Guided form generation in a document management system
Systems and methods are disclosed herein for generating and modifying a workflow comprising a series of webpages based on an online document. A document management system accesses an online document selected by a user and classifies each field of the online document into one of a set of categories. For each category, the system generates a form webpage comprising questions corresponding to each field classified as the category and combines the generated webpages to create a workflow. The system may modify the workflow by generating and adding one or more additional form webpages based on one or more answers provided by an entity completing the webform page. In response to the entity completing the modified generated workflow, the system generates a completed document based on the online document and the answers provided by the entity.
1. A method comprising:
accessing, by one or more processors, an online document;
applying, by the one or more processors, a machine-learned model to the online document to identify a plurality of fields of the online document, each field of the plurality of fields configured to receive a corresponding answer, wherein applying the machine-learned model comprises, for each field of the plurality of fields, performing natural language processing on text of the online document to identify a field type of the field and classifying the field into one of a set of categories based on the identified field type;
for each category of the set of categories, generating, by the one or more processors, a form web page comprising one or more questions corresponding to each field of the plurality of fields classified as the category;
generating, by the one or more processors, a workflow, wherein generating the workflow comprises combining the generated form web pages;
modifying, by the one or more processors, the generated workflow to generate a modified generated workflow, wherein the modifying comprises adding one or more additional form web pages to the generated workflow based on an answer provided by an entity completing a generated form web page of the generated form web pages, wherein the answer is responsive to a field of the plurality of fields identified by the machine-learned model, and wherein the one or more additional form web pages comprise an additional field not included in the plurality of fields identified by the machine-learned model; and
in response to the entity completing the modified generated workflow, generating, by the one or more processors, a completed document based on the online document and the answer provided by the entity, the completed document including the additional field not included in the plurality of fields identified by the machine-learned model.
2. The method of claim 1 , wherein applying the machine-learned model comprises identifying one or more of a header, a section break, a page break, or other contextual information within the online document.
3. The method of claim 1 , wherein the one or more additional form webpages are not provided for display to a second entity that provided a second answer, different from the answer, responsive to the field.
4. The method of claim 1 , further comprising modifying, by the one or more processors, the generated workflow based on user input comprising one or more of an instruction to add, remove, or reorder one or more fields or webform pages of the generated workflow.
5. The method of claim 1 , further comprising:
training the machine-learned model, using a set of training data, to identify, for each field of one or more fields in a document, a portion within the document corresponding to the field,
wherein applying the machine-learned model comprises applying the machine-learned model to the online document to identify portions of the online document that correspond to the plurality of fields of the online document.
6. The method of claim 1 , further comprising providing, by the one or more processors, a workflow creation interface on a first user device, the workflow creation interface including an outline area comprising a list of the set of categories and the plurality of fields identified by the machine-learned model in an outline format and a webform editing area displaying fields associated with a selected category.
7. The method of claim 1 , further comprising providing, by the one or more processors, a form completion interface on a second user device associated with the entity, the form completion interface comprising a series of form webpages each associated with a category of the modified generated workflow.
8. Non-transitory computer readable storage media comprising instructions that when executed by one or more processors cause the one or more processors to:
access an online document comprising a plurality of fields;
apply a machine-learned model to the online document to identify a plurality of fields of the online document, each field of the plurality of fields configured to receive a corresponding answer, wherein to apply the machine-learned model the instructions cause the one or more processors to, for each field of the plurality of fields, perform natural language processing on text of the online document to identify a field type of the field and classify the field into one of a set of categories based on the identified field type;
for each category of the set of categories, generate a form web page comprising one or more questions corresponding to each field of the plurality of fields classified as the category;
generate a workflow, wherein the instructions to generate the workflow cause the one or more processors to combine the generated form web pages;
modify the generated workflow to generate a modified generated workflow, wherein the instructions to modify cause the one or more processors to add one or more additional form web pages to the generated workflow based on an answer provided by an entity completing a generated form web page of the generated form web pages, wherein the answer is responsive to a field of the plurality of fields identified by the machine-learned model, and wherein the one or more additional form web pages comprise an additional field not included in the plurality of fields identified by the machine-learned model; and
in response to the entity completing the modified generated workflow, generate a completed document based on the online document and the answer provided by the entity, the completed document including the additional field not included in the plurality of fields identified by the machine-learned model.
9. The non-transitory computer readable storage media of claim 8 , wherein the instructions to apply the machine-learned model cause the one or more processors to identify one or more of a header, a section break, a page break, or other contextual information within the online document.
10. The non-transitory computer readable storage media of claim 8 , wherein the one or more additional form webpages are not provided for display to a second entity that provided a second answer, different from the answer, responsive to the field.
11. The non-transitory computer readable storage media of claim 8 , wherein the instructions further cause the one or more processors to modify the generated workflow based on user input comprising one or more of an instruction to add, remove, or reorder one or more fields or webform pages of the generated workflow.
12. The non-transitory computer readable storage media of claim 8 , wherein the instructions further cause the one or more processors to:
train the machine-learned model, using a set of training data, to identify, for each field of one or more fields in a document, a portion within the document corresponding to the field,
wherein the instructions to apply the machine-learned model cause the one or more processors to apply the machine-learned model to the online document to identify portions of the online document that correspond to the plurality of fields of the online document.
13. The non-transitory computer readable storage media of claim 8 , wherein the instructions further cause the one or more processors to provide a workflow creation interface on a first user device, the workflow creation interface including an outline area comprising a list of the set of categories and the plurality of fields identified by the machine-learned model in an outline format and a webform editing area displaying fields associated with a selected category.
14. The non-transitory computer readable storage media of claim 8 , wherein the instructions further cause the one or more processors to provide a form completion interface on a second user device associated with the entity, the form completion interface comprising a series of form webpages each associated with a category of the modified generated workflow.
15. A system comprising:
one or more processors; and
non-transitory computer readable storage media comprising instructions that when executed by one or more processors cause the one or more processors to:
access an online document comprising a plurality of fields;
apply a machine-learned model to the online document to identify a plurality of fields of the online document, each field of the plurality of fields configured to receive a corresponding answer, wherein to apply the machine-learned model the instructions cause the one or more processors to, for each field of the plurality of fields, perform natural language processing on text of the online document to identify a field type of the field and classify the field into one of a set of categories based on the identified field type;
for each category of the set of categories, generate a form web page comprising one or more questions corresponding to each field of the plurality of fields classified as the category;
generate a workflow, wherein the instructions to generate the workflow cause the one or more processors to combine the generated form web pages;
modify the generated workflow to generate a modified generated workflow, wherein the instructions to modify cause the one or more processors to add one or more additional form web pages to the generated workflow based on an answer provided by an entity completing a generated form web page of the generated form web pages, wherein the answer is responsive to a field of the plurality of fields identified by the machine-learned model, and wherein the one or more additional form web pages comprise an additional field not included in the plurality of fields identified by the machine-learned model; and
in response to the entity completing the modified generated workflow, generate a completed document based on the online document and the answer provided by the entity, the completed document including the additional field not included in the plurality of fields identified by the machine-learned model.
16. The system of claim 15 , wherein the instructions to apply the machine-learned model cause the one or more processors to identify one or more of a header, a section break, a page break, or other contextual information within the online document.
17. The system of claim 15 , wherein the one or more additional form webpages are not provided for display to a second entity that provided a second answer, different from the answer, responsive to the field.
18. The system of claim 15 , wherein instructions further cause the one or more processors to modify the generated workflow based on user input comprising one or more of an instruction to add, remove, or reorder one or more fields or webform pages of the generated workflow.
19. The system of claim 15 , wherein the instructions further cause the one or more processors to provide a workflow creation interface on a first user device, the workflow creation interface including an outline area comprising a list of the set of categories and the plurality of fields identified by the machine-learned model in an outline format and a webform editing area displaying fields associated with a selected category.
20. The system of claim 15 , wherein the instructions further cause the one or more processors to provide a form completion interface on a second user device associated with the entity, the form completion interface comprising a series of form webpages each associated with a category of the modified generated workflow.