JP2007164692A - Image output device, image output method, and image output program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To automatically insert and display a proper image indicating the content of a keyword in a passage in a position desired by a user. <P>SOLUTION: The image output device comprises: an image storage part for storing images by associating them with keywords indicating the content of the images; an image placement position determination part for determining an image placement position where images are placed in an output region where a text is outputted; a keyword extraction part for extracting keywords from the text; an image extraction part for extracting images stored in the image storage part, which are associated with the extracted keywords; an image selection part which selects images stored in the image storage part from the extracted images, which are associated with more kinds of keywords inputted in the position closer to the image placement position determined by the image placement position determination part; and an image output part for placing the selected images in the image placement position and outputting them together with the inputted text. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an image output apparatus, an image output method, and an image output program. In particular, the present invention relates to an image output apparatus, an image output method, and an image output program for outputting an image related to a sentence together with the input sentence.

There has been proposed an apparatus for facilitating a search for an image to be inserted when an image is inserted into a sentence (see, for example, Patent Document 1). In the apparatus according to the invention described in Patent Document 1, a part of a sentence input by a user is selected, the selected sentence is analyzed by morphological analysis or the like, and a word contributing to the specification of an image is extracted. Subsequently, an image stored in advance by the device in association with a word included in the sentence is searched. Then, the user lays out the searched image in the sentence.
JP-A-6-282539

  However, in the invention described in Patent Document 1, a plurality of images stored in the apparatus are extracted in association with words included in a sentence input by the user, and the user selects a plurality of images extracted from the extracted plurality of images. The user selects the desired image. Therefore, since the user spends time selecting an image while inputting a sentence, the user's thought may be interrupted.

  Accordingly, an object of the present invention is to provide an image output apparatus, an image output method, and an image output program that can solve the above-described problems. This object is achieved by a combination of features described in the independent claims. The dependent claims define further advantageous specific examples of the present invention.

  In order to solve the above-described problem, in the first embodiment of the present invention, an image output apparatus that outputs an image related to a sentence together with the input sentence, and corresponds to at least one keyword indicating the content of the image Then, an image storage unit for storing an image, an image arrangement position determination unit for determining an image arrangement position that is a position where an image is to be arranged in an output region where the input sentence is output, and an input sentence A keyword extraction unit for extracting a keyword stored in the image storage unit; an image extraction unit for extracting an image stored in the image storage unit in association with at least one of the keywords extracted by the keyword extraction unit; Corresponds to more types of keywords input at positions closer to the image arrangement position determined by the image arrangement position determination unit among the images extracted by the image extraction unit The image selection unit that selects the image stored in the image storage unit, and the image selected by the image selection unit are arranged at the image arrangement position determined by the image arrangement position determination unit and output together with the input text An image output unit.

  In addition, among the keywords extracted by the keyword extraction unit, a position weight determination unit that gives greater weight to a keyword that is input at a position closer to the image arrangement position determined by the image arrangement position determination unit, and an image extraction unit extracted A weight sum calculating unit that calculates a total value of keyword weights weighted by the position weight determining unit for each image, and the image selecting unit includes a weight sum calculating unit out of the images extracted by the image extracting unit. You may select the image with the largest total value of the calculated keyword weight. Further, the input sentence is divided into a plurality of ranges, and among the keywords extracted by the keyword extraction unit, the keywords input in a range closer to the image arrangement position determined by the image arrangement position determination unit are weighted more heavily. A position weight determination unit; and a weight total calculation unit that calculates a total value of keyword weights weighted by the position weight determination unit for each image extracted by the image extraction unit. The image selection unit includes: Among the extracted images, an image having the largest total value of the keyword weights calculated by the weight sum calculation unit may be selected.

  The position weighting determination unit may weight the keyword extracted by the keyword extraction unit input in a row closer to the image arrangement position determined by the image arrangement position determination unit. In addition, a sentence storage unit that stores sentences input by the user in the past, a keyword frequency calculation unit that calculates the number of keywords included in the sentence stored in the sentence storage unit for each keyword, and a keyword frequency calculation unit And a keyword weighting determination unit that assigns a smaller weight to a keyword having a larger number of keywords calculated by the image, and the weight sum calculation unit includes a position weight determination unit and a keyword weighting determination for each image extracted by the image extraction unit. The image selection unit selects an image having the smallest keyword weight total value calculated by the weight total calculation unit from the images extracted by the image extraction unit. May be.

  The keyword extraction unit further includes a sentence range determination unit that determines a sentence input within a predetermined range from the image arrangement position determined by the image arrangement position determination unit as a sentence from which the keyword extraction unit extracts a keyword. May extract a keyword stored in the image storage unit from the range of the sentence determined by the sentence range determination unit. The image extraction unit further includes a keyword selection control unit that allows the user to select a keyword stored in the image storage unit from a text range excluding the text range determined by the text range determination unit. The image stored in the image storage unit may be extracted in association with at least one of the extracted keyword and the keyword selected by the user by the keyword selection control unit.

  According to a second aspect of the present invention, there is provided an image output method for outputting an image related to a sentence together with an inputted sentence, wherein the image is associated with at least one keyword indicating the content of the image. An image storage stage for storing in the storage unit, an image placement position determination stage for determining an image placement position, which is a position where an image should be placed in an output area where the inputted sentence is output, and image storage from the inputted sentence A keyword extraction stage for extracting a keyword stored in the section, an image extraction stage for extracting an image stored in the image storage section in association with at least one of the keywords extracted in the keyword extraction stage, and an image Among the images extracted in the extraction stage, more types of keywords input at positions closer to the image layout position determined in the image layout position determination stage An image selection stage for selecting an image stored in the image storage unit in association with each other, and an image selected by the image selection stage is arranged at the image arrangement position determined by the image arrangement position determination stage, together with the inputted text And an image output stage for outputting.

  According to a third aspect of the present invention, there is provided an image output program for an image output apparatus that outputs an image related to a sentence together with an input sentence, and the image output apparatus includes at least one image content. An image storage unit that stores images in association with one keyword, an image placement position determination unit that determines an image placement position that is a position in which an image should be placed in an output region in which input text is output, and an input A keyword extraction unit that extracts a keyword stored in the image storage unit from the written text and an image stored in the image storage unit in association with at least one of the keywords extracted by the keyword extraction unit Among the images extracted by the image extraction unit and the image extraction unit, more types input at positions closer to the image arrangement position determined by the image arrangement position determination unit An image selection unit that selects an image stored in the image storage unit in association with a keyword, and an image selected by the image selection unit is arranged at the image arrangement position determined by the image arrangement position determination unit and input It is made to function as an image output part which outputs with a text.

  The above summary of the invention does not enumerate all the necessary features of the present invention, and sub-combinations of these feature groups can also be the invention.

  According to the present invention, an image stored in the image output device is automatically selected in association with a larger number of types of keywords input at a position closer to a region where an image is inserted into a sentence, and the region is selected. Since the selected image can be automatically inserted, when the user inputs a sentence, the image suitable for the image recalled by the user during the sentence input, the sentence without interrupting the user's thought The user can automatically insert and display the image at a position where the user desires to insert the image.

  Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the scope of claims, and all combinations of features described in the embodiments are included. It is not necessarily essential for the solution of the invention.

  FIG. 1 shows an outline of an output screen 900 when an image output apparatus 10 according to an embodiment of the present invention is applied to a blog. The image output device 10 may be a PC, a portable information terminal, or the like that includes a display device such as a monitor. The image output device 10 may be a device that outputs a blog or the like that records a sentence or the like together with a URL of a web page on a website on the Internet to a display device. The image output apparatus 10 according to the present embodiment automatically selects an image stored in the image output apparatus 10 in association with a larger number of types of keywords input at positions closer to the area where the image is to be inserted into the sentence. Then, by automatically inserting the selected image into the area, when the user inputs a sentence, the user's thought is interrupted with an image appropriate for the image recalled by the user during the sentence input. The purpose is to automatically insert and display the image in a position where the user desires to insert an image.

  On the output screen 900, the user inputs text into the image output device 10. For example, the user inputs a sentence to the image output device 10 on the output screen 900 as in the case of inputting a sentence to a blog. Then, for example, the image output apparatus 10 inputs the keyword closest to the image arrangement position 800 among the keywords indicating the contents of a plurality of images included in the text input within a predetermined range from the image arrangement position 800. The image stored in association with the keyword 902 is automatically extracted. Then, the image output apparatus 10 inserts the extracted image at the image arrangement position 800 and displays the image on the output screen 900 together with the text. Similarly, the image output apparatus 10 is input at a distance closest to the image arrangement position 802 among keywords indicating the contents of a plurality of images included in a sentence input within a predetermined range from the image arrangement position 802. The image stored in association with the keyword 904 is automatically extracted. Then, the image output device 10 inserts the extracted image at the image arrangement position 802 and displays the image on the output screen 900 together with the text.

  The image output apparatus 10 according to the present embodiment automatically stores an image stored in the image output apparatus 10 in association with a keyword input at a position closest to the image arrangement position, which is an area in which an image is inserted into a sentence. Select Then, the image output device 10 inserts the selected image into the image arrangement position and displays it. Therefore, when the user inputs a sentence, an image appropriate for the image recalled by the user during the sentence input is displayed. The user can automatically insert and display the image at a position where the user desires to insert an image without interrupting the thought.

  FIG. 2 shows an example of a functional configuration of the image output apparatus 10 according to the present embodiment. The image output device 10 includes a text input unit 100, an image input unit 102, an image arrangement position input control unit 104, a keyword selection control unit 106, an image storage unit 110, a text storage unit 112, an image arrangement position determination unit 120, and a keyword extraction unit. 130, an image extraction unit 140, a total weight calculation unit 150, a position weight determination unit 160, an image selection unit 170, a keyword frequency calculation unit 180, a keyword weight determination unit 182, a sentence range determination unit 184, and an image output unit 190.

  The text input unit 100 inputs text to the image output device 10. The text input unit 100 supplies the text input by the user to the keyword extraction unit 130 and the image output unit 190. The text input unit 100 supplies the position where the text is input to the image arrangement position determination unit 120 and the text range determination unit 184. Note that the position where the text is input may be the position where the text input in the output area where the image output unit 190 outputs the text and the image is the position where the text is input. The image input unit 102 inputs an image to the image output device 10. The image input unit 102 supplies the input image to the image storage unit 110. The image storage unit 110 stores an image in association with at least one keyword indicating the content of the image. The image storage unit 110 supplies the stored image to the image extraction unit 140 based on the control of the image extraction unit 140.

  The image arrangement position input control unit 104 causes the user to input an image arrangement position that is a position where an image is to be arranged in an output area where the input text is output. Specifically, the image arrangement position input control unit 104 causes the user to input a position where an image should be arranged in the output area. For example, the image arrangement position input control unit 104 causes the user to input a position where an image should be arranged by causing the user to select a position where the image is desired to be arranged. Further, the image arrangement position input control unit 104 presents the user with a plurality of layouts in which the positions where the images are to be arranged are predetermined in the output area, and requests the user from the plurality of presented layouts. You may select the layout. Note that the image arrangement position input control unit 104 may cause the user to input the image arrangement position before the user completes the input of the sentence in the case where the user is inputting the sentence. Further, the image arrangement position input control unit 104 may cause the user to input the image arrangement position after the user completes the input of the text. In such a case, the image arrangement position input control unit 104 may cause the user to input the position where the image should be arranged and the size of the area where the image should be arranged. The image arrangement position input control unit 104 supplies the image arrangement position input by the user to the image arrangement position determination unit 120.

  The image arrangement position determination unit 120 determines an image arrangement position that is a position where an image is to be arranged in an output region where an input sentence is output. Specifically, the image arrangement position determination unit 120 receives information about the position where the text input in the output area is arranged from the text input unit 100. Then, the image arrangement position determination unit 120 may calculate a position where no text is arranged in the output area, and determine the calculated position as the image arrangement position. Further, when the image arrangement position determination unit 120 receives the image arrangement position input by the user from the image arrangement position input control unit 104, the image arrangement position input by the user is output as an input sentence. You may determine as an image arrangement position which is a position where an image should be arrange | positioned in an area | region. The image arrangement position determination unit 120 supplies the determined image arrangement position to the position weighting determination unit 160, the sentence range determination unit 184, and the image output unit 190.

  The keyword extraction unit 130 extracts keywords stored in the image storage unit 110 from the input text. Specifically, the keyword extraction unit 130 extracts keywords stored in the image storage unit 110 from the text received from the text input unit 100 using a processing method such as natural language processing. The keyword extraction unit 130 also extracts information related to the keyword position, which is the position where the extracted keyword is arranged in the output area, in association with the keyword. Further, the keyword extraction unit 130 may divide the input sentence into a plurality of ranges and extract keywords from the divided ranges. For example, the keyword extraction unit 130 may divide the input sentence into ranges for each line and each paragraph, and extract a keyword from the line or paragraph. The keyword extraction unit 130 supplies the extracted keyword to the image extraction unit 140. The keyword extraction unit 130 also supplies the image selection unit 170 with information regarding the extracted keyword and the position of the extracted keyword. Further, the keyword extraction unit 130 supplies information regarding the position of the extracted keyword to the position weighting determination unit 160.

  The text range determination unit 184 determines a text input within a predetermined range from the image layout position received from the image layout position determination unit 120 as a text from which the keyword extraction unit 130 extracts a keyword. Specifically, the sentence range determination unit 184 receives from the sentence input unit 100 the position occupied by the input sentence in the output area, and receives the image arrangement position from the image arrangement position determination unit 120. Then, the sentence range determination unit 184 calculates the range of the sentence input within a predetermined range from the image arrangement position from the position in the output area of the input sentence received from the sentence input unit 100, The keyword extraction part 130 determines as a text which extracts a keyword. It should be noted that the range including the text for extracting the keyword determined by the text range determination unit 184 may be determined based on a predetermined distance from the image arrangement position.

  Specifically, the sentence range determination unit 184 sets a predetermined number of lines among lines input within a predetermined range from the image layout position as a sentence range including a sentence from which a keyword is extracted. You may decide. For example, the sentence range determination unit 184 sets the number of lines such as five lines or ten lines from the image arrangement position, and determines a sentence including a plurality of lines as a sentence range from which the keyword extraction unit 130 extracts keywords. It's okay. Note that the range of sentences from which keywords are extracted, which is set in advance by the sentence range determination unit 184, may be a range for each paragraph. The sentence range determination unit 184 supplies the position that the determined sentence range occupies in the output area to the keyword extraction unit 130 and the keyword selection control unit 106. In such a case, the keyword extracting unit 130 that has received the text range from which the keyword is extracted from the text range determining unit 184 extracts the keyword stored in the image storage unit 110 from the range.

  The keyword selection control unit 106 causes the user to select the keyword stored in the image storage unit 110 from the text range excluding the text range received from the text range determination unit 184. Note that the keyword selection control unit 106 may cause the user to select a plurality of keywords. The keyword selection control unit 106 supplies the keyword selected by the user to the image extraction unit 140. The image extraction unit 140 works with the image storage unit 110 to extract the image stored in the image storage unit 110 in association with at least one of the keywords extracted by the keyword extraction unit 130 from the image storage unit 110. . In addition, the image extraction unit 140 works on the image storage unit 110 with an image stored in the image storage unit 110 in association with at least one of the keywords received from the keyword selection control unit 106, thereby causing the image storage unit 110. Extract from The image extraction unit 140 supplies the extracted image to the image selection unit 170. In addition, the image extraction unit 140 supplies the keyword stored in the image storage unit 110 in association with the image to the weight sum calculation unit 150.

  The position weighting determination unit 160 weights a keyword input at a position closer to the image arrangement position received from the image arrangement position determination unit 120 out of the information related to the keyword position received from the keyword extraction unit 130. Specifically, the position weighting determination unit 160 uses the keyword position received from the keyword extraction unit 130 and the image layout position received from the image layout position determination unit 120 for each keyword extracted by the keyword extraction unit 130. The distance from the image layout position to the position where the keyword is input to the output area is calculated. Then, the position weighting determination unit 160 gives a greater weight to the keyword with the shorter calculated distance. For example, the position weight determination unit 160 may calculate the reciprocal of the calculated distance and use the calculated value as the keyword weight. In addition, the position weighting determination unit 160 divides the input sentence into a plurality of ranges, and among the keywords extracted by the keyword extraction unit 130 from the divided ranges, the position weighting determination unit 160 uses the image placement position received from the image placement position determination unit 120. You may give more weighting to the keyword input in the near range. Here, text lines and paragraphs are examples of ranges. Note that the position weight determining unit 160 may weight the keywords included in the same line or the same paragraph with the same weight. The position weight determination unit 160 supplies the determined weight to the weight total calculation unit 150 in association with the keyword.

  The sentence storage unit 112 stores sentences that the user has input in the past. The text storage unit 112 may further store a keyword indicating the content of the image included in the text, and further store the weight of the keyword in association with the keyword. The text storage unit 112 supplies keywords included in the text to the keyword frequency calculation unit 180 based on the control of the keyword frequency calculation unit 180. The keyword frequency calculation unit 180 calculates the number of keywords included in the text stored in the text storage unit 112 for each keyword. Specifically, the keyword frequency calculation unit 180 works on the text storage unit 112 to extract keywords included in the text stored in the text storage unit 112 using a processing method such as natural language processing. Then, the keyword frequency calculation unit 180 calculates the number of keywords for each extracted keyword. The keyword frequency calculation unit 180 supplies the calculated number of keywords for each keyword to the keyword weighting determination unit 182.

  The keyword weighting determination unit 182 gives a smaller weight to a keyword having a larger number of keywords calculated by the keyword frequency calculation unit 180. Specifically, the keyword weighting determination unit 182 may calculate the reciprocal of the number of keywords calculated by the keyword frequency calculation unit 180 and associate the reciprocal of the calculated number of keywords with the keyword as a weight. Thereby, the keyword weighting determination unit 182 can apply a smaller weight to a keyword having a larger number of keywords. The keyword weighting determination unit 182 may arrange the number of keywords in descending or ascending order, classify the number of aligned keywords into a plurality of ranges, and set a predetermined coefficient for each classified range. Then, the keyword weighting determination unit 182 may calculate the weight by multiplying the number of keywords calculated by the keyword frequency calculation unit 180 by a set coefficient.

  For example, the keyword weighting determining unit 182 classifies the number of keywords into a plurality of ranges such as 1 to 5, 6 to 10, 11 to 50, 51 or more. Then, the keyword weighting determination unit 182 may set a coefficient for which a smaller value is calculated for each range when the number of keywords is multiplied. For example, the keyword weighting determination unit 182 may use 0.1 for a range of 1 to 5 keywords, 0.2 for a range of 6 to 10, and 2 for a range of 51 or more. A coefficient such as .0 may be set. Subsequently, the keyword weighting determination unit 182 may calculate the reciprocal of the value obtained by multiplying the number of keywords by the set coefficient, and use the calculated value as the keyword weight. Accordingly, the keyword weighting determination unit 182 calculates the inverse of the value calculated by multiplying the set coefficient by the number of keywords, thereby weighting a smaller weight in association with a keyword having a larger number of keywords. be able to. The keyword weight determination unit 182 supplies the weight weighted in association with the keyword to the weight sum calculation unit 150. The keyword weighting determination unit 182 may store the keyword weights in the sentence storage unit 112 in association with the keywords.

  The weight total calculation unit 150 calculates the total value of the keyword weights determined by the position weight determination unit 160 for each image extracted by the image extraction unit 140. Specifically, the weight sum calculation unit 150 receives the keyword weight stored in the image storage unit 110 in association with the image extracted by the image extraction unit 140 from the position weight determination unit 160. Then, the total weight calculation unit 150 calculates the total value of the weights of the keywords associated with the images for each image. Further, the weight total calculation unit 150 may calculate the total value of the keyword weights weighted by the keyword weighting determination unit 182 for each image extracted by the image extraction unit 140. The weight total calculation unit 150 supplies the calculated keyword weight total value for each image to the image selection unit 170.

  The image selection unit 170 associates the image storage unit 110 with more types of keywords input at positions closer to the image arrangement position determined by the image arrangement position determination unit 120 among the images extracted by the image extraction unit 140. Select the image stored by. Specifically, the image selection unit 170 compares the keyword weight total values for each image received from the weight total calculation unit 150 among the images extracted by the image extraction unit 140, and has the largest total value. You may select an image. In addition, when the total weight calculation unit 150 calculates the total value of the keyword weights weighted by the keyword weighting determination unit 182, the image selection unit 170 includes the image extracted by the image extraction unit 140. You may select the image with the smallest total value of the weight of the keyword which the weight total calculation part 150 calculated. The image selection unit 170 supplies the selected image to the image output unit 190.

  The image output unit 190 arranges the image received from the image selection unit 170 at the image arrangement position determined by the image arrangement position determination unit 120 and outputs it together with the text received from the text input unit 100. Specifically, the image output unit 190 arranges the image selected by the image selection unit 170 at the image arrangement position received from the image arrangement position determination unit 120. Then, the image output unit 190 outputs an image together with the text to a display device such as a monitor. Specifically, when the user inputs a sentence on a blog or the like, the image output unit 190 arranges the image selected in the above description using a keyword included in the sentence input by the user at the image arrangement position. , Output with text.

  The image output apparatus 10 according to the present embodiment extracts an image associated with a keyword included in the input sentence. Then, a greater weight is given to the keyword input at a position closer to the image arrangement position, and the total value of the weight of the keyword associated with the image is calculated for each image. Subsequently, since the image having the maximum keyword weight total value can be selected and the selected image can be output, the user only has to input a sentence and close to the position where the user wants to insert the image. An image that appropriately represents the content of the input keyword can be automatically inserted and displayed.

  In addition, the image output apparatus 10 according to the present embodiment is based on the number of keywords included in a sentence input by the user in the past, and a keyword that includes a large number of sentences is more than a keyword that includes a small number of sentences. , Weight smaller weights. Subsequently, the total value of the weights of the keywords associated with the images is calculated for each image. Since the image having the smallest keyword weight total value can be selected from images associated with more types of keywords input closer to the image arrangement position, the user rarely uses them. An image associated with a keyword can be automatically selected and output. As a result, the image output device 10 is not familiar to the user, and can automatically select and output an image that feels fresh and feels unusual, so that the user does not get bored and is unexpected for the user. You can create sentences with high-quality images inserted.

  FIG. 3 shows an example of the data structure of the image storage unit 110 according to the present embodiment. The image storage unit 110 stores an image in association with a keyword indicating the content of the image. Note that the image storage unit 110 may store images in association with a plurality of keywords. The image stored in the image storage unit 110 may be an image received by the image input unit 102 via a network such as the Internet, a captured image captured by the user, and an image created by the user. The keyword indicating the content of the image is a keyword determined based on a keyword indicating the object name of the object included in the image, a keyword indicating the background included in the image, and incidental information attached to the image. Good. Further, when the image is a captured image, the incidental information includes the imaging date and time, the imaging location, the imaging mode (such as the close-up mode, portrait mode, and night view mode), and the imaging conditions (brightness, saturation, And in-focus distance, etc.). On the other hand, when the image is an image created by the user, the accompanying information may be a keyword indicating the file name of the image and the content of the image attached by the user to the image.

  For example, if the image 300 is an image representing a city of Odawara, the image storage unit 110 stores the image 300 in association with the keyword “Odawara”. When the image 310 is an image representing Odawara Castle, the image storage unit 110 may store the image 310 in association with keywords “Odawara” and “castle”. Furthermore, for example, when the image 320 is a captured image of a white cat captured in the daytime, the image storage unit 110 stores the image 320 in association with the keywords “white cat” and “daytime”. Good.

  FIG. 4 shows an example of output by the image output unit 190 according to the present embodiment. The image arrangement position determination unit 120 determines an image arrangement position 810 that is an area in which an image is to be arranged in an output area 910 where the image output unit 190 outputs text and an image. Subsequently, information regarding the position of the image arrangement position 810 determined by the image arrangement position determination unit 120 is supplied to the text range determination unit 184. Then, the text range determination unit 184 that has received information regarding the position of the image arrangement position 810 determines a text range from which the keyword extraction unit 130 should extract keywords. For example, the sentence range determination unit 184 determines the sentence range 950. Then, the keyword extraction unit 130 extracts keywords from the sentence range 950. Subsequently, the image selection unit 170 is a keyword included in the text range 950 as an image to be arranged at the image arrangement position 810, and is associated with more types of keywords at a position closer to the image arrangement position 810. Select an image. For example, consider a case where the keyword extraction unit 130 extracts a keyword 912, a keyword 914, a keyword 916, a keyword 918, and a keyword 920 as keywords indicating the contents of an image input in the sentence range 950.

  In such a case, the image extraction unit 140 extracts an image stored in the image storage unit 110 in association with at least one of the keywords extracted by the keyword extraction unit 130. For example, from the image storage unit 110 described with reference to FIG. 3, the image extraction unit 140 may extract the image 300 and the image 310 stored in the image storage unit 110 in association with the keyword 912 “Odawara”. Similarly, the image extraction unit 140 extracts an image stored in the image storage unit 110 in association with the keyword 914, the keyword 916, the keyword 918, and the keyword 920. Then, the image selection unit 170 selects an image having the largest keyword weight total value calculated for each image by the weight total calculation unit 150 among the plurality of images extracted by the image extraction unit 140.

  For example, the image storage unit 110 stores the distance from the image layout position 810 to each keyword in association with the keyword 918 and the keyword 920 input at a position closer to the image layout position 810 than the other keywords. The image selection unit 170 may select an image. Then, the image output unit 190 arranges the image selected by the image selection unit 170 at the image arrangement position 810 and displays it together with the text. Further, the image extraction unit 140 may extract an image stored in the image storage unit 110 in association with a keyword included in the text range 950 determined by the text range determination unit 184. The text range determination unit 184 determines in advance a text range that includes the keyword to be extracted by the keyword extraction unit 130, so that the keyword extraction unit 130 extracts keywords from the entire text, and the image extraction unit 140 uses the keyword The image can be extracted more quickly than when the image stored in the image storage unit 110 is extracted in association with the keyword extracted by the extraction unit 130.

  FIG. 5 shows an example of output by the image output unit 190 according to the present embodiment. When the sentence range determination unit 184 sets the sentence range 950 in the output area 940, the keyword selection control unit 106 causes the user to select a keyword from sentences input in a range excluding the sentence range 950. For example, the keyword 922 and the keyword 924 are selected. The image extraction unit 140 extracts an image stored in the image storage unit 110 in association with a keyword included in the sentence range 950 and a keyword selected by the user.

  Then, the image selection unit 170 associates more types of keywords input at positions closer to the image arrangement position determined by the image arrangement position determination unit 120 from among the plurality of images extracted by the image extraction unit 140. An image stored in the image storage unit 110 may be selected. For example, in the case where the keywords input to the position closer to the image arrangement position 812 than the other keywords among the distances from the image arrangement position 812 to the keywords are the keyword 922 and the keyword 924, the keyword 922 and the keyword 924 are used. The image selection unit 170 may select an image stored in the image storage unit 110 in association with the. Then, the image output unit 190 arranges the image selected by the image selection unit 170 at the image arrangement position 812 and displays it together with the text.

  Further, an image stored in the image storage unit 110 may be selected in association with a keyword input at a position closest to the image layout position 812 determined by the image layout position determination unit 120. For example, when the keyword input at a position closest to the image arrangement position 812 is the keyword 922, the image selection unit 170 may select an image stored in the image storage unit 110 in association with the keyword 922. . The image output unit 190 may arrange the image selected by the image selection unit 170 at the image arrangement position 810 and display it together with the text.

  FIG. 6 shows an example of a functional configuration of the image output apparatus 10 according to the present embodiment. The image output device 10 includes a keyword generation unit 132, a keyword assignment unit 134, an object extraction unit 136, an object name assignment unit 138, an image keyword weight storage unit 162, a combination weight storage unit 164, a trimming unit 172, and a text keyword weight storage unit 186. Further, an expression mode weight storage unit 188 and an image weight determination unit 20 may be further provided. In addition, the image weight determination unit 20 may include a frequency calculation unit 200, a frequency weight determination unit 202, a position weight determination unit 204, and a size weight determination unit 206.

  The image storage unit 110 further supplies the stored image to the keyword generation unit 132, the object extraction unit 136, and the image weight determination unit 20. Further, the image storage unit 110 supplies the stored keywords to the image keyword weight storage unit 162 and the combination weight storage unit 164. The keyword generation unit 132 generates a keyword indicating the content of the image based on the supplementary information of the image stored in the image storage unit 110. Specifically, the keyword generation unit 132 extracts incidental information attached to the image stored in the image storage unit 110. For example, when the image is a captured image, the incidental information includes the imaging date and time, the imaging location, the imaging mode (such as the close-up mode, the portrait mode, and the night view mode) of the image, and the imaging conditions (brightness, saturation, And in-focus distance, etc.).

  For example, for an image captured in the night view mode, the keyword generation unit 132 generates “night” as a keyword for the image. Further, the keyword generation unit 132 may generate the year, month, or day when the image was captured from the date and time when the image was captured as a keyword. Moreover, the keyword generation part 132 may generate | occur | produce the season in which the said image was imaged as a keyword from the imaging date and time of an image. For example, the keyword generation unit 132 captures “Spring” for images captured from March to April, “Summer” for images captured from June to August, and September to November. “Autumn” may be generated as a keyword for images captured in the image, and “Winter” may be generated as a keyword for images captured from December to February.

  The keyword generation unit 132 may generate keywords such as “morning”, “daytime”, “evening”, and “night” based on the imaging time. Furthermore, the keyword generation unit 132 may generate, as keywords, the name of the area, the name of the place, the name of the city, and the like where the image is captured based on the imaging location. Then, based on the imaging conditions, the keyword generation unit 132 may generate “bright” or the like as a keyword when the brightness is high, or “bright” or “flash” or the like as a keyword when the saturation is high. Good. When the image is an image created by the user, the keyword generation unit 132 may generate a keyword assigned to the image by the user as a keyword. The keyword generating unit 132 supplies the generated keyword to the keyword adding unit 134. The keyword assigning unit 134 stores the keyword generated by the keyword generating unit 132 in the image storage unit 110 in association with the image. The keyword assigning unit 134 may associate a plurality of keywords with the image and store the plurality of keywords in the image storage unit 110 in association with the image.

  The object extraction unit 136 extracts an object included in the image stored in the image storage unit 110. For example, the object extraction unit 136 extracts an object using image processing such as edge detection. Further, the object extraction unit 136 may extract the object and the background by dividing into an area where the spatial frequency component of the image is higher than a predetermined frequency and an area excluding the area. The object extraction unit 136 supplies the extracted object to the object name assigning unit 138. The object name assigning unit 138 associates the object name of the object extracted by the object extracting unit 136 with the image as a keyword indicating the content of the image. Then, the object name assigning unit 138 stores the keyword associated with the image in the image storage unit 110.

  For example, the object name assigning unit 138 may have an object template database that stores object names in association with template images. The object name assigning unit 138 matches the object received from the object extracting unit 136 with the template image stored in the object template database, and associates the object name stored in the object template database with the matched template image. The keyword may be associated with the image as a keyword indicating the content of the image. For example, when it is found by matching with the template image that the object included in the image is a cat, the object name assigning unit 138 may associate “cat” with the image as a keyword indicating the content of the image. The object name assigning unit 138 may store the keyword input by the user in the image storage unit 110 in association with the image.

  The text storage unit 112 further supplies the text to the expression mode weight storage unit 188. The expression mode weight storage unit 188 stores the weight of the character font or the character size in association with the character font or character size. Specifically, the expression mode weight storage unit 188 stores a weight associated with each typeface such as Mincho, Gothic, and line typeface. Also, the expression mode weight storage unit 188 stores the weight associated with each character expression mode, such as the size of the character, whether italic or not, and whether it is bold. When the user changes the typeface or size of the character with respect to the character, the user often wants to display the character more emphasized than other characters. Therefore, for example, when the size of the character is large, the expression mode weight storage unit 188 may store a larger weight than the size of the character having a smaller character size. The expression mode weight storage unit 188 supplies the weight stored in association with the font or size of a predetermined keyword to the keyword weight determination unit 182.

  When the weight stored in the expression mode weight storage unit 188 is greater than the weight of the predetermined keyword included in the text stored in the text storage unit 112 in correspondence with the font or character size of the predetermined keyword, A larger weight may be associated with a predetermined keyword. For example, the keyword weighting determination unit 182 adds the keyword weight calculated by the keyword frequency calculation unit 180 and the weight stored in the expression form weight storage unit 188 in association with the typeface and size of the keyword, The weight of the keyword may be calculated. Also, the keyword weighting determination unit 182 may calculate the weight of the keyword by multiplying the weight of the keyword by the weight stored in the expression form weight storage unit 188 in association with the typeface of the keyword. Good. The keyword weighting determination unit 182 supplies the weight determined in association with the keyword to the sentence keyword weight storage unit 186. The sentence keyword weight storage unit 186 stores the keyword weight in association with the keyword included in the sentence stored in the sentence storage unit 112. Specifically, the sentence keyword weight storage unit 186 receives and stores the weight for each keyword determined by the keyword weight determination unit 182. The text keyword weight storage unit 186 supplies weights associated with the keywords to the image selection unit 170 based on the control of the image selection unit 170.

  Accordingly, the keyword weighting determination unit 182 can associate a larger weight with a keyword that is frequently input by the user than a keyword that is less input by the user, and thus the image output apparatus 10 according to the present embodiment. Can accurately grasp a keyword that is highly interested by the user and often recalled by the user by referring to the weight associated with the keyword included in the sentence. Further, since the keyword weighting determination unit 182 can weight the predetermined keyword based on the typeface or size of the character set by the user as the predetermined keyword, according to the interest when the user is inputting the sentence, Appropriate weights can be associated with keywords included in the text.

  The image keyword weight storage unit 162 stores keyword weights in association with the keywords stored in the image storage unit 110. Further, the image keyword weight storage unit 162 may store keyword weights based on the control of the image weight determination unit 20. The image keyword weight storage unit 162 supplies the keyword weight to the weight total calculation unit 150. The combination weight storage unit 164 stores the weight of the combination of the plurality of keywords in association with the combination of the plurality of keywords indicating the content of the image. The combination weight storage unit 164 supplies the weights of combinations of a plurality of keywords to the weight sum calculation unit 150. The image weight determination unit 20 calculates a weight for each of a plurality of image keywords received from the image storage unit 110, and stores the calculated weight in the image keyword weight storage unit 162 in association with the image keyword. Specifically, the image weight determination unit 20 includes a frequency calculation unit 200, a frequency weight determination unit 202, a position weight determination unit 204, and a size weight determination unit 206.

  The frequency calculation unit 200 calculates the number of images including the object for each object having an object name that is a keyword indicating the content of the image in the plurality of images stored in the image storage unit 110. In addition, the frequency calculation unit 200 associates a keyword associated with each of the plurality of images stored in the image storage unit 110 with the plurality of images stored in the image storage unit 110. The number of keywords may be calculated for each keyword. The frequency calculation unit 200 supplies the frequency weight determination unit 202 with the number of images including the calculated object for each object and the number of the keywords for each keyword associated with the image included in a plurality of images. To do. The frequency weight determination unit 202 causes the image keyword weight storage unit 162 to store a larger weight in association with a keyword that is an object name having a larger number of images calculated for each object by the frequency calculation unit 200. Further, the frequency weight determination unit 202 associates the keyword calculated by the frequency calculation unit 200 for each keyword with a larger number of keywords included in the plurality of images, and stores a larger weight in the image keyword weight storage unit 162. You may let them.

  As a result, when the user captures more images of the predetermined object, the frequency weight determination unit 202 can apply a greater weight to the image including the object, and thus the user is highly interested. An image including an object can be given a higher weight than an image including an object that is not of interest to the user.

  The position weight determination unit 204 causes the image keyword weight storage unit 162 to store a larger weight in association with the keyword that is the object name of the object closer to the center position of the image stored in the image storage unit 110. For example, the position weight determination unit 204 calculates the position occupied by the object included in the image with respect to the image. Subsequently, the position weight determination unit 204 calculates the distance from the center position of the image to the object. Then, the position weight determination unit 204 associates a larger weight with the keyword that is the object name of the object in association with the distance from the center position of the image to the object and when the distance is closer. Here, when the user captures an image, an object that the user desires to capture is often included in an area close to the center position of the image. Therefore, since the image output apparatus 10 according to the present embodiment includes the position weight determination unit 204, a larger weight is applied to an image including an object with high user interest than an image including an object with low user interest. Can be weighted.

  The size weight determination unit 206 stores the larger weight in the image keyword weight storage unit 162 in association with the keyword that is the object name of the object having a larger size with respect to the image stored in the image storage unit 110. For example, the size weight determination unit 206 calculates the area of the imaging region of the image and the area of the object included in the image. Subsequently, the size weight determination unit 206 calculates the ratio of the area of the object to the image. Then, the size weight determination unit 206 may associate the weight of the object area with the keyword that is the object name of the object in association with the ratio of the area of the object to the image, and when the ratio is larger. The image extraction unit 140 further supplies the keyword stored in the image storage unit 110 in association with the extracted image to the weight sum calculation unit 150.

  The weight total calculation unit 150 is a keyword stored in the image storage unit 110 in association with the image received from the image extraction unit 140 and is associated with the same keyword as the keyword extracted by the keyword extraction unit 130. The keyword weights stored in the keyword weight storage unit 162 are extracted. Then, the weight total calculation unit 150 calculates the total value by adding the weights of the extracted keywords for each image. Further, the weight sum calculation unit 150 sets a plurality of keywords stored in the image storage unit 110 in association with the image received from the image extraction unit 140 and the same keyword as the keyword extracted by the keyword extraction unit 130. The combination weights stored in the combination weight storage unit 164 are extracted in association with each other. Then, the total weight calculation unit 150 calculates the total value by adding the weights of the extracted combinations of the keywords for each image. Further, the weight sum calculation unit 150 associates the keyword stored in the image storage unit 110 with the image received from the image extraction unit 140 and the same keyword as the keyword extracted by the keyword extraction unit 130. Then, the total value of the keyword weights stored in the sentence keyword weight storage unit 186 may be calculated. The weight sum calculation unit 150 further supplies the calculated weight for each image to the image selection unit 170.

  The image selection unit 170 associates the image storage unit 110 with more types of keywords input at positions closer to the image arrangement position determined by the image arrangement position determination unit 120 among the images extracted by the image extraction unit 140. When a plurality of images are selected from the images stored in the image, a predetermined number of images are received from the image extraction unit 140 from images having a large total weight value received from the weight total calculation unit 150. You may select from an image. In addition, the image selection unit 170 may select, from the images received from the image extraction unit 140, images whose total weight value received from the weight total calculation unit 150 is larger than a predetermined value. Further, the image selection unit 170 may select an image having the maximum weight total value received from the weight total calculation unit 150 from the images received from the image extraction unit 140. When there are a plurality of images having the same keyword weight total value received from the weight total calculation unit 150, the image selection unit 170 calculates the total weight of the combination of the plurality of keywords calculated by the weight total calculation unit 150. A larger image may be selected from the images received from the image extraction unit 140. Further, when there are a plurality of images having the same keyword weight total value received from the weight total calculation unit 150, the image selection unit 170 stores the text keyword weight storage unit 186 calculated by the weight total calculation unit 150. An image having a larger total weight value of keywords may be selected from the images received from the image extraction unit 140. The image selection unit 170 further supplies the selected image to the trimming unit 172.

  The trimming unit 172 trims the image received from the image selection unit 170 so that the object corresponding to the keyword assigned to the image by the object name assigning unit 138 is included. For example, the trimming unit 172 may perform trimming using position information of the object attached to the image in association with the object included in the image. The trimming unit 172 may trim the object included in the image so as to include an object corresponding to the keyword added to the image by the object name assigning unit 138 by image processing such as pattern matching. Further, the trimming unit 172 may enlarge and reduce the object included in the image. The trimming unit 172 supplies the trimmed image to the image output unit 190. The image output unit 190 may output the trimmed image received from the trimming unit 172 together with the input text. For example, the image output unit 190 outputs an image together with text on a monitor or the like.

  According to the image output apparatus 10 according to the present embodiment, even when a plurality of images are selected by the image selection unit 170, based on the keyword weight stored in the image storage unit 110 in association with the image, It is possible to appropriately select and display an image that the user desires to display. As a result, even when a plurality of images are selected by the image selection unit 170, the user does not select an image himself, so the user can input a sentence without interrupting his / her thoughts.

  FIG. 7 shows an example of the data structure of the image keyword weight storage unit 162 according to this embodiment. The image keyword weight storage unit 162 stores keyword weights in association with the keywords stored in the image storage unit 110. Specifically, the image keyword weight storage unit 162 stores the keyword weight received from the image weight determination unit 20 in association with the keyword. For example, the image keyword weight storage unit 162 stores the keyword A in association with the weight “3”. Further, the image keyword weight storage unit 162 stores the keyword B in association with the weight “2”. The image keyword weight storage unit 162 stores the weight “1” in association with the keyword C. Further, the image keyword weight storage unit 162 stores the keyword D in association with the weight “4”.

  The weight sum calculation unit 150 extracts the keyword weight associated with the image from the image keyword weight storage unit 162. Then, the total weight calculation unit 150 calculates the total value of the weights of the keywords associated with the image. For example, consider a case where the keywords extracted by the keyword extraction unit 130 from the text input from the text input unit 100 are the keyword “A” and the keyword “D”. In such a case, the image extraction unit 140 extracts an image associated with at least one of the keyword “A” or the keyword “D” from the image storage unit 110.

  Then, the total weight calculation unit 150 calculates the total value of the weight of the keyword “A” and the weight of the keyword “D” associated with each of the extracted plurality of images for each image. For example, consider a case where the extracted image is associated with the keyword “A”, the keyword “B”, and the keyword “D”. In this case, the keywords identical to the keywords extracted by the keyword extraction unit 130 among the keywords associated with the images are the keyword “A” and the keyword “D”. In this case, the weight sum calculation unit 150 calculates the weight of the image as “7”, which is the sum of the weight of the keyword “A” and the weight of the keyword “D”. Subsequently, the image selection unit 170 compares the total weight value calculated for each image calculated by the total weight calculation unit 150 and selects the image having the maximum total weight value. Then, the image selection unit 170 selects the image having the maximum weight value. The image output unit 190 displays the image selected by the image selection unit 170 together with the text input by the user.

  According to the image output apparatus 10 according to the present embodiment, an image associated with the same keyword as at least one of the keywords included in the text input by the user is extracted, and the keyword associated with the image is extracted. A weight is calculated for each image. Since the keyword weight total value calculated for each image can be compared and the image can be automatically selected, the image recalled by the user can be appropriately selected and displayed together with the text input by the user. For example, according to the image output apparatus 10 according to the present embodiment, an image recalled by the user is automatically selected based on the weight of the keyword included in the text input by the user on a blog or the like, and the text is output together. Can be displayed.

  FIG. 8 shows an example of the data structure of the combination weight storage unit 164 according to this embodiment. The combination weight storage unit 164 stores the weight of the combination of the plurality of keywords in association with the combination of the plurality of keywords indicating the content of the image. Specifically, the combination weight storage unit 164 stores weights based on associations between keywords of a plurality of keywords associated with images. More specifically, among the plurality of images stored in the image storage unit 110, when the number of combinations of a plurality of keywords associated with the image is larger, the combination of the plurality of keywords is larger. Store weights in association with each other. For example, consider a case where a user frequently takes images of winter mountains and stores a plurality of images of the taken winter mountains in the image storage unit 110. In such a case, the image storage unit 110 has more winter mountain images associated with the keywords “winter” and “mountain” than images associated with keywords other than the keywords “winter” and “mountain”. Since it is stored, the relationship between the keywords “winter” and “mountain” is high, and a combination of keywords of “winter” and “mountain” may be associated with a larger weight and stored.

  For example, the combination weight storage unit 164 stores the weight “4” in association with the combination of the keyword “A” and the keyword “B”. Further, the combination weight storage unit 164 stores the combination of the keyword “A” and the keyword “D” in association with the weight “3”. Similarly, the combination weight storage unit 164 assigns a weight “2” to the combination of the keyword “A” and the keyword “F”, a weight “5” to the combination of the keyword “B” and the keyword “D”, and the keyword “D”. ”And the keyword“ F ”are stored in association with the weight“ 1 ”. The combination weight storage unit 164 is not limited to a combination of two keywords, and may store a weight in association with a combination of at least two or more keywords. The image output apparatus 10 may further include a combination weight determining unit that determines combination weights between a plurality of keywords. The combination weight determining unit calculates the number of combinations of a plurality of keywords associated with the image, and the combination having a larger number of combinations of the plurality of keywords is compared to a combination having a smaller number of combinations of the plurality of keywords. Larger weights may be associated.

  FIG. 9 shows an example of a hardware configuration of the image output apparatus 10 according to the present embodiment. The image output apparatus 10 according to the present embodiment includes a CPU peripheral unit including a CPU 1505, a RAM 1520, a graphic controller 1575, and a display device 1580 connected to each other by a host controller 1582, and a host controller 1582 by an input / output controller 1584. I / O unit having a communication interface 1530, a hard disk drive 1540, and a CD-ROM drive 1560 connected to the I / O controller, and a legacy input having a ROM 1510, a flexible disk drive 1550, and an I / O chip 1570 connected to the I / O controller 1584. And an output unit.

  The host controller 1582 connects the RAM 1520 to the CPU 1505 and the graphic controller 1575 that access the RAM 1520 at a high transfer rate. The CPU 1505 operates based on programs stored in the ROM 1510 and the RAM 1520 to control each unit. The graphic controller 1575 acquires image data generated by the CPU 1505 or the like on a frame buffer provided in the RAM 1520 and displays it on the display device 1580. Alternatively, the graphic controller 1575 may include a frame buffer that stores image data generated by the CPU 1505 or the like.

  The input / output controller 1584 connects the host controller 1582 to the communication interface 1530, the hard disk drive 1540, and the CD-ROM drive 1560, which are relatively high-speed input / output devices. The communication interface 1530 communicates with other devices via a network. The hard disk drive 1540 stores programs and data used by the CPU 1505 in the image output apparatus 10. The CD-ROM drive 1560 reads a program or data from the CD-ROM 1595 and provides it to the hard disk drive 1540 via the RAM 1520.

  The input / output controller 1584 is connected to the ROM 1510, the flexible disk drive 1550, and the relatively low-speed input / output device of the input / output chip 1570. The ROM 1510 stores a boot program executed when the image output apparatus 10 is started, a program depending on the hardware of the image output apparatus 10, and the like. The flexible disk drive 1550 reads a program or data from the flexible disk 1590 and provides it to the hard disk drive 1540 via the RAM 1520. The input / output chip 1570 connects various input / output devices via a flexible disk drive 1550 such as a parallel port, a serial port, a keyboard port, and a mouse port.

  The image output program provided to the hard disk drive 1540 via the RAM 1520 is stored in a recording medium such as the flexible disk 1590, the CD-ROM 1595, or an IC card and provided by the user. The image output program is read from the recording medium, installed in the hard disk drive 1540 in the image output apparatus 10 via the RAM 1520, and executed by the CPU 1505. The image output program installed and executed in the image output apparatus 10 works on the CPU 1505 or the like to make the image output apparatus 10 operate as described with reference to FIGS. 1 to 8, the text input unit 100, the image input unit 102, and the image arrangement position input. Control unit 104, keyword selection control unit 106, image storage unit 110, text storage unit 112, image arrangement position determination unit 120, keyword extraction unit 130, image extraction unit 140, weight total calculation unit 150, position weight determination unit 160, image Selection unit 170, keyword frequency calculation unit 180, keyword weight determination unit 182, sentence range determination unit 184, image output unit 190, keyword generation unit 132, keyword assignment unit 134, object extraction unit 136, object name assignment unit 138, image keyword Weight storage unit 162, combination weight storage unit 1 4, trimming unit 172, sentence keyword weight storage unit 186, expression mode weight storage unit 188, image weight determination unit 20, frequency calculation unit 200, frequency weight determination unit 202, position weight determination unit 204, size weight determination unit 206, And function as a combination weight determination unit.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above-described embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

3 is a conceptual diagram of an output screen 900. FIG. 3 is a block diagram illustrating a functional configuration of the image output apparatus 10. FIG. 2 is a diagram illustrating an image storage unit 110. FIG. It is a figure which shows the output of the image output part 190. FIG. It is a figure which shows the output of the image output part 190. FIG. 3 is a block diagram illustrating a functional configuration of the image output apparatus 10. FIG. It is a figure which shows the image keyword weight storage part 162. FIG. It is a figure which shows the combination weight storage part 164. FIG. 2 is a block diagram illustrating a hardware configuration of the image output apparatus 10. FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Image output device 20 Image weight determination part 100 Text input part 102 Image input part 104 Image arrangement position input control part 106 Keyword selection control part 110 Image storage part 112 Text storage part 120 Image arrangement position determination part 130 Keyword extraction part 132 Keyword generation Unit 134 keyword adding unit 136 object extracting unit 138 object name adding unit 140 image extracting unit 150 weight sum calculating unit 160 position weight determining unit 162 image keyword weight storing unit 164 combination weight storing unit 170 image selecting unit 172 trimming unit 180 keyword frequency calculation Unit 182 Keyword weight determination unit 184 Sentence range determination unit 186 Sentence keyword weight storage unit 188 Expression mode weight storage unit 190 Image output unit 200 Frequency calculation unit 202 Frequency weight determination unit 20 4 Position Weight Determination Unit 206 Size Weight Determination Unit 300, 310, 320, 330 Image 800, 802, 810, 812 Image Arrangement Position 900 Output Screen 910, 940 Output Area 902, 904, 906, 908 Keyword 912, 914, 916 , 918 Keyword 920, 922, 924 Keyword 950 Text range 1505 CPU
1510 ROM
1520 RAM
1530 Communication interface 1540 Hard disk drive 1550 Flexible disk drive 1560 CD-ROM drive 1570 Input / output chip 1575 Graphic controller 1580 Display device 1582 Host controller 1584 Input / output controller 1590 Flexible disk 1595 CD-ROM

Claims (9)

An image output device that outputs an image related to a sentence together with the input sentence,
An image storage unit for storing the image in association with at least one keyword indicating the content of the image;
An image placement position determination unit for determining an image placement position, which is a position where an image is to be placed in an output region where an input sentence is output;
A keyword extraction unit for extracting a keyword stored in the image storage unit from the input text;
An image extraction unit for extracting an image stored in the image storage unit in association with at least one of the keywords extracted by the keyword extraction unit;
Among the images extracted by the image extraction unit, images stored in the image storage unit in association with more types of keywords input at positions closer to the image arrangement position determined by the image arrangement position determination unit An image selector for selecting
An image output apparatus comprising: an image output unit that arranges an image selected by the image selection unit at an image arrangement position determined by the image arrangement position determination unit and outputs the image together with an input sentence. Among the keywords extracted by the keyword extraction unit, a position weighting determination unit that gives greater weight to a keyword input at a position closer to the image arrangement position determined by the image arrangement position determination unit;
A weight total calculation unit that calculates a total value of keyword weights weighted by the position weight determination unit for each image extracted by the image extraction unit;
The image output device according to claim 1, wherein the image selection unit selects an image having the largest total weight value of the keywords calculated by the weight sum calculation unit from images extracted by the image extraction unit. The input sentence is divided into a plurality of ranges, and among the keywords extracted by the keyword extraction unit, a keyword that is input in a range closer to the image arrangement position determined by the image arrangement position determination unit is weighted more heavily. A position weight determination unit;
A weight total calculation unit that calculates a total value of keyword weights weighted by the position weight determination unit for each image extracted by the image extraction unit;
The image output device according to claim 1, wherein the image selection unit selects an image having the largest total weight value of the keywords calculated by the weight sum calculation unit from images extracted by the image extraction unit. The image output device according to claim 3, wherein the position weight determination unit weights a keyword extracted by the keyword extraction unit input to a line closer to the image arrangement position determined by the image arrangement position determination unit to a greater weight. . A sentence storage unit that stores sentences input by the user in the past;
A keyword frequency calculation unit that calculates the number of keywords included in the text stored in the text storage unit for each keyword;
A keyword weighting determination unit that assigns a smaller weight to a keyword having a larger number of keywords calculated by the keyword frequency calculation unit;
The weight total calculation unit calculates a total value of keyword weights weighted by the position weight determination unit and the keyword weight determination unit for each image extracted by the image extraction unit,
4. The image output device according to claim 2, wherein the image selection unit selects an image having the smallest total value of keyword weights calculated by the weight total calculation unit from among images extracted by the image extraction unit. 5. . A text range determining unit that determines a text input within a predetermined range from the image layout position determined by the image layout position determining unit as a text from which the keyword extracting unit extracts a keyword;
The image output device according to claim 1, wherein the keyword extraction unit extracts a keyword stored in the image storage unit from a text range determined by the text range determination unit. A keyword selection control unit that allows a user to select a keyword stored in the image storage unit from a range of sentences excluding a range of sentences determined by the sentence range determination unit;
The image extraction unit extracts an image stored in the image storage unit in association with at least one of the keyword extracted by the keyword extraction unit and the keyword selected by the keyword selection control unit by the user. The image output apparatus according to claim 6. An image output method for outputting an image related to a sentence together with the input sentence,
An image storage stage for storing the image in the image storage unit in association with at least one keyword indicating the content of the image;
An image placement position determination stage for determining an image placement position, which is a position where an image is to be placed in an output region in which an input sentence is output;
A keyword extraction step of extracting a keyword stored in the image storage unit from the input sentence;
An image extraction step of extracting an image stored in the image storage unit in association with at least one of the keywords extracted by the keyword extraction step;
Among the images extracted in the image extraction stage, the image stored in the image storage unit in association with more types of keywords input at positions closer to the image arrangement position determined in the image arrangement position determination stage An image selection stage for selecting,
An image output method comprising: an image output step of placing the image selected in the image selection step at the image placement position determined in the image placement position determination step and outputting the image together with the input text. An image output program for an image output apparatus that outputs an image related to a sentence together with an input sentence, the image output apparatus comprising:
An image storage unit for storing the image in association with at least one keyword indicating the content of the image;
An image placement position determination unit for determining an image placement position, which is a position where an image is to be placed in an output region where an input sentence is output;
A keyword extraction unit for extracting a keyword stored in the image storage unit from the input text;
An image extraction unit for extracting an image stored in the image storage unit in association with at least one of the keywords extracted by the keyword extraction unit;
Among the images extracted by the image extraction unit, images stored in the image storage unit in association with more types of keywords input at positions closer to the image arrangement position determined by the image arrangement position determination unit An image selector for selecting
An image output program that functions as an image output unit that arranges an image selected by the image selection unit at an image arrangement position determined by the image arrangement position determination unit and outputs the image together with an input sentence.

Images