# US 2021/0081602 A1 · Automatically Identifying Chunks in Sets of Documents

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

- Number: US 2021/0081602 A1
- Document ID: US20210081602A1
- Status: Published application
- Kind: A1
- Application number: 16/986,139
- Filed: 2020-08-05
- Published: 2021-03-18
- Earliest claimed: 2019-09-16
- Assignees: Docugami, Inc.
- Applicants: Docugami, Inc.
- Inventors: Andrew Begun; Steven DeRose; Taqi Jaffri; Luis Marti Orosa; Michael Palmer; Jean Paoli; Christina Pavlopoulou; Elena Pricoiu; Swagatika Sarangi; Marcin Sawicki; Manar Shehadeh; Michael Taron; Bhaven Toprani; Zubin Rustom Wadia; David Watson; Eric White; Joshua Yongshin Fan; Kush Gupta; Andrew Minh Hoang; Zhanlin Liu; Jerome George Paliakkara; Zhaofeng Wu; Yue Zhang; Xiaoquan Zhou
- Web page: https://patentgrep.com/patent/US20210081602A1

## CPC

- G06F 40/186: Templates
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06F 16/2457: with adaptation to user needs
- G06F 16/248: Presentation of query results
- G06F 16/93: Document management systems
- G06F 40/106: Display of layout of documents; Previewing
- G06F 40/117: Tagging; Marking up (details of markup languages G06F40/143); Designating a block; Setting of attributes (style sheets, e.g. eXtensible Stylesheet Language Transformation [XSLT], G06F40/154)
- G06F 40/131: Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces
- G06F 40/169: Annotation, e.g. comment data or footnotes
- G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking
- G06F 40/295: Named entity recognition
- G06F 40/30: Semantic analysis
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N 3/09: Supervised learning
- G06N 3/091: Active learning
- G06N 20/00: Machine learning
- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G06V 30/416: Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
- G06V 30/418: Document matching, e.g. of document images
- G06F 40/205: Parsing
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set). Similarity is not limited to exact or fuzzy string or property comparisons, but may include similarity of natural language grammatical structure, ML (machine learning) techniques such as measuring similarity of word, chunk, and other embeddings, and the datatypes and semantic roles of previously-identified chunks.

## Claims

### Claim 1

A method implemented on a computer system executing instructions for analyzing and annotating documents, the method comprising:
accessing a document set that contains a plurality of documents;
automatically identifying chunks within individual documents in the document set (a) based on the content, layout and contexts in the individual document; and (b) based on patterns of content, layout and contexts across the documents in the document set; and
annotating documents in the document set based on analysis of the identified chunks from documents within the document set.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
assembling the document set by clustering documents into the document set based on similarity of content and/or layout.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein automatically identifying chunks within individual documents in the document set is further (c) based on identifying semantic roles within the individual document; and (d) based on identifying counterpart chunks in different documents in the document set, wherein counterpart chunks play a same semantic role in different documents.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein identifying counterpart chunks in different documents comprises:
identifying content that is different in different documents but occurs within substantially similar contexts within the different documents.

### Claim 5 (depends on 3)

The computer-implemented method of claim 3, wherein identifying counterpart chunks in different documents comprises:
identifying content that is substantially the same in different documents.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
annotating some of the identified chunks with metadata describing the chunk, wherein identifying counterpart chunks in different documents is based on similarity of the metadata.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on patterns across the documents in the document set comprises:
identifying, in an individual document, a chunk that is commonly occurring in the documents of the document set but does not appear to occur in the individual document.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the identified chunks comprise:
field chunks that contain content within the documents suitable for use as fields in document templates; and
structural chunks that contain content comprising structures within the layout of the documents.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein some of the field chunks are hierarchical and contain other chunks as sub-chunks.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein some of the identified chunks contain content that is descriptive of semantic roles played by other chunks.

### Claim 11 (depends on 1)

The computer-implemented method of claim 1, further comprising:
annotating some of the identified chunks with a datatype of the chunk and a semantic role of the chunk.

### Claim 12 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on layout comprises:
grouping line-oriented text into structural chunks, wherein the grouping is based on word shapes, first and last tokens, formatting characteristics, and/or punctuation.

### Claim 13 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on layout comprises:
identifying spatial boundaries of structural chunks using machine learning inference trained on tiles of page images.

### Claim 14 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on layout comprises:
identifying spatial boundaries of structural chunks using artificial intelligence-based visual recognition of geometric patterns of the layout.

### Claim 15 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on layout comprises:
identifying structural chunks based on layout of non-text structural features, wherein the non-text structural features comprise at least one of a figure, a table, a sidebar, a footnote, and a page header or footer.

### Claim 16 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on content comprises:
identifying chunks using AI techniques for topic estimation.

### Claim 17 (depends on 1)

The computer-implemented method of claim 1, wherein identifying chunks based on content comprises:
using few-shot Named Entity recognition techniques to identify chunks within the set of documents.

### Claim 18 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving user corrections for incorrectly identified chunks; and
improving the step of automatically identifying chunks in response to the user corrections.

### Claim 19

A non-transitory computer-readable storage medium storing executable computer program instructions for analyzing and improving documents, the instructions executable by a computer system and causing the computer system to perform a method comprising:
accessing a document set that contains a plurality of documents;
automatically identifying chunks within individual documents in the document set (a) based on the content, layout and contexts in the individual document; and (b) based on patterns of content, layout and contexts across the documents in the document set; and
annotating documents in the document set based on analysis of the identified chunks from documents within the document set.

### Claim 20

A computer system for analyzing and improving documents, the computer system comprising:
a storage medium for receiving and storing a document set that contains a plurality of documents; and
a processor system having access to the storage medium and executing an application program for analyzing and annotating documents, wherein the processor system executing the application program:
automatically identifies chunks within individual documents in the document set (a) based on the content, layout and contexts in the individual document; and (b) based on patterns of content, layout and contexts across the documents in the document set; and
annotates documents in the document set based on analysis of the identified chunks from documents within the document set