JP6696344B2 - Information processing device and program - Google Patents

Description

  The present invention relates to an information processing device and a program.

  A technique is known in which image attribute information (for example, keyword or tag information) representing the content of an image is automatically added to the image.

  In the system described in Patent Document 1, an html page including an image having a feature similar to the feature of the keyword addition target image is searched, and the noun group described in the html page is extracted. Nouns that appear frequently in the noun group are provided as keyword candidates.

JP, 2011-54006, A

  By the way, when a word or phrase extracted by searching for an image similar to the image to which the image attribute information is given (target image) is specified as an image attribute information candidate of the target image, the image attribute information for the target image of the word or phrase is specified. Therefore, there is a case where a word / phrase that is not suitable for expressing the target image is specified as the image attribute information candidate because it is not evaluated.

  An object of the present invention is to compare words extracted using a search for an image similar to the target image with a case in which the words are more suitable for expressing the target image than in the case of specifying them as image attribute information candidates of the target image. It is to specify as an attribute information candidate.

  The invention according to claim 1 is an extraction unit that extracts a word or phrase that appears in extraction target data that includes a first image similar to the target image, and an image search unit that searches the second image using the extracted word or phrase. And a first specifying unit that specifies, as an image attribute information candidate of the target image, a phrase used to search for a second image similar to the target image.

  The invention according to claim 2 is characterized in that the first specifying means further specifies a word or phrase related to the image attribute information candidate as a new image attribute information candidate of the target image. Information processing device.

  The invention according to claim 3 is characterized in that the word or phrase related to the image attribute information candidate is a synonym of the image attribute information candidate extracted from synonym dictionary information defining a synonym group. The information processing device described in 1.

  In the invention according to claim 4, when there are a plurality of target images, the extraction unit extracts a word or phrase for each target image, and the image search unit is common among the word or phrase groups extracted for the plurality of target images. The information processing apparatus according to any one of claims 1 to 3, wherein the second image is searched collectively for words and phrases to be performed.

  In the invention according to claim 5, the plurality of target images are classified into a plurality of groups having different impressions according to the impressions of the respective target images, and the image search means is the same for each group. The second image is searched collectively for common words / phrases in the word / phrase group extracted for the target image group belonging to the group, and the information processing device is specified for each group using the second image. Identifying the image attribute information candidates that are common to the target image groups that belong to the same group as the common attribute information candidates for the target image groups that belong to the same group. The information processing apparatus according to claim 4, further comprising two specifying means.

  According to a sixth aspect of the present invention, the first specifying unit determines that the word or phrase used in the search for the second image whose similarity to the target image is equal to or more than a preset threshold value is the target image. The information processing device according to any one of claims 1 to 5, wherein the information processing device is specified as the image attribute information candidate.

  The invention according to claim 7 is the information processing apparatus according to any one of claims 1 to 6, further comprising control means for displaying the image attribute information candidates on a display means. ..

  According to an eighth aspect of the present invention, a computer is used to extract a word or phrase that appears in extraction target data that includes a first image similar to the target image, and an image to search for a second image using the extracted word or phrase. It is a program that functions as a searching unit and a specifying unit that specifies a word or phrase used for searching a second image similar to the target image as an image attribute information candidate of the target image.

  According to the inventions according to claims 1, 2, 3, 6, 7, and 8, comparison is made with a case where a word or phrase extracted by using a search for an image similar to the target image is specified as an image attribute information candidate of the target image. Then, a word more suitable for expressing the target image is specified as the image attribute information candidate.

  According to the invention of claim 4, the efficiency of searching the second image is improved as compared with the case where the second image is individually searched for the words and phrases extracted for each target image.

  According to the fifth aspect of the invention, the group is expressed in comparison with the case where the word / phrase extracted using the search for the image similar to the target image is specified as the common attribute information candidate of the group to which the target image belongs. Therefore, a suitable word is specified as a common attribute information candidate.

It is a block diagram which shows the keyword provision system which concerns on 1st Embodiment of this invention. It is a block diagram which shows the keyword candidate selection apparatus which concerns on 1st Embodiment. It is a block diagram which shows a terminal device. It is a figure which shows an example of a target image. It is a figure which shows an example of a web page (html page). It is a figure which shows an example of a primary keyword candidate list. It is a figure which shows an example of a search result image and a final keyword candidate. It is a flow chart which shows processing by a keyword candidate selection device concerning a 1st embodiment. It is a block diagram which shows the keyword candidate selection apparatus which concerns on 2nd Embodiment. It is a figure which shows an example of the correspondence of a target image, a primary keyword candidate, and a search result image. It is a block diagram which shows the keyword candidate selection apparatus which concerns on 4th Embodiment. It is a figure which shows an example of a target image and a group. It is a figure which shows an example of the correspondence of a target image, a primary keyword candidate, and a search result image.

[First Embodiment]
Hereinafter, the first embodiment of the present invention will be described. FIG. 1 shows an example of a keyword assigning system as an information processing system according to the first embodiment of the present invention. As an example, this system includes a keyword candidate selection device 10 as an information processing device, one or a plurality of terminal devices 12, and one or a plurality of web servers 14. The keyword candidate selection device 10 and the terminal device 12 communicate with each other via a communication path such as the Internet or a LAN (Local Area Network). The keyword candidate selection device 10 and the individual web servers 14 communicate with each other via a communication path such as the Internet or a LAN. Of course, the terminal device 12 and each web server 14 may communicate with each other via a communication path such as the Internet or a LAN.

  The keyword candidate selection device 10 has a function of receiving an image to which image attribute information is added (hereinafter referred to as “target image”) and specifying a candidate of image attribute information representing the content of the target image. The image attribute information is, for example, a keyword or tag information. The data of the target image is sent from the terminal device 12, for example. The keyword candidate selection device 10 also has a function of transmitting and receiving data to and from other devices.

  The terminal device 12 is, for example, a device such as a PC (personal computer), a tablet PC, a smart phone, and a mobile phone, and has a function of transmitting and receiving data to and from other devices.

  The web server 14 has a function of providing a web page, a function of searching a web page, and a function of transmitting / receiving data to / from another device. For example, the web server 14 provides the data of the web page to the keyword candidate selection device 10 via the Internet.

  Hereinafter, the keyword assigning system will be described in detail. In the following, as an example of the image attribute information, a case of specifying a keyword representing the content of the target image will be described.

  The configuration of the keyword candidate selection device 10 will be described in detail with reference to FIG. FIG. 2 shows the configuration of the keyword candidate selection device 10.

  The communication unit 16 is a communication interface, and has a function of transmitting data to another device and a function of receiving data from another device. The communication unit 16 may be a communication interface having a wireless communication function or may be a communication interface having a wired communication function. As an example, the communication unit 16 receives the target image data from the terminal device 12 and the web page data from the web server 14. The communication unit 16 also transmits the keyword candidate data as the image attribute information candidates to the terminal device 12.

  The web page acquisition unit 18 acquires, from each web server 14, one or a plurality of web page data (html page data) including an image similar to the target image (hereinafter referred to as “similar image”). The similar image corresponds to an example of the first image, and the web page data corresponds to an example of extraction target data. For example, each web server 14 searches for a web page including a similar image in response to a request from the keyword candidate selection device 10 and transmits the data of the web page to the keyword candidate selection device 10. The web page acquisition part 18 acquires the data of the web page. The web page acquisition unit 18 may not be provided in the keyword candidate selection device 10 but may be provided in another device (for example, a search server or the like). In this case, the keyword candidate selection device 10 acquires the data of the web page acquired by the other device from the other device.

  The concept of similarity includes the concept of identity. For example, a known method is used as the similar image search process or the feature extraction process. For example, the web page acquisition unit 18 extracts information representing a feature from the target image (for example, parameters such as pixel grayscale, average grayscale, image outline, and the like), and identifies features similar to the extracted feature. The data of the web page including the similar image is acquired from each web server 14. For example, a building image, a mountain image, a sky image, a cloud image, a sea image, a river image, a person image, an animal image, a plant image, an image of an article, etc. are characteristic information of the target image. To be extracted. For example, when a mountain image is extracted as feature information from the target image, each web server 14 searches for a web page including a mountain image having a shape similar to that of the mountain, and the data of the web page is used as the keyword candidate selection device. Sent to 10.

  The word / phrase extraction unit 20 analyzes a web page acquired by the web page acquisition unit 18, that is, a web page including a similar image, and extracts a word / phrase (character string) appearing on the web page as a primary keyword candidate. To do. When the data of a plurality of web pages is acquired by the web page acquisition unit 18, the phrase extraction unit 20 extracts a phrase for each web page.

  Although the data of the web page is used as an example of the extraction target data, data other than the web page may be used as the extraction target data. For example, document data including an image and a character string, image data, or the like may be used as the extraction target data. In this case, the web page acquisition unit 18 acquires the document data or the image data including the similar image from a storage device (for example, a document database or an image database) (not shown) in which the extraction target data is stored. When document data including an image and a character string is used as extraction target data, the word / phrase extraction unit 20 extracts a word / phrase from the document data. When the image data is used as the extraction target data, the word / phrase extracting unit 20 extracts the word / phrase from the image data by applying, for example, OCR (Optical Character Recognition) processing to the image data.

  The image search unit 22 searches for one or a plurality of images (hereinafter, referred to as “search result image”) by using the words (primary keyword candidates) extracted by the word extraction unit 20 as search keywords. The search result image corresponds to an example of the second image. When a plurality of words / phrases are extracted by the word / phrase extraction unit 20, the image search unit 22 searches for an image for each word / phrase using each word / phrase as a single search keyword. As another example, the image search unit 22 may search for an image using a combination of a plurality of words as a search keyword group. For example, the image search unit 22 performs an AND search, that is, an image that matches a plurality of words and phrases that form the search keyword group. In response to a request from the keyword candidate selection device 10, each web server 14 searches for an image from a group of images existing on the Internet or in an image database using the primary keyword candidate, and searches for the image (search result image). The data is transmitted to the keyword candidate selection device 10. The image search unit 22 acquires the image data. For example, a known method is used as the image search processing. For example, an image in which the same or similar words as the primary keyword candidate are associated is searched from an image group existing on the Internet or in an image database, and the image data (data of the search result image) is selected as the keyword candidate. It is transmitted to the device 10. Of course, the images may be searched by another search technique.

  The similarity calculation unit 24 calculates the similarity between the target image and the search result image. When a plurality of search result images are searched, the similarity calculation unit 24 calculates the similarity between the target image and the search result image for each search result image. As the similarity calculation processing, for example, a known method is used. For example, the similarity calculation unit 24 extracts characteristic information (for example, parameters such as pixel shading, average value of shading, image outline, etc.) from each of the target image and the search result image, and extracted from the target image. By comparing the characteristic information with the characteristic information extracted from the search result image, the degree of similarity between the target image and the search result image is calculated.

  The keyword candidate specifying unit 26 specifies the word or phrase used for searching the search result image similar to the target image as the final keyword candidate (information corresponding to an example of the image attribute information candidate) of the target image. For example, the keyword candidate specifying unit 26 determines a word (primary keyword candidate) used for searching a search result image whose similarity to the target image is equal to or more than a preset similarity threshold as a final keyword of the target image. Specify as a candidate. The similarity threshold may be changed by the user, the administrator, or the like.

  The final keyword candidate data is transmitted from the keyword candidate selection device 10 to the terminal device 12. On the terminal device 12, for example, the final keyword candidate is displayed.

  The control unit 28 controls the operation of each unit of the keyword candidate selection device 10.

  Hereinafter, the configuration of the terminal device 12 will be described in detail with reference to FIG. FIG. 3 shows the configuration of the terminal device 12.

  The communication unit 30 is a communication interface, and has a function of transmitting data to another device and a function of receiving data from another device. The communication unit 30 may be a communication interface having a wireless communication function or may be a communication interface having a wired communication function. As an example, the communication unit 30 transmits the data of the target image to the keyword candidate selection device 10, and receives the data of the final keyword candidate as the image attribute information candidate from the keyword candidate selection device 10.

  The storage unit 32 is a storage device such as a hard disk or a memory, and stores, for example, various programs and various data. Of course, they may be stored in separate storage devices, or may be stored in the same storage device.

  The UI unit 34 and the user interface unit include a display unit and an operation unit. The display unit is a display device such as a liquid crystal display. The operation unit is, for example, an input device such as a touch panel or a keyboard. Of course, the UI unit 34 may be a user interface having both functions of a display unit and an operation unit (for example, a display as a touch panel or a display that electronically displays a keyboard or the like).

  The control unit 36 controls the operation of each unit of the terminal device 12. When the data of the final keyword candidate is transmitted from the keyword candidate selection device 10 to the terminal device 12, the control unit 36 causes the UI unit 34 to display the final keyword candidate. For example, when the user gives a keyword addition instruction using the UI unit 34, the control unit 36 associates the final keyword candidate with the target image. Of course, this association may be performed by the keyword candidate selection device 10.

  The keyword assigning system will be described in detail below.

  FIG. 4 shows an example of the target image. The target image 38 is, for example, an image showing “tofu”. The target image 38 is an image designated by the user using the terminal device 12 as a keyword addition target image. For example, an image group is displayed on the UI unit 34 of the terminal device 12, and the user uses the UI unit 34 to specify a target image 38 to be a keyword addition target from the image group. Of course, the target image 38 may be designated or input to the terminal device 12 by another method. The data of the target image 38 is transmitted from the terminal device 12 to the keyword candidate selection device 10 via the communication path.

  The web page acquisition unit 18 extracts “tofu image” from the target image 38 as characteristic information, and outputs data of one or more web pages including images similar to the “tofu image” from each web server 14. get.

  FIG. 5 shows an example of a web page provided by the web server 14. The web page 40 includes an image 42. Tofu is represented in the image 42, and the image 42 is an image similar to the target image 38. In this way, the web page 40 including the image 42 similar to the target image 38 is searched, and the data of the web page 40 is transmitted from the web server 14 to the keyword candidate selection device 10.

  When the data of the web page 40 is provided from the web server 14 to the keyword candidate selection device 10, the word / phrase extraction unit 20 extracts a word / phrase appearing on the web page 40 as a primary keyword candidate. For example, the word / phrase extracting unit 20 applies a morphological analysis to divide the character string into a plurality of words and extracts a noun as a primary keyword candidate. Of course, the phrase extracting unit 20 may extract phrases other than nouns (for example, verbs, adjectives, adverbs, etc.) as primary keyword candidates.

  The word / phrase extraction unit 20 may extract a word / phrase as a primary keyword candidate based on the number of appearances of the word / phrase. For example, the word / phrase extracting unit 20 extracts, as a primary keyword candidate, a word / phrase whose number of appearances is equal to or more than a preset number-of-times threshold value in a group of terms / words appearing on the web page 40, and a number of words / phrases whose number of appearances is less than the number-of-times threshold value. Need not be extracted. The number of times threshold may be changed by a user, an administrator, or the like. It is predicted that a word or phrase whose number of appearances is equal to or more than the number of times threshold has a higher relevance to the image 42, that is, a relevance to the target image 38 than a word or phrase whose number of appearances is less than the number of times threshold. Therefore, by extracting words and phrases whose number of appearances is greater than or equal to the number of times threshold value, words and phrases predicted to have a relatively high degree of association with the target image 38 are extracted as primary keyword candidates.

  As another example, the phrase extraction unit 20 may extract a phrase as a primary keyword candidate based on the rank of the number of appearances of the phrase. For example, the word / phrase extracting unit 20 assigns words to the higher rank in the descending order of the number of appearances, and in the word / phrase group appearing on the web page 40, the word or phrase in which the order of the number of appearances is equal to or higher than a preset rank threshold value. May be extracted as a primary keyword candidate, and a word having an appearance frequency rank less than a rank threshold may not be extracted. The rank threshold value may be changed by the user, the administrator, or the like. For example, the word / phrase extracting unit 20 extracts, as a primary keyword candidate, words / phrases included within the order of several (eg, fifth) from the top of the entire word group appearing on the web page 40. It is predicted that a word or phrase whose appearance frequency rank is equal to or higher than the rank threshold value has a higher relevance to the target image 38 than a word or phrase whose appearance frequency rank is lower than the rank threshold value. Therefore, by extracting a word or phrase whose appearance frequency rank is equal to or higher than the rank threshold value, a word or phrase predicted to be relatively high in relation to the target image 38 is extracted as a primary keyword candidate.

  As another example, the phrase extraction unit 20 may extract a phrase as a primary keyword candidate based on the frequency of appearance of the phrase. For example, the phrase extraction unit 20 calculates the total number of appearances of all the phrases appearing on the web page 40, and calculates, for each individual phrase, the ratio of the number of appearances of the relevant phrase to the total sum as the appearance frequency of the relevant phrase. .. The word / phrase extraction unit 20 extracts, from the word / phrase group appearing on the web page 40, words / phrases whose appearance frequency is equal to or higher than a preset frequency threshold as primary keyword candidates, and extracts words / phrases whose appearance frequency is less than the frequency threshold. You don't have to. The frequency threshold may be changed by the user, the administrator, or the like. It is predicted that a word or phrase whose appearance frequency is equal to or higher than the frequency threshold has a higher relevance to the target image 38 than a word or phrase whose appearance frequency is less than the frequency threshold. Therefore, by extracting a word or phrase whose appearance frequency is equal to or higher than the frequency threshold value, a word or phrase that is predicted to be relatively highly related to the target image 38 is extracted as a primary keyword candidate.

  As another example, the word / phrase extracting unit 20 may extract a word / phrase that is a primary keyword candidate based on the rank of the appearance frequency of the word / phrase. For example, the word / phrase extracting unit 20 assigns words to a higher rank in descending order of appearance frequency, and among words / phrases appearing on the web page 40, a word or phrase whose appearance frequency rank is equal to or higher than a preset rank threshold value. May be extracted as a primary keyword candidate, and a word or phrase whose appearance frequency rank is less than the rank threshold may not be extracted. The rank threshold value may be changed by the user, the administrator, or the like. For example, the word / phrase extracting unit 20 extracts, as a primary keyword candidate, words / phrases included within the order of several (eg, fifth) from the top of the entire word group appearing on the web page 40. It is predicted that a word having an appearance frequency rank higher than the rank threshold has a higher relevance to the target image 38 than a word having an appearance frequency rank lower than the rank threshold. Therefore, by extracting words and phrases whose appearance frequency rank is equal to or higher than the rank threshold value, words and phrases predicted to be relatively high in relation to the target image 38 are extracted as primary keyword candidates.

  As another example, the phrase extraction unit 20 may extract a phrase that is a primary keyword candidate based on the font size of the phrase. For example, the word / phrase extraction unit 20 extracts, as a primary keyword candidate, a word / phrase having a font size that is equal to or larger than a preset size threshold value in the word group that appears on the web page 40, and a word whose font size is less than the size threshold value. Need not be extracted. The size threshold may be changed by the user, the administrator, or the like. It is predicted that words and phrases whose font size is equal to or larger than the size threshold value are more conspicuous in the web page 40 than words and phrases whose font size is smaller than the size threshold value, and are more likely to be associated with the target image 38. Therefore, by extracting words and phrases whose font size is equal to or larger than the size threshold value, words and phrases predicted to be relatively high in relation to the target image 38 are extracted as primary keyword candidates.

  As another example, the phrase extraction unit 20 may extract a phrase as a primary keyword candidate based on the rank of the font size of the phrase. For example, the word / phrase extracting unit 20 assigns words to a higher rank in descending order of font size, and among words / phrases appearing on the web page 40, words / phrases whose font size rank is equal to or higher than a preset rank threshold value. May be extracted as a primary keyword candidate, and a word or phrase whose font size rank is less than the rank threshold may not be extracted. The rank threshold value may be changed by the user, the administrator, or the like. For example, the word / phrase extraction unit 20 extracts, as a primary keyword candidate, a word / phrase included within the order of several (eg, fifth) from the top of the entire word group appearing on the web page 40. It is predicted that words and phrases whose font size rank is equal to or higher than the rank threshold value are more prominent in the web page 40 than words and words whose font size rank rank is lower than the rank threshold value, and are highly relevant to the target image 38. To be done. Therefore, by extracting words and phrases whose font size rank is equal to or higher than the rank threshold value, words and phrases predicted to be relatively high in relation to the target image 38 are extracted as primary keyword candidates.

  As another example, the phrase extraction unit 20 may extract a phrase as a primary keyword candidate based on the ratio of the font size of the phrase. For example, the word / phrase extracting unit 20 calculates the average font size (hereinafter, referred to as “average font size”) of all words / phrases appearing on the web page 40, and for each word / phrase, the word / phrase with respect to the average font size is calculated. Calculate the percentage of font size. The word / phrase extracting unit 20 extracts, as a primary keyword candidate, words / phrases whose ratio is equal to or higher than a preset threshold value ratio among words / phrases appearing on the web page 40, and extracts words / phrases whose ratio ratio is lower than the ratio threshold value. You don't have to. The ratio threshold may be changed by the user, the administrator, or the like. It is predicted that words and phrases whose font size ratio is equal to or greater than the ratio threshold value are more prominent in the web page 40 than words and phrases whose font size ratio is less than the ratio threshold value, and are predicted to be more relevant to the target image 38. To be done. Therefore, by extracting words and phrases having a font size ratio of not less than the ratio threshold value, words and phrases predicted to be relatively high in relation to the target image 38 are extracted as primary keyword candidates.

  As another example, the phrase extraction unit 20 may extract a phrase as a primary keyword candidate based on the rank of the font size ratio of the phrase. For example, the word / phrase extracting unit 20 assigns a higher rank to the words in the descending order of the font size ratio, and the rank of the font size ratio in the word group appearing on the web page 40 is a preset threshold value. The words and phrases described above may be extracted as primary keyword candidates, and the words and phrases in which the font size ratio is less than the rank threshold may not be extracted. The rank threshold value may be changed by the user, the administrator, or the like. For example, the word / phrase extraction unit 20 extracts, as a primary keyword candidate, a word / phrase included within the order of several (eg, fifth) from the top of the entire word group appearing on the web page 40. Words whose font size ratio rank is higher than the rank threshold value are predicted to be more prominent in the web page 40 than words whose font size ratio rank is lower than the rank threshold value, and are associated with the target image 38. Is expected to be high. Therefore, by extracting words and phrases whose ranks of the font size ratio are equal to or higher than the rank threshold value, words and phrases predicted to be relatively high in relation to the target image 38 are extracted as primary keyword candidates.

  As another example, the phrase extracting unit 20 may extract a phrase as a primary keyword candidate based on the positional relationship with the image 42 as a similar image. For example, the word / phrase extracting unit 20 may extract, as a primary keyword candidate, a noun described within a preset range based on the arrangement position of the image 42. It is predicted that the nouns described in the range have higher relevance to the target image 38 than the nouns described outside the range. Therefore, by extracting the nouns included in the range, the nouns predicted to be more relevant to the target image 38 than the nouns described outside the range are extracted as the primary keyword candidates. As another example, the phrase extracting unit 20 may extract the noun described at the position closest to the image 42 as a primary keyword candidate. The phrase extraction unit 20 may specify the positional relationship between the image 42 and each phrase by analyzing the hierarchical structure of the html source of the web page 40, for example.

  Of course, the phrase extraction unit 20 may extract a phrase from the web page 40 according to a criterion other than the above.

  When the web page other than the web page 40 is also acquired, the word / phrase extracting unit 20 extracts the word / phrase from the web page other than the web page 40 as described above.

  FIG. 6 shows an example of the primary keyword candidate list. This primary keyword candidate list includes words and phrases extracted as primary keyword candidates. As an example, nouns such as “tofu”, “limited company”, “AAA (store name)”, “store”, and “health” are extracted as primary keyword candidates. Since “AAA (store name)” is a proper noun, the phrase extraction unit 20 may exclude “AAA (store name)” from the primary keyword candidates. In this case, “AAA (store name)” is not included in the primary keyword candidate list. The data of the primary keyword candidate list may be transmitted from the keyword candidate selection device 10 to the terminal device 12, and the primary keyword candidate list may be displayed on the UI unit 34 of the terminal device 12.

  Hereinafter, the processes performed by the image search unit 22, the similarity calculation unit 24, and the keyword candidate specifying unit 26 will be described in detail with reference to FIG. 7.

  When a word or phrase as a primary keyword candidate is extracted as shown in FIG. 6, the image search unit 22 searches for an image using the primary keyword candidate as a search keyword. For example, the image search unit 22 searches for an image for each primary keyword candidate by using each primary keyword candidate as a single search keyword. FIG. 7 shows a search result image acquired by the search. The search result image 44 is an image searched using the primary keyword candidate “tofu” as the search keyword (for example, an image associated with the phrase “tofu”), and is an image showing tofu, for example. is there. The search result image 46 is an image searched using the primary keyword candidate “limited company” as a search keyword (for example, an image associated with the phrase “limited company”). It is a represented image. The search result image 48 is an image searched using the primary keyword candidate “AAA (store name)” as a search keyword (for example, an image associated with the phrase “AAA”), and for example, the name is “AAA. It is an image in which a person who is ". The search result image 50 is an image searched using the primary keyword candidate “store” as a search keyword (for example, an image associated with the word “store”), and is, for example, an image showing a certain store. is there. The search result image 52 is an image searched using the primary keyword candidate “health” as a search keyword (for example, an image associated with the phrase “health”), and is, for example, an image reminiscent of health. is there.

  The primary keyword candidate list may be displayed on the UI unit 34 of the terminal device 12, and the user may specify a primary keyword candidate to be used as a search keyword from the primary keyword candidate list. In this case, the data of the primary keyword candidate specified by the user is transmitted from the terminal device 12 to the keyword candidate selecting device 10, and the image search unit 22 searches for an image using the primary keyword candidate specified by the user as a search keyword. To do. When a plurality of primary keyword candidates are designated by the user, the image search unit 22 searches for an image for each primary keyword candidate by using each primary keyword candidate as a single search keyword.

  The image search unit 22 may search for an image by performing an AND search using a combination of a plurality of primary keyword candidates as a search keyword group. Explaining with the example shown in FIG. 6, the image search unit 22 uses, for example, a combination of the primary keyword candidates “tofu” and “health” as a search keyword group, and performs an AND search to obtain the primary keyword candidate “tofu”. And an image that matches both "health" (for example, an image in which both the words "tofu" and "health" are associated) are searched. As a result, images related to both the primary keyword candidates “tofu” and “health” are searched. The number of primary keyword candidates included in the search keyword group may be a preset number, or may be changed by the user, the administrator, or the like. The primary keyword candidates included in the search keyword group may be randomly selected by the image search unit 22 from the primary keyword candidate group, or may be selected by the user from the primary keyword candidate group. For example, the primary keyword candidate list may be displayed on the UI unit 34 of the terminal device 12, and the user may specify a plurality of primary keyword candidates to be used as a search keyword group from the primary keyword candidate list.

  The similarity calculator 24 calculates the similarity between the target image 38 and each of the search result images 44, 46, 48, 50, 52. That is, the similarity between the target image 38 and the search result image 44, the similarity between the target image 38 and the search result image 46, the similarity between the target image 38 and the search result image 48, the target image 38 And the search result image 50 and the similarity between the target image 38 and the search result image 52 are calculated.

  The keyword candidate specifying unit 26 specifies the search result image whose similarity to the target image 38 is equal to or higher than the similarity threshold value, and determines the primary keyword candidate used to search the search result image as the final keyword of the target image 38. Specify as a keyword candidate. In the example shown in FIG. 7, the similarity between the target image 38 and the search result image 44 is equal to or higher than the similarity threshold, and the primary keyword candidate “tofu” used for searching the search result image 44 is the final keyword. Identified as a candidate.

  The data of the final keyword candidate “tofu” is transmitted from the keyword candidate selection device 10 to the terminal device 12, and the final keyword candidate “tofu” is displayed on the UI unit 34 of the terminal device 12. For example, when the user gives an instruction to attach a keyword using the UI unit 34, the control unit 36 of the terminal device 12 associates the final keyword candidate “tofu” with the target image 38 as image attribute information. Of course, in the terminal device 12, the final keyword candidate “tofu” may be automatically associated with the target image 38 as image attribute information. In the keyword candidate selection device 10, the final keyword candidate “tofu” is automatically associated with the target image 38 as image attribute information, and the data of the target image 38 associated with the final keyword candidate “tofu” is the keyword. It may be transmitted from the candidate selection device 10 to the terminal device 12.

  The final keyword candidate “tofu” as the image attribute information is used as a search keyword for searching the target image 38, for example. For example, when the phrase “tofu” is given as the search keyword, the target image 38 associated with the final keyword candidate “tofu” is searched.

  In the example shown in FIG. 7, one word “tofu” is specified as the final keyword candidate from the primary keyword candidate group, but a plurality of words may be specified as the final keyword candidate. For example, when there are a plurality of search result images whose similarity to the target image 38 is equal to or higher than the similarity threshold value, the primary keyword candidate used to search each search result image is specified as the final keyword candidate. In this case, a plurality of final keyword candidates are displayed on the UI unit 34 of the terminal device 12, and when the user uses the UI unit 34 to specify a final keyword candidate to be given from among the plurality of final keyword candidates, the final keyword candidate is specified by the user. The final keyword candidates thus created are associated with the target image 38. Of course, the terminal device 12 or the keyword candidate selection device 10 may automatically associate a plurality of final keyword candidates with the target image 38 as image attribute information.

  In addition, when an image is searched using a combination of a plurality of primary keyword candidates as a search keyword group, a plurality of search result images whose similarity with the target image 38 is equal to or higher than the similarity threshold value are used. The primary keyword candidate is identified as the final keyword candidate. For example, when the similarity between the image (search result image) ANDed using the primary keyword candidates “tofu” and “health” as the search keyword group is equal to or higher than the similarity threshold value, the primary keyword Both the candidates "tofu" and "health" are identified as final keyword candidates.

  Hereinafter, the processing by the keyword candidate selection device 10 will be described with reference to FIG. FIG. 8 shows a flowchart showing an example of the processing.

  First, the keyword candidate selection device 10 receives the data of the target image transmitted from the terminal device 12 (S01). The web page acquisition unit 18 acquires the data of one or a plurality of web pages including the similar image of the target image from each web server 14 (S02). The phrase extracting unit 20 extracts, for each web page, a phrase appearing on the web page as a primary keyword candidate (S03). As a result, the primary keyword candidate list including the primary keyword candidates is generated. Hereinafter, the processing is repeated until the processing for all the primary keyword candidates included in the primary keyword candidate list is completed. The image search unit 22 searches for an image using the primary keyword candidate as a search keyword (S04). The image obtained by this search is the search result image. The similarity calculation unit 24 calculates the similarity between the target image and the search result image (S05). When the similarity is equal to or higher than the similarity threshold (S06, Yes), the keyword candidate specifying unit 26 specifies the primary keyword candidate used for the search of the search result image as the final keyword candidate (S07). When the similarity is less than the similarity threshold (S06, No), the process is performed on the next primary keyword candidate. When the processing from step S04 to step S07 is completed for all the primary keyword candidates included in the primary keyword candidate list, the processing is completed.

  As described above, in the first embodiment, a primary keyword candidate is extracted by using a search for an image (similar image) similar to the target image, and an image (search result image) is searched using the primary keyword candidate. The primary keyword candidate used for the search of the search result image whose similarity to the target image is equal to or higher than the similarity threshold is specified as the final keyword candidate. By verifying the degree of similarity between the target image and the search result image, it is evaluated whether or not the primary keyword candidate is a phrase that appropriately expresses the content of the target image. That is, the suitability as the image attribute information for the target image of the primary keyword candidate is evaluated. The similarity with the target image is greater than or equal to the similarity threshold. By searching the image using the primary keyword candidates used to search the search result image, the similarity with the target image is greater than or equal to the similarity threshold. Therefore, the primary keyword candidates used in the search for the search result image whose similarity to the target image is equal to or higher than the similarity threshold are similar in similarity to the target image. It is predicted that the word (primary keyword candidate) more suitable for expressing the target image than the primary keyword candidate used for the search of the search result image that is less than the frequency threshold value. Therefore, by specifying the primary keyword candidate used for the search of the search result image whose similarity to the target image is equal to or higher than the similarity threshold value in the primary keyword candidate group as the final keyword candidate, Compared to the case where the group is directly specified as the final keyword candidate, a word (primary keyword candidate) more suitable for expressing the target image is specified as the final keyword candidate.

  For example, a web page for selling products, such as an Internet auction, may include an image that is not related to the target image. In addition, the words appearing on the web page and the images included in the web page do not always correlate. Therefore, in such a case, even if the web page including an image similar to the target image is searched and the word (primary keyword candidate) appearing on the web page is specified as the final keyword candidate, the target image is appropriately searched. The final keyword candidate to be expressed is not always specified. Explaining with reference to FIG. 6 and FIG. 7, the terms “limited company”, “AAA”, “store”, and “health” extracted as primary keyword candidates are terms not related to the target image 38 representing tofu, That is, it is not always a word suitable for expressing the target image 38. When such a phrase is specified as the final keyword candidate, a phrase that is not suitable for expressing the target image 38 may be specified as the final keyword candidate. On the other hand, according to the first embodiment, it is verified whether or not the primary keyword candidate is a phrase that appropriately expresses the content of the target image 38, and thus a phrase that is not suitable for expressing the target image 38. Are excluded from the final keyword candidates, and the words and phrases suitable for expressing the target image 38 are specified as the final keyword candidates.

[Second Embodiment]
The second embodiment of the present invention will be described below. FIG. 9 shows a keyword candidate selection device according to the second embodiment. The keyword candidate selection device 10A according to the second embodiment includes a synonym dictionary DB (database) 54 in addition to the configuration of the keyword candidate selection device 10 according to the first embodiment. The configuration other than the synonym dictionary DB 54 is the same as the configuration of the keyword candidate selection device 10 according to the first embodiment.

  The synonym dictionary DB 54 is a storage device such as a hard disk or a memory, and stores data indicating synonyms (synonyms) of phrases. In the synonym dictionary DB 54, the words and the synonyms are associated with each other. The data indicating the synonyms is created in advance and stored in the synonym dictionary DB 54, for example.

  The keyword candidate specifying unit 26 specifies the final keyword candidate as the image attribute information candidate, as in the first embodiment. Further, the keyword candidate specifying unit 26 specifies a word or phrase related to the final keyword candidate as a new final keyword candidate. The phrase related to the final keyword candidate is, for example, a synonym of the final keyword candidate. The keyword candidate specifying unit 26 searches the synonym dictionary DB 54 for a synonym of the final keyword candidate, and specifies the synonym obtained by the search as a new final keyword candidate.

  As described above, by specifying a synonym of the final keyword candidate as a new final keyword candidate, as compared with the case where the primary keyword candidate is directly specified as the final keyword candidate, the word more suitable for expressing the target image is the final word. It is specified as a keyword candidate.

[Third Embodiment]
The third embodiment of the present invention will be described below. The keyword candidate selection device according to the third embodiment has the same configuration as the keyword candidate selection device 10 according to the first embodiment or the keyword candidate selection device 10A according to the second embodiment.

  In the third embodiment, final keyword candidates for a plurality of target images are specified. For example, the web page acquisition unit 18 acquires, for each target image, data of one or a plurality of web pages including similar images of the target image from each web server 14. The word / phrase extraction unit 20 extracts a word / phrase (primary keyword candidate) from the web page for each target image. The image search unit 22 collectively searches for images (search result images) for common phrases (primary keyword candidates) in a group of phrases (primary keyword candidates) extracted for a plurality of target images. The similarity calculation unit 24 calculates the similarity between the target image and the search result image for each target image. The keyword candidate specifying unit 26 specifies, for each target image, a word or phrase (primary keyword candidate) used for searching a search result image whose similarity is equal to or higher than the similarity threshold as a final keyword candidate of the target image.

  Hereinafter, the third embodiment will be described in detail with reference to FIG. 10. FIG. 10 shows an example of the correspondence relationship between the target image, the primary keyword candidate, and the search result image.

  As an example, it is assumed that the data of the target images A and B are transmitted from the terminal device 12 to the keyword candidate selection device 10 and the final keyword candidates for the target images A and B are specified.

  The web page acquisition unit 18 acquires data of one or a plurality of web pages including the similar image of the target image A from each web server 14, and data of one or a plurality of web pages including the similar image of the target image B. From each web server 14.

  The word / phrase extracting unit 20 extracts words / phrases (primary keyword candidates) from the one or more web pages acquired for the target image A, and words / words (primary keyword candidates) from the one or more web pages acquired for the target image B. To extract. As shown in FIG. 10, for example, it is assumed that the words a and b are extracted as the primary keyword candidates for the target image A and the words a and c are extracted as the primary keyword candidates for the target image B. The word a is a primary keyword candidate common to the target images A and B.

  The image search unit 22 collectively searches for images of the common word a. For example, it is assumed that the search result image α has been searched for the word a. Since the words and phrases b and c are not primary keyword candidates that are common to the target images A and B, the image search unit 22 searches the images individually for the words and phrases b and c. For example, it is assumed that the search result image β is searched for the word b and the search result image γ is searched for the word c.

  The similarity calculation unit 24 determines the similarity between the search result image and the target image related to the phrase used to search the search result image (the target image used to acquire the web page from which the phrase was extracted). Calculate the degree. In the example shown in FIG. 10, the similarity calculation unit 24 determines the similarity between the target image A and the search result image α, the similarity between the target image A and the search result image β, the target image B and the search result. The similarity between the image α and the similarity between the target image B and the search result image γ are calculated.

  As in the first embodiment, the keyword candidate specifying unit 26 determines, for each target image, the word (primary keyword candidate) used for searching the search result image whose similarity is equal to or higher than the similarity threshold as the final target image. Specify as a keyword candidate. In the example shown in FIG. 10, since the similarity between the target image A and the search result image α is equal to or higher than the similarity threshold, the phrase a (primary keyword candidate) used for searching the search result image α is , Is specified as the final keyword candidate for the target image A. On the other hand, since the similarity between the target image A and the search result image β is less than the similarity threshold, the phrase b (primary keyword candidate) used for searching the search result image β is the final keyword for the target image A. Not identified as a candidate. Further, since the similarity between the target image B and the search result image γ is equal to or higher than the similarity threshold, the phrase c (primary keyword candidate) used for searching the search result image γ is the same as the target image B. It is specified as the final keyword candidate. On the other hand, since the similarity between the target image B and the search result image α is equal to or less than the similarity threshold, the phrase a (primary keyword candidate) used for searching the search result image α is the final keyword for the target image B. Not identified as a candidate.

  As described above, by searching the search result images collectively for the common primary keyword candidates, the search result images are searched for in comparison with the case where the search result images are individually searched for the individual primary keyword candidates. Efficiency is improved.

  Of course, in the third embodiment, as in the second embodiment, the synonyms of the final keyword candidates may be specified as new final keyword candidates.

[Fourth Embodiment]
Hereinafter, a fourth embodiment of the present invention will be described. FIG. 11 shows a keyword candidate selection device 10B according to the second exemplary embodiment. The keyword candidate selection device 10B according to the fourth embodiment includes a common keyword candidate identification unit 56 in addition to the configuration of the keyword candidate selection device 10 according to the first embodiment. The configuration other than the common keyword candidate identification unit 56 is the same as the configuration of the keyword candidate selection device 10 according to the first embodiment. Of course, the keyword candidate selection device 10B according to the fourth embodiment may include the synonym dictionary DB 54 according to the second embodiment.

  In the fourth embodiment, final keyword candidates for a plurality of target images are specified. The plurality of target images are classified into a plurality of groups having different tastes according to the impression (taste) of each target image. The classification may be performed in advance, or may be performed by the keyword candidate selection device 10B that has received data of a plurality of target images.

  The taste is determined, for example, according to a preference model that typifies the impression that a person feels for a certain object. For example, by quantifying the impression evoked by the target image, the affective score as the impression similarity can be obtained. The affective score is a value indicating the degree to which the target image contributes to arousing an impression (a value indicating the intensity of the impression). The affective score is obtained, for example, by an affective evaluation experiment according to typification 1.

  For example, the affective score for the target image is predetermined, the taste of the target image is predetermined based on the affective score, and the target image is associated with information indicating the taste. Examples of tastes include, for example, "warm impression", "cold impression", "hard impression", "soft impression", and the like. More specifically, examples of the taste include “wild”, “natural”, “romantic”, “dynamic”, “pretty”, and the like. Each taste is digitized in advance as an affective score, and the affective score for each taste, that is, the affective score representing each taste is determined in advance. The taste corresponding to the affective score of the target image is determined as the taste of the target image.

  Each target image is pre-classified according to taste. For example, a plurality of target images having the same or similar tastes to each other are classified into the same group, and a plurality of target images having different tastes (non-identical and non-similar tastes) are classified into different groups. .. Note that the plurality of tastes that are similar to each other are, for example, a plurality of tastes in which the difference in the affective score for each taste is included in a preset numerical range.

  The control unit 28 of the keyword candidate selection device 10B may specify the taste of the target image by calculating the affective score of the received target image and specifying the taste corresponding to the affective score. In this case, the control unit 28 may classify each target image into the same or different groups according to the taste of each target image.

  In the fourth embodiment, for example, the web page acquisition unit 18 acquires, for each target image, data of one or a plurality of web pages including similar images of the target image from each web server 14. The word / phrase extraction unit 20 extracts a word / phrase (primary keyword candidate) from the web page for each target image. The image search unit 22 collectively searches images (search result images) for common phrases (primary keyword candidates) in the phrase groups (primary keyword candidate groups) extracted for the target image groups belonging to the same group. .. Of course, the image search unit 22 may search an image for each word or phrase, instead of collectively searching the images for common words and phrases. The similarity calculation unit 24 calculates the similarity between the target image and the search result image for each target image. The keyword candidate specifying unit 26 specifies, for each target image, a word or phrase (primary keyword candidate) used for searching a search result image whose similarity is equal to or higher than the similarity threshold as a final keyword candidate of the target image.

  In the fourth embodiment, the common keyword candidate specifying unit 56 further sets, for each group, a final keyword candidate common to target image groups belonging to the same group as a common keyword candidate for target image groups belonging to the same group. Specify as. The common keyword candidate corresponds to an example of the common attribute information candidate.

  Hereinafter, the fourth embodiment will be described in detail with reference to FIGS. 12 and 13. FIG. 12 shows an example of target images and groups. FIG. 13 shows an example of the correspondence relationship between the target image, the primary keyword candidate, and the search result image.

  As an example, it is assumed that the data of the target images A, B, C, D are transmitted from the terminal device 12 to the keyword candidate selection device 10B, and the final keyword candidates for the target images A, B, C, D are specified.

  The target images A, B, C, and D are classified into the same or different groups according to the taste of each target image (for example, information indicating the taste associated with each target image). In the example shown in FIG. 12, since the tastes of the target images A and B are the same or similar, the target images A and B are classified into the same group X, and the tastes of the target images C and D are different. The target images C and D are classified into the same group Y because they are the same or similar. This classification may be performed in advance or may be performed by the control unit 28 of the keyword candidate selection device 10B.

  Hereinafter, the processing according to the fourth embodiment will be described in detail with reference to FIG. 13.

  The web page acquisition unit 18 acquires, for each of the target images A, B, C, and D, data of one or a plurality of web pages including similar images from each web server 14. That is, the web page acquisition unit 18 acquires data of one or a plurality of web pages including the similar image of the target image A from each web server 14, and one or a plurality of web pages including the similar image of the target image B. Of the target image C is acquired from each web server 14, the data of one or more web pages including the similar image of the target image C is acquired from each web server 14, and the one or more of the similar images of the target image D are included. The web page data is acquired from each web server 14.

  The word / phrase extracting unit 20 extracts a word / phrase (primary keyword candidate) from one or a plurality of web pages acquired for each of the target images A, B, C, and D. That is, the word / phrase extracting unit 20 extracts words / phrases (primary keyword candidates) from the one or more web pages acquired for the target image A, and extracts words / words (primary keywords) from the one or more web pages acquired for the target image B. Candidates), and extracts words (primary keyword candidates) from the one or more web pages acquired for the target image C, and extracts words (primary keyword candidates) from the one or more web pages acquired for the target image D. To extract. As shown in FIG. 13, as an example, for group X, words a, b, and c are extracted as primary keyword candidates for target image A, and words a, b, and d are extracted as primary keyword candidates for target image B. It is assumed that The words a and b are primary keyword candidates common to the target images A and B. Although the description of the target images C and D belonging to the group Y is omitted, as with the group X, words and phrases as primary keyword candidates are extracted.

  The image search unit 22 collectively searches images for common primary keyword candidates for each group. In group X, the words a and b are primary keyword candidates that are common to the target images A and B, so the image search unit 22 searches the images collectively for the common words a and similarly, for the common words b. Search images collectively. It is assumed that the search result image α is searched for the phrase a and the search result image β is searched for the phrase b. Since the words and phrases c and d are not primary keyword candidates that are common to the target images A and B, the image search unit 22 searches the images individually for the words and phrases c and d. For example, it is assumed that the search result image γ is searched for the word c and the search result image δ is searched for the word d. As with the group X, the images of the group Y are searched using the primary keyword candidates.

  The similarity calculation unit 24 determines the similarity between the search result image and the target image related to the phrase used to search the search result image (the target image used to acquire the web page from which the phrase was extracted). Calculate the degree. In the example illustrated in FIG. 13, for the group X, the similarity calculation unit 24 determines the similarity between the target image A and the search result image α, the similarity between the target image A and the search result image β, and the target image. Similarity between A and search result image γ, similarity between target image B and search result image α, similarity between target image B and search result image β, and target image B and search The degree of similarity with the result image δ is calculated. Similar to the group X, the similarity between the target image and the search result image is calculated for the group Y.

  As in the first embodiment, the keyword candidate specifying unit 26 determines, for each target image, the word (primary keyword candidate) used for searching the search result image whose similarity is equal to or higher than the similarity threshold as the final target image. Specify as a keyword candidate. In the example shown in FIG. 13, since the similarity between the target image A and the search result image α is equal to or higher than the similarity threshold, the phrase a (primary keyword candidate) used for searching the search result image α is , Is specified as the final keyword candidate for the target image A. Similarly, since the similarity between the target image A and the search result image β is equal to or higher than the similarity threshold, the phrase b (primary keyword candidate) used for searching the search result image β is the target image A. Is identified as the final keyword candidate for. On the other hand, since the similarity between the target image A and the search result image γ is less than the similarity threshold, the phrase c (primary keyword candidate) used for searching the search result image γ is the final keyword for the target image A. Not identified as a candidate. Further, since the similarity between the target image B and the search result image β is equal to or higher than the similarity threshold, the phrase b (primary keyword candidate) used for searching the search result image β is the same as the target image B. It is specified as the final keyword candidate. On the other hand, since the similarity between the target image B and the search result image α is less than the similarity threshold, the phrase a used for searching the search result image α is not specified as the final keyword candidate for the target image B. Similarly, since the similarity between the target image B and the search result image δ is less than the similarity threshold, the phrase d used for searching the search result image δ is not specified as the final keyword candidate for the target image B. .. As with the group X, the final keyword candidates for the group Y are specified for each target image.

  Of course, also in the fourth embodiment, similar to the second embodiment, a synonym of the final keyword candidate may be specified as a new final keyword candidate.

  The common keyword candidate specifying unit 56 specifies the final keyword candidate common to the target images A and B belonging to the group X as the common keyword candidate for the target images A and B belonging to the group X. In the example shown in FIG. 13, the word b as the final keyword candidate is the final keyword candidate common to the target images A and B. Therefore, the phrase b is specified as a common keyword candidate for the group X. Similar to group X, common keyword candidates are specified for group Y as well. Of course, if there is no final keyword candidate common to the target image groups belonging to the same group, no common keyword candidate for that group is specified.

  The final keyword candidate data for each target image and the common keyword candidate data for each group are transmitted from the keyword candidate selecting device 10B to the terminal device 12, and the final keyword candidate and the common keyword candidate are the UI of the terminal device 12. It is displayed on the section 34. When the user uses the UI unit 34 to specify a final keyword candidate and a target image to which the final keyword candidate is given, the final keyword candidate specified by the user is associated with the target image specified by the user. .. Further, when the user uses the UI unit 34 to specify a common keyword candidate and a group to which the common keyword candidate is given, the common keyword candidate specified by the user is associated with the group specified by the user. .. Of course, the designated common keyword candidate may be associated with the target image belonging to the designated group.

  In the terminal device 12 or the keyword candidate selection device 10B, the final keyword candidate may be associated with the target image corresponding to the final keyword candidate, or the common keyword candidate may be a group corresponding to the common keyword candidate or the group thereof. It may be associated with the target image belonging to the group. In the example shown in FIG. 13, the phrases a and b may be associated with the target image A as final keyword candidates, and the phrase b may be associated with the target image B as final keyword candidates. Further, the phrase b may be associated with the group X and the target images A and B as common keyword candidates. Similarly to the group X, for the group Y, the final keyword candidate may be automatically associated with the target image, or the common keyword candidate may be automatically associated with the group Y.

  As described above, in the fourth embodiment, the final keyword candidate common to the target image groups belonging to the same group is specified as the common keyword candidate for the group. As a result, compared to the case where the final keyword candidates that are not common to the target image groups that belong to the same group are specified as the common keyword candidates for the group, the phrase (final keyword candidate) that is more suitable for expressing the group is the common keyword. Identified as a candidate.

  Each of the above keyword candidate selection devices 10, 10A, 10B and the terminal device 12 is realized by the cooperation of hardware resources and software, for example. Specifically, each of the keyword candidate selection devices 10, 10A, 10B and the terminal device 12 includes one or more processors such as a CPU (not shown). The processor reads and executes a program stored in a storage device (not shown), whereby the functions of the respective units of the keyword candidate selection devices 10, 10A, 10B and the terminal device 12 are realized. The program is stored in the storage device via a recording medium such as a CD or a DVD, or via a communication path such as a network. Alternatively, the respective units of the keyword candidate selection device 10, 10A, 10B and the terminal device 12 may be realized by hardware resources such as a processor and an electronic circuit. A device such as a memory may be used in the realization thereof. As another example, each part of the keyword candidate selection devices 10, 10A, 10B and the terminal device 12 may be realized by a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), or the like.

  10, 10A, 10B keyword candidate selection device, 12 terminal device, 14 web server, 16 communication unit, 18 web page acquisition unit, 20 word extraction unit, 22 image search unit, 24 similarity calculation unit, 26 keyword candidate specifying unit, 28 control unit, 54 synonym dictionary DB, 56 common keyword candidate specifying unit.

Claims (8)

Extraction means for extracting a word or phrase that appears in the extraction target data including the first image similar to the target image;
An image search means for searching the second image using the extracted words and phrases;
First specifying means for specifying a word or phrase used for searching for a second image similar to the target image as an image attribute information candidate of the target image;
Information processing device having a. The first specifying unit further specifies a word or phrase related to the image attribute information candidate as a new image attribute information candidate of the target image,
The information processing apparatus according to claim 1, wherein: The phrase related to the image attribute information candidate is a synonym of the image attribute information candidate extracted from the synonym dictionary information defining a synonym group,
The information processing apparatus according to claim 2, wherein: When there are a plurality of target images, the extracting means extracts a phrase for each target image,
The image search means collectively searches the second image for common words / phrases in the word / phrase group extracted for the plurality of target images.
The information processing apparatus according to any one of claims 1 to 3, characterized in that: The plurality of target images are classified into a plurality of groups having different impressions according to the impression of each target image,
The image search means collectively searches the second image for common words / phrases among the word / phrase groups extracted for the target image groups belonging to the same group for each group,
The information processing device is
For each of the groups, the image attribute information candidates identified by using the second image, and the image attribute information candidates that are common to the target image groups that belong to the same group belong to the same group. Further comprising second specifying means for specifying as a common attribute information candidate for the target image group,
The information processing apparatus according to claim 4, wherein: The first specifying unit specifies, as the image attribute information candidate of the target image, a phrase used for searching for the second image having a similarity with the target image equal to or greater than a preset threshold value. ,
The information processing apparatus according to any one of claims 1 to 5, characterized in that: Further comprising control means for displaying the image attribute information candidates on a display means,
The information processing apparatus according to any one of claims 1 to 6, characterized in that. Computer,
Extraction means for extracting a word or phrase that appears in the extraction target data including the first image similar to the target image,
An image search means for searching the second image using the extracted words and phrases;
Specifying means for specifying a word or phrase used for searching for a second image similar to the target image as a candidate for image attribute information of the target image;
Program to function as.

Images