# US 2025/0095803 A1 · Context aware chunking for automatic soap note generation

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

- Number: US 2025/0095803 A1
- Document ID: US20250095803A1
- Status: Published application
- Kind: A1
- Application number: 18/829,834
- Filed: 2024-09-10
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Oracle International Corporation
- Applicants: Oracle International Corporation
- Inventors: Syed Najam Abbas Zaidi; Shiquan Yang; Poorya Zaremoodi; Nitika Mathur; Shubham Pawankumar Shah; Arash Shamaei; Sagar Kalyan Gollamudi
- Web page: https://patentgrep.com/patent/US20250095803A1

## CPC

- G06F 40/30: Semantic analysis
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G06F 40/205: Parsing
- G06F 40/295: Named entity recognition
- G06F 40/56: Natural language generation
- G06N 3/045: Combinations of networks
- G06N 3/0475: Generative networks
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G16H 10/00: ICT specially adapted for the handling or processing of patient-related medical or healthcare data (for medical reports G16H15/00; for therapies or health-improving plans G16H20/00; for the handling or processing of medical images G16H30/00)
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Techniques are disclosed for automatically generating Subjective, Objective, Assessment and Plan (SOAP) notes. Particularly, techniques are disclosed for identifying entities for automatic SOAP note generation. A text transcript is accessed and segmented into portions. The text transcript can correspond to an interaction between a first entity and a second entity. One or more entities for the respective portions are identified using one or more machine-learning models. Facts are from the respective portions using the one or more machine-learning models based at least in-part on the context of the respective portions. A SOAP note is generated using the one or more machine-learning models and based at least in-part on the facts. The SOAP note can be stored in a database in association with at least one of the first entity and the second entity.

## Claims

### Claim 1

A computer-implemented method comprising:
accessing a text transcript, the text transcript corresponding to an interaction between a plurality of entities;
segmenting the text transcript into a plurality of portions;
for each respective portion of the plurality of portions:
identifying, using one or more machine-learning models, one or more entities included in the respective portion,
extracting, using the one or more machine-learning models, one or more facts from the respective portion based at least in-part on the one or more entities and context information of the respective portion, the context information comprising information included in one or more other portions of the plurality of portions, and
adding the one or more facts to a collection of facts;
generating, using the one or more machine-learning models, a Subjective, Objective, Assessment and Plan (SOAP) note based at least in-part on a set of facts derived from the collection of facts; and
storing the SOAP note in a database associated with at least one entity of the plurality of entities.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the text transcript comprises a first number of tokens, wherein each portion of the plurality of portions comprises a second number of tokens that is less than the first number of tokens, and wherein segmenting the text transcript into the plurality of portions comprises selecting a respective portion of the text transcript having a number of tokens corresponding to the second number of tokens and determining whether the respective portion of the text transcript satisfies a predetermined criteria.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein respective portion includes a sequence of turns of a dialog between one or more entities of the plurality of entities, the sequence of turns comprising a first turn, a last turn, and a plurality of turns between the first turn and the last turn, and determining whether the respective portion of the text transcript satisfies the predetermined criteria comprises determining whether the last turn of the sequence of turns includes a question or is an incomplete sentence.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, further comprising:
in response to determining that the last turn of the sequence of turns includes a question, adding a turn from another portion of the plurality of portions, the turn answering the question.

### Claim 5 (depends on 3)

The computer-implemented method of claim 3, further comprising:
in response to determining that the last turn of the sequence of turns is an incomplete sentence, completing the incomplete sentence by adding a turn from another portion of the plurality of portions.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the context information comprises at least part of a portion of the plurality of portions that occurs before the respective portion in the text transcript, at least part of a portion of the plurality of portions that occurs after the respective portion in the text transcript, or a combination thereof.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein extracting, using the one or more machine-learning models, the one or more facts from the respective portion comprises using a machine-learning model prompt to extract the one or more facts from the respective portion, the machine-learning model prompt comprising the respective portion, and the context information, and one or more instructions.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein identifying, using one or more machine-learning models, the one or more entities included in the respective portion comprises using a machine-learning model prompt to identify the one or more entities included in the respective portion, the machine-learning model prompt comprising the respective portion and one or more instructions.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein generating, using the one or more machine-learning models, the SOAP note comprises:
dividing the set of facts into subsets of facts;
extracting information associated with a particular entity of the plurality of entities from an electronic record associated with the particular entity;
using the one or more machine-learning models to generate a set of note sections based at least in-part on the subsets of facts and the information; and
combining note sections of the set of note sections into the SOAP note.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein a first entity of the plurality of entities is a healthcare provider, wherein a second entity of the plurality of entities is a patient associated with the healthcare provider, and wherein storing the SOAP note in the database comprises storing the SOAP note in an electronic health record associated with the patient.

### Claim 11

A system comprising:
one or more processing systems; and
one or more computer-readable media storing instructions which, when executed by the one or more processing systems, cause the system to perform operations comprising:
accessing a text transcript, the text transcript corresponding to an interaction between a plurality of entities;
segmenting the text transcript into a plurality of portions;
for each respective portion of the plurality of portions:
identifying, using one or more machine-learning models, one or more entities included in the respective portion,
extracting, using the one or more machine-learning models, one or more facts from the respective portion based at least in-part on the one or more entities and context information of the respective portion, the context information comprising information included in one or more other portions of the plurality of portions, and
adding the one or more facts to a collection of facts;
generating, using the one or more machine-learning models, a Subjective, Objective, Assessment and Plan (SOAP) note based at least in-part on a set of facts derived from the collection of facts; and
storing the SOAP note in a database associated with at least one entity of the plurality of entities.

### Claim 12 (depends on 11)

The system of claim 11, wherein the text transcript comprises a first number of tokens, wherein each portion of the plurality of portions comprises a second number of tokens that is less than the first number of tokens, and wherein segmenting the text transcript into the plurality of portions comprises selecting a respective portion of the text transcript having a number of tokens corresponding to the second number of tokens and determining whether the respective portion of the text transcript satisfies a predetermined criteria.

### Claim 13 (depends on 12)

The system of claim 12, wherein respective portion includes a sequence of turns of a dialog between one or more entities of the plurality of entities, the sequence of turns comprising a first turn, a last turn, and a plurality of turns between the first turn and the last turn, and determining whether the respective portion of the text transcript satisfies the predetermined criteria comprises determining whether the last turn of the sequence of turns includes a question or is an incomplete sentence.

### Claim 14 (depends on 13)

The system of claim 13, the operations further comprising:
in response to determining that the last turn of the sequence of turns includes a question, adding a turn from another portion of the plurality of portions, the turn answering the question.

### Claim 15 (depends on 13)

The system of claim 13, the operations further comprising:
in response to determining that the last turn of the sequence of turns is an incomplete sentence, completing the incomplete sentence by adding a turn from another portion of the plurality of portions.

### Claim 16 (depends on 11)

The system of claim 11, wherein the context information comprises at least part of a portion of the plurality of portions that occurs before the respective portion in the text transcript, at least part of a portion of the plurality of portions that occurs after the respective portion in the text transcript, or a combination thereof.

### Claim 17 (depends on 11)

The system of claim 11, wherein extracting, using the one or more machine-learning models, the one or more facts from the respective portion comprises using a machine-learning model prompt to extract the one or more facts from the respective portion, the machine-learning model prompt comprising the respective portion, and the context information, and one or more instructions.

### Claim 18 (depends on 11)

The system of claim 11, wherein identifying, using one or more machine-learning models, the one or more entities included in the respective portion comprises using a machine-learning model prompt to identify the one or more entities included in the respective portion, the machine-learning model prompt comprising the respective portion and one or more instructions.

### Claim 19 (depends on 11)

The system of claim 11, wherein generating, using the one or more machine-learning models, the SOAP note comprises:
dividing the set of facts into subsets of facts;
extracting information associated with a particular entity of the plurality of entities from an electronic record associated with the particular entity;
using the one or more machine-learning models to generate a set of note sections based at least in-part on the subsets of facts and the information; and
combining note sections of the set of note sections into the SOAP note.

### Claim 20 (depends on 11)

The system of claim 11, wherein a first entity of the plurality of entities is a healthcare provider, wherein a second entity of the plurality of entities is a patient associated with the healthcare provider, and wherein storing the SOAP note in the database comprises storing the SOAP note in an electronic health record associated with the patient.

### Claim 21

One or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations comprising:
accessing a text transcript, the text transcript corresponding to an interaction between a plurality of entities;
segmenting the text transcript into a plurality of portions;
for each respective portion of the plurality of portions:
identifying, using one or more machine-learning models, one or more entities included in the respective portion,
extracting, using the one or more machine-learning models, one or more facts from the respective portion based at least in-part on the one or more entities and context information of the respective portion, the context information comprising information included in one or more other portions of the plurality of portions, and
adding the one or more facts to a collection of facts;
generating, using the one or more machine-learning models, a Subjective, Objective, Assessment and Plan (SOAP) note based at least in-part on a set of facts derived from the collection of facts; and
storing the SOAP note in a database associated with at least one entity of the plurality of entities.

### Claim 22 (depends on 21)

The one or more non-transitory computer-readable media of claim 21, wherein the text transcript comprises a first number of tokens, wherein each portion of the plurality of portions comprises a second number of tokens that is less than the first number of tokens, and wherein segmenting the text transcript into the plurality of portions comprises selecting a respective portion of the text transcript having a number of tokens corresponding to the second number of tokens and determining whether the respective portion of the text transcript satisfies a predetermined criteria.

### Claim 23 (depends on 22)

The one or more non-transitory computer-readable media of claim 22, wherein respective portion includes a sequence of turns of a dialog between one or more entities of the plurality of entities, the sequence of turns comprising a first turn, a last turn, and a plurality of turns between the first turn and the last turn, and determining whether the respective portion of the text transcript satisfies the predetermined criteria comprises determining whether the last turn of the sequence of turns includes a question or is an incomplete sentence.

### Claim 24 (depends on 23)

The one or more non-transitory computer-readable media of claim 23, the operations further comprising:
in response to determining that the last turn of the sequence of turns includes a question, adding a turn from another portion of the plurality of portions, the turn answering the question.

### Claim 25 (depends on 23)

The one or more non-transitory computer-readable media of claim 23, the operations further comprising:
in response to determining that the last turn of the sequence of turns is an incomplete sentence, completing the incomplete sentence by adding a turn from another portion of the plurality of portions.

### Claim 26 (depends on 21)

The one or more non-transitory computer-readable media of claim 21, wherein the context information comprises at least part of a portion of the plurality of portions that occurs before the respective portion in the text transcript, at least part of a portion of the plurality of portions that occurs after the respective portion in the text transcript, or a combination thereof.

### Claim 27 (depends on 21)

The one or more non-transitory computer-readable media of claim 21, wherein extracting, using the one or more machine-learning models, the one or more facts from the respective portion comprises using a machine-learning model prompt to extract the one or more facts from the respective portion, the machine-learning model prompt comprising the respective portion, and the context information, and one or more instructions.

### Claim 28 (depends on 21)

The one or more non-transitory computer-readable media of claim 21, wherein identifying, using one or more machine-learning models, the one or more entities included in the respective portion comprises using a machine-learning model prompt to identify the one or more entities included in the respective portion, the machine-learning model prompt comprising the respective portion and one or more instructions.

### Claim 29 (depends on 21)

The one or more non-transitory computer-readable media of claim 21, wherein generating, using the one or more machine-learning models, the SOAP note comprises:
dividing the set of facts into subsets of facts;
extracting information associated with a particular entity of the plurality of entities from an electronic record associated with the particular entity;
using the one or more machine-learning models to generate a set of note sections based at least in-part on the subsets of facts and the information; and
combining note sections of the set of note sections into the SOAP note.

### Claim 30 (depends on 21)

The one or more non-transitory computer-readable media of claim 21, wherein a first entity of the plurality of entities is a healthcare provider, wherein a second entity of the plurality of entities is a patient associated with the healthcare provider, and wherein storing the SOAP note in the database comprises storing the SOAP note in an electronic health record associated with the patient.
