Document initiated intelligent workflow
In an example embodiment, a solution is provided that allows a user to submit a document. Information can be obtained from the document using optical character recognition (OCR) or other techniques. This information can then be used to identify one or more workflows that pertain to the document. The one or more workflows may be ranked using machine learning techniques and presented to the user. Once the user selects a desired workflow, the information obtained from the document can then be used to automatically complete at least a portion of the workflow, for example by prefilling one or more fields in a form.
1. A system comprising:
at least one hardware processor; and
a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising:
receiving a document from a user device, at a workflow initiation hub, and over a communications network;
identifying a document type associated with the document;
accessing a configuration store to identify one or more mappings that contain the document type, the one or more mappings each specifying one or more workflow processes available for execution at a service operating on hardware separate and distinct from the workflow initiation hub;
transmitting, over the communications network, an indication of one or more of the one or more workflow processes available for execution to the user device;
receiving, from the user device over the communications network, a selected workflow process from the one or more workflow processes available for execution;
obtaining information, about an account associated with the document, identified in a list of data needs stored for the selected workflow process;
prefilling the selected workflow process using the obtained information; and
sending the prefilled selected workflow process to the service associated with the selected workflow process for execution.
2. The system of claim 1 , wherein the accessing the configuration store includes:
identifying a plurality of mappings containing the document type;
obtaining information about a user associated with the user device; and
feeding the plurality of mappings and the information about the user associated with the user device to a machine learned model trained to output an indication of relevance of each of the plurality of mappings to the user associated with the user device.
3. The system of claim 2 , wherein the indication of relevance is a numerical score.
4. The system of claim 2 , wherein the operations further comprise:
obtaining training data, the training data comprising an identification of one or more workflow processes and usage information, the usage information identifying users who have initiated the one or more workflow processes in the training data; and
feeding the training data to a machine learning algorithm to train the machine learned model, wherein an indication that a user has initiated a workflow process is a positive label used during the training and features are extracted from the identification of the one or more workflow processes and user information.
5. The system of claim 3 , wherein the transmitting further includes sending the numerical score for each of the one or more workflow processes available for execution that are being transmitted to the user device.
6. The system of claim 1 , wherein the operations further comprise performing optical character recognition on the document, using a document template, for the document, stored in the configuration store.
7. The system of claim 1 , wherein the obtaining information, about an account associated with the document, identified in a list of data needs stored for the selected workflow process includes accessing data about a user associated with the user device from the user device.
8. A method comprising:
receiving a document from a user device, at a workflow initiation hub, and over a communications network;
identifying a document type associated with the document;
accessing a configuration store to identify one or more mappings that contain the document type, the one or more mappings each specifying one or more workflow processes available for execution at a service operating on hardware separate and distinct from the workflow initiation hub;
transmitting, over the communications network, an indication of one or more of the one or more workflow processes available for execution to the user device;
receiving, from the user device over the communications network, a selected workflow process from the one or more workflow processes available for execution;
obtaining information, about an account associated with the document, identified in a list of data needs stored for the selected workflow process;
prefilling the selected workflow process using the obtained information; and
sending the prefilled selected workflow process to the service associated with the selected workflow process for execution.
9. The method of claim 8 , wherein the accessing the configuration store includes:
identifying a plurality of mappings containing the document type;
obtaining information about a user associated with the user device; and
feeding the plurality of mappings and the information about the user associated with the user device to a machine learned model trained to output an indication of relevance of each of the plurality of mappings to the user associated with the user device.
10. The method of claim 9 , wherein the indication of relevance is a numerical score.
11. The method of claim 9 , wherein the operations further comprise:
obtaining training data, the training data comprising an identification of one or more workflow processes and usage information, the usage information identifying users who have initiated the one or more workflow processes in the training data; and
feeding the training data to a machine learning algorithm to train the machine learned model, wherein an indication that a user has initiated a workflow process is a positive label used during the training and features are extracted from the identification of the one or more workflow processes and user information.
12. The method of claim 10 , wherein the transmitting further includes sending the numerical score for each of the one or more workflow processes available for execution that are being transmitted to the user device.
13. The method of claim 8 , further comprising performing optical character recognition on the document, using a document template, for the document, stored in the configuration store.
14. The method of claim 8 , wherein the obtaining information, about an account associated with the document, identified in a list of data needs stored for the selected workflow process includes accessing data about a user associated with the user device from the user device.
15. A non-transitory machine-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving a document from a user device, at a workflow initiation hub, and over a communications network;
identifying a document type associated with the document;
accessing a configuration store to identify one or more mappings that contain the document type, the one or more mappings each specifying one or more workflow processes available for execution at a service operating on hardware separate and distinct from the workflow initiation hub;
transmitting, over the communications network, an indication of one or more of the one or more workflow processes available for execution to the user device;
receiving, from the user device over the communications network, a selected workflow process from the one or more workflow processes available for execution;
obtaining information, about an account associated with the document, identified in a list of data needs stored for the selected workflow process;
prefilling the selected workflow process using the obtained information; and
sending the prefilled selected workflow process to the service associated with the selected workflow process for execution.
16. The non-transitory machine-readable medium of claim 15 , wherein the accessing the configuration store includes:
identifying a plurality of mappings containing the document type;
obtaining information about a user associated with the user device; and
feeding the plurality of mappings and the information about the user associated with the user device to a machine learned model trained to output an indication of relevance of each of the plurality of mappings to the user associated with the user device.
17. The non-transitory machine-readable medium of claim 16 , wherein the indication of relevance is a numerical score.
18. The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise:
obtaining training data, the training data comprising an identification of one or more workflow processes and usage information, the usage information identifying users who have initiated the one or more workflow processes in the training data; and
feeding the training data to a machine learning algorithm to train a machine learned model, wherein an indication that a user has initiated a workflow process is a positive label used during the training and features are extracted from the identification of the one or more workflow processes and user information.
19. The non-transitory machine-readable medium of claim 17 , wherein the transmitting further includes sending the numerical score for each of the one or more workflow processes available for execution that are being transmitted to the user device.
20. The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise performing optical character recognition on the document, using a document template, for the document, stored in the configuration store.