Data management apparatus
First Claim
Patent Images
1. A data management apparatus comprising:
- scanning means for scanning a document image to provide digital document image data;
document image memory means for storing said document image data;
input means for entry of attribute data relevant to said document image data;
management data memory means for storing classification data and an attribute occurrence frequency table in which plural attribute data are assigned to each of the classification data, and in which frequency of occurrence data equal to the number of documents having a particular attribute j (j;
an integer equal to or greater than
1) in classification i (i;
an integer equal to or greater than
1) is appended to each of the attribute data;
a central processing unit for accessing said management data memory means using said attribute data entered through said input means as a parameter, for computing the frequency of occurrence of the attribute data entered by the input means, for calculating the sum of the frequency of occurrence data of each of said attribute data for each of the classification data, and for selecting classification data having attribute data with a predetermined large sum of frequency of occurrence data; and
display means for displaying said plural classification data selected by said central processing unit, whereby the operator can select a single of the classification data and thereby efficiently classify a document.
1 Assignment
0 Petitions
Accused Products
Abstract
A data management apparatus includes a scanner for reading a plurality of pieces of image information, an optical disk for storing a plurality of pieces of image information read by the scanner, a keyboard for entering attribute names featuring the respective pieces of image information stored in the optical disk, a magnetic disk for storing classification names having higher correlation with the attribute names, and a display. The attribute name entered at the keyboard is used as a parameter to access the magnetic disk to retrieve the classification name having the highest similarity. This classification name is displayed on the display.
330 Citations
6 Claims
-
1. A data management apparatus comprising:
-
scanning means for scanning a document image to provide digital document image data; document image memory means for storing said document image data; input means for entry of attribute data relevant to said document image data; management data memory means for storing classification data and an attribute occurrence frequency table in which plural attribute data are assigned to each of the classification data, and in which frequency of occurrence data equal to the number of documents having a particular attribute j (j;
an integer equal to or greater than
1) in classification i (i;
an integer equal to or greater than
1) is appended to each of the attribute data;a central processing unit for accessing said management data memory means using said attribute data entered through said input means as a parameter, for computing the frequency of occurrence of the attribute data entered by the input means, for calculating the sum of the frequency of occurrence data of each of said attribute data for each of the classification data, and for selecting classification data having attribute data with a predetermined large sum of frequency of occurrence data; and display means for displaying said plural classification data selected by said central processing unit, whereby the operator can select a single of the classification data and thereby efficiently classify a document. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A data management apparatus comprising:
-
scanning means for scanning a document image to provide digital document image data; document image memory means for storing said document image data; input means for entry of at least one of attribute data relevant to said document image data; classification system memory means for storing a predetermined list of classification data of said document image data and plural attribute data which relate to said classification data and are given predetermined weighting coefficients according to a degree of relevance between said classification data and said attribute data; a central processing unit for assigning a weighting coefficient to the attribute data entered via said input means such that when more than one of the attribute data is entered, the sum of the weighting coefficients of the entered attribute data becomes one and the first of the attribute data entered has the largest weighting coefficient, and for assessing said classification system memory means to compute the weighting coefficients of the attribute data entered via said input means and the weighting coefficients of the same attribute data as the entered attribute data, which is stored in said classification system memory means, based on an equation expressed by Xi=2(N-n)/(N(N+1)), where N is the number of attribute data, Xi is the weighting coefficient of the nth attribute data and 0≦
n≦
(N-1), and computing a similarity between the entered attribute data and the attribute data stored in said classification system memory means for each of the classification data based on an equation given by yj(1-|xi+yj|)/(1+|xi-yj|), where xi is the weighting coefficient of the ith attribute data entered and yj is the weighting coefficient of jth attribute data stored in said classification system memory means, and selecting the classification data, whose similarites are large, from all the classification data; anddisplay means for displaying said classification data selected by said central processing unit, whereby the operator can efficiently select a single of the classification data as the classification of the document being classified.
-
Specification