Proofreader ability managing method and system

• US 20020025070A1
• Filed: 03/13/2001
• Published: 02/28/2002
• Est. Priority Date: 08/31/2000
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Fujino, Akio, Ozawa, Hitoshi, Matsushita, Tsutomu, Nakade, Yoitsu, Kita, Mariko
• Granted Patent: US 6,826,317 B2
• Time in Patent Office: Days
• US Class Current: 382/181
• CPC Class Codes: G06V 10/98 Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns

Abstract

A technology of the present invention is capable of objectively judging an ability of a proofreader who proofreads a digitized document by use OCR programs. A method of managing an ability of a proofreader who proofreads an electronic document generated from a recognition target document by executing a character auto recognition program, comprises a step of estimating a character count of potential mis-recognized characters contained in the electronic document, a step of detecting a mis-recognized character discover count as a mis-recognized character count with which the proofreader discovers the mis-recognized characters in the electronic document, a step of detecting a processing time spent for proofreading the electronic document, and a step of calculating a score relative to a proofreader ability based on a ratio of the potential mis-recognized character count to the mis-recognized character discover count per unit time.

Claims

1. A method of managing an ability of a proofreader who proofreads an electronic document generated from a recognition target document by executing character auto recognition programs, said method comprising:

a step of estimating a character count of potential mis-recognized characters contained in the electronic document;

a step of detecting a mis-recognized character discover count with which the proofreader discovers the mis-recognized characters in the electronic document;

a step of detecting a processing time spent for proofreading the electronic document; and

a step of calculating a score relative to a proofreader ability based on a ratio of the mis-recognized character discover count per unit time to the potential mis-recognized character count.

2. A method of managing an ability of a proofreader according to claim 1, wherein said step of counting the potential mis-recognized character count is executed by counting a non-coincident character count between the electronic documents generated by executing plural types of character auto recognition programs with respect to the same recognition target document, or by counting a character count of which a degree of coincidence showing a preciseness of the character auto recognition for each character by a character auto recognition programs is a predetermined value or under.

3. A method of managing an ability of a proofreader according to claim 1, further comprising:

a step of calculating a degree of difficulty of a proofreading target electronic document on the basis of a ratio of the potential mis-recognized character count to a total character count of the electronic document;

a step of calculating a proofreader ability level by averaging the scores with respect to the plurality of proofreading target electronic documents per predetermined range of the degree of difficulty; and

a step of selecting an optimal proofreader corresponding to the degree of difficulty of the proofreading target electronic document.

4. A method of managing an ability of a proofreader according to claim 1, further comprising:

a step of calculating a change in the score relative to the proofreader ability with respect to the operation time for consecutively proofreading the plurality of proofreading target electronic documents; and

a step of setting the operation time based on the change in the score relative to the proofreader ability.

5. A method of managing an ability of a proofreader according to claim 4, further comprising:

a step of evaluating the proofreader ability for every predetermined operation time; and

a step of setting again the operation time on the basis of the change in the proofreader ability.

6. A system for managing an ability of a proofreader who proofreads an electronic document generated from a recognition target document by executing character auto recognition programs, said system comprising:

an information input/output unit for detecting a mis-recognized character discover count with which the proofreader discovers the mis-recognized characters in the electronic document, and a processing time spent for proofreading the electronic document;

an information recording unit;

an information display unit; and

a control unit for executing a step of counting a character count of potential mis-recognized characters contained in the electronic document, and a step of calculating a score relative to a proofreader ability based on a ratio of the mis-recognized character discover count per unit time to the potential mis-recognized character count.

7. A system for managing an ability of a proofreader according to claim 6, further comprising a timer,

wherein said information input/output unit detects a start of the proofreading operation and an end of the proofreading operation, and

said timer counts a period of time from the start of the proofreading operation to the end of the proofreading operation.

8. A system for managing an ability of a proofreader according to claim 6, wherein said control unit, in said step of counting the potential mis-recognized character count, estimates the potential mis-recognized character count by counting a non-coincident character count between the electronic documents generated by executing plural types of character auto recognition programs with respect to the same recognition target document, or by counting a character count of which a degree of coincidence showing a preciseness of each character by a character auto recognition program is a predetermined value or under.

9. A system for managing an ability of a proofreader according to claim 6, where said control unit further executes:

a step of calculating a degree of difficulty of a proofreading target electronic document on the basis of a ratio of the potential mis-recognized character count to a total character count of the electronic document;

a step of calculating a proofreader ability level by averaging the scores with respect to the plurality of proofreading target electronic documents per predetermined range of the degree of difficulty; and

a step of selecting an optimal proofreader corresponding to the degree of difficulty of the proofreading target electronic document.

10. A system for managing an ability of a proofreader according to claim 6, wherein said control unit further executes:

a step of calculating a change in the score relative to the proofreader ability with respect to the operation time for consecutively proofreading the plurality of proofreading target electronic documents; and

a step of setting the operation time based on the change in the proofreader ability.

11. A system for managing an ability of a proofreader according to claim 10, wherein said control unit further executes:

a step of evaluating the proofreader ability for every predetermined operation time; and

a step of setting again the operation time on the basis of the change in the proofreader ability.

12. A readable-by-computer recording medium recorded with a program, executed by a computer, for managing an ability of a proofreader who proofreads an electronic document generated from a recognition target document by executing character auto recognition programs, said program comprising:

a process of estimating a character count of potential mis-recognized characters contained in the electronic document;

a process of detecting a mis-recognized character discover count as a mis-recognized character count with which the proofreader discovers the mis-recognized characters in the electronic document;

a process of detecting a processing time spent for proofreading the electronic document; and

a process of calculating a score relative to a proofreader ability based on a ratio of the mis-recognized character discover count per unit time to the potential mis-recognized character count.