Generating conversation models from documents
View Patent ↗Methods and systems for generating conversation models from documents are described herein. A system may receive a document and generate a conversation model that may be deployed by a chatbot or other automated agent (e.g., voice assistant, messenger bot, etc.). The chatbot may use the conversation model to engage in a conversation with a user and obtain information from the user to complete the document. The system may generate questions to ask the user based on text in the document that indicates a request for information. Additionally, the system may provide instructions to a user via a chatbot. The instructions may be generated based on text in the document that explains how to fill out the document.
1. A device comprising:
one or more processors; and
memory storing computer-executable instructions that, when executed by at least one of the one or more processors, cause the device to:
access a paper-based form document and expose an image of the paper-based form document to a chatbot, wherein the chatbot is configured to engage in a conversation, based on a first conversation model, with a first user, and wherein content of the image of the paper-based form document controls in part the conversation;
set, based on a message from the first user in response to information provided by the chatbot, a response value for the information provided by the chatbot via a chat interface associated with the first conversation model; and
render, based on the response value and to another conversation model, the information provided by the chatbot in the first conversation model.
2. The device of claim 1 , wherein the rendering is further based on one or more responses received from the first user during the conversation.
3. The device of claim 1 , wherein the conversation, based on the first conversation model and associated with the image of the paper-based form document, is an interactive conversation between the chatbot and the first user.
4. The device of claim 3 , wherein the conversation between the chatbot and the first user comprises a request for the first user to verify the message.
5. The device of claim 1 , wherein the first conversation model comprises explanatory text within the image of the paper-based form document and interrogatory text within the image of the paper-based form document.
6. The device of claim 5 , wherein the instructions, when executed by the at least one processor, further cause the device to:
parse the explanatory text within the image of the paper-based form document;
parse the interrogatory text within the image of the paper-based form document; and
generate vector representations of the explanatory text and vector representations of the interrogatory text.
7. The device of claim 6 , wherein the instructions, when executed by the at least one processor, cause the device to:
provide a plurality of chatbot generators, each configured to automatically create a chatbot for a different one of a plurality of different communication interfaces.
8. The device of claim 6 , wherein the instructions, when executed by the at least one processor, cause the device to:
determine, based on the interrogatory text and the explanatory text, a validation model for the information provided by the chatbot; and
determine, based on the validation model and the information provided by the chatbot, that the message from the first user is valid.
9. The device of claim 8 , wherein the instructions, when executed by the at least one processor, cause the device to:
based on determining that the message from the first user is valid, provide, to the first user and by the chatbot, additional information.
10. The device of claim 1 , wherein the instructions, when executed by the at least one processor, cause the device to:
trigger a workflow, performed independent of the chatbot, in response to completing the conversation with the first user, wherein the workflow comprises the message of the first user.
11. A method comprising:
accessing a paper-based form document and exposing an image of the paper-based form document to a chatbot, wherein the chatbot is configured to engage in a conversation, based on a first conversation model, with a first user, and wherein content of the image of the paper-based form document controls in part the conversation;
setting, based on a message from the first user in response to information provided by the chatbot, a response value for the information provided by the chatbot via a chat interface associated with the first conversation model; and
rendering, based on the response value and to another conversation model, the information provided by the chatbot in the first conversation model.
12. The method of claim 11 , wherein the rendering is further based on one or more responses received from the first user during the conversation.
13. The method of claim 11 , wherein the conversation, based on the first conversation model and associated with the image of the paper-based form document, is an interactive conversation between the chatbot and the first user.
14. The method of claim 13 , wherein the conversation between the chatbot and the first user comprises a request for the first user to verify the message.
15. The method of claim 11 , wherein the first conversation model comprises explanatory text within the image of the paper-based form document and interrogatory text within the image of the paper-based form document.
16. The method of claim 15 , further comprising:
parsing the explanatory text within the image of the paper-based form document;
parsing the interrogatory text within the image of the paper-based form document; and
generating vector representations of the explanatory text and vector representations of the interrogatory text.
17. The method of claim 16 , further comprising:
providing a plurality of chatbot generators, each configured to automatically create a chatbot for a different one of a plurality of different communication interfaces.
18. The method of claim 16 , further comprising:
determining, based on the interrogatory text and the explanatory text, a validation model for the information provided by the chatbot; and
determining, based on the validation model and the information provided by the chatbot, that the message from the first user is valid.
19. The method of claim 11 , further comprising:
triggering a workflow, performed independent of the chatbot, in response to completing the conversation with the first user, wherein the workflow comprises the message of the first user.
20. A non-transitory computer readable medium comprising computer-executable instructions that, when executed, cause performance of:
accessing a paper-based form document and exposing an image of the paper-based form document to a chatbot, wherein the chatbot is configured to engage in a conversation, based on a first conversation model, with a first user, and wherein content of the image of the paper-based form document controls in part the conversation;
setting, based on a message from the first user in response to information provided by the chatbot, a response value for the information provided by the chatbot via a chat interface associated with the first conversation model; and
rendering, based on the response value and to another conversation model, the information provided by the chatbot in the first conversation model.