System for automatically filling in paper forms with electronic data
View Patent ↗Embodiments of the disclosed technology provide a system and method for automatically filling paper form with electronic data. The system receives from a user a scanned image of a paper form that includes a plurality of fields. The system then retrieves a schema map that maps the plurality of fields in the paper form to a plurality of fields in an electronic data record associated with the user. Next, the system retrieves data values of the fields in the electronic data record based on the schema map. The system also synthesizes the retrieved data values and the scanned image to create an image of the paper form in which the fields are filled with the retrieved data values.
1. A computer-implemented method for automatically filling a paper form, comprising:
receiving a scanned image of a paper form which comprises a plurality of fields;
determining, by the computer, whether a schema map record for the paper form is available, wherein the schema map record includes mappings between a plurality of data-entry areas of the paper form that correspond to a plurality of fields in the paper form and a plurality of fields in an electronic data record associated with a user;
in response to the schema map record not being available, interacting with the user to create the schema map record, wherein creating the schema map record involves:
extracting field labels from the scanned image of the paper form;
searching for data fields in the electronic data record based on the extracted field labels;
identifying common fields between the scanned image of the paper form and schema maps for pre-existing paper form images;
presenting, to the user, one or more potential mappings between the identified common fields of the paper form images and the data fields of the electronic data record; and
generating the schema map record based on potential mappings selected by the user;
retrieving data values, for the data-entry areas of the paper form, using fields of the electronic data record as determined based on the schema map record; and
synthesizing the retrieved data values and the scanned image to create an image of the paper form in which the fields are filled with the retrieved data values.
2. The method of claim 1 , further comprising:
prompting the user to define a data-entry area in the scanned image corresponding to a respective field of the paper form;
converting information in the user-defined data-entry area from the image to text;
selecting from the electronic data record a number of fields that are likely to correspond to the field of the paper form based on the converted text;
suggesting to the user the selected fields as choices for the corresponding field in the electronic data record; and
receiving a field selection from the user, wherein the field selection includes one or more of the selected fields from the electronic data record.
3. The method of claim 1 , further comprising:
in response to a respective field in the paper form not being included in the schema map record, prompting the user to enter a value for the field in the paper form; and
synthesizing the value received from the user into the image of the paper form in which the fields are filled.
4. The method of claim 1 , further comprising:
in response to the value corresponding to a respective field in the paper form not being successfully retrieved from the electronic data record, prompting the user to enter a value for the field in the paper form; and
synthesizing the value received from the user into the image of the paper form in which the fields are filled.
5. The method of claim 1 , wherein synthesizing the retrieved data values and the scanned image comprises:
converting each retrieved data value to an image of the data value; and
overlaying the image of the data value transparently over the scanned image of the paper form.
6. The method of claim 5 , further comprising:
adjusting the size and the position of the image of the data value based on the schema map record.
7. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for automatically filling out paper forms, the method comprising:
receiving a scanned image of a paper form which comprises a plurality of fields;
determining whether a schema map record for the paper form is available, wherein the schema map record includes mappings between a plurality of data-entry areas of the paper form that correspond to a plurality of fields in the paper form and a plurality of fields in an electronic data record associated with a user;
in response to the schema map record not being available, interacting with the user to create the schema map record, wherein creating the schema map record involves:
extracting field labels from the scanned image of the paper form;
searching for data fields in the electronic data record based on the extracted field labels;
identifying common fields between the scanned image of the paper form and schema maps for pre-existing paper form images;
presenting, to the user, one or more potential mappings between the identified common fields of the paper form images and the data fields of the electronic data record; and
generating the schema map record based on potential mappings selected by the user;
retrieving data values, for the data-entry areas of the paper form, using fields of the electronic data record as determined based on the schema map record; and
synthesizing the retrieved data values and the scanned image to create an image of the paper form in which the plurality of fields are filled with the retrieved data values.
8. The non-transitory computer-readable storage medium of claim 7 , wherein the method further comprises:
prompting the user to define a data-entry area in the scanned image corresponding to a respective field of the paper form;
converting information in the user-defined data-entry area from the image to text;
selecting from the electronic data record a number of fields that are likely to correspond to the field of the paper form based on the converted text;
suggesting to the user the selected fields as choices for the corresponding field in the electronic data record; and
receiving a field selection from the user, wherein the field selection includes one or more of the selected fields from the electronic data record.
9. The non-transitory computer-readable storage medium of claim 7 , wherein the method further comprises:
in response to a respective field in the paper form not being included in the schema map record, prompting the user to enter a value for the field in the paper form; and
synthesizing the value received from the user into the image of the paper form in which the plurality of fields are filled.
10. The non-transitory computer-readable storage medium of claim 7 , wherein the method further comprises:
in response to the value corresponding to a respective field in the paper form not being successfully retrieved from the electronic data record, prompting the user to enter a value for the field in the paper form; and
synthesizing the value received from the user into the image of the paper form in which the plurality of fields are filled.
11. The non-transitory computer-readable storage medium of claim 7 , wherein synthesizing the retrieved data values and the scanned image comprises:
converting each retrieved data value to an image of the data value; and
overlaying the image of the data value transparently over the scanned image of the paper form.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the method further comprises:
adjusting the size and the position of the image of the data value based on the schema map record.
13. A system, comprising:
a processor;
a memory;
a receiving mechanism configured to receive a scanned image of a paper form which comprises a plurality of fields;
a determining mechanism configured to determine whether a schema map record for the paper form is available, wherein the schema map record includes mappings between a plurality of data-entry areas of the paper form that correspond to a plurality of fields in the paper form and a plurality of fields in an electronic data record associated with a user,
a schema generating mechanism configured to create the schema map record by interacting with the user in response to the schema map record not being available, wherein creating the schema map record involves:
extracting field labels from the scanned image of the paper form;
searching for data fields in the electronic data record based on the extracted field labels;
identifying common fields between the scanned image of the paper form and schema maps for pre-existing paper form images;
presenting, to the user, one or more potential mappings between the identified common fields of the paper form images and the data fields of the electronic data record; and
generating the schema map record based on potential mappings selected by the user;
wherein the retrieving mechanism is further configured to retrieve data values, for the data-entry areas of the paper form, using fields of the electronic data record as determined based on the schema map record; and
a synthesizing mechanism configured to synthesize the retrieved data values and the scanned image to create an image of the paper form in which the plurality of fields are filled with the retrieved data values.
14. The system of claim 13 , the schema generating mechanism is further configured to:
prompt the user to define a data-entry area in the scanned image corresponding to a respective field of the paper form;
convert information in the user-defined data-entry area from the image to text;
select from the electronic data record a number of fields that are likely to correspond to the field of the paper form based on the converted text;
suggest to the user the selected fields as choices for the corresponding field in the electronic data record; and
receive a field selection from the user, wherein the field selection includes one or more of the selected fields from the electronic data record.
15. The system of claim 13 ,
wherein the schema generating mechanism is further configured to prompt the user to enter a value for the field in the paper form in response to a respective field in the paper form not included in the schema map record; and
wherein the synthesizing mechanism is further configured to synthesize the value received from the user into the image of the paper form in which the plurality of fields are filled.
16. The system of claim 13 ,
wherein the schema generating mechanism is further configured to prompt the user to enter a value for the field in the paper form in response to the value corresponding to a respective field in the paper form not being successfully retrieved from the electronic data record; and
wherein the synthesizing mechanism is further configured to synthesize the value received from the user into the image of the paper form in which the plurality of fields are filled.
17. The system of claim 13 , wherein the synthesizing mechanism is further configured to:
convert each retrieved data value to an image of the data value; and
overlay the image of the data value transparently over the scanned image of the paper form.
18. The system of claim 17 , wherein the synthesizing mechanism is further configured to adjust the size and the position of the image of the data value based on the schema map record.