# US 2023/0273906 A1 · Dynamic selection of an aeronautical data provider

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

- Number: US 2023/0273906 A1
- Document ID: US20230273906A1
- Status: Published application
- Kind: A1
- Application number: 17/680,731
- Filed: 2022-02-25
- Published: 2023-08-31
- Earliest claimed: 2022-02-25
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Marco Gaertner; Ralf Rene Cabos
- Web page: https://patentgrep.com/patent/US20230273906A1

## CPC

- G06F 16/215: Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
- 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

Apparatuses, methods, systems, and program products are disclosed for dynamic selection of an aeronautical data provider. An apparatus includes a processor and a memory that stores code executable by the processor to receive streams of aeronautical data from a plurality of aeronautical data providers streaming aeronautical data from different geographic locations, determine a quality of each of the received streams of aeronautical data by checking the aeronautical data against data provided by at least one secondary data source that has a known quality, select an aeronautical data provider of the plurality of aeronautical data providers that provides a stream of aeronautical data that is closest to the data provided by the at least one secondary data source, and expose aeronautical data from the stream of aeronautical data of the selected aeronautical data provider to an end user according to one or more parameters.

## Claims

### Claim 1

An apparatus, comprising:
a processor; and
a memory that stores code executable by the processor to:
receive streams of aeronautical data from a plurality of aeronautical data providers streaming aeronautical data from different geographic locations;
determine a quality of each of the received streams of aeronautical data by checking the aeronautical data against data provided by at least one secondary data source that has a known quality;
select an aeronautical data provider of the plurality of aeronautical data providers that provides a stream of aeronautical data that is closest to the data provided by the at least one secondary data source; and
expose aeronautical data from the stream of aeronautical data of the selected aeronautical data provider to an end user according to one or more parameters.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the code is executable by the processor to normalize data of each of the streams of aeronautical data from the plurality of aeronautical data providers.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the code is executable by the processor to group the aeronautical data that are normalized from each of the streams of aeronautical data by data attributes.

### Claim 4 (depends on 3)

The apparatus of claim 3, wherein the data attributes are selected from the group comprising latitude, longitude, heading, altitude, speed, time of day, date, and geographic location.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the quality of each of the received streams of aeronautical data is determined by calculating a proximity of data points of each of the received streams of aeronautical data to corresponding data points of the at least one secondary data source.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the at least one secondary data source is selected from a plurality of secondary data sources according to the known quality of each of the plurality of secondary data sources.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the code is executable by the processor to train a machine learning model along the one or more parameters using the stream of aeronautical data from the selected aeronautical data provider, the machine learning model used to predict which of the plurality of aeronautical data providers to select based on the one or more parameters along a boundary where the streams of aeronautical data overlap.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the one or more parameters is selected from the group comprising a latitude, a longitude, a heading, an altitude, a speed, a time of day, a date, and a geographic location.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the code is executable by the processor to determine a quality of the received streams of aeronautical data on a per-attribute basis and expose the aeronautical data on the per-attribute basis from multiple streams of the plurality of aeronautical data providers according to the determined quality.

### Claim 10 (depends on 1)

The apparatus of claim 1, wherein the plurality of aeronautical data providers comprises data repositories that provide streams of aeronautical data for a plurality of flights, the received streams comprising streams of overlapping aeronautical data from different data repositories.

### Claim 11

A method, comprising:
receiving streams of aeronautical data from a plurality of aeronautical data providers streaming aeronautical data from different geographic locations;
determining a quality of each of the received streams of aeronautical data by checking the aeronautical data against data provided by at least one secondary data source that has a known quality;
selecting an aeronautical data provider of the plurality of aeronautical data providers that provides a stream of aeronautical data that is closest to the data provided by the at least one secondary data source; and
exposing aeronautical data from the stream of aeronautical data of the selected aeronautical data provider to an end user according to one or more parameters.

### Claim 12 (depends on 11)

The method of claim 11, further comprising normalizing data of each of the streams of aeronautical data from the plurality of aeronautical data providers and grouping the aeronautical data that are normalized from each of the streams of aeronautical data by data attributes.

### Claim 13 (depends on 12)

The method of claim 12, wherein the data attributes are selected from the group comprising latitude, longitude, heading, altitude, speed, time of day, date, and geographic location.

### Claim 14 (depends on 11)

The method of claim 11, wherein the quality of each of the received streams of aeronautical data is determined by calculating a proximity of data points of each of the received streams of aeronautical data to corresponding data points of the at least one secondary data source.

### Claim 15 (depends on 11)

The method of claim 11, wherein the at least one secondary data source is selected from a plurality of secondary data sources according to the known quality of each of the plurality of secondary data sources.

### Claim 16 (depends on 11)

The method of claim 11, further comprising training a machine learning model along the one or more parameters using the stream of aeronautical data from the selected aeronautical data provider, the machine learning model used to predict which of the plurality of aeronautical data providers to select based on the one or more parameters.

### Claim 17 (depends on 11)

The method of claim 11, wherein the one or more parameters is selected from the group comprising a latitude, a longitude, a heading, an altitude, a speed, a time of day, a date, and a geographic location.

### Claim 18 (depends on 11)

The method of claim 11, further comprising determining a quality of the received streams of aeronautical data on a per-attribute basis and expose the aeronautical data on the per-attribute basis from multiple streams of the plurality of aeronautical data providers according to the determined quality.

### Claim 19 (depends on 11)

The method of claim 11, wherein the plurality of aeronautical data providers comprises data repositories that provide streams of aeronautical data for a plurality of flights, the received streams comprising streams of overlapping aeronautical data from different data repositories.

### Claim 20

A system, comprising:
a plurality of data repositories each streaming aeronautical data from different geographic locations; and
an on-board flight controller comprising a processor and a memory that stores code executable by the processor to:
receive streams of aeronautical data from the plurality of data repositories;
determine a quality of each of the received streams of aeronautical data by checking the aeronautical data against data provided by at least one secondary data source that has a known quality;
select a data repository of the plurality of data repositories that provides a stream of aeronautical data that is closest to the data provided by the at least one secondary data source; and
expose aeronautical data from the stream of aeronautical data of the selected data repository to an end user according to one or more parameters.
