurav Garsa; Selvaraj Karuppusamyu; Rachit Kumar; Jonah Back; James Donald Peters
- Web page: https://patentgrep.com/patent/US20250148020A1

## CPC

- G06F 16/93: Document management systems
- G06F 40/30: Semantic analysis
- G06F 16/353: into predefined classes
- G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191)
- G06F 40/131: Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
- G06F 40/137: Hierarchical processing, e.g. outlines
- G06N 20/00: Machine learning
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Example systems and methods for analyzing and summarizing legal documents using artificial intelligence are disclosed. A system receives a legal document such as a contract or agreement, and utilizes multiple AI models in combination to process and summarize the document. This includes identifying the type of legal document using a natural language model, and then extracting key information like parties, dates, and monetary values. Related clauses within the document are consolidated using a clause consolidation algorithm even if they are not contiguous. Summaries are generated for each section of the document. Additionally, a question-answering module preemptively generates common questions and answers about the agreement to highlight key considerations for the parties involved. By leveraging an ensemble of customized AI models, the system aims to simplify comprehension of legal documents.

## Claims

### Claim 1

A computer-implemented method to categorize a document comprising:
receiving a document;
extracting text from the document;
using an artificial intelligence engine, identifying a document type corresponding to the document from among a plurality of document types;
accessing a database comprising a plurality of document type categories, each document type associated with a respective set of document type categories;
identifying, from the database, a set of document type categories associated with the identified document type;
processing the extracted text to identify text corresponding to each of the set of document type categories associated with the identified document type; and
generating an output comprising the identified text organized according to the set of document type categories.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein identifying, from the database, a set of document type categories associated with the identified document type comprises:
querying the database using the identified document type; and
receiving, from the database, the respective set of document type categories associated with the identified document type.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein processing the extracted text comprises:
dividing the extracted text into segments;
for each segment:
providing the segment to the artificial intelligence engine; and
receiving, from the artificial intelligence engine, an identified document type category corresponding to the segment.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
combining identified text corresponding to a same document type category into a composite segment; and
providing the composite segment to a summarization engine to generate a summary of the composite segment.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the artificial intelligence engine utilizes a natural language model.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein extracting text comprises converting the document to plain text.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein converting the document to plain text comprises removing formatting and non-textual elements.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein dividing the extracted text into segments further comprises removing stop words from each segment.

### Claim 9 (depends on 3)

The computer-implemented method of claim 3, wherein providing the segment to the artificial intelligence engine further comprises encoding the segment.

### Claim 10 (depends on 9)

The computer-implemented method of claim 9, wherein encoding the segment comprises generating a vector representation of the segment.

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, wherein generating the output further comprises formatting the identified text for readability.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, wherein formatting comprises arranging the identified text into paragraphs based on the document type categories.

### Claim 13 (depends on 1)

The computer-implemented method of claim 1, further comprising training the artificial intelligence engine using a plurality of training documents.

### Claim 14 (depends on 13)

The computer-implemented method of claim 13, wherein training the artificial intelligence engine comprises supervised learning techniques.

### Claim 15 (depends on 1)

The computer-implemented method of claim 1, further comprising storing the output in a searchable format.

### Claim 16 (depends on 15)

The computer-implemented method of claim 15, further comprising receiving a search query and returning a portion of the output responsive to the search query.

### Claim 17 (depends on 1)

The computer-implemented method of claim 1, wherein the output is generated as part of a cloud-implemented service.

### Claim 18 (depends on 1)

The method of claim 1, wherein the artificial intelligence engine comprises an ensemble of natural language processing models.

### Claim 19

A computing apparatus comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, configure the at least one processor to perform operations comprising:
receive a document;
extract text from the document;
using an artificial intelligence engine, identify a document type corresponding to the document from among a plurality of document types;
access a database comprising a plurality of document type categories, each document type associated with a respective set of document type categories;
identify, from the database, a set of document type categories associated with the identified document type;
process the extracted text to identify text corresponding to each of the set of document type categories associated with the identified document type; and
generate an output comprising the identified text organized according to the set of document type categories.

### Claim 20

At least one non-transitory computer-readable storage medium including instructions that when executed by at least one processor, cause the at least one processor to perform operations comprising:
receive a document;
extract text from the document;
using an artificial intelligence engine, identify a document type corresponding to the document from among a plurality of document types;
access a database comprising a plurality of document type categories, each document type associated with a respective set of document type categories;
identify, from the database, a set of document type categories associated with the identified document type;
process the extracted text to identify text corresponding to each of the set of document type categories associated with the identified document type; and
generate an output comprising the identified text organized according to the set of document type categories.
