Video processing method and device, equipment and medium
By determining and displaying keyword and object information in the video, the problem of excessively long video content and insufficient explanation is solved, and the user experience and video playback effect are improved.
Patent Information
- Application Number
- CN202411009697.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-22
AI Technical Summary
The content of existing videos is long when introducing items and the explanation is insufficient, making it difficult for users to quickly understand the key points, which affects the user experience.
By obtaining the target video and its object information, determine the keyword information, including the target keyword, its appearance time and special effect style, and send it to the client, and display the keywords and objects according to the appearance time and special effect style of the keyword during the video playback process. information.
Help users quickly understand the focus of videos, improve the completion rate and conversion rate of video playback, and improve user experience.
Smart Images

Figure CN119011930A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to a video processing method, device, equipment and medium. Background Art
[0002] With the development of applications, people can shop online on various applications. Applications can introduce an item by playing a video related to the item. In related technologies, the content and duration of these videos are long, and the explanations are not sufficient, making it difficult for users to quickly understand the key points. The video playback effect is poor, affecting the user experience. Summary of the invention
[0003] In order to solve the above technical problems, the present disclosure provides a video processing method, device, equipment and medium.
[0004] The present disclosure provides a video processing method, the method comprising:
[0005] Obtaining a target video and object information of an object corresponding to the target video;
[0006] Determining keyword information based on the target video and the object information, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style;
[0007] The target video, the object information, and the keyword information are sent to the client, so that the client displays the target keyword according to the appearance time and special effect style of the target keyword and displays the object information during the playback of the target video.
[0008] The present disclosure also provides a video processing method, the method comprising:
[0009] Acquire a target video, object information of an object corresponding to the target video, and keyword information of the target video, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style;
[0010] During the playing of the target video, the target keyword is displayed according to the appearance time and special effect style of the target keyword, and the object information is displayed.
[0011] The present disclosure also provides a video processing device, the device comprising:
[0012] A first acquisition module, used to acquire a target video and object information of an object corresponding to the target video;
[0013] A determination module, configured to determine keyword information based on the target video and the object information, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style;
[0014] A sending module is used to send the target video, the object information, and the keyword information to the client, so that the client can display the target keyword and the object information according to the appearance time and special effect style of the target keyword during the playback of the target video.
[0015] The present disclosure also provides a video processing device, the device comprising:
[0016] A second acquisition module is used to acquire a target video, object information of an object corresponding to the target video, and keyword information of the target video, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style;
[0017] A display module is used to display the target keyword according to the appearance time and special effect style of the target keyword during the playback of the target video, and to display the object information.
[0018] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the video processing method provided by the embodiment of the present disclosure.
[0019] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the video processing method provided by the embodiment of the present disclosure.
[0020] Compared with the prior art, the technical solution provided by the disclosed embodiment has the following advantages: the video processing solution provided by the disclosed embodiment obtains the target video and the object information of the object corresponding to the target video; determines the keyword information based on the target video and the object information, wherein the keyword information includes the target keyword, the appearance time of the target keyword and the special effect style; sends the target video, the object information and the keyword information to the client, so that the client displays the target keyword and the object information according to the appearance time and the special effect style of the target keyword during the process of playing the target video. By adopting the above technical solution, the keywords are extracted based on the video and the object information of the video, and the appearance time and the special effect style of the keywords are determined. Subsequently, in the process of playing the video and displaying the object information on the client, the keywords are displayed according to the appearance time and the special effect style, realizing the highlighting of the keywords of the video content following the video playback, and the continuous display of key information, which can help users quickly understand the key points of the video, improve the completion rate and conversion rate of the video playback, and thus improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.
[0022] Figure 1 A schematic diagram of a video processing method provided by an embodiment of the present disclosure;
[0023] Figure 2 A flowchart of another video processing method provided by an embodiment of the present disclosure;
[0024] Figure 3 A schematic diagram of a special effect style provided by an embodiment of the present disclosure;
[0025] Figure 4 A schematic diagram of another special effect style provided by an embodiment of the present disclosure;
[0026] Figure 5 A flowchart of another video processing method provided by an embodiment of the present disclosure;
[0027] Figure 6 A flowchart of another video processing method provided by an embodiment of the present disclosure;
[0028] Figure 7 A schematic diagram of obtaining a composite image provided by an embodiment of the present disclosure;
[0029] Figure 8A data interaction diagram of a video processing method provided by an embodiment of the present disclosure;
[0030] Fig. 9 A schematic diagram of the structure of a video processing device provided by an embodiment of the present disclosure;
[0031] Fig.10 A schematic diagram of the structure of another video processing device provided by an embodiment of the present disclosure;
[0032] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0033] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0034] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0035] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0036] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0037] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0038] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0039] With the development of applications, people can shop online on various applications. Applications can introduce an item by playing a video related to the item. In related technologies, in order to explain more information about the item in a video, the content and duration of the video will be long, and users are likely to stop and interrupt the video before it is finished. In addition, the explanation of the video is often insufficient. Even if users watch the video for a long time, it is difficult to understand the introduction of the item and the core competitive points. The video playback effect is poor, and it is difficult to arouse users' interest in the item, which affects the user experience.
[0040] In order to solve the above problems, the embodiments of the present disclosure provide a video processing method, which is introduced below in conjunction with specific embodiments.
[0041] Figure 1 The present invention provides a flow chart of a video processing method provided by an embodiment of the present invention. The method can be executed by a server or a video processing device provided on the server. The device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:
[0042] Step 101: Obtain a target video and object information of an object corresponding to the target video.
[0043] The target video may be a video introducing an object, which may be used to attract users, stimulate users' interest in the object, and prompt users to pay resources in exchange for the object. The resources may include physical resources or virtual resources for exchange. The object may be an object highlighted in the target video, which may be a product that can be exchanged. This embodiment does not limit the type of the object, for example, the object may include items such as headphones and sleeves.
[0044] Object information may be a general term for all relevant information about an object, through which the object may be promoted, disseminated or introduced. This embodiment does not limit the information type of the object information. For example, the object information may include one or more of a video, an image, and a text. Optionally, the object information may include material information and / or associated videos of the target video. The material information may include the target video title, landing page text, and landing page pictures. The landing page may be a page that carries and plays the target video in the client. The landing page text may be text recorded in the landing page for introducing the object. The landing page picture may be a picture related to the object in the landing page. The target video title, landing page text, and landing page image may be displayed on the page together with the target video. The associated video may be a video introducing the object other than the target video.
[0045] In the embodiment of the present disclosure, the client may send a request to the video processing device to obtain video stream data. After receiving the request, the video processing device obtains the target video and object information of the objects involved in the target video.
[0046] Step 102: Determine keyword information based on the target video and object information, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style.
[0047] Among them, keyword information can be information that additionally introduces the object in the form of special effects. The target keyword is used to record the advantages, characteristics or functions of the object in one or more dimensions, which can attract users and prompt users to exchange for the object. The appearance time can be the specific time point when the target keyword follows the target video. The special effect style is used to display the text special effect style of the target keyword, and the special effect style can display the target keyword in the form of virtual stickers. Through this special effect style, the target keyword can be highlighted to attract the user's attention.
[0048] In the disclosed embodiment, after obtaining the target video and the object information of the object corresponding to the target video, the video processing device can perform text recognition on the target video and the object information to determine the target keyword, the appearance time of the target keyword, and the special effect style for displaying the target keyword.
[0049] Figure 2 A flowchart of another video processing method provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, in some embodiments of the present disclosure, determining keyword information based on the target video and object information includes:
[0050] Step 201: Use the target classification model to identify the target video and object information and determine the target keywords.
[0051] The target classification model may be a trained model for text classification. This embodiment does not limit the type of the target classification model. For example, the target classification model may be a named entity recognition classification model or a generative model. The target classification model may be obtained by training based on labeled training data.
[0052] In this embodiment, the video processing device may input text determined based on the target video and object information into a target classification model, and the target classification model extracts and classifies the text to obtain target keywords.
[0053] In some embodiments of the present disclosure, the target classification model is used to identify the target video and object information to determine the target keyword, including:
[0054] Step a1: perform text recognition on the target video and the audio and image in the object information to obtain a first text.
[0055] The first text may be text obtained by performing automatic speech recognition on audio and / or performing optical character recognition on an image.
[0056] In this embodiment, the video processing device can extract the audio in the target video, perform automatic speech recognition on the audio, and obtain the first text corresponding to the audio in the target video. Perform optical character recognition on the image in the target video to obtain the first text corresponding to the image in the target video. In addition, the time when the first text appears in the audio or image in the target video is recorded.
[0057] The video processing device may also extract the audio of the associated video in the object information, perform automatic speech recognition on the audio, and obtain the first text corresponding to the video in the object information. Perform optical character recognition on the image in the associated video to obtain the first text corresponding to the image in the associated video. For images such as landing page images in the object information, perform optical character recognition on the image to obtain the first text corresponding to the image in the object information.
[0058] Step a2: input the first text and the second text in the object information into a target classification model, and extract a plurality of initial keywords divided into a plurality of categories.
[0059] Among them, the second text can be information whose information type is text contained in the object information. The second text may include the target video title and / or landing page text. The type may be the dimension in which the initial keyword introduces the object, and this embodiment does not limit the type. For example, the type may include: one or more of function, usage scenario, and personnel recommendation. The initial keyword may be the original keyword extracted by the target classification model.
[0060] In this embodiment, the video processing device can extract object information in text format to obtain a second text, and input the recognized first text and second text into a target classification model, extract initial keywords from the first text and second text through the target classification model, and determine multiple types corresponding to the initial keywords through the target classification model.
[0061] Step a3: extracting initial keywords of a preset type from a plurality of initial keywords of a plurality of types and determining them as target keywords.
[0062] The preset type may be a pre-set type that needs to be retained, and this embodiment does not limit the preset type. It can be understood that the total number of the preset types is less than the total number of types.
[0063] In this embodiment, the video processing device can determine the initial keywords of the preset type among multiple initial keywords of multiple types as target keywords. For example, if the type includes function type, usage scenario type, and personnel recommendation type, and the target type includes function and usage scenario, the initial keywords corresponding to the function type and the initial keywords corresponding to the usage scenario are determined as target keywords. Taking the object as a soymilk maker as an example, if the initial keywords under the function type include appointment, steam sterilization, automatic cleaning, and mute; the initial keywords under the usage scenario type include home use, and the initial keywords under the personnel recommendation type include A personnel recommendation. If the target type includes the function type and the usage scenario type, the target keywords include appointment, steam sterilization, automatic cleaning, mute, and home use. Optionally, the video processing device can also determine corresponding similar words for each target keyword.
[0064] In the above scheme, automatic text recognition is performed on the target video and object information, and keyword extraction and classification are performed on the text through the target classification model. The extracted keywords are screened according to preset types to obtain the final target keywords, thereby realizing automatic extraction of the target video and object information to obtain the target keywords, which represent the expression focus of the target video and object information.
[0065] Step 202: Determine the corresponding appearance time according to the target keyword.
[0066] In this embodiment, the video processing device can determine the appearance time of the target keyword according to the target keyword and the source of the target keyword, wherein the source is basic data for determining the target keyword, and the source may include target video and / or object information.
[0067] In some embodiments of the present disclosure, determining the corresponding appearance time according to the target keyword includes:
[0068] Step b1: If the target keyword comes from the target video, the time when the target keyword appears in the target video is determined as the corresponding appearance time.
[0069] In this embodiment, if the target keyword is determined based on the target video, the time when the target keyword appears in the audio or image in the target video is determined as the appearance time of the target keyword.
[0070] Step b2: If the target keyword comes from the object information, the appearance time of the target keyword is determined as the preset time.
[0071] The preset time may be a preset time point for displaying the target keywords from the object information. The present embodiment does not limit the preset time. For example, the preset time may include one or more of the 3rd second, the 5th second, and the 8th second. Optionally, the preset time may be less than the user's historical viewing time. The historical viewing time may be historical data of the length of time the user has viewed the video. Furthermore, the target keywords are subsequently displayed to the user before the user ends the playback of the target video, thereby realizing the pre-display of the target keywords, so that the focus of the target video can be conveyed to the customer more quickly.
[0072] In this embodiment, if the target keyword is determined based on the object information, the video processing device can assign different preset times to the corresponding target keywords, and use the preset time assigned to the target keyword as the appearance time of the target keyword. For example, if two target keywords come from the target video title and the landing page text respectively, and the preset times include the 3rd second and the 5th second, the video processing device can determine the appearance time of the target keyword from the target video title as the 3rd second, and the appearance time of the target keyword from the landing page text as the 5th second.
[0073] In the above scheme, the appearance time of the keyword from the target video is determined as the time when the target keyword is located in the target video, so that the appearance of the target keyword is consistent with the content displayed by the target video, which improves the user's viewing experience. The appearance time of the target keyword from the object information is determined as the preset time. By adjusting the preset time, the appearance time of the first target keyword and the interval time between target keywords can be adjusted, which realizes personalized adjustment of the target keyword and improves the user's viewing experience.
[0074] Step 203: Determine the special effect style of the target keyword according to the target video, object information, target keyword and corresponding appearance time.
[0075] In this embodiment, there are multiple methods for determining the special effect style of the target keyword based on the target video, object information, target keyword and the corresponding appearance time, which is not limited in this embodiment.
[0076] In some embodiments of the present disclosure, the special effect style of the target keyword is determined according to the target video, object information, target keyword and corresponding appearance time, including:
[0077] Step c1, determining the style color of the target keyword based on at least one of the color block analysis result of the target video, the video length of the target video, the number of target keywords, and the first appearance time of the target keyword.
[0078] Among them, the color block analysis result can divide the similar color area in the target video into a corresponding color block, and analyze the characteristics of these color blocks to obtain the result, and the color block analysis result may include the color adapted to the target video. The similar color area can be an area where the pixel value difference is within a preset difference threshold. The video length can be the total length of the target video. The first appearance time can be the most forward appearance time in the multiple appearance times corresponding to the target keyword. The style color can be a color related to the display of the target keyword, and the style color can include the color of the target keyword itself and / or the background color of the text box where the target keyword is located, etc.
[0079] In this embodiment, the video processing device can perform color block analysis on the target video as a whole to obtain a color block analysis result. And, the appearance time with the earliest timing among the multiple appearance times corresponding to the multiple target keywords is determined as the first appearance time. Furthermore, the video processing device can configure the style color of the target keyword according to a preset style color strategy based on the color block analysis result, the video length of the target video, the number of target keywords, and the first appearance time. Among them, the style color strategy can be understood as a pre-set rule for determining the style color according to one or more of the above parameters. Thereby, the style color of the target keyword is determined based on multiple dimensions, the degree of adaptation of the style color to the target video is improved, and the user's viewing experience is improved.
[0080] For example, the style color may include a first style and a second style, the first style may include a more eye-catching strong style such as orange, and the second style may include a more universal weak style such as white. The style color strategy may include at least one of the following:
[0081] The style of the first style and the second style that is closest to the color of the color block analysis result is determined as the final color style.
[0082] If the video duration of the target video is less than the preset duration threshold, and the time interval between the appearance times of adjacent target keywords is less than the preset interval threshold, and the first appearance time of the target keyword is less than the first preset time threshold. This indicates that the duration of the target video is short, the target keywords are more concentrated, and the target keywords appear earlier, and the color style is determined to be the second style. Among them, the preset duration threshold can be a preset threshold for determining whether the duration of the target video is short. The preset interval threshold can be a preset threshold for determining whether the target keywords are concentrated. The first preset time threshold can be a preset threshold for determining whether the target keyword appears early.
[0083] If the first appearance time of the target keyword is less than the second preset time threshold, the color style is determined as the second style. The second preset time threshold may be a preset threshold for determining whether the target keyword appears early. The relationship between the first preset time threshold and the second preset time threshold is not limited in this embodiment. The second preset time threshold may be 3 seconds.
[0084] Step c2: based on the text recognition result of the target video, determine the special effect elements of the target keyword.
[0085] Among them, the text recognition result can characterize whether there is text in the image of the target video. Special effect elements can be used to control the dynamic display effect of the target keyword. This embodiment does not limit the special effect element, and the special effect element may include the movement method of the target keyword and / or the arrangement method of the target keyword. In an optional implementation, the special effect element can control the target keyword to fade in from the appearance position on the page and move to the end position to fade out, wherein the stop position can be the end point of the target keyword movement. In another optional implementation, the special effect element can control multiple target keywords to be displayed in a vertical arrangement, and each target element fades in and remains displayed at the appearance position.
[0086] In this embodiment, the video processing device can perform text recognition on the image in the target video to obtain a text recognition result, and determine the corresponding special effect element according to the text recognition result.
[0087] In some embodiments of the present disclosure, based on the text recognition result of the target video, the special effect element of the target keyword is determined, including: if the text recognition result of the target video is that text exists, the special effect element of the target keyword is set to a target special effect element with a motion intensity greater than a preset intensity.
[0088] Among them, the dynamic effect intensity can be the degree of visual effect significance that characterizes the special effect element, and the dimensions involved in the dynamic effect intensity can include one or more of the movement, rotation, scaling, deformation, color gradient, and light and shadow changes of the special effect element. The preset intensity can be a preset intensity threshold, and the preset intensity can be adjusted according to user needs, etc., and this embodiment does not limit it. The target special effect element can be a pre-set special effect element with obvious visual effects. For example, the target special effect element can include moving from the appearance position to the stop position in the interface.
[0089] In this embodiment, if the text recognition result of the target video is that there is text in the target video, it means that when the target keyword is displayed, the text displayed in the target video itself may attract the user's attention, reducing the user's attention to the target keyword. Therefore, the video processing device sets the special effect element of the target keyword to a target special effect element with a dynamic effect strength greater than a preset strength. Thereby, the user's attention to the target keyword is increased.
[0090] Step c3: Determine the appearance position of the target keyword based on the position of the object in the target video.
[0091] The position of the object may be the position of the object in the target video.
[0092] In this embodiment, the video processing device can identify the object in the target video, and determine the position of the object in the target video as the position of the object, determine other positions in the target video except the position of the object as candidate positions, and determine a position in the candidate positions that can fully display the target keyword as the appearance position of the target keyword. Thus, the target keyword avoids blocking the object in the target video, and improves the user's viewing experience.
[0093] Figure 3 A schematic diagram of a special effect style provided by an embodiment of the present disclosure, Figure 3 In the example, page 300 is a landing page, text box 301 is a text box displayed when the target special effect element starts, and the position of text box 301 is the appearance position of the target keyword, text box 302 is a text box displayed when the target special effect element ends, and the position of text box 302 is the stop position of the target keyword, and object 303 is an object in the target video, and the position of the object is the position of the object. Figure 3 As shown, taking the target keyword D as an example, the appearance position does not block the position of the object. In addition, the target video played in the landing page contains words such as "headphones", and the text recognition result of the target video is that there is text. The special effect element of the target keyword D is a special effect element with a large dynamic effect intensity, in which the text box of the target keyword slides from the appearance position to the stop position, and each target keyword gradually fades out after reaching the stop position.
[0094] Figure 4 A schematic diagram of another special effect style provided in an embodiment of the present disclosure, Figure 4 In the example, page 400 is a landing page, text box 401 is a text box for displaying target keywords, and position 402 is the position of the object where the object is located. Figure 4As shown, taking the target keyword D as an example, the position of the appearance does not block the position of the object. In addition, there is no text in the target video played in the landing page. The special effect element of the target keyword is a text box of the target keyword arranged in a vertical row, and each text box is expanded and displayed in place in turn. The dynamic effect intensity of this special effect element is relatively small.
[0095] In some other embodiments of the present disclosure, the special effect style of the target keyword is determined according to the target video, object information, target keyword and corresponding appearance time, including:
[0096] The target video, object information, and target keyword are input into the special effect prediction model, and the special effect prediction model outputs the special effect style of the target keyword. The special effect prediction model can be a model with a special effect style selection function. This embodiment does not limit the type of the special effect prediction model. For example, the special effect prediction model can be a binary classification model. The training data of the special effect prediction model may include the target video, object information, target keyword, appearance time, special effect style, and special effect label as samples. The special effect label is used to characterize whether the special effect style is selected in the case of the corresponding target video, object information, target keyword, appearance time, and special effect style.
[0097] Step 103: Send the target video, object information, and keyword information to the client, so that the client displays the target keyword and the object information according to the appearance time and special effect style of the target keyword during the playback of the target video.
[0098] In the disclosed embodiment, the video processing device sends the target video, the object information of the object corresponding to the target video, and the keyword information determined based on the target video and the object information to the client. After receiving the target video, the object information, and the keyword information, the client plays the target video on the page and displays the target video title, landing page text, landing page image and other object information. For each target keyword, when the playback time of the target video reaches the appearance time of the target keyword, the target keyword is displayed in the special effect style of the target keyword.
[0099] The video processing solution provided by the disclosed embodiment obtains the target video and the object information of the object corresponding to the target video; determines the keyword information based on the target video and the object information, wherein the keyword information includes the target keyword, the appearance time of the target keyword and the special effect style; sends the target video, the object information and the keyword information to the client, so that the client displays the target keyword and the object information according to the appearance time and the special effect style of the target keyword during the playback of the target video. Using the above technical solution, keywords are extracted based on the video and the object information of the video, and the appearance time and the special effect style of the keyword are determined. Subsequently, in the process of playing the video and displaying the object information on the client, the keywords are displayed according to the appearance time and the special effect style, realizing the highlighting of the keywords of the video content as the video is played. The key information is continuously displayed, which can help users quickly understand the key points of the video, improve the completion rate and conversion rate of the video playback, and thus improve the user experience.
[0100] Figure 5 This is a flow chart of another video processing method provided by an embodiment of the present disclosure. The method can be executed by a client or a video processing device set in the client, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Optionally, when the client has sufficient computing power, Figure 1 Provides video processing methods and Figure 5 The provided video processing methods can be executed by the same client, such as Figure 5 As shown, the method includes:
[0101] Step 501: Obtain a target video, object information of an object corresponding to the target video, and keyword information of the target video, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style.
[0102] In the disclosed embodiment, the server sends the target video, object information of the object in the target video, keyword information including target keyword, appearance time, and special effect style to the video processing device. The video processing device obtains the target video, object information, and keyword information.
[0103] Step 502: during the playback of the target video, the target keyword is displayed according to the appearance time and special effect style of the target keyword, and the object information is displayed.
[0104] In the disclosed embodiment, the video processing device plays a target video on a page and displays object information such as the target video title, landing page text, and landing page image. During the playback of the target video, for each target keyword, when the playback time of the target video reaches the appearance time of the target keyword, the target keyword is displayed in the special effects style of the target keyword.
[0105] The video processing solution provided by the disclosed embodiment obtains the target video, the object information of the object corresponding to the target video, and the keyword information of the target video, wherein the keyword information includes the target keyword, the appearance time and special effect style of the target keyword; during the process of playing the target video, the target keyword is displayed according to the appearance time and special effect style of the target keyword, and the object information is displayed. Using the above technical solution, in the process of playing the video and displaying the object information on the client, the keywords are displayed according to the appearance time and special effect style, which realizes the highlighting of the keywords of the video content as the video is played. The key information is continuously displayed, which can help users quickly understand the key points of the video, improve the completion rate and conversion rate of the video playback, and thus improve the user experience.
[0106] Figure 6 A flowchart of another video processing method provided by an embodiment of the present disclosure is shown as follows: Figure 6 As shown, before displaying the target keyword according to the appearance time and special effect style of the target keyword during the playing of the target video, the method further includes:
[0107] Step 601: Draw a keyword view for the target keyword in a special effect style.
[0108] The keyword view may be a view that displays target keywords on a page.
[0109] In this embodiment, the video processing device may draw a view of the target keyword according to the special effect style corresponding to the target keyword to obtain a keyword view.
[0110] Step 602: synthesize the keyword view with the main view of the video frame of the target video at the appearance time of the target keyword to obtain a synthesized view.
[0111] The video frame may be an image frame corresponding to the target keyword in the target video, and the main view may be a view showing the video frame in the page.
[0112] In this embodiment, for each target keyword, the video processing device can determine the video frame in the target view whose playback time is the same as the appearance time of the target keyword, and draw the main view of the video frame, and further synthesize the keyword view with the main view to obtain a synthesized view. The synthesized view is cached for subsequent playback on the client.
[0113] Figure 7 A schematic diagram of obtaining a composite image provided by an embodiment of the present disclosure is shown in FIG. Figure 7As shown, the appearance time includes tx, ty, and tz. At each appearance time, the main view of the corresponding video frame and the keyword view displayed at the appearance time are synthesized to obtain a synthesized view corresponding to the appearance time.
[0114] Accordingly, during the playback of the target video, the target keyword is displayed according to the appearance time and special effect style of the target keyword, including: playing the target video, and rendering and displaying the synthetic view according to the appearance time of the target keyword during the playback process, so that the target keyword is displayed in a special effect style.
[0115] In this embodiment, the video processing device determines the corresponding synthetic view according to the appearance time of the target keyword during the process of playing the target video, and renders and displays the synthetic view on the page. When the user views the page, the target keyword is superimposed on the target video in a special effect style for display.
[0116] In the above scheme, a keyword view corresponding to the target keyword and a main view of the video frame corresponding to the target keyword are drawn, and the keyword view and the main view are synthesized to achieve superimposition of the target keyword in the corresponding special effects style on the basis of the video frame, creating a basis for displaying the target keyword while playing the target video.
[0117] Next, the video processing method in the embodiment of the present disclosure is further described by using a specific example. Figure 8 A data interaction diagram of a video processing method provided by an embodiment of the present disclosure is shown in FIG. Figure 8 As shown, the video processing method includes:
[0118] The client sends a request to obtain the material to the stream interface in the server. After receiving the request, the stream interface (stream) in the server sends a request for mixing to the recommendation system. After receiving the request, the recommendation system sends a request to obtain the target video to the video engine. After receiving the request to obtain the target video, the video engine returns the click identifier to the recommendation system. After mixing, the recommendation system sends the mixing result to the stream interface. The packaging service sends a request to obtain the target keyword and the time of appearance to the derivative management platform. The derivative management platform sends a request to obtain the target keyword to the derivative engine. The derivative engine forwards the request to obtain the keyword to the content generation program. The content production program determines the target keyword and stores the target keyword in the data storage. The target keyword is returned to the packaging service through the content production program, the derivative engine, and the derivative management platform in sequence through the data storage.
[0119] The streaming interface generates a packaging request including a click identifier, and sends the packaging request to the packaging service to request the packaging service to package the material. After receiving the packaging request, the packaging service packages the target video, object information, and keyword information, generates a packaged material, and returns the packaged material to the streaming interface. The streaming interface sends the packaged material to the client as a response. After receiving the packaged material, the client generates a synthetic view and caches the synthetic view. The synthetic view is rendered during playback to display the synthetic view to the user.
[0120] In this embodiment, the stream interface can be an interface service, and the stream interface can be an information stream interface or a live stream interface, etc. The recommendation system can be a video recommendation system, and the recommendation system can be used to request the video engine to obtain the target video and perform the mixing of the target video. The video engine can be understood as a policy module in the video recommendation process, through which the target video that meets the user's needs can be returned. The packaging module can be used to package the target video, object information, and keyword information and send them to the client. The derived management platform can be used to manage the video resources derived from the server, and the derived management platform can have functions such as storage, retrieval, and query. The derived engine can be understood as the core processor of the derived function, through which the original materials such as the target video and comparison information can be transmitted and the return results can be delivered. The content generation program can be used to call the target classification model to determine the target keyword.
[0121] In this embodiment, the client sends a request to the server to request the video stream data to be played. The server determines the target video and calls the derived management platform to obtain the material information such as the object information corresponding to the target video. The content production program in the server obtains the title of the target video, the landing page text, the text of the landing page image recognition, the text of the audio recognition of the associated video, the text of the image recognition of the associated video, the text of the audio recognition of the target video, the text of the image recognition of the target video, etc. The text is input into the target classification model to obtain the target keyword, and the appearance time of the target keyword is determined.
[0122] The server performs color block analysis, text analysis, target keyword interval analysis, and object position analysis on the target video, and determines the special effect style of the target keyword based on the analysis results. The server sends the target video, object information, and keyword information to the client. After receiving the target video, object information, and keyword information, the client encapsulates the target keyword in the keyword information according to its corresponding special effect style to obtain a keyword view, synthesizes the keyword view with the corresponding main view to obtain a synthetic view, caches the synthetic view, and renders the synthetic view during playback to achieve dynamic display of the target keyword.
[0123] The process of determining the style color may include one or more of the following methods: Optionally, determining a style color that matches the color block analysis result of the target video. Optionally, if the video duration of the target video is less than a preset duration threshold, the time interval between the appearance times of adjacent target keywords is less than a preset interval threshold, and the first appearance time of the target keyword is less than a first preset time threshold, the style color is determined as a weak style, and the arrangement style of the target keyword is determined as a vertical arrangement. Optionally, if the first appearance time of the target keyword is less than a second preset time threshold, the style color is determined as a weak style.
[0124] The process of determining the special effect element may include: if the text recognition result of the target video is that text exists, determining a special effect element with a strong motion effect as a target special effect element.
[0125] The above-mentioned video processing method provided by the embodiment of the present disclosure derives a target keyword with a special effect style on the basis of the original target video, and synthesizes the main view of the video frame and the keyword view of the target keyword during the playback of the target video, thereby realizing the highlighting of the target keyword, highlighting the key points of the current explanation of the target video, helping the user to highlight the key points, and can also dynamically adjust the appearance time of the target keyword, effectively improving the probability of complete playback of the target video.
[0126] Furthermore, by adjusting the preset time of the event to the front time of the target video, the target keyword can be displayed in front, so that the user can understand the key points of the target video more quickly. By adjusting the interval between adjacent preset times to be greater than the preset threshold, the probability of the target video being fully played can be increased.
[0127] Fig. 9 FIG. 1 is a schematic diagram of the structure of a video processing device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Fig. 9 As shown, the video processing device includes:
[0128] A first acquisition module 901 is used to acquire a target video and object information of an object corresponding to the target video;
[0129] A determination module 902 is used to determine keyword information based on the target video and the object information, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style;
[0130] The sending module 903 is used to send the target video, the object information, and the keyword information to the client, so that the client can display the target keyword and the object information according to the appearance time and special effect style of the target keyword during the playback of the target video.
[0131] In some embodiments of the present disclosure, the determination module 902 includes:
[0132] An identification submodule, used to identify the target video and the object information using a target classification model to determine target keywords;
[0133] A first determination submodule, used to determine the corresponding appearance time according to the target keyword;
[0134] The second determination submodule is used to determine the special effect style of the target keyword according to the target video, the object information, the target keyword and the corresponding appearance time.
[0135] In some embodiments of the present disclosure, the identification submodule is used to:
[0136] Performing text recognition on the target video and the audio and image in the object information to obtain a first text;
[0137] Inputting the first text and the second text in the object information into a target classification model to extract a plurality of initial keywords divided into a plurality of categories;
[0138] An initial keyword of a preset type is extracted from the multiple initial keywords of the multiple types and determined as a target keyword.
[0139] In some embodiments of the present disclosure, the first determining submodule is used to:
[0140] If the target keyword comes from the target video, determining the time when the target keyword appears in the target video as the corresponding appearance time;
[0141] If the target keyword comes from the object information, the appearance time of the target keyword is determined as the preset time.
[0142] In some embodiments of the present disclosure, the second determining submodule includes:
[0143] A first determining unit, configured to determine a style color of the target keyword based on at least one of a color block analysis result of the target video, a video duration of the target video, a number of the target keywords, and a first appearance time of the target keyword;
[0144] A second determination unit, configured to determine a special effect element of the target keyword based on a text recognition result of the target video;
[0145] The third determining unit is used to determine the appearance position of the target keyword based on the position of the object in the target video.
[0146] In some embodiments of the present disclosure, the second determining unit is used to:
[0147] If the text recognition result of the target video is that text exists, the special effect element of the target keyword is set to a target special effect element with a motion effect strength greater than a preset strength.
[0148] The video processing device provided in the embodiments of the present disclosure can execute the video processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
[0149] Fig.10 This is a schematic diagram of the structure of another video processing device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Fig.10 As shown, the video processing device includes:
[0150] The second acquisition module 1001 is used to acquire a target video, object information of an object corresponding to the target video, and keyword information of the target video, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style;
[0151] The display module 1002 is used to display the target keyword according to the appearance time and special effect style of the target keyword during the playback of the target video, and to display the object information.
[0152] In some embodiments of the present disclosure, the video processing device further includes:
[0153] A drawing module, used for drawing a keyword view for the target keyword in accordance with the special effect style before displaying the target keyword according to the appearance time and special effect style of the target keyword during the playing of the target video;
[0154] a synthesis module, configured to synthesize the keyword view with a main view of a video frame of an appearance time of the target keyword in the target video to obtain a synthesized view;
[0155] Among them, the display module is used to:
[0156] The target video is played, and during the playback, the synthetic view is rendered and displayed according to the appearance time of the target keyword, so that the target keyword is displayed in the special effect style.
[0157] The video processing device provided in the embodiments of the present disclosure can execute the video processing method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.
[0158] A computer program product comprises a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the steps of any of the above-mentioned video processing methods are implemented.
[0159] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.
[0160] The following specific reference Fig.11 , which shows a schematic diagram of the structure of an electronic device 1100 suitable for implementing the embodiment of the present disclosure. The electronic device 1100 in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.11 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0161] like Fig.11 As shown, the electronic device 1100 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage device 1108 to a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the electronic device 1100 are also stored. The processing device 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.
[0162] Typically, the following devices may be connected to the I / O interface 1105: an input device 1106 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1108 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1109. The communication device 1109 may allow the electronic device 1100 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.11The electronic device 1100 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0163] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 1109, or installed from a storage device 1108, or installed from a ROM 1102. When the computer program is executed by the processing device 1101, the above-mentioned functions defined in the video processing method of the embodiment of the present disclosure are executed.
[0164] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0165] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0166] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0167] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the target video and the object information of the object corresponding to the target video; determines the keyword information based on the target video and the object information, wherein the keyword information includes the target keyword, the appearance time of the target keyword, and the special effect style; sends the target video, the object information, and the keyword information to the client, so that the client displays the target keyword according to the appearance time and special effect style of the target keyword during the playback of the target video, and displays the object information. And / or, obtains the target video, the object information of the object corresponding to the target video, and the keyword information of the target video, wherein the keyword information includes the target keyword, the appearance time and special effect style of the target keyword; displays the target keyword according to the appearance time and special effect style of the target keyword during the playback of the target video, and displays the object information.
[0168] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0169] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0170] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.
[0171] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0172] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0173] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.
[0174] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.
[0175] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0176] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.
Claims
1. A video processing method, characterized in that: include: Obtaining a target video and object information of an object corresponding to the target video; Determining keyword information based on the target video and the object information, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style; The target video, the object information, and the keyword information are sent to the client, so that the client displays the target keyword according to the appearance time and special effect style of the target keyword and displays the object information during the playback of the target video.
2. The method according to claim 1, characterized in that Determining keyword information based on the target video and the object information includes: Using a target classification model to identify the target video and the object information, and determine target keywords; Determine the corresponding appearance time according to the target keyword; The special effect style of the target keyword is determined according to the target video, the object information, the target keyword and the corresponding appearance time.
3. The method according to claim 2, characterized in that Using the target classification model to identify the target video and the object information to determine the target keyword includes: Performing text recognition on the target video and the audio and image in the object information to obtain a first text; Inputting the first text and the second text in the object information into a target classification model to extract a plurality of initial keywords divided into a plurality of categories; An initial keyword of a preset type is extracted from the multiple initial keywords of the multiple types and determined as a target keyword.
4. The method according to claim 2, characterized in that: Determining the corresponding appearance time according to the target keyword includes: If the target keyword comes from the target video, determining the time when the target keyword appears in the target video as the corresponding appearance time; If the target keyword comes from the object information, the appearance time of the target keyword is determined as the preset time.
5. The method according to claim 2, characterized in that: Determining a special effect style of the target keyword according to the target video, the object information, the target keyword and the corresponding appearance time includes: Determine the style color of the target keyword based on at least one of the color block analysis result of the target video, the video duration of the target video, the number of the target keywords, and the first appearance time of the target keyword; Determining the special effect element of the target keyword based on the text recognition result of the target video; Based on the position of the object in the target video, the appearance position of the target keyword is determined.
6. The method according to claim 5, characterized in that Determining the special effect elements of the target keyword based on the text recognition result of the target video, including: If the text recognition result of the target video is that text exists, the special effect element of the target keyword is set to a target special effect element with a motion effect strength greater than a preset strength.
7. A video processing method, characterized in that: include: Acquire a target video, object information of an object corresponding to the target video, and keyword information of the target video, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style; During the playing of the target video, the target keyword is displayed according to the appearance time and special effect style of the target keyword, and the object information is displayed.
8. The method according to claim 7, characterized in that Before displaying the target keyword according to the appearance time and special effect style of the target keyword during the playing of the target video, the method further includes: Draw a keyword view for the target keyword according to the special effect style; Synthesize the keyword view with a main view of a video frame of an appearance time of the target keyword in the target video to obtain a synthesized view; The process of playing the target video includes displaying the target keyword according to the appearance time and special effect style of the target keyword, including: The target video is played, and during the playback, the synthetic view is rendered and displayed according to the appearance time of the target keyword, so that the target keyword is displayed in the special effect style.
9. A video processing device, characterized in that: include: A first acquisition module, used to acquire a target video and object information of an object corresponding to the target video; A determination module, configured to determine keyword information based on the target video and the object information, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style; A sending module is used to send the target video, the object information, and the keyword information to the client, so that the client can display the target keyword and the object information according to the appearance time and special effect style of the target keyword during the playback of the target video.
10. A video processing device, characterized in that: include: A second acquisition module is used to acquire a target video, object information of an object corresponding to the target video, and keyword information of the target video, wherein the keyword information includes a target keyword, an appearance time of the target keyword, and a special effect style; A display module is used to display the target keyword according to the appearance time and special effect style of the target keyword during the playback of the target video, and to display the object information.
11. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the video processing method described in any one of claims 1-8.
12. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the video processing method described in any one of claims 1 to 8.
Citation Information
Cited By
Video generation model training method and device, electronic equipment and storage medium
CN120358394A
