Form field prediction service
Processing a first document using a first service that includes a first machine learning model. One embodiment provides a method that includes receiving, over a network, the first document including a first form field and identifying a first value associated with a first entity. The method also includes obtaining a first subset of documents from the first service, analyzing, using the first machine learning model, the first subset of documents to extract a second document including a first value and a second value, automatically populating the first form field with the first value or the second value, and providing, via a graphical user interface, the first document to a user to be validated. The method also includes saving a validated first document to a database, transmitting the validated first document to a second service, and updating the first machine learning model with the validated first document.
1. A method of processing a first document using a first service including a first machine learning model, the method comprising:
receiving, over a network from a first entity, the first document, wherein the first document includes a first form field;
identifying a first value associated with the first entity;
obtaining a first subset of documents from the first service, wherein each document included in the first subset of documents contains the first value;
analyzing, using the first machine learning model, the first subset of documents to extract a second document, wherein the second document includes a second form field containing the first value and a third form field containing a second value;
automatically populating the first form field with one selected from the group consisting of the first value and the second value;
providing, via a graphical user interface, the first document to a user to be validated;
saving, in response to the first document being validated, a validated first document to a database;
transmitting the validated first document to a second service; and
in response to transmitting the validated first document to the second service, updating, based on a parameter, the first machine learning model with the validated first document.
2. The method of claim 1 , wherein the parameter is at least one selected from the group consisting of a threshold number of documents saved to the database and a time of day.
3. The method of claim 1 , wherein identifying a first value associated with the first entity includes extracting the first value from the first document.
4. The method of claim 1 , wherein the first machine learning model is associated with the first subset of documents.
5. The method of claim 1 further comprising:
receiving, in response to the user not validating the first document, an edit to the second value via the graphical user interface.
6. The method of claim 1 , wherein each document contained within the first subset of documents is a validated document.
7. The method of claim 1 , wherein the first value is at least one selected from the group consisting of a customer account identification number and a vendor identification number.
8. The method of claim 1 , wherein the first machine learning model is a semantic machine learning model.
9. The method of claim 1 , wherein the first document is one of an invoice, a sales order, an order confirmation, and a remittance advice.
10. A system for processing a first document using a first service including a first machine learning model, the system comprising:
an electronic processor configured to
receive, over a network, the first document, wherein the first document includes a first form field containing a first value and a second form field not containing a value,
extract the first value from the first form field,
obtain a first subset of documents from the first service, wherein each document included in the first subset of documents contains the first value,
analyze, using the first machine learning model, the first subset of documents to extract a second document, wherein the second document includes a third form field containing the first value and a fourth form field containing a second value,
automatically populate the second form field with the second value,
provide, via a graphical user interface, the first document to a user to be validated,
save, in response to the first document being validated, a validated first document to a database,
transmit the validated first document to a second service, and
in response to transmitting the validated first document to the second service, update, based on a parameter, the first machine learning model with the validated first document.
11. The system of claim 10 , wherein the parameter is at least one selected from the group consisting of a threshold number of documents saved to the database and a time of day.
12. The system of claim 10 , wherein the electronic processor is further configured to:
receive, in response to the user not validating the first document, an edit to the second value via the graphical user interface.
13. The system of claim 10 , wherein each document contained within the first subset of documents is a validated document.
14. The system of claim 10 , wherein the first value is associated with a first entity.
15. A non-transitory computer-readable medium comprising instructions that, when executed by an electronic processor, causes the electronic processor to perform a set of operations comprising:
receiving, over a network from a first entity, a first document, wherein the first document includes a first form field;
identifying a first value associated with the first entity;
obtaining a first subset of documents from a first service, wherein each document included in the first subset of documents contains the first value;
analyzing, using a first machine learning model, the first subset of documents to extract a second document, wherein the second document includes a second form field containing the first value and a third form field containing a second value;
automatically populating the first form field with one selected from the group consisting of the first value and the second value;
providing, via a graphical user interface, the first document to a user to be validated;
saving, in response to the first document being validated, a validated first document to a database;
transmitting the validated first document to a second service; and
in response to transmitting the validated first document to the second service, updating, based on a parameter, the first machine learning model with the validated first document.
16. The non-transitory computer-readable medium of claim 15 , wherein the parameter is at least one selected from the group consisting of a threshold number of documents saved to the database and a time of day.
17. The non-transitory computer-readable medium of claim 15 , wherein the set of operations further includes receiving, in response to the user not validating the first document, an edit to the second value via the graphical user interface.
18. The system of claim 10 , wherein the first machine learning model is a semantic machine learning model.
19. The non-transitory computer-readable medium of claim 15 , wherein the first machine learning model is associated with the first subset of documents.
20. The non-transitory computer-readable medium of claim 15 , wherein the first value does not appear within the first document.