Determining content to present for human review

1. A method comprising:

receiving a request associated with a review of content;

determining, based at least in part on receiving the request, one or more conditions associated with the review of the content;

analyzing the content to identify a first field of interest and a second field of interest, wherein the first field of interest and the second field of interest represent fields of interest associated with the review of the content;

determining that at least one of the first field of interest or the second field of interest does not satisfy the one or more conditions;

analyzing the content to identify a third field of interest and a fourth field of interest, wherein the third field of interest and the fourth field of interest represent fields of interest associated with the review of the content;

determining that the third field of interest and the fourth field of interest satisfy the one or more conditions;

determining to not request review of the third field of interest and the fourth field of interest based at least in part on determining that the third field of interest and the fourth field of interest satisfy the one or more conditions; and

generating data associated with the review of the content.

2. The method of claim 1 , further comprising transmitting the data associated with the review to a device, wherein the device is configured to display at least a portion of the content including at least one of the first field of interest or the second field of interest.

3. The method of claim 1 , wherein the first field of interest is associated with a predicted key of a predicted key value pair and the second field of interest is associated with a predicted value of the predicted key value pair.

4. The method of claim 3 , wherein the one or more conditions include a first confidence and a second confidence, and wherein determining that the at least one of the first field of interest or the second field of interest does not satisfy the one or more conditions comprises:

determining that a confidence that the predicted key represents a key of the predicted key value pair is less than the first confidence;

determining that a confidence that the predicted value presents a value of the predicted key value pair is less than the first confidence; or

determining that a confidence that the predicted key and the predicted value represent a key value pair is less than the second confidence.

5. The method of claim 1 , wherein analyzing the content to identify the first field of interest and the second field of interest comprises analyzing the content using at least one of a first machine learning (ML) model or a second ML model.

6. The method of claim 5 , wherein the one or more conditions are associated with a human reviewer reviewing results of at least one of the first ML model or the second ML model.

7. The method of claim 1 , wherein:

the review of the content corresponds to identifying objects within the content;

the first field of interest represents a first object for review; and

the second field of interest represents a second object for review.

8. The method of claim 7 , wherein:

the first object is identified within the review of the content via a first bounding box; and

the second object is identified within the review of the content via a second bounding box.

9. A system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:

receiving a request to review content, the request including one or more conditions comprising a confidence threshold and associated with the review of the content;

identifying, based at least in part on the request, a first field of interest;

identifying, based at least in part on the request, a second field of interest;

determining that the first field of interest satisfies the one or more conditions including determining that a first confidence of the first field of interest is greater than the confidence threshold;

determining that the second field of interest does not satisfy the one or more conditions;

determining that a second confidence of the second field of interest is less than the confidence threshold; and

generating data associated with the review of the content, the review including a portion of the content corresponding to the second field of interest.

10. The system of claim 9 , wherein the first field of interest is represented within the review by at least one of a box, an outline, or a highlight.

11. The system of claim 9 , wherein at least one of:

the request is associated with identifying one or more objects of interest within the content; or

the request is associated with identifying one or more characters, words, or text within the content.

12. The system of claim 9 , wherein:

the first field of interest is identified based at least in part on a first machine learning (ML) model; and

the second field of interest is identified based at least in part on the first ML model or a second ML model.

13. The system of claim 12 , the acts further comprising:

determining the first confidence is associated with the first ML model identifying the first field of interest; and

determining the second confidence is associated with the at least one of the first ML model or the second ML model identifying the second field of interest.

14. A method comprising:

receiving a request associated with a review of content;

determining one or more conditions associated with the review of the content including a first confidence and a second confidence;

analyzing the content to identify a first field of interest and a second field of interest, wherein:

the first field of interest and the second field of interest represent fields of interest associated with the review of the content; and

the first field of interest is associated with a predicted key of a predicted key value pair and the second field of interest is associated with a predicted value of the predicted key value pair;

determining that at least one of the first field of interest or the second field of interest does not satisfy the one or more conditions comprising:

determining that a confidence that the predicted key represents a key of the predicted key value pair is less than the first confidence;

determining that a confidence that the predicted value presents a value of the predicted key value pair is less than the first confidence; or

determining that a confidence that the predicted key and the predicted value represent a key value pair is less than the second confidence; and

generating data associated with the review of the content.

15. The method of claim 14 , wherein analyzing the content to identify the first field of interest and the second field of interest comprises analyzing the content using at least one of a first machine learning (ML) model or a second ML model.

16. The method of claim 15 , wherein the one or more conditions are associated with a human reviewer reviewing results of at least one of the first ML model or the second ML model.

17. The method of claim 14 , wherein at least one of: the request is associated with identifying one or more objects of interest within the content; or the request is associated with identifying one or more characters, words, or text within the content.

18. The method of claim 14 , wherein:

the first field of interest is identified based at least in part on a first machine learning (ML) model; and

the second field of interest is identified based at least in part on the first ML model or a second ML model.

19. The method of claim 18 , further comprising: determining a first confidence associated with the first ML model identifying the first field of interest; and determining a second confidence associated with the at least one of the first ML model or the second ML model identifying the second field of interest.

20. The method of claim 14 , wherein:

the review of the content corresponds to identifying objects within the content;

the first field of interest represents a first object for review; and

the second field of interest represents a second object for review.