Video tag acquisition method and apparatus, electronic device, and storage medium

Abstract

The application discloses a video label acquisition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring multiple pictures of a target video; inputting the multiple pictures into a trained network model to acquire a label of the target video; and the network model acquires the label of the target video according to the transformation of object graph structures in the multiple pictures of the target video. The scheme provided by the application can acquire the label of the video based on the changes of objects in the video, has high practicability and high accuracy.

Description

Technical Field

[0001] This invention relates to the field of video tagging technology, and in particular to a video tag acquisition method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of the internet, users can access various types of videos, such as movies and TV series, through video applications or websites on various devices. For videos, video tags effectively showcase their type and characteristics, allowing users to select their preferred video types based on these tags, greatly enhancing the user experience.

[0003] Currently, video tagging is typically done by operators who watch video content and derive tags based on experience. However, this method requires significant manual labor and suffers from low accuracy due to inconsistent standards among operators. Summary of the Invention

[0004] To address the existing technical problems of difficulty and low accuracy in video tag acquisition, embodiments of the present invention provide a video tag acquisition method, apparatus, electronic device, and storage medium.

[0005] The technical solution of this invention is implemented as follows:

[0006] This invention provides a method for obtaining video tags, the method comprising:

[0007] Acquire multiple frames from the target video;

[0008] The multi-frame images are input into a trained network model to obtain the label of the target video; wherein, the network model obtains the label of the target video based on the transformation of the object graph structure in the multi-frame images of the target video.

[0009] In the above scheme, there are multiple network models, and the step of inputting the multiple frames of images into the trained network model to obtain the tags of the target video includes:

[0010] The multi-frame images are input into each of the multiple network models to obtain the label results output by each network model for the multi-frame images;

[0011] The results of multiple labels are used as the labels for the target video.

[0012] In the above scheme, the step of inputting the multi-frame images into each of the multiple network models and obtaining the label results output by each network model for the multi-frame images includes:

[0013] Object detection and recognition are performed on each of the multiple frames of images to construct the object graph structure of each frame.

[0014] The object graph structure corresponding to each frame of the multi-frame images is input into each of the multiple network models to obtain the label results output by each network model for the multi-frame images.

[0015] In the above scheme, the step of performing object detection and recognition on each frame of the multi-frame images and constructing the object graph structure for each frame includes:

[0016] Object detection and recognition are performed on each frame of the multi-frame images to determine the object position and object type of each object in each frame.

[0017] Based on the object position and object type of each object in each frame of the image, a relationship diagram between objects in each frame of the image is constructed.

[0018] The relationship graph between objects in each frame of the constructed image is defined as the object graph structure of each frame.

[0019] In the above scheme, the training process of the network model includes:

[0020] Obtain the training image set;

[0021] Object detection and recognition are performed on each frame of the training image set to determine the object graph structure of each frame of the training image set.

[0022] The object that appears most frequently in the training image set is taken as the center node; the object graph structure of each frame in the training image set is input into a preset network model for training to obtain a trained network model; wherein, the label results output by the network model trained based on the transformation of the object graph structure are different depending on the center node.

[0023] In the above scheme, acquiring multiple frames of the target video includes:

[0024] Acquire the target video;

[0025] The target video is processed by extracting frames at preset time intervals to obtain multiple frames of the target video.

[0026] In the above scheme, after obtaining the tags of the target video, the method further includes:

[0027] The target video is labeled with the aforementioned tags.

[0028] This invention also provides a video tag acquisition device, which includes:

[0029] The acquisition module is used to acquire multiple frames of the target video.

[0030] An input module is used to input the multi-frame images into a trained network model to obtain the label of the target video; wherein, the network model obtains the label of the target video based on the transformation of the object graph structure in the multi-frame images of the target video.

[0031] This invention also provides an electronic device, including: a processor and a memory for storing a computer program capable of running on the processor; wherein,

[0032] When the processor is used to run a computer program, it performs the steps of any of the methods described above.

[0033] This invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above methods.

[0034] This invention can be applied to computer vision within the field of deep learning technology. The video tag acquisition method, apparatus, electronic device, and storage medium provided by this invention acquire multiple frames of a target video; input the multiple frames of images into a trained network model to obtain the tags of the target video; wherein the network model obtains the tags of the target video based on the transformation of the object graph structure in the multiple frames of the target video. The solution provided by this invention can obtain video tags based on changes in objects in the video, exhibiting strong practicality and high accuracy. Attached Figure Description

[0035] Figure 1 This is a flowchart illustrating the video tag acquisition method according to an embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of the object diagram structure according to an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram illustrating the video tagging process in an application embodiment of the present invention;

[0038] Figure 4 This is a schematic diagram of the video tag acquisition device according to an embodiment of the present invention;

[0039] Figure 5 This is an internal structural diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0040] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments.

[0041] This invention provides a method for obtaining video tags, such as... Figure 1As shown, the method includes:

[0042] Step 101: Obtain multiple frames from the target video;

[0043] Step 102: Input the multi-frame images into the trained network model to obtain the label of the target video; wherein, the network model obtains the label of the target video based on the transformation of the object graph structure in the multi-frame images of the target video.

[0044] Specifically, this embodiment can generate a scene graph, called an object graph structure, from a single image using image deep learning methods. See also... Figure 2 , is an object graph structure generated based on a single image.

[0045] This embodiment treats each frame of a video as a photograph, constructing an object graph structure for each image. By statistically analyzing the transformations of the object graph structure, the transformations of different objects in the video can be determined, thereby identifying the video type and assigning it a label. Here, a network model can be used to statistically analyze the transformations of the object graph structure, determine the transformations of different objects within the object graph structure, and thus determine the video type and obtain its label.

[0046] In one embodiment, there are multiple network models, and the step of inputting the multiple frames of images into the trained network model to obtain the tags of the target video includes:

[0047] The multi-frame images are input into each of the multiple network models to obtain the label results output by each network model for the multi-frame images;

[0048] The results of multiple labels are used as the labels for the target video.

[0049] Furthermore, there can be multiple network models. Each network model has a different central node. For the same video segment, analyzing the transformation of objects in multiple frames based on different central nodes will yield different video labels. That is, different network models, due to their different central nodes, will produce different video labels even when analyzing the object graph structure of the same multiple frames of video. For example, using... Figure 2Taking the object graph structure shown as an example, one network model uses the entire street as the central node, and the network connections of other objects such as pedestrians, rickshaws, streetlights, and motorcycles constantly change. By analyzing the changes in other objects in this object graph structure, the video tag "recording local customs and culture" might be obtained. Another network model uses a woman on a motorcycle as the central node, and the connections between other people and the rider change. By analyzing the changes in other objects in this object graph structure, the video tag "street pickup" might be obtained. Yet another network model uses a motorcycle as the central node, and the changes in motorcycle nodes such as people and close-up shots, by analyzing the changes in other objects in this object graph structure, the video tag "product (motorcycle) introduction" might be obtained. In other words, three network models, using the entire street, the woman on the motorcycle, and the motorcycle as the central nodes respectively, for the same image object graph structure, might obtain different video tags: recording local customs and culture, street pickup, and product (motorcycle) introduction.

[0050] Since the video tags obtained by taking different objects in the image as the center node in this embodiment are different, the appropriate center node can be determined based on the actual scene, so as to obtain the appropriate video tags, improve the accuracy of obtaining video tags, and improve the applicability of tags.

[0051] In one embodiment, the step of inputting the multi-frame images into each of the multiple network models and obtaining the label results output by each network model for the multi-frame images includes:

[0052] Object detection and recognition are performed on each of the multiple frames of images to construct the object graph structure of each frame.

[0053] The object graph structure corresponding to each frame of the multi-frame images is input into each of the multiple network models to obtain the label results output by each network model for the multi-frame images.

[0054] In practical applications, after determining the multiple frames of the target video, the object graph structure of these frames is first obtained. This object graph structure is then input into each of multiple network models to obtain video tags for each model based on different central nodes. All these video tags are then used as the video tags for the target video. Here, each network model can output one or more video tags. For example, a network model, based on a central node, might obtain one video tag by analyzing the object transformations in the object graph structure of the multiple frames, such as "scenery description"; or it might obtain two tags, such as "scenery description" or "subtropical scenery."

[0055] In one embodiment, the step of performing object detection and recognition on each frame of the multi-frame images and constructing the object graph structure for each frame includes:

[0056] Object detection and recognition are performed on each frame of the multi-frame images to determine the object position and object type of each object in each frame.

[0057] Based on the object position and object type of each object in each frame of the image, a relationship diagram between objects in each frame of the image is constructed.

[0058] The relationship graph between objects in each frame of the constructed image is defined as the object graph structure of each frame.

[0059] Specifically, object detection and recognition can be performed on each frame of the multi-frame image using deep learning methods to determine the location and type of objects in each frame. Commonly used deep learning methods can be employed here. Furthermore, the objects can be represented by their names. By analyzing the object types in the images and constructing a relationship graph, the object graph structure of each frame can be obtained.

[0060] In one embodiment, the training process of the network model includes:

[0061] Obtain the training image set;

[0062] Object detection and recognition are performed on each frame of the training image set to determine the object graph structure of each frame of the training image set.

[0063] The object that appears most frequently in the training image set is taken as the center node; the object graph structure of each frame in the training image set is input into a preset network model for training to obtain a trained network model; wherein, the label results output by the network model trained based on the transformation of the object graph structure are different depending on the center node.

[0064] Here, the network model in this embodiment can be a deep learning-based neural network model.

[0065] Specifically, public datasets can be used for model training, thereby reducing the amount of image annotation and eliminating the need to label the object type and location in each image.

[0066] In practical applications, the center node of an image can be determined in various ways. For example, the object that appears most frequently in the training image set can be used as the center node; the object with the largest area in the image can be used as the center node; or an important object can be manually determined as the center node.

[0067] In one embodiment, acquiring multiple frames of the target video includes:

[0068] Acquire the target video;

[0069] The target video is processed by extracting frames at preset time intervals to obtain multiple frames of the target video.

[0070] Specifically, in application, to improve recognition accuracy, a minimum length of the target video can be set. For example, the minimum length of the target video can be set to 5 seconds. Of course, to enhance usability, no limit can be placed on the length of the target video.

[0071] Additionally, the system can be configured to extract frames from the target video at preset time intervals. For example, it can be configured to extract one frame from the target video every 2 seconds.

[0072] In one embodiment, after obtaining the tags of the target video, the method further includes:

[0073] The target video is labeled with the aforementioned tags.

[0074] After obtaining the tags of the target video, the target video can be annotated.

[0075] The video tag acquisition method provided in this invention involves acquiring multiple frames of a target video; inputting these multiple frames into a trained network model to obtain the tags for the target video; wherein the network model obtains the tags for the target video based on the transformation of the object graph structure in the multiple frames of the target video. The solution provided by this invention can acquire video tags based on changes in objects within the video, offering strong practicality and high accuracy.

[0076] The present invention will be further described in detail below with reference to application examples.

[0077] This embodiment provides a method for tagging short videos based on state changes in a scene-generated graph, i.e., a method for obtaining video themes. This embodiment mainly involves identifying objects in an image and constructing a relationship graph between these objects; statistically analyzing the changes in connections between nodes in the relationship graph; determining video scene changes based on these node connection changes; and then determining the video type and tagging the video accordingly.

[0078] Specifically, see Figure 3 The video tagging process in this embodiment is as follows:

[0079] Step 301: Data acquisition, i.e., video acquisition; then proceed to step 302;

[0080] Step 302: Extract frames from the video to obtain multiple images; then proceed to step 303.

[0081] Step 303: Object detection and recognition based on image deep learning, constructing an object graph structure; then proceed to step 304;

[0082] Step 304: Construct a graph neural network using the most frequently occurring object as the node; then proceed to step 305.

[0083] Step 305: The graph neural network processes the object graph structure to obtain the processing result; then proceed to step 306.

[0084] Step 306: Classify the processing results and obtain video tags.

[0085] Furthermore, the method of this embodiment will be described in detail below based on the above steps.

[0086] (1) Perform frame extraction on the video to be processed to obtain multiple independent images;

[0087] (2) Using a deep learning-based approach, objects in the images are detected to obtain the location and type of objects in each image;

[0088] The type here refers to the object's type. The reason for obtaining the object's type is to prepare for the next step of constructing the graph structure (e.g., ...). Figure 2 As shown, the features are referred to by name.

[0089] Public datasets are used to identify object types, so it is not necessary to label the object type and location in each image;

[0090] (3) Construct a relationship diagram between objects in the image in (2);

[0091] Here, the relationship diagram uses names to refer to feature diagrams, and feature diagrams are used to obtain the relationships between different objects;

[0092] The connection method of the relationship graph is not binary linking or non-linking, but text-to-feature numerical values, which facilitates the next step of building a classification model.

[0093] (4) Using the most frequently occurring people or objects in (2) as the central nodes, and using the relationship network in (3), construct multiple graph neural networks and train the recognition network;

[0094] During the training phase, videos may have multiple labels, so different labels are assigned according to different visualization graph neural networks to train the graph neural recognition network;

[0095] During the testing phase, graph neural networks with different objects as the central nodes will give different classification results, and multiple results will serve as different labels for the video.

[0096] (5) Tag the video based on the transformation of the structure graph;

[0097] Here, with Figure 2 Using the images shown as an example, the video style suggests a combination of documenting local customs and traditions, street chatting, and product (motorcycle) introductions. The documenting local customs and traditions segment might use the entire street as a central node, with other objects like pedestrians, rickshaws, streetlights, and motorcycles constantly changing their network connections. The street chatting segment might use a woman on a motorcycle as a central node, with the connections between other people and the rider evolving. The product introduction segment might use the motorcycle as a central node, with changes in the motorcycle itself, such as people and close-up shots.

[0098] This embodiment, based on the transformation of the human-object connection graph structure in the video, determines the video type and labels the video. It has the following advantages: it is based on deep learning image recognition technology for object recognition, which has good versatility; it labels the video based on the graph structure between objects, and provides multiple labels according to different networks, which has strong practicality; it can adjust the elements of interest according to the actual use scenario, thereby improving the model accuracy.

[0099] To implement the method of the embodiments of the present invention, the embodiments of the present invention also provide a video tag acquisition device, such as... Figure 4 As shown, the video tag acquisition device 400 includes: an acquisition module 401 and an input module 402; wherein,

[0100] The acquisition module 401 is used to acquire multiple frames of the target video;

[0101] The input module 402 is used to input the multi-frame images into a trained network model to obtain the label of the target video; wherein, the network model obtains the label of the target video based on the transformation of the object graph structure in the multi-frame images of the target video.

[0102] In practical applications, the acquisition module 401 and the input module 402 can be implemented by the processor in the video tag acquisition device.

[0103] It should be noted that the above-described apparatus, when executed, is only illustrated by the division of the program modules described above. In actual applications, the processing can be assigned to different program modules as needed, that is, the internal structure of the terminal can be divided into different program modules to complete all or part of the processing described above. Furthermore, the apparatus and method embodiments described above belong to the same concept, and their specific implementation processes are detailed in the method embodiments, and will not be repeated here.

[0104] Based on the hardware implementation of the above-described program modules, and in order to implement the method of this embodiment of the invention, this embodiment also provides an electronic device (computer device). Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05, and a memory (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A06. The network interface A02 is used for communication with external terminals via a network connection. When the computer program is executed by the processor A01, it implements the method of any of the above embodiments. The display screen A04 can be a liquid crystal display or an electronic ink display. The input device A05 can be a touch layer covering the display screen, a button, trackball, or touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0105] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0106] The device provided in the embodiments of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the method of any of the above embodiments.

[0107] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0109] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0111] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0112] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0113] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0114] It is understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or both. Specifically, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), ferromagnetic random access memory (FRAM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); magnetic surface memory can be disk storage or magnetic tape storage. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), SyncLink Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable types of memories.

[0115] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0116] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for obtaining video tags, characterized in that, The method includes: Acquire multiple frames from the target video; The multi-frame images are input into a trained network model to obtain the labels of the target video; wherein, there are multiple network models, and each network model is trained with different objects in the target video as the central node; the step of inputting the multi-frame images into the trained network model to obtain the labels of the target video includes: inputting the multi-frame images into each of the multiple network models, obtaining the label results output by each network model for the multi-frame images, and using the multiple label results as the labels of the target video; The training process of the network model includes: acquiring a training image set; performing object detection and recognition on each frame of the training image set to determine the object graph structure of each frame of the training image set; wherein, constructing the object graph structure includes: based on the detected object type, converting the text corresponding to the object type into feature values ​​to construct relational edges between objects based on the feature values. The object that appears most frequently in the training image set is taken as the center node; The object graph structure of each frame in the training image set is input into a preset network model for training to obtain a trained network model. The network model trained based on the transformation of the object graph structure has different label results due to different center nodes. Multiple network models can output different label results for the same target video based on their different center nodes.

2. The method according to claim 1, characterized in that, The step of inputting the multi-frame images into each of the multiple network models and obtaining the label results output by each network model for the multi-frame images includes: Object detection and recognition are performed on each of the multiple frames of images to construct the object graph structure of each frame. The object graph structure corresponding to each frame of the multi-frame images is input into each of the multiple network models to obtain the label results output by each network model for the multi-frame images.

3. The method according to claim 2, characterized in that, The step of performing object detection and recognition on each frame of the multi-frame images, and constructing the object graph structure for each frame, includes: Object detection and recognition are performed on each frame of the multi-frame images to determine the object position and object type of each object in each frame. Based on the object position and object type of each object in each frame of the image, a relationship diagram between objects in each frame of the image is constructed. The relationship graph between objects in each frame of the constructed image is defined as the object graph structure of each frame.

4. The method according to claim 1, characterized in that, The acquisition of multiple frames of the target video includes: Acquire the target video; The target video is processed by extracting frames at preset time intervals to obtain multiple frames of the target video.

5. The method according to claim 1, characterized in that, After obtaining the tags of the target video, the method further includes: The target video is labeled with the aforementioned tags.

6. A video tag acquisition device, characterized in that, The video tag acquisition device includes: The acquisition module is used to acquire multiple frames of the target video. An input module is used to input the multi-frame images into a trained network model to obtain the labels of the target video; wherein, there are multiple network models, and each network model is trained with different objects in the target video as the central nodes; the step of inputting the multi-frame images into the trained network model to obtain the labels of the target video includes: inputting the multi-frame images into each of the multiple network models, obtaining the label results output by each network model for the multi-frame images, and using the multiple label results as the labels of the target video; the training process of the network model includes: obtaining a training image set; performing object detection and recognition on each frame of the training image set to determine the... The training image set includes constructing an object graph structure for each frame. This construction involves: converting the text corresponding to the detected object type into feature values ​​to construct relationship edges between objects based on these feature values; using the object that appears most frequently in the training image set as the center node; inputting the object graph structure of each frame into a preset network model for training to obtain a trained network model; wherein, different center nodes result in different label outputs from the network models trained based on the transformation of the object graph structure; multiple network models can output different label results for the same target video based on their respective different center nodes.

7. An electronic device, characterized in that, include: A processor and memory for storing computer programs that can run on the processor; wherein, When the processor is used to run the computer program, it performs the steps of the method according to any one of claims 1 to 5.

8. A storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images