Information filtering method and apparatus for preferentially taking out information having a high necessity

• US 6,647,378 B2
• Filed: 02/09/2001
• Issued: 11/11/2003
• Est. Priority Date: 09/04/1995
• Status: Expired due to Term

• Current Assignee: Panasonic Intellectual Property Corporation of America (Panasonic Holdings Corporation)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Kindo, Toshiki
• Primary Examiner(s): Davis, George B.
• Application Number:
  US09/779,837
• Publication Number:
  US 20010047345A1
• Time in Patent Office: 1,005 Days
• Field of Search: 706/21, 706/20
• US Class Current: 706/21
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99937 Sorting

Abstract

A method and apparatus are provided of adapting a dictionary into which a keyword effective for judging whether or not information provided from either one of an information recording medium or an information communication network is recorded preferentially. The information includes information data and one or more keywords attached to the information data. The method is implemented by providing a user with the information data, enabling the user to input a signal indicating that the provided information data is necessary or unnecessary; calculating a prediction value for predicting a user'"'"'s necessity degree of each keyword attached to the provided information data on the basis of the signal inputted in the inputting step, and registering preferentially the keyword effective for the dictionary by using the prediction value.

Claims

1. An adaptive dictionary apparatus with which a keyword effective for judging whether or not information provided from either one of an information recording medium or an information communication network is recorded preferentially into a dictionary, the information including information data and one or more keywords attached to the information data, the apparatus comprising:

information providing means for providing a user with the information data;

inputting means for enabling the user to input a signal indicating that the provided information data is necessary or unnecessary;

learning means for calculating a prediction value for predicting a user'"'"'s necessity degree of each keyword attached to the provided information data on the basis of the signal inputted by the inputting means; and

dictionary updating means for preferentially registering the keyword effective for the dictionary by using the prediction value.

2. An adaptive dictionary apparatus according to claim 1, wherein the dictionary updating means updates a content of the dictionary on the basis of a keyword cost signal calculated on the basis of a first frequency of the information judged to be necessary, a second frequency of the information judged to be unnecessary, a third frequency at which the information including a keyword signal of each keyword is necessary, and a fourth frequency at which the information including the keyword signal of each keyword is unnecessary.

3. An adaptive dictionary apparatus according to claim 2, wherein the keyword cost signal for each keyword signal is set to a signal to quantitatively estimate a difference between a first probability distribution indicating that the information is necessary or unnecessary and a second probability distribution indicating that the information including the keyword signal is necessary or unnecessary.

4. An adaptive dictionary apparatus according to claim 3, wherein the keyword cost signal for each keyword signal is increased in value as a difference between the first and second probability distributions becomes larger, and the keyword signal for which the keyword cost signal is large is retained, while the keyword signal for which the keyword cost signal is small is discarded.

5. An adaptive dictionary apparatus according to claim 1, wherein the dictionary updating means comprises:

means for memorizing both the total number of affirmative responses indicating that the signal inputted by the inputting means shows that the provided information data is necessary and the total number of negative responses indicating that the signal inputted by the inputting means shows that the provided information data is unnecessary;

a table used for converting a character stream showing each keyword signal into a numeral;

an adaptive dictionary memory for memorizing both the number of affirmative times showing that the information including the character stream as the keyword signal is necessary and the number of negative times showing that the information including the character stream as the keyword signal is unnecessary; and

a dictionary learning unit for updating the total number of affirmative responses, the total number of negative responses, and a signal showing the times memorized by the adaptive dictionary memory on the basis of the signal inputted by the inputting means, the keyword signal included in the information, the total number of affirmative responses, the total number of negative responses, and the signal showing the times memorized by the adaptive dictionary memory.

6. An adaptive dictionary apparatus according to claim 1, wherein a signal of the keyword includes a classification symbol.

7. A method of adapting a dictionary into which a keyword effective for judging whether or not information provided from either one of an information recording medium or an information communication network is recorded preferentially, the information including information data and one or more keywords attached to the information data, the method comprising the steps of:

providing a user with the information data;

enabling the user to input a signal indicating that the provided information data is necessary or unnecessary;

calculating a prediction value for predicting a user'"'"'s necessity degree of each keyword attached to the provided information data on the basis of the signal inputted in the inputting step; and

registering preferentially the keyword effective for the dictionary by using the prediction value.

8. A method of adapting a dictionary according to claim 7, comprising the further step of updating a content of the dictionary on the basis of a keyword cost signal calculated on the basis of a first frequency of information judged to be necessary, a second frequency of information judged to be unnecessary, a third frequency at which the information including a keyword signal of each keyword is necessary, and a fourth frequency at which the information including the keyword signal of each keyword is unnecessary.

9. A method of adapting a dictionary according to claim 8, comprising the step of setting the keyword cost signal for each keyword signal to a signal to quantitatively estimate a difference between a first probability distribution indicating that the information is necessary or unnecessary and a second probability distribution indicating that the information including the keyword signal is necessary or unnecessary.

10. A method of adapting a dictionary according to claim 9, comprising the step of increasing a value of the keyword cost signal for each keyword signal as a difference between the first and second probability distributions becomes larger, retaining the keyword signal for which the keyword cost signal is large, and discarding the keyword signal for which the keyword cost signal is small.