Foot differentiation scoring

1. A method comprising:

receiving, from sensors of a scanning device configured to perform pressure measurements and/or capture foot images, pressure and/or measurement data corresponding to feet of a user;

preprocessing the pressure and/or measurement data; and

generating, based on the preprocessed pressure and/or measurement data, a foot differentiation score that assigns a numerical rating based on how different the user's left foot and right foot are from each other, wherein the foot differentiation score is generated based at least in part on rules that assign points to the foot differentiation score based on threshold conditions met by the preprocessed pressure and/or measurement data.

2. The method of claim 1 , further comprising:

causing an orthotic recommendation to be provided to the user based on the foot differentiation score.

3. The method of claim 1 , wherein the generating of the foot differentiation score comprises:

inputting the preprocessed pressure and/or measurement data into a trained machine learning model; and

receiving, from the trained machine learning model, the foot differentiation score.

4. The method of claim 3 , wherein the trained machine learning model is trained based on historical pressure and/or measurement data compiled in a data bank, wherein the method further comprises storing the pressure and/or measurement data in the data bank for further training of the trained machine learning model.

5. The method of claim 1 , wherein generating the foot differentiation score comprises:

partitioning preprocessed historical pressure and/or measurement data into a training set and a validation set; and

training a machine learning model for foot differentiation scoring to cause orthotic recommendations to be provided to users, wherein the training of the machine learning model comprises tuning hyperparameters of the learning model based on rule-based scoring.

6. The method of claim 5 , wherein generating the foot differentiation score further comprises:

validating the trained machine learning model using the validation set.

7. The method of claim 6 , wherein partitioning the preprocessed historical pressure and/or measurement data into the training set and the validation set comprise using k-fold cross-validation.

8. The method of claim 2 , wherein providing the orthotic recommendation comprises one or more of:

causing a graphical user interface (GUI) to display the foot differentiation score to inform the user of the differences between the left foot and the right foot of the user;

causing the GUI to display a visual representation of an orthotic product based on the foot differentiation score; or

causing the orthotic product to be provided to the user based on the foot differentiation score through available prefabricated orthotics or custom orthotics provided by 3D printing or other method.

9. A system comprising:

a foot scanning device configured for obtaining pressure and/or image data corresponding to feet of a user;

a memory to store the pressure and/or image data; and

a processing device, coupled to the memory and the foot scanning device, wherein the processing device is to:

receive, from sensors of the foot scanning device, pressure and/or measurement data corresponding to feet of a user;

preprocess the pressure data and/or measurement data derived from the image data; and

generate, based on the preprocessed pressure and/or measurement data, a foot differentiation score that assigns a numerical rating based on how different the user's left foot and right foot are from each other, wherein the foot differentiation score is generated based at least in part on rules that assign points to the foot differentiation score based on threshold conditions met by the preprocessed pressure and/or measurement data.

10. The system of claim 9 , wherein to generate the foot differentiation score, the processing device is to further:

cause an orthotic recommendation to be provided to the user based on the foot differentiation score.

11. The system of claim 9 , wherein to generate the foot differentiation score, the processing device is to further:

input the preprocessed pressure and/or measurement data into a trained machine learning model; and

receive, from the trained machine learning model, the foot differentiation score.

12. The system of claim 11 , wherein the trained machine learning model is trained based on historical pressure and/or measurement data compiled in a data bank, wherein the processing device is to further store the pressure and/or measurement data in the data bank for further training of the trained machine learning model.

13. The system of claim 9 , wherein to generate the foot differentiation score, the processing device is to further:

partition preprocessed historical pressure and/or measurement data into a training set and a validation set; and

train a machine learning model for foot differentiation scoring to cause orthotic recommendations to be provided to users, wherein the training of the machine learning model comprises tuning hyperparameters of the learning model based on rule-based scoring.

14. The system of claim 13 , wherein to generate the foot differentiation score, the processing device is to further:

validate the trained machine learning model using the validation set.

15. The system of claim 14 , wherein the processing device is to use k-fold cross-validation to partition the preprocessed historical pressure and/or measurement data into the training set and the validation set.

16. The system of claim 10 , wherein to provide the orthotic recommendation, the system is to:

cause a graphical user interface (GUI) to display the foot differentiation score to inform the user of the differences between the left foot and the right foot of the user;

cause the GUI to display a visual representation of an orthotic product based on the foot differentiation score; or

cause the orthotic product to be provided to the user based on the foot differentiation score through available prefabricated orthotics or custom orthotics provided by 3D printing or other method.

17. A non-transitory computer-readable storage medium having instructions encoded thereon that, when executed by a processing device, cause the processing device to:

receive, from sensors of a foot scanning device configured to perform pressure measurements and/or capture images of feet, pressure and/or measurement data corresponding to feet of a user;

preprocess the pressure and/or measurement data; and

generate, based on the preprocessed pressure and/or measurement data, a foot differentiation score that assigns a numerical rating based on how different the user's left foot and right foot are from each other, wherein the foot differentiation score is generated based at least in part on rules that assign points to the foot differentiation score based on threshold conditions met by the preprocessed pressure and/or measurement data.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions further cause the processing device to:

cause an orthotic recommendation to be provided to the user based on the foot differentiation score.

19. The non-transitory computer-readable storage medium of claim 17 , wherein to generate the foot differentiation score, the instructions further cause the processing device to:

input the preprocessed pressure and/or measurement data into a trained machine learning model; and

receive, from the trained machine learning model, the foot differentiation score.

20. The non-transitory computer-readable storage medium of claim 19 , wherein the trained machine learning model is trained based on historical pressure and/or measurement data compiled in a data bank, wherein the instructions further cause the processing device to store the pressure and/or measurement data in the data bank for further training of the trained machine learning model.

21. The non-transitory computer-readable storage medium of claim 17 , wherein to generate the foot differentiation score, the instructions further cause the processing device to:

partition preprocessed historical pressure and/or measurement data into a training set and a validation set;

train a machine learning model for foot differentiation scoring to cause orthotic recommendations to be provided to users, wherein the training of the machine learning model comprises tuning hyperparameters of the learning model based on rule-based scoring; and

validate the trained machine learning model using the validation set.

22. The non-transitory computer-readable storage medium of claim 21 , wherein the instructions further cause the processing device to use k-fold cross-validation to partition the preprocessed historical pressure and/or measurement data into the training set and the validation set.

23. The non-transitory computer-readable storage medium of claim 18 , wherein to provide the orthotic recommendation, the instructions further cause the processing device to:

cause a graphical user interface (GUI) to display the foot differentiation score to inform the user of the differences between the left foot and the right foot of the user;

cause the GUI to display a visual representation of an orthotic product based on the foot differentiation score; or

cause the orthotic product to be provided to the user based on the foot differentiation score through available prefabricated orthotics or custom orthotics provided by 3D printing or other method.