JP7518124B2 - IMAGE PROCESSING APPARATUS, PROGRAM, AND IMAGE PROCESSING METHOD - Google Patents

Description

The present invention relates to an image processing device, a program, and an image processing method.

Patent document 1 describes a moving image recording device that processes an input video signal to generate moving image data, generates one or more thumbnail image data of the moving image data, and records the moving image data in association with the thumbnail image data.
[Prior Art Literature]
[Patent Documents]
[Patent Document 1] JP 2017-135621 A

According to one embodiment of the present invention, there is provided an image processing device. The image processing device may include a video acquisition unit that acquires a video. The image processing device may include an image acquisition unit that acquires a plurality of thumbnail images for the video. The image processing device may include a count acquisition unit that acquires, for each of the plurality of thumbnail images, the number of times the video has been played by selecting the thumbnail image. The image processing device may include an image selection unit that selects one of the plurality of thumbnail images based on the number of times acquired by the count acquisition unit. The image processing device may include an image registration unit that registers the thumbnail image selected by the image selection unit in association with the video.

In the image processing device, the image acquisition unit may extract multiple frames of the video as the multiple thumbnail images.

In any of the image processing devices, the image selection unit may select the thumbnail image that has the highest ratio represented by the number of times each of the plurality of thumbnail images was selected relative to the number of times the video was played within a predetermined period of time.

In any of the image processing devices, the image selection unit may select multiple thumbnail images in descending order of the ratio represented by the number of times each of the multiple thumbnail images was selected to the number of times the video was played within a predetermined period of time, and display them on the communication terminal, and may select a specified thumbnail image from the multiple thumbnail images displayed on the communication terminal.

In any of the image processing devices, the number acquisition unit may display each of the multiple thumbnail images acquired by the image acquisition unit on multiple communication terminals, and acquire the number of times each of the multiple thumbnail images has been selected on the multiple communication terminals. The image processing device may include a superimposition information acquisition unit that acquires superimposition information to be superimposed on a thumbnail image corresponding to the video, and the number acquisition unit may superimpose the superimposition information on each of the multiple thumbnail images acquired by the image acquisition unit and display them on the multiple communication terminals.

Any of the image processing devices may include a history storage unit that stores history data including the video and the thumbnail image selected by the image selection unit. The image processing device may include a model generation unit that uses the multiple history data stored in the history storage unit as teacher data, and generates a learning model by machine learning in which the video is input and a thumbnail image acquired from the video is output. The history data may further include video-related information related to the video, and the model generation unit may generate a learning model by machine learning in which the video and the video-related information are input and a thumbnail image acquired from the video is output. The video-related information may include at least one of the title of the video, category information of the video, and average volume of the video. The history data may further include thumbnail image-related information related to the thumbnail image selected by the image selection unit. The image acquisition unit may extract multiple frames of the video as the multiple thumbnail images, and the thumbnail image-related information may include the volume at the time of the thumbnail image in the video. The image processing device may include an image providing unit that inputs a video for which a thumbnail image is to be generated and video-related information about the video into the learning model generated by the model generation unit, and provides a thumbnail image output from the learning model.

According to one embodiment of the present invention, a program is provided for causing a computer to function as the image processing device.

According to one embodiment of the present invention, there is provided an image processing method executed by a computer. The image processing method may include a video acquisition step of acquiring a video. The image processing method may include an image acquisition step of acquiring a plurality of thumbnail images for the video. The image processing method may include a number acquisition step of acquiring, for each of the plurality of thumbnail images, the number of times the video has been played by selecting the thumbnail image. The image processing method may include an image selection step of selecting one of the plurality of thumbnail images based on the number of times acquired in the number acquisition step. The image processing method may include an image registration step of registering the thumbnail image selected in the image selection step in association with the video.

Note that the above summary of the invention does not list all of the necessary features of the present invention. Also, subcombinations of these features may also be inventions.

1 illustrates a schematic diagram of an example of a system 10. FIG. 2 is an explanatory diagram for explaining the processing contents by the image processing device 100. 2 illustrates an example of a functional configuration of an image processing device 100. 1 illustrates an example of a processing flow by the image processing device 100. 1 illustrates an example of a processing flow by the image processing device 100. An example of the hardware configuration of a computer 1200 functioning as the image processing device 100 is shown in schematic form.

When various videos are displayed in a list on a video sharing site, the thumbnail image and title are what define the video, and how the thumbnail image and title are chosen affects not only how easily the video can be found, but also the number of views to the video. However, there is no correct answer as to what kind of thumbnail image should be, and selecting a thumbnail image can be a hassle and troublesome. In the system 10 according to this embodiment, for example, first, thumbnail images are optimized by a pattern test of thumbnail images randomly extracted from videos, and data is collected. Then, the system 10 creates AI (Artificial Intelligence) from the collected data, and optimizes the thumbnail images using the AI.

The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

Figure 1 shows an example of a system 10. The system 10 includes an image processing device 100. The system 10 may include a video management device 200.

The video management device 200 provides a video sharing service. The video management device 200 displays a list of multiple thumbnail images each corresponding to a plurality of videos, and plays the video corresponding to a selected thumbnail image. The video management device 200 may display the title of the video together with the thumbnail image. The video management device 200 may display the category of the video together with the thumbnail image. The video management device 200 may display text explaining the content of the video together with the thumbnail image. For example, a user 302 of a communication terminal 300 accesses the video management device 200 via the network 20 using the communication terminal 300, selects one of the multiple thumbnail images displayed in the list, and views the video corresponding to the selected thumbnail image.

The image processing device 100 executes a process for providing an appropriate thumbnail image for a video. For example, the image processing device 100 receives a video via the network 20 from the communication terminal 300 of a user 302 who wishes to create a thumbnail image suitable for the video. The image processing device 100 then creates a thumbnail image suitable for the received video and provides it to the requesting user 302.

A thumbnail image suitable for a video may be, for example, a thumbnail image that makes the video more likely to be selected. A thumbnail image suitable for a video may be, for example, a thumbnail image that can more appropriately represent the content of the video.

The image processing device 100, for example, extracts multiple frames of a video received from the communication terminal 300 as multiple thumbnail images. The image processing device 100 transmits the video and the multiple thumbnail images to the video management device 200 via the network 20.

The video management device 200 adds the video received from the image processing device 100 to the video sharing service. The video management device 200 executes a pattern test using the multiple thumbnail images received from the image processing device 100.

For example, the video management device 200 switches the thumbnail image to be displayed for each communication terminal 300. For example, the video management device 200 sequentially switches the thumbnail image to be displayed for the video for each of the multiple communication terminals 300 from among the multiple thumbnail images. As a specific example, when three thumbnail images are received from the image processing device 100, the video management device 200 repeatedly causes the first communication terminal 300 to display the first thumbnail image, the second communication terminal 300 to display the second thumbnail image, the third communication terminal 300 to display the third thumbnail image, the fourth communication terminal 300 to display the first thumbnail image, the fifth communication terminal 300 to display the second thumbnail image, and the sixth communication terminal 300 to display the third thumbnail image.

Then, for each of the multiple thumbnail images, the video management device 200 counts the number of times that the thumbnail image was selected and the video was played. The video management device 200 notifies the image processing device 100 of the counting result. The video management device 200 executes a pattern test for a predetermined period of time, for example, and notifies the image processing device 100 of the number of times that each of the multiple thumbnail images was selected during that period.

The video management device 200 may switch thumbnail images when a reload of the list display occurs on the communication terminal 300. For example, when a reload of the list display occurs on the communication terminal 300 that was displaying a first thumbnail image, the video management device 200 switches to a second thumbnail image.

When a thumbnail image is selected once on one communication terminal 300, the video management device 200 may fix the thumbnail image to be displayed on that communication terminal 300. For example, when a first thumbnail image is selected on one communication terminal 300 and a video is played, the video management device 200 may thereafter display the first thumbnail image on that communication terminal 300 instead of another thumbnail image. In this case, the video management device 200 may not count the first thumbnail image even if it is selected again on that communication terminal 300.

The image processing device 100 obtains from the video management device 200, for each of the multiple thumbnail images, the number of times the video has been played by selecting the thumbnail image, and selects one of the multiple thumbnail images based on the number of times. For example, the image processing device 100 selects the thumbnail image that represents the highest ratio of the number of times each of the multiple thumbnail images was selected to the number of times the video has been played within a predetermined period of time. The image processing device 100 registers the selected thumbnail image in association with the video. The image processing device 100 may provide the selected thumbnail image to the user 302 who desires it as a recommended thumbnail image.

After performing the above-mentioned thumbnail image selection for multiple videos, the image processing device 100 may further use the history data to generate an AI that takes a video as input and outputs a thumbnail image suitable for that video.

For example, the image processing device 100 stores history data including a video, video-related information related to the video, and a thumbnail image selected for the video. Then, using the multiple historical data as training data, a learning model is generated by machine learning in which the video and the video-related information are input and a thumbnail image obtained from the video is output. After generating the learning model, when the image processing device 100 receives a video from the communication terminal 300 of a user 302 who wishes to create a thumbnail image, the image processing device 100 may input the video into the learning model and provide the output thumbnail image to the user 302 as a recommended thumbnail image.

The image processing device 100 and the video management device 200 may be integrated. In other words, the image processing device 100 may have the functions of the video management device 200.

The communication terminal 300 may be any terminal that has a communication function and an image display function. Examples of the communication terminal 300 include, but are not limited to, a PC (Personal Computer), a smartphone, and a tablet terminal.

The network 20 may include the Internet. The network 20 may include a LAN (Local Area Network). The network 20 may include a mobile communication system.

The image processing device 100 may be connected to the network 20 by wire. The image processing device 100 may be connected to the network 20 by wireless. The image processing device 100 may be connected to the network 20 via a wireless base station, a Wi-Fi (registered trademark) access point, etc.

The video management device 200 may be connected to the network 20 via a wired connection. The video management device 200 may be connected to the network 20 wirelessly. The video management device 200 may be connected to the network 20 via a wireless base station, a Wi-Fi access point, etc.

The communication terminal 300 may be connected to the network 20 by wire. The communication terminal 300 may be connected to the network 20 by wireless. The communication terminal 300 may be connected to the network 20 via a wireless base station, a Wi-Fi access point, etc.

Figure 2 is an explanatory diagram for explaining the processing contents by the image processing device 100. In the example shown in Figure 2, the image processing device 100 extracts four frames of a video 400 for which thumbnail images are to be created as thumbnail image 402, thumbnail image 404, thumbnail image 406, and thumbnail image 408.

Test result 500 shows the result of a pattern test by video management device 200. In this example, the percentage of times thumbnail image 402 was selected relative to the number of times video 400 was played within a predetermined period of time was 12%, the percentage of thumbnail image 404 was selected was 20%, the percentage of thumbnail image 406 was selected was 50%, and the percentage of thumbnail image 408 was selected was 18%.

The image processing device 100 may select the thumbnail image 406 with the highest selection rate. The image processing device 100 may register the thumbnail image 406 in association with the video 400.

The image processing device 100 may select multiple thumbnail images in descending order of selection rate, present them to the user 302, and register the thumbnail image selected by the user 302 in association with the video 400. For example, the image processing device 100 transmits thumbnail image 406 and thumbnail image 404 to the communication terminal 300 for display, and registers the one selected by the user 302 in association with the video 400.

Figure 3 shows an example of the functional configuration of the image processing device 100. The image processing device 100 includes a memory unit 110, a video acquisition unit 120, an image acquisition unit 122, a count acquisition unit 124, an image selection unit 126, an image registration unit 128, an image provision unit 130, a superimposition information acquisition unit 132, and a model generation unit 140. Note that it is not essential that the image processing device 100 includes all of these.

The video acquisition unit 120 acquires videos. The video acquisition unit 120 stores the acquired videos in the memory unit 110. The video acquisition unit 120 acquires videos (sometimes referred to as target videos) for which thumbnail images are to be created. The video acquisition unit 120 receives videos from, for example, the communication terminal 300 of the user 302 who wishes to create a thumbnail image. The video acquisition unit 120 receives videos registered in the video management device 200 from the video management device 200, for example.

A user 302 who wishes to create a thumbnail image sends the target video to the image processing device 100, for example, by using a communication terminal 300. A user 302 who wishes to create a thumbnail image registers the target video in the video management device 200, for example, and then sends an instruction to create a thumbnail image to the video management device 200 by using the communication terminal 300. The video management device 200, which has received the instruction, sends the target video to the image processing device 100.

The image acquisition unit 122 acquires multiple thumbnail images for the target video. The image acquisition unit 122 stores the acquired multiple thumbnail images in the storage unit 110. The image acquisition unit 122 extracts, for example, multiple frames of the target video as multiple thumbnail images.

The image acquisition unit 122 may, for example, extract a preset number of frames from the target video. The set number may be arbitrarily set and may be changeable. The image acquisition unit 122 may extract a number of frames from the target video according to the length of the target video. For example, the image acquisition unit 122 extracts a greater number of frames the longer the target video is. The image acquisition unit 122 may randomly extract a preset number of frames from the target video. The image acquisition unit 122 may preferentially extract frames at scene changes from the target video.

The image acquisition unit 122 extracts frames from the target video, for example, based on the analysis results of the target video. The image acquisition unit 122 extracts all frames of scene changes in the target video, for example. The image acquisition unit 122 recognizes, for example, multiple objects that appear in the target video, and extracts frames in which the object stands out for each of the multiple objects. Frames in which an object stands out may be, for example, frames in which the object accounts for a large proportion of the display area, frames in which the object is located more centrally in the display area, etc., or may be other frames.

The image acquisition unit 122 may acquire a thumbnail image without extracting it from the target video. For example, the image acquisition unit 122 acquires a thumbnail image created by the user 302. For example, the image acquisition unit 122 receives the thumbnail image created by the user 302 from the communication terminal 300 or the video management device 200.

The number of times acquisition unit 124 acquires the number of times the target video has been played by selecting a thumbnail image for each of the multiple thumbnail images for the target video acquired by the image acquisition unit 122. The number of times acquisition unit 124 stores the acquired number of times in the storage unit 110. For example, the number of times acquisition unit 124 causes each of the multiple thumbnail images acquired by the image acquisition unit 122 to be displayed on multiple communication terminals 300, and acquires the number of times each of the multiple thumbnail images has been selected on the multiple communication terminals 300.

For example, the count acquisition unit 124 transmits the target video and multiple thumbnail images to the video management device 200, causes the video management device 200 to execute a pattern test, and receives the test results from the video management device 200. The video management device 200, for example, sequentially switches thumbnail images displayed for the target video within a range of multiple thumbnail images for multiple communication terminals 300. The video management device 200 counts the number of times each of the multiple thumbnail images is selected and notifies the image processing device 100. When the image processing device 100 has the functions of the video management device 200, the count acquisition unit 124 may execute a pattern test in a video sharing service provided by the image processing device 100.

The image selection unit 126 selects one of the multiple thumbnail images based on the number of times acquired by the number of times acquisition unit 124. The image selection unit 126, for example, selects a thumbnail image that has the highest ratio represented by the number of times each of the multiple thumbnail images was selected to the number of times the target video was played. The image selection unit 126, for example, selects a thumbnail image that has the highest ratio represented by the number of times each of the multiple thumbnail images was selected to the number of times the target video was played within a predetermined period of time. This makes it possible to select the thumbnail image that is most likely to be selected from the multiple thumbnail images.

The image selection unit 126, for example, selects multiple thumbnail images in descending order of the ratio represented by the number of times each of the multiple thumbnail images was selected to the number of times the video was played, displays them on the communication terminal 300, and selects a thumbnail image specified by the user 302 from the multiple thumbnail images displayed on the communication terminal 300. The image selection unit 126 may select multiple thumbnail images in descending order of the ratio represented by the number of times each of the multiple thumbnail images was selected to the number of times the target video was played within a predetermined period. This makes it possible to present multiple thumbnail images that are more likely to be selected when presenting multiple thumbnail images as candidates to the user 302.

The image registration unit 128 registers the thumbnail image selected by the image selection unit 126 in association with the target video.

The image providing unit 130 provides the thumbnail image selected by the image selecting unit 126 to the user 302. For example, the image providing unit 130 transmits the thumbnail image selected by the image selecting unit 126 to the communication terminal 300 of the user 302. For example, the image providing unit 130 transmits the thumbnail image selected by the image selecting unit 126 to the video management device 200 and stores it in association with the target image.

The superimposition information acquisition unit 132 acquires superimposition information to be superimposed on a thumbnail image corresponding to the target video. The superimposition information acquisition unit 132 stores the acquired superimposition information in the storage unit 110 in association with the target video. The superimposition information may be text information to be superimposed on the thumbnail image. The superimposition information may also be image information to be superimposed on the thumbnail image.

The video acquisition unit 120 receives superimposition information, for example, from the communication terminal 300 of the user 302 who wishes to create a thumbnail image. The video acquisition unit 120 may receive the superimposition information along with the target video from the communication terminal 300 of the user 302 who wishes to create a thumbnail image. The count acquisition unit 124 may superimpose the superimposition information acquired by the superimposition information acquisition unit 132 on each of the multiple thumbnail images acquired by the image acquisition unit 122 and display them on the multiple communication terminals 300. This makes it possible to select a thumbnail image that is likely to be selected when the superimposition information is displayed superimposed.

The storage unit 110 has a history storage unit 112. The history storage unit 112 stores history data including videos and thumbnail images selected by the image selection unit 126. The history data may include video-related information related to the videos. The history data may include thumbnail image-related information related to the thumbnail images selected by the image selection unit 126.

The video related information may include a title of the video. The video related information may include a category of the video. The video related information may include an average volume of the video.

The thumbnail image related information may include the volume of the video at the time of the thumbnail image selected by the image selection unit 126. The thumbnail image related information may include an object contained in the thumbnail image, which is detected from the thumbnail image selected by the image selection unit 126. The detection of the object may be performed by the image processing device 100.

The model generation unit 140 uses multiple pieces of history data stored in the history storage unit 112 as teacher data, and generates a learning model by machine learning, in which a video is input and a thumbnail image obtained from the video is output. The model generation unit 140 may use multiple pieces of history data stored in the history storage unit 112 as teacher data, and generate a learning model by machine learning, in which a video and video-related information are input and a thumbnail image obtained from the video is output. The model generation unit 140 generates a neural network that receives, for example, a video and video-related information and outputs a thumbnail image obtained from the video. The model generation unit 140 stores the generated learning model in the storage unit 110. The model generation unit 140 can generate a learning model that can output, from a video, a thumbnail image that is highly likely to be suitable for the video.

When the video acquisition unit 120 acquires a target image, the image providing unit 130 may provide the user 302 with a thumbnail image for the target image using the learning model generated by the model generation unit 140. For example, the image providing unit 130 inputs the target image and at least one of the title, category, and average volume of the target image into the learning model generated by the model generation unit 140, and transmits the thumbnail image output from the learning model to the communication terminal 300 of the user 302 who desires it. This makes it possible to quickly provide the user 302 who desires to create a thumbnail image with a thumbnail image that is likely to be suitable for the target video.

Figure 4 shows an example of the flow of processing by the image processing device 100. Here, we explain the flow of processing when a thumbnail image suitable for a target video is selected using a pattern test.

In step (sometimes abbreviated to S) 102, the video acquisition unit 120 acquires the target video. In this example, the video acquisition unit 120 receives the target image from the communication terminal 300 of a user 302 who wishes to generate a thumbnail image for the target image.

In S104, the image acquisition unit 122 acquires multiple thumbnail images for the target video acquired by the video acquisition unit 120 in S102. The image acquisition unit 122 may extract multiple frames from the target video as multiple thumbnail images.

In S106, the count acquisition unit 124 transmits the target video acquired in S102 and the multiple thumbnail images acquired in S104 to the video management device 200 to perform a pattern test. After the pattern test is completed, the count acquisition unit 124 receives a test result from the video management device 200, including the number of times each of the multiple thumbnail images was selected.

In S108, the image selection unit 126 selects one of the multiple thumbnail images based on the result of the pattern test in S106. The image selection unit 126 determines the selection ratio for each of the multiple thumbnail images, and selects the thumbnail image with the highest selection ratio.

In S110, the image registration unit 128 registers the thumbnail image selected in S108 in association with the target video acquired in S102. In S120, the image provision unit 130 transmits the thumbnail image selected in S108 to the communication terminal 300 that is the source of the target image.

Figure 5 shows an example of a processing flow by the image processing device 100. Here, we explain the processing flow of generating a learning model that takes a video and video-related information as input and outputs thumbnail images obtained from the video, and using the learning model to provide thumbnail images suitable for the video.

In S202, the model generation unit 140 acquires multiple pieces of history data from the history storage unit 112. In S204, the model generation unit 140 executes machine learning using the multiple pieces of history data acquired in S202 as teacher data to generate a learning model. In S206, the model generation unit 140 registers the learning model generated in S204.

In S208, the video acquisition unit 120 acquires the target video and video-related information for the target video. In this example, the video acquisition unit 120 receives the target image from the communication terminal 300 of the user 302 who wishes to generate a thumbnail image for the target image.

In S210, the image providing unit 130 inputs the video acquired in S208 into the learning model registered in S206, and acquires a thumbnail image output from the learning model. In S212, the image providing unit 130 transmits the thumbnail image acquired in S210 to the communication terminal 300 that is the source of the target image.

FIG. 6 shows an example of a hardware configuration of a computer 1200 functioning as the image processing device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to the present embodiment, or to execute operations or one or more "parts" associated with the device according to the present embodiment, and/or to execute a process or steps of the process according to the present embodiment. Such a program can be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input/output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input/output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid state drive, or the like. The computer 1200 also includes a ROM 1230 and a legacy input/output unit such as a keyboard, which are connected to the input/output controller 1220 via an input/output chip 1240.

The CPU 1212 operates according to the programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and/or writes programs and data to an IC card.

ROM 1230 stores therein a boot program, etc., executed by computer 1200 upon activation, and/or a program that depends on the hardware of computer 1200. I/O chip 1240 may also connect various I/O units to I/O controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. The information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by realizing the operation or processing of information according to the use of the computer 1200.

For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214, storage device 1224, DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

The CPU 1212 may also cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, DVD drive 1226 (DVD-ROM 1227), IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search/replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and writes back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

The above-described programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

The blocks in the flowcharts and block diagrams in this embodiment may represent stages of a process in which an operation is performed or "parts" of a device responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and/or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and/or analog hardware circuits and may include integrated circuits (ICs) and/or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements, such as, for example, field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs).

A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk (registered trademark), JAVA (registered trademark), C++, etc., and conventional procedural programming languages such as the "C" programming language or similar programming languages.

The computer-readable instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, or a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, etc., so that the processor of the general-purpose computer, special-purpose computer, or other programmable data processing apparatus, or the programmable circuit, executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

The present invention has been described above using an embodiment, but the technical scope of the present invention is not limited to the scope described in the above embodiment. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiment. It is clear from the claims that forms incorporating such modifications or improvements can also be included in the technical scope of the present invention.

The order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and it should be noted that the processes may be performed in any order, unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is essential to perform the processes in that order.

10 System, 20 Network, 100 Image processing device, 110 Memory unit, 112 History memory unit, 120 Video acquisition unit, 122 Image acquisition unit, 124 Number acquisition unit, 126 Image selection unit, 128 Image registration unit, 130 Image provision unit, 132 Overlay information acquisition unit, 140 Model generation unit, 200 Video management device, 300 Communication terminal, 302 User, 400 Video, 402, 404, 406, 408 Thumbnail image, 500 Test result, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 Graphic controller, 1218 Display device, 1220 Input/output controller, 1222 Communication interface, 1224 Storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 input/output chip

Claims (16)

a video acquisition unit that receives a video and superimposition information to be superimposed on a thumbnail image corresponding to the video from a user's communication terminal ;
an image acquisition unit that acquires a plurality of thumbnail images for the video;
a number acquisition unit that superimposes the superimposition information on each of the plurality of thumbnail images and displays the superimposition information on a plurality of communication terminals, and acquires a number of times that the video has been played by each of the plurality of thumbnail images being selected on the plurality of communication terminals ;
an image selection unit that selects one of the plurality of thumbnail images based on the number of times acquired by the number acquisition unit;
an image registration unit that registers the thumbnail image selected by the image selection unit in association with the video. The image processing device according to claim 1, wherein the image acquisition unit extracts multiple frames of the video as the multiple thumbnail images. The image processing device according to claim 1, wherein the image selection unit selects the thumbnail image having the highest ratio represented by the number of times each of the plurality of thumbnail images was selected relative to the number of times the video was played within a predetermined period of time. The image processing device according to claim 1, wherein the image selection unit selects and displays on the communication terminal a plurality of thumbnail images in descending order of the ratio represented by the number of times each of the plurality of thumbnail images was selected relative to the number of times the video was played within a predetermined period of time, and selects a specified thumbnail image from the plurality of thumbnail images displayed on the communication terminal. a history storage unit that stores history data including the moving image and the thumbnail image selected by the image selection unit;
2. The image processing device according to claim 1, further comprising: a model generation unit that uses the plurality of history data stored in the history memory unit as teacher data, inputs a video, and outputs a thumbnail image obtained from the video through machine learning to generate a learning model. The history data further includes video-related information related to the video;
The image processing device according to claim 5 , wherein the model generation unit receives the video and the video-related information as input, and generates a learning model by machine learning, the learning model receiving thumbnail images obtained from the video as output. The image processing device according to claim 6 , wherein the video related information includes at least one of a title of the video, category information of the video, and an average volume of the video. The image processing device according to claim 6 , wherein the history data further includes thumbnail image related information related to the thumbnail image selected by the image selection section. The image acquisition unit extracts a plurality of frames of the video as the plurality of thumbnail images;
The image processing device according to claim 8 , wherein the thumbnail image related information includes a volume of the moving image at a time when the thumbnail image is displayed. The image processing device according to claim 5 , further comprising: an image providing unit that inputs a video for which a thumbnail image is to be generated and video-related information for the video into the learning model generated by the model generation unit, and provides a thumbnail image output from the learning model. A video acquisition unit that acquires a video;
an image acquisition unit that acquires a plurality of thumbnail images for the video;
a number acquisition unit that acquires, for each of the plurality of thumbnail images, a number of times that the video has been played by selecting the thumbnail image;
an image selection unit that selects one of the plurality of thumbnail images based on the number of times acquired by the number of times acquisition unit, selects a plurality of thumbnail images in descending order of the ratio represented by the number of times each of the plurality of thumbnail images was selected to the number of times the video was played within a predetermined period of time, and displays them on a communication terminal; and selects a specified thumbnail image from the plurality of thumbnail images displayed on the communication terminal;
an image registration unit that registers the thumbnail image selected by the image selection unit in association with the moving image;
An image processing device comprising: A video acquisition unit that acquires a video;
an image acquisition unit that acquires a plurality of thumbnail images for the video;
a number acquisition unit that acquires, for each of the plurality of thumbnail images, a number of times that the video has been played by selecting the thumbnail image;
an image selection unit that selects one of the plurality of thumbnail images based on the number of times acquired by the number acquisition unit;
an image registration unit that registers the thumbnail image selected by the image selection unit in association with the moving image;
Equipped with
a history storage unit that stores history data including the moving image and the thumbnail image selected by the image selection unit;
a model generation unit that uses the plurality of history data stored in the history storage unit as teacher data, inputs a video, and outputs a thumbnail image obtained from the video by machine learning to generate a learning model;
The image processing device further comprises: A program for causing a computer to function as an image processing device according to any one of claims 1 to 12. 1. A computer-implemented image processing method, comprising the steps of:
a video acquisition step of receiving a video and superimposition information to be superimposed on a thumbnail image corresponding to the video from a user's communication terminal ;
acquiring a plurality of thumbnail images for the video;
a count acquisition step of superimposing the superimposition information on each of the plurality of thumbnail images, displaying the superimposition information on a plurality of communication terminals, and acquiring a number of times that each of the plurality of thumbnail images has been selected on the plurality of communication terminals to cause the video to be played;
an image selection step of selecting one of the plurality of thumbnail images based on the number of times acquired in the number acquisition step;
an image registration step of registering the thumbnail image selected in the image selection step in association with the moving image. 1. A computer-implemented image processing method, comprising the steps of:
a video acquisition stage for acquiring a video;
acquiring a plurality of thumbnail images for the video;
a count acquisition step of acquiring, for each of the plurality of thumbnail images, a number of times the video has been played by selecting the thumbnail image;
an image selection step of selecting one of the plurality of thumbnail images based on the number of times acquired in the number of times acquisition step, in which the plurality of thumbnail images are selected in descending order of the ratio represented by the number of times each of the plurality of thumbnail images was selected relative to the number of times the video was played within a predetermined period of time, and displayed on a communication terminal; and an image selection step of selecting a specified thumbnail image from the plurality of thumbnail images displayed on the communication terminal;
an image registration step of registering the thumbnail image selected in the image selection step in association with the moving image;
An image processing method comprising: 1. A computer-implemented image processing method, comprising the steps of:
a video acquisition stage for acquiring a video;
acquiring a plurality of thumbnail images for the video;
a count acquisition step of acquiring, for each of the plurality of thumbnail images, a number of times the video has been played by selecting the thumbnail image;
an image selection step of selecting one of the plurality of thumbnail images based on the number of times acquired in the number acquisition step;
an image registration step of registering the thumbnail image selected in the image selection step in association with the moving image;
Equipped with
a history storage step of storing history data including the moving image and the thumbnail image selected in the image selection step in a history storage unit;
a model generation step of generating a learning model by machine learning using the plurality of history data stored in the history storage unit as teacher data, a video as an input, and a thumbnail image obtained from the video as an output;
The image processing method further comprises:

Images