Information abstracting method, information abstracting apparatus, and weighting method

• US 6,064,952 A
• Filed: 11/17/1995
• Issued: 05/16/2000
• Est. Priority Date: 11/18/1994
• Status: Expired due to Fees

• Current Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Matsuura, Satoshi, Kataoka, Mitsuteru, Imanaka, Takeshi
• Primary Examiner(s): Thomas, Joseph
• Application Number:
  US08/560,394
• Time in Patent Office: 1,642 Days
• Field of Search: 704/1, 704/9, 704/8, 704/10, 707/530, 707/531, 707/500, 707/532, 707/1, 707/3, 707/4, 707/5, 707/6, 707/7, 348/468
• US Class Current: 704/9
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/53 Processing of non-Latin text kana-to-kanji conversion G06F40/129; vowelisation G06F40/232

Abstract

An information abstracting method and apparatus for extracting and displaying keywords as an information abstract. Given a large number of character string data sets divided into prescribed units, the extracted keywords are significant and effective in describing a topic common to the plurality of units. The information abstracting apparatus comprises an input section for accepting an input of character string data divided into prescribed units, with each individual character represented by a character code, and an output section for displaying the result of information abstracting. Keywords contained in each of the prescribed units are extracted by a keyword extracting section from the character string input data from the input section. A score is calculated for each keyword by a score calculating section, so that a higher score is given to a keyword extracted from a larger number of units. On the basis of the calculated scores, keywords are selected by an abstracting section and are outputted as an information abstract by the output section.

Claims

1. An information abstracting method comprising the steps of:

accepting an input of character string data divided into prescribed units, with each individual character represented by a character code;

extracting a keyword for each of said prescribed units from said input character string data;

weighting said extracted keyword by taking into account a state of occurrence, in the other prescribed units, of keywords that are identical to said extracted keyword;

selecting at least one keyword from said extracted keywords on the basis of the weighted result; and

outputting said selected keyword as an information abstract relating to said character string data.

2. An information abstracting method according to claim 1, wherein said extracted keyword is weighted by using at least one of the number of prescribed units from which the keyword to be weighted was extracted, the frequency of occurrence of said keyword in each prescribed unit, and the number of characters of said keyword.

18. An information abstracting method according to claim 1, 5, 2, or 6, wherein

said input character string data is stored in a prescribed work area, and

after outputting said information abstract, when a keyword is designated from among the keywords constituting said information abstract, all or part of said character string data containing said designated keyword is output by using said designated keyword.

19. An information abstracting method according to claim 1, 2, or 6, wherein

an input of an arbitrary keyword is accepted, and

after outputting said information abstract, when data contents of a paragraph in said unit are updated and said input keyword is found in said updated data, then

the whole or part of said data containing said keyword is output or stored, or

information indicating the existence of said data containing said keyword is output or stored.

20. An information abstracting method according to claim 1, 5, 2, or 6, wherein

after outputting said information abstract, a keyword is designated from among the keywords constituting said output information abstract, and

when data contents of a paragraph in said unit are thereafter updated and said designated keyword is found in said updated data, then

the whole or part of said data containing said keyword is output or stored, or

information indicating the existence of said data containing said keyword is output or stored.

3. An information abstracting apparatus comprising:

input means for accepting an input of character string data divided into prescribed units, with each individual character represented by a character code;

keyword extracting means for extracting a keyword for each of said prescribed units from the character string data input from said input means;

weighting means for weighting said extracted keyword by taking into account a state of occurrence, in the other prescribed units, of keywords that are identical to said extracted keyword;

keyword selecting means for selecting at least one keyword from said extracted keywords on the basis of the weighted result; and

output means for outputting said selected keyword as an information abstract relating to said character string data.

4. An information abstracting apparatus according to claim 3, wherein said extracted keyword is weighted by using at least one of the number of prescribed units from which the keyword to be weighted was extracted, the frequency of occurrence of said keyword in each prescribed unit, and the number of characters of said keyword.

5. An information abstracting method comprising the steps of:

accepting an input of character string data divided into prescribed units each subdivided into prescribed paragraphs, with each individual character represented by a character code;

extracting a keyword for each paragraph in each of said prescribed units from said input character string data;

generating a keyword association by associating one keyword with another among keywords obtained from the same paragraph;

weighting said extracted keyword by taking into account a state of occurrence, in the other prescribed units, of keywords that are identical to said extracted keyword, and also weighting said generated keyword association by taking into account a state of occurrence, in the other prescribed paragraphs, of keyword associations that are identical to said generated keyword association;

selecting keywords and keyword associations from said extracted keywords and said generated keyword associations on the basis of the weighted results; and

outputting said selected keywords and keyword associations as an information abstract relating to said character string data.

6. An information abstracting method according to claim 5, wherein

said extracted keyword is weighted by using at least one of the number of prescribed units from which the keyword to be weighted was extracted, the frequency of occurrence of said keyword in each prescribed unit, and the number of characters of said keyword, and

said generated keyword is weighted by using at least one of the number of prescribed paragraphs from which the keyword association to be weighted was obtained, the frequency of occurrence of keywords constituting said keyword association in each prescribed paragraph, and the number of characters of the keywords constituting said keyword association.

7. An information abstracting method according to claim 5, wherein a plurality of mutually associated keywords are arranged essentially in one cluster and the thus clustered keywords are output as said information abstract.

8. An information abstracting method according to claim 5, wherein a plurality of mutually associated keywords are output as said information abstract for display on said display means in such a manner that, of said plurality of keywords, the first keyword is displayed in a reference position and the subsequent keywords are each displayed on a new line by being displaced by a prescribed number of characters to the right with respect to said reference position, thus displaying said plurality of mutually associated keywords as a cluster when viewed.

9. An information abstracting apparatus comprising:

input means for accepting an input of character string data divided into prescribed units each subdivided into prescribed paragraphs, with each individual character represented by a character code;

keyword extracting means for extracting a keyword for each paragraph in each of said prescribed units from the character string data input from said input means;

keyword associating means for generating a keyword association by associating one keyword with another among keywords obtained from the same paragraph;

weighting means for weighting said extracted keyword by taking into account a state of occurrence, in the other prescribed units, of keywords that are identical to said extracted keyword, and for weighting said generated keyword association by taking into account a state of occurrence, in the other prescribed paragraphs, of keyword associations that are identical to said generated keyword association;

selecting means for selecting keywords and keyword associations from said extracted keywords and said generated keyword associations on the basis of the weighted results; and

output means for outputting said selected keywords and keyword associations as an information abstract relating to said character string data.

10. An information abstracting apparatus according to claim 9, wherein said weighting means weights

said extracted keyword by using at least one of the number of prescribed units from which the keyword to be weighted was extracted, the frequency of occurrence of said keyword in each prescribed unit, and the number of characters of said keyword, and

said generated keyword by using at least one of the number of prescribed paragraphs from which the keyword association to be weighted was obtained, the frequency of occurrence of keywords constituting said keyword association in each prescribed paragraph, and the number of characters of the keywords constituting said keyword association.

21. An information abstracting apparatus according to claim 3, 9, 11, 13, 4, 10, 16, or 17, further including

keyword designating means for designating a keyword, and

a work area for storing said character string data input from said input means, wherein

after said information abstract is output to said output means, when a keyword is designated by said keyword designating means from among the keywords constituting said output information abstract, all or part of said character string data containing said designated keyword is output by said output means by using said designated keyword.

22. An information abstracting apparatus according to claim 3, 9, 11, 13, 4, 10, 16, or 17, further including

keyword input means for inputting an arbitrary keyword, and

data storing means for storing data, wherein

after said information abstract is output by said output means, when data contents of a paragraph in said unit are updated and said input keyword is found in said updated data, then

the whole or part of said data containing said keyword is output by said output means or stored in said data storing means, or

information indicating the existence of said data containing said keyword is output by said output means or stored in said data storing means.

11. An information abstracting apparatus comprising:

input means for accepting an input of character string data divided into prescribed units, with each individual character represented by a character code;

keyword extracting means for extracting a keyword for each of said prescribed units from said input character string data;

similarity calculating means for calculating similarity between keywords thus extracted;

weighting means for weighting said extracted keyword by taking into account a state of occurrence, in the other prescribed units, of keywords that are identical or similar to said extracted keyword;

keyword selecting means for selecting keywords from said extracted keywords on the basis of the weighted result; and

output means for outputting said selected keywords as an information abstract relating to said character string data.

12. An information abstracting apparatus according to claim 11, wherein said keyword is weighted by using at least one of the number of units from which keywords whose similarity with the keyword to be weighted is greater than a predetermined reference were extracted, the frequency of occurrence in each prescribed unit of keywords whose similarity with said keyword is greater than said predetermined reference, and the number of characters of said keyword.

23. An information abstracting apparatus according to claim 3, 9, 11, 13, 4, 20, 16, or 17, further including

keyword designating means for designating a keyword, and

data storing means for storing data, wherein

after said information abstract is output by said output means, when a keyword is designated by said keyword designating means from among the keywords constituting said output information abstract and when data contents of a paragraph in said unit are thereafter updated and said designated keyword is found in said updated data, then

the whole or part of said data containing said keyword is output by said output means or stored in said data storing means, or

information indicating the existence of said data containing said keyword is output by said output means or stored in said data storing means.

13. An information abstracting apparatus comprising:

input means for accepting an input of character string data divided into prescribed units each subdivided into prescribed paragraphs, with each individual character represented by a character code;

keyword extracting means for extracting a keyword for each paragraph in each of said prescribed units from said character string data input from said input means;

keyword associating means for generating a keyword association by associating one keyword with another among keywords obtained from the same paragraph;

similarity calculating means for calculating similarity between keywords thus extracted, on the basis of a plurality of factors including said keyword association;

weighting means for weighting said extracted keyword by taking into account a state of occurrence, in the other prescribed units, of keywords that are identical or similar to said extracted keyword, and for weighting said generated keyword association by taking into account a state of occurrence, in the other prescribed paragraphs, of keyword associations that are identical to said generated keyword association;

selecting means for selecting keywords and keyword associations from said extracted keywords and said generated keyword associations on the basis of the weighted results; and

outputting said selected keywords and keyword associations as an information abstract relating to said character string data.

14. An information abstracting apparatus according to claim 13, wherein the larger the number of paragraphs containing said keyword association constituted by the keywords having said larger similarity between the keywords is, the larger the weight which is to be assinged to the keyword association becomes.

15. An information abstracting apparatus according to claim 13, wherein said keyword is weighted by using at least one of the number of units from which keywords whose similarity with the keyword to be weighted is greater than a predetermined reference were extracted, the frequency of occurrence in each prescribed unit of keywords whose similarity with said keyword is greater than said predetermined reference, and the number of characters of said keyword.

24. An information abstracting apparatus according to claim 9, 13, 16, or 17, wherein a plurality of mutually associated keywords are arranged essentially in one cluster and the thus clustered keywords are output as said information abstract by said output means.

25. An information abstracting apparatus according to claim 9, 13, 16, or 17, wherein

said output means includes a display section for displaying a plurality of mutually associated keywords as said information abstract, and

a display control section for displaying said plurality of mutually associated keywords as a cluster when viewed, in such a manner that, of said plurality of keywords, the first keyword is displayed in a reference position and the subsequent keywords are each displayed on a new line by being displaced by a prescribed number of characters to the right with respect to said reference position.

16. An information abstracting apparatus comprising:

input means for accepting an input of character string data divided into prescribed units each subdivided into prescribed paragraphs, with each individual character represented by a character code;

keyword extracting means for extracting a keyword for each paragraph in each of said prescribed units from the character string data input from said input means;

keyword associating means for generating a keyword association by associating one keyword with another among keywords obtained from the same paragraph;

weighting means for weighting said generated keyword association by taking into account a state of occurrence, in the other prescribed paragraphs, of keyword associations that are identical to said generated keyword association;

selecting means for selecting keyword associations from said generated keyword associations on the basis of the weighted result; and

output means for outputting an information abstract, generated based on the selection results, relating to said character string data.

17. An information abstracting apparatus comprising:

input means for accepting an input of character string data divided into prescribed units each subdivided into prescribed paragraphs, with each individual character represented by a character code;

keyword extracting means for extracting a keyword for each paragraph in each of said prescribed units from said character string data input from said input means;

keyword associating means for generating a keyword association by associating one keyword with another among keywords obtained from the same paragraph;

similarity calculating means for calculating similarity between keywords thus extracted;

keyword association/similarity calculating means for, by using said similarity calculated between keywords constituting said generated keyword association and keywords constituting another keyword association, calculating similarity between the keyword associations;

weighting means for weighting said generated keyword association by taking into account a state of occurrence, in the other prescribed paragraphs, of keyword associations that are identical or similar to said generated keyword association;

selecting means for selecting keyword associations from said generated keyword associations on the basis of the weighted result; and

outputting said selected keyword associations as an information abstract relating to said character string data.