JP7362506B2 - Content creation device and content creation method - Google Patents

Description

The present invention relates to a content creation device and a content creation method for creating content to be played in a content display system.

BACKGROUND ART Content display systems called digital signage that are installed in public facilities and display content such as advertisements have been known (for example, see Patent Document 1). Generally, a content display system repeatedly reproduces the content based on a preset reproduction schedule.

Japanese Patent Application Publication No. 2013-117603

Here, content is often created based on the experience of content creators such as advertisers and advertising agencies. For this reason, the effect of advertising due to reproduction of content affects the experience of the content creator, making it difficult to efficiently create content that can obtain the effect of advertising.

An object of the present invention is to provide a content creation device and a content creation method that can efficiently create content that can produce advertising effects.

A content creation device according to one aspect of the present invention is a content creation device that creates content to be played back in a content display system, and wherein when the content is played back in the content display system, the content creation device includes: an evaluation value acquisition unit that acquires evaluation values corresponding to a plurality of features; and a first feature that corresponds to the first feature to be included in the content among the plurality of features based on the evaluation value acquired by the evaluation value acquisition unit. A content information presentation unit that presents content information.

A content creation method according to another aspect of the present invention is a content creation method for creating content to be played in a content display system, wherein when the content is played in the content display system, the contents included in the content are an evaluation value acquisition step of acquiring evaluation values corresponding to a plurality of features; and a first feature that corresponds to the first feature to be included in the content among the plurality of features based on the evaluation value obtained by the evaluation value acquisition step. A content information presentation step of presenting content information is performed by one or more processors.

According to the present invention, it is possible to efficiently create content that can produce advertising effects.

FIG. 1 is a schematic diagram showing a schematic configuration of a content management system according to an embodiment of the present invention. FIG. 2 is a block diagram showing the configuration of a content management system according to an embodiment of the present invention. FIG. 3 is a diagram showing an example of content registered in the content management server according to the embodiment of the present invention. FIG. 4 is a diagram showing an example of content registered in the content management server according to the embodiment of the present invention. FIG. 5 is a diagram showing an example of a feature selection screen displayed on the content management server according to the embodiment of the present invention. FIG. 6 is a diagram showing an example of learning data generated in the content display system according to the embodiment of the present invention. FIG. 7 is a diagram showing an example of a playback schedule created in the content management server according to the embodiment of the present invention. FIG. 8 is a flowchart for explaining an example of the procedure of the learning data generation process executed in the content display system according to the embodiment of the present invention. FIG. 9 is a diagram showing an example of evaluation information used in the content display system according to the embodiment of the present invention. FIG. 10 is a diagram showing an example of cumulative effect points calculated in the content display system according to the embodiment of the present invention. FIG. 11 is a flowchart illustrating an example of the procedure of a reproduction schedule creation process executed by the content management server according to the embodiment of the present invention. FIG. 12 is a flowchart illustrating an example of the procedure of a reproduction schedule creation process executed by the content management server according to the embodiment of the present invention. FIG. 13 is a diagram showing an example of cumulative effect points corresponding to each feature calculated in the content display system according to the embodiment of the present invention.

Embodiments of the present invention will be described below with reference to the accompanying drawings. Note that the following embodiment is an example embodying the present invention, and does not have the character of limiting the technical scope of the present invention.

The content display system 2 according to the present embodiment is applied to a system that displays (reproduces) content including video and audio such as advertisements in various places such as stores, stations, streets, and offices. For example, the content display system 2 is suitable for a digital signage system.

FIG. 1 is a diagram showing a schematic configuration of a content management system 100 according to an embodiment of the present invention. The content management system 100 includes a content management server 1, a content display system 2, a POS management server 3, and a POS terminal 30. Content management server 1 and content display system 2 are communicably connected via network N1. Further, the content management server 1 and the POS management server 3 are communicably connected via a network N2. Further, the POS management server 3 and the POS terminal 30 are communicably connected via the network N3. The networks N1 and N2 are communication networks such as the Internet, LAN, WAN, or public telephone line. The network N3 is a communication network such as a wired LAN or wireless LAN, or an inter-device communication line such as HDMI (registered trademark), RS232C, I2C, etc.

Further, the content management system 100 may include a plurality of content display systems 2. Furthermore, the content management system 100 may include a plurality of POS terminals 30. When the content management system 100 includes a plurality of content display systems 2, each content display system 2 is placed at a different location corresponding to the content management server 1. Further, the content management server 1 monitors and controls, for example, a plurality of content display systems 2, and distributes signage data including content and reproduction schedules to each content display system 2. The content management server 1 may be one or more than one. Further, the content management server 1 and the POS management server 3 may be configured integrally.

The content management server 1 distributes and manages content. The specific configuration of the content management system 100 will be described below. In the following embodiment, as an example of the content management system 100, the content management server 1 distributes signage data including content and a reproduction schedule to the content display system 2, and the content display system 2 reproduces the content based on the reproduction schedule. The configuration will be explained.

[Content management server 1]
As shown in FIG. 2, the content management server 1 includes a control section 11, a storage section 12, an operation display section 13, a communication section 14, and the like. The content management server 1 may be, for example, an information processing device such as a personal computer. The content management server 1 is an example of a content creation device of the present invention. That is, the content management server 1 is a content creation device that creates content to be played in the content display system 2.

The communication unit 14 is a communication interface that connects the content management server 1 to the network N1 by wire or wirelessly, and executes data communication with the content display system 2 via the network N1 according to a predetermined communication protocol. be. The communication unit 14 also connects the content management server 1 to the network N2 by wire or wirelessly, and communicates with the POS management server 3 via the network N2 to perform data communication according to a predetermined communication protocol. It is an interface.

The operation display unit 13 is a user interface that includes a display unit such as a liquid crystal display or an organic EL display that displays various information, and an operation unit such as a mouse, keyboard, or touch panel that receives operations. The operation display unit 13 receives, for example, an operation by an administrator of the content management server 1. Note that the administrator has the authority to create and manage content to be distributed.

The storage unit 12 is a nonvolatile storage unit such as a flash memory that stores various information. For example, the storage unit 12 stores control programs such as a reproduction schedule creation program for causing the control unit 11 to execute various processes. For example, the playback schedule creation program is non-temporarily recorded in a computer-readable recording medium such as a USB (registered trademark) memory, CD, or DVD, and is stored in the storage unit 12 of the content management server 1 from these recording media. be remembered.

The storage unit 12 also stores content data corresponding to content to be displayed on the content display system 2 and content information CD regarding the content. The storage unit 12 also stores learning data LD for generating a reproduction schedule indicating the display date and time (display start date and time, display end date and time, required reproduction time) and display order of the content. The storage unit 12 also stores content feature information CT representing the features of the content. The storage unit 12 also stores, in association with the content, identification information of the content display system 2 to which the content is output, playback schedule TS representing the playback schedule, and the like.

FIG. 3 shows an example of a content information CD. Information such as "content type", "content file name", "target gender", "target age", "minimum display time", "characteristics", etc. is registered in the content information CD for each content. “Content type” is information representing the type of content. “Content file name” is the file name of content data. "Target gender" and "target age" are the gender and age of the viewer group (purchasing group) targeted for marketing of the advertisement corresponding to the content. The "minimum display time" is the lower limit of the content playback time. For example, a percentage of the total display time of the content display system 2 per day is registered in the "minimum display time". "Target gender", "target age", and "minimum display time" are set by the administrator.

“Features” are information indicating characteristics of content. Note that the "Features" column shown in FIG. 3 is shown in FIG. For example, the characteristics are information indicating characteristics of images (photos, illustrations), characters, logos, backgrounds, etc. included in the displayed content. As shown in FIG. 3, a plurality of features are registered for each content. Each feature may be determined by a selection operation by an administrator (a user of the present invention), or may be determined by the control unit 11 by analyzing the contents of the content. For example, the administrator selects the feature of the target content on the feature selection screen P2 shown in FIG. 4. For example, for the content "Clearance Sale for Men," the administrator selects features that correspond to the target audience group, features that he or she senses when displaying the content, and the like. Further, for example, the control unit 11 performs image analysis of the content and determines a plurality of elements included in the image as features. The control unit 11 registers the determined characteristics in the learning data LD for each content. The administrator can update the content information CD as appropriate.

FIG. 6 shows an example of the learning data LD. The learning data LD is generated in the content display system 2 based on information obtained by reproducing content. A specific method of generating the learning data LD will be described later. When the content management server 1 receives the learning data LD from the content display system 2, it stores it in the storage unit 12.

The learning data LD includes "log ID", "date", "start time", "end time", "day of the week", "by holiday", "effect points", "estimated gender", " Information such as "estimated age", "content type", and "characteristics" is registered. "Date" is the playback date of the content, "start time" is the time to start playing the content, and "end time" is the time to end the playback of the content. "Effect points" are information (an example of an evaluation value of the present invention) that quantifies the effect obtained by playing the content. The method for calculating effect points will be described later. "Estimated gender" is the estimated gender of the viewer who viewed the content, and "estimated age" is the estimated age of the viewer who viewed the content. The estimated gender and estimated age are estimated based on images captured by the camera 24 provided in the content display system 2. The type of reproduced content is registered in the "content type" field. The "feature" is information indicating the feature of the content, and the "feature" information of the content information CD shown in FIG. 3 is registered.

FIG. 7 shows an example of the reproduction schedule TS. The reproduction schedule TS is created by the control unit 11 of the content management server 1 based on the learning data LD. The reproduction schedule TS includes a timetable and information on content (content file name) assigned to the timetable. For example, when assigning predetermined content to a timetable, the administrator specifies a feature presented by the control unit 11 from among a plurality of features associated with the content. The control unit 11 assigns the content including the characteristics specified by the administrator to the timetable.

The control unit 11 includes control devices such as a CPU, ROM, and RAM. The CPU is a processor that executes various types of arithmetic processing. The ROM is a nonvolatile storage unit in which control programs such as a BIOS and an OS for causing the CPU to execute various processes are stored in advance. The RAM is a volatile or nonvolatile storage unit that stores various types of information, and is used as a temporary storage memory (work area) for various processes executed by the CPU. The control unit 11 controls the content management server 1 by executing various control programs stored in advance in the ROM or storage unit 12 on the CPU.

Specifically, the control unit 11 includes various processing units such as a learning data receiving unit 111, a content information presenting unit 112, a reproduction schedule creating unit 113, and a data distribution unit 114.

Note that the control unit 11 functions as the various processing units by executing various processes according to the reproduction schedule creation program. Furthermore, some or all of the processing units included in the control unit 11 may be configured with electronic circuits. Note that the playback schedule creation program may be a program for causing a plurality of processors to function as the various processing units.

The learning data receiving unit 111 receives learning data LD generated in the content display system 2 from the content display system 2 . Upon receiving the learning data LD, the learning data receiving unit 111 stores it in the storage unit 12 (see FIG. 4). The learning data receiving section 111 is an example of an evaluation value obtaining section of the present invention. Specifically, when the content is played back in the content display system 2, the learning data receiving unit 111 acquires effect points corresponding to a plurality of features included in the content. As described later, the effect points corresponding to the characteristics are set based on the person's behavior with respect to the content.

The content information presentation unit 112 presents suggestion information (corresponding to content information of the present invention) regarding content that affects the effectiveness of advertisements to the administrator based on the learning data LD. Specifically, when creating the playback schedule TS of the content, the content information presentation unit 112 selects a feature that increases the effect points included in the learning data LD (advertisement (features that increase advertising effectiveness) or features that lower effectiveness points (features that reduce advertising effectiveness), and display proposal information corresponding to the extracted features (corresponding to the first feature of the present invention) on the operation display unit 13. . The proposal information may be text information of the extracted features, content including the extracted features, or an image (still image, illustration) of the content including the extracted features. You can. In this way, the content information presenting unit 112 presents proposal information corresponding to the first feature to be included in the content among the plurality of features, based on the effect points acquired by the learning data receiving unit 111. The specific configuration of the content information presentation section 112 will be described later.

The reproduction schedule creation unit 113 creates a reproduction schedule TS (see FIG. 7) for a plurality of contents included in the content information CD based on the learning data LD. A specific method for creating the reproduction schedule TS will be described later.

The data distribution unit 114 distributes signage data SD including a plurality of contents (content data) included in the content information CD and a reproduction schedule TS of each content to the content display system 2. Note that the data distribution unit 114 can distribute the reproduction schedule TS created manually by the administrator and the reproduction schedule TS created by the reproduction schedule creation unit 113 to the content display system 2.

[Content display system 2]
As shown in FIG. 2, the content display system 2 includes a control section 21, a storage section 22, an operation display section 23, a camera 24, a printer 25, a communication section 26, and the like. The content display system 2 may be, for example, an information processing device such as a personal computer. Further, the content display system 2 may include, for example, an STB (Set Top Box) and a display.

The communication unit 26 is a communication interface that connects the content display system 2 to the network N1 by wire or wirelessly, and executes data communication with the content management server 1 via the network N1 according to a predetermined communication protocol. be.

The printer 25 is capable of performing printing processing based on image data using an electrophotographic method or an inkjet method, and forms an image on a sheet based on the image data.

The operation display unit 23 is an interface that includes a display unit such as a liquid crystal display or an organic EL display that displays various information such as content, and an operation unit such as a touch panel that receives operations from a user (viewer).

The camera 24 is a digital camera that is installed to be able to photograph a predetermined range in front of the operation display section 23, for example, and that captures an image of a person (viewer) as a subject and outputs the image as digital image data.

The storage unit 22 is a nonvolatile storage unit such as a flash memory that stores various information. For example, the storage unit 22 stores control programs such as a learning data generation program for causing the control unit 21 to execute various processes. For example, the learning data generation program is non-temporarily recorded in a computer-readable recording medium such as a USB (registered trademark) memory, a CD, or a DVD, and is stored in the storage unit 22 of the content display system 2 from these recording media. is memorized.

The storage unit 22 also stores learning data LD generated by the control unit 21, signage data SD distributed from the content management server 1, and the like.

The control unit 21 includes control devices such as a CPU, ROM, and RAM. The CPU is a processor that executes various types of arithmetic processing. The ROM is a nonvolatile storage unit in which control programs such as a BIOS and an OS for causing the CPU to execute various processes are stored in advance. The RAM is a volatile or nonvolatile storage unit that stores various types of information, and is used as a temporary storage memory (work area) for various processes executed by the CPU. The control unit 21 controls the content display system 2 by executing various control programs stored in the ROM or storage unit 22 in advance on the CPU.

Specifically, the control unit 21 includes various processing units such as a signage data reception unit 211, a content reproduction unit 212, an image acquisition unit 213, an operation acquisition unit 214, a print processing unit 215, and a learning data generation unit 216.

Note that the control unit 21 functions as the various processing units by executing various processes according to the learning data generation program. Furthermore, some or all of the processing units included in the control unit 21 may be configured with electronic circuits. Note that the learning data generation program may be a program for causing a plurality of processors to function as the various processing units.

The signage data receiving unit 211 receives signage data SD distributed from the content management server 1. The signage data SD includes a plurality of contents (content data) included in the content information CD and a reproduction schedule TS of each content. The signage data receiving section 211 stores the received signage data SD in the storage section 22.

The content playback section 212 displays the content on the operation display section 23 based on the playback schedule TS. Note that the playback schedule TS includes the playback schedule TS created manually by the administrator and the playback schedule TS created by the playback schedule creation unit 113 of the content management server 1, so the content playback unit 212 , the content is displayed based on one of the reproduction schedules TS.

The image acquisition unit 213 acquires an image of a person (viewer) in front of the operation display unit 23, which is captured by the camera 24.

The operation acquisition unit 214 acquires operation information regarding the viewer's operation on the operation display unit 23. For example, when a viewer performs a touch operation on the operation display unit 23 that is displaying content, the operation information is acquired.

The print processing unit 215 outputs a print instruction to the printer 25 and causes the printer 25 to execute print processing. For example, when the operation acquisition unit 214 acquires an operation for requesting specific information from the viewer, the print processing unit 215 causes the printer 25 to perform a print process to print the specific information. The specific information is privilege information that can be used at facilities corresponding to the content, such as discount coupons, usage tickets, and service tickets that can be used at various facilities such as retail stores, restaurants, entertainment facilities, and accommodation facilities. .

The learning data generation unit 216 generates learning data LD for creating a content reproduction schedule TS. For example, the learning data generation unit 216 generates the learning data LD based on the captured image acquired by the image acquisition unit 213. A specific method of generating the learning data LD will be described later. The learning data generation unit 216 stores the generated learning data LD in the storage unit 22. Further, the learning data generation unit 216 transmits the generated learning data LD to the content management server 1. Note that the learning data generation unit 216 adds identification information (equipment information, location information, etc.) of the content display system 2 to the learning data LD, and transmits the data to the content management server 1.

[POS management server 3]
As shown in FIG. 2, the POS management server 3 includes a control section 31, a storage section 32, an operation display section 33, a communication section 34, and the like.

The communication unit 34 is a communication interface that connects the POS management server 3 to the network N2 by wire or wirelessly, and executes data communication according to a predetermined communication protocol with the content management server 1 via the network N2. be. Further, the communication unit 34 is a communication interface for connecting the POS management server 3 to the network N3 by wire or wirelessly, and performing data communication according to a predetermined communication protocol with the POS terminal 30 via the network N3. It is.

The operation display unit 33 is an interface that includes a display unit such as a liquid crystal display or an organic EL display that displays various information, and an operation unit such as a touch panel that receives operations from a user (store manager).

The storage unit 32 is a nonvolatile storage unit such as a flash memory that stores various information. For example, the storage unit 32 stores control programs for causing the control unit 31 to execute various processes. For example, the control program is non-temporarily recorded in a computer-readable recording medium such as a USB (registered trademark) memory, CD, or DVD, and is stored in the storage unit 32 of the POS management server 3 from these recording media. Ru.

The storage unit 32 also stores POS data such as purchase information acquired from each POS terminal 30.

The control unit 31 includes control devices such as a CPU, ROM, and RAM. The CPU is a processor that executes various types of arithmetic processing. The ROM is a nonvolatile storage unit in which control programs such as a BIOS and an OS for causing the CPU to execute various processes are stored in advance. The RAM is a volatile or nonvolatile storage unit that stores various types of information, and is used as a temporary storage memory (work area) for various processes executed by the CPU. The control unit 31 controls the POS management server 3 by executing various control programs stored in advance in the ROM or storage unit 32 on the CPU.

[How to generate learning data LD]
Hereinafter, an example of the procedure of the learning data generation process executed by the control unit 21 of the content display system 2 will be described with reference to FIG. 8. A part of the learning data generation process may be executed by the control unit 11 of the content management server 1.

Note that the present invention can be regarded as an invention of a learning data generation method that executes one or more steps included in the learning data generation process. Furthermore, one or more steps included in the learning data generation process described here may be omitted as appropriate. Further, each step in the learning data generation process may be executed in a different order as long as similar effects are produced. Furthermore, although the case where each step in the learning data generation process is executed by the control unit 21 will be described as an example, in other embodiments, each step in the learning data generation process is executed by a plurality of processors. may be executed in a distributed manner.

First, in step S21, the control unit 21 determines whether or not the signage data SD has been distributed from the content management server 1. If the signage data SD is distributed from the content management server 1 (S21: Yes), the process moves to step S22, and if the signage data SD is not distributed from the content management server 1 (S21: No), the process moves to step S22. The process moves to S23.

In step S22, the control unit 21 receives signage data SD from the content management server 1. The control unit 21 stores the received signage data SD in the storage unit 22. Note that each time the control unit 21 receives signage data SD from the content management server 1, it stores the signage data SD in the storage unit 22. Therefore, the latest signage data SD is stored in the storage unit 22.

In step S23, the control unit 21 reproduces the content based on the signage data SD stored in the storage unit 22. For example, the control unit 21 sequentially reproduces a plurality of contents based on a reproduction schedule TS included in the signage data SD.

In step S24, the control unit 21 starts recording the learning data LD corresponding to the reproduced content. Specifically, the control unit 21 acquires a captured image of a person (viewer) captured by the camera 24, determines the behavior of the person based on the captured image, and determines the behavior of the person according to the processing of steps S241 to S245 below. The information obtained is recorded as learning data LD.

In step S241, the control unit 21 analyzes the captured image and determines whether the viewer momentarily looked at the display screen displaying the content. If it is determined that the viewer looked at the display screen for a moment (S241: Yes), the process moves to step S25, and if it is not determined that the viewer looked at the display screen for a moment (S241: No), the process moves to step S25. The process moves to S242.

In step S25, the control unit 21 updates the effect points. Specifically, the control unit 21 updates the effect points with reference to the evaluation information P1. FIG. 9 shows an example of evaluation information P1. The evaluation information P1 is stored in the storage unit 22 in advance.

In the evaluation information P1, the behavior of the viewer and the effect points corresponding to the behavior are registered in association with each other. The higher the effect points are set, the more the viewer's behavior is determined to have a high degree of interest in the content. That is, the effect points (evaluation values) correspond to the viewer's interest level in the content. For example, if the viewer passes by without looking at the display screen even though the content is displayed on the display screen, it can be determined that the viewer is not interested in the content, so the behavior of "no response" is "0" is set as the effect point. For example, if a viewer performs a touch operation on the display screen (such as requesting a coupon) while the content is displayed on the display screen, it can be determined that the viewer is interested in the content. A high value is set for the effect points for certain actions.

For example, if the control unit 21 plays the content "cosmetics for men" between 10:00 and 10:01 on January 1, 2019, the viewer (passerby) may not see the display screen. If the object passes by, the control unit 21 determines that the content of the action toward the content is "no reaction." In this case, the control unit 21 registers the log information regarding the content and the effect point "0" (see FIG. 9) in the learning data LD (see FIG. 6). On the other hand, if the viewer looks at the display screen for a moment, the control unit 21 determines that the action regarding the content is "looked at the screen for a moment." In this case, the control unit 21 registers the log information regarding the content and the effect point "5" in the learning data LD.

In step S242, the control unit 21 analyzes the captured image and determines whether the viewer has viewed the display screen on which the content is being displayed for a certain period of time. If it is determined that the viewer has viewed the display screen for a certain period of time (S242: Yes), the process moves to step S26, and if it is not determined that the viewer has viewed the display screen for a certain period of time (S242: No), the process The process moves to step S243.

In step S26, the control unit 21 updates the effect points. For example, when the viewer looks at the display screen for a certain period of time, the control unit 21 determines that the content of the action regarding the content is "stopped in front of the screen and looked at it for a certain period of time." In this case, the control unit 21 registers the log information regarding the content and the effect point "10" (see FIG. 9) in the learning data LD.

In step S243, the control unit 21 analyzes the captured image and determines whether the viewer has performed a touch operation on the display screen that is displaying the content. If it is determined that the viewer has performed a touch operation on the display screen (S243: Yes), the process moves to step S27, and if it is determined that the viewer has not performed a touch operation on the display screen (S243: No), the process The process moves to step S244.

In step S27, the control unit 21 updates the effect points. For example, when the viewer performs a touch operation on the display screen, the control unit 21 determines that the action regarding the content is "operated the touch panel." In this case, the control unit 21 registers the log information regarding the content and the effect point "20" (see FIG. 9) in the learning data LD. For example, if the viewer continues to perform a touch operation after viewing the display screen for a certain period of time, the control unit 21 determines that the content of the action regarding the content is "stopped in front of the screen and looked at it for a certain period of time." , and it is determined that the touch panel was operated. In this case, the control unit 21 updates the effect points to "30" by adding the effect points "20" corresponding to the latter action to the effect points "10" corresponding to the former action. In this way, the control unit 21 sets the effect points when the person looks at the operation display section 23 and performs a touch operation to a higher value than the effect points when the person looks at the operation display section 23 and does not perform a touch operation. .

In step S244, the control unit 21 analyzes the captured image and determines whether the viewer performed a coupon request operation on the display screen while the content was being displayed. If it is determined that the viewer has performed a coupon request operation (S244: Yes), the process moves to step S28, and if it is determined that the viewer has not performed a coupon request operation (S244: No), The process moves to step S245.

The coupon is, for example, discount information for a product included in an advertisement corresponding to the content. By acquiring the coupon, the viewer can purchase the product at a discounted price. For example, when a viewer wishes to purchase a product included in the content being displayed, the viewer performs an operation to request a coupon on the display screen. Upon acquiring the operation information, the control unit 21 causes the printer 25 to output a discount coupon for the product. When the viewer obtains the coupon, the viewer visits a store that sells the product and uses the coupon to purchase the product. The store's POS terminal 30 transmits purchase information to the POS management server 3. Further, the POS management server 3 transmits the purchase information to the content management server 1. The purchase information includes information indicating that the coupon has been used (usage history information).

In step S28, the control unit 21 updates the effect points. For example, when the viewer performs an operation to request a coupon on the display screen, the control unit 21 determines that the content of the action for the content is "outputting a coupon." In this case, the control unit 21 registers the log information regarding the content and the effect point "50" (see FIG. 9) in the learning data LD. Further, for example, if the viewer continues to perform a touch operation after viewing the display screen for a certain period of time and outputs a coupon, the control unit 21 adds the effect points according to the content of each action and outputs "80". Update to. In this way, the control unit 21 calculates the effect points when a person looks at the operation display unit 23 and performs an operation to output a coupon, and the effect points when a person looks at the operation display unit 23 and does not perform an operation to output a coupon. Set to a value higher than points.

Here, if the viewer uses the coupon to purchase a product corresponding to the content, it can be determined that the viewer's level of interest in the content is even higher. Therefore, upon receiving information indicating that the coupon has been used (usage history information) from the content management server 1, the control unit 21 updates the effect points. For example, the effect point "50" corresponding to the action content "purchased using a coupon" is added to the effect point "80" and updated to "130". In this way, the control unit 21 updates the effect points for the content when a coupon corresponding to the content is used at a facility.

In step S245, the control unit 21 analyzes the captured image and determines whether the viewer performed an operation to display a two-dimensional code on the display screen while displaying the content. If it is determined that the viewer has performed an operation to display a two-dimensional code (S245: Yes), the process moves to step S29, and if it is determined that the viewer has not performed an operation to display a two-dimensional code (S245: No), the process moves to step S30.

The two-dimensional code corresponds to electronic data of the coupon. For example, a viewer can obtain coupon information by reading a two-dimensional code displayed on a display screen using the viewer's mobile terminal. The viewer can use the coupon by displaying the coupon information on the mobile terminal and having the POS terminal 30 read it. Note that the POS terminal 30 may include a reader (for example, a barcode reader) for reading coupon information (see FIG. 1).

In step S29, the control unit 21 updates the effect points. For example, when the viewer performs an operation to display a two-dimensional code on the display screen, the control unit 21 determines that the action regarding the content is "reading the two-dimensional code on the screen." In this case, the control unit 21 registers the log information regarding the content and the effect point "50" (see FIG. 9) in the learning data LD. Further, for example, if the viewer continues to perform a touch operation to read a two-dimensional code after viewing the display screen for a certain period of time, the control unit 21 adds effect points according to the content of each action and adds " 80”.

In this manner, while displaying the content, the control unit 21 determines the behavior of the viewer regarding the content, and sets effect points corresponding to the content of the behavior. Specifically, the control unit 21 determines, based on the captured image, whether the person has looked at the operation display unit 23, whether the person has performed a touch operation on the operation display unit 23, and whether the person has touched the operation display unit 23. 23 to determine whether specific information has been outputted or not, and set effect points according to the determination result. Then, the control unit 21 generates learning data LD in which content and effect points are associated with each other. FIG. 6 is a diagram showing an example of the learning data LD generated in this manner. Note that the learning data LD generated in the learning data generation process does not include information on the characteristics of the content.

In step S30, the control unit 21 transmits the generated learning data LD to the content management server 1. After that, the process returns to step S21, and the above-described process is repeated. That is, the control unit 21 sets effect points for a plurality of contents that are repeatedly displayed on the operation display unit 23, and updates the learning data LD every time the plurality of contents are displayed.

In the above-mentioned process, the control unit 21 calculates the effect points of each content while reproducing the plurality of contents according to the reproduction schedule TS. However, as another method, the control unit 21 calculates the effect points for each content. The effect points per unit time of the content may be calculated while continuously playing the content. For example, when the control unit 21 receives the signage data SD of "clearance sale for men" from the content management server 1, the control unit 21 continues the operation during the operating hours of the content display system 2 "9:00 to 23:00 on Monday". to play the "Men's Clearance Sale" content. Then, the control unit 21 determines the behavior of the viewer regarding the content and calculates the effect points. Specifically, the control unit 21 calculates cumulative effect points every hour. For example, the cumulative effect points for the time period are calculated by adding up the effect points of each action that the viewer performed regarding the content between "9:00 and 10:00." FIG. 10 is a graph showing cumulative effect points corresponding to the content. According to the graph shown in FIG. 10, it can be seen that the content has high effect points in the time zones "13:00-14:00" and "18:00-19:00". The control unit 21 calculates the cumulative effect points for each content. Then, the control unit 21 generates learning data LD in which content and cumulative effect points are associated with each other, and transmits the generated learning data LD to the content management server 1.

Here, the control unit 21 that executes the learning data generation process is an example of the learning data generation device of the present invention. That is, the control unit 21 functions as a learning data generation device that generates learning data for creating a content playback schedule. The control unit 21 includes an image acquisition unit (image acquisition unit 213) that acquires a captured image of a person in front of the display unit (operation display unit 23) that displays the content; a person determination unit that determines the behavior of the person, an evaluation value setting unit that calculates effect points (evaluation values) for the content based on the behavior of the person, and generates learning data LD that associates the content and the effect points. It functions as a learning data generation unit (learning data generation unit 216).

[How to create playback schedule TS]
Hereinafter, an example of the procedure of the reproduction schedule creation process executed by the control unit 11 of the content management server 1 will be described with reference to FIGS. 11 and 12.

Note that the present invention can be regarded as an invention of a playback schedule creation method that executes one or more steps included in the playback schedule creation process. Furthermore, one or more steps included in the reproduction schedule creation process described here may be omitted as appropriate. Furthermore, the steps in the playback schedule creation process may be executed in a different order as long as similar effects are produced. Further, although a case will be described here taking as an example a case where each step in the playback schedule creation process is executed by the control unit 11, in other embodiments, each step in the playback schedule creation process is executed in a distributed manner by a plurality of processors. It may also be executed as follows.

First, in step S1, the control unit 11 determines whether learning data LD has been transmitted from the content display system 2. When the learning data LD is transmitted from the content display system 2 (S1: Yes), the process moves to step S2, and when the learning data LD is not transmitted from the content display system 2 (S1: No), the process The process moves to step S3.

In step S2, the control unit 11 receives the learning data LD from the content display system 2. The control unit 21 stores the received learning data LD in the storage unit 12. Note that, at this point, the learning data LD does not include the characteristics of the content. Further, the control unit 11 stores the learning data LD in the storage unit 12 every time the learning data LD is received from the content display system 2 . Therefore, the latest learning data LD is stored in the storage unit 12.

In step S3, the control unit 11 registers content features determined in steps S10 and S11, which will be described later, in the learning data LD.

In step S4, the control unit 11 determines whether or not the purchase information has been received from the POS management server 3. If the control unit 11 receives the purchase information (S4: Yes), the process moves to step S5, and if the control unit 11 does not receive the purchase information (S4: No), the process moves to step S6. do.

In step S5, the control unit 11 updates the effect points. For example, when the viewer outputs a coupon by performing a touch operation after viewing the display screen for a certain period of time, "80" is registered as the effect point in the learning data LD. Thereafter, when the viewer makes a purchase using the coupon, the control unit 11 receives the purchase information from the POS management server 3. In this case, the control unit 11 updates the effect point "80" of the learning data LD to "130". Further, the control unit 11 transmits the purchase information to the content display system 2. In the content display system 2, the control unit 21 receives the purchase information and updates the effect points of the learning data LD in the storage unit 22 to “130”.

In step S6, the control unit 11 determines whether a termination operation has been received from the administrator. If the control unit 11 accepts the termination operation (S6: Yes), the process ends, and if the control unit 11 does not accept the termination operation (S6: No), the process moves to step S7.

In step S7, the control unit 11 determines whether to execute the reproduction schedule TS creation command. For example, when receiving a creation instruction from the administrator, the control unit 11 executes a command to create a playback schedule TS. If the creation command is not executed (S7: No), the process moves to step S14.

In step S8, the administrator performs an operation to input content to be assigned to the reproduction schedule TS, and the control unit 11 accepts the operation. For example, as shown in FIG. 3, the administrator inputs (registers) desired content into the content information CD.

In step S9, the control unit 11 determines whether or not to automatically generate content features. For example, if the administrator selects manual generation (S9: No), the process moves to step S10, and if the administrator selects automatic generation (S9: Yes), the process moves to step S11. .

In step S10, the control unit 11 receives an operation by the administrator to select a feature of the content (see FIG. 5). Upon receiving the selection operation, the control unit 11 registers the selected feature in the content information CD (see FIG. 4) and the learning data LD (see FIG. 6).

In step S11, the control unit 11 performs image analysis of the content and extracts a plurality of elements included in the image as features. The control unit 11 registers the extracted features in the content information CD (see FIG. 4) and the learning data LD (see FIG. 6).

In step S12, the control unit 11 creates a reproduction schedule TS. Specifically, the control unit 11 allocates the content registered in the content information CD to the timetable based on the learning data LD. For example, the control unit 11 allocates each content to the timetable based on the learning data LD so that each content has a high effect point.

Here, the control unit 11 generates the reproduction schedule TS using the learning data LD. Specifically, the control unit 11 generates a learned model by performing machine learning using the learning data LD. For example, the control unit 11 generates a learned model that estimates a playback schedule corresponding to arbitrary content.

Machine learning includes algorithms such as supervised learning using supervised data, unsupervised learning using unsupervised data, and reinforcement learning. To achieve this, a method called ``deep learning'' is used that learns to extract the feature values themselves. In this embodiment, the control unit 11 has a learning model based on the various algorithms described above. Note that in this embodiment, content associated with effect points corresponds to supervised data, and content not associated with effect points corresponds to unsupervised data. The control unit 11 can estimate a playback schedule by performing machine learning using these supervised data and unsupervised data as input data.

Specifically, the learned model is capable of learning the content when information about the content (content type, target gender, target age, minimum display time, etc.) and effect points associated with the content are input, for example. Estimate the optimal playback schedule (display start time, display end time, etc.).

The control unit 11 creates a playback schedule TS using the generated trained model. That is, the control unit 11 that generates the learned model is an example of the learning device of the present invention. That is, the control unit 11 functions as a learning device that generates a trained model by performing machine learning using the learning data LD generated by the learning data generation device (control unit 21). Note that the learned model may be stored in an external device. Thereby, the device functions as a content reproduction schedule TS creation device (learning device). Further, the trained model may be downloadable to the device via a communication network such as the Internet.

For example, regarding the content "Clearance Sale for Men," the control unit 11 uses the learning data LD shown in FIGS. If it is determined that the effect points are high in the time period, the content is assigned to "13:00-14:00" and "18:00-19:00" in the timetable (see FIG. 7). Each time the learning data LD is updated, the control unit 11 estimates the optimal display time slot for the content and allocates it to the timetable.

Furthermore, the control unit 11 allocates the content to the timetable in consideration of the minimum display time (see FIG. 3). That is, the minimum display time is included in the learning data LD. As a result, each prepared content is allocated to an optimal display time slot while ensuring a minimum display time.

When the control unit 11 allocates a plurality of contents to the timetable and creates a reproduction schedule TS (see FIG. 7) as described above, in step S13, the control unit 11 assigns the signage data SD including a plurality of contents and the reproduction schedule TS to the content. It is distributed to the display system 2.

In step S14, the control unit 11 determines whether an instruction to execute a content creation command has been received. If the control unit 11 receives the execution instruction from the administrator (S14: Yes), the process proceeds to step S15, and if the control unit 11 does not accept the execution instruction from the administrator (S14: No), the process proceeds to step S15. The process moves to step S11.

In step S15, the administrator performs an operation to input content to be created, and the control unit 11 accepts the operation. Specifically, the administrator inputs the type of content to be created, target gender, target age, display time zone, location (identification information of content display system 2, etc.), and the like.

In step S16, the control unit 11 presents the administrator with the proposal information that affects the effectiveness of the advertisement regarding the content to be created, based on the information input by the administrator.

Specifically, first, the control unit 11 transmits signage data SD of various patterns with different characteristics to the content display system 2 regarding predetermined content. Then, the control unit 11 receives learning data LD corresponding to each pattern of content from the content display system 2. Upon receiving each learning data LD, the control unit 11 calculates cumulative effect points for each of the plurality of features associated with each content. FIG. 13 shows an example of the cumulative effect points. According to the results shown in FIG. 13, the effect points are the highest when content that includes "Feature 10" is played, and the effect points are the lowest when content that includes "Feature 1" and "Feature 12" is played. I know it will happen.

Therefore, the control unit 11 extracts a plurality of features, such as "Feature 10", "Feature 3", and "Feature 4", which are effective for the effectiveness of the advertisement, based on the effect points. Then, the control unit 11 displays the extracted “feature 10,” “feature 3,” and “feature 4” on the operation display unit 13. Further, the control unit 11 displays content including the extracted “feature 10,” “feature 3,” and “feature 4,” or an image of the content on the operation display unit 13.

Furthermore, the control unit 11 extracts a plurality of features that are not effective for the effectiveness of the advertisement, such as "feature 1," "feature 12," and "feature 2," based on the effect points. Then, the control unit 11 displays the extracted “feature 1”, “feature 12”, and “feature 2” on the operation display unit 13. Further, the control unit 11 displays content including the extracted “feature 1”, “feature 12”, and “feature 2” or an image of the content on the operation display unit 13.

In this way, the control unit 11 presents the administrator with content plans suitable for obtaining advertising effects and content plans that are not suitable for obtaining advertising effects.

That is, the control unit 11 generates content using the learning data LD. Specifically, the control unit 11 generates a learned model by performing machine learning using the learning data LD. For example, the control unit 11 generates a trained model that estimates content including optimal features corresponding to arbitrary content. For example, the content information presentation unit 112 extracts a first feature from among a plurality of features by performing machine learning using learning data LD including content, features, and effect points. In this case, the learning data LD includes the content, the effect points set based on the behavior of the person determined from the captured image of the person in front of the operation display unit 23 that displays the content, and the This is data associated with features included in content.

Specifically, when information on arbitrary content (content type, target gender, target age, display time zone, location, etc.) is input, the trained model estimates the optimal characteristics for the content.

The control unit 11 creates content using the generated trained model. That is, the control unit 11 that generates the learned model is an example of the learning device of the present invention. That is, the control unit 11 functions as a learning device that generates a trained model by performing machine learning using the learning data LD generated by the learning data generation device (control unit 21). Note that the learned model may be stored in an external device. Thereby, the device functions as a content creation device (learning device). Further, the trained model may be downloadable to the device via a communication network such as the Internet.

For example, regarding the content of "Clearance Sale for Men," the control unit 11 generates content including "Feature 10," "Feature 3," and "Feature 4," and generates content that includes "Feature 10", "Feature 3", and "Feature 4", and :00” and “18:00-19:00”. After allocating a plurality of contents to the timetable and creating a reproduction schedule TS in this way, the control section 11 distributes signage data SD including a plurality of contents and the reproduction schedule TS to the content display system 2.

As described above, the content management system 100 according to the present embodiment acquires effect points corresponding to a plurality of features included in the content when the content is played in the content display system 2, and Based on the effect points, proposal information (content information of the present invention) corresponding to the feature to be included in the content (first feature of the present invention) among the plurality of features is presented. For example, the content management system 100 presents features that should be included in the content and features that should not be included in the content to a content creator such as an administrator. This allows content creators to select features that are highly effective for advertising and create content. Therefore, it is possible to efficiently create content that can produce advertising effects.

Further, the content management system 100 according to the present embodiment acquires a captured image of a person in front of the operation display section 23 that displays content, determines the behavior of the person based on the captured image, and determines the behavior of the person based on the captured image. An evaluation value for the content is set based on the behavior of the user. Further, the content management system 100 generates learning data LD in which the content and the evaluation value are associated with each other. Then, the content management system 100 uses the learning data LD to create an optimal reproduction schedule TS for the content. As a result, it becomes possible to reduce the workload of the administrator and easily create an optimal reproduction schedule TS that achieves advertising effects.

The invention is not limited to the embodiments described above. As another embodiment, the control unit 21 of the content display system 2 determines the gender and age of the viewer based on the captured image, and the determined gender and age are the target gender (target gender) and target gender corresponding to the content. If the age (target age) matches, the effect points for the content may be updated. Specifically, if the estimated gender and age match the target gender and age, the control unit 21 assigns a coefficient of 1 or more to the effect points (see FIG. 6) set based on the viewer's behavior. Update to the multiplied value. That is, the control unit 21 may weight the effect points of each content according to the gender and age of the viewer. This makes it possible to create an optimal reproduction schedule TS that matches the target audience of the content.

1: Content management server 2: Content display system 3: POS management server 100: Content management system 111: Learning data receiving unit 112: Content information presenting unit 113: Playback schedule creating unit 114: Data distribution unit 211: Signage data receiving unit 212: Content playback unit 213: Image acquisition unit 214: Operation acquisition unit 215: Print processing unit 216: Learning data generation unit

Claims (14)

A content creation device that creates content to be played in a content display system, the content creation device comprising:
an evaluation value acquisition unit that acquires evaluation values corresponding to a plurality of features included in the content when the content is played in the content display system;
a content information presentation unit that presents content information corresponding to a first feature to be included in the content among the plurality of features based on the evaluation value acquired by the evaluation value acquisition unit;
A content creation device comprising: The content information presentation unit presents text information representing the first feature, content including the first feature, or an image of the content including the first feature.
The content creation device according to claim 1. It further includes a playback schedule creation section that creates a content playback schedule,
The playback schedule creation unit creates a playback schedule for the content created based on the content information.
The content creation device according to claim 1 or claim 2. The plurality of features are determined by a user's selection operation,
The content creation device according to any one of claims 1 to 3. The plurality of features are determined by image analysis of the content.
The content creation device according to any one of claims 1 to 3. The evaluation value corresponding to the feature is set based on a person's behavior with respect to the content,
The content creation device according to any one of claims 1 to 5. The content information presentation unit extracts the first feature from among the plurality of features by performing machine learning using learning data including the content, the feature, and the evaluation value.
The content creation device according to any one of claims 1 to 6. The learning data includes the content, the evaluation value that is set based on the behavior of the person determined from a captured image of the person in front of the display unit that displays the content, and the content. is data associated with features,
The content creation device according to claim 7. The evaluation value includes whether or not the person looked at the display section of the content display system, whether or not the person touched the operation section of the content display system, and whether the person operated the operation section. is set according to the determination result of whether or not specific information has been output.
The content creation device according to claim 6 or claim 8 . An evaluation value that is set when the person looks at the display section and performs the touch operation is set higher than an evaluation value that is set when the person looks at the display section and does not perform the touch operation.
The content creation device according to claim 9. The evaluation value when the person looks at the display section and performs an operation to output the specific information is higher than the evaluation value when the person looks at the display section and does not perform an operation to output the specific information. is set,
The content creation device according to claim 9. The specific information is privilege information that can be used at a facility corresponding to the content;
The content creation device according to any one of claims 9 to 11. The evaluation value is updated when the specific information corresponding to the content is used at the facility.
The content creation device according to claim 12. A content creation method for creating content to be played in a content display system, comprising:
an evaluation value acquisition step of acquiring evaluation values corresponding to a plurality of features included in the content when the content is played in the content display system;
a content information presentation step of presenting content information corresponding to a first feature to be included in the content among the plurality of features based on the evaluation value obtained in the evaluation value obtaining step;
A content creation method that executes using one or more processors.

Images