Context-aware handwriting recognition for application input fields

Patent metadata

Field	Value
Publication number	US-9639767-B2
Application number	US-201414328196-A
Country	US
Kind code	B2
Filing date	Jul 10, 2014
Priority date	Jul 10, 2014
Publication date	May 2, 2017
Grant date	May 2, 2017

Abstract

For context-aware handwriting recognition for input fields, an apparatus, system, method, and computer program product are disclosed. The apparatus may include a processor, a handwriting input unit operatively coupled to the processor, a display operatively coupled to the processor, a field metadata module that obtains metadata related to an input field, a field type module that identifies a field type of the input field associated with the handwriting input based on the metadata, and a recognition tuning module that adjusts a handwriting recognition engine based on the field type. Adjusting the handwriting recognition engine may include increasing a weight given to text having particular characteristics, based on the field type. Obtaining the metadata related to an input field may include querying an application for properties of the input field and/or identifying text adjacent to the input field.

First claim

What is claimed is:

1. An apparatus comprising:
a processor;
an input device operatively coupled to the processor that receives, by user input, a handwriting input;
a memory that stores code executable by the processor to:
obtain metadata related to an input field associated with the handwriting input;
identify a field type of the input field using the metadata; and
increase a weight given by a handwriting recognition engine to text having properties associated with the identified field type.

2. The apparatus of claim 1 , wherein the processor further queries an application for properties of the input field, wherein obtaining metadata related to the input field associated with the handwriting input comprises receiving one or more results of the query as metadata.

3. The apparatus of claim 1 , wherein the processor further identifies text adjacent to the input field, wherein obtaining metadata related to the input field associated with the handwriting input comprises receiving the text as metadata.

4. The apparatus of claim 1 , wherein the processor further associates the handwriting input with a particular input field using a field type of the particular input field and content of the handwriting input.

5. The apparatus of claim 4 , wherein the processor identifies a plurality of input fields near a location of the handwriting input and associates the handwriting input with an input field having a field type related to content of the handwriting input.

6. The apparatus of claim 1 , wherein the processor further associates the handwriting input with a particular input field using a location of the handwriting input.

7. The apparatus of claim 6 , wherein associating the handwriting input with a particular input field using a location of the handwriting input comprises the processor:
identifying the location of the handwriting input with respect to a plurality of input fields;
calculating distances between the location of the handwriting input and each input field; and
associating the handwriting input with a nearest one of the plurality of input fields.

8. The apparatus of claim 6 , wherein associating the handwriting input with a particular input field using a location of the handwriting input comprises the processor:
identifying a plurality of input fields that are located within a predetermined distance of the location of the handwriting input;
analyzing content of the handwriting input; and
selecting one of the plurality of input fields matching the content of the handwriting input.

9. The apparatus of claim 1 , wherein the processor further provides an input suggestion from a contacts database in response to the input field type being one of: an email address field, an address field, a telephone number field, and a uniform resource locator field.

10. A method comprising:
receiving handwriting input from an input device in response to user input;
identifying, by use of a processor, a field type of an input field associated with the handwriting input;
causing a handwriting recognition engine to use a language model specific to the identified field type; and
increasing a weight given by the handwriting recognition engine to text having characteristics associated with the identified field type.

11. The method of claim 10 , further comprising obtaining metadata related to the input field, wherein identifying a field type of the input field comprises identifying a field type using the metadata.

12. The method of claim 11 , wherein obtaining metadata related to the input field comprises at least one action selected from the group consisting of: querying an application for a property of the input field and identifying text adjacent to the input field.

13. The method of claim 10 , further comprising:
calculating distances between the handwriting input and positions of a plurality of the input fields; and
associating the handwriting input with each input field having a distance within a predetermined percentage of a distance between the handwriting input and a nearest input fields.

14. The method of claim 10 , further comprising:
calculating distances between the location of handwriting input and positions of a plurality of input fields; and
associating the handwriting input with an input field in response to the distance being less than a predetermined threshold.

15. The method of claim 10 , further comprising:
comparing content of the handwriting input to the input field type; and
associating the handwriting input with another input field in response to the content not matching the input field type.

16. The method of claim 10 , further comprising:
identifying a plurality of input fields that are located within a predetermined distance of each other;
analyzing content of the handwriting input; and
selecting one of the plurality of input fields matching the content of the handwriting input.

17. The method of claim 10 , further comprising:
providing provides an input suggestion from a contacts database in response to the identified field type being one of: an email address field, an address field, a telephone number field, and a uniform resource locator field.

18. A program product comprising a non-transitory computer readable storage medium that stores code executable by a processor to perform:
receiving handwriting input;
obtaining metadata related to an input field associated with the handwriting input;
identifying a field type of the input field using the metadata; and
increasing a weight given by a handwriting recognition engine to text having characteristics associated with the field type.

19. The program product of claim 18 , further comprising associating the handwriting input with the input field using a location of the handwriting input.

20. The program product of claim 19 , wherein associating the handwriting input with the input field comprises identifying a plurality of input fields near a location of the handwriting input and associating the handwriting input with an input field having a field type related to content of the handwriting input.

Assignees

• Lenovo Singapore Pte Ltd
• Lenovo Singapore Pte Ltd

Inventors

• Perrin Steven Richard
• Kelso Scott Edwards
• Nicholson John Weldon
• Zhang Jianbang

Classifications

• G06V30/1448

  based on markings or identifiers characterising the document or the area · CPC title

• G06V30/333 Primary

  Preprocessing; Feature extraction · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K2209/01

  Physics · mapped topic

• G06K9/00409

  Physics · mapped topic