# US 2021/0342709 A1 · Use of Machine Learning to Provide Answer Patterns and Context Descriptions

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

- Number: US 2021/0342709 A1
- Document ID: US20210342709A1
- Status: Published application
- Kind: A1
- Application number: 16/862,495
- Filed: 2020-04-29
- Published: 2021-11-04
- Earliest claimed: 2020-04-29
- Assignees: Airin, Inc.
- Inventors: Linda Klug; Elisha Davidson
- Web page: https://patentgrep.com/patent/US20210342709A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N 20/20: Ensemble learning
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06N 3/08: Learning methods
- G06N 3/10: Interfaces, programming languages or software development kits, e.g. for simulating neural networks
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Technology is described for providing relevant context in order to assist with solving a problem. The method can include a first operation of identifying a graph with a topical problem statement to be solved and plurality of section groups representing sub-topics. The section groups may contain a plurality of topical arguments in a plurality of nodes. Another operation may be receiving a first request for an answer pattern associated with the topical argument. A first response with the answer pattern for the topical argument and a description of the pattern for a user answer to the topical argument may be provided. A second request for a context explanation field associated with the topical argument may be received. A further operation may be providing a context explanation field which explains a context for asking the topical argument.

## Claims

### Claim 1

A method for providing relevant context in order to assist with solving a problem, comprising:
identifying a graph with a topical problem statement to be solved and plurality of section groups representing sub-topics, wherein the section groups contain a plurality of topical arguments in a plurality of nodes;
receiving a first request for an answer pattern associated with the topical argument;
providing a first response with the answer pattern for the topical argument and a description of the pattern for a user answer to the topical argument; and
receiving a second request for a context explanation field associated with the topical argument; and
providing a context explanation field which explains a context for asking the topical argument.

### Claim 2 (depends on 1)

The method as in claim 1, further comprising providing an answer pattern that is an example user answer.

### Claim 3 (depends on 1)

The method as in claim 1, further comprising providing a topical argument that is at least one of: a topical question or investigative statement.

### Claim 4 (depends on 1)

The method as in claim 1, further comprising providing the first response for an answer pattern describing how a correct user answer to the topical argument is to be patterned.

### Claim 5 (depends on 1)

The method as in claim 1, further comprising providing an interface control that when activated displays a goal statement for a question or investigative statement which explains at least one of: why the question is being asked or a context for asking the question.

### Claim 6 (depends on 1)

The method as in claim 1, further comprising using an indicator of access to the answer pattern and context explanation field as additional inputs to machine learning to identify at least one of: additional section groups or topical arguments to be presented.

### Claim 7

A non-transitory machine readable storage medium including instructions embodied thereon to provide relevant context in a graphical user interface in order to assist with solving a problem, wherein the instructions, when executed by at least one processor, comprising:
displaying a portion of a graph with a topical problem statement to be solved and plurality of section groups representing sub-topics, wherein the section groups contain a plurality of topical questions or investigative statements in a plurality of nodes;
enabling a user to access a topical question or investigative statement in a section group;
providing a first interface control that when activated displays an example answer for a topical question or investigative statement and presents how a correct user answer to the topical question is to be patterned; and
providing a second interface control that when activated displays a goal statement for the topical question or topical statement which explains a context for asking the question.

### Claim 8 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, wherein the example answer and the goal statement are linked to the question or investigative statement.

### Claim 9 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising using indicators of access to an answer pattern and context explanation field as additional inputs to machine learning to identify at least one of: additional section groups or additional topical arguments to be presented.

### Claim 10 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising retrieving the example answer for a topical question and a goal statement using a topic of the section group.

### Claim 11 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising retrieving the example answer for a topical question and a goal statement using the problem statement.

### Claim 12 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising:
identifying a use pattern of questions and investigative statements by a user;
using a machine learning model to classify the use pattern; and
presenting an additional section group in the graph in the user interface using the use pattern to determine which additional sub-topics to present.

### Claim 13 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising:
identifying a use pattern for questions, investigative statements, the first interface control to access an example answer, and the second interface control to access the goal statement;
matching the use pattern to an expert pattern of use by an expert using the questions to solve a problem; and
determining a level of expertise of a user based on an amount of use of the first interface control to access an example answer, and the second interface control to access goal statement.

### Claim 14 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising tracking use of the questions and investigative statements by tracking interactions with the questions and investigative statements through a user interface.

### Claim 15 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, further comprising present additional training material to a user about a topic of a section group based on the example answers and correct answer patterns viewed.

### Claim 16 (depends on 7)

The non-transitory machine readable storage medium as in claim 7, wherein the graph is a tree graph with a topical problem statement at a root of the graph.

### Claim 17

A system to provide relevant context via a graphical user interface in order to assist with solving a problem, wherein the instructions, when executed by at least one processor, comprising:
at least one processor;
a memory device including instructions that, when executed by the at least one processor, cause the system to:
identify a graph with a topical problem statement to be solved and plurality of section groups representing sub-topics, wherein the section groups contain a plurality of questions or investigative statements in a plurality of nodes;
enable a user to access a topical question in a section group;
provide a first interface control that when activated displays an example answer for a topical question or topical statement and presents how a correct user answer to the topical question will be patterned; and
provide a second interface control that when activated displays a goal statement for the topical question or topical statement which explains a context for asking the question.

### Claim 18 (depends on 17)

The system as in claim 17, wherein the example answer and the goal statement are linked to the question or investigative statement.

### Claim 19 (depends on 17)

The system as in claim 17, further comprising retrieving the example answer for a topical question and a goal statement using a topic of the section group or a problem statement of the graph.

### Claim 20 (depends on 17)

The system as in claim 17, further comprising:
identifying a use pattern of questions and investigative statements;
using a machine learning model to classify the use pattern; and
presenting an additional section group in the graph in the user interface using the use pattern to determine an additional section group to present.
