Image-based kitchen tracking system with dynamic labeling management

1. A method, comprising:

receiving, by a processing device, image data comprising one or more image frames indicative of a state of a meal preparation area;

determining, by the processing device based on the image data, a first feature characterization representative of a first meal preparation item associated with the state of the meal preparation area;

determining, by the processing device, that the first feature characterization does not meet meal preparation item classification criteria for a set of meal preparation item classifications, wherein each meal preparation item classification of the set of meal preparation item classifications indicates an identity of a meal preparation item; and

causing, by the processing device, a notification indicating the first meal preparation item and one of a meal preparation item classification or a classification status corresponding to the first meal preparation item on a graphical user interface (GUI).

2. The method of claim 1 , wherein determining the first feature characterization comprises:

using the image data as input to a machine learning model; and

obtaining one or more outputs of the machine learning model, the one or more outputs indicative of the first feature characterization.

3. The method of claim 1 , further comprising

determining, by the processing device, a proximity between the first feature characterization and a set of previous feature characterizations corresponding to unclassified meal preparation items, wherein the classification status indicates the proximity between the first feature characterization and the set of previous feature characterizations corresponding to unclassified meal preparation items.

4. The method of claim 1 , further comprising:

receiving, by the processing device using the GUI, a first user input indicating a class label corresponding to the first meal preparation item;

generating, by the processing device, a new meal preparation item classification using the class label and the first feature characterization; and

associating the meal preparation item with the new meal preparation item classification.

5. The method of claim 1 , further comprising:

receiving, by the processing device from a kitchen display system (KDS), menu configuration data indicating a first menu item and a set of ingredients corresponding to the first menu item;

determining, by the processing device, an association between the first meal preparation item and the first menu item based on a comparison between the first feature characterization and the set of ingredients, wherein the first feature characterization identifies one or more ingredients corresponding to the first meal preparation item;

generating, by the processing device, a new meal preparation item classification using the first menu item and the first feature characterization; and

associating the meal preparation item with the new meal preparation item classification.

6. The method of claim 5 , wherein the first menu item comprises a limited duration menu item for display on an order display device associated with the menu configuration data.

7. The method of claim 1 , further comprising:

receiving, by the processing device from a point of sale (POS) system, order data indicative of one of more pending meal orders;

generating, by the processing device, a new meal preparation item classification based on the one or more pending meal orders and the first feature characterization; and

associating the meal preparation item with the new meal preparation item classification.

8. The method of claim 7 , wherein:

the one or more pending meal orders comprises a first pending meal order indicating a first menu item and a first customization to the first menu item, wherein the new meal preparation item classification is generated further based on the first customization to the first menu item.

9. The method of claim 7 , further comprising;

determining, by the processing device, an order preparation error based on the order data and the first meal preparation item; and

causing, by the processing device, the order preparation error to be displayed on the GUI.

10. A system comprising:

one or more cameras disposed within a meal preparation area, the one or more cameras capturing image data comprising one or more image frames indicative of a current state of the meal preparation area;

a memory; and

a processing device, coupled to the memory; to:

receive the image data from the one or more cameras;

determine a first feature characterization representative of a first meal preparation item associated with the current state of the meal preparation area;

determine that the first feature characterization does not meet meal preparation item classification criteria for a set of meal preparation item classifications, wherein each meal preparation item classification of the set of meal preparation item classifications indicates an identity of a meal preparation item; and

cause a notification indicating the first meal preparation item and one of a meal preparation item classification or a classification status corresponding to the first meal preparation item on a graphical user interface (GUI).

11. The system of claim 10 , wherein to determine the first feature characterization the processing device is further to:

use the image data as input to a machine learning model; and

obtain one or more outputs of the machine learning model, the one or more outputs indicative of the first feature characterization.

12. The system of claim 10 , wherein the processing device is further to:

determine a proximity between the first feature characterization and a set of previous feature characterizations corresponding to unclassified meal preparation items, wherein the classification status indicates the proximity between the first feature characterization and the set of previous feature characterizations corresponding to unclassified meal preparation items.

13. The system of claim 10 , wherein the processing device is further to:

receive, using the GUI, a first user input indicating a class label corresponding to the first meal preparation item;

generate a new meal preparation item classification using the class label and the first feature characterization; and

store, in the memory, data associating the meal preparation item with the new meal preparation item classification.

14. The system of claim 10 , wherein the processing device is further to:

receive, from a kitchen display system, menu configuration data indicating a first menu item and a set of ingredients corresponding to the first menu item;

determine an association between the first meal preparation item and the first menu item based on a comparison between the first feature characterization and the set of ingredients, wherein the first feature characterization identifies one or more ingredients corresponding to the first meal preparation item;

generate a new meal preparation item classification using the first menu item and the first feature characterization; and

store, in the memory, data associating the meal preparation item with the new meal preparation item classification.

15. The system of claim 14 , wherein the first menu item comprises a limited duration menu item for display on an order display device associated with the menu configuration data.

16. The system of claim 10 , wherein the processing device is further to:

receive, from a point of sale (POS) system, order data indicative of one of more pending meal orders;

generate a new meal preparation item classification based on the one or more pending meal orders and the first feature characterization; and

store, in the memory, data associating the meal preparation item with the new meal preparation item classification.

17. The system of claim 16 , wherein the one or more pending meal orders comprises a first pending meal order indicating a first menu item and a first customization to the first menu item, wherein the new meal preparation item classification is generated further based on the first customization to the first menu item.

18. The system of claim 16 , wherein the processing device is further to:

determine an order preparation error based on the order data and the first meal preparation item; and

cause the order preparation error to be displayed on the GUI.

19. A non-transitory machine-readable storage medium comprising instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

receiving image data comprising one or more image frames indicative of a state of a meal preparation area;

determining, based on the image data, a first feature characterization representative of a first meal preparation item associated with the state of the meal preparation area;

determining that the first feature characterization does not meet meal preparation item classification criteria for a set of meal preparation item classifications, wherein each meal preparation item classification of the set of meal preparation item classifications indicates an identity of a meal preparation item; and

causing a notification indicating the first meal preparation item and one of an meal preparation item classification or an classification status corresponding to the first meal preparation item on a graphical user interface (GUI).

20. The non-transitory machine-readable storage medium of claim 19 , wherein the operations further comprise:

using the image data as input to a machine learning model; and

obtaining one or more outputs of the machine learning model, the one or more outputs indicative of the first feature characterization.