Search supporting apparatus, and method utilizing exclusion keywords
First Claim
1. A searching apparatus comprising:
- processor means;
storage means for storing search object data;
means for selecting a population from the stored object data;
means for providing information for determining an exclusion keyword to be specified for an efficient exclusion to exclude a piece of data associated with a specified exclusion keyword from pieces of searching object data stored in said storage means, wherein an exclusion efficiency indicates a level of exclusion efficiency of data for an individual keyword associated with said searching object data when said keyword is specified as said exclusion keyword;
said means for providing information for determining an exclusion keyword comprises means for determining an exclusion efficiency of excluding a piece of data associated with a specified keyword comprising means for calculating exclusion efficiency for an individual keyword associated with said searching object data, based on a first parameter indicating a level of exclusion efficiency of data in a set of part of said searching object data when said keyword is specified as said exclusion keyword and a second parameter indicating a level of exclusion efficiency of data in a set of all of said searching object data when said keyword is specified as said exclusion keyword;
wherein said exclusion efficiency increases as the value of said first parameter is smaller, and increases as the value of said second parameter is greater;
said first parameter indicating the intensity of correlation between a selection keyword and an exclusion keyword wherein the value of the first parameter is greater with stronger correlation between the selection keyword and the exclusion keyword, said first parameter being calculated using the following formula;
where X is a searching object population set, T(X, word0) is a set of document data in which keyword0 appears in the set X, and #(X) denotes the number of elements in the set X, and the second parameter is a value indicating the number of documents excluded by specifying the exclusion keyword, wherein the calculation expression for the second parameter is set up so that the value of the second parameter is greater when more documents are excluded, the selection keyword is “
word0” and
the exclusion keyword is “
word1”
, wherein the second parameter is calculated employing the following formula;
where T(X, word1) is a set of document data in which keyword1 appears in the set X, wherein the exclusion efficiency calculator calculates exclusion efficiency from the first and second parameters in accordance with the following formula, which satisfies the conditions where the exclusion efficiency increases as the first parameter is smaller, and increases as the second parameter is greater;
where 0<
a<
1, the first and second parameters taking a value from 0 to 1, whereby the exclusion efficiency has a value from 0 to 1;
wherein said providing means provides said information in a format of making a difference between the contribution levels of said first parameter and said second parameter to said exclusion efficiency clear; and
means for providing said exclusion efficiency to a user.
2 Assignments
0 Petitions
Accused Products
Abstract
Facilitating a user determination of an exclusion keyword in order to specify an efficient exclusion of an unwanted piece of data when the user narrows searching objects. Exclusion is accomplished in a system having a searching object data storage for storing pieces of searching object data, a searcher for performing a primary narrowing of the search, a common keyword extractor for extracting the common keywords associated with a piece of data, an input/output device for passing a selected keyword selected the extracted common keywords while receiving and displaying a result from an exclusion efficiency calculator. The exclusion efficiency calculator calculates exclusion efficiency and indicates a level of exclusion efficiency of data that is not associated with a selected keyword for an individual common keyword.
12 Citations
6 Claims
-
1. A searching apparatus comprising:
-
processor means; storage means for storing search object data; means for selecting a population from the stored object data; means for providing information for determining an exclusion keyword to be specified for an efficient exclusion to exclude a piece of data associated with a specified exclusion keyword from pieces of searching object data stored in said storage means, wherein an exclusion efficiency indicates a level of exclusion efficiency of data for an individual keyword associated with said searching object data when said keyword is specified as said exclusion keyword; said means for providing information for determining an exclusion keyword comprises means for determining an exclusion efficiency of excluding a piece of data associated with a specified keyword comprising means for calculating exclusion efficiency for an individual keyword associated with said searching object data, based on a first parameter indicating a level of exclusion efficiency of data in a set of part of said searching object data when said keyword is specified as said exclusion keyword and a second parameter indicating a level of exclusion efficiency of data in a set of all of said searching object data when said keyword is specified as said exclusion keyword;
wherein said exclusion efficiency increases as the value of said first parameter is smaller, and increases as the value of said second parameter is greater;said first parameter indicating the intensity of correlation between a selection keyword and an exclusion keyword wherein the value of the first parameter is greater with stronger correlation between the selection keyword and the exclusion keyword, said first parameter being calculated using the following formula; where X is a searching object population set, T(X, word0) is a set of document data in which keyword0 appears in the set X, and #(X) denotes the number of elements in the set X, and the second parameter is a value indicating the number of documents excluded by specifying the exclusion keyword, wherein the calculation expression for the second parameter is set up so that the value of the second parameter is greater when more documents are excluded, the selection keyword is “
word0” and
the exclusion keyword is “
word1”
,wherein the second parameter is calculated employing the following formula; where T(X, word1) is a set of document data in which keyword1 appears in the set X, wherein the exclusion efficiency calculator calculates exclusion efficiency from the first and second parameters in accordance with the following formula, which satisfies the conditions where the exclusion efficiency increases as the first parameter is smaller, and increases as the second parameter is greater; where 0<
a<
1, the first and second parameters taking a value from 0 to 1, whereby the exclusion efficiency has a value from 0 to 1;wherein said providing means provides said information in a format of making a difference between the contribution levels of said first parameter and said second parameter to said exclusion efficiency clear; and means for providing said exclusion efficiency to a user. - View Dependent Claims (2)
-
-
3. A searching method for use in a computer having a processor means and storage means, said method comprising the steps of:
-
extracting a plurality of common keywords associated with a piece of searching object data; storing said plurality of extracted common keywords into storage means; accepting a selected keyword selected by a user from said plurality of common keywords stored in said storage means; calculating exclusion efficiency indicating a level of exclusion efficiency of data that is not associated with said selected keyword for an individual common keyword of said plurality of common keywords stored in said storage means except for said selected keyword when said common keyword is specified as an exclusion keyword, based on a first parameter indicating a level of exclusion efficiency in a set of data that is associated with said selected keyword when said keyword is specified as the exclusion keyword and a second parameter indicating a level of exclusion efficiency in a set of all of said searching object data when said keyword is specified as the exclusion keyword by the steps of; (1) calculating said first parameter being calculated using the following formula; where X is a searching object population set, T(X, word0) is a set of document data in which keyword0 appears in the set X, and #(X) denotes the number of elements in the set X, and the second parameter is a value indicating the number of documents excluded by specifying the exclusion keyword, (2) calculating the second parameter using the following formula, where the selection keyword is “
word0” and
the exclusion keyword is “
word1”
, and the second parameter is calculated employing the following formula;where T(X, word1) is a set of document data in which keyword1 appears in the set X, (3) calculating the exclusion efficiency from the first and second parameters in accordance with the following formula, which satisfies the conditions where the exclusion efficiency increases as the first parameter is smaller, and increases as the second parameter is greater; where 0<
a<
1, the first and second parameters taking a value from 0 to 1, whereby the exclusion efficiency has a value from 0 to 1;a providing step, wherein said providing step provides said information in a format of making a difference between the contribution levels of said first parameter and said second parameter to said exclusion efficiency clear; and providing said exclusion efficiency to a user. - View Dependent Claims (4)
-
-
5. A computer program product comprising a computer readable storage recording medium having computer code thereon, said computer code causing a computer to execute the operations of:
-
extracting a plurality of common keywords associated with a piece of searching object data; storing said plurality of extracted common keywords into storage means; accepting a selected keyword selected by a user from said plurality of common keywords stored in said storage means; calculating exclusion efficiency indicating a level of exclusion efficiency of data that is not associated with said selected keyword for an individual common keyword of said plurality of common keywords stored in said storage means except for said selected keyword when said common keyword is specified as an exclusion keyword, based on a first parameter indicating a level of exclusion efficiency in a set of data that is associated with said selected keyword when said keyword is specified as the exclusion keyword and a second parameter indicating a level of exclusion efficiency in a set of all of said searching object data when said keyword is specified as the exclusion keyword by the steps of; (1) calculating said first parameter being calculated using the following formula; where X is a searching object population set, T(X, word0) is a set of document data in which keyword0 appears in the set X, and #(X) denotes the number of elements in the set X, and the second parameter is a value indicating the number of documents excluded by specifying the exclusion keyword, (2) calculating the second parameter using the following formula, where the selection keyword is “
word0” and
the exclusion keyword is “
word1”
, and the second parameter is calculated employing the following formula;where T(X, word1) is a set of document data in which keyword1 appears in the set X, (3) calculating the exclusion efficiency from the first and second parameters in accordance with the following formula, which satisfies the conditions where the exclusion efficiency increases as the first parameter is smaller, and increases as the second parameter is greater; where 0<
a<
1, the first and second parameters taking a value from 0 to 1, whereby the exclusion efficiency has a value from 0 to 1;a providing operation, wherein said providing operation comprises causing the computer to provide said information in a format of making a difference between the contribution levels of said first parameter and said second parameter to said exclusion efficiency clear; and providing said exclusion efficiency to a user. - View Dependent Claims (6)
-
Specification