Devices, systems and methods for transcription suggestions and completions
View Patent ↗Methods, devices and systems are described for transcribing text from artifacts to electronic files. A computer system is provided, wherein the computer system comprises a computer-readable storage device. An image of the artifact is received wherein text is present on the artifact. A first portion of the text is analyzed. Characters representing the first portion of the text are identified at a first confidence level equal to or greater than a threshold confidence level. The characters representing the first portion of the text are stored. A second portion of the text appearing on the artifact is analyzed. A plurality of candidates to represent the second portion of the text are identified at a second confidence level below the threshold confidence level. Finally, the plurality of candidates to a user for selection are presented.
1. A method for transcribing text from an artifact to an electronic file, the method comprising:
providing a computer system, wherein the computer system comprises a non-transitory computer-readable storage device;
receiving, by the computer system, an image, wherein text is present on the image;
analyzing, by the computer system, a first portion of the text;
identifying, by the computer system, at a first confidence level equal to or greater than a threshold confidence level, characters representing the first portion of the text;
storing, by the non-transitory computer-readable storage device, the characters representing the first portion of the text;
analyzing, by the computer system, a second portion of the text;
identifying, by the computer system, at a second confidence level below the threshold confidence level, a plurality of candidates to represent the second portion of the text, wherein at least one candidate having a candidate threshold confidence level of the plurality of candidates to represent the second portion of text is identified based on related characters within a data category from two or more records of a plurality of records; and
presenting, by the computer system, the plurality of candidates to a user for selection based on the candidate threshold confidence level; wherein
the data category comprises compiling the two or more records of a plurality of records into a data category database; and
the two or more records of a plurality of records are chosen from a group consists individual records that stored for individual persons, places, and time periods.
2. The method of claim 1 , further comprising:
receiving, by the computer system, from the user a selection of one of the plurality of candidates to represent the second portion of the text; and
storing, by the non-transitory computer-readable storage device, the selection.
3. The method of claim 2 , further comprising creating, by the computer system, the electronic file comprising the digital characters representing the first portion of the text and the selection.
4. The method of claim 1 , wherein the characters comprise one or more of: letters, numbers, punctuation, or symbols.
5. The method of claim 1 , further comprising:
providing, by the computer system, a database, wherein the database comprises electronic text transcribed from physical documents;
determining, by the computer system, a link between at least one record of the database and the physical document; and
matching, at the computer system, at least a portion of the at least one record to a portion of imaged text of the physical document.
6. A non-transitory computer-readable medium for transcribing text to an electronic file having sets of instructions stored thereon which, when executed by a computer, cause the computer to:
receive an image, wherein text is present on the image;
analyze a first portion of the text;
identify at a first confidence level equal to or greater than a threshold confidence level, characters representing the first portion of the text;
store the characters representing the first portion of the text;
analyze a second portion of the text;
identify at a second confidence level below the threshold confidence level, a plurality of candidates to represent the second portion of the text, wherein at least one candidate having a candidate threshold confidence level of the plurality of candidates to represent the second portion of text is identified based on related characters within a data category from two or more records of a plurality of records; and
present the plurality of candidates to a user for selection based on the candidate threshold confidence level; wherein
the data category comprises compiling the two or more records of a plurality of records into a data category database; and
the two or more records of a plurality of records are chosen from a group consists individual records that stored for individual persons, places, and time periods.
7. The non-transitory computer-readable medium of claim 6 , wherein the sets of instructions further cause the computer system to:
provide a database, wherein the database comprises electronic text transcribed from physical documents;
determine a link between at least one record of the database and the physical document; and
match at least a portion of the at least one record to a portion of imaged text of the physical document.
8. The non-transitory computer-readable medium of claim 7 , wherein the matching is used to identify at least one of the plurality of candidate strings of electronic text to represent portions of the imaged text.
9. The non-transitory computer-readable medium of claim 7 , wherein the link between the at least one record of the database and the physical document is a common string of text.
10. The non-transitory computer-readable medium of claim 7 , wherein the link between the at least one record of the database and the physical document is a common person's name.
11. The non-transitory computer-readable medium of claim 6 , wherein the sets of instructions further cause the computer system to:
receive from the user a selection of one of the plurality of candidates to represent the second portion of the text; and
store the selection.
12. The non-transitory computer-readable medium of claim 6 , wherein the sets of instructions further cause the computer system to:
identify a string of digitized text to represent a portion of the text;
determine a confidence level of the string of text;
compare the confidence level to a threshold confidence level;
determine that the confidence level is greater than or equal to the threshold confidence level;
store the string of text as part of the electronic document.
13. A system for transcribing text appearing in imaged documents to an electronic file, the system comprising:
a memory device having sets of instructions stored thereon; and
a computer processor in communication with the memory device, wherein the sets of instructions when executed by the computer processor, cause the computer processor to:
receive an image, wherein text is present on the image;
analyze a first portion of the text;
identify at a first confidence level equal to or greater than a threshold confidence level, characters representing the first portion of the text;
store the characters representing the first portion of the text;
analyze a second portion of the text;
identify at a second confidence level below the threshold confidence level, a plurality of candidates to represent the second portion of the text, wherein at least one candidate having a candidate threshold confidence level of the plurality of candidates to represent the second portion of text is identified based on related characters within a data category from two or more records of a plurality of records; and
present the plurality of candidates to a user for selection based on the candidate threshold confidence level; wherein
the data category comprises compiling the two or more records of a plurality of records into a data category database; and
the two or more records of a plurality of records are chosen from a group consists individual records that stored for individual persons, places, and time periods.
14. The system of claim 13 , wherein the sets of instructions further cause the computer processor to:
transcribe text from the image of the document, wherein the text is transcribed at a confidence level equal to or greater than the threshold confidence level; and
store transcribed text in the electronic document.
15. The system of claim 14 , wherein the threshold confidence level is configurable by the user.
16. The system of claim 13 , wherein the related characters within the record is determined based upon a common data element of the record and the document of one or more of the following: a name of a person, a date of birth of the person, a date of death of the person, a relative of the person, a location, an address, or a social security number.
17. The system of claim 16 , wherein the record and the document are members comprise one or more of: census documents, birth certificates, death certificates, marriage licenses, or immigration records.
18. The system of claim 13 , wherein the characters comprise one or more of: letters, numbers, punctuation, or symbols.
19. The method of claim 13 , wherein the sets of instructions further cause the computer processor to:
receive from the user a selection of one of the plurality of candidates to represent the second portion of the text; and
store the selection.
20. The method of claim 19 , wherein the sets of instructions further cause the computer processor to:
create the electronic file comprising the digital characters representing the first portion of the text and the selection.