Data processing: artificial intelligence – Knowledge processing system
Reexamination Certificate
2000-02-18
2001-12-04
Chaki, Kakali (Department: 2122)
Data processing: artificial intelligence
Knowledge processing system
C706S016000, C706S021000
Reexamination Certificate
active
06327583
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to an information filtering apparatus and an information filtering method for easily taking out necessary information from an information communication network or a storing apparatus in which pieces of information are transmitted by using electrons or light as a transmission medium.
2. Description of the Related Art
An information filtering apparatus has been recently desired as a technique corresponding to an information communication network developed on a large scale and the considerable increase of an amount of communication while an information communication has been developed. That is, because a volume of information capable to be accessed by an individual is larger than that capable to be processed by the individual, the individual cannot find out necessary information from a large volume of information capable to be accessed by the individual. Therefore, an information filtering apparatus and an information filtering method for easily taking out necessary information from a large volume of information is required.
In a conventional information filtering apparatus, for example, a keyword logical equation used for a patent retrieval is well-known. That is, a large number of patent information of which the number ranges from hundreds of thousands to millions are filtered according to the keyword logical equation.
3. Problems to be Solved by the Invention
However, in the conventional information filtering apparatus using a keyword logical equation, because a user is required to strictly set a keyword logical equation, the user is required to sufficiently and skillfully know types of a large volume of filed information (for example, a method for determining keywords for the information on some condition) or a system configuration for a large volume of information (for example, a system for keywords). Therefore, there is a first drawback that a beginner cannot perform an information filtering with a high precision.
Also, when the user performs an information filtering, the user can only estimate that a piece of information obtained in the information filtering is fit for a keyword logical equation. Therefore, even though the information is fit for a keyword logical equation, there is a case that the information is not a piece of required information. That is, there is a second drawback that the user cannot easily take out information having a high necessity for the user from a large volume of information in the information filtering.
SUMMARY OF THE INVENTION
An object of the present invention is to provide, with due consideration to the drawbacks of such a conventional information filtering apparatus, an information filtering method and an information filtering apparatus in which an information filtering is performed with a high precision by an beginner and information having a high necessity for a user is easily retrieved from a large volume of information.
The object is achieved by the provision of an information filtering apparatus, comprising:
information indicating means for indicating pieces of learning information;
learning information control means for receiving a plurality of teaching signals respectively indicating whether one piece of learning information indicated by the information indicating means is necessary or unnecessary and generating pieces of teaching data respectively composed of one piece of learning information and one teaching signal corresponding to the piece of learning information;
learning means for performing a learning operation for each of the pieces of teaching data generated by the learning information control means to produce records indicating whether each piece of learning information indicated by the information indicating means is judged to be necessary or unnecessary; and
information filtering means for filtering pieces of information data according to the records produced by the learning means to arrange the pieces of information data in order of necessity.
In the above configuration, a user judges whether each piece of learning information indicated by the information indicating means is necessary or unnecessary. That is, in cases where one piece of learning information is necessary for the user, a teaching signal indicating that the piece of learning information is necessary is received by the learning information control means. In contrast, in cases where one piece of learning information is unnecessary for the user, a teaching signal indicating that the piece of learning information is unnecessary is received by the learning information control means. Thereafter, a teaching data composed of one piece of learning information and one teaching signal is produced for each of the learning information. Thereafter, a learning operation is performed for each of the teaching data in the learning unit, and records indicating whether each piece of learning information indicated by the information indicating means is a piece of necessary information or a piece of unnecessary information are produced. Thereafter, pieces of information data are filtered according to the records in the information filtering means to arrange the information data in order of necessity.
Accordingly, because the pieces of information data can be indicated to the user in order of necessity, information having a high necessity for a user can be easily retrieved from a large volume of information.
Also, the object is achieved by the provision of an information filtering method, comprising the steps of:
indicating pieces of learning information on an indicating unit;
receiving a plurality of teaching signals respectively indicating whether one piece of learning information indicated on the indicating unit is necessary or unnecessary;
generating pieces of teaching data respectively composed of one piece of learning information and one teaching signal corresponding to the piece of learning information;
performing a learning operation for each of the pieces of teaching data to produce records indicating whether each piece of learning information indicated by the information indicating means is judged to be necessary or unnecessary; and
filtering pieces of information data according to the records to arrange the pieces of information data in order of necessity.
In the above steps, information having a high necessity for a user can be easily retrieved from a large volume of information, in the same manner as in the information filtering apparatus.
REFERENCES:
patent: 5048100 (1991-09-01), Kuperstein
patent: 5226092 (1993-07-01), Chen
patent: 5446891 (1995-08-01), Kaplan et al.
patent: 5535382 (1996-07-01), Ogawa
patent: 5619709 (1997-04-01), Caid et al.
patent: 5692176 (1997-11-01), Holt et al.
patent: 5724567 (1998-03-01), Rose et al.
patent: 5802504 (1998-08-01), Suda et al.
patent: 5832465 (1998-11-01), Tom
patent: 5855015 (1998-12-01), Shoham
patent: 5907841 (1999-05-01), Sumita et al.
patent: 6064971 (2000-05-01), Hartnett
patent: 6067535 (2000-05-01), Hobson et al.
patent: 6076082 (2000-06-01), Kindo
patent: 6202058 (2001-03-01), Rose et al.
patent: 6-243173 (1994-09-01), None
H. Chen, “A machine learning approach to document retrieval: an overview and an experiment,” Proceedings of the 27th Annual Hawaii International Conference on System Sciences, vol. 3, pp. 631-640, 1994.*
Schapire et al, “Boosting and rocchio applied to text filtering”, SIGIR ACM pp. 215-223, Aug. 1998.*
Syed et al, “A study of support vectors on model independent example selection”, KDD ACM pp. 272-276, Jul. 1999.*
Merhav et al, “Universal sequential learning and decision from individual data sequence”, COLT ACM pp. 413-427, Aug. 1992.*
Blum et al, “On line learning and metrical task system problem”, COLT ACM pp. 45-53, Jun. 1997.*
M. Ojala, “Filtered Information and Intelligent Agent Software,” Business Information Alert, vol. 8, No. 6, Jun. 1995.*
T. Nomura et al., “A method for retrieval of a target still image by selecting similar and dissimilar images”, In Proceedings of the 45th National Conference, Infor
Chaki Kakali
Gopstein Israel
Khatri Anil
Matshita Electric Industrial Co., Ltd.
LandOfFree
Information filtering method and apparatus for... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Information filtering method and apparatus for..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Information filtering method and apparatus for... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2562209