JPH10260975A - Information processor and method for processing information - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically similarity between key words as a user intends. SOLUTION: An image data registering process part 5 adds a key word to image data inputted from an input part 1 and registers them in an image data storage part 6. A similarity varying process part 10 increases the similarity between key words added to the same data by the image data registering process part 5 as to similarity data which are previously set by a key word registering process part 2 and stored in a key word similarity storage part 4. Thus, the similarity between key words is varied according to how many times the key words are added together to the same image data to automatically set the similarity between the key words as the user intends.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an information processing apparatus capable of retrieving an object stored in the form of a database.

[0002]

2. Description of the Related Art With the rapid spread of computers, electronic information handled by people is rapidly increasing. Such a large amount of electronic information is generally stored together with search information such as a keyword, and it is possible to search for desired electronic information by designating the search information.

[0003] As such an information processing apparatus, there is a "document retrieval apparatus (Japanese Patent Laid-Open No. 8-77203)". This document search device has a related word dictionary and an index. This index associates a related word with a document file name in which the related word exists. And
Related word candidates for the input search word are determined using the related word dictionary, and among the obtained related word candidates, those that do not exist in the index are deleted and displayed as a list. Then, a search process is performed using the search word and the related word set by the user.

[0004]

However, in the above-described conventional document retrieval apparatus, the relevance is not set between the related words registered in the related word dictionary. Therefore,
The related words of the entered search term will be determined based only on whether or not they are listed in the related word dictionary and index, and among the obtained related word candidates, related words that are not necessary for the current search will be included. There are many things that exist. When such a situation frequently occurs, it is necessary for the user to manually delete related words having low relevance from the related word dictionary. Such an operation is not a problem when the number of related words is small, but places a great burden on the user when the number of registered documents and the number of related words are large.

[0005] In the above-described problem, a degree of relevance is given between related words according to some degree of relevance, and a search ambiguity is specified at the time of search, and the relevance is higher than the specified ambiguity. To some extent this is accomplished by performing a search based on related words. However, the defined degree of relevance is uniquely set, and a low degree of relevance may be given to a related word that is considered to be highly relevant to the user. In that case, the ambiguity at the time of retrieval must be set to an unnecessarily low value in order to use the related word at the time of retrieval, and as a result, retrieval noise is generated. Therefore, as in the above-described case, it is necessary for the user to manually change the degree of relevance between related words, and when the number of registered documents is large or the number of related words is large, a large burden is imposed on the user. . Also, when assigning a degree of relevance between the newly registered related word and the already registered related word, one related word is selected from among many registered related words and another related word is selected. Setting the optimal degree of relevance in view of the relevance to the related word becomes a very difficult task as the number of related words increases.

An object of the present invention is to provide an information processing apparatus that can automatically set the similarity between search information to a value that meets the user's intention.

[0007]

According to a first aspect of the present invention, there is provided an information processing apparatus comprising: an input unit;
An object storage unit in which an object and search information for searching for the object are stored in association with each other, and a search information storage in which the search information is stored in association with the degree of similarity to other search information Unit, an object registration processing unit that adds search information to the object input from the input unit and registers the object in the object storage unit,
A search processing unit for searching for a candidate object from the object storage unit based on the setting search information set from the input unit; an output unit for outputting the candidate object searched for by the search processing unit; A similarity change processing unit that changes the similarity between the added search information stored in the search information storage unit to increase the similarity when a plurality of pieces of search information are added to the same object by the unit. It is characterized by having.

According to the above configuration, the object to be registered is registered in the object storage unit with the search information added by the object registration processing unit. Then, when a plurality of pieces of search information are added to the registration target object, the similarity change processing unit increases the similarity between the additional search information stored in the search information storage unit to increase the similarity. Be changed. In this way, by increasing the similarity between the search information added to the same object, the search information storage unit in which the similarity between the search information recognized by the user and the similarity is registered is automatically constructed. Will be done.

Therefore, when the user first registers the search information and the similarity in the search information storage unit, the user considers the relevance with many already registered search information and determines the optimum similarity. It is not necessary to set strictly, and it is released from the difficulty of search information registration processing. Further, even if the user initially sets a similarity that does not match in the search information storage unit, the user searches for the target similarity from the similarity between the complicatedly related search information and manually retrieves the similarity. This eliminates the need for correction and eliminates the hassle of correcting the similarity.

According to a second aspect of the present invention, there is provided an information processing method comprising the steps of: inputting an object, adding search information to the input object, and matching the similarity between the search information and other search information. In addition, a registration step of registering the object, the search information, and the similarity in a storage unit, and, when a plurality of search information is added to the same object, a similarity between the plurality of added search information. A changing step for changing the similarity to be higher, a specifying step for specifying the search information and the similarity, and adding the specified search information from the storage unit based on the specified search information and the similarity. A search step of searching for the searched object; and an output step of outputting the searched object.

According to the above configuration, when a plurality of pieces of search information are added to an object to be registered, the similarity between the plurality of pieces of added search information is changed so as to increase the similarity. In this way, a database in which a similarity matching the similarity between the pieces of search information recognized by the user is registered is automatically constructed.

According to a third aspect of the present invention, in the program storage medium, an input step of inputting an object, adding search information to the input object, and associating similarity between the search information and other search information. In addition, a registration step of registering the object, the search information, and the similarity in a storage unit, and, when a plurality of search information is added to the same object, a similarity between the plurality of added search information. A changing step of changing the similarity to be higher, a specifying step of specifying search information and similarity, and adding the specified search information from the storage unit based on the specified search information and similarity. Storing an information processing program by a search step of searching for the searched object and an output step of outputting the searched object. It is.

According to the above arrangement, when a plurality of pieces of search information are added to an object to be registered by executing a program stored in the program storage medium, the plurality of pieces of added search information are added. Is changed to increase the similarity. In this way, a database in which a similarity matching the similarity between the pieces of search information recognized by the user is registered is automatically constructed.

Here, the above-mentioned "object" is
Electronic information to be stored by the information processing device (e.g., text data or image data), or
It means a folder or the like in which these are put together. The “search information” is information used when searching for the object added to the “object”,
For example, information (keyword,
(Color, shape, feature quantity, etc.), data creator name, creation date, registration date,
There are size, comments, icons, etc.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the illustrated embodiments. FIG. 1 is a functional block diagram of the information processing apparatus according to the present embodiment. In the present embodiment, the object is “image data”, and “keyword” is used as search information.

From the input unit 1, image data, keywords, various instructions, and the like stored in the image data storage unit 6 are input. The keyword registration processing unit 2 registers the keyword input from the input unit 1 in the keyword storage unit 3, adds a similarity to another keyword, and stores the keyword in the keyword similarity storage unit 4. Image data registration processing unit 5
Adds a keyword selected from the keywords registered in the keyword storage unit 3 to the image data input from the input unit 1 and registers the image data in the image data storage unit 6.
The similarity change processing unit 10 includes the image data registration processing unit 5
Changes the similarity between keywords stored in the keyword similarity storage unit 4 based on the keywords added to the image data.

The image data search processing unit 7 includes the input unit 1
And the ambiguity x to be described in detail later
Is used as a search condition, the image data registered in the image data storage unit 6 is searched for image data that satisfies the above search condition. The image data display processing unit 8 displays the candidate image on the display unit 9 based on the image data of the candidate image searched by the image data search processing unit 7.

That is, in the present embodiment, the image data storage unit 6 constitutes the object storage unit, the keyword similarity storage unit 4 constitutes the search information storage unit, and the image data display processing unit 8 The display section 9 constitutes the output section. The display of the menu screen other than the candidate images is performed by a display processing unit (not shown) different from the image data display processing unit 8.

FIGS. 2 and 3 are diagrams showing a hardware configuration for realizing the functions of FIG. As shown in FIG. 2, the information processing apparatus includes a CRT (cathode ray tube) 12, a keyboard 13, a control device 11 having a CPU (central processing unit) mounted thereon and controlling the operation of the entire information processing apparatus. Mouse 14, floppy disk drive 15b, hard disk drive 16, printer 17, scanner 18, C
It comprises a D-ROM drive 19b, a speaker 20, a microphone 21 and the like.

The CRT 12 displays information such as searched images and characters and various information necessary for operation. The keyboard 13 and the mouse 14 are used for various input operations and instruction operations. The floppy disk 15a
The data is stored and reproduced by being mounted on the floppy disk drive 15b of the control device 11. The hard disk device 16 stores a similarity between keywords, image data, and keywords as search information. The printer 17
An image based on image data, a drawing created by image organization, and the like are output on paper. The scanner 18 reads an image on a sheet-shaped document and outputs image data. CD
The ROM 19a stores image data in a predetermined format, and is mounted on the CD-ROM drive 19b to reproduce the image data. The speaker 20 performs audio output, and the microphone 21 performs audio input. Here, the image data read by the scanner 18 and the CD-ROM drive 19b is stored in the hard disk drive 1
6 is stored. The scanner 18, the CD-ROM drive 19b, the speaker 20, and the microphone 21 are
It may be built in the control device 11 and integrated.

FIG. 3 is a block diagram of FIG. 2 focusing on the CPU mounted on the control device 11. The CPU 25 is, for example, a product number i8 manufactured by Intel Corporation.
0486DX or the like is used. The CPU 25 stores, via a data bus 26, a ROM (read only memory) 2 in which a program for controlling the information processing apparatus is stored.
8. RAM for storing various data and programs
(Random access memory) 29, a display control circuit 30 for displaying images or characters on the CRT 12, and a keyboard control circuit 3 for controlling input from the keyboard 13.
1, a mouse control circuit 32 for controlling input from the mouse 14, a floppy disk drive control circuit 33 for controlling the floppy disk drive 15b, a hard disk control circuit 34 for controlling the hard disk device 16,
Printer control circuit 3 for controlling output operation of printer 17
5. A scanner control circuit 36 for controlling the image input operation of the scanner 18, and a C for controlling the CD-ROM drive 19b.
A D-ROM drive control circuit 37, a speaker control unit 38 for controlling the sound output of the speaker 20, and a microphone control circuit 39 for controlling the sound input from the microphone 21 are connected.

The CPU 25 is connected to a clock 27 for generating a reference clock necessary for operating the information processing apparatus, and is connected to various extension boards via a data bus 26. Expansion slot 4
0 is connected. Here, SC is added to the expansion slot 40.
An SI board may be connected, and the floppy disk drive 15b, the hard disk drive 16, the scanner 18, the CD-ROM drive 19b, and the like may be connected via the SCSI board.

That is, in this embodiment, the input unit 1 is connected to the keyboard 13, the mouse 14, the hard disk device 16, the scanner 18, and the CD-ROM drive 1.
9b, the image data storage unit 6 is composed of the floppy disk 15a and the hard disk device 16, and the keyword storage unit 3 and the similarity between keywords storage unit 4 are R.
The display unit 9 is configured by the CRT 12, and the keyword registration processing unit 2, the image data registration processing unit 5, the image data search processing unit 7, the image data display processing unit 8, and the similarity change processing unit 10 are configured by the CPU 25. It is composed.

In the present embodiment, as described above,
Although the image data storage unit 6 is constituted by the floppy disk 15a and the hard disk device 16, other storage media such as a magneto-optical disk device may be used. Although the input section of the input section 1 for inputting image data is constituted by the hard disk drive 16, the scanner 18, and the CD-ROM drive 19b, other input apparatuses such as a still video camera and a digital camera may be used. Further, another output device such as a digital copying machine may be used instead of the printer 17.

Further, in the present information processing apparatus, a program for image search processing and the like is stored in the ROM 28. However, part or all of the above program may be transferred to the floppy disk 15a or the hard disk drive 16a.
Alternatively, the program may be stored in an external storage medium such as the above, and the program may be read into the RAM 29 as needed.

The information processing apparatus having the above configuration operates as follows. FIG. 4 is a flowchart of a basic processing operation executed under the control of the CPU 25 based on the program stored in the ROM 28. Hereinafter, FIG.
The basic processing operation of the information processing apparatus will be described with reference to FIG.

When the power of the information processing apparatus is turned on and the program is started, the basic processing operation starts.
In step S1, initialization of flags and the like necessary in each process and initial setting processes such as initial screen display on the display unit 9 are performed. In step S2, the display unit 9
If it is determined that the job menu "search" has been selected from the initial screen displayed in step S3, the process proceeds to step S3, and if not, the process proceeds to step S5.

In step S3, a retrieval process for ambiguously retrieving desired image data from the image data storage unit 6 is executed in accordance with the selected job menu "search" as described later in detail. Note that the search processing is performed by the image data search processing unit 7. In step S4, based on the candidate image data obtained by the search processing,
Search result display processing for displaying the candidate images on the display unit 9 is performed. After that, the process proceeds to step S13. The search result display processing is performed by the image data display processing unit 8.

If it is determined in step S5 that the job menu "data registration" has been selected from the initial screen displayed on the display unit 9, the process proceeds to step S6, and if not, the process proceeds to step S8. In step S6, the image data input from the input unit 1 is fetched in accordance with the selected job menu "data registration", and a keyword selected from the keyword storage unit 3 is added to this image data. 6 is executed. Note that the image data registration processing is performed by the image data registration processing unit 5. In step S7, similarity change processing for changing the similarity between keywords stored in the inter-keyword similarity storage unit 4 based on the keyword added in step S6 (hereinafter, referred to as an additional keyword) includes: This is performed as described in detail below. After that, the process proceeds to step S13. This similarity change processing is performed by the similarity change processing unit 10.

If it is determined in step S8 that the job menu "keyword registration" has been selected from the initial screen displayed on the display unit 9, the process proceeds to step S9, and if not, the process proceeds to step S10. In step S9, the keyword input from the input unit 1 is stored in the keyword storage unit 3 in accordance with the selected job menu “keyword registration”.
And the similarity between the input keyword and another keyword is associated with the keyword similarity storage unit 4.
Is registered. After that, the process proceeds to step S13. Note that the keyword registration processing is performed by the keyword registration processing unit 2.

If it is determined in step S10 that the job menu "other menu" has been selected from the initial screen displayed on the display unit 9, the process proceeds to step S11, and if not, the process proceeds to step S12. In step S11, other menu processing such as printout of the search image is executed according to the selected job menu "other menu". After that, the process proceeds to step S13.

In step S12, it is determined whether or not "end" has been selected from the initial screen displayed on the display unit 9. As a result, if "end" is selected, the basic processing operation is ended. Otherwise, the process proceeds to step S13. In step S13, other processing is executed. After that, the process returns to step S2 and shifts to the next menu process. Then, in the above step S12, "end"
Is selected, the basic processing operation ends.

Hereinafter, the "search processing" and the "similarity change processing" will be described in detail. Note that the "search result display processing", "image data registration processing", "keyword registration processing", and "other menu processing" are not directly related to the present invention and will not be described in detail.

FIG. 5 is a flowchart of a search processing subroutine executed by the image data search processing section 7 in step S3 in the basic processing operation shown in FIG. Hereinafter, the search processing operation will be described in detail with reference to FIG. When it is determined in step S2 of the main routine of the basic processing operation shown in FIG. 4 that the "search" job menu has been selected, a search processing subroutine starts.

In step S21, the keyword storage unit 3
Is displayed on the display unit 9, and the user sets search information including the keyword from the input unit 1 based on the keyword list.
In step S22, the degree of ambiguity (ie, the threshold value of the degree of similarity of the keyword determined to be hit) x when the above-mentioned fuzzy search is performed by the user from the input unit 1 is set.

Here, in the present embodiment, the similarity d between the basic keyword and its similar keyword is defined as follows. Note that the definition of the similarity d is not limited to this. Similarity 0: Same as basic keyword (basic keyword) ↑: High similarity to basic keyword ↓: Low similarity to basic keyword Similarity 1: No similarity to basic keyword x is set using the similarity d between “0” and “1”.

In step S23, the following fuzzy search processing is executed based on the set keyword set in step S21 and the ambiguity x set in step S22. That is, the set ambiguity x
Is "0", image data to which the set keyword is added as search information is searched. On the other hand, the set ambiguity x is “0 <x
If ≦ 1, the image data to which the keyword whose similarity d with the set keyword is equal to or less than the ambiguity x is added is searched. Therefore, when the set ambiguity x is “1”, even a keyword having no similarity with the set keyword is searched. After that, the search processing subroutine ends, and the process returns to the main routine shown in FIG.

FIG. 6 is a flowchart of a similarity change processing subroutine executed by the similarity change processing section 10 in step S7 of the basic processing operation shown in FIG. Hereinafter, the similarity change processing operation will be described in detail with reference to FIGS. In step S6 of the basic processing operation shown in FIG. 4, the image data registration processing ends, and the image data registration processing unit 5 sends the similarity change processing unit 1
When the information indicating the additional keyword is transferred to 0, the similarity change processing subroutine starts.

In step S31, it is determined whether or not a plurality of additional keywords have been added to the image data to be registered during the image data registration process. As a result, if there are a plurality, the process proceeds to step S32. On the other hand, otherwise, the similarity change processing operation ends, and the process returns to the main routine shown in FIG. In step S32, the similarity d between the currently set additional keywords is acquired by referring to the inter-keyword similarity storage unit 4.

In step S33, the current similarity d between the additional keywords acquired in step S32 is changed so as to increase the relevance of the two additional keywords. For example, the additional keywords are keyword A and keyword B.
And the similarity d between the current keywords A and B is "0.
5 ". In this case, the similarity d in this example is set as a decimal value of 0 to 1, and it is defined that the smaller the similarity d is, the higher the relevance is. Is subtracted, and the new similarity d is changed to “0.4”. The same applies to the case where the number of additional keywords is three or more. When the number of additional keywords is three of keywords C, D, and E, the similarity between keywords C and D and the similarity between keywords D and E , And the similarity between the keywords C and E is similarly changed.

In step S34, the inter-keyword similarity storage unit 4 is updated with the similarity d changed in step S33. After that, the search processing subroutine ends, and the process returns to the main routine shown in FIG.

As a result, step S of the basic processing operation is performed.
The similarity d between the keywords once set in 9 is
The keyword is reduced (the relevance is increased) according to the number of times that both keywords related to the similarity d are added together to the same image data. Therefore, the user frequently adds a pair to the keyword similarity storage unit 4.
The similarity d set so that the relevance between keywords (that is, the user recognizes that the relevance is high) is stored is stored. In other words, the similarity between the keywords is automatically set so as to meet the user's will.

As described above, the present embodiment has the similarity change processing unit 10. Then, of the similarities d set in advance by the keyword registration processing unit 2 and stored in the inter-keyword similarity storage unit 4, the similarity d between the keywords added together by the user to the same image data is determined by the two keywords. They are changed to increase the relevance between them. Therefore, the similarity set so as to meet the user's intention is automatically registered in the inter-keyword similarity storage unit 4. Moreover,
Since the similarity d is reset according to the number of times the same image data is added together, the more the user uses the information processing apparatus, the more the database that can be searched according to the user's sense is used. It is being built.

Therefore, according to the present embodiment, since the similarity d that is not relevant to the keyword is set in advance, the user can use the similarity d between the keywords that are intricately related to each other. This eliminates the hassle of finding out the similarity d and manually correcting it one by one.

As described above, in the conventional fuzzy search, there are two keywords that the user wants to set as search conditions.
When the similarity d between the two keywords is set so as to have a low relevance, the user needs to set the ambiguity x high in preparation for an increase in the number of candidate image data.
However, in the present embodiment, the similarity d between a plurality of keywords that the user wants to set as a search condition has already been set to a small value. Therefore, the user does not need to reluctantly set the ambiguity x high, and can search for the target image data with a small number of candidate image data.

Further, in the present embodiment, as described above, the similarity d between the keywords is automatically changed to meet the user's will. Therefore, when performing the keyword registration process in the basic processing operation, the user does not need to strictly set the optimal similarity in view of the relevance to many registered keywords. The similarity may be set with a certain degree of strictness. That is, according to the present embodiment, keyword registration processing is facilitated.

In the above embodiment, when the similarity d is changed in step S33 of the similarity change processing subroutine, the similarity d is changed by simple subtraction, but the present invention is not limited to this. Not something. For example, the similarity may be calculated in consideration of the distance between the keywords, and the current similarity d may be changed based on the calculated value.

In the above embodiment, the fuzzy search process based on the keyword attached to the still image data has been described as an example. However, the present invention is not limited to this, and is also applicable to the case of ambiguous search processing based on keywords attached to moving image data, character data, audio data, and multimedia data obtained by combining them. Further, in each of the above embodiments, the case of the fuzzy search process using the similarity d based on the keyword attached to the image data is described as an example. However,
The present invention is not limited to this, but includes feature amounts extracted from media data and media data feature information.
It can also be applied to the case of ambiguous search processing using similarity based on (for example, the color of an image or the rough shape of an image).

Further, in the above-described embodiment, the case where the similarity between keywords is applied to the fuzzy search processing has been described as an example, but it is also possible to apply the similarity to other processing. For example, if one keyword is set at the time of setting a keyword at the time of search, the value of the similarity d with that keyword is small.
A list of keywords (that is, highly relevant) may be displayed, and the operator may be prompted to set another keyword.

[0050]

As is apparent from the above description, the information processing apparatus according to the first aspect of the present invention, when registering an object in the object storage unit by the object registration processing unit, when a plurality of pieces of search information are added, Since the similarity change processing unit changes the similarity between the added search information already stored in the search information storage unit so as to increase the similarity, the similarity between the search information added to the same object is changed. Sex is enhanced. Therefore, it is possible to automatically construct a search information storage unit in which a similarity corresponding to the similarity between search information recognized by the user is registered.

In other words, according to the present invention, a search information storage unit that meets the user's intention is automatically constructed. Therefore, when the search information and similarity are first registered in the search information storage unit, There is no need to strictly set the optimal similarity in view of the relevance to many already registered search information. Therefore, the user can be released from the difficulty of the search information registration process. In addition, even if an unsatisfactory similarity is initially set in the search information storage unit, the target similarity is searched for from the similarities between the complicatedly related search information and manually corrected. No need. Therefore, it is possible to release the user from the trouble of correcting the similarity.

Further, in the search information storage unit constructed as described above, the similarity corresponding to the similarity between the search information recognized by the user is registered. Therefore, when the candidate object is searched from the object storage unit by the fuzzy search using the similarity, the similarity of the search information to be used is low, so that the ambiguity is not reluctantly set to be narrow. Can be reduced.

According to a second aspect of the present invention, there is provided an information processing method comprising the steps of: inputting an object, adding search information to the input object, and matching the similarity between the search information and other search information. A registration step of registering the object, the search information, and the similarity in the storage unit; and, when a plurality of search information is added to the same object, the similarity between the added plurality of search information is similar. Because it has a change step to change to increase the likelihood,
Similarity between search information added to the same object is enhanced. Therefore, it is possible to automatically construct a database in which a similarity matching the similarity between the pieces of search information recognized by the user is registered.

That is, according to the information processing method of the present invention, a database that meets the user's intention is automatically constructed, so that the user can be released from the difficulty of registering search information and the trouble of correcting similarity.

Further, in the program storage medium according to the third aspect of the present invention, there is provided an input step for inputting an object,
A registration step of adding search information to the input object, associating the similarity between the search information and other search information, and registering the object, the search information, and the similarity in a storage unit; In the case where a plurality of pieces of search information are added to a plurality of pieces of search information, a change step of changing the similarity between the plurality of pieces of added search information so as to increase the similarity is provided. By executing the program, the similarity between the pieces of search information added to the same object is increased. Therefore, it is possible to automatically construct a database in which a similarity matching the similarity between the pieces of search information recognized by the user is registered.

That is, according to the program storage medium of the present invention, a database that meets the user's wish is automatically constructed, so that the user can be relieved from the difficulty of registering search information and the trouble of correcting similarity.

[Brief description of the drawings]

FIG. 1 is a functional block diagram illustrating an embodiment of an information processing apparatus according to the present invention.

FIG. 2 is a diagram showing an apparatus configuration for realizing the functions shown in FIG.

FIG. 3 is a hardware CP realizing the functions shown in FIG. 1;
It is a block diagram centering on U.

FIG. 4 is a flowchart of a basic processing operation executed under control by a CPU in FIG. 3;

FIG. 5 is a flowchart of a search processing subroutine executed by an image data search processing unit in FIG. 1;

FIG. 6 is a flowchart of a similarity change processing subroutine executed by a similarity change processing unit in FIG. 1;

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... input part, 2 ... keyword registration processing part, 3 ... keyword storage part, 4 ... keyword similarity storage part, 5 ... image data registration processing part,
6 image data storage unit, 7 image data search processing unit, 8 image data display processing unit, 9 display unit, 10 similarity change processing unit.

Claims (3)

[Claims] 1. An object storage unit in which an input unit, an object, and search information for searching for the object are stored in association with each other, and the search information corresponds to the similarity with other search information. A search information storage unit attached and stored; an object registration processing unit that adds search information to the object input from the input unit and registers the object in the object storage unit; and a setting search set from the input unit. A search processing unit for searching for a candidate object from the object storage unit based on the information and the degree of similarity; an output unit for outputting the candidate object searched for by the search processing unit; When a plurality of pieces of search information are added, the added search information stored in the search information storage unit An information processing apparatus comprising: a similarity change processing unit that changes a similarity between images so as to increase similarity. 2. An input step of inputting an object, adding search information to the input object, associating the similarity between the search information and other search information, A registration step of registering a plurality of pieces of search information in the storage unit, and, when a plurality of pieces of search information are added to the same object, changing a similarity between the plurality of pieces of added search information so that the similarity increases. A specifying step of specifying search information and a similarity; a search step of searching the storage unit for an object to which the specified search information is added based on the specified search information and the similarity; An information processing method comprising an output step of outputting a searched object. 3. An input step of inputting an object, adding search information to the input object, associating the similarity between the search information and other search information, A registration step of registering a plurality of pieces of search information in the storage unit, and, when a plurality of pieces of search information are added to the same object, changing a similarity between the plurality of pieces of added search information so that the similarity increases. A specifying step of specifying search information and a similarity; a search step of searching the storage unit for an object to which the specified search information is added based on the specified search information and the similarity; A program storage medium storing an information processing program in an output step of outputting a searched object.