# US 2022/0028502 A1 · Handling form data errors arising from natural language processing

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

- Number: US 2022/0028502 A1
- Document ID: US20220028502A1
- Status: Published application
- Kind: A1
- Application number: 16/934,061
- Filed: 2020-07-21
- Published: 2022-01-27
- Earliest claimed: 2020-07-21
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Paul Joseph Hake; Igor S. Ramos; Andrew J. Lavery; Scott Carrier
- Web page: https://patentgrep.com/patent/US20220028502A1

## CPC

- G06F 40/174: Form filling; Merging
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G06F 16/93: Document management systems
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/24: Classification techniques
- G06F 18/285: {Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system}
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06V 10/22: by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V 30/246: using linguistic properties, e.g. specific for English or German language
- G06V 30/40: Document-oriented image-based pattern recognition
- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Aspects include receiving a document and classifying at least a subset of the document as having a first type of data. Features are extracted from the document. The extracting includes initiating processing of the at least a subset of the document by a first processing engine that was previously trained to extract features from the first type of data. The extracting also includes initiating processing of a remaining portion of the document not included in the at least a subset of the document by a second processing engine that was previously trained to extract features from a second type of data. The first type of data is different than the second type of data. Features are received from one or both of the first processing engine and the second processing engine. The received features are stored as features of the document.

## Claims

### Claim 1

A method comprising:
receiving a document at a processor;
classifying, by the processor, at least a subset of the document as having a first type of data;
extracting features from the document, the extracting comprising:
initiating processing of the at least a subset of the document by a first processing engine that was previously trained to extract features from the first type of data;
initiating processing of a remaining portion of the document not included in the at least a subset of the document by a second processing engine that was previously trained to extract features from a second type of data, the first type of data different than the second type of data; and
receiving features from one or both of the first processing engine and the second processing engine; and
storing, by the processor, the received features as features of the document.

### Claim 2 (depends on 1)

The method of claim 1, wherein the first type of data is form data and the second type of data is sentence or paragraph data.

### Claim 3 (depends on 1)

The method of claim 1, further comprising combining the received features to generate combined features of the document, wherein the features of the document that are stored are the combined features of the document.

### Claim 4 (depends on 1)

The method of claim 1, wherein the document is a healthcare document for a patient and the method further comprises associating the received features with the patient.

### Claim 5 (depends on 4)

The method of claim 4, wherein the healthcare document is a medical record.

### Claim 6 (depends on 1)

The method of claim 1, wherein the processing by one or both of the first processing engine and the second processing engine includes a natural language processing (NLP) engine.

### Claim 7 (depends on 1)

The method of claim 1, further comprising converting the document to a text format prior to the classifying.

### Claim 8 (depends on 1)

The method of claim 1, further comprising converting the document to an image format prior to the classifying.

### Claim 9 (depends on 1)

The method of claim 1, wherein the classifying is performed by a classifier engine that was previously trained to identify the first type of data in documents.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
receiving a second document that does not include the first type of data; and
extracting features from the second document, the extracting features from the second document comprising:
initiating processing of the second document by the second processing engine; and
receiving second features from the second processing engine; and
storing, by the processor, the received second features as features of the second document.

### Claim 11

A system comprising:
one or more processors for executing computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
receiving a document at a processor of the one or more processors;
classifying, by the processor, at least a subset of the document as having a first type of data;
extracting features from the document, the extracting comprising:
initiating processing of the at least a subset of the document by a first processing engine that was previously trained to extract features from the first type of data;
initiating processing of a remaining portion of the document not included in the at least a subset of the document by a second processing engine that was previously trained to extract features from a second type of data, the first type of data different than the second type of data; and
receiving features from one or both of the first processing engine and the second processing engine; and
storing, by the processor, the received features as features of the document.

### Claim 12 (depends on 11)

The system of claim 11, wherein the first type of data is form data and the second type of data is sentence or paragraph data.

### Claim 13 (depends on 11)

The system of claim 11, wherein the operations further comprise combining the received features to generate combined features of the document, wherein the features of the document that are stored are the combined features of the document.

### Claim 14 (depends on 11)

The system of claim 11, wherein the document is a healthcare document for a patient and the method further comprises associating the received features with the patient.

### Claim 15 (depends on 14)

The system of claim 14, wherein the healthcare document is a medical record.

### Claim 16 (depends on 11)

The system of claim 11, wherein the processing by one or both of the first processing engine and the second processing engine includes natural language processing (NLP) engine.

### Claim 17 (depends on 11)

The system of claim 11, wherein the classifying is performed by a classifier engine that was previously trained to identify the first type of data in documents.

### Claim 18 (depends on 11)

The system of claim 11, wherein the operations further comprise: receiving a second document that does not include the first type of data; and
extracting features from the second document, the extracting features from the second document comprising:
initiating processing of the second document by the second processing engine; and
receiving second features from the second processing engine; and
storing, by the processor, the received second features as features of the second document.

### Claim 19

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
receiving a document at a processor of the one or more processors;
classifying, by the processor, at least a subset of the document as having a first type of data;
extracting features from the document, the extracting comprising:
initiating processing of the at least a subset of the document by a first processing engine that was previously trained to extract features from the first type of data;
initiating processing of a remaining portion of the document not included in the at least a subset of the document by a second processing engine that was previously trained to extract features from a second type of data, the first type of data different than the second type of data; and
receiving features from one or both of the first processing engine and the second processing engine; and
storing, by the processor, the received features as features of the document.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein the first type of data is form data and the second type of data is sentence or paragraph data.

### Claim 21

A method comprising:
receiving, by a processor, a document that includes a form;
determining, by the processor, a style of the form;
selecting, by the processor, a natural language processing (NLP) engine based at least in part on the style of the form, wherein the selected NLP engine was previously trained to extract features from forms having the determined style; and
initiating, by the processor, processing of the form by the selected NLP engine.

### Claim 22 (depends on 21)

The method of claim 21, wherein the determining is performed by a classifier engine that was previously trained to identify styles of forms.

### Claim 23 (depends on 21)

The method of claim 21, wherein the style is a check box style form.

### Claim 24 (depends on 21)

The method of claim 21, wherein the style is a circle applicable conditions style form.

### Claim 25 (depends on 21)

The method of claim 21, wherein the style is a radio button style form.
