JP2018200565A - Image selection method of article in news site using degree of interest of user - Google Patents

Abstract

To attach an image that improves a browsing ratio of an article when the article includes only texts.SOLUTION: In an image selection device 10, an image interest degree calculation unit 102 calculates a degree of interest of a user for an image attached to a public article, an image related information DB 204 manages the image, a keyword and a degree of interest in the image in association with each other, a complementary image determination unit 105 selects an image with which a key word suitable to the keyword included in a delivered article is associated as a candidate image from the image related information DB 204 and determines a complementary image to be attached to the delivered article among candidate images based on the degree of interest in images.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a technique for selecting an image to be attached to an article.

  Articles distributed on the Internet include articles with images attached and text-only articles without images attached. In general, an article with an image attached tends to have a higher user selection rate (viewing rate) than an article with only text. For this reason, conventionally, for an article with only text, an image is selected at random or manually from among images (photos) prepared in advance by a content provider. Alternatively, it may be possible to select an image suitable for the text of an article using the technique disclosed in Patent Document 1.

  In Patent Document 1, a keyword is extracted from an input document, the attribute of the input document is determined, a degree of association between the keyword and the candidate image corresponding to the attribute is obtained, and an image selection score is calculated from the degree of association for the candidate image. And selecting an image to be added to an input document from candidate images based on the score.

JP 2011-221794 A

  However, an image selected based only on a keyword included in an article is not necessarily an image that increases the selection rate of the article.

  An object of the present invention is to attach an image that increases a user's selection rate to an article with only a text to which no image is attached.

  An image selection device according to an aspect of the present invention is an image selection device that selects an image to be attached to a distribution article, and an image interest degree calculation unit that calculates a user's degree of interest in an image attached to a published article. A management unit that associates and manages the image, the keyword, and an image interest level for the image, and an image in which a keyword that matches the keyword included in the distribution article is associated with the management unit. Is selected as a candidate image, and a complementary image determination unit that determines a complementary image to be attached to the distribution article from the candidate images based on the degree of image interest.

  An object of the present invention is to attach an image that increases a user's selection rate to an article with only a text to which no image is attached.

3 is a schematic diagram for explaining an overview of the first embodiment. FIG. 1 is a block diagram illustrating a configuration example of an image selection device according to Embodiment 1. FIG. 4 is a table diagram illustrating an example of a configuration of an image related information DB (DataBase) according to Embodiment 1. FIG. 6 is a flowchart illustrating an example of a complementary image determination process according to the first embodiment. 6 is a block diagram illustrating an example of a configuration of an image selection device according to Embodiment 2. FIG. It is a table figure which shows the structural example of image relevant information DB which concerns on Embodiment 2. FIG. 10 is a flowchart illustrating an example of a complementary image determination process according to the second embodiment. It is a figure which shows the hardware structural examples, such as an image selection apparatus concerning this invention.

  Hereinafter, embodiments will be described with reference to the drawings.

(Embodiment 1)
<Summary of implementation>
First, the outline of the first embodiment will be described with reference to FIG.

  The article browsing application running on the portable terminal 23 first displays the titles and images of the distributed articles in a list format. When the user operates the mobile terminal 23 to select one article from the article list, the article browsing application displays the text (details) of the selected article. Accordingly, the probability of reading the article selection rate (viewing rate), that is, the body text (details) of the article, also varies depending on the image displayed in the article list.

  The image selection device 10 selects an image to be displayed in the article list. Specifically, when the image selection apparatus 10 acquires an article scheduled to be distributed only with text to which no image is attached (hereinafter referred to as “distributed article”), the image selecting apparatus 10 extracts a keyword included in the distributed article, and the keyword Select an image associated with a matching keyword. For example, as illustrated in FIG. 1, when keywords “golf” and “Tokyo Olympics” are extracted from the distribution article T1, the image selection device 10 is associated with an image G1 associated with a keyword matching “golf”. , An image G2 associated with a keyword that matches the “Tokyo Olympics” is selected.

  Each of the images G1 and G2 is associated with an image interest level indicating the degree of interest of the user in the image. The degree of image interest is a value calculated based on a user's reaction to a previously published article (hereinafter referred to as “published article”) attached with an image.

  The image selection device 10 selects an image to be attached to the text-only article T1 based on the degree of image interest. For example, as illustrated in FIG. 1, when the image interest level of the image G <b> 1 is “0.17” and the image interest level of the image G <b> 2 is “0.12”, the image selection device 10 has an image G <b> 1 with a high image interest level. To the attached image. Then, the image selection device 10 attaches the selected image to the article T1 and uploads it to a predetermined article publication server.

  The article browsing application running on the portable terminal 23 downloads and displays an article with an image attached from the article publishing server. Since the image attached in this way is an image of high user interest, the article selection rate (viewing rate) can be increased rather than attaching an image selected based only on keywords as in the past. Can do. Details will be described below.

<Configuration of image selection device>
Next, the configuration of the image selection device 10 according to the first embodiment will be described with reference to FIG.

  As illustrated in FIG. 2, the image selection device 10 includes a totaling unit 101, an image interest level calculation unit 102, a distribution article acquisition unit 103, a distribution article information extraction unit 104, a complementary image determination unit 105, and a public article. A generation unit 106, an application log DB 201, a keyword dictionary 202, an owned image DB 203, and an image related information DB 204 are provided.

<Each DB of Image Selection Device>
Next, each DB 201, 202, 203, 204 provided in the image selection apparatus 10 will be described.

  The application log DB 201 is a DB that manages application logs transmitted from the article browsing application 24 operating on each mobile terminal 23 via a predetermined network (for example, the Internet). The application log is selected at least by the article browsing application 24 when the image attached to the published article is displayed on the display on the portable terminal 23 (hereinafter referred to as “image display number”) and the published article is selected by the user. (Viewed) number of times (hereinafter referred to as “article selection number”).

  The keyword dictionary 202 is a dictionary used when extracting keywords from articles. For example, the keyword dictionary 202 manages keywords and parts of speech in association with each other. The keyword may be different for each genre of the article.

  The owned image DB 203 is a DB that manages owned images. An image to be attached to a text-only published article is selected from images registered in the owned image DB.

  The image related information DB 204 is a DB that manages information related to images. Hereinafter, the image related information DB 204 will be described in detail with reference to FIG. The image related information DB 204 manages an image ID 301, a keyword 302, an article selection number 303, an image display number 304, a weighting coefficient 305, an image interest level 306, and a genre 307 in association with each other.

  An image ID 301 is an identifier of an image registered in the owned image DB 203. In FIG. 3, an image image is displayed in the image ID 301 for easy understanding, but in practice, an identifier is registered in the image ID 301.

  A keyword 302 is a keyword associated with the image ID 301. In the first embodiment, it is assumed that the keyword 302 is associated with the image with the image ID 301 in advance.

  The article selection number 303 is the number of times an article with the image ID 301 attached is selected (viewed) by the user. The image display number 304 is the number of times that the image with the image ID 301 is displayed on the display of the portable terminal 23. That is, the image display number 304 corresponds to the number of times the image with the image ID 301 is viewed by the user, and may be referred to as an impression number.

  The weighting coefficient 305 is a coefficient used for calculating the image interest level 306. Details of the calculation method of the weighting coefficient 305 will be described later (see details of the calculation method of the image interest level). The image interest level 306 is a value indicating the level of interest of the image with the image ID 301. Details of the method for calculating the image interest level will be described later. A genre 307 indicates a genre of an article appropriate for attaching an image with an image ID 301. It is assumed that the genre 307 is associated with the image with the image ID 301 in advance.

<Each function of the image selection device>
Next, each function 101, 102, 103, 104, 105, 106 provided in the image selection apparatus 10 will be described.

  The tabulation unit 101 analyzes the application log stored in the application log DB 201 and tabulates the number of times an article with an image ID attached is selected (viewed) by each user, and selects the article with the image ID. Calculate the number. Further, the totaling unit 101 analyzes the application log, totals the number of times the image with the image ID is displayed on each portable terminal 23, and calculates the number of images displayed with the image ID. The totaling unit 101 may use an application log for a predetermined period in the past (for example, several hours) as a target for totaling the number of article selections and the number of image displays.

  The image interest level calculation unit 102 calculates the weighting coefficient using the article selection number and / or the image display number calculated by the totaling unit 101. Further, the image interest level calculation unit 102 calculates the image interest level 306 using the article selection number, the image display number, and / or the weighting factor. Then, the image interest level calculation unit 102 registers the number of article selections, the number of image displays, the weighting coefficient, and the image interest level in the image related information DB 204. The details of the method for calculating the image interest level 306 will be described later.

  The distribution article acquisition unit 103 acquires a distribution article from the article providing server 21 that provides the article via a predetermined network (for example, the Internet).

  The distribution article information extraction unit 104 selects a distribution article (that is, a text-only distribution article) to which no image is attached from the distribution articles acquired by the distribution article acquisition unit 103. Then, using the keyword dictionary 202, the distribution article information extraction unit 104 extracts keywords from the distribution articles only with text, and outputs the keywords to the complementary image determination unit 105. The distribution article information extraction unit 104 outputs the distribution article to which the image has been attached to the public article generation unit 106 as it is.

  The supplemental image determination unit 105 receives a text-only distribution article and a keyword from the distribution article information extraction unit 104, and attaches an image (hereinafter referred to as “text”) to the distribution article only of the text based on the keyword and the image related information DB 204. "Supplemental image"). The details of the complementary image determination process in the complementary image determination unit 105 will be described later.

  The public article generation unit 106 attaches the complementary image determined by the complementary image determination unit 105 to the text-only distribution article and uploads it to the article public server 22. Also, the public article generation unit 106 uploads the distribution article with the attached image to the article public server 22 as it is.

<Details of image interest calculation method>
Next, details of a method for calculating the degree of interest in an image will be described. The image interest level calculation unit 102 calculates the image interest level P according to the following (Equation 1).

P = (A / B) × W (Formula 1)
Here, A is the number of article selections, B is the number of image displays, and W is a weighting factor. A / B may be referred to as an article selection rate. As a result, the image interest degree P increases as the image has a higher article selection rate, so that an image that has received high interest from the user in the past is easily selected as a complementary image.

  The weighting factor W may be a predetermined value, or may be determined based on the image display number B as in the following method 1 or method 2, for example.

(Method 1) The image interest level calculation unit 102 determines the weighting coefficient W according to the ranking of the number of displayed images. For example, the image display numbers of each image ID are arranged in descending order, W from the top 1 to 20 is “0.6”, W from 21 to 40 is “0.7”, and 41 to 60 The W from the 61st position to the 80th position is “0.9”, and the W from the 81st position to the 100th position is “1.0”.

(Method 2) The image interest level calculation unit 102 determines the weighting coefficient W according to the number of displayed images. For example, if “W <first threshold value”, W is “1.0”. If “first threshold value ≦ W <second threshold value”, W is “0.5” and “second threshold value ≦ W. ", W is set to" 0 ".

  In both methods 1 and 2, the weight coefficient W of an image with a relatively small number of display times is increased, and the weight coefficient W of an image with a relatively large number of display times is decreased. Thereby, since the image interest degree P becomes high as the image having a relatively small number of display times, a fresh image that is not familiar to the user is easily selected as a complementary image. That is, by applying the weighting factor W, it is possible to suppress the same image from being selected as a complementary image. The weighting factor W may be different for each genre and / or for each publication article publication time.

<Details of complementary image determination processing>
Hereinafter, the flow and specific example of the complementary image determination process will be described.

  First, the flow of complementary image determination processing will be described using the flowchart of FIG.

  The complementary image determination unit 105 determines whether or not the keyword 302 that matches the keyword of the distribution article exists in the image related information DB 204 (ST101).

  When the matching keyword 302 exists (ST101: YES), the complementary image determination unit 105 selects the image ID 301 associated with the matching keyword 302 as a candidate image ID, and proceeds to the process of ST104 (ST102). ).

  When the matching keyword 302 does not exist (ST101: NO), the complementary image determination unit 105 uses the image ID 301 associated with the genre 307 that matches the genre of the distribution article in the image related information DB 204 as the candidate image ID. The process proceeds to ST104 (ST103).

  Next, the complementary image determination unit 105 selects a candidate image ID having the highest image interest level 306 from the candidate image IDs selected in ST102 or ST103 (ST104).

  Next, the complementary image determination unit 105 determines whether the candidate image ID selected in ST104 is the same as the complementary image ID of another distribution article released within a predetermined period (for example, within 24 hours). (ST105). In addition, in the case of the operation of collectively uploading the distribution articles at every predetermined time and uploading them to the article publishing server 22, the complementary image determination unit 105 determines whether or not it is the same as the complementary image ID of other distribution articles uploaded at that time. May be determined.

  When the candidate image ID is the same as the complementary image ID of another distribution article (ST105: YES), the complementary image determination unit 105 excludes the candidate image ID (ST106) and executes the processing from ST104 again. . Thereby, it can prevent that the same complementary image is displayed side by side on the display of the portable terminal 23, or a user sees the same complementary image many times in a short time. In this case, in ST104, a candidate image ID having the second highest image interest level 306 is selected.

  If the candidate image ID is not the same as the candidate image ID of another distribution article (ST105: NO), the complementary image determination unit 105 determines the candidate image ID as the complementary image ID, and ends this processing (ST107).

  Next, a specific example of the complementary image determination process will be described with reference to FIG. For example, when “Tokyo Olympics” and “Golf” are included in the distribution article, the complementary image determination unit 105 determines from the image related information DB 204 the image ID 301 “G11 associated with the keyword 302 that matches the keyword. And “G12” are extracted as candidate image IDs. Then, since the image interest level 306 of the candidate image ID “G12” is the highest of “0.17” among these two candidate image IDs, the complementary image determination unit 105 selects the candidate image ID “G12” as a complementary image. ID is determined.

<Effect of Embodiment 1>
As described above, in the image selection device 10 according to Embodiment 1, the image interest level of the image is calculated based on the past user's reaction to the published article attached with the image, and the image with the highest image interest level is calculated. Is determined as a complementary image to be attached to a text-only distribution article. As a result, when a randomly selected image is attached to a text-only distribution article or when an image selected using only a keyword included in the distribution article is attached, the complementary image is The user selection rate (viewing rate) of the attached distribution article can be increased.

(Embodiment 2)
In the first embodiment, the case where the complementary image is determined using the image interest level of the owned image has been described, but in the second embodiment, an image attached to the distribution article (hereinafter referred to as “unowned image”). A case where a complementary image is determined using the degree of interest will be described.

<Configuration of image selection device>
First, the configuration of the image selection device 11 according to the second embodiment will be described with reference to FIG.

  As shown in FIG. 5, the image selection device 11 includes a public article acquisition unit 111, a public article information extraction unit 112, a similar image search unit 116, in addition to the functions of the image selection device 10 shown in FIG. And an unowned image DB 211. In addition, about the same function as Embodiment 1, the same referential mark is attached | subjected and description is abbreviate | omitted.

<Each DB of Image Selection Device>
Next, differences between the image related information DB 214 according to the second embodiment and the image related information DB 204 according to the first embodiment (see FIG. 3) will be described with reference to FIG. As illustrated in FIG. 6, the image related information DB 214 manages the image ID 351 in association with the owned image flag 358.

  The image ID 351 is an identifier of an image registered in the owned image DB 203 or the unowned image DB 211.

  The keyword 352 is a keyword associated with the image ID 351. The keyword 352 is a keyword associated in advance when the image with the image ID 351 is an owned image, and the keyword extracted from the published article to which the unowned image is attached when the image with the image ID 351 is an unowned image. It is.

  The owned image flag 358 is a flag indicating whether or not the image with the image ID 351 is an owned image. For example, the owned image flag 358 “YES” indicates that the image with the image ID 351 is an owned image, and the owned image flag 358 “NO” indicates that the image with the image ID 351 is an unowned image.

<Each function of the image selection device>
Next, differences between the image selection device 11 according to the second embodiment and the image selection device 10 according to the first embodiment (see FIG. 2) will be described.

  The published article acquisition unit 111 acquires published articles from the article publication server 22 via a predetermined network (for example, the Internet).

  The published article information extraction unit 112 extracts an unowned image from the published article acquired by the published article acquisition unit 111, assigns an image ID, and registers it in the unowned image DB 211. Also, the published article information extraction unit 112 extracts a keyword from the published article using the keyword dictionary 202, associates the extracted keyword with the image ID assigned above, and registers the keyword in the image related information DB 214. . At this time, the published article information extraction unit 112 sets the owned image flag 358 associated with the image ID to “NO”.

  Similar to the complementary image determination unit 105 described in the first embodiment, the complementary image determination unit 115 receives a text-only distribution article and keyword from the distribution article information extraction unit 104, and based on the keyword and the image related information DB 214. Thus, a complementary image to be attached to the distribution article only of the text is determined. Details of the complementary image determination process in the complementary image determination unit 115 will be described later.

  When the complementary image determined by the complementary image determination unit 115 is an unowned image, the similar image search unit 116 searches for an owned image similar to the unowned image. The similar image search unit 116 may search for similar images using a known technique. For example, the similar image search unit 116 performs machine learning in advance on the characteristics of various objects included in the image. Then, the similar image search unit 116 recognizes the feature of the object included in the unowned image, and searches the owned image DB 203 for the owned image including the similar object feature. Then, the similar image search unit 116 sets, as the similar images, owned images whose feature matching degrees are equal to or greater than a predetermined threshold among the owned images of the search results.

<Details of complementary image determination processing>
Hereinafter, the flow and specific example of the complementary image determination process will be described.

  First, the flow of complementary image determination processing will be described using the flowchart of FIG.

  First, the complementary image determination unit 115 executes the processing of S101 to S107 shown in FIG.

  Next, the complementary image determination unit 115 refers to the owned image flag 358 and determines whether or not the complementary image determined in ST107 is an owned image (ST201).

  When the complementary image is the possessed image (ST201: YES), the complementary image determination unit 115 ends this processing as it is.

  When the complementary image is an unowned image (ST201: NO), the similar image search unit 116 searches the owned image DB 203 for an owned image similar to the complementary image (ST202). Then, the complementary image determination unit 115 replaces the complementary image determined in ST107 with one of the similar owned images searched in ST202 (ST203), and ends this process.

  Next, a specific example of the complementary image determination process will be described with reference to FIG. For example, when “Tokyo Olympics” and “Golf” are included in the distribution article, the complementary image determination unit 115 stores the image ID 351 “G11 associated with the keyword 352 that matches the keyword from the image related information DB 214. ”,“ G21 ”, and“ G22 ”are extracted as candidate image IDs. Then, since the image interest degree 306 of the candidate image ID “G21” is the highest “0.17” among these three candidate image IDs, the complementary image determination unit 115 first complements the candidate image ID “G21”. The image ID is determined. However, since the owned image flag 358 of the complementary image ID “G21” is “NO”, the similar image search unit 116 searches for an image similar to the complementary image ID “G21”. For example, it is assumed that the owned image ID “G22” is searched. In this case, the complementary image determination unit 115 replaces the complementary image ID from “G21” to “G22”.

<Effect of Embodiment 2>
As described above, in the image selection device 11 according to the second embodiment, not only the owned image published by attachment of the image selection device 11 but also the unowned image originally attached to the distribution article and published. The degree of interest is calculated, and the complementary image to be attached to the text-only distribution article is determined using the image having the highest degree of image interest among these owned and unowned images. This makes it possible to select an image with the highest image interest level from among a larger number of images compared to selecting an image with the highest image interest level from only the owned images. The user selection rate (viewing rate) of the attached distribution article can be further increased.

  In addition, when the image having the highest degree of image interest is an unowned image, priority can be given to using the owned image instead of the unowned image by replacing it with an owned image similar to the unowned image. When the unowned image extracted from the published article can be freely used, the published article information extraction unit 112 registers the unowned image in the owned image DB 203. Thereby, the image selection apparatus 11 can use the unowned image as the owned image.

(Hardware configuration)
In addition, the block diagram used for description of the said embodiment has shown the block of the functional unit. These functional blocks (components) are realized by any combination of hardware and / or software. Further, the means for realizing each functional block is not particularly limited. That is, each functional block may be realized by one device physically and / or logically coupled, and two or more devices physically and / or logically separated may be directly and / or indirectly. (For example, wired and / or wireless) and may be realized by these plural devices.

  For example, a radio base station, a user terminal, etc. in an embodiment of the present invention may function as a computer that performs processing of the radio communication method of the present invention. FIG. 8 is a diagram illustrating an example of a hardware configuration of the image selection apparatuses 10 and 11 according to the embodiment of the present invention. The image selection devices 10 and 11, the article providing server 21, the article publishing server 22, and the portable terminal 23 described above physically include a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, You may comprise as a computer apparatus containing the bus | bath 1007 grade | etc.,.

  In the following description, the term “apparatus” can be read as a circuit, a device, a unit, or the like. The hardware configurations of the image selection devices 10 and 11, the article providing server 21, the article publishing server 22, and the mobile terminal 23 may be configured to include one or a plurality of the devices illustrated in the figure, or a part of them. You may comprise without an apparatus.

  The functions of the image selection apparatuses 10 and 11, the article providing server 21, the article publishing server 22, and the mobile terminal 23 are read by predetermined software (programs) on hardware such as the processor 1001 and the memory 1002, thereby allowing the processor 1001. Is performed by controlling communication by the communication device 1004 and reading and / or writing of data in the memory 1002 and the storage 1003.

  For example, the processor 1001 controls the entire computer by operating an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like. For example, the above-described totaling unit 101, image interest level calculating unit 102, distributed article acquiring unit 103, distributed article information extracting unit 104, complementary image determining units 105 and 115, published article generating unit 106, published article acquiring unit 111, published article The information extraction unit 112, the similar image search unit 116, and the like may be realized by the processor 1001.

  Further, the processor 1001 reads a program (program code), software module, and data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, the functions of the image selection devices 10 and 11, the article providing server 21, the article publishing server 22, and the mobile terminal 23 may be realized by a control program stored in the memory 1002 and operating on the processor 1001. Although the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

  The memory 1002 is a computer-readable recording medium and includes, for example, at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), and the like. May be. The memory 1002 may be called a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store a program (program code), a software module, and the like that can be executed to implement the wireless communication method according to the embodiment of the present invention.

  The storage 1003 is a computer-readable recording medium such as an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (for example, a compact disk, a digital versatile disk, a Blu-ray (Registered trademark) disk, smart card, flash memory (for example, card, stick, key drive), floppy (registered trademark) disk, magnetic strip, and the like. The storage 1003 may be referred to as an auxiliary storage device. The storage medium described above may be, for example, a database, server, or other suitable medium including the memory 1002 and / or the storage 1003. For example, the application log DB 201, the keyword dictionary 202, the owned image DB 203, the image related information DB 204, and the unowned image DB 211 may be configured by the memory 1002 and / or the storage 1003.

  The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also referred to as a network device, a network controller, a network card, a communication module, or the like. For example, the distribution article acquisition unit 103 and the public article acquisition unit 111 described above may be realized by the communication device 1004.

  The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, or the like) that accepts an external input. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).

  Each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured with a single bus or may be configured with different buses between apparatuses.

The image selection devices 10 and 11, the article providing server 21, the article publishing server 22, and the portable terminal 23 include a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), and a programmable logic (PLD). Device), FPGA (Field Programmable Gate Array) or the like may be included, and a part or all of each functional block may be realized by the hardware. For example, the processor 1001 may be implemented by at least one of these hardware.
May be sent to.

(Judgment method)
The determination may be performed by a value represented by 1 bit (0 or 1), may be performed by a true / false value (Boolean: true or false), or may be performed by comparing numerical values (for example, a predetermined value) Comparison with the value).

(Aspect variations, etc.)
Each aspect / embodiment described in this specification may be used independently, may be used in combination, or may be switched according to execution. In addition, notification of predetermined information (for example, notification of being “X”) is not limited to explicitly performed, but is performed implicitly (for example, notification of the predetermined information is not performed). Also good.

  Although the present invention has been described in detail above, it will be apparent to those skilled in the art that the present invention is not limited to the embodiments described herein. The present invention can be implemented as modified and changed modes without departing from the spirit and scope of the present invention defined by the description of the scope of claims. Therefore, the description of the present specification is for illustrative purposes and does not have any limiting meaning to the present invention.

  (Meaning and interpretation of terms)

(software)
Software, whether it is called software, firmware, middleware, microcode, hardware description language, or other names, instructions, instruction sets, codes, code segments, program codes, programs, subprograms, software modules , Applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc. should be interpreted broadly.

  Also, software, instructions, etc. may be transmitted / received via a transmission medium. For example, software may use websites, servers, or other devices using wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or wireless technology such as infrared, wireless and microwave. When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission media.

(Information, signal)
Information, signals, etc. described herein may be represented using any of a variety of different technologies. For example, data, commands, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description are voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these May be represented by a combination of

  Note that the terms described in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meaning. For example, the channel and / or symbol may be a signal. The signal may be a message. Further, the component carrier (CC) may be called a carrier frequency, a cell, or the like.

("System", "Network")
As used herein, the terms “system” and “network” are used interchangeably.

(Parameter name)
In addition, information, parameters, and the like described in this specification may be represented by absolute values, may be represented by relative values from a predetermined value, or may be represented by other corresponding information. .

  The names used for the parameters described above are not limiting in any way. Further, mathematical formulas and the like that use these parameters may differ from those explicitly disclosed herein.

("Connected", "coupled")
The terms “connected”, “coupled”, or any variation thereof, means any direct or indirect connection or coupling between two or more elements and It can include the presence of one or more intermediate elements between two “connected” or “coupled” elements. The coupling or connection between the elements may be physical, logical, or a combination thereof. As used herein, the two elements are radio frequency by using one or more wires, cables and / or printed electrical connections, and as some non-limiting and non-inclusive examples By using electromagnetic energy, such as electromagnetic energy having a wavelength in the region, microwave region, and light (both visible and invisible) region, it can be considered to be “connected” or “coupled” to each other.

(Meaning “based on”)
As used herein, the phrase “based on” does not mean “based only on,” unless expressly specified otherwise. In other words, the phrase “based on” means both “based only on” and “based at least on.”

("First", "second")
Any reference to elements using the designations "first", "second", etc. as used herein does not generally limit the amount or order of those elements. These designations can be used herein as a convenient way to distinguish between two or more elements. Thus, a reference to the first and second elements does not mean that only two elements can be employed there, or that in some way the first element must precede the second element.

("means")
The “means” in the configuration of each apparatus described above may be replaced with “unit”, “circuit”, “device”, and the like.

(Open format)
As long as “including”, “comprising”, and variations thereof are used in the specification or claims, these terms are inclusive of the term “comprising”. Intended to be Furthermore, the term “or” as used herein or in the claims is not intended to be an exclusive OR.

(article)
Throughout this disclosure, if articles are added by translation, for example, a, an, and the in English, these articles must be clearly indicated otherwise in context, Including multiple things.

DESCRIPTION OF SYMBOLS 10, 11 Image selection apparatus 21 Article provision server 22 Article publication server 23 Portable terminal 101 Counting part 102 Image interest level calculation part 103 Distribution article acquisition part 104 Distribution article information extraction part 105,115 Complementary image determination part 106 Public article production | generation part 111 Published article acquisition unit 112 Published article information extraction unit 116 Similar image search unit 201 Application log DB
202 Keyword dictionary 203 Owned image DB
204, 214 Image related information DB
211 Unowned image DB

Claims (10)

An image selection device for selecting an image to be attached to a distribution article,
An image interest calculation unit that calculates the user's image interest in the image attached to the published article;
A management unit that manages the image, the keyword, and the degree of image interest in the image in association with each other;
From the management unit, an image associated with a keyword that matches a keyword included in the distribution article is selected as a candidate image, and attached to the distribution article from the candidate images based on the degree of image interest A complementary image determination unit for determining a complementary image to be
An image selection device comprising: The image interest degree calculation unit
Calculating the degree of image interest based on the number of articles selected, which is the number of times the published article has been selected by the user;
The image selection device according to claim 1. The image interest degree calculation unit
Calculating the degree of image interest based on the ratio of the number of article selections to the number of image displays, which is the number of times an image attached to the published article is displayed;
The image selection device according to claim 2. The degree of image interest is a value that increases as the number of article selections increases and decreases as the number of image displays increases.
The image selection device according to claim 3. The complementary image determination unit
From the candidate images, determine the image with the highest degree of image interest as a complementary image to be attached to the distribution article.
The image selection device according to any one of claims 1 to 4. The complementary image determination unit
When the determined complementary image is the same as the complementary image attached to another distribution article released within a predetermined period, the image having the second highest image interest level is attached when the distribution article is published. Decide on a complementary image,
The image selection device according to any one of claims 1 to 5. The management unit further manages the image and the genre of the article in association with each other,
The complementary image determination unit
If there is no image in the management unit that is associated with a keyword that matches a keyword included in the distribution article, an image that is associated with a genre that matches the genre of the distribution article is selected as a candidate image. ,
The image selection device according to any one of claims 1 to 6. A public article information extracting unit that associates an image attached to the published article with a keyword extracted from the published article and registers the image in the management unit;
The image selection device according to any one of claims 1 to 7. The complementary image determination unit
If the determined complementary image is not a pre-owned image, replace the determined complementary image with any pre-owned image,
The image selection device according to claim 8. An image selection method for selecting an image to be attached to a distribution article,
Calculate the user ’s interest in the image attached to the published article,
Managing the image, the keyword, and the image interest level for the image in association with each other;
From the managed images, select an image associated with a keyword that matches the keyword included in the distribution article as a candidate image,
Determining a complementary image to be attached to the distribution article from the candidate images based on the degree of image interest;
Image selection method.