Golf club fitting based on machine learning

Patent metadata

Field	Value
Publication number	US-12403372-B2
Application number	US-202318401320-A
Country	US
Kind code	B2
Filing date	Dec 29, 2023
Priority date	Dec 30, 2022
Publication date	Sep 2, 2025
Grant date	Sep 2, 2025

Abstract

Apparatus for a machine-learning-based golf club fitting platform is disclosed. An apparatus includes a processor and a memory. The memory stores code executable by the processor to receive a first set of golf swing data for a user, the first set of golf swing data representative of one or more characteristics of a golf swing of the user; determine one or more optimal specifications of at least one hypothetical golf club that is a best fit for the user using a property prediction machine learning model based on the first set of golf swing data; and determine at least one pre-existing golf club, comprising predefined specifications, that is a best match for the user based on a comparison of the determined one or more optimal specifications of the at least one hypothetical golf club to the predefined specifications of a plurality of different pre-existing golf clubs.

First claim

What is claimed is:

1. An apparatus, comprising:
a processor; and
a memory that stores code executable by the processor to:
receive a first set of golf swing data for a user, the first set of golf swing data representative of one or more characteristics of a golf swing of the user, the first set of golf swing data comprising sensed data, survey data, or a combination thereof;
determine one or more optimal specifications of at least one hypothetical golf club that is a best fit for the user using a property prediction machine learning model based on the first set of golf swing data, wherein the property prediction machine learning model is specially trained using a second set of golf swing data to analyze golf swing data; and
determine at least one pre-existing golf club, comprising predefined specifications, that is a best match for the user based on a comparison of the determined one or more optimal specifications of the at least one hypothetical golf club to the predefined specifications of a plurality of different pre-existing golf clubs.

2. The apparatus of claim 1 , wherein the code is executable by the processor to:
receive the second set of golf swing data, the second set of golf swing data comprising historical golf swing data; and
train the property prediction machine learning model based on the historical golf swing data.

3. The apparatus of claim 2 , wherein the historical golf swing data comprises at least one selected from the group of fitting data, demographic data, motion capture data, test data, survey data, and experiential data.

4. The apparatus of claim 3 , wherein the code is executable by the processor to clean the historical golf swing data prior to using the data for training the property prediction machine learning model by removing outlier data points from the historical golf swing data.

5. The apparatus of claim 2 , wherein the code is executable by the processor to:
identify data points that are missing within the first set of golf swing data, the historical golf swing data, or a combination thereof; and
estimate values for the identified data points that are missing within the first set of golf swing data, the historical golf swing data, or a combination thereof.

6. The apparatus of claim 5 , wherein the code is executable by the processor to provide the first set of golf swing data for the user, the historical golf swing data, or a combination thereof with the missing data points to an input prediction machine learning model for estimating values for the identified data points that are missing.

7. The apparatus of claim 1 , wherein the sensed data of the first set of golf swing data for the user comprises at least one selected from the group of fitting data, motion capture data, and experiential data and the survey data comprises at least one selected from the group of demographic data, preference data, scoring data, and estimation data.

8. The apparatus of claim 1 , wherein the code is executable by the processor to assign weights to various specifications of a golf club, the weights provided to the property prediction machine learning model and used to determine the one or more optimal specifications of the at least one hypothetical golf club.

9. The apparatus of claim 1 , wherein the code is executable by the processor to assign weights to various parameters of the first set of golf swing data, the weights provided to the property prediction machine learning model and used to determine the one or more optimal specifications of the at least one hypothetical golf club.

10. The apparatus of claim 1 , wherein the code is executable by the processor to define one or more specifications for the property prediction machine learning model that correspond to the plurality of different pre-existing golf clubs using a scaling factor for each of the one or more specifications.

11. The apparatus of claim 1 , wherein the one or more optimal specifications of the at least one hypothetical golf club that the property prediction machine learning model generates are associated with a golf club head, a golf club shaft, a golf club grip, or a combination thereof, and the plurality of different pre-existing golf clubs comprise pre-existing golf club heads, golf club shafts, golf club grips, or a combination thereof.

12. The apparatus of claim 1 , wherein the code is executable by the processor to further determine the one or more optimal specifications of the at least one hypothetical golf club using a content-based machine learning model that predicts a metric for one or more different golf clubs based on historical player performance data and the predefined performance specifications of a plurality of different pre-existing golf clubs.

13. The apparatus of claim 12 , wherein the code is executable by the processor to determine the one or more optimal specifications of the at least one hypothetical golf club based on predicting the metric for a plurality of other golfers using the content-based machine learning model and determining which of the plurality of other golfers most closely resembles the user, the golf club specifications for the determined other golfer used to determine the one or more optimal specifications.

14. The apparatus of claim 1 , wherein the code is executable by the processor to further determine the one or more optimal specifications of the at least one hypothetical golf club using a collaborative filtering machine learning model that predicts a plurality of pre-existing golf clubs for the user based on preference data of a plurality of other similar users.

15. The apparatus of claim 1 , wherein the code is executable by the processor to determine one or more physics-based parameters of the property prediction machine learning module to optimize for the user.

16. The apparatus of claim 15 , wherein the code is executable by the processor to update the determined one or more optimal specifications of at least one hypothetical golf club based on the determined one or more physics-based parameters to optimize for the user.

17. The apparatus of claim 1 , wherein the at least one pre-existing golf club comprises a driver-type golf club, and the one or more optimal specifications of the at least one hypothetical golf club that the property prediction machine learning model generates are associated with at least one golf club head for the driver-type golf club.

18. The apparatus of claim 17 , wherein the at least one golf club head is selected from a plurality of different driver-type golf club heads.

19. The apparatus of claim 18 , wherein the plurality of different driver-type golf club heads comprise at least one distinct specification, the at least one distinct specification selected from the group consisting of at least one of a volume, a delta 1 value, a Zup value, a BP projection value, an Ixx inertia value, an Izz inertia value, and a center of gravity (CGx) value.

20. The apparatus of claim 19 , wherein:
a first of the plurality of different driver-type golf club heads comprises a low spin/low launch specification;
a second of the plurality of different driver-type golf club heads comprises a high inertia specification; and
a third of the plurality of different driver-type golf club heads comprises a draw bias specification.

21. The apparatus of claim 19 , wherein:
a first of the plurality of different driver-type golf club heads comprises a first volume (V 1 ), a first head mass (m 1 ), a first delta 1 (d1 1 ), a first Ixx (Ixx 1 ), a first Izz (Izz 1 ),

Assignees

• Taylor Made Golf Co

Inventors

• Rahman Brian
• Roberts Peter
• Beach Todd

Classifications

• A63B71/0622

  Visual, audio or audio-visual systems for entertaining, instructing or motivating the user · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• A63B2225/50

  Wireless data transmission, e.g. by radio transmitters or telemetry · CPC title

• A63B69/3605 Primary

  Golf club selection aids informing player of his average or expected shot distance for each club · CPC title