Method and apparatus for automatically building conversational systems
View Patent ↗A system and method provides a natural language interface to world-wide web content. Either in advance or dynamically, webpage content is parsed using a parsing algorithm. A person using a telephone interface can provide speech information, which is converted to text and used to automatically fill in input fields on a webpage form. The form is then submitted to a database search and a response is generated. Information contained on the responsive webpage is extracted and converted to speech via a text-to-speech engine and communicated to the person.
1. A method comprising:
prompting a user, via a prompt, to provide information associated with a field on a form;
receiving speech from the user in response to the prompt;
converting, via a processor, the speech to a text;
filling in the field of the form with the text, to yield a filled form; and
receiving a webpage generated based at least in part on the filled form.
2. The method of claim 1 , wherein the field comprises a plurality of fields.
3. The method of claim 2 , wherein the plurality of fields comprises a first field of the form and a second field of the form; and
wherein filling in the field of the form with the text further comprises:
placing a first portion of the text into the first field of the form; and
placing a second portion of the text into the second field of the form.
4. The method of claim 1 , wherein the speech relates to an entity name and location identifier.
5. The method of claim 1 , wherein prompting the user and receiving the speech occur within a spoken dialog.
6. The method of claim 1 , further comprising analyzing a website structure associated with the form, where the prompt is associated with the website structure.
7. The method of claim 6 , wherein analyzing the website structure occurs off-line.
8. A system comprising:
a processor; and
a non-transitory computer-readable storage medium storing instructions which, when executed on the processor, perform a method comprising:
prompting a user, via a prompt, to provide information associated with a field on a form;
receiving speech from the user in response to the prompt;
converting the speech to a text;
filling in the field of the form with the text, to yield a filled form; and
receiving a webpage generated based at least in part on the filled form.
9. The system of claim 8 , wherein the field comprises a plurality of fields.
10. The system of claim 8 , wherein the plurality of fields comprises a first field of the form and a second field of the form; and
wherein filling in the field of the form with the text further comprises:
placing a first portion of the text into the first field of the form; and
placing a second portion of the text into the second field of the form.
11. The system of claim 8 , wherein the speech relates to an entity name and location identifier.
12. The system of claim 8 , wherein prompting the user and receiving the speech occur within a spoken dialog.
13. The system of claim 8 , the non-transitory computer-readable storage medium storing additional instructions which perform a method comprising analyzing a website structure associated with the form, where the prompt is associated with the website structure.
14. The system of claim 13 , wherein analyzing the website structure occurs off-line.
15. A non-transitory computer-readable storage medium storing instructions which, when executed on a computing device, cause the computing device to perform a method comprising:
prompting a user, via a prompt, to provide information associated with a field on a form;
receiving speech from the user in response to the prompt;
converting the speech to a text;
filling in the field of the form with the text, to yield a filled form; and
receiving a webpage generated based at least in part on the filled form.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the field comprises a plurality of fields.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of fields comprises a first field of the form and a second field of the form; and
wherein filling in the field of the form with the text further comprises:
placing a first portion of the text into the first field of the form; and
placing a second portion of the text into the second field of the form.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the speech relates to an entity name and location identifier.
19. The non-transitory computer-readable storage medium of claim 15 , wherein prompting the user and receiving the speech occur within a spoken dialog.
20. The non-transitory computer-readable storage medium of claim 15 , the non-transitory computer-readable storage medium storing additional instructions which perform a method comprising analyzing a website structure associated with the form, where the prompt is associated with the website structure.