Information processing system and method therefor

• US 6,697,165 B2
• Filed: 12/29/1997
• Issued: 02/24/2004
• Est. Priority Date: 12/26/1996
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Wakai, Masanori, Takayama, Masayuki, Jeyachandran, Suresh, Suda, Aruna Rohra
• Primary Examiner(s): Coles, Edward
• Assistant Examiner(s): POKRZYWA, JOSEPH R
• Application Number:
  US08/999,140
• Publication Number:
  US 20020015166A1
• Time in Patent Office: 2,248 Days
• Field of Search: 358/404, 358/407, 358/434, 358/462, 358/402, 358/403, 358/442, 358/443, 358/444, 358/1.11, 358/1.15, 358/1.18, 382/175, 382/176, 382/173, 382/180, 382/181, 382/209, 382/287, 382/297, 382/317, 382/179, 382/182, 382/187, 382/190, 395/114, 709/218
• US Class Current: 358/1.11
• CPC Class Codes: H04N 1/00968 by scanning marks on a sheet mark-sheet input means H04N1/00355; sensing record carriers G06K7/00
• CPC Class Codes: H04N 1/32561 using a programmed control device, e.g. a microprocessor

Abstract

A document is read by a scanner, the document type is detected, and a specific block in the document, for which character recognition is to be performed, is determined. The character recognition is performed for the specific block, the obtained character strings are analyzed, and in accordance with the analysis results, document objectives, such as the extraction of data, filing, transmission to a printer or notification of transmission, are attained. A process corresponding to the attained objectives is performed for the document that has been read.

Claims

1. An information processing apparatus comprising:

an input unit for inputting a document;

a character recognition unit for recognizing a specific block of the document input by said input unit;

a first character recognition controller for controlling said character recognition unit to recognize a character in a specific block of the document;

a first identifier for identifying a form of the document based on a recognition result of the specific block in the document;

a second character recognition controller for controlling said character recognition unit to recognize a character in the document as a whole when said first identifier cannot identify the form of the document;

a second identifier for identifying a form of the document based on a recognition result of the document as a whole;

an interpreter for interpreting a word formed of characters recognized by said character recognition unit by referring to a knowledge base corresponding to the form of the document identified by said first identifier or second identifier;

a determination unit for determining a process to be performed for the document based on a result of interpretation by said interpreter; and

an execution processor for performing the process determined by said determination unit for the document.

2. An information processing apparatus according to claim 1, further comprising:

an inference unit for inferring a document type in advance of a recognition by said character recognition unit,

wherein the specific block is determined in consonance with the document type inferred by said inference unit.

3. An information processing apparatus according to claim 2, wherein said inference unit reads a document at a higher speed and with a lower resolution than when reading the specific block, and infers the document type.

4. An information processing apparatus according to claim 2, wherein said first identifier identifies the form of the document when a document type obtained based on the recognition result of the specific block matches the document type inferred by said inference unit.

5. An information processing apparatus according to claim 1, wherein said determination unit determines whether the process to be performed for the document is a filling process or a transmission process.

6. An information processing apparatus according to claim 1, wherein, when said determination unit determines that the process to be performed for the document is a filing process, said execution processor files the document input by said input unit.

7. An information processing apparatus according to claim 6, wherein, in accordance with the result of interpretation obtained by said interpreter, said execution processor sorts and files the document input by said input unit.

8. An information processing apparatus according to claim 6, wherein said determination unit determines a filing destination in consonance with the result of interpretation.

9. An information processing apparatus according to claim 1, wherein, when said determination unit determines that the process to be performed for the document is a transmission process, said execution processor transmits the document input by said input unit.

10. An information processing apparatus according to claim 9, wherein said determination unit determines a transmission destination in consonance with the result of interpretation.

11. An information processing apparatus according to claim 9, wherein said determination unit identifies a medium at a transmission destination in accordance with the result of interpretation, and, as needed, performs a medium conversion.

12. An information processing apparatus according to claim 1, wherein said determination unit determines the process to be performed based on a date included in the document and on a current date.

13. An information processing apparatus according to claim 1, wherein said first identifier or said second identifier identifies the form of the document in accordance with a command described in the document.

14. An information processing apparatus according to claim 1, further comprising:

a history memory for storing a history of operations performed by said execution processor.

15. An information processing, apparatus according to claim 14, wherein, when transmission of the document is not recorded in the history of operations, said determination unit determines that the process to be performed is the transmission process.

16. An information processing apparatus according to claim 1, further comprising:

an extractor for extracting predetermined attribute information from results from said character recognition unit; and

a register for registering in a database the extracted predetermined attribute information.

17. An information processing apparatus according to claim 1, further comprising a receiver for receiving a response from a user.

18. An information processing apparatus according to claim 1, further comprising a query unit for issuing a query to a user.

19. An information processing apparatus according to claim 1, wherein media information from various types of media is input to said input unit, and necessary information is extracted from the media information by performing processes corresponding to the media.

20. An information processing method comprising:

an input step, of inputting a document;

a first character recognition step, of recognizing a character in a specific block of the document input in said input step;

a first identification step, of identifying a form of the document based on a recognition result of the specific block in the document recognized in said first character recognition step;

a second character recognition step, of recognizing a character in the document as a whole when the form of the document cannot be identified in said first identification step;

a second identification step, of identifying a form of the document based on a recognition result of the document as a whole recognized in said second character recognition step;

an interpretation step, of interpreting a word formed of characters recognized in said first or second character recognition step by referring to a knowledge base corresponding to the form of the document identified in said first or second identification step;

a determination step, of determining a process to be performed for the document based on a result of interpretation in said interpretation step; and

an execution step, of performing the process determined in said determination step for the document.

21. An information processing method according to claim 20, further comprising:

an inference step, of inferring a document type in advance of a recognition in said character recognition step,

wherein the specific block is determined in consonance with the document type inferred in said inference step.

22. An information processing method according to claim 21, wherein, in said inference step, a document is read at a higher speed and with a lower resolution than when reading the specific block, and the document type is inferred.

23. An information processing method according to claim 21, wherein in said first identification step the form of the document is identified when a document type obtained based on the recognition result of the specific block matches the document type inferred in said inference step.

24. An information processing method according to claim 20, wherein in said determination step it is determined whether the process to be performed for the document is a filling process or a transmission process.

25. An information processing method according to claim 20, wherein, when it is determined in said determination step that the process to be performed for the document is a filing process, the document input in said input step is filed in said execution step.

26. An information processing method according to claim 25, wherein, in said execution step, the document input in said input step is sorted and filed in accordance the result of interpretation.

27. An information processing method according to claim 25, wherein said determination step includes determining a filing destination in consonance with the result of interpretation.

28. An information processing method according to claim 20, wherein, when it is determined in said determination step that the process to be performed for the document is a transmission process, the document input in said input step is transmitted in said execution step.

29. An information processing method according to claim 28, wherein said determination step includes determining a transmission destination in consonance with the result of interpretation.

30. An information processing method according to claim 28, wherein said determination step includes determining a medium at a transmission destination in accordance with the result of interpretation, and, as needed, performs a medium conversion.

31. An information processing method according to claim 20, wherein, in said determination step, the process to be performed is determined based on a date included in the document and on a current date.

32. An information processing method according to claim 20, wherein the form of the document is identified in said first or second identification step in accordance with a command described in the document.

33. An information processing method according to claim 20, further comprising:

a history storage step, of storing a history of operations performed in said execution step.

34. An information processing method according to claim 33, wherein, when transmission of the document input in said input step is not recorded in the history of operations, it is determined in said determination step that the process to be performed is the transmission process.

35. An information processing method according to claim 20, further comprising:

an extraction step, of extracting predetermined attribute information from results obtained in said character recognition step; and

a registration step, of registering in a database the extracted predetermined attribute information.

36. An information processing method according to claim 20, further comprising a reception step, of receiving a response from a user.

37. An information processing method according to claim 20, further comprising a query step, of issuing a query to a user.

38. An information processing method according to claim 20, wherein, in said input step, media information from various types of media is input, and necessary information is extracted from the media information by performing processes corresponding to the media.

39. A computer-readable storage medium on which is stored an information processing program for controlling a computer to perform information processing, the program comprising codes for causing the computer to perform:

an input step, of inputting a document;

a first character recognition step, of recognizing a specific block of the document input in said input step;

a first identification step, of identifying a form of the document based on a recognition result of the specific block in the document recognized in the first character recognition step;

a second character recognition step, of recognizing a character in the document as a whole when the form of the document cannot be identified in the first identification step;

a second identification step, of identifying a form of the document based on a recognition result of the document as a whole recognized in the second character recognition step;

an interpretation step, of interpreting a word formed of characters recognized in the first or second character recognition step by referring to a knowledge base corresponding to the form of the document identified in the first or second identification step;

a determination step, of determining a process to be performed for the document based on a result of interpretation in the interpretation step; and

an execution step, of performing the process determined in said determination step for the document.