A data processing method, apparatus, computer device, and storage medium

Abstract

The present application discloses a data processing method, apparatus, computer device, and storage medium. Among them, the method includes: obtaining a video to be processed associated with a target scenario, performing video frame sampling on the video to be processed according to a sampling rule to obtain one or more sampled video frames, extracting an image of a region to be recognized from the reference sampled video frames, and determining reference tag information associated with the target scenario of the reference sampled video frames according to the image of the region to be recognized; the reference sampled video frames are any one of the one or more sampled video frames, and the image of the region to be recognized includes one or more of a text region image of a display region where a target text object is located and an icon region image of a display region where a target icon object is located; determining target tag information associated with the target scenario of the video to be processed according to the reference tag information of each of the one or more sampled video frames in the one or more sampled video frames. Through this method, the efficiency of determining video tag information can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of computer technologies, and in particular, to a data processing method, a data processing device, a computer device, and a computer-readable storage medium. Background Art

[0002] Video generally refers to various technologies that capture, record, process, store, transmit, and reproduce a series of static images in the form of electrical signals. When the continuous image change exceeds 24 frames per second, according to the principle of persistence of vision, the human eye cannot distinguish a single static image; it looks like a smooth and continuous visual effect, and such continuous images are called videos.

[0003] To facilitate distinguishing different contents in a video or different videos, tag information can be marked for the video. Currently, usually, the tag information of the video is determined manually, but the manual determination method has low efficiency. Summary of the Invention

[0004] Embodiments of this application provide a data processing method, device, computer device, and storage medium, which can effectively improve the efficiency of determining video tag information.

[0005] Embodiments of this application disclose a data processing method on the one hand. The method includes:

[0006] Obtain a to-be-processed video associated with a target scene, and perform video frame sampling on the to-be-processed video according to a sampling rule to obtain one or more sampled video frames;

[0007] Extract an image of a region to be recognized from a reference sampled video frame, and determine reference tag information associated with the target scene for the reference sampled video frame according to the image of the region to be recognized; wherein, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the region to be recognized includes one or more of the following: a text region image of a display region where a target text object is located, an icon region image of a display region where a target icon object is located;

[0008] Determine target tag information associated with the target scene for the to-be-processed video according to the reference tag information of each frame in the one or more sampled video frames.

[0009] Embodiments of this application disclose a data processing device on the one hand. The device includes:

[0010] An obtaining unit, configured to obtain a to-be-processed video associated with a target scene, and perform video frame sampling on the to-be-processed video according to a sampling rule to obtain one or more sampled video frames;

[0011] A processing unit is configured to extract an image of a region to be recognized from a reference sampled video frame, and determine reference tag information associated with the target scene according to the image of the region to be recognized; wherein, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the region to be recognized includes one or more of the following: a text region image of a display region where a target text object is located, an icon region image of a display region where a target icon object is located.

[0012] A determining unit is configured to determine target tag information associated with the target scene of the video to be processed according to the reference tag information of each frame in the one or more sampled video frames.

[0013] One aspect of an embodiment of the present application discloses a computer device, including an input interface and an output interface. The computer device further includes a processor adapted to implement one or more computer programs; and a computer storage medium storing one or more computer programs, the one or more computer programs being adapted to be loaded and executed by the processor to perform the above data processing method.

[0014] One aspect of an embodiment of the present application discloses a computer-readable storage medium storing one or more computer programs, the one or more computer programs being adapted to be loaded and executed by a processor to perform the above data processing method.

[0015] One aspect of an embodiment of the present application discloses a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device performs the above data processing method.

[0016] In an embodiment of the present application, first, a video to be processed associated with a target scene is obtained, and video frame sampling is performed on the video to be processed according to a sampling rule to obtain one or more sampled video frames; then, for any one of the sampled video frames, an image of a region to be recognized (including a text region image of a display region where a target text object is located and / or an icon region image of a display region where a target icon object is located) is extracted from the any one sampled video frame, and reference tag information associated with the target scene of the any one sampled video frame is determined according to the image of the region to be recognized; finally, target tag information associated with the target scene of the video to be processed is determined according to the reference tag information of each sampled video frame. By adopting this method, the automation and intelligence of determining video tag information can be realized, thereby effectively improving the efficiency of determining video tag information. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0018] Figure 1 is a schematic structural diagram of a data processing system disclosed in an embodiment of the present application;

[0019] Figure 2 is a schematic flowchart of a data processing method disclosed in an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of a display interface of tag information disclosed in an embodiment of the present application;

[0021] Figure 4 is a schematic flowchart of another data processing method disclosed in an embodiment of the present application;

[0022] Figure 5 is a schematic flowchart of a data processing method for a game scenario disclosed in an embodiment of the present application;

[0023] Figure 6 is a schematic diagram of an image of an area to be recognized for a game scenario disclosed in an embodiment of the present application;

[0024] Figure 7 is a schematic structural diagram of a data processing device disclosed in an embodiment of the present application;

[0025] Figure 8 is a schematic structural diagram of a computer device disclosed in an embodiment of the present application. Detailed implementation manners

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0027] The data processing method provided by this application involves cloud technology and big data technology in cloud technology. Specifically, cloud technology is a hosting technology that unifies a series of resources such as hardware, software, and networks within a wide area network or local area network to achieve data computing, storage, processing, and sharing. Cloud technology is the general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the cloud computing business model, which can form a resource pool, be used on demand, and be flexible and convenient. Cloud computing technology will become an important support. The back-end services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the highly developed application of the Internet industry, in the future, each item may have its own identification mark and needs to be transmitted to the back-end system for logical processing. Data at different levels will be processed separately, and various industry data requires the support of a powerful system back-end, which can only be achieved through cloud computing.

[0028] Big data refers to a collection of data that cannot be captured, managed, and processed by conventional software tools within a certain time range. It is a massive, high-growth, and diverse information asset that requires a new processing mode to have stronger decision-making power, insight discovery ability, and process optimization ability. With the advent of the cloud era, big data has also attracted more and more attention. Big data requires special technologies to effectively process a large amount of data tolerated over time. Technologies applicable to big data include massively parallel processing databases, data mining, distributed file systems, distributed databases, cloud computing platforms, the Internet, and scalable storage systems. Corresponding to the data processing method provided by the embodiments of this application, different types of tag information can be determined according to different target application scenarios, and then the tag information corresponding to the video can be recommended or displayed to the user.

[0029] See Figure 1 As shown, it is a schematic diagram of the architecture of a data processing system disclosed in the embodiments of this application. Specifically, the data processing system 100 may at least include: multiple first terminal devices 101, multiple second terminal devices 102, and a server 103. Among them, the first terminal device 101 and the second terminal device 102 may be the same device or different devices. Among them, the first terminal device 101 and the second terminal device 102 are mainly used to send the video to be processed associated with the target scenario and receive the target tag information of the video to be processed associated with the target scenario; the server 103 is mainly used to execute the relevant steps of the data processing method to obtain the target tag information. Among them, the first terminal device 101, the second terminal device 102, and the server 103 can be communicatively connected, and the connection method may include wired connection and wireless connection, which is not limited herein.

[0030] It should be noted that: Any of the above-mentioned terminal devices 101 and 102 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart vehicle, etc., but is not limited thereto. The above-mentioned server 103 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Figure 1 It is only an exemplary representation of the architecture diagram of the data processing system and is not limited thereto. For example, Figure 1 the server 103 in it can be deployed as a node in the blockchain network, or the server 103 can be connected to the blockchain network, so that the server 103 can upload the video data and the target label information data to the blockchain network for storage to prevent the internal data from being tampered with, thereby ensuring data security.

[0031] In a specific implementation, the server 103 obtains a video to be processed associated with a target scenario, performs video frame sampling on the video to be processed according to a sampling rule to obtain one or more sampled video frames, further extracts an image of the area to be recognized from the reference sampled video frames, and determines the reference label information associated with the target scenario of the reference sampled video frames according to the image of the area to be recognized; wherein, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the area to be recognized includes one or more of the following: the text area image of the display area where the target text object is located, the icon area image of the display area where the target icon object is located; finally, according to the reference label information of each frame of the sampled video frames in the one or more sampled video frames, the target label information associated with the target scenario of the video to be processed is determined. When the image of the area to be recognized is different, the corresponding process of determining the target label information is also different.

[0032] Based on the above description, the data processing method provided in the embodiments of the present application involves text recognition and icon recognition. Different recognition methods can be used for different area images, which can realize the automation and intelligence of the process of determining video label information, thereby effectively improving the efficiency of determining video label information.

[0033] Based on the above description of the data processing system, the embodiments of the present application disclose a data processing method. Please refer to Figure 2 which is a schematic flowchart of a data processing method disclosed in the embodiments of the present application. This data processing method can be executed by a computer device. The computer device can specifically be Figure 1The server 103 shown. Correspondingly, the data processing method may specifically include the following steps:

[0034] S201. Obtain the video to be processed associated with the target scenario, and perform video frame sampling on the video to be processed according to the sampling rule to obtain one or more sampled video frames.

[0035] Among them, the target scenario can include multiple types. Therefore, the video to be processed associated with the target scenario can be the video to be processed associated with the game scenario, or the video to be processed associated with the teaching scenario, or the video to be processed associated with the news scenario, etc. Here, the target scenario is not limited.

[0036] In a possible implementation manner, the video to be processed associated with the target scenario can be sent by the client to the server so that the server can further obtain the video processing result, and the video processing result is the target label information; the video to be processed associated with the target scenario can also be pulled by the server regularly or in real time from the Internet so that the server can further intelligently process the video to obtain the target label information. In order to intelligently recommend videos to relevant users subsequently, for example, when user A searches for videos by keywords, when the input keywords match the target label information, the corresponding video can be presented to user A.

[0037] When the video to be processed associated with the target scenario is obtained, the server can also perform video frame sampling on the video to be processed according to the sampling rule to obtain one or more sampled video frames. Among them, the sampling rule can specifically refer to setting the sampling time interval, which can include uniform sampling and skip sampling. Uniform sampling can be sampling two frames per second. For example, for a 6-second video, sampling it according to the rule of sampling two frames per second, the finally obtained is 12 sampled video frames; skip sampling can be sampling once every certain time interval. For example, sampling once every 0.5 seconds and sampling 4 frames per second. For a 5-second video, the sampling times are 1 - 2 seconds, 2.5 - 3.5 seconds, and 4 - 5 seconds, and the finally obtained is 12 sampled video frames.

[0038] Among them, it should be noted that the situation of obtaining one sampled video frame is relatively rare, but this possibility cannot be excluded. For example, for a video with an extremely short time length, such as less than 1 second, and the sampling frequency is 2 frames per second, then in this case, the sampled video frame obtained by sampling may be 1 frame.

[0039] S202. Extract the image of the area to be recognized from the reference sampled video frame, and determine the reference label information associated with the target scenario of the reference sampled video frame according to the image of the area to be recognized.

[0040] Among them, the reference sampled video frame is any frame in one or more sampled video frames. The reference sampled video frame is a name without special meaning. Similar descriptions such as the first sampled video frame and the second sampled video frame can also be used, which is not limited here.

[0041] In a possible implementation, the image of the area to be identified includes one or more of a text area image of the display area where the target text object is located and an icon area image of the display area where the target icon object is located. It can be understood that the image of the area to be identified can include two categories, one is a text area image, and the other is an icon area image; the text area image includes the target text object, and the icon area image includes the target icon object. The target text object has different text contents corresponding to different target scenes, and the target icon object has different icon contents corresponding to different target scenes. After obtaining the image of the area to be identified, the area to be identified can also be preprocessed, which can be a cutout process for the image to be identified to remove the redundant background. For example, when extracting a text area image including the words "Come on", the image area that may be extracted is relatively large, and contains more background areas, so it can be cutout to cut out as much redundant areas in the image as possible while ensuring that the words "Come on" are intact.

[0042] For example, in a game scene where two teams are fighting, the target text object may include the names of the two teams, the names of the players of each team, and the perspective of the battle, etc., and the target icon object may include the weapons used by each player of each team and the map of the battle between the two teams, etc. For another example, in a live broadcast scene where a teacher is teaching, the target text object may include the name of the teacher, the names of the students watching the live broadcast, etc., and the target icon object may include the avatar of the teacher doing the live broadcast teaching and the avatar of the students, etc. Since there are many target scenes, they will not be listed one by one here.

[0043] According to the above description, 1. When the image of the area to be recognized is the text area image of the display area where the target text object is located, the specific method for determining the reference tag information associated with the target scene of the reference sampling video frame based on the image of the area to be recognized is to perform text recognition on the text area image of the display area where the target text object is located to obtain the text object, and determine the first tag information associated with the target scene of the reference sampling video frame according to the recognized text object. For different target scenes, the first tag information is different; 2. When the image of the area to be recognized is the icon area image of the display area where the target icon object is located, the specific method for determining the reference tag information associated with the target scene of the reference sampling video frame based on the image of the area to be recognized is to perform icon recognition on the icon area image of the display area where the target icon object is located to obtain the icon object, and determine the second tag information associated with the target scene of the reference sampling video frame according to the recognized icon object. For different target scenes, the second tag information is different. 3. When the image of the area to be recognized is the text area image of the display area where the target text object is located and the icon area image of the display area where the target icon object is located, the specific method for determining the reference tag information associated with the target scene of the reference sampling video frame based on the image of the area to be recognized is to perform text recognition and icon recognition on the text area image of the display area where the target text object is located and the icon area image of the display area where the target icon object is located respectively to obtain the text object and the icon object, and determine the first tag information and the second tag information associated with the target scene of the reference sampling video frame according to the recognized icon object and text object. In this case, text recognition is performed on the text area image and icon recognition is performed on the icon area image simultaneously, realizing the combination of text recognition and icon recognition, and jointly determining the target tag information of the video to be processed, thereby improving the efficiency of determining the video tag information. Among them, both the first tag information and the second tag information refer to the above-mentioned reference tag information.

[0044] The following explains the tag information. For example, in a game scene where two teams are in a battle, when the target text objects are the team names of the two teams, the names of the players in each team, and the battle perspective, the first tag information may include the target team names, the target player names, and the target battle perspective. When the target icon objects are the weapons used by each player in each team and the map of the battle between the two teams, the second tag information may include the target weapons and the target map, etc.

[0045] S203. Determine the target tag information associated with the target scene of the video to be processed according to the reference tag information of each frame of the sampled video frame in one or more frames of the sampled video frame.

[0046] As can be seen from the above description, the reference label information may include one or both of the first label information and the second label information. The first label information is determined based on the text area image of the display area where the target text object is located, and the second label information is determined based on the icon area image of the display area where the target icon object is located. Both belong to local labels and cannot completely represent the target label information associated with the target scene. Therefore, we need to further determine the target label information associated with the target scene of the video to be processed based on the reference label information of each sampled video frame in one or more sampled video frames.

[0047] For example, in some scenarios, the label information corresponding to video segments in different time periods of the video to be processed is different. Therefore, it is necessary to further comprehensively determine the target label information of the video to be processed based on the label information of each video segment.

[0048] In a possible implementation manner, when the reference label information includes the first label information and the first label information includes the participating object label, to determine the target label information associated with the target scene of the video to be processed based on the reference label information of each sampled video frame in one or more sampled video frames, the specific process may include: determining the interrupted video segment and the playback video segment from the video to be processed according to the participating object labels of each sampled video frame in one or more sampled video frames; determining the event video segment from the video segments other than the interrupted video segment and the playback video segment in the video to be processed; wherein, the event video segment is a video segment whose video duration is greater than or equal to the first duration, the proportion of the sampled video frames including non-empty participating object labels is greater than or equal to the first proportion threshold, and the video interruption duration is less than or equal to the second duration; determining the target label information of the event video segment according to the participating object label with the largest proportion in the event video segment and the time information of the event video segment. The first duration and the second duration are specific time durations, which can be set according to different target scenes and are not specifically limited here. Further, after determining the target label information, the target label information can also be checked according to the pre-stored label information to ensure the accuracy of the obtained target label information.

[0049] Among them, the interrupted video segment described above is a video segment with a video duration greater than or equal to the third duration and the participant object labels of the sampled video frames included therein being empty, and the playback video segment is a video segment with a video duration less than or equal to the fourth duration and the proportion of the sampled video frames with non-empty participant object labels included therein being less than or equal to the second ratio threshold. Simply put, in a game battle video, the interrupted video can refer to a video without battle participants and with a duration greater than or equal to a certain time length; the playback video can refer to a video with battle participants, but with a short duration and the proportion of the frames in which the battle participants appear being small in the total number of frames. Optionally, in the target label information, the interruption label corresponding to the interrupted video and the playback label included in the playback video can also be included. Among them, both the third duration and the fourth duration are relatively small numerical values of time length, such as 2 seconds, 1 second.

[0050] If the event video segment includes multiple sub-video segments, then determine the participant object labels corresponding to each sub-video segment, and then select the participant object label with the largest proportion as the target label information of the event video segment. At the same time, according to the time information of the event video segment, determine the time labels of each sub-video segment. For example, for a game video, clip out the interrupted video and the playback video in the game video, and the remaining exciting game video segments are left. The participants of each exciting game video segment include team names, player names, etc. Determine a target label information for each exciting game video segment. For example, for a 60-second game video, 20 seconds to 22 seconds is the interrupted video, and 39 seconds to 40 seconds is the playback video. After removing these two video segments, what is obtained is video 1 from 0 to 20 seconds, video 2 from 22 to 39 seconds, and video 3 from 40 to 60 seconds. For example, for video 1, assuming that the participant object is the team name and the sampling is performed at 2 frames per second, there will be 40 sampled video frames in video 1. Then analyze the team names in these 40 sampled video frames. If it is found that the team names in 92% of the sampled video frames are "Team 1, Team 2", and the team names in 8% of the sampled video frames are "Team 1, Team 3", according to the proportion, the team name label of video 1 can be determined as "Team 1 VS Team 2". At the same time, for video 1, video 2, and video 3, time labels can also be output. For example, the time label output for video 1 is 0 to 20 seconds (i.e., including the start time and the end time), the time label output for video 2 is 22 to 39 seconds, and the time label output for video 3 is 40 to 60 seconds. The confirmation process of other target labels is the same as this process and will not be elaborated one by one. If the event video segment includes 1 sub-video segment, then select the one with the largest proportion as the target label information of the value video segment according to the participant object labels corresponding to each frame of the sampled video frames of the sub-video segment.

[0051] In some possible implementations, after determining the target label information of a video, the target label information can be stored in a database for convenient management; it can also be displayed during the video playback. Among them, there are various ways to display the label information, which can be displayed in the form of a floating window, in the form of a bubble, in the form of scrolling bullet comments, or in a transparent form (without affecting viewing). Optionally, during the video playback, there is a switch control for label information on the screen. When the control is in the on state, the label information of the video will be displayed when playing the video; when the control switches from the on state to the off state, the label information will no longer be displayed. Or in some implementation scenarios, to avoid affecting the normal viewing of the video, the label information can automatically disappear after being displayed for a certain period of time (such as 2s), and then be displayed again after an interval of a certain period of time (such as 1 minute).

[0052] For example, for a game video, the label information includes "9:00 - 9:20, the first game between Team A and Team B". When playing the video, the corresponding label information display method can be as Figure 3 shown. 310 is the label information, and the display form is a bullet comment box. 320 can refer to the switch control of the label information, and the display of the label information can be controlled through this control.

[0053] In the embodiments of the present application, first, obtain the video to be processed associated with the target scene, perform video frame sampling on the video to be processed according to the sampling rule to obtain one or more sampled video frames, then extract the image of the area to be recognized from any video frame among the one or more sampled video frames, and determine the reference label information associated with the target scene of the reference sampled video frame according to the image of the area to be recognized; wherein, the image of the area to be recognized includes one or more of the following: the text area image of the display area where the target text object is located, the icon area image of the display area where the target icon object is located; determine the target label information associated with the target scene of the video to be processed according to the reference label information of each sampled video frame in the one or more sampled video frames. When the image of the area to be recognized is different, the corresponding target label information determination process is also different. Based on the above description, it can be known that the data processing method provided by the embodiments of the present application can adopt different recognition methods for different area images, can realize the automation and intelligence of determining video label information, and thus effectively improve the efficiency of determining video label information.

[0054] According to the description of the above embodiments, when the image of the area to be recognized is an icon area image, the process of performing icon recognition on the icon area image to determine the icon object can be specifically referred to Figure 4, which is a schematic flowchart of another data processing method disclosed in the embodiments of the present application, includes the processes of obtaining a training data set, training, and prediction. This data processing method can be executed by a computer device, which can specifically be Figure 1 the server 103 shown in

[0055] S401. Obtain a reference icon image associated with the target scene from the image database.

[0056] Among them, the icon images associated with the target scene included in the image database are obtained from the image frames in the video associated with the target scene. For example, for a game scene, the icon images included in the image database are obtained from game videos.

[0057] S402. Preprocess the reference icon image, and determine a sample icon image according to the preprocessed reference icon image.

[0058] Among them, the preprocessing may include one or more of the following: performing image transformation processing on the reference icon image, and adjusting the size of the reference icon image (which can be adjusted according to a certain ratio). No matter which method is used to preprocess the reference icon image, the size of the preprocessed reference icon image is always within the set size range.

[0059] In a possible implementation manner, after preprocessing the reference icon image, determine the pixels to be adjusted in the preprocessed reference icon image whose pixel values are less than the set pixel value, and adjust the pixel values of the pixels to be adjusted in the preprocessed reference icon image to the set pixel value to obtain a sample icon image. This process is equivalent to normalizing the pixel values of the image, so that the pixel value difference between the foreground and background of the regional image including the target icon is reduced, thereby improving the subsequent model iteration rate.

[0060] S403. Generate a sample class label of the sample icon image according to the result of classifying the sample icon image using a clustering algorithm.

[0061] Specifically, use a clustering algorithm to classify the sample icon image to obtain a classification result, and generate a sample class label of the sample icon image according to the classification result.

[0062] Among them, the hierarchical clustering algorithm (Agglomerative Clustering) provided by opencv can be used to pre-classify the sample icon image. Its advantage is that the similarity of distance and rules is easy to define, with few restrictions, and there is no need to pre-set the number of clusters. Of course, other clustering algorithms can also be used to classify the sample icon image, which is not limited here.

[0063] S404. Combine the sample icon image and the sample class label to form a training data pair, and generate a training data set based on the training data pair.

[0064] Specifically, combine the sample icon image and the obtained class label to form a training data pair, and generate a training data set based on the training data pair.

[0065] Among them, steps S401 to S404 are all processes for obtaining the training data set. Taking the target scenario as a game scenario as an example, the process of obtaining the training data set is described below. For games, the icons to be recognized are generally weapons used during battles. The classification of weapons can include primary weapon, secondary weapon, score streak, operator skill, Lethal, Tactical, and background. The process of obtaining the training data set for weapon categories can include: Extract frames from 8 relatively long mobile game e-sports videos at 1 FPS (1 frame per second), and obtain the weapon region images of the currently selected weapon part in each video frame, totaling approximately 210,000 images (reference icon images). First, perform automatic pre-classification on all the images: Resize the images to 1 / 2 of the original size and convert them to grayscale images. Then, uniformly set the points with pixel values less than 127 to 127 and perform normalization processing to obtain the processed images (sample icon images); After vectorizing the processed images, use the hierarchical clustering algorithm provided by opencv for pre-classification. The parameter of the clustering algorithm is the Euclidean distance between different clusters, and the parameter of the clustering algorithm can be set to 10; Then, manually merge the categories containing the same weapon and label the class labels to obtain the weapon class labels of the weapon sample icon images. The weapon sample icon images and the weapon class labels are in one-to-one correspondence. Since the number of skill images is small, the original images are flipped horizontally and added to the training set, doubling the number; The number of background and primary weapon images is large, and 1 / 10 of them are evenly selected for training. After this series of processes, determine the training data set for the weapon classification network from the pairs of weapon sample icon images and weapon class labels.

[0066] S405. Train an icon classification network using the training data set.

[0067] Among them, step S405 describes the training process of the icon classification network. For different target scenarios, different initialized networks can be used for training.

[0068] In a possible implementation, the sample icon images included in the training dataset are input into the initialized network to obtain the predicted class labels of the sample icon images; then, based on the predicted class labels and the sample class labels, the network parameters of the initialized network are adjusted. When the loss value calculated based on the predicted class labels and the sample class labels is less than the set threshold, that is, when the prediction accuracy of the network reaches a certain threshold, the training of the initialized network is stopped to obtain the icon classification network. For example, when training a weapon classification network, the MobileNetV2 model with fewer parameters can be used as the backbone network. Specifically, the present application embodiment does not limit what kind of initialized network is used.

[0069] S406. Input the icon region image into the icon classification network for processing to obtain the icon classification result, and determine the recognized icon object according to the icon classification result.

[0070] Among them, step S406 describes the prediction process of the icon classification network. Specifically, after the icon region image is obtained through the steps S201 - S203 described in Figure 2 , the icon region image is input into the icon classification network for processing to obtain the icon classification result, and the recognized icon object is determined according to the icon classification result.

[0071] The embodiments of the present application mainly describe the training process and prediction process of the icon classification network. During the training process, the sample icon images in the training dataset are pre - trained through a clustering algorithm to obtain the sample class labels, realizing the automatic acquisition of class labels without manual labeling one by one, thereby improving the training rate of the icon classification network.

[0072] Based on the above description of the data processing method, a specific target scenario is introduced below, such as a game scenario where two teams are in a battle. In this scenario, the video to be processed is the game video to be processed. The flowchart of the specific data processing method can be seen in Figure 5 , which is a schematic flowchart of a data processing method for a game scenario disclosed in the embodiments of the present application, and specifically may include the following steps:

[0073] S501. Obtain the game video to be processed, and perform video frame sampling on the game video to be processed according to the sampling rule to obtain multiple sampled video frames.

[0074] S502. Extract the text region image and the icon region image from each sampled video frame.

[0075] Among them, the text region image may include the game player name region image, the game team name region image, and the game perspective region image, and the icon region image may include the game weapon region image. The text region image and the icon region image can be specifically seen inFigure 6 Among them, the images of the game player name areas are shown as 601 and 602, the images of the game team name areas are shown as 603 and 604, the image of the game perspective area is shown as 605, and the image of the game weapon area is shown as 606. For each sampled video frame, a target game weapon can be determined based on the image 606 of the game weapon area in the sampled video frame.

[0076] S503. Perform text recognition on the text area image to obtain text object labels, and perform icon recognition on the icon area image to obtain icon object labels.

[0077] Perform text recognition on the images of the game player name area, the game team name area, and the game perspective area respectively to determine the game player name, the game team name, and the game perspective; then perform icon recognition on the image of the game weapon area according to the trained icon classification network to obtain the game weapon.

[0078] S504. Determine the target label information of the game video to be processed according to the text object labels and the icon object labels.

[0079] Output the target label information of the game video to be processed based on the determined game player name, game team name, game perspective, and game weapon. The target label information includes the team name, the names of the players included in each team, the weapons used by each player, and the perspective of the team during the battle.

[0080] In a possible implementation manner, the game sessions in the video can also be determined according to the game player name and the game team name. For example, for a complete video with a fixed frame rate (such as 2FPS) and the game player name is recognized. A video segment that does not recognize the game player name and has a duration exceeding a time length (such as 3 seconds) is identified as a game interruption video; in the remaining non-interrupted video segments, the team names of both sides in the battle game are detected, and the occurrence times of the team names are calculated respectively. If it is less than a certain threshold, this video segment is identified as a replay video segment and is not counted in the number of sessions. After removing the replay video segments and the interruption video segments, in the remaining video segments, the segments with exactly the same team names on both sides are aggregated and sorted in chronological order. Only when the interval between two consecutive segments of the same opponent exceeds a certain time length (such as two minutes) is it considered that the number of game sessions of the two game teams increases, otherwise the number of sessions remains unchanged. Finally, the number of game sessions between all two teams in the video and the start and end times of each session can be obtained. For example, "The first game between Team A and Team B, the time is from time 1 to time 2", "The first game between Team C and Team D, the time is from time 3 to time 4", "The second game between Team A and Team B, the time is from time 5 to time 6".

[0081] Embodiments of the present application mainly provide examples of specific scenarios. Through a real scenario, the process of determining video tags is described, combining image recognition technology and text recognition technology for key regions in the game to accurately identify tag information in the video.

[0082] Based on the above method embodiments, embodiments of the present application further provide a schematic structural diagram of a data processing device. Refer to Figure 7 , which is a schematic structural diagram of an image processing device provided by an embodiment of the present application. Figure 7 The data processing device 700 shown can operate the following units:

[0083] An acquisition unit 701, configured to acquire a video to be processed associated with a target scenario, and perform video frame sampling on the video to be processed according to a sampling rule to obtain one or more sampled video frames;

[0084] A processing unit 702, configured to extract an image of a region to be recognized from a reference sampled video frame, and determine reference tag information associated with the target scenario according to the image of the region to be recognized; wherein, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the region to be recognized includes one or more of the following: a text region image of a display region where a target text object is located, an icon region image of a display region where a target icon object is located;

[0085] A determination unit 703, configured to determine target tag information associated with the target scenario of the video to be processed according to the reference tag information of each frame of the one or more sampled video frames.

[0086] In a possible implementation manner, the determination unit 703 determines the reference tag information associated with the target scenario according to the image of the region to be recognized, including:

[0087] When the image of the region to be recognized includes a text region image of a display region where a target text object is located, perform text recognition on the text region image, and determine first tag information associated with the target scenario of the reference sampled video frame according to the recognized text object;

[0088] When the image of the region to be recognized includes an icon region image of a display region where a target icon object is located, perform icon recognition on the icon region image, and determine second tag information associated with the target scenario of the reference sampled video frame according to the recognized icon object;

[0089] Wherein, the reference tag information includes one or more of the first tag information and the second tag information.

[0090] In a possible implementation, the processing unit 702 performs icon recognition on the icon area image, including:

[0091] Inputting the icon area image into an icon classification network for processing to obtain an icon classification result;

[0092] Determining the recognized icon object according to the icon classification result;

[0093] Wherein, the icon classification network is obtained by training using a training data set, the training data set includes multiple groups of training data pairs, each group of training data pairs includes a sample icon image and a sample category label of the sample icon image, and the sample category label is generated according to the result of classifying the sample icon image by using a clustering algorithm.

[0094] In a possible implementation, the obtaining unit 701 is further configured to obtain a reference icon image associated with the target scene from an image database, and the icon images associated with the target scene included in the image database are obtained from the image frames in a video associated with the target scene;

[0095] The processing unit 702 is further configured to:

[0096] Preprocess the reference icon image, and determine a sample icon image according to the preprocessed reference icon image; wherein, preprocessing the reference icon image includes one or more of the following: performing image transformation processing on the reference icon image, and adjusting the size of the reference icon image, and the size of the adjusted reference icon image is within a set size range;

[0097] Generating a sample category label of the sample icon image according to the result of classifying the sample icon image by using a clustering algorithm; forming a training data pair with the sample icon image and the sample category label, and generating a training data set according to the training data pair.

[0098] In a possible implementation, the processing unit 702 determines a sample icon image according to the preprocessed reference icon image, including:

[0099] Determining the to-be-adjusted pixel points in the preprocessed reference icon image whose pixel values are less than a set pixel value;

[0100] Adjusting the pixel values of the to-be-adjusted pixel points in the preprocessed reference icon image to the set pixel value to obtain a sample icon image.

[0101] In a possible implementation, the reference label information includes the first label information, and the first label information includes a participating object label;

[0102] The determining unit 703 determines the target label information associated with the target scene of the video to be processed according to the reference label information of each sampled video frame in the one or more sampled video frames, including:

[0103] Determine an interrupted video segment and a playback video segment from the video to be processed according to the participating object labels of each sampled video frame in the one or more sampled video frames;

[0104] Determine an event video segment from the video segments of the video to be processed other than the interrupted video segment and the playback video segment; wherein, the event video segment is a video segment with a video duration greater than or equal to a first duration, the proportion of sampled video frames including non-empty participating object labels is greater than or equal to a first proportion threshold, and the video interruption duration is less than or equal to a second duration;

[0105] Determine the target label information of the event video segment according to the participating object label with the largest proportion in the event video segment and the time information of the event video segment.

[0106] In a possible implementation manner, the processing unit 702 performs video frame sampling on the video to be processed according to a sampling rule, and obtains one or more sampled video frames, including:

[0107] Perform video frame sampling on the video to be processed according to a set sampling time interval, and obtain one or more sampled video frames.

[0108] According to an embodiment of the present application, Figure 2 、 Figure 4 and Figure 5 Each step involved in the data processing method shown can be executed by each unit in the Figure 7 data processing device shown. Taking Figure 2 as an example, step S201 can be executed by the obtaining unit 701 in the Figure 7 data processing device shown, step S202 can be executed by the processing unit 702 in the Figure 7 data processing device shown, and step S203 can be executed by the determining unit 703 in the Figure 7 data processing device shown.

[0109] According to another embodiment of the present application, Figure 7Each unit in the data processing device shown can be separately or all combined into one or several other units to form, or some of them can be further split into multiple smaller units with more specific functions to form. This can achieve the same operations without affecting the realization of the technical effects of the embodiments of this application. The above units are divided based on logical functions. In practical applications, the function of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of this application, based on the data processing device, other units can also be included. In practical applications, these functions can also be assisted by other units and can be realized through the cooperation of multiple units.

[0110] According to another embodiment of this application, it can be achieved by running a computer program (including program code) that can execute the respective steps involved in the corresponding method shown in, for example, on a general computing device such as a computer that includes processing elements and storage elements such as a central processing unit (CPU), a random access storage medium (RAM), and a read-only storage medium (ROM). Figure 2 , Figure 4 and Figure 5 to construct the data processing device shown in, and to implement the data processing method of the embodiments of this application. The computer program can be recorded on, for example, a computer-readable storage medium, loaded into the above computing device through the computer-readable storage medium, and run therein. Figure 7

[0111] In the embodiments of this application, first, the acquisition unit 701 acquires a video to be processed associated with a target scenario, and the processing unit 702 samples the video frames of the video to be processed according to a sampling rule to obtain one or more sampled video frames; then, for any sampled video frame, an image of the region to be recognized is extracted from the any sampled video frame (including the text region image of the display region where the target text object is located and / or the icon region image of the display region where the target icon object is located), and reference label information associated with the target scenario of the any sampled video frame is determined according to the image of the region to be recognized; finally, the determination unit 703 determines the target label information associated with the target scenario of the video to be processed according to the reference label information of each sampled video frame. By adopting this method, the automation and intelligence of determining video label information can be realized, thereby effectively improving the efficiency of determining video label information.

[0112] Based on the above method and device embodiments, the embodiments of this application provide a computer device, and the computer device can be Figure 1 the server 103 shown. Refer to Figure 8 , which is a schematic structural diagram of a computer device provided by the embodiments of this application. Figure 8The computer device 800 shown at least includes a processor 801, an input interface 802, an output interface 803, a computer storage medium 804, and a memory 805. Among them, the processor 801, the input interface 802, the output interface 803, the computer storage medium 804, and the memory 805 can be connected through a bus or other means.

[0113] The computer storage medium 804 can be stored in the memory 805 of the computer device 800. The computer storage medium 804 is used to store a computer program, and the computer program includes program instructions. The processor 801 is used to execute the program instructions stored in the computer storage medium 804. The processor 801 (or CPU (Central Processing Unit, central processor)) is the computing core and control core of the computer device 800, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more computer instructions to implement the corresponding method flow or corresponding function.

[0114] The embodiment of the present application also provides a computer storage medium (Memory). The computer storage medium is a memory device in the computer device 800, which is used to store programs and data. It can be understood that the computer storage medium here can include both the built-in storage medium in the computer device 800, and of course, can also include the extended storage medium supported by the computer device 800. The computer storage medium provides a storage space, and the operating system of the computer device 800 is stored in this storage space. And, one or more instructions suitable for being loaded and executed by the processor 801 are also stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory; optionally, it can also be at least one computer storage medium located far from the aforementioned processor.

[0115] In one embodiment, the computer storage medium can be loaded and executed by the processor 801 with one or more instructions stored in the computer storage medium to implement the above-mentioned relevant Figure 2 and Figure 3 corresponding steps of the data processing method shown. In a specific implementation, one or more instructions in the computer storage medium are loaded and executed by the processor 801 as follows:

[0116] Obtain a video to be processed associated with a target scenario, and perform video frame sampling on the video to be processed according to a sampling rule to obtain one or more sampled video frames;

[0117] Extract the image of the area to be recognized from the reference sampled video frame, and determine the reference label information associated with the target scene according to the image of the area to be recognized; wherein, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the area to be recognized includes one or more of the following: the text area image of the display area where the target text object is located, the icon area image of the display area where the target icon object is located;

[0118] Determine the target label information associated with the target scene of the video to be processed according to the reference label information of each frame in the one or more sampled video frames.

[0119] In a possible implementation manner, the processor 801 determines the reference label information associated with the target scene according to the image of the area to be recognized, including:

[0120] When the image of the area to be recognized includes the text area image of the display area where the target text object is located, perform text recognition on the text area image, and determine the first label information associated with the target scene of the reference sampled video frame according to the recognized text object;

[0121] When the image of the area to be recognized includes the icon area image of the display area where the target icon object is located, perform icon recognition on the icon area image, and determine the second label information associated with the target scene of the reference sampled video frame according to the recognized icon object;

[0122] Wherein, the reference label information includes one or more of the first label information and the second label information.

[0123] In a possible implementation manner, the processor 801 performs icon recognition on the icon area image, including:

[0124] Input the icon area image into an icon classification network for processing to obtain an icon classification result;

[0125] Determine the recognized icon object according to the icon classification result;

[0126] Wherein, the icon classification network is trained by using a training data set, the training data set includes multiple groups of training data pairs, and each group of training data pairs includes a sample icon image and the sample category label of the sample icon image, and the sample category label is generated according to the result of classifying the sample icon image by using a clustering algorithm.

[0127] In a possible implementation manner, the processor 801 is further configured to:

[0128] Obtain a reference icon image associated with the target scene from an image database, where the icon images included in the image database and associated with the target scene are obtained from image frames in a video associated with the target scene;

[0129] Preprocess the reference icon image, and determine a sample icon image according to the preprocessed reference icon image; wherein, preprocessing the reference icon image includes one or more of the following: performing an image transformation process on the reference icon image, and adjusting the size of the reference icon image, and the size of the adjusted reference icon image is within a set size range;

[0130] Generate a sample class label of the sample icon image according to the result of classifying the sample icon image using a clustering algorithm; form a training data pair with the sample icon image and the sample class label, and generate a training data set according to the training data pair.

[0131] In a possible implementation manner, the processor 801 determines a sample icon image according to the preprocessed reference icon image, including:

[0132] Determine the pixel points to be adjusted in the preprocessed reference icon image whose pixel values are less than a set pixel value;

[0133] Adjust the pixel values of the pixel points to be adjusted in the preprocessed reference icon image to the set pixel value to obtain a sample icon image.

[0134] In a possible implementation manner, the reference label information includes the first label information, and the first label information includes a participating object label; the processor 801 determines the target label information associated with the target scene of the video to be processed according to the reference label information of each frame of the sampled video frame in the one or more frames of sampled video frames, including:

[0135] According to the participating object labels of each frame of the sampled video frame in the one or more frames of sampled video frames, determine an interrupted video segment and a playback video segment from the video to be processed;

[0136] Determine an event video segment from the video segments other than the interrupted video segment and the playback video segment in the video to be processed; wherein, the event video segment is a video segment whose video duration is greater than or equal to a first duration, the proportion of the sampled video frames including non-empty participating object labels is greater than or equal to a first proportion threshold, and the video interruption duration is less than or equal to a second duration;

[0137] Determine the target tag information of the event video segment according to the participation object tag with the largest proportion in the event video segment and the time information of the event video segment.

[0138] In a possible implementation, the processor 801 samples video frames of the video to be processed according to a sampling rule, and obtains one or more sampled video frames, including:

[0139] Sample video frames of the video to be processed at a set sampling time interval to obtain one or more sampled video frames.

[0140] In the embodiment of the present application, the processor 801 first obtains the video to be processed associated with the target scene, samples video frames of the video to be processed according to a sampling rule to obtain one or more sampled video frames; then for any sampled video frame, extract the image of the area to be recognized from the any sampled video frame (including the text area image of the display area where the target text object is located and / or the icon area image of the display area where the target icon object is located), and determine the reference tag information associated with the target scene of the any sampled video frame according to the image of the area to be recognized; finally, determine the target tag information associated with the target scene of the video to be processed according to the reference tag information of each sampled video frame. By adopting this method, the automation and intelligence of determining video tag information can be realized, thereby effectively improving the efficiency of determining video tag information.

[0141] According to one aspect of the present application, the embodiment of the present application further provides a computer product or a computer program. The computer product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor 801 reads the computer instructions from the computer-readable storage medium, and the processor 801 executes the computer instructions, so that the computer device 800 executes Figure 2 、 Figure 4 And Figure 5 The data processing methods shown.

[0142] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps may be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0143] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above-mentioned module division is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0144] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A data processing method, characterized in that, The method includes: Obtain a video to be processed associated with a target scenario, and perform video frame sampling on the video to be processed according to a sampling rule to obtain one or more sampled video frames; Extract an image of a region to be recognized from a reference sampled video frame, and determine reference label information associated with the target scenario for the reference sampled video frame according to the image of the region to be recognized; wherein, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the region to be recognized includes one or more of the following: a text region image of a display region where a target text object is located, an icon region image of a display region where a target icon object is located; the reference label information includes a participating object label; Determine an interrupted video segment and a playback video segment from the video to be processed according to the participating object labels of each sampled video frame in the one or more sampled video frames; wherein, the interrupted video segment is a video segment with a video duration greater than or equal to a third duration and the participating object labels of the sampled video frames included therein being empty; the playback video segment is a video segment with a video duration less than or equal to a fourth duration and the proportion of the sampled video frames with non-empty participating object labels included therein being less than or equal to a second proportion threshold; Determine an event video segment from the video segment of the video to be processed other than the interrupted video segment and the playback video segment; wherein, the event video segment is a video segment with a video duration greater than or equal to a first duration, the proportion of the sampled video frames with non-empty participating object labels included therein being greater than or equal to a first proportion threshold, and the video interruption duration being less than or equal to a second duration; Determine target label information of the event video segment according to the participating object label with the largest proportion in the event video segment and the time information of the event video segment.

2. The method according to claim 1, wherein The determining the reference label information associated with the target scenario for the reference sampled video frame according to the image of the region to be recognized includes: When the image of the region to be recognized includes a text region image of a display region where a target text object is located, perform text recognition on the text region image, and determine first label information associated with the target scenario for the reference sampled video frame according to the recognized text object; When the image of the region to be recognized includes an icon region image of a display region where a target icon object is located, perform icon recognition on the icon region image, and determine second label information associated with the target scenario for the reference sampled video frame according to the recognized icon object; Wherein, the reference label information includes one or more of the first label information and the second label information.

3. The method according to claim 2, wherein The performing icon recognition on the icon region image includes: Input the icon region image into an icon classification network for processing to obtain an icon classification result; Determine the recognized icon object according to the icon classification result; Among them, the icon classification network is obtained by training with a training data set. The training data set includes multiple groups of training data pairs. Each group of training data pairs includes a sample icon image and a sample category label of the sample icon image. The sample category label is generated according to the result of classifying the sample icon image by using a clustering algorithm.

4. The method according to claim 3, characterized in that, The method further includes: obtaining a reference icon image associated with the target scene from an image database. The icon images included in the image database and associated with the target scene are obtained from the image frames in the video associated with the target scene; performing preprocessing on the reference icon image, and determining a sample icon image according to the preprocessed reference icon image. Among them, performing preprocessing on the reference icon image includes one or more of the following: performing image transformation processing on the reference icon image, and adjusting the size of the reference icon image, and the size of the adjusted reference icon image is within a set size range; generating a sample category label of the sample icon image according to the result of classifying the sample icon image by using a clustering algorithm; forming the sample icon image and the sample category label into a training data pair, and generating a training data set according to the training data pair.

5. The method according to claim 4, characterized in that, The determining the sample icon image according to the preprocessed reference icon image includes: determining the to-be-adjusted pixel points in the preprocessed reference icon image whose pixel values are less than a set pixel value; adjusting the pixel values of the to-be-adjusted pixel points in the preprocessed reference icon image to the set pixel value to obtain a sample icon image.

6. The method according to any one of claims 1-5, characterized in that, The performing video frame sampling on the to-be-processed video according to a sampling rule to obtain one or more sampled video frames includes: performing video frame sampling on the to-be-processed video at a set sampling time interval to obtain one or more sampled video frames.

7. A data processing device, characterized in that, The device includes: an obtaining unit, configured to obtain a to-be-processed video associated with a target scene, and perform video frame sampling on the to-be-processed video according to a sampling rule to obtain one or more sampled video frames; a processing unit, configured to extract an image of a to-be-identified region from a reference sampled video frame, and determine reference label information associated with the target scene of the reference sampled video frame according to the image of the to-be-identified region. Among them, the reference sampled video frame is any one of the one or more sampled video frames, and the image of the to-be-identified region includes one or more of the following: a text region image of a display region where a target text object is located, an icon region image of a display region where a target icon object is located; the reference label information includes a participating object label. A determination unit, configured to: determine an interrupted video segment and a playback video segment from the video to be processed according to the participation object tags of each sampled video frame in the one or more sampled video frames; wherein, the interrupted video segment is a video segment with a video duration greater than or equal to a third duration and the participation object tags of the included sampled video frames are empty; the playback video segment is a video segment with a video duration less than or equal to a fourth duration and the proportion of the included sampled video frames with non-empty participation object tags is less than or equal to a second proportion threshold; determine an event video segment from the video segment other than the interrupted video segment and the playback video segment in the video to be processed; wherein, the event video segment is a video segment with a video duration greater than or equal to a first duration, the proportion of the included sampled video frames with non-empty participation object tags is greater than or equal to a first proportion threshold, and the video interruption duration is less than or equal to a second duration; determine the target tag information of the event video segment according to the participation object tag with the largest proportion in the event video segment and the time information of the event video segment.

8. A computer device, characterized in that, Including an input interface and an output interface, the computer device further includes: A processor, adapted to implement one or more computer programs; and, A computer storage medium, the computer storage medium stores one or more computer programs, and the one or more computer programs are adapted to be loaded and executed by the processor to perform the data processing method according to any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer storage medium stores one or more computer programs, and the one or more computer programs are adapted to be loaded and executed by the processor to perform the data processing method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program, the computer program is stored in a computer-readable storage medium, the processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program to enable the computer device to perform the data processing method according to any one of claims 1-6.

Images