Non-transitory computer-readable recording medium, retrieval support device, and retrieval support method

Patent metadata

Field	Value
Publication number	US-10353902-B2
Application number	US-201615170146-A
Country	US
Kind code	B2
Filing date	Jun 1, 2016
Priority date	Jun 4, 2015
Publication date	Jul 16, 2019
Grant date	Jul 16, 2019

Abstract

A retrieval support method including acquiring, for each of a plurality of categories relating to computer systems, frequency information including a frequency of occurrence of each of a plurality of terms included in pieces of text information on the computer systems, specifying, a plurality of first terms and a plurality of second terms, the plurality of first terms being terms which is not used in common to the plurality of categories, the plurality of second terms being a terms which is used in common, generating correspondence information, for each of the plurality of first terms, that associates selected first term with at least one of the plurality of second terms which is included in a piece of text information including the selected first term, and generating specified information to identify each combination of first terms, belonging to different category among the plurality of categories, that have correlativity.

First claim

What is claimed is:

1. A non-transitory computer-readable recording medium storing a retrieval support program that causes a computer to execute a process comprising:
acquiring, for each of a plurality of categories relating to computer systems, frequency information including a frequency of occurrence of each of a plurality of terms included in pieces of text information on the computer systems, each of the pieces of text information belonging to one of the plurality of categories;
specifying, among each of the plurality of terms, a plurality of first terms and a plurality of second terms included in at least one of the pieces of text information based on the frequency information, the plurality of first terms being terms which are not used in common to the plurality of categories, the plurality of second terms being a terms which are used in common to the plurality of categories;
generating correspondence information for each of the plurality of first terms, the correspondence information associating, for each selected first term of the plurality of first terms, the selected first term with at least one of the plurality of second terms which is included in a piece of text information including the selected first term; and
generating specified information to identify each combination of first terms, belonging to a different category among the plurality of categories, that have correlativity in at least one of the associated plurality of second terms based on the generated correspondence information,
wherein the frequency information is information indicating a percentage of pieces of text information including the respective terms among pieces of text information corresponding to the respective categories, wherein each of the plurality of first terms is a term in which a difference between a maximum value and a minimum value of the pieces of frequency information is equal to or greater than a first threshold value, among the terms included in the pieces of text information stored in a storage, and wherein each of the plurality of second terms is a term in which a difference between a maximum value and a minimum value of the pieces of frequency, information is less than the first threshold value.

2. The non-transitory computer-readable recording medium according to claim 1 ,
wherein each of the plurality of second terms is a term whose frequency of occurrence is equal to or greater than a second threshold value.

3. The non-transitory computer-readable recording medium according to claim 1 ,
wherein the correlativity in at least one of the associated plurality of second terms is detected when a percentage of the second terms which are associated in common with the first terms is equal to or greater than a third threshold value.

4. The non-transitory computer-readable recording medium according to claim 1 ,
wherein in a case where the text information is retrieved, a first term included in association with a first term included in the retrieved text information is further extracted from the specified information, and the extracted first term is output.

5. The non-transitory computer-readable recording medium according to claim 4 ,
wherein the outputting of the first term includes re-retrieving text information including at least one of the plurality of second terms included in the retrieved text information among the pieces of text information stored in the storage and the extracted first term, and the re-retrieved text information is output.

6. A retrieval support device comprising:
a memory; and
a processor configured to:
acquire, for each of a plurality of categories relating to computer systems, frequency information including a frequency of occurrence of each of a plurality of terms included in pieces of text information on the computer systems, each of the pieces of text information belonging to one of the plurality of categories;
specify, among each of the plurality of terms, a plurality of first terms and a plurality of second terms included in at least one of the pieces of text information based on the frequency information, the plurality of first terms being terms which are not used in common to the plurality of categories, the plurality of second terms being terms which are used in common to the plurality of categories;
generate correspondence information for each of the plurality of first terms, the correspondence information associating, for each selected first term of the plurality of first terms, the selected first term with at least one of the plurality of second terms which is included in a piece of text information including the selected first term; and
generate specified information to identify each combination of first terms, belonging to a different category among the plurality of categories, that have correlativity in at least one of the associated plurality of second terms based on the generated correspondence information,

wherein the frequency information is information indicating a percentage of pieces of text information including the respective terms among pieces of text information corresponding to the respective categories, wherein each of the plurality of first terms is a term in which a difference between a maximum value and a minimum value of the pieces of frequency information is equal to or greater than a first threshold value, among the terms included in the pieces of text information stored in a storage, and wherein each of the plurality of second terms is a term in which a difference between a maximum value and a minimum value of the pieces of frequency information is less than the first threshold value.

7. A retrieval support method comprising:
acquiring, for each of a plurality of categories relating to computer systems, frequency information including a frequency of occurrence of each of a plurality of terms included in pieces of text information on the computer systems, each of the pieces of text information belonging to one of the plurality of categories;
specifying, among each of the plurality of terms, a plurality of first terms and a plurality of second terms included in at least one of the pieces of text information based on the frequency information, the plurality of first terms being terms which are not used in common to the plurality of categories, the plurality of second terms being terms which are used in common to the plurality of categories;
generating correspondence information for each of the plurality of first terms, the correspondence information associating, for each selected first term of the plurality of first terms, the selected first term with at least one of the plurality of second terms which is included in a piece of text information including the selected first term; and
generating specified information to identify each combination of first terms, belonging to a different category among the plurality of categories, that have correlativity in at least one of the associated plurality of second terms based on the generated correspondence information,
wherein the frequency information is information indicating a percentage of pieces of text information including the respective terms among pieces of text information corresponding to the respective categories, wherein each of the plurality of first terms is a term in which a difference between a maximum value and a minimum value of the pieces of frequency information is equal to or greater than a first threshold value, among the terms included in the pieces of text information stored in a storage, and wherein each of the plurality of second terms is a term in which a difference between a maximum value and a minimum value of the pieces of frequency information is less than the first threshold value.

8. The retrieval support device accord

Assignees

• Fujitsu Ltd

Inventors

• Obinata Shunichi
• Sengoku Tamotsu

Classifications

• G06F16/24575 Primary

  using context · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G06F16/383

  using metadata automatically derived from the content · CPC title