GENERATING AND PROCESSING FORMS FOR RECEIVING SPEECH DATA

• US 20100100377A1
• Filed: 10/13/2009
• Published: 04/22/2010
• Est. Priority Date: 10/10/2008
• Status: Abandoned Application

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bearman, Robert, Branthwaite, Matthew D., Bertoglio, Mark D., Pollard, John F., Madhavapeddi, Shreedhar, Wiggs, Jonathan
• Application Number:
  US12/578,542
• Publication Number:
  US 20100100377A1
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A system and method for dynamically generating and processing forms for receiving data, such as text-based data or speech data provided over a telephone, mobile device, via a computer and microphone, etc. is disclosed. A form developer can use a toolkit provided by the system to create forms that end-users connect to and complete. The system provides a user-friendly interface for the form developer to create various input fields for the form and impose parameters on the data that may be used to complete or populate those fields. These fields may be included to receive specific information, such as the name of the person filling out the form, or may be free-form, allowing a user to provide a continuous stream of information. Furthermore, the system allows a form developer to establish means for providing access to the form and set access limits on the form. Other aspects are disclosed herein.

Claims

1. A method for executing a voice-based form, the method comprising:

receiving from a user a request to connect to a voice-based form, the voice-based form having a plurality of fields, each field having an associated type;

determining whether the user is authorized to access the voice-based form based at least on identification information received from the user;

after the user is authorized to access the voice-based form, for at least one of the plurality of fields,

prompting the user to provide data for the field,

receiving data from the user for the field,

when it is determined that the data received from the user for the field is voice data,

converting the voice data to text data,

generating a confidence score for the converted voice data, and

when it is determined that the generated confidence score does not exceed a first threshold, prompting the user re-enter the data, and

storing data received from the user for the field; and

providing the stored data for each of the plurality of fields to a predetermined destination location, wherein the destination location is accessible via a network.

2. The method of claim 1 wherein the request to connect to the voice-based form is a telephone call to a phone number associated with the voice-based form, and wherein determining whether the user is authorized to access the voice-based form includes determining whether a telephone number of caller identification (caller ID) data associated with the telephone call is an authorized telephone number.

3. The method of claim 1 wherein the request to connect to the voice-based form is a call to a number associated with the voice-based form.

4. The method of claim 1 wherein the request to connect to the voice-based form is a short message received from a mobile device of the user, wherein prompting the user to provide data for at least one of the plurality of fields includes sending a short message to the mobile device of the user, and wherein data received from the user for at least one of the fields is received via a Multimedia Messaging Service (MMS) message.

5. The method of claim 1 wherein the request to connect to the voice-based form is a Short Message Service (SMS) message received from a mobile device of the user and wherein prompting the user to provide data for at least one of the plurality of fields includes sending an SMS message to the mobile device of the user.

6. The method of claim 1, further comprising sending to a form administrator an indication of the stored data for each of the plurality of fields, and wherein the indication of the stored data for each of the plurality of fields is sent to the form administrator via an email message.

7. A system for generating and processing voice-based forms, the system comprising:

a form creation component configured to provide an interface for a form developer to define multiple fields for a voice-based form,

wherein each field of the form has an associated type and,

wherein each of the multiple fields has multiple parameters for prompting a user to enter data for each of the multiple fields and for processing data provided by the user,

wherein at least one of the multiple fields is associated with a free-form audio type;

a form access component configured to establish a connection with the user to receive input data for the form;

a form execution component configured to prompt the user to provide data for each of the multiple fields of the form, and to receive data from the user for each of the multiple fields of the form; and

a speech-to-text component configured to convert audio data received from a user into text data for the form.

8. The system of claim 7 wherein the form access component is configured to establish a connection with the user at least in part by automatically and periodically placing a telephone call to the user.

9. The system of claim 7 wherein the form access component is configured to establish a connection with the user at least in part by sending an email to the user.

10. The system of claim 7 wherein the speech-to-text component is configured to generate a confidence score for converted audio data, the confidence score corresponding to a probability that the speech-to-text component correctly converted the audio data to text data.

11. The system of claim 7 wherein the speech-to-text component is configured to identify keywords within audio data.

12. The system of claim 11, further comprising:

a advertisement component configured to present advertisements to the user based on identified keywords.

13. A computer-readable storage medium storing instructions that, when executed by a computer, cause the computer to perform a method of generating a form for gathering user input, the method comprising:

providing at least two different authorization options for users who are authorized to provide user input to the form;

receiving user input selecting one of the two authorization options;

providing at least two data input fields for the form;

receiving user input defining the at least two data input fields, including at least one parameter defining data acceptable for the two data input fields;

providing at least one free-speech input field for the form, wherein the free-speech input field may receive spoken audio input, and wherein the received spoken audio input is to be automatically converted from speech to text for the free-speech input field;

setting a destination for data input to the form; and

,

creating the form based on the received user input selecting one of the two authorization options and defining the at least two data input fields.

14. The computer-readable storage medium of claim 13 wherein the two different authorization options include a public option that permits anyone to provide input, and a private option that permits only a select set of users to provide input based on phone numbers for the select set of users;

wherein parameters for the two different data fields include at least two of;

number, currency, date and time, yes/no, and a name of a person or group; and

,

wherein the destination includes an email address or text message number for sending data received via the form, a database or spreadsheet to be updated or revised based on data received via the form, or an external application to process data received via the form.

15. The computer-readable storage medium of claim 13 wherein the form is an extensible markup language (XML) form, and wherein providing the at least two input fields includes providing application programming interfaces (APIs) that define acceptable input for the two input fields, wherein the acceptable input includes two different data types, and wherein the APIs define feedback to users for data received via the two input fields.

16. The computer-readable storage medium of claim 13, further comprising providing at least two different template forms, wherein the template forms are associated with two different workflows and include different data input fields, and wherein the method further comprises:

receiving user input selecting one of the template forms; and

,

receiving user input modifying the selected template form to either add an additional data input field, or modify one of the different data input fields.

17. The computer-readable storage medium of claim 13 wherein one of the two different authorization options includes verifying a user'"'"'s voice from a stored version of the user'"'"'s voice.

18. The computer-readable storage medium of claim 13, further comprising receiving user input defining certain times when, or certain geographic locations from where, user input is acceptable.

19. The computer-readable storage medium of claim 13, further comprising:

receiving user input for when to periodically send the created form to multiple users to gather data;

automatically forwarding the form to the multiple users;

automatically gathering data from the multiple users via the form;

tabulating the gathered data; and

,

producing a graphical representation of the tabulated data.

20. The computer-readable storage medium of claim 13, further comprising providing an option of whether to show an advertisement based on received user input, wherein the advertisement is not provided if a confidence of received data is below a threshold.

21. The computer-readable storage medium of claim 13, further comprising automatically sending a confirming message to a user after creating the form.

22. The computer-readable storage medium of claim 13, further comprising automatically adding additional data fields, wherein the automatically added data fields include a phone number of a user providing input to the created form, a URL of a user providing input to the created form, a time when a user provided input to the created form, or a name of a user providing input to the created form.

23. The computer-readable storage medium of claim 13 wherein providing the at least two input fields includes providing application programming interfaces (APIs) that define acceptable input data for the two input fields, wherein the input data is received as spoken input, and

when a confidence of a conversion of the spoken input is below a lower threshold, user feedback or instructions are provided to request that the user again provide the spoken input;

when a confidence of a conversion of the spoken input is above the lower threshold but below an upper threshold, user feedback or instructions are provided to request that the user confirm the spoken input; and

,

when a confidence of a conversion of the spoken input above the upper threshold, no user feedback or instructions are provided.

24. The computer-readable storage medium of claim 13, further comprising:

automatically gathering statistics from data input to the at least two data input fields by multiple users of the form; and

,

automatically providing usability data or notification that data input to at least one of the two data input fields frequently is below a confidence level.

25. A method performed by a mobile device, such a wireless telecommunications device, for providing input to a previously created form, wherein the mobile device includes at least a manual input portion and an audio input portion, wherein the mobile device is at least intermittently coupled with a network, and wherein the network is coupled to a computer, the method comprising:

receiving the created form from the computer and via the network, wherein the form includes;

at least one data input field having a predetermined format, and

at least one free-text field configured to receive uttered audio input, and

wherein the received uttered audio input is to be automatically converted to text for the free-text field;

presenting the form to the user, including individually presenting the one data input field and the one free-text field;

receiving, from the user, data for input to the one data input field;

receiving, from the user, uttered audio input for input to the free-text field; and

,

providing to the network the received data for the one data input field and the received uttered audio input, wherein the received uttered audio input is to be automatically converted to text for the free-text field.

26. The method of claim 25 wherein presenting the form to the user includes displaying the form to the user, and wherein receiving data for input to the one data input field includes receiving manual user input selecting the one data input field, and receiving spoken user input for the selected one data input field.

27. The method of claim 25 wherein the mobile device is a wireless mobile phone, and wherein the received form is stored on the mobile phone for later data input by the user.

28. A system for generating forms, wherein the forms may receive audio input, the system comprising:

means for providing authorization regarding which users can provide input to a form;

means for providing at least two data input fields for the form;

means for providing at least one free-speech input field, wherein the free-speech input field may receive spoken audio input, and wherein the received spoken audio input is to be automatically converted from speech to text for the free-speech input field; and

,

means for defining an output destination for user data received via the form.