A video processing method and related equipment

Abstract

The present disclosure relates to a video processing method and related equipment, the method comprising: in response to a series video viewing instruction corresponding to a currently playing video, displaying a video collection display page; in the video collection display page, displaying a series video corresponding to the currently playing video according to a preset effect; the series video includes the currently playing video; the series video corresponds to the same account ID. When a viewing user is willing to watch videos in the same series as the currently playing video and enters the video collection display page, the present disclosure can highlight the series video corresponding to the currently playing video in the video collection display page, so that the series video is distinguished from other videos on the video collection display page, so that the viewing user can pay more attention to the series video, thus saving time in finding the series video, reducing the tediousness of playing the series video, and improving the user's viewing experience.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to a video processing method and related equipment. Background Art

[0002] With the popularization of mobile Internet, various video software has been widely used in people's daily lives, so that users can watch short videos posted by various users through the video software.

[0003] In the field of short videos, consumers are usually attracted to series videos when browsing short videos, such as TV drama commentary, character experience introduction, special knowledge popularization, etc. Such videos are generally divided into multiple episodes to be told. When consumers are attracted by one of them and intend to watch the same series of videos, they need to enter the creator's homepage and find related videos among the large number of works published by the creator. The whole process is relatively time-consuming, which increases the cumbersomeness of series video playback and affects users' viewing experience of series videos. Summary of the invention

[0004] The present disclosure provides a video processing method and related equipment. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a video processing method is provided, including:

[0006] In response to a series video viewing instruction corresponding to the currently playing video, display a video collection display page;

[0007] Determine a video collection corresponding to the account ID according to the obtained video ID and account ID of the currently playing video; the video collection includes multiple release times and multiple video IDs corresponding to multiple videos;

[0008] Based on the release time and video identifier of each video in the multiple videos, determine a series of videos corresponding to the currently played video from the multiple videos;

[0009] In the video collection display page, series videos are displayed according to preset effects; the series videos include the currently playing video; the series videos correspond to the same account ID.

[0010] In some possible embodiments, based on the release time and video identifier of each video in the multiple videos, determining a series of videos corresponding to the currently played video from the multiple videos includes:

[0011] Sorting the multiple videos based on the release time of each of the multiple videos to obtain a plurality of sorted videos;

[0012] Based on the video identifier of the currently playing video, determine the current ranking of the currently playing video among the multiple videos, determine the videos with preset positions before and after the current ranking as the videos to be matched, and obtain a set of videos to be matched;

[0013] A series of videos is determined from the set of videos to be matched.

[0014] In some possible embodiments, determining a series of videos from a set of videos to be matched includes:

[0015] Obtain text description information of the currently playing video and text description information of each to-be-matched video in the to-be-matched video set;

[0016] Determining a first matching degree value between the currently playing video and each of the videos to be matched based on the text description information of the currently playing video and the text description information of each of the videos to be matched;

[0017] A target video in the to-be-matched video set is determined as a series of videos; and a first matching degree value corresponding to the target video is greater than or equal to a first preset value.

[0018] In some possible embodiments, determining a first matching degree value between the currently playing video and each to-be-matched video based on the text description information of the currently playing video and the text description information of each to-be-matched video includes:

[0019] Perform word segmentation processing on the text description information of the currently playing video to obtain a first word segmentation result;

[0020] Perform word segmentation processing on the text description information of the matching video to obtain a second word segmentation result;

[0021] Input the first word segmentation result into the word vector model to obtain the corresponding first word vector;

[0022] Input the second word segmentation result into the word vector model to obtain the corresponding second word vector;

[0023] Determine a first matching degree value between the first word vector and the second word vector according to a cosine similarity calculation formula;

[0024] A first matching degree value between the first word vector and the second word vector is determined as a first matching degree value between the currently playing video and the video to be matched.

[0025] In some possible embodiments, determining a series of videos from a set of videos to be matched includes:

[0026] Obtaining a representation image of the currently playing video and a representation image of each to-be-matched video in the to-be-matched video set;

[0027] Determine a second matching degree value between the representation image of the currently playing video and the representation images of each to-be-matched video according to the trained image matching model;

[0028] A target video in the to-be-matched video set is determined as a series of videos; and a second matching degree value corresponding to the target video is greater than or equal to a second preset value.

[0029] In some possible embodiments, the image matching model is generated by:

[0030] Acquire multiple training image pairs; each of the multiple training image pairs includes two training images and corresponding matching labels;

[0031] Constructing a preset machine learning model; the preset machine learning model includes a first feature extraction module and a second feature extraction module;

[0032] Inputting one of the two training images into a first feature extraction module to obtain a first feature vector;

[0033] Inputting the other training image of the two training images into a second feature extraction module to obtain a second feature vector;

[0034] According to the first eigenvector, the second eigenvector and the matching label, the preset machine learning model is trained to obtain an image matching model.

[0035] In some possible embodiments, in the video collection display page, a series of videos corresponding to the currently playing video are displayed according to a preset effect, including:

[0036] In the display area corresponding to the series video on the video collection display page, a special effect animation for highlighting the series video is displayed;

[0037] or;

[0038] In the display area corresponding to the series video on the video collection display page, text prompt information is displayed; the text prompt information is used to prompt that the video in the current display area is a series video corresponding to the currently playing video;

[0039] or;

[0040] On the video collection display page, the dynamic stroke process along the edge of the display area corresponding to the series of videos is displayed.

[0041] According to a second aspect of an embodiment of the present disclosure, there is provided a video processing device, including:

[0042] A first display module is configured to execute a series video viewing instruction corresponding to a currently playing video and display a video collection display page;

[0043] The first determination module is configured to determine a video collection corresponding to the account identifier based on the video identifier and the account identifier of the currently playing video; the video collection includes multiple release times and multiple video identifiers corresponding to multiple videos;

[0044] A second determination module is configured to determine a series of videos corresponding to a currently played video from a plurality of videos based on a release time and a video identifier of each of the plurality of videos;

[0045] The second display module is configured to be executed in the video collection display page to display a series of videos according to a preset effect; the series of videos includes the currently playing video; the series of videos correspond to the same account ID.

[0046] In some possible embodiments, the second determining module includes:

[0047] A sorting submodule is configured to sort the multiple videos based on the release time of each of the multiple videos to obtain a plurality of sorted videos;

[0048] The first determination submodule is configured to execute a video identification based on the currently playing video, determine the current ranking of the currently playing video among the multiple videos, determine the videos with a preset number of places before and after the current ranking as the videos to be matched, and obtain a set of videos to be matched;

[0049] The second determination submodule is configured to determine a series of videos from the set of videos to be matched.

[0050] In some possible embodiments, the second determination submodule is further configured to execute the acquisition of text description information of the currently playing video and text description information of each video to be matched in the set of videos to be matched; determine a first matching degree value between the currently playing video and each video to be matched based on the text description information of the currently playing video and the text description information of each video to be matched; determine a target video in the set of videos to be matched as a series of videos; and the first matching degree value corresponding to the target video is greater than or equal to a first preset value.

[0051] In some possible embodiments, the second determination submodule is further configured to perform word segmentation processing on the text description information of the currently playing video to obtain a first word segmentation result; perform word segmentation processing on the text description information of the video to be matched to obtain a second word segmentation result; input the first word segmentation result into the word vector model to obtain the corresponding first word vector; input the second word segmentation result into the word vector model to obtain the corresponding second word vector; determine the first matching degree value between the first word vector and the second word vector according to the cosine similarity calculation formula; determine the first matching degree value between the first word vector and the second word vector as the first matching degree value between the currently playing video and the video to be matched.

[0052] In some possible embodiments, the second determination submodule is further configured to execute the acquisition of a representation image of the currently playing video and a representation image of each video to be matched in a set of videos to be matched; determine a second matching degree value between the representation image of the currently playing video and the representation image of each video to be matched based on a trained image matching model; determine a target video in the set of videos to be matched as a series of videos; and the second matching degree value corresponding to the target video is greater than or equal to a second preset value.

[0053] In some possible embodiments, the device also includes a generation method module of an image matching model, and the generation method module of the image matching model is configured to execute acquisition of multiple training image pairs; each training image pair in the multiple training image pairs includes two training images and corresponding matching labels; construct a preset machine learning model; the preset machine learning model includes a first feature extraction module and a second feature extraction module; input one of the two training images into the first feature extraction module to obtain a first feature vector; input the other training image of the two training images into the second feature extraction module to obtain a second feature vector; train the preset machine learning model according to the first feature vector, the second feature vector and the matching label to obtain an image matching model.

[0054] In some possible embodiments, the second display module is further configured to display a special effect animation for highlighting the series of videos in the display area corresponding to the series of videos in the video collection display page; or; display text prompt information in the display area corresponding to the series of videos in the video collection display page; the text prompt information is used to prompt that the video in the current display area is a series of videos corresponding to the currently playing video; or; in the video collection display page, display a dynamic stroking process along the edge of the display area corresponding to the series of videos.

[0055] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0056] processor;

[0057] a memory for storing processor-executable instructions;

[0058] The processor is configured to execute instructions to implement the video processing method of the first aspect of the embodiment of the present disclosure.

[0059] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the video processing method of the first aspect of the embodiment of the present disclosure.

[0060] According to the fifth aspect of the embodiments of the present disclosure, a computer program product is provided, the computer program product includes a computer program, the computer program is stored in a readable storage medium, at least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the computer device executes the video processing method of the first aspect of the embodiments of the present disclosure.

[0061] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0062] In response to the series video viewing instruction corresponding to the currently playing video, the video collection display page is displayed; in the video collection display page, the series videos corresponding to the currently playing video are displayed according to the preset effect; the series videos include the currently playing video; the series videos correspond to the same account ID. In this way, when the viewing user intends to watch the videos in the same series as the currently playing video and enters the video collection display page, the series videos corresponding to the currently playing video are highlighted in the video collection display page, so that the series videos are distinguished from other videos on the video collection display page, making it easier for the viewing user to pay attention to the series videos. In this way, it can save time in finding series videos, reduce the tediousness of playing series videos, and improve the user viewing experience.

[0063] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0065] Figure 1 is a schematic diagram of an application environment according to an exemplary embodiment;

[0066] Figure 2 is a flow chart of a video processing method according to an exemplary embodiment;

[0067] Figure 3 is a page schematic diagram of a terminal device according to an exemplary embodiment;

[0068] Figure 4 is a flow chart showing a method of determining a set of videos to be matched from multiple videos according to an exemplary embodiment;

[0069] Figure 5 is a flowchart showing a method of determining a series of videos from a set of videos to be matched according to an exemplary embodiment;

[0070] Figure 6is another flowchart showing a method of determining a series of videos from a set of videos to be matched according to an exemplary embodiment;

[0071] Figure 7 is a flow chart showing a method for generating an image matching model according to an exemplary embodiment;

[0072] Figure 8 is a schematic diagram of a structure of a preset machine learning model according to an exemplary embodiment;

[0073] Fig. 9 is a schematic diagram of a video collection display page according to an exemplary embodiment;

[0074] Fig.10 is a block diagram of a video processing device according to an exemplary embodiment;

[0075] Fig.11 The invention is a block diagram of an electronic device for video processing according to an exemplary embodiment. DETAILED DESCRIPTION

[0076] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0077] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar first objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0078] It should be noted that the user information involved in this disclosure (including but not limited to user device information, user personal information, etc.) is all information authorized by the user or fully authorized by all parties.

[0079] See also Figure 1 , Figure 1 A schematic diagram of an application environment according to an exemplary embodiment is shown as follows: Figure 1 As shown, it includes a server 01 and a terminal device 02. Optionally, the server 01 and the terminal device 02 may be connected via a wireless link or a wired link, which is not limited in the present disclosure.

[0080] In an optional embodiment, the server 01 can provide different videos to the terminal device 02 for the user to browse. Specifically, the server 01 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. Optionally, the operating system running on the server 01 may include but is not limited to IOS, Linux, Windows, Unix, Android systems, etc.

[0081] In an optional embodiment, the terminal device 02 can receive and play various videos provided by the server 01. The terminal device 02 can respond to instructions triggered by user operations, such as a series of video viewing instructions corresponding to the currently playing video, and display the corresponding video collection display page; in the video collection display page, the series of videos corresponding to the currently playing video are displayed according to the preset effect. Specifically, the terminal device 02 may include but is not limited to electronic devices such as smart phones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, smart wearable devices, etc. Optionally, the operating system running on the electronic device may include but is not limited to Android, IOS, Linux, Windows, etc.

[0082] In addition, it should be noted that Figure 1 What is shown is only one application environment of the video processing method provided by the present disclosure. In practical applications, other application environments may also be included.

[0083] Figure 2 is a flowchart of a video processing method according to an exemplary embodiment. Figure 2 As shown, the video processing method is applicable to a terminal device and includes the following steps:

[0084] In step S201, in response to a series video viewing instruction corresponding to the currently playing video, a video collection display page is displayed.

[0085] In the disclosed embodiment, video software is installed on the terminal device, and the user can browse various types of videos through the video software. Among them, the series video viewing instruction corresponding to the currently playing video represents the user's willingness to watch the series of videos corresponding to the currently playing video. The instruction can be triggered by a user operation on the browsing page of the video software; when the instruction is triggered, the browsing page of the video software is playing the currently playing video, so that the instruction carries information for determining the series of videos corresponding to the currently playing video. The specific information will be described in detail below and will not be repeated here. The video collection display page is used to display multiple videos, and the multiple videos can be published by the same creator or by different creators. The series of videos described in the present disclosure refers to at least two videos produced and uploaded by the creator around the same or similar themes; the types of series videos can include TV series commentary, character experience introduction, special knowledge popularization, etc.

[0086] In short video application scenarios, short video software usually provides a short video browsing page, which can switch to play different short videos according to user operations. For example, the terminal device detects the user's sliding operation in the short video browsing page and switches from the currently playing short video to the next short video for playback. However, since short video software provides fragmented videos, the content displayed by the currently playing video and the next short video are usually unrelated. This means that when a user browses a video in a series of videos, they need to enter the creator's homepage and find other videos in the series among the large number of works published by the creator. The whole process is very time-consuming and affects the user's viewing experience of the series of videos.

[0087] Based on this, the embodiment of the present disclosure proposes a video processing method, which can highlight the series videos corresponding to the currently playing video in the creator's homepage, so that the series videos can be distinguished from other videos on the creator's homepage, making it easier for viewing users to pay attention to the series videos. In this way, it can save time in searching for series videos, reduce the tediousness of playing series videos, and improve the user viewing experience.

[0088] In some possible embodiments, the series video viewing instruction corresponding to the currently playing video may be generated by triggering a jump operation from the current video playback page to the video collection display page. Specifically, the above-mentioned jump operation from the current video playback page to the video collection display page may include a left swipe operation, a right swipe operation, or a click operation on the creator's avatar within the current video playback page. Correspondingly, the video collection display page may refer to the creator's homepage. At this time, the multiple videos displayed in the video collection display page are all published by the same creator, that is, the multiple videos displayed in the video collection display page correspond to the same account ID, which is the creator's account ID; in addition to all the videos published by the creator, the video collection display page may also display the creator's personal information.

[0089] like Figure 3 As shown, Figure 3 : is a page schematic diagram of a terminal device provided by an embodiment of the present disclosure. After the terminal device opens the short video software, the current video playback page 30 is displayed. The user can continuously switch the video being played in the current video playback page 30 through specified operations; in addition to displaying the currently playing video, the current video playback page 30 also displays the creator information corresponding to the currently playing video, such as the creator's avatar; at a certain moment, the user watches the video 301 being played in the current video playback page 30. The content of the video 301 is about the episode commentary of a certain TV series, such as the commentary of the first episode of TV series A. If the user wants to watch the commentary of the second episode of TV series A, the user can click the creator's avatar or swipe left to trigger the series video viewing instruction corresponding to the currently playing video. The terminal device responds to the instruction and displays the video collection display page 31, that is, the creator's homepage.

[0090] In order to highlight the series of videos corresponding to the currently playing video on the video collection display page, the terminal device needs to first identify which of the series of videos corresponding to the currently playing video are displayed on the video collection display page.

[0091] In step S203, based on the obtained video ID and account ID of the currently playing video, a video collection corresponding to the account ID is determined; the video collection includes multiple release times and multiple video IDs corresponding to multiple videos.

[0092] The video ID of the currently playing video is used to characterize the uniqueness of the video, which can be generated by the terminal device or the backend server when it is released. The video ID can be formed by numbers, letters, or a combination of the two. The account ID of the currently playing video is the account ID of the creator who published the currently playing video.

[0093] Specifically, according to the account ID of the creator who posted the currently played video, all videos that the creator has posted are searched in the preset storage area to form a corresponding video collection; wherein the preset storage area can be a cache area of ​​the terminal device. When the creator posts a video, the terminal device can store the relevant information of the posted video (such as the video posting time, video ID) in the cache area so that it can be called when needed, which can save the time of the terminal device to obtain relevant information from the backend server and improve the efficiency of video processing.

[0094] In step S205, based on the release time and video identifier of each video in the multiple videos, a series of videos corresponding to the currently played video is determined from the multiple videos.

[0095] In order to narrow the search scope of the series of videos, the terminal device can preliminarily screen all videos that the creator has released. Considering that the series of videos may be released continuously by the creator over a period of time, the terminal device can first preliminarily screen multiple videos based on the release time and video identifier of each video in the multiple videos to obtain a set of videos to be matched, and then further match and verify each video to be matched in the set of videos to be matched with the currently playing video.

[0096] In a specific embodiment, step S205 may include: Figure 4 The following steps are shown:

[0097] In step S401, the multiple videos are sorted based on the release time of each video in the multiple videos to obtain a plurality of sorted videos.

[0098] For example, according to the release time of each video, multiple videos are sorted in order from the earliest release time to the latest release time, so as to obtain multiple videos sorted by time.

[0099] In step S403, based on the video identifier of the currently playing video, the current ranking of the currently playing video among the multiple videos is determined, and the videos with preset digits before and after the current ranking are determined as the videos to be matched, thereby obtaining a set of videos to be matched.

[0100] The preset number of bits may be determined according to actual applications; for example, the preset number of bits may be 10 bits, and the to-be-matched video set includes 20 to-be-matched videos.

[0101] In step S405, a series of videos is determined from the set of videos to be matched.

[0102] After a preliminary screening of all videos that the creator has released, a set of videos to be matched is obtained, and then the set of videos to be matched is further screened to determine the series of videos corresponding to the currently playing video.

[0103] In the above embodiment, all videos in the video collection display page are sorted according to the release time, and then the currently playing video is located according to the video identifier, and the preset digits before and after are selected to complete the initial screening of the series video. Subsequently, each to-be-matched video in the to-be-matched video set is further matched with the currently playing video. This can reduce the number of video matches, improve the matching efficiency, and shorten the time for determining the series video. Through the above steps, it is possible to identify which of the series videos corresponding to the currently playing video from all the videos displayed on the video collection display page are series videos corresponding to the currently playing video, which paves the way for the subsequent highlighting of the series videos corresponding to the currently playing video in the video collection display page.

[0104] How to determine a series of videos from a set of videos to be matched is described in detail below. Two specific embodiments are described below.

[0105] In a specific embodiment, the above step S405 may include: Figure 5 The following steps are shown:

[0106] In step S501, text description information of the currently playing video and text description information of each to-be-matched video in the to-be-matched video set are obtained.

[0107] The text description information of the currently playing video may include the title information and / or text information of the currently playing video; correspondingly, the text description information of each to-be-matched video may include the title information and / or text information of each to-be-matched video.

[0108] In step S503, a first matching degree value between the currently playing video and each of the videos to be matched is determined based on the text description information of the currently playing video and the text description information of each of the videos to be matched.

[0109] Among them, the text description information of the currently playing video is consistent with the text description information of each video to be matched. For example, when the text description information of the currently playing video is the title information of the currently playing video, the text description information of each video to be matched is also the title information of each video to be matched.

[0110] In a specific embodiment, step S503 may include the following steps:

[0111] In step S5031, the text description information of the currently playing video is segmented to obtain a first segmentation result.

[0112] Among them, the word segmentation processing mainly removes special symbols such as stop words used in the text description information, retains only the text part, and converts a series of text description information into multiple words.

[0113] In step S5032, the text description information of the video to be matched is segmented to obtain a second segmentation result.

[0114] In step S5033, the first word segmentation result is input into the word vector model to obtain the corresponding first word vector;

[0115] The word vector model may be a word2vec model. Word2vec, or word to vector, is a tool specifically used to convert words into vector form.

[0116] In step S5034, the second word segmentation result is input into the word vector model to obtain the corresponding second word vector.

[0117] In step S5035, a first matching degree value between the first word vector and the second word vector is determined according to a cosine similarity calculation formula;

[0118] For example, the first matching degree value is determined according to the following cosine similarity calculation formula (1):

[0119]

[0120] Among them, cosθ represents the first matching degree value; x represents the first word vector; y i Represents the second word vector corresponding to each video to be matched.

[0121] In step S5036, the first matching degree value between the first word vector and the second word vector is determined as the first matching degree value between the currently playing video and the video to be matched.

[0122] In step S505, a target video in the set of videos to be matched is determined as a series of videos; and a first matching degree value corresponding to the target video is greater than or equal to a first preset value.

[0123] After calculating the first matching degree value between each to-be-matched video and the currently played video, it is compared with the first preset value. If the first matching degree value is greater than or equal to the first preset value, it means that the contents expressed by the two videos are the same or similar, and the corresponding to-be-matched video is determined as the target video, and the target video is the series of videos corresponding to the currently played video. The first preset value can be determined according to actual applications, for example, the first preset value can be 0.92.

[0124] In the above embodiment, the text description information of the currently playing video and the text description information of each to-be-matched video are used to calculate the matching degree value between each to-be-matched video and the currently playing video, so as to achieve the determination of a series of videos from the to-be-matched video set. Since the text description information is a form of expression of the video content and can directly reflect the video content, therefore, determining the matching degree value between each to-be-matched video and the currently playing video based on the text description information can improve the recognition accuracy of the series of videos.

[0125] In another specific embodiment, the above step S405 may also include the following steps: Figure 6 The following steps are shown:

[0126] In step S601, a representation image of the currently playing video and a representation image of each to-be-matched video in a to-be-matched video set are obtained.

[0127] Among them, the representation image of the currently playing video refers to an image that can reflect the content of the currently playing video, and the representation image of the currently playing video may include a cover image or other representative images captured from the currently playing video; correspondingly, the representation image of each video to be matched refers to an image that can reflect the content of each video to be matched, and the representation image of each video to be matched may include a cover image or other representative images captured from each video to be matched.

[0128] In step S603, a second matching degree value between the representation image of the currently playing video and the representation images of each to-be-matched video is determined according to the trained image matching model.

[0129] Here, the image matching model may be pre-trained. The image matching model is used to determine whether two input images match. In some possible embodiments, the generation method of the image matching model may include: Figure 7 The following steps are shown:

[0130] In step S701, a plurality of training image pairs are obtained; each of the plurality of training image pairs includes two training images and corresponding matching labels.

[0131] Among them, if the two training images are matching images, the corresponding matching label is "1"; if the two training images are not matching images, the corresponding matching label is "0".

[0132] In step S703, a preset machine learning model is constructed; the preset machine learning model includes a first feature extraction module and a second feature extraction module.

[0133] In step S705, one of the two training images is input into a first feature extraction module to obtain a first feature vector.

[0134] In step S707, the other training image of the two training images is input into a second feature extraction module to obtain a second feature vector.

[0135] like Figure 8 As shown, Figure 8 It is a structural diagram of a preset machine learning model provided by an embodiment of the present disclosure. The preset machine learning model includes a convolutional neural network and a classifier. The convolutional neural network includes a first feature extraction module and a second feature extraction module, both of which are used to extract features from an input image to obtain a corresponding feature vector; the classifier is used to confirm whether the two input feature vectors match.

[0136] In step S709, the preset machine learning model is trained according to the first feature vector, the second feature vector and the matching label to obtain an image matching model.

[0137] During the training process, the model parameters are optimized according to the matching labels, and a trained image matching model is obtained when the preset training end condition is met. The preset training end condition may include ending the training when the number of iterations reaches a preset number; or ending the training when the model parameters reach the optimization target.

[0138] In step S605, the target video in the set of videos to be matched is determined as a series of videos; and the second matching degree value corresponding to the target video is greater than or equal to a second preset value.

[0139] After calculating the second matching degree value between each to-be-matched video and the currently played video, it is compared with the second preset value. If the second matching degree value is greater than or equal to the second preset value, it means that the contents expressed by the two videos are the same or similar, and the corresponding to-be-matched video is determined as the target video, and the target video is the series of videos corresponding to the currently played video. The second preset value can be determined according to actual applications, for example, the second preset value can be 0.92.

[0140] In practical applications, the trained image matching model can directly output the result of whether the representation image of each to-be-matched video is consistent with the representation image of the currently playing video, without the need to compare with the second preset value.

[0141] In the above embodiment, the representation image of the currently playing video and the representation images of each video to be matched are used to calculate the matching degree value between each video to be matched and the currently playing video, so as to determine the series of videos from the set of videos to be matched. Since the representation image is also a form of expression of the video content, it can also directly reflect the video content. Therefore, in addition to using text description information, the representation image can also be used to determine the corresponding series of videos, providing a variety of means for determining the series of videos. In actual applications, the priority of using the two means can be set. For example, the text description information is used first. When there is no text description information, the representation image is used to determine the corresponding series of videos, which can ensure that the series of videos can be accurately and efficiently identified.

[0142] The above embodiments are all explained by taking execution on the terminal device side as an example. In other embodiments of the present disclosure, the above process of identifying the series of videos corresponding to the currently playing video from all the videos displayed on the video collection display page can also be executed on the back-end server side. The advantage of executing on the back-end server side is that the processing performance requirements of the terminal device are lower, the processing resources of the terminal device can be released, and the terminal device can provide better page display effects.

[0143] In step S207, in the video collection display page, a series of videos are displayed according to a preset effect; the series of videos includes the currently playing video; the series of videos correspond to the same account ID.

[0144] In the disclosed embodiment, after identifying which videos in the video collection display page are series videos, the series videos are displayed according to a preset effect, so that the series videos are distinguished from other videos in the video collection display page, making it easier for viewing users to pay attention to the series videos.

[0145] In some possible embodiments, the above-mentioned displaying a series of videos corresponding to the currently played video according to a preset effect in the video collection display page may include:

[0146] In the display area corresponding to the series video on the video collection display page, special effect animations used to highlight the series video are displayed.

[0147] like Fig. 9 As shown, Fig. 9 Schematic diagram of a video collection display page provided by an embodiment of the present disclosure. Figure 3 In an embodiment, when entering the video collection display page 31, the terminal device recognizes that video 302 is a series of videos corresponding to video 301, and displays a special effect animation in the display area corresponding to video 302. The special effect animation can be obtained from the corresponding material library and is replaced by a shadow in the figure.

[0148] Or; in some possible embodiments, the above-mentioned displaying the series of videos corresponding to the currently playing video according to a preset effect in the video collection display page may also include: displaying text prompt information in the display area corresponding to the series of videos in the video collection display page; the text prompt information is used to prompt that the video in the current display area is a series of videos corresponding to the currently playing video.

[0149] Or; in some possible embodiments, the above-mentioned displaying the series of videos corresponding to the currently playing video according to a preset effect in the video collection display page may also include: displaying the dynamic stroking process along the edge of the display area corresponding to the series of videos in the video collection display page.

[0150] In this way, through any of the preset effects provided in the above embodiments, the corresponding series of videos is highlighted, so that after the user enters the video collection display page, the user can easily notice the series of videos, so that the user no longer needs to search from a large number of videos, which can save the user's time in searching for the series of videos and reduce the tediousness of playing the series of videos.

[0151] To sum up, the embodiment of the present disclosure provides a video processing method. When a viewing user intends to watch videos in the same series as the currently playing video and enters a video collection display page, the series videos corresponding to the currently playing video will be highlighted in the video collection display page to distinguish the series videos from other videos on the video collection display page, making it easier for the viewing user to pay attention to the series videos. In this way, it can save time in searching for series videos, reduce the tediousness of playing series videos, and improve the user viewing experience.

[0152] Fig.10 is a block diagram of a video processing device according to an exemplary embodiment. Fig.10 , the device includes a first display module 1001, a first determination module 1002, a second determination module 1003 and a second display module 1004:

[0153] The first display module 1001 is configured to execute a series video viewing instruction corresponding to the currently playing video and display a video collection display page;

[0154] The first determination module 1002 is configured to determine a video collection corresponding to the account identifier according to the obtained video identifier and account identifier of the currently playing video; the video collection includes multiple release times and multiple video identifiers corresponding to multiple videos;

[0155] The second determination module 1003 is configured to determine the series of videos corresponding to the currently played video from the multiple videos based on the release time and video identifier of each video in the multiple videos;

[0156] The second display module 1004 is configured to be executed in the video collection display page to display a series of videos according to a preset effect; the series of videos includes the currently playing video; the series of videos correspond to the same account ID.

[0157] In some possible embodiments, the second determining module includes:

[0158] A sorting submodule is configured to sort the multiple videos based on the release time of each of the multiple videos to obtain a plurality of sorted videos;

[0159] The first determination submodule is configured to execute a video identification based on the currently playing video, determine the current ranking of the currently playing video among the multiple videos, determine the videos with a preset number of places before and after the current ranking as the videos to be matched, and obtain a set of videos to be matched;

[0160] The second determination submodule is configured to determine a series of videos from the set of videos to be matched.

[0161] In some possible embodiments, the second determination submodule is further configured to execute the acquisition of text description information of the currently playing video and text description information of each video to be matched in the set of videos to be matched; determine a first matching degree value between the currently playing video and each video to be matched based on the text description information of the currently playing video and the text description information of each video to be matched; determine a target video in the set of videos to be matched as a series of videos; and the first matching degree value corresponding to the target video is greater than or equal to a first preset value.

[0162] In some possible embodiments, the second determination submodule is further configured to perform word segmentation processing on the text description information of the currently playing video to obtain a first word segmentation result; perform word segmentation processing on the text description information of the video to be matched to obtain a second word segmentation result; input the first word segmentation result into the word vector model to obtain the corresponding first word vector; input the second word segmentation result into the word vector model to obtain the corresponding second word vector; determine the first matching degree value between the first word vector and the second word vector according to the cosine similarity calculation formula; determine the first matching degree value between the first word vector and the second word vector as the first matching degree value between the currently playing video and the video to be matched.

[0163] In some possible embodiments, the second determination submodule is further configured to execute the acquisition of a representation image of the currently playing video and a representation image of each video to be matched in a set of videos to be matched; determine a second matching degree value between the representation image of the currently playing video and the representation image of each video to be matched based on a trained image matching model; determine a target video in the set of videos to be matched as a series of videos; and the second matching degree value corresponding to the target video is greater than or equal to a second preset value.

[0164] In some possible embodiments, the device also includes a generation method module of an image matching model, and the generation method module of the image matching model is configured to execute acquisition of multiple training image pairs; each training image pair in the multiple training image pairs includes two training images and corresponding matching labels; construct a preset machine learning model; the preset machine learning model includes a first feature extraction module and a second feature extraction module; input one of the two training images into the first feature extraction module to obtain a first feature vector; input the other training image of the two training images into the second feature extraction module to obtain a second feature vector; train the preset machine learning model according to the first feature vector, the second feature vector and the matching label to obtain an image matching model.

[0165] In some possible embodiments, the second display module is further configured to display a special effect animation for highlighting the series of videos in the display area corresponding to the series of videos in the video collection display page; or; display text prompt information in the display area corresponding to the series of videos in the video collection display page; the text prompt information is used to prompt that the video in the current display area is a series of videos corresponding to the currently playing video; or; in the video collection display page, display a dynamic stroking process along the edge of the display area corresponding to the series of videos.

[0166] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0167] Fig.11 The invention is a block diagram of an electronic device for video processing according to an exemplary embodiment.

[0168] The electronic device may be a server or a terminal device, and its internal structure diagram may be as follows: Fig.11 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a video processing method is implemented.

[0169] Those skilled in the art will understand that Fig.11The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0170] In an exemplary embodiment, an electronic device is also provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the video processing method in the embodiment of the present disclosure.

[0171] In an exemplary embodiment, a computer-readable storage medium is further provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the video processing method in the embodiment of the present disclosure.

[0172] In an exemplary embodiment, a computer program product is also provided, which includes a computer program. The computer program is stored in a readable storage medium. At least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the computer device executes the video processing method of the embodiment of the present disclosure.

[0173] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0174] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0175] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A video processing method, characterized in that: include: In response to a series video viewing instruction corresponding to the currently playing video, display a video collection display page; Determine, based on the acquired video ID and account ID of the currently playing video, a video collection corresponding to the account ID; the video collection includes multiple release times and multiple video IDs corresponding to multiple videos; Based on the release time and video identifier of each video in the multiple videos, determining a series of videos corresponding to the currently played video from the multiple videos; In the video collection display page, the series of videos are displayed according to a preset effect; the series of videos includes the currently playing video; The series of videos correspond to the same account ID; The step of determining, from the multiple videos, a series of videos corresponding to the currently played video based on the release time and the video identifier of each video in the multiple videos comprises: Sorting the multiple videos based on the release time of each video in the multiple videos to obtain a plurality of sorted videos; Based on the video identifier of the currently playing video, determine the current ranking of the currently playing video among the multiple videos, and determine the videos with preset positions before and after the current ranking as the videos to be matched, so as to obtain a set of videos to be matched; Determine the series of videos from the set of videos to be matched; The step of determining the series of videos from the set of videos to be matched comprises: Obtaining text description information of the currently playing video and text description information of each to-be-matched video in the to-be-matched video set; Determining a first matching degree value between the currently playing video and each of the videos to be matched based on the text description information of the currently playing video and the text description information of each of the videos to be matched; A target video in the to-be-matched video set is determined as the series of videos; and a first matching degree value corresponding to the target video is greater than or equal to a first preset value.

2. The video processing method according to claim 1, characterized in that: The determining, based on the text description information of the currently playing video and the text description information of the videos to be matched, a first matching degree value between the currently playing video and the videos to be matched, includes: Performing word segmentation processing on the text description information of the currently playing video to obtain a first word segmentation result; Performing word segmentation processing on the text description information of the to-be-matched video to obtain a second word segmentation result; Inputting the first word segmentation result into a word vector model to obtain a corresponding first word vector; Inputting the second word segmentation result into the word vector model to obtain a corresponding second word vector; Determine a first matching degree value between the first word vector and the second word vector according to a cosine similarity calculation formula; A first matching degree value between the first word vector and the second word vector is determined as a first matching degree value between the currently playing video and the video to be matched.

3. The video processing method according to claim 1, characterized in that: The step of determining the series of videos from the set of videos to be matched comprises: Acquire a representation image of the currently playing video and a representation image of each to-be-matched video in the to-be-matched video set; Determining a second matching degree value between the representation image of the currently playing video and the representation images of each to-be-matched video according to the trained image matching model; A target video in the to-be-matched video set is determined as the series of videos; and a second matching degree value corresponding to the target video is greater than or equal to a second preset value.

4. The video processing method according to claim 3, characterized in that: The method for generating the image matching model includes: Acquire a plurality of training image pairs; each of the plurality of training image pairs comprises two training images and corresponding matching labels; Constructing a preset machine learning model; the preset machine learning model includes a first feature extraction module and a second feature extraction module; Inputting one of the two training images into the first feature extraction module to obtain a first feature vector; Inputting the other training image of the two training images into the second feature extraction module to obtain a second feature vector; The preset machine learning model is trained according to the first feature vector, the second feature vector and the matching label to obtain the image matching model.

5. The video processing method according to claim 1, characterized in that: In the video collection display page, the series of videos are displayed according to the preset effects, including: In the display area corresponding to the series of videos in the video collection display page, a special effect animation for highlighting the series of videos is displayed; or; Displaying text prompt information in the display area corresponding to the series of videos in the video collection display page; the text prompt information is used to prompt that the video in the current display area is a series of videos corresponding to the currently playing video; or; In the video collection display page, a dynamic stroking process is displayed along the edge of the display area corresponding to the series of videos.

6. A video processing device, characterized in that: include: A first display module is configured to execute a series video viewing instruction corresponding to a currently playing video and display a video collection display page; A first determination module is configured to determine a video collection corresponding to the account identifier according to the obtained video identifier and account identifier of the currently playing video; The video collection includes multiple release times and multiple video identifiers corresponding to multiple videos; A second determination module is configured to determine, from the multiple videos, a series of videos corresponding to the currently played video based on the release time and video identifier of each video in the multiple videos; A second display module is configured to be executed in the video collection display page and display the series of videos according to a preset effect; The series of videos includes the currently playing video; The series of videos correspond to the same account ID; The second determining module includes: A sorting submodule is configured to sort the multiple videos based on the release time of each video in the multiple videos to obtain a plurality of sorted videos; A first determination submodule is configured to execute, based on the video identifier of the currently playing video, determine the current ranking of the currently playing video among the multiple videos, determine the videos with a preset number of places before and after the current ranking as the videos to be matched, and obtain a set of videos to be matched; A second determination submodule is configured to determine the series of videos from the set of videos to be matched; The second determination submodule is further configured to execute the acquisition of text description information of the currently playing video and text description information of each to-be-matched video in the to-be-matched video set; determine a first matching degree value between the currently playing video and each to-be-matched video based on the text description information of the currently playing video and the text description information of each to-be-matched video; determine a target video in the to-be-matched video set as the series of videos; and the first matching degree value corresponding to the target video is greater than or equal to a first preset value.

7. The video processing device according to claim 6, characterized in that: The second determination submodule is further configured to perform word segmentation processing on the text description information of the currently playing video to obtain a first word segmentation result; perform word segmentation processing on the text description information of the video to be matched to obtain a second word segmentation result; input the first word segmentation result into a word vector model to obtain a corresponding first word vector; The second word segmentation result is input into the word vector model to obtain a corresponding second word vector; according to the cosine similarity calculation formula, a first matching degree value between the first word vector and the second word vector is determined; the first matching degree value between the first word vector and the second word vector is determined as the first matching degree value between the currently playing video and the video to be matched.

8. The video processing device according to claim 6, characterized in that: The second determination submodule is further configured to execute the acquisition of the representation image of the currently playing video and the representation image of each video to be matched in the set of videos to be matched; determine the second matching degree value between the representation image of the currently playing video and the representation image of each video to be matched according to the trained image matching model; determine the target video in the set of videos to be matched as the series of videos; and the second matching degree value corresponding to the target video is greater than or equal to a second preset value.

9. The video processing device according to claim 8, characterized in that: The device also includes a generation module of an image matching model. The generation method module of the image matching model is configured to execute acquisition of multiple training image pairs; each training image pair in the multiple training image pairs includes two training images and corresponding matching labels; construct a preset machine learning model; the preset machine learning model includes a first feature extraction module and a second feature extraction module; input one of the two training images into the first feature extraction module to obtain a first feature vector; input the other of the two training images into the second feature extraction module to obtain a second feature vector; train the preset machine learning model according to the first feature vector, the second feature vector and the matching labels to obtain the image matching model.

10. The video processing device according to claim 6, characterized in that: The second display module is further configured to display a special effect animation for highlighting the series of videos in the display area corresponding to the series of videos in the video collection display page; or display text prompt information in the display area corresponding to the series of videos in the video collection display page; The text prompt information is used to prompt that the video in the current display area is a series of videos corresponding to the currently playing video; or; in the video collection display page, a dynamic stroking process along the edge of the display area corresponding to the series of videos is displayed.

11. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the video processing method according to any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the video processing method according to any one of claims 1 to 5.

13. A computer program product, characterized in that The computer program product comprises a computer program, which is stored in a readable storage medium. At least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the computer device executes the video processing method according to any one of claims 1 to 5.

Images