Processing of an electronic document, apparatus and system for processing the document, and storage medium containing computer executable instructions for processing the document

• US 10,255,357 B2
• Filed: 12/23/2013
• Issued: 04/09/2019
• Est. Priority Date: 12/21/2012
• Status: Active Grant

• Current Assignee: DocuWare GmbH (Ricoh Company Limited)
• Original Assignee: DocuWare GmbH (Ricoh Company Limited)
• Inventors: Schuster, Daniel, Muthmann, Klemens
• Primary Examiner(s): Arjomandi, Noosha
• Application Number:
  US14/138,401
• Publication Number:
  US 20140181114A1
• Time in Patent Office: 1,933 Days
• Field of Search: 707740
• CPC Class Codes: G06F 16/38 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 7/24 Sorting, i.e. extracting data from one or more carriers, rearranging the data in numerical or other ordered sequence, and rerecording the sorted data on the original carrier or on a different carrier or set of carriers sorting methods in generalG06F7/36 takes precedence

Abstract

In a method for processing an electronic document, a local database is used to extract information relating to the document, and a super ordinate database is used to extract information relating to the document if a predefined condition is met. An apparatus, a computer program product and a storage medium can execute the method.

Claims

1. A method for processing an electronic document, which comprises the steps of:

extracting information relating to the electronic document via a local database, wherein the electronic document is an electronically scanned optical character recognized preprocessed document;

extracting the information relating to the electronic document when a predefined condition is met via a super ordinate database, the predefined condition includes a fact that an extraction of the information via the local database does not provide any results or does not provide any good results, the extracting step including the following substeps;

providing the predefined condition with a fact that a quality is determined for an extraction of the information using the local database;

comparing the quality with a predefined threshold value; and

using the super ordinate database to extract the information relating to the electronic document when the quality does not reach the predefined threshold value;

using information relating to which fields are intended to be extracted to extract the information from the electronic document; and

determining the information relating to which fields are intended to be extracted using at least one training document.

2. The method according to claim 1, wherein the predefined condition includes a fact that a sufficient number of training documents or sufficiently similar training documents are not available in the local database.

3. The method according to claim 1, which further comprises using the super ordinate database for extraction by virtue of the electronic document being transmitted to the super ordinate database and the information extracted being returned by the super ordinate database.

4. The method according to claim 1, which further comprises performing at least one extraction algorithm for extracting the information relating to the electronic document.

5. The method according to claim 4, which further comprises determining a quality for each extraction proposal for each said extraction algorithm.

6. The method according to claim 5, which further comprises determining a total quality taking into account fields to be extracted and taking into account the quality for each said extraction proposal.

7. The method according to claim 1, which further comprises:

determining a document type by performing a document type recognition method, at least one training document is determined on a basis of a recognized document type; and

extracting information relating to the electronic document using the at least one training document.

8. The method according to claim 1, which further comprises carrying out a manual classification by a user when the extraction by means of the super ordinate database has not reached a required total extraction quality.

9. The method according to claim 8, wherein the manual classification by the user involves a marking of at least one alphanumeric character in the electronic document.

10. The method according to claim 8, which further comprises adapting the local database using the manual classification, a result of the manual classification and/or the electronic document.

11. The method according to claim 10, wherein the local database has an elimination mechanism used to carry out a correction when there are a multiplicity of identical training documents.

12. The method according to claim 8, which further comprises adapting the super ordinate database using the manual classification, a result of the manual classification and/or the electronic document.

13. The method according to claim 12, wherein the super ordinate database has an elimination mechanism used to carry out a correction when there are a multiplicity of identical training documents.

14. The method according to claim 8, wherein the manual classification by the user involves a marking of at least one word in the electronic document.

15. An apparatus for processing an electronic document, the apparatus comprising:

a computer set up such that a local database can be used to extract information relating to the electronic document, and a super ordinate database can be used to extract the information relating to the electronic document when a predefined condition is met, the predefined condition including a fact that an extraction of the information via the local database does not provide any results or does not provide any good results, wherein the electronic document is an electronically scanned optical character recognized preprocessed document, said computer being programmed to;

provide the predefined condition with a fact that a quality is determined for an extraction of the information using the local database;

compare the quality with a predefined threshold value;

use the super ordinate database to extract the information relating to the electronic document when the quality does not reach the predefined threshold value;

use information relating to which fields are intended to be extracted to extract the information from the electronic document; and

determine the information relating to which fields are intended to be extracted using at least one training document.

16. The apparatus according to claim 15, further comprising:

said local database; and

/or

said super ordinate database.

17. A system for processing an electronic document, comprising:

at least one apparatus having a computer set up such that a local database can be used to extract information relating to the electronic document, and a super ordinate database can be used to extract the information relating to the electronic document when a predefined condition is met, the predefined condition including a fact that an extraction of the information via the local database does not provide any results or does not provide any good results, wherein the electronic document is an electronically scanned optical character recognized preprocessed document, said computer being programmed to;

provide the predefined condition with a fact that a quality is determined for an extraction of the information using the local database;

compare the quality with a predefined threshold value;

use the super ordinate database to extract the information relating to the electronic document when the quality does not reach the predefined threshold value;

use information relating to which fields are intended to be extracted to extract the information from the electronic document; and

determine the information relating to which fields are intended to be extracted using at least one training document.

18. Computer executable instructions to be loaded into a non-transitory memory of a digital computer, for performing a method for processing an electronic document, which comprises the steps of:

extracting information relating to the electronic document via a local database, wherein the electronic document is an electronically scanned optical character recognized preprocessed document;

extracting the information relating to the electronic document when a predefined condition is met via a super ordinate database, the predefined condition including a fact that an extraction of the information via the local database does not provide any results or does not provide any good results, the extracting step including the following substeps;

providing the predefined condition with a fact that a quality is determined for an extraction of the information using the local database;

comparing the quality with a predefined threshold value; and

using the super ordinate database to extract the information relating to the electronic document when the quality does not reach the predefined threshold value;

using information relating to which fields are intended to be extracted to extract the information from the electronic document; and

determine the information relating to which fields are intended to be extracted using at least one training document.

19. A non-transitory computer-readable storage medium having computer executable instructions to be executed by a computer for performing a method for processing an electronic document, which comprises the steps of:

extracting information relating to the electronic document via a local database, wherein the electronic document is an electronically scanned optical character recognized preprocessed document;

extracting the information relating to the electronic document when a predefined condition is met via a super ordinate database, the predefined condition including a fact that an extraction of the information via the local database does not provide any results or does not provide any good results, the extracting step including the following substeps;

providing the predefined condition with a fact that a quality is determined for an extraction of the information using the local database;

comparing the quality with a predefined threshold value; and

using the super ordinate database to extract the information relating to the electronic document when the quality does not reach the predefined threshold value;

using information relating to which fields are intended to be extracted to extract the information from the electronic document; and

determining the information relating to which fields are intended to be extracted using at least one training document.