JP7036695B2 - Distribution device and distribution method - Google Patents

Description

The present invention relates to a distribution device, a distribution method, a display terminal, a display program, and a display method for distributing electronic contents.

Conventionally, a service of displaying a list of headlines associated with contents such as news articles and displaying detailed articles by a user selecting one of the headlines has become widespread (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2008-176491

Such a service may cut out a part of the image included in each article and display it as a thumbnail image in the vicinity of the headline so that the user can visually grasp the content of the article. The size of the thumbnail image that can be displayed is limited in order to ensure the listability of the headline. Therefore, if you cut out a fixed position (for example, the upper part or the center part) in the image, the part of the image that is not related to the content of the article will become a thumbnail image, and even if the user sees the thumbnail image, the content of the article will be displayed. There were times when I couldn't figure it out.

The present invention has been made in view of the above points, and a distribution device, a distribution method, a display terminal, a display program, and a distribution device, a distribution method, a display terminal, and a display program capable of displaying a thumbnail image in which the content of the content is easy for the user to understand based on the image included in the content. The purpose is to provide a display method.

The distribution device according to the first aspect of the present invention includes an acquisition unit for acquiring content including an image and a sentence, calculates a feature amount of a subject in the image, and is one of the images based on the calculated feature amount. A specific part that specifies the range of the part, a generation part that generates a partial image by cutting out the range in the image, and information for displaying the first screen including the partial image are transmitted to the display terminal. In addition, it has a transmission unit that transmits information for displaying the second screen including the content to the display terminal when the user selects an element associated with the content on the first screen.

The specific unit may recognize a person or mark in the image based on the feature amount, and may specify the range including the recognized person or mark.

When a plurality of persons or marks are recognized in the image, the specific unit may specify the range including the recognized plurality of persons or marks.

The specific unit may specify the range by comparing the feature amount with the reference feature amount stored in the storage unit.

The specific unit acquires the reference feature amount associated with the name of the person or group included in the sentence from the storage unit, and specifies the range based on the feature amount and the reference feature amount. May be good.

The specific unit may acquire the reference feature amount that matches the taste of the user from the storage unit, and specify the range based on the feature amount and the reference feature amount.

The generation unit generates a plurality of the partial images by cutting out the ranges different from each other in the image, and the transmission unit generates the user's selection status for the plurality of the partial images among the plurality of the partial images. Information for displaying the first screen including any one of the partial images statistically selected based on the above may be transmitted to the display terminal.

The specific unit may change the size of the partial image or the size of the range based on the attributes of the user.

In the distribution method of the second aspect of the present invention, the processor acquires a content including an image and a sentence, calculates a feature amount of a subject in the image, and the image is based on the calculated feature amount. A step of specifying a part of the range of the image, a step of generating a partial image by cutting out the range in the image, and information for displaying the first screen including the partial image are transmitted to the display terminal. At the same time, when the user selects an element associated with the content on the first screen, the step of transmitting information for displaying the second screen including the content to the display terminal is executed.

The display terminal according to the third aspect of the present invention includes an acquisition unit that acquires content including an image and a sentence, calculates a feature amount of a subject in the image, and is one of the images based on the calculated feature amount. A specific part that specifies the range of the part, a generation part that generates a partial image by cutting out the range in the image, and a first screen including the partial image are displayed, and the content is displayed on the first screen. It has a display unit for displaying a second screen including the content when the user selects an element associated with.

The specific unit may recognize a person or mark in the image based on the feature amount, and may specify the range including the recognized person or mark.

The specific unit may specify the range by comparing the feature amount with the reference feature amount stored in the storage unit.

The specific unit acquires the reference feature amount associated with the name of the person or group included in the sentence from the storage unit, and specifies the range based on the feature amount and the reference feature amount. May be good.

In the display program of the fourth aspect of the present invention, the step of acquiring the content including the image and the text on the display terminal, the feature amount of the subject in the image is calculated, and the feature amount is calculated based on the calculated feature amount. A step of specifying a partial range of an image, a step of generating a partial image by cutting out the range in the image, and a first screen including the partial image are displayed, and the first screen includes the above. When the user selects an element associated with the content, the step of displaying the second screen including the content is executed.

In the display method of the fifth aspect of the present invention, the processor acquires a content including an image and a sentence, calculates a feature amount of a subject in the image, and the image is based on the calculated feature amount. A step of specifying a part of the range, a step of generating a partial image by cutting out the range in the image, a first screen including the partial image is displayed, and the content is displayed on the first screen. When the user selects an element associated with, the step of displaying the second screen including the content is executed.

According to the present invention, it is possible to display a thumbnail image in which the content of the content is easy for the user to understand based on the image included in the content.

It is a schematic diagram of the distribution system which concerns on 1st Embodiment. It is a block diagram of the distribution system which concerns on 1st Embodiment. It is a front view of the display terminal which displays the content list screen and the detail screen. It is a schematic diagram of the feature information stored in the feature information storage part. It is a schematic diagram of the method in which a range specifying part and a partial image generation part generate a partial image based on an image. It is a schematic diagram of the method of specifying the range when a plurality of people or marks are detected in an image. It is a figure which shows the flowchart of the delivery method which concerns on 1st Embodiment. It is a block diagram of the distribution system which concerns on 2nd Embodiment. It is a schematic diagram of the feature information stored in the feature information storage part. It is a schematic diagram of the user information stored in the user information storage unit. It is a schematic diagram of the method in which a range specifying part and a partial image generation part generate a partial image based on an image. It is a schematic diagram of the user information stored in the user information storage unit. It is a schematic diagram which shows the selection situation of the user in the list screen.

(First Embodiment)
[Overview of distribution system S]
FIG. 1 is a schematic diagram of a distribution system S according to the present embodiment. The distribution system S includes a distribution server 1 and a display terminal 2. The distribution system S may include other devices such as servers and terminals.

The distribution server 1 (distribution device) is a computer capable of performing wired or wireless communication and transmitting data for displaying electronic contents (hereinafter referred to as contents) to the display terminal 2. Content includes text (text) and images (still or moving images). The distribution server 1 transmits data for displaying contents to the display terminal 2 via a network N such as the Internet or a local area network.

The display terminal 2 is a communication device capable of performing wired or wireless communication and displaying contents acquired by communication. For example, the display terminal 2 is a mobile terminal such as a smartphone or a tablet terminal, or a personal computer. The display terminal 2 receives data for displaying the content via the network N from the distribution server 1 and displays the content.

[Configuration of distribution system S]
FIG. 2 is a block diagram of the distribution system S according to the present embodiment. In FIG. 2, the arrows indicate the main data flows, and there may be data flows other than those shown in FIG. In FIG. 2, each block shows not a hardware (device) unit configuration but a functional unit configuration. Therefore, the block shown in FIG. 2 may be mounted in a single device, or may be mounted separately in a plurality of devices. Data can be exchanged between blocks via any means such as a data bus, a network, and a portable storage medium.

The distribution server 1 has a control unit 11 and a storage unit 12. The control unit 11 includes an operation reception unit 111, a content acquisition unit 112, a range specifying unit 113, a partial image generation unit 114, and a transmission unit 115. The storage unit 12 has a content storage unit 121 and a feature information storage unit 122.

The storage unit 12 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk drive, and the like. The storage unit 12 stores in advance the program executed by the control unit 11. The storage unit 12 may be provided outside the distribution server 1, and in that case, data may be exchanged with the control unit 11 via a network.

The content storage unit 121 stores data for displaying the content. The feature information storage unit 122 stores feature information for detecting a predetermined subject in an image. The content storage unit 121 and the feature information storage unit 122 may each be a storage area on the storage unit 12, or may be a database configured on the storage unit 12.

The control unit 11 is, for example, a processor such as a CPU (Central Processing Unit), and by executing a program stored in the storage unit 12, the operation reception unit 111, the content acquisition unit 112, the range specifying unit 113, and the partial image generation It functions as a unit 114 and a transmission unit 115. At least some of the functions of the control unit 11 may be performed by an electric circuit. Further, at least a part of the functions of the control unit 11 may be executed by a program executed via the network.

The display terminal 2 has a display unit 21 and an operation unit 22. The display unit 21 includes a display device capable of displaying information such as a liquid crystal display. The operation unit 22 includes an operation device such as a keyboard and a mouse that can accept user operations. The display unit 21 and the operation unit 22 may be integrally configured by using a touch screen capable of detecting the position of contact by the user as the display unit 21.

The distribution system S according to the present embodiment is not limited to the specific configuration shown in FIG. The distribution server 1 and the display terminal 2 are not limited to one device each, and may be configured by connecting two or more physically separated devices by wire or wirelessly.

[Explanation of delivery method]
The content storage unit 121 stores in advance image and text data included in content such as news articles. Here, the content storage unit 121 stores the data of the news article as the content, but may store the data of other types of content. Further, the content storage unit 121 stores the data of the partial image generated by cutting out a part of the image included in the content by the range specifying unit 113 and the partial image generation unit 114, which will be described later, in association with the content.

FIG. 3A is a front view of the display terminal 2 displaying the content list screen A. The list screen A (first screen) includes one or more partial images A1 and one or more headings A2. The partial image A1 (also referred to as a thumbnail image) is an image obtained by cutting out a part of the image B1 included in the content. The heading A2 is the title of the sentence B2 included in the content. The partial image A1 and the heading A2 are elements associated with the content and are linked to the detail screen B of the content.

FIG. 3B is a front view of the display terminal 2 displaying the content detail screen B. The detail screen B (second screen) includes an image B1 and a sentence B2. The image B1 is an image included in the content and is an image that is the source of the partial image A1. The sentence B2 is a sentence included in the content.

In the distribution method according to the present embodiment, when the user of the display terminal 2 wants to view the list screen A, the operation unit 22 is used to perform an operation for displaying the list screen A. The display terminal 2 transmits information indicating an operation for displaying the list screen A to the distribution server 1.

In the distribution server 1, the operation reception unit 111 receives and receives information indicating an operation for displaying the list screen A from the display terminal 2. The content acquisition unit 112 of the partial image A1 associated with one or more contents displayed on the list screen A when the operation reception unit 111 receives information indicating an operation for displaying the list screen A. The data and the data of the heading A2 are acquired from the content storage unit 121. The content displayed on the list screen A may be automatically specified based on a predetermined rule. In this case, for example, the content acquisition unit 112 acquires a predetermined number of contents in the order of newest recorded time. Alternatively, the content displayed on the list screen A may be manually specified in advance by the administrator of the distribution server 1 or the like.

When the data of the partial image A1 associated with the content displayed on the list screen A is not stored in the content storage unit 121, the range specifying unit 113 and the partial image generation unit 114 may display the content displayed on the list screen A. A partial image A1 is generated based on the image B1 included in.

Specifically, the range specifying unit 113 acquires the data of the image B1 included in the content displayed on the list screen A from the content storage unit 121 and the feature information from the feature information storage unit 122.

FIG. 4 is a schematic diagram of the feature information C stored in the feature information storage unit 122. The feature information C is information indicating a feature amount for detecting a subject such as a person or a mark (company logo) in an image. In this embodiment, the person and mark are not a specific person and mark, but a general person and mark. The feature information storage unit 122 stores the feature information C of one or more representative or average persons. Further, the feature information storage unit 122 stores the feature information C of one or a plurality of representative or average marks.

The feature information C indicates the type C1 and the feature amount C2 associated with the type C1. The type C1 is a type such as a person or a mark. The feature amount C2 is a value representing a feature for detecting a person (person's face) or a mark (whole mark). The feature amount C2 may be a distribution of luminance values of a plurality of pixels of an image (template image) including a person or a mark. Further, the feature amount C2 may be a relative position of a predetermined portion (for example, the eyes, nose, mouth, outline of the mark, etc. of the person) in the image including the person or the mark.

Further, the feature amount C2 may be a value calculated according to a predetermined rule from the luminance values of a plurality of pixels of an image including a person or a mark (for example, a HOG feature amount, a Haar-Like feature amount). Further, the feature amount C2 may be a feature amount automatically extracted from an image including a person or a mark by deep learning (deep neural network). The feature amount C2 is not limited to the specific value shown here, and may be another value capable of detecting a subject such as a person or a mark in an image.

In FIG. 4, the feature information C is represented by a table of character strings for visibility, but each data may be recorded in any format, and may be, for example, any of character string data, numerical data, and binary data. .. The feature information C may be recorded as a database or may be recorded as a list listing data.

5 (a) and 5 (b) are schematic views of a method in which the range specifying unit 113 and the partial image generation unit 114 generate the partial image A1 based on the image B1. FIG. 5A shows an example of generating a partial image A1 including a person based on the image B1, and FIG. 5B shows an example of generating a partial image A1 including a mark based on the image B1. There is.

First, the range specifying unit 113 calculates the feature amount in the predetermined range including one position in the image B1 by the same method as the feature amount C2 of the feature information C. The range specifying unit 113 compares the feature amount C2 (that is, the reference feature amount) of each feature information C stored in the feature information storage unit 122 with the calculated feature amount. Then, when the relationship between the feature amount C2 of any of the feature information C and the calculated feature amount satisfies a predetermined condition, the range specifying unit 113 detects a person or a mark. For example, the range specifying unit 113 calculates the similarity (Euclidean distance, etc.) between the feature amount C2 of the feature information C and the calculated feature amount, and when the calculated similarity is equal to or more than a predetermined value, the person or Detect the mark.

The range specifying unit 113 repeats the calculation of the feature amount and the detection of the person or the mark for each position in the image B1 and records the position where the person or the mark is detected. The range specifying unit 113 may end the detection of the person or the mark when a predetermined number of people or the mark are detected. Then, the range specifying unit 113 specifies a range R having a predetermined size including a position where a person or a mark is detected in the image B1.

When a plurality of persons or marks are detected in the image B1, the range specifying unit 113 includes a plurality of persons or marks, or includes one person or mark selected from a plurality of persons or marks. , Specify the range R.

FIG. 6A is a schematic diagram of a method of specifying a range R including a plurality of persons or marks when a plurality of persons or marks are detected in the image B1. When a plurality of persons or marks are detected in the image B1, the range specifying unit 113 calculates the center point R1 (for example, the center of gravity) of the positions of the plurality of persons or marks. Then, the range specifying unit 113 specifies a range R having a predetermined size including the center point R1. At this time, the range specifying unit 113 may change the size of the range R so that the range R including the center point R1 includes a plurality of persons or marks. As a result, the distribution server 1 can generate a partial image A1 including a plurality of people or marks in the image B1.

FIG. 6B is a schematic diagram of a method of specifying a range R including one person or mark selected from a plurality of people or marks when a plurality of people or marks are detected in the image B1. When the range specifying unit 113 detects a plurality of persons or marks in the image B1, any one of the plurality of persons or marks or one of the plurality of persons or marks is based on the relative positional relationship between the plurality of persons or marks. Select a mark. For example, when a plurality of persons or marks are detected in the image B1, the range specifying unit 113 selects the person or mark located at the top of the plurality of persons or marks. As a result, the distribution server 1 can generate a partial image A1 that selectively includes one person or mark when the image B1 includes a plurality of people or marks.

The range specifying unit 113 may always select one person or mark, or may select one person or mark when the distance between the plurality of persons or marks is a predetermined value or more. Further, when both the person and the mark are detected in the image B1, the range specifying unit 113 may preferentially select the person or may preferentially select the mark.

The partial image generation unit 114 generates a partial image A1 by cutting out a range R specified by the range specifying unit 113 in the image B1, and stores the partial image A1 in the content storage unit 121 in association with the content including the original image B1. .. The transmission unit 115 transmits information for displaying the list screen A including the partial image A1 and the heading A2 to the display terminal 2. The display terminal 2 displays the list screen A illustrated in FIG. 3A on the display unit 21 based on the information received from the distribution server 1.

When the user of the display terminal 2 wants to view the detail screen B, he / she performs an operation for displaying the detail screen B by using the operation unit 22. The operation for displaying the detail screen B is an operation for selecting any one of the partial images A1 or the heading A2 in the list screen A. The display terminal 2 transmits information indicating the content associated with the selected partial image A1 or the heading A2 to the distribution server 1.

In the distribution server 1, the operation receiving unit 111 receives and receives information indicating the content associated with the selected partial image A1 or the heading A2 from the display terminal 2. The content acquisition unit 112 acquires the data of the image B1 and the data of the sentence B2 associated with the content indicated by the information received by the operation reception unit 111 from the content storage unit 121.

The transmission unit 115 transmits information for displaying the detail screen B including the image B1 and the text B2 to the display terminal 2. The display terminal 2 displays the detailed screen B illustrated in FIG. 3B on the display unit 21 based on the information received from the distribution server 1.

In this way, since the distribution server 1 identifies the range R including the person or the mark in the image B1 and reflects it in the partial image A1, the distribution server 1 generates the partial image A1 in which the content of the content is easy for the user to understand, and the display terminal 2 Can be sent to.

[Flowchart of delivery method]
FIG. 7 is a diagram showing a flowchart of the distribution method according to the present embodiment. First, the user of the display terminal 2 performs an operation for displaying the list screen A using the operation unit 22 when he / she wants to view the list screen A, and uses the operation unit 22 when he / she wants to view the detail screen B. Perform an operation to display B. In the distribution server 1, the operation receiving unit 111 receives and receives information indicating an operation by the user from the display terminal 2 (S11).

When the operation reception unit 111 receives an operation for displaying the list screen A (YES in S12), the content acquisition unit 112 is a partial image associated with one or more contents displayed on the list screen A. The data of A1 and the data of the heading A2 are acquired from the content storage unit 121 (S13).

When the content acquisition unit 112 can acquire the partial image A1 (YES in S14), the distribution server 1 proceeds to S18. When the content acquisition unit 112 cannot acquire the partial image A1 (NO in S14), the range specifying unit 113 acquires the data of the image B1 included in the content displayed on the list screen A from the content storage unit 121. At the same time, the feature information C is acquired from the feature information storage unit 122.

The range specifying unit 113 calculates the feature amount using the acquired image B1, and sets the feature amount C2 (that is, the reference feature amount) of each feature information C stored in the feature information storage unit 122 and the calculated feature amount. Compare. Then, when the relationship between the feature amount C2 of any of the feature information C and the calculated feature amount satisfies a predetermined condition, the range specifying unit 113 detects a person or a mark (S15).

The range specifying unit 113 specifies a range R having a predetermined size including a position where a person or a mark is detected in the image B1 (S16). The partial image generation unit 114 generates a partial image A1 by cutting out a range R specified by the range specifying unit 113 in the image B1, and stores the partial image A1 in the content storage unit 121 in association with the content including the original image B1. (S17).

The transmission unit 115 includes a partial image A1 acquired by the content acquisition unit 112 in step S13, a partial image A1 generated by the partial image generation unit 114 in step S17, and a heading A2 acquired by the content acquisition unit 112 in step S13. Information for displaying the list screen A is transmitted to the display terminal 2 (S18). The display terminal 2 displays the list screen A on the display unit 21 based on the information received from the distribution server 1.

When the operation reception unit 111 receives an operation for displaying the detail screen B (NO in S12), the content acquisition unit 112 of the image B1 associated with the content indicated by the information received by the operation reception unit 111. The data and the data of the sentence B2 are acquired from the content storage unit 121 (S19).

The transmission unit 115 transmits information for displaying the detail screen B including the image B1 and the text B2 acquired by the content acquisition unit 112 in step S19 to the display terminal 2 (S20). The display terminal 2 displays the detail screen B on the display unit 21 based on the information received from the distribution server 1.

In the flowchart illustrated in FIG. 7, the distribution server 1 generates a partial image A1 for the image B1 of the content included in the list screen A at the timing of displaying the list screen A, and the image B1 of the content not included in the list screen A. Does not generate a partial image A1. Therefore, the distribution server 1 can reduce the capacity required for the content storage unit 121 to store the partial image A1. Alternatively, the distribution server 1 may generate partial images A1 for all images B1 at the timing of storing the images B1 in the content storage unit 121. In this case, since the distribution server 1 does not perform the process of generating the partial image A1 when displaying the list screen A, the time required for display can be shortened.

[Effect of embodiment]
The distribution server 1 according to the present embodiment identifies a range R including a person or a mark in the image B1 and cuts out the range R from the image B1 to generate and transmit a partial image A1. Therefore, it is highly probable that the partial image A1 includes a subject related to the content of the content, and the partial image A1 in which the content of the content is easy to understand can be provided to the user.

[Modification example]
In the above example, the distribution server 1 generates the partial image A1, but the display terminal 2 may generate the partial image A1. In this case, the display terminal 2 includes a control unit 11 having the above-mentioned operation reception unit 111, content acquisition unit 112, range specifying unit 113, and partial image generation unit 114. The data of the content storage unit 121 and the feature information storage unit 122 may be stored in the storage unit 12 of the distribution server 1 or may be stored in the storage unit of the display terminal 2.

In the display terminal 2 according to this modification, the operation reception unit 111 receives information indicating an operation for displaying the list screen A from the operation unit 22. The content acquisition unit 112 of the partial image A1 associated with one or more contents displayed on the list screen A when the operation reception unit 111 receives information indicating an operation for displaying the list screen A. The data and the data of the heading A2 are received from the distribution server 1 and acquired.

When the data of the partial image A1 associated with the content displayed on the list screen A is not stored in the content storage unit 121, the content acquisition unit 112 is the image B1 included in the content displayed on the list screen A. Data is received from the distribution server 1 and acquired. The range specifying unit 113 and the partial image generation unit 114 generate the partial image A1 based on the image B1 by the method described above, or by the method according to the second embodiment or the third embodiment described later.

The display unit 21 displays the list screen A illustrated in FIG. 3A based on the information received from the distribution server 1 and the partial image A1 generated by the range specifying unit 113 and the partial image generation unit 114.

Further, the operation reception unit 111 receives information indicating the content associated with the partial image A1 or the heading A2 selected on the list screen A from the operation reception unit 22. The content acquisition unit 112 receives and acquires the data of the image B1 and the data of the sentence B2 associated with the content indicated by the information received by the operation reception unit 111 from the distribution server 1.

The display unit 21 displays the detailed screen B illustrated in FIG. 3B based on the information received from the distribution server 1.

In this way, the display terminal 2 can utilize the computational resources of the display terminal 2 by generating and displaying the partial image A1 based on the image B1.

(Second embodiment)
The distribution server 1 according to the first embodiment generates a partial image A1 by detecting a general person and a mark, whereas the distribution server 1 according to the present embodiment has a specific person and a specific person in the image. The partial image A1 is generated by recognizing the mark. Hereinafter, the differences from the first embodiment will be mainly described.

FIG. 8 is a block diagram of the distribution system S according to the present embodiment. The storage unit 12 of the distribution server 1 according to the present embodiment has a user information storage unit 123 in addition to the content storage unit 121 and the feature information storage unit 122. The user information storage unit 123 stores user information data indicating information about the user of the display terminal 2. The user information storage unit 123 may be a storage area on the storage unit 12, or may be a database configured on the storage unit 12.

FIG. 9 is a schematic diagram of the feature information C stored in the feature information storage unit 122. The feature information C is information indicating a feature amount for detecting a subject such as a person or a mark in an image. In the present embodiment, the person and the mark are a specific person (that is, an individual) and a specific mark (that is, a logo of a specific company, etc.). The feature information storage unit 122 stores the feature information C of a specific person or a plurality of persons. Further, the feature information storage unit 122 stores the feature information C of a specific one or a plurality of marks.

The feature information C indicates the name C3 and the feature amount C2 associated with the name C3. The name C3 is the name of a person (name, nickname, etc.) and the name of a group (company name, abbreviation, etc.). The definition of the feature amount C2 is the same as that of the first embodiment.

FIG. 10 is a schematic diagram of the user information D stored in the user information storage unit 123. The user information D is information about the user of the display terminal 2. The user information storage unit 123 stores the user information D of each user in advance.

The user information D indicates the user's identification information D1 and the preference D2. The identification information D1 is identification information (user ID, telephone number, e-mail address, etc.) for identifying the user. Preference D2 is the name of a person or group preferred by the user.

The distribution server 1 may determine the preference D2 based on the history of the user browsing the content of the detail screen B in the past. For example, when one user displays content including the name of a certain person or group a predetermined number of times or more, the distribution server 1 associates the identification information D1 of the user with the preference D2 indicating the name of the person or group. Then, it is stored in the user information storage unit 123 as the user information D.

Further, the distribution server 1 takes a questionnaire to ask the user to answer the name of the person or group of preference, associates the identification information D1 of the user with the preference D2 indicating the name of the person or group, and user information. It may be stored in the user information storage unit 123 as D.

In FIGS. 9 and 10, the feature information C and the user information D are represented by a table of character strings for visibility, but each data may be recorded in any format, for example, character string data and numerical data. And binary data. The feature information C and the user information D may be recorded as a database or may be recorded as a list listing data.

11 (a), 11 (b), and 11 (c) are schematic views of a method in which the range specifying unit 113 and the partial image generation unit 114 generate the partial image A1 based on the image B1. 11 (a) and 11 (b) show a method of generating a partial image A1 including a person or a mark based on the image B1 and the sentence B2. First, the range specifying unit 113 acquires the data of the image B1 and the sentence B2 included in the content displayed on the list screen A from the content storage unit 121, and acquires the feature information C from the feature information storage unit 122.

The range specifying unit 113 reads the sentence B2 and detects the name C3 included in the sentence B2. The range specifying unit 113 acquires the feature amount C2 associated with the name C3 included in the sentence B2 from the feature information C. The range specifying unit 113 compares the feature amount C2 (that is, the reference feature amount) associated with the name C3 included in the sentence B2 with the feature amount calculated for each position in the image B1 to be a person. Or detect the mark. Then, the range specifying unit 113 specifies a range R having a predetermined size including a position where a person or a mark is detected in the image B1.

FIG. 11A shows an example in which the name of the person is included in the sentence B2, and the range specifying unit 113 specifies the range R including the face of the person in the image B1. FIG. 11B shows an example in the case where the name of the group is included in the sentence B2, and the range specifying unit 113 specifies the range R including the mark of the group in the image B1.

The partial image generation unit 114 generates a partial image A1 by cutting out a range R specified by the range specifying unit 113 in the image B1, and stores the partial image A1 in the content storage unit 121 in association with the content including the original image B1. .. As described above, since the distribution server 1 specifies the range R including the person or mark corresponding to the name of the person or group included in the sentence B2 in the image B1 and reflects it in the partial image A1, the content for the user. Not only is the content easy to understand, but a partial image A1 that matches the content of the text B2 of the content can be generated and transmitted to the display terminal 2.

Here, the range specifying unit 113 has described the process of detecting the person or mark corresponding to the name C3 in the image B1 after detecting the name C3 included in the sentence B2, but conversely, a plurality of people in the image B1. After detecting the person or mark of, the person or mark corresponding to the name C3 included in the sentence B2 may be selected. In this case, first, the range specifying unit 113 detects one or a plurality of persons or marks in the image B1. When one person or mark is detected in the image B1, the range specifying unit 113 specifies the range R including the one person or mark.

When a plurality of persons or marks are detected in the image B1, the range specifying unit 113 acquires the name C3 indicated by the feature information C for each of the detected plurality of persons or marks. Then, the range specifying unit 113 determines whether or not each of the detected plurality of persons or the names C3 corresponding to the marks is included in the sentence B2. Then, the range specifying unit 113 specifies a range R including one or a plurality of persons or marks corresponding to the name C3 included in the sentence B2. Even by such processing, the distribution server 1 can generate a partial image A1 that matches the content of the text B2 of the content and transmit it to the display terminal 2.

FIG. 11C shows a method of generating a partial image A1 including a person or a mark based on the image B1 and the user information D. First, the range specifying unit 113 acquires the data of the image B1 included in the content displayed on the list screen A from the content storage unit 121, acquires the feature information C from the feature information storage unit 122, and obtains the user information D from the user. Obtained from the information storage unit 123.

The range specifying unit 113 acquires the feature amount C2 associated with the name C3 that matches the preference D2 indicated by the user information D from the feature information C. The range specifying unit 113 compares the feature amount C2 (that is, the reference feature amount) associated with the name C3 that matches the preference D2 with the feature amount calculated for each position in the image B1 to obtain a person or a mark. Is detected. Then, the range specifying unit 113 specifies a range R having a predetermined size including a position where a person or a mark is detected in the image B1.

FIG. 11C shows an example in which a person matching the user's preference D2 is included in the image B1, and the range specifying unit 113 specifies a range R including the face of the person in the image B1. is doing.

The partial image generation unit 114 generates a partial image A1 by cutting out a range R specified by the range specifying unit 113 in the image B1, and stores the partial image A1 in the content storage unit 121 in association with the content including the original image B1. .. As described above, the distribution server 1 specifies the range R including the person or mark corresponding to the name of the person or group that matches the user's preference D2 in the image B1 and reflects it in the partial image A1. Not only is the content easy to understand, but a partial image A1 that matches the user's preference D2 can be generated and transmitted to the display terminal 2.

Here, the range specifying unit 113 has described the process of detecting the person or mark corresponding to the name C3 in the image B1 after detecting the name C3 that matches the user's preference D2, but conversely, a plurality of people in the image B1. After detecting the person or mark of, the person or mark corresponding to the name C3 that matches the user's preference D2 may be selected. In this case, first, the range specifying unit 113 detects one or a plurality of persons or marks in the image B1. When one person or mark is detected in the image B1, the range specifying unit 113 specifies the range R including the one person or mark.

When a plurality of persons or marks are detected in the image B1, the range specifying unit 113 acquires the name C3 indicated by the feature information C for each of the detected plurality of persons or marks. Then, the range specifying unit 113 determines whether or not each of the detected names C3 corresponding to the plurality of persons or marks matches the user's preference D2. Then, the range specifying unit 113 specifies a range R including one or a plurality of persons or marks corresponding to the name C3 that matches the user's preference D2. Even by such processing, the distribution server 1 can generate a partial image A1 that matches the user's preference D2 and transmit it to the display terminal 2.

[Modification example]
In this modification, the distribution server 1 changes the size of the partial image A1 or the size of the range R based on the attribute of the user indicated by the user information D. FIG. 12 is a schematic diagram of the user information D stored in the user information storage unit 123. The user information D shows the age D3 and the visual acuity D4 as the user's attributes in association with the user's identification information D1. Age D3 is the age of the user and visual acuity D4 is the visual acuity of the user. The user information D may further indicate the preference D2 similar to that in FIG. As the user's attribute, a value other than the user's age and visual acuity may be used.

For example, the distribution server 1 takes a questionnaire to ask the user to answer the age and visual acuity, associates the user's identification information D1 with the age D3 and the visual acuity D4 indicated by the answer, and records the user information D as the user information storage unit 123. To memorize in advance.

The partial image generation unit 114 changes the size of the partial image A1 based on at least one of the age D3 and the visual acuity D4 of the user information D. For example, the partial image generation unit 114 generates a partial image A1 larger than that when the age D3 is equal to or greater than a predetermined value. Further, for example, the partial image generation unit 114 generates a partial image A1 larger than that when the visual acuity D4 is equal to or less than a predetermined value. As a result, the distribution server 1 can provide a larger partial image A1 to an elderly user or a user with low visual acuity, and makes it easier for the user to see the list screen A.

Further, the range specifying unit 113 changes the size of the range R based on at least one of the age D3 and the visual acuity D4 of the user information D. For example, the partial image generation unit 114 specifies a range R that is smaller when the age D3 is equal to or greater than a predetermined value. Further, for example, the partial image generation unit 114 specifies a range R smaller than that when the visual acuity D4 is equal to or less than a predetermined value. If the partial image A1 has the same size, the smaller the range R in the image B1, the larger the subject in the partial image A1. Therefore, the distribution server 1 can provide the partial image A1 in which the subject is largely captured to the elderly user or the user with low visual acuity, and the list screen A can be easily seen by the user.

(Third embodiment)
The distribution server 1 according to the present embodiment generates a plurality of different partial images A1 based on one image B1, and selectively transmits one of the partial images A1 according to the user's selection status. Hereinafter, the differences from the first embodiment will be mainly described.

When a plurality of persons or marks are detected in the image B1, the range specifying unit 113 specifies a plurality of ranges R including each of the plurality of persons or marks. The partial image generation unit 114 generates a plurality of partial images A1 by cutting out each of the plurality of ranges R from the image B1.

FIG. 13 is a schematic diagram showing a user's selection status on the list screen A. In the example of FIG. 13, the partial image generation unit 114 generated a plurality of partial images A1a and A1b for the image B1 having the same content. The transmission unit 115 of the distribution server 1 randomly transmits either the partial image A1a or the partial image A1b to the display terminals 2 of the plurality of users U1, U2, and U3. The users U1 and U2 selected the content associated with the partial image A1a on the list screen A, and the user U3 did not select the content associated with the partial image A1b on the list screen A. Therefore, it can be said that the selectivity of the partial image A1a is higher than the selectivity of the partial image A1b.

In the distribution server 1, the partial image generation unit 114 acquires the selection status of the plurality of partial images A1 by the plurality of users. Then, the partial image generation unit 114 statistically processes the acquired selection status, and when a significant difference occurs in the selection rates of the plurality of partial images A1, one partial image having a higher selection rate among the plurality of partial images A1. Select A1. When the same content is displayed on the list screen A thereafter, the transmission unit 115 transmits the partial image A1 selected by the partial image generation unit 114. In this way, the distribution server 1 generates a plurality of partial images A1 and statistically selects and transmits the partial image A1 based on the selection status of the user, so that the partial image A1 is easily selected by the user (that is, attracts the interest of the user). (Easy) Partial image A1 can be provided.

The range specifying unit 113 and the partial image generation unit 114 are more suitable based on the learning result when the partial image A1 is generated from the next time onward by machine learning the selection status of the plurality of partial images A1 by the plurality of users. The range R may be specified. The range specifying unit 113 and the partial image generation unit 114 can use a known method such as deep learning (deep neural network) as a machine learning method.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes can be made within the scope of the gist. be. For example, the specific embodiment of the distribution / integration of the device is not limited to the above embodiment, and all or a part thereof may be functionally or physically distributed / integrated in any unit. Can be done. Also included in the embodiments of the present invention are new embodiments resulting from any combination of the plurality of embodiments. The effect of the new embodiment produced by the combination has the effect of the original embodiment together.

The processor of the distribution server 1 and the display terminal 2 is the main body of each step (process) included in the method shown in FIG. That is, the processors of the distribution server 1 and the display terminal 2 read a program for executing the method shown in FIG. 7 from the storage unit, execute the program, and control each unit of the distribution system S, so that FIG. 7 shows. Perform the method shown. The steps included in the method shown in FIG. 7 may be partially omitted, the order between the steps may be changed, or a plurality of steps may be performed in parallel.

S Distribution system 1 Distribution server 11 Control unit 112 Content acquisition unit 113 Range specification unit 114 Partial image generation unit 115 Transmission unit 12 Storage unit 2 Display terminal

Claims (8)

The acquisition unit that acquires content including images and sentences,
The feature amount of the subject is calculated in the image, and the reference feature amount of the person or mark corresponding to the name of the person or group included in the sentence is acquired from the storage unit and calculated. A specific part that specifies a range including a person or a mark corresponding to the name of a part of the image based on the feature amount obtained and the reference feature amount acquired .
A generation unit that generates a partial image by cutting out the range in the image,
A transmission unit that transmits information for displaying the first screen including the partial image to the display terminal, and a transmission unit.
A reception unit that receives information indicating an operation performed by the user on the first screen from the display terminal.
Have,
The transmitting unit is for displaying a second screen including the content when the receiving unit receives information indicating that the user has selected an element associated with the content on the first screen. Sending information to the display terminal,
Delivery device. The distribution device according to claim 1, wherein the element is at least one of a partial image which is a part of the image included in the content and a heading which is a part of the sentence included in the content. The distribution device according to claim 1 or 2, wherein the specific unit recognizes a person or a mark in the image based on the feature amount, and specifies the range including the recognized person or the mark. The distribution device according to claim 3, wherein the specific unit specifies the range including the recognized plurality of persons or marks when the plurality of persons or marks are recognized in the image. Any one of claims 1 to 4, wherein the specific unit acquires the reference feature amount that matches the taste of the user from the storage unit, and specifies the range based on the feature amount and the reference feature amount. The delivery device described in the section . The generation unit generates a plurality of the partial images by cutting out the different ranges in the image.
Information for displaying the first screen including any one of the partial images statistically selected based on the user's selection status for the plurality of the partial images among the plurality of the partial images. The distribution device according to any one of claims 1 to 5 , wherein the image is transmitted to the display terminal. The distribution device according to any one of claims 1 to 6 , wherein the specific unit changes the size of the partial image or the size of the range based on the attribute of the user. The processor,
Steps to get content including images and text,
The step of calculating the feature amount of the subject in the image and
A step of acquiring the reference feature amount of the person or mark corresponding to the name of the person or group included in the sentence from the storage unit, and
A step of specifying a range including a person or a mark corresponding to the name of a part of the image based on the calculated feature amount and the acquired reference feature amount .
A step of generating a partial image by cutting out the range in the image,
A step of transmitting information for displaying the first screen including the partial image to the display terminal, and
A step of receiving information indicating an operation performed by the user on the first screen from the display terminal, and
In the receiving step, when the user receives the information indicating that the user has selected the element associated with the content on the first screen, the information for displaying the second screen including the content is displayed. Steps to send to the terminal and
Delivery method to execute.

Images