Intelligent autofill

• US 20050257148A1
• Filed: 06/23/2004
• Published: 11/17/2005
• Est. Priority Date: 05/12/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Bradford, Donald E., Glasgow, Dane A., Chickering, David M., Goodman, Joshua T., Kadie, Carl M.
• Granted Patent: US 7,254,569 B2
• Time in Patent Office: Days
• US Class Current: 715/226
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

The present invention provides a unique system and method that can employ machine learning techniques to automatically fill one or more fields across a diverse array of web forms. In particular, one or more instrumented tools can collect input or entries of form fields. Machine learning can be used to learn what data corresponds to which fields or types of fields. The input can be sent to a central repository where other databases can be aggregated as well. This input can be provided to a machine learning system to learn how to predict the desired outputs. Alternatively or in addition, learning can be performed in part by observing entries and then adapting the autofill component accordingly. Furthermore, a number of features of database fields as well as constraints can be employed to facilitate assignments of database entries to form values—particularly when the web form has never been seen before by the autofill system.

Claims

1. A method that facilitates automatic data entry of forms comprising:

providing a web-based form having a plurality of input fields; and

employing a machine learning technique to automatically fill at least one of the input fields.

2. The method of claim 1, the input fields comprise at least one of text fields, file input fields, select boxes, radio buttons, and check boxes.

3. The method of claim 2, further comprising determining what file to automatically enter into a field based in part on some combination of recently used entries in the file field and recently accessed files, the combination being based at least in part on a time of last access and a time of last entry.

4. The method of claim 1, the act of employing a machine learning technique to automatically fill at least one of the input fields comprises:

observing and collecting input in the input fields; and

mapping the input to their respective fields to learn what input corresponds to which input fields.

5. The method of claim 4, further comprising sending the input collected and/or observed to a central repository, from which a plurality of inputs can be generated for use by the machine learning technique to learn what database entries correspond to which database fields.

6. The method of claim 5, the central repository comprising one or more databases corresponding to at least one of a user profile, an address book, contact list, an account registration, and a product registration.

7. The method of claim 5, further comprising generating one or more assignments from database entries to form values based at least in part upon one or more constraints.

8. The method of claim 7, the one or more constraints comprising reuse constraints that limit a number of times any one database entry is used per web-based.

9. The method of claim 7, the one or more constraints comprising composition constraints that control which database entries or output types are allowed to be present concurrently on any web-based form.

10. The method of claim 7, the one or more constraints comprising constraints on fields occurring together or in a particular order.

11. The method of claim 5, further comprising deriving features from the one or more database entries and/or database fields to facilitate learning correlations between input and input fields.

12. The method of claim 11, at least one feature corresponds to a particular database field being at least one of above, below, to the left of, to the right of, immediately below, immediately above, immediately to the left of, or immediately to the right of some other database field.

13. The method of claim 11, further comprising determining a joint probability of a particular assignment of input fields to form fields that involve at least one of the features.

14. The method of claim 5, further comprising:

personalizing the mapping from database fields to form values by learning that for a particular user, some input field entries correspond to observed database entries; and

updating the autofill component with such information in a site-specific manner that involves learning that some input field entries on a particular web page correspond to particular database entries.

15. The method of claim 5, further comprising observing that a user is entering data into a field consistent with data found in the one or more databases which triggers the autofill component to provide new autofill suggestions based in part on best ranked consistent entries.

16. The method of claim 5, further comprising maintaining the central repository on a machine separate from the user'"'"'s computer.

17. The method of claim 5, further comprising using one or more instrumented toolbars to observe and collect the input.

18. The method of claim 1, the input comprising at least one of the following:

MAXLENGTH or SIZE entries;

substrings of a field name;

information from one or more adjacent form fields; and

at least one of nearby text and substrings of nearby text.

19. The method of claim 1, further comprising converting one or more inputs to one or more feature values.

20. The method of claim 19, the feature values are one of Boolean values and numeric values.

21. The method of claim 20, automatically determining the Boolean values by performing at least one of the following:

finding useful ranges; and

looking for common and useful character sequences.

22. The method of claim 20, manually determining the Boolean values by inspecting input values and determining one or more most useful Boolean values.

23. The method of claim 1, further comprising providing autofill suggestions in at least one of the following manners:

in a drop down box from a field when a user begins to enter data into the field; and

as soon as a user enters the field, filling the field with suggested data.

24. The method of claim 1, further comprising detecting whether the web-based form comprises multiple varieties of fields and separates them into at least two subsets of fields.

25. The method of claim 24, the component employs Heuristics to detect the multiple sets and to separate them into at least two subsets.

26. The method of claim 1, further comprising observing user entries of form fields to facilitate learning what value is most appropriate for the one or more form fields.

27. The method of claim 26, further comprising learning which of the entries a user has previously made, and that the user is most likely to enter into a given input field.

28. The method of claim 27, further comprising not learning user entries for fields that appear to comprise sensitive information.

29. The method of claim 26, further comprising generating one or more features based in part on the values possible for the fields.

30. The method of claim 29, the one or more features are order-based for each value preceding a next value.

31. The method of claim 26, the machine learning system is trained using an offline algorithm that includes collecting a plurality of observed instances of field entries and storing them.

32. The method of claim 26, the machine learning system is trained using an online algorithm using any one of Naï

ves Bayes approach, gradient descent, winnow, and perceptron algorithm.

33. The method of claim 1, further comprising analyzing one or more database entries and observed entries to learn at least one of the following:

a probability of a field being filled with an entry from the database times a probability that the database field is a correct entry; and

a probability of a field not being filled with an entry from the database times a probability computed by observing user entries.

34. A computer readable medium having stored thereon computer-executable instructions for implementing the method of claim 1.

35. A data packet adapted to be transmitted between two or more computer processes facilitating easier viewing, browsing and/or manipulating of media items, the data packet comprising information associated with a grouping of selected media items that are pulled from a host media store and sent to an interactive media frame display, the grouping being based at least in part upon metadata associated with the media items.

36. An intelligent autofill system comprising:

means for observing and collecting data entries in form fields; and

means for machine learning what data entries correspond to which form fields to facilitate automatically entering form fields with such data entries.

37. A computer readable medium having stored thereon computer-executable components for the system of claim 36.