Document processing device and document processing method

A document processing device comprising:

• a frequency memory that stores a frequency with which a word appears for each of a plurality of words;
• an input unit that optically reads in a document;
• a recognition unit that estimates character strings constituting the document read in by the input unit from the shapes of characters in that document, the recognition unit comprises:
• a shape recognition unit that estimates characters in the document read in by the input unit based on the shapes of those characters;
• and
• a word frequency unit that performs a grammatical analysis on character strings made of the estimation result of the shape recognition unit, based on the content stored in the frequency memory, to correct those character strings and take the corrected character strings as the estimation result;
• an updating unit that updates the frequencies stored in the frequency memory, based on an estimation result of the recognition unit;
• and
• a frequency recognition memory that stores an estimation result of the recognition unit.

A document processing method performed by a document processing device shared by predetermined users, comprising:

• receiving a first document and an instruction;
• performing a process on the received first document in accordance with the received instruction, the process including extracting feature vectors from shapes of characters in the first document;
• outputting the processed first document, while recognizing characters on the received first document based on the feature vectors extracted from the first document and a content stored in a general feature vector memory;
• obtaining information reflecting a character recognition accuracy;
• storing information reflecting extracted feature vectors and a character recognition accuracy in a specific feature vector memory;
• receiving a second document;
• recognizing characters on the received second document on the basis of the information stored in the specific feature vector memory.

A document processing device comprising:

• a general feature vector memory that stores feature vectors of a shape for each of a plurality of characters;
• an input unit that optically reads in a first document;
• an extracting unit that extracts feature vectors from the shapes of characters in the first document read in by the input unit;
• a general shape recognition unit that estimates a character for which the feature vectors of its shape extracted by the extracting unit, based on the feature vectors extracted by the extracting unit and the content stored in the general feature vector memory;
• and
• a specific feature vector memory that stores the feature vectors extracted by the extracting unit in association with an estimation result of the general shape recognition unit and in association with a character recognition accuracy, such that characters of a second document are recognizable based on the information stored in the specific feature vector memory.