Video processing method and system, computing device and storage medium

Abstract

The embodiment of the invention relates to the technical field of computers, in particular to a video processing method and system, computing equipment and a storage medium, and the video processing method comprises the following steps: determining a to-be-processed video played in a video playing interface, carrying out information extraction on the to-be-processed video, and obtaining key video information of the to-be-processed video, the key video information is displayed on an information display interface; and in response to an information acquisition instruction for the video playing interface, displaying the video playing interface and the information display interface according to a preset display style, and / or switching the video playing interface to the information display interface. Therefore, the user can determine the related content of the to-be-processed video according to the key video information, so that the user can know the video content of the to-be-processed video without spending a lot of time, and the video watching experience of the user is improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of computer technology, and in particular to video processing methods, systems, computing devices, and storage media. Background Art

[0002] With the development of computer technology, more and more entertainment applications have emerged. For example, various video playback platforms and live broadcast platforms can provide users with video playback services. These videos can be TV series videos, game videos, animation videos, etc., or live broadcast videos. However, when the user just clicks on the video, it is not clear what the specific content of the current video is. It is necessary to stay on the platform and watch for a while to understand the content of the current video. For example, when the user just clicks on the live broadcast room, it is impossible to immediately understand the specific content of the current live broadcast, resulting in a poor user experience. Therefore, an effective technical solution is urgently needed to solve the above problems. Summary of the invention

[0003] In view of this, an embodiment of the present specification provides a video processing method. One or more embodiments of the present specification also relate to a video processing device, a video processing system, a computing device, a computer-readable storage medium and a computer program product to solve the technical defects existing in the prior art.

[0004] According to a first aspect of an embodiment of this specification, a video processing method is provided, including: Determine the video to be processed played in the video playback interface, extract information from the video to be processed, and obtain key video information of the video to be processed, wherein the key video information is displayed in the information display interface; In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface are displayed according to a preset display style, and / or the video playback interface is switched to the information display interface.

[0005] According to a second aspect of the embodiments of this specification, there is provided a video processing device, including: A determination module is configured to determine a video to be processed played in a video playback interface, extract information from the video to be processed, and obtain key video information of the video to be processed, wherein the key video information is displayed in an information display interface; The display module is configured to respond to the information acquisition instruction for the video playback interface, display the video playback interface and the information display interface according to a preset display style, and / or switch the video playback interface to the information display interface.

[0006] According to a third aspect of the embodiments of this specification, a video processing system is provided, including a viewing user end and a server end of a video to be processed, wherein: The viewing user terminal is configured to determine the video to be processed played in the video playback interface, and send the video to be processed to the server terminal; The server is configured to extract information from the video to be processed, obtain key video information of the video to be processed, and send the key video information to the viewing user terminal, wherein the key video information is displayed on the information display interface of the viewing user terminal; The viewing user terminal is also configured to respond to an information acquisition instruction for the video playback interface, display the video playback interface and the information display interface according to a preset display style, and / or switch the video playback interface to the information display interface.

[0007] According to a fourth aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the above method are implemented.

[0008] According to a fifth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores a computer program / instruction, and the steps of the above method are implemented when the computer program / instruction is executed by a processor.

[0009] According to a sixth aspect of the embodiments of this specification, a computer program product is provided, comprising a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0010] An embodiment of the present specification provides a video processing method, including: determining a video to be processed that is played in a video playback interface, extracting information from the video to be processed, and obtaining key video information of the video to be processed, wherein the key video information is displayed in an information display interface; in response to an information acquisition instruction for the video playback interface, displaying the video playback interface and the information display interface according to a preset display style, and / or switching the video playback interface to the information display interface.

[0011] The above method obtains key video information of the video to be processed by extracting information from the video to be processed played in the video playback interface. The key video information can be displayed in the information display interface. In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface can be displayed according to a preset display style, and / or the video playback interface can be switched to the information display interface to realize the display of the key video information on the information display interface. The key video information of the video to be processed is displayed without affecting the user's viewing of the video to be processed, so that the user can determine the relevant content of the video to be processed based on the key video information, so that the user can understand the video content of the video to be processed without spending a lot of time, thereby improving the user's video viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 This is a schematic diagram of an application scenario of a video processing method provided by an embodiment of this specification; Figure 2 is a flow chart of a video processing method provided by an embodiment of this specification; Figure 3 It is a schematic diagram of generating video summary information in a video processing method provided by an embodiment of this specification; Figure 4 This is a schematic diagram of generating key video clips in a video processing method provided by an embodiment of this specification; Figure 5 It is a schematic diagram of generating a resource display interface in a video processing method provided in an embodiment of this specification; Figure 6 It is a schematic diagram of a resource display interface in a video processing method provided by an embodiment of this specification; Figure 7 It is a schematic diagram of generating product summary information in a video processing method provided by an embodiment of this specification; Figure 8 It is a schematic diagram of a product interface to be explained in a video processing method provided in an embodiment of this specification; Fig. 9 is a processing flow chart of a video processing method provided by an embodiment of this specification; Fig.10 is a structural schematic diagram of a video processing device provided by an embodiment of this specification; Fig.11 is a structural schematic diagram of a video processing system provided by an embodiment of this specification; Fig.12 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0012] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0013] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0014] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0015] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0016] In one or more embodiments of this specification, a large model refers to a deep learning model with large-scale model parameters, which usually contains hundreds of millions, tens of billions, hundreds of billions, trillions, or even more than 10 trillion model parameters. A large model can also be called a foundation model / foundation model. The large model is pre-trained with large-scale unlabeled corpus to produce a pre-trained model with more than 100 million parameters. This model can adapt to a wide range of downstream tasks, and the model has good generalization ability, such as a large-scale language model (LLM), a multi-modal pre-training model, etc.

[0017] When the big model is used in practice, only a small number of samples are needed to fine-tune the pre-trained model and it can be applied to different tasks. The big model can be widely used in natural language processing (NLP), computer vision and other fields. Specifically, it can be applied to computer vision tasks such as visual question answering (VQA), image caption (IC), image generation, as well as natural language processing tasks such as text-based sentiment classification, text summary generation, and machine translation. The main application scenarios of the big model include digital assistants, intelligent robots, search, online education, office software, e-commerce, intelligent design, etc.

[0018] First, the terms involved in one or more embodiments of this specification are explained.

[0019] ASR: Automatic Speech Recognition, is a technology that converts human spoken language into text that can be understood by computer programs. The goal of ASR technology is to accurately identify what the speaker said from the audio signal and convert it into text form, which usually does not require human intervention.

[0020] In this specification, a video processing method is provided. This specification also relates to a video processing device, a video processing system, a computing device, a computer-readable storage medium and a computer program product, which are described in detail one by one in the following embodiments.

[0021] See also Figure 1 , Figure 1 A schematic diagram of an application scenario of a video processing method provided according to an embodiment of the present specification is shown.

[0022] Figure 1 The device 102 is included in the terminal side.

[0023] In specific implementation, the user can enter the live broadcast room through the terminal device 102. At this time, the video playback interface of the terminal device 102 displays and plays the live video in the live broadcast room, and the live video can be the anchor's explanation of the goods. Information extraction can be performed on the live video to obtain key video information of the live video. In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface are displayed according to the preset display style, and / or the video playback interface is switched to the information display interface.

[0024] Furthermore, in one embodiment of the present specification, information can be extracted from the live video to obtain video summary information and key video clips of the live video. In the video playback interface, the user can click the "Live Program List" entry control (i.e., information acquisition instruction) to enter the information display interface, which displays video summary information and cover images of multiple key video clips. At this time, the information display interface and the video playback interface are displayed overlappingly. In response to the user's click instruction on the cover image of one of the key video clips, the video playback interface is switched to the information display interface, and the key video clip is displayed and played on the information display interface. At this time, the terminal device 102 only displays the information display interface but not the video playback interface, so that the user can understand the live content in a timely manner, and can also freely choose whether to play the key video clips, meet the needs of the user, and improve the user experience.

[0025] The end-side device 102 may include a browser, an APP (Application), or a web application such as an H5 (Hyper Text Markup Language 5, version 5 of Hypertext Markup Language) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The end-side device may be based on a software development kit (SDK) of the corresponding service provided by the server, such as based on the real-time communication (RTC, Real Time Communication) SDK development and acquisition. The end-side device may be deployed in an electronic device and needs to rely on the device to run or some APPs in the device to run. The electronic device may have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, etc. Various other types of applications may also be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0026] See also Figure 2 , Figure 2A flow chart of a video processing method provided according to an embodiment of the present specification is shown, which specifically includes the following steps.

[0027] Step 202: Determine the video to be processed played in the video playback interface, extract information from the video to be processed, and obtain key video information of the video to be processed, wherein the key video information is displayed in the information display interface.

[0028] Specifically, the video processing method provided in the embodiments of this specification can be executed by the viewing user end of the video to be processed, and the viewing user end can be understood as the client of the viewing user. The video processing method provided in the embodiments of this specification can be applied to the live broadcast field or the video playback field. In the live broadcast field, the video processing method can process the live video being broadcast in the live broadcast room. In the video playback field, the video processing method can process the video being played in the video playback platform. The embodiments of this specification do not limit this.

[0029] For ease of understanding, the embodiments of this specification are described by applying the video processing method to the live broadcast field, so the video to be processed can be understood as a live broadcast video.

[0030] The video playback interface can be understood as the live video playback interface after the viewing user terminal of the live video enters the live broadcast room. The key video information can be understood as information that can represent the video content of the video to be processed. The key video information includes but is not limited to the video summary information and key video clips of the video to be processed. The information display interface can be understood as the interface of the viewing user terminal for displaying key video information.

[0031] Based on this, the viewing user terminal can determine the live video played in the video playback interface, and extract information from the live video to obtain key video information of the live video.

[0032] In one embodiment of the present specification, the viewing user end can send the live broadcast room information corresponding to the live broadcast video to the server end, and the server end obtains the live broadcast video based on the live broadcast room information, extracts information from the live broadcast video, and obtains key video information of the live broadcast video. The server end can send the key video information to the viewing user end, so that the viewing user end displays the key video information on the information display interface.

[0033] For example, a user enters live broadcast room A through a viewing user terminal, and starts playing the live video in live broadcast room A through the video playback interface of the viewing user terminal. The viewing user terminal can obtain the live video played by the live broadcast room A, extract information from the live video, and obtain key video information of the live video.

[0034] In one embodiment of the present specification, the key video information includes video summary information of the video to be processed; The extracting information from the video to be processed to obtain key video information of the video to be processed includes: Extract summary information of the video to be processed to obtain video summary information of the video to be processed.

[0035] Among them, the video summary information can be used to briefly describe the video content of the video to be processed. For example, in the case that the live broadcast video is a live broadcast of product promotion, the video summary information can be, for example, "This is another super large show of the anchor after 6 months. This show mainly discussed the super youthful atmosphere of dressing. The anchor gave several corresponding dressing ideas. And gave a detailed explanation of the individual items."

[0036] Specifically, summary information may be extracted from the video to be processed to obtain video summary information of the video to be processed.

[0037] In summary, by extracting the video summary information of the video to be processed, it is convenient to display the video summary information later, so that the user can understand the video content of the video to be processed according to the video summary information.

[0038] In a specific implementation, extracting summary information of the video to be processed to obtain video summary information of the video to be processed includes: Performing text conversion on the video to be processed to obtain a video text corresponding to the video to be processed; The summary information of the video text is extracted by using the summary extraction model to obtain the video summary information of the video to be processed.

[0039] The video text may be the text of the video content of the video to be processed. For example, if the video to be processed is a live video, the video text may be the text corresponding to the words spoken by the host in the live video. The summary extraction model may be understood as a model for extracting summary information from the video text corresponding to the video to be processed.

[0040] Based on this, the video content of the video to be processed can be converted into text to obtain the video text of the video content of the video to be processed, and the video text is input into the summary extraction model to obtain the video summary information of the video to be processed output by the summary extraction model.

[0041] In practical applications, the summary extraction model can be a large model, a neural network model, a machine learning model, etc. Specifically, the summary extraction model can be, for example, an extractive summary model or a generative summary model, etc. The generative summary model can be, for example, an encoder-decoder architecture, a model based on a self-attention mechanism, a pre-trained model, etc., which is not limited in the embodiments of this specification. When converting the video to be processed into text, the audio corresponding to the video to be processed can be determined, and the audio can be converted into video text using ASR.

[0042] In addition, the video to be processed may be directly input into the summary extraction model to obtain the video summary information of the video to be processed output by the summary extraction model.

[0043] In summary, by converting the processed video into text and then generating video summary information, the accuracy of video cancer drug information generation can be achieved.

[0044] Furthermore, the extracting summary information from the video text using the summary extraction model to obtain the video summary information of the video to be processed includes: Using the summary extraction model, extracting summary information from the video text multiple times to obtain multiple video summary information of the video to be processed; Using a summary evaluation model, evaluating the plurality of video summary information to obtain evaluation results corresponding to the plurality of video summary information; According to the evaluation result, target video summary information whose evaluation result meets a preset evaluation condition is determined from the multiple video summary information as the video summary information of the video to be processed.

[0045] Among them, the summary evaluation model can be understood as a model for performing sentiment scoring on the generated video summary information. The evaluation results corresponding to multiple video summary information can be, for example, the scores for evaluating multiple video summary information. The preset evaluation condition can be that the evaluation score meets the preset score threshold, such as the evaluation score being greater than 90 points, or the preset evaluation condition can also be the highest evaluation score. When the summary extraction model is used to extract summary information from the video text multiple times, the number of video summary information obtained is the same as the number of times the summary information is extracted using the summary extraction model. For example, the summary extraction model is used to extract summary information from the video text 100 times to obtain 100 video summary information corresponding to the video to be processed.

[0046] It can be understood that the multiple video summary information obtained by performing multiple summary information extractions using the summary extraction model can be the same or different. Specifically, when the same video summary information exists in multiple video summary information, the multiple video summary information can be deduplicated to facilitate subsequent evaluation of multiple non-duplicate video summary information.

[0047] Based on this, the summary extraction model can be used to extract summary information from the video text multiple times to obtain multiple video summary information of the video to be processed, and the summary evaluation model can be used to evaluate the multiple video summary information to obtain evaluation scores corresponding to the multiple video summary information. The evaluation scores corresponding to the multiple video summary information are compared, and the video summary information with the highest evaluation score is determined as the video summary information of the video to be processed.

[0048] In practical applications, the summary evaluation model can be a general sentiment dictionary, a machine learning model, a deep learning model, a pre-trained model, a hybrid model, etc., which is not limited in the embodiments of this specification.

[0049] Using the above example, the summary extraction model can be used to extract summary information from the video text three times to obtain three video summary information corresponding to the video to be processed. The summary evaluation model can be used to evaluate the three video summary information to obtain evaluation scores of 90, 92 and 95 corresponding to the three video summary information. According to the evaluation scores of the three video summary information, the video summary information with the highest evaluation score of 95 is used as the video summary information of the live video. It can be understood that in order to ensure the accuracy of the video summary information, a large number of summary information extractions can usually be performed, such as more than 100 times. The three times here are only for example, and the embodiments of this specification do not limit this.

[0050] In summary, by extracting summary information from video texts multiple times and evaluating multiple video summary information, the video summary information with the highest evaluation result is determined as the video summary information of the video to be processed, thereby improving the accuracy of video summary information generation.

[0051] In addition, after obtaining the evaluation results corresponding to the plurality of video summary information, the method further includes: The summary extraction model is optimized according to the evaluation results corresponding to the multiple video summary information.

[0052] Specifically, the server can also optimize the summary extraction model according to the evaluation results corresponding to the summary information of multiple videos, so as to realize the feedback model optimization scoring.

[0053] It is understandable that the summary extraction model and the summary evaluation model can be deployed on the viewing user side or on the server side, and the embodiments of this specification do not limit this.

[0054] In summary, by optimizing the summary extraction model according to the evaluation results, the video summary information generated by the optimized summary extraction model is more accurate.

[0055] Furthermore, the server can also collect feedback data from multiple viewing users, and use the feedback data and evaluation results to optimize the summary extraction model. The specific implementation method is as follows: According to a preset diversion rule, the plurality of video summary information is pushed to a viewing user terminal of the video to be processed; The summary extraction model is optimized according to the feedback data for the multiple video summary information and the evaluation results corresponding to the multiple video summary information sent by the viewing user terminal.

[0056] The preset traffic diversion rule can be understood as a rule for pushing multiple video summary information using different push traffic. The preset traffic diversion rule can be, for example, determining the push traffic based on the evaluation result. The higher the evaluation result, the larger the push traffic. The feedback data for multiple video summary information can be understood as the time a user stays on the video summary information by watching the user terminal.

[0057] Specifically, according to the preset diversion rules, the first push traffic can be used to push the video summary information with the highest evaluation result to multiple viewing user terminals, and the second push traffic can be used to push the video summary information with the highest comparison result to multiple viewing user terminals according to the comparison results between the evaluation results, wherein the first push traffic is greater than the second push traffic. It can be understood that the number of viewing user terminals can be related to the push traffic. For example, when the first push traffic is 90% and the second push traffic is 10%, the video summary information with the highest evaluation result can be pushed to 90 viewing user terminals, and the video summary information with the highest comparison result can be distributed and pushed to 10 viewing user terminals. Afterwards, the user evaluation data for the multiple video summary information can be determined according to the residence time for the multiple video summary information sent by the viewing user terminals, and the summary extraction model can be optimized according to the user evaluation data and the evaluation results.

[0058] In practical applications, see Figure 3 , Figure 3 FIG. 1 is a schematic diagram showing the generation of video summary information in a video processing method provided according to an embodiment of the present specification. Figure 3As shown, the live video of the current live broadcast room can be recorded, and the live audio corresponding to the live video can be converted into video text through ASR technology, the video text can be stored in a database, and the video text can be input into a summary extraction model. The summary extraction model can be used to extract summary information from the video text multiple times to obtain multiple video summary information, and the multiple video summary information can be input into a summary evaluation model to obtain evaluation scores of multiple video summary information. According to 90% of the push traffic, the video summary information with the highest evaluation score is pushed to the viewing user end. According to 10% of the push traffic, the video summary information with evaluation scores ranked 2-10 is distributed and pushed to the viewing user end. The residence time for these video summary information returned by the viewing user end is obtained, and the user evaluation score corresponding to each video summary information is determined according to the residence time. According to the user evaluation score and the evaluation scores of multiple video summary information, the summary extraction model and the summary evaluation model are optimized.

[0059] In summary, by optimizing the summary extraction model according to the evaluation results and user feedback data, the video summary information generated by the optimized summary extraction model is more accurate.

[0060] In one embodiment of the present specification, the key video information includes a key video segment of the video to be processed; The extracting information from the video to be processed to obtain key video information of the video to be processed includes: Performing interactive video extraction on the video to be processed to obtain interactive video segments in the video to be processed and interactive data corresponding to the interactive video segments; The interactive video segment whose interactive data meets the preset interactive condition is determined as the key video segment of the video to be processed.

[0061] Among them, the key video clips can be understood as the wonderful video clips in the video to be processed. The interactive video clips in the video to be processed can be understood as the multiple sub-video clips contained in the video to be processed. The interactive data corresponding to the interactive video clips can include the data of the interactive behavior of the users received during the playback of the interactive video clips. The interactive data may include the amount of user comments, the amount of user likes, the current number of viewers, etc. The preset interactive condition can be understood as the interactive data reaching the preset interactive threshold, for example, the amount of user comments, the amount of user likes and the current number of viewers all reaching the preset interactive threshold, or the interactive rate calculated based on the interactive data reaches the preset interactive threshold.

[0062] Based on this, interactive video extraction can be performed on the video to be processed to obtain multiple sub-video clips contained in the video to be processed and the interactive data corresponding to each sub-video clip, and the sub-video clips whose interactive data reach a preset interactive threshold are determined as key video clips of the video to be processed.

[0063] In summary, by generating wonderful video clips in the video to be processed, it is convenient to display the wonderful video clips later, so that users can directly watch the wonderful video clips, saving user time and ensuring user experience.

[0064] In a specific implementation, the interactive video extraction is performed on the video to be processed to obtain the interactive video segment in the video to be processed and the interactive data corresponding to the interactive video segment, including: Determine multiple playback time periods for playing the video to be processed; According to the multiple play time periods, extract interactive videos from the video to be processed, and determine interactive video segments corresponding to each play time period of the video to be processed in the multiple play time periods, and interactive data corresponding to the interactive video segments; The step of determining the interactive video segment whose interactive data satisfies the preset interactive condition as the key video segment of the video to be processed includes: According to the interactive video segments corresponding to each of the multiple playback time periods and the interactive data corresponding to the interactive video segments, the interactive video segments corresponding to the target playback time periods whose interactive data meet the preset interactive conditions are determined as the key video segments of the video to be processed.

[0065] The play time period may be understood as a time window, such as every second, or a time period within 5 seconds.

[0066] Specifically, multiple time windows for playing the video to be processed can be determined, a snapshot of the interactive behavior of the video to be processed in each time window can be generated, and the interactive data of the video to be processed in each time window can be obtained. The start time and end time of the time period in which the interactive rate reaches a preset interactive threshold can be calculated based on the interactive data of the video to be processed in each time window. According to the start time and end time, a target playback time period in which the interactive data meets the preset interactive conditions can be determined based on the start time and end time. According to the target playback time period, video cropping can be performed on the video to be processed, and the interactive video segment of the video to be processed within the target playback time period can be determined, and the interactive video segment can be determined as the key video segment of the video to be processed.

[0067] In practical applications, see Figure 4 , Figure 4 FIG. 1 shows a schematic diagram of generating key video clips in a video processing method provided according to an embodiment of the present specification. Figure 4As shown, the anchor can start the live broadcast in the live broadcast room by pushing the stream through the live broadcast user end, and the live broadcast video can be recorded. The user can watch the live broadcast in the live broadcast room through the viewing user end, and interact by giving likes and comments in the live broadcast room. A time snapshot can be generated for the user's interactive behavior within a unit of time, and interactive data such as likes, comments and the current number of viewers in each time snapshot in multiple time windows can be obtained. The interaction rate of each time window can be calculated, and the start time and end time of the high interaction rate period can be calculated. The recorded live broadcast video can be cropped according to the start time and end time to obtain the cropped key video clips.

[0068] In summary, by determining the interaction data based on the behavior snapshots of each time window and calculating the key video clips during the high interaction rate period, the generation of wonderful video clips is achieved, which is convenient for subsequent display of the wonderful video clips to users.

[0069] Step 204: In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface are displayed according to a preset display style, and / or the video playback interface is switched to the information display interface.

[0070] The information acquisition instruction for the video playback interface may be understood as an acquisition instruction for the user for the key video information of the video to be processed on the video playback interface in the viewing user terminal.

[0071] Specifically, in response to a user's information acquisition instruction for the video playback interface, the video playback interface can be switched to an information display interface, and key video information can be displayed on the information display interface, and / or the video playback interface and the information display interface can be displayed according to a preset display style, and key video information can be displayed on the information display interface.

[0072] In a specific implementation, displaying the video playback interface and the information display interface according to a preset display style includes: Synchronously displaying the video playback interface and the information display interface according to a preset display style in which the interfaces partially overlap; or According to the preset display style in which the interfaces are arranged in sequence, the video playback interface and the information display interface are displayed synchronously.

[0073] Specifically, the video playback interface and the information display interface may be displayed synchronously according to a preset display style in which the interfaces partially overlap, and in this case, the video playback interface and the information display interface partially overlap. Alternatively, the video playback interface and the information display interface may be displayed synchronously according to a preset display style in which the interfaces are arranged sequentially, and in this case, the video playback interface and the information display interface do not overlap.

[0074] In one embodiment of the present specification, the key video information displayed on the information display interface may be video summary information. Then, the information display interface may be displayed overlappingly on top of the video playback interface, or the video playback interface may be switched to the information display interface, or the video summary information may be displayed in the video playback interface in the form of live barrage.

[0075] In one embodiment of the present specification, the key video information displayed on the information display interface may be a key video clip, and the video playback interface may be switched to the information display interface to display the key video clip on the information display interface. Alternatively, in the case of including multiple key video clips, in response to an information acquisition instruction, cover images of multiple key video clips may be displayed on the video playback interface, and in response to a user's click instruction on one of the cover images, the video playback interface may be switched to the information display interface, and the key video clip corresponding to the cover image clicked by the user may be played on the information display interface.

[0076] In another embodiment of the present specification, the key video information displayed on the information display interface may be video summary information and key video clips, and the video playback interface may be switched to the information display interface, and the video summary information and key video clips may be displayed on the information display interface. Alternatively, in response to an information acquisition instruction, the video summary information and cover images of multiple key video clips may be displayed on the video playback interface, and in response to a user's click instruction on one of the cover images, the video playback interface may be switched to the information display interface, and the key video clip corresponding to the cover image clicked by the user may be played on the information display interface.

[0077] In summary, by realizing the synchronous display and / or switching of the video playback interface and the information display interface in different ways, it is possible to display the key video information of the live video to the user without affecting the user's viewing of the live broadcast, so that the user can understand the live broadcast content as soon as possible and ensure the user's live broadcast viewing experience.

[0078] In one embodiment of this specification, the video to be processed is a live video; The method further comprises: Receiving resource distribution information sent by the server, wherein the resource distribution information is obtained according to data filled in by the live broadcast user of the live broadcast video; A resource display interface is generated according to the resource distribution information, and the resource display interface is displayed on the video playback interface.

[0079] Among them, resource distribution information can be understood as welfare distribution information. Welfare may include but is not limited to red envelopes, shopping coupons and lucky draws, etc. Welfare distribution information includes but is not limited to welfare distribution start time, welfare distribution end time, welfare content, etc.

[0080] Specifically, the anchor can fill in the welfare distribution information through the live broadcast user terminal, the live broadcast user terminal sends the welfare distribution information filled in by the anchor to the server terminal, the server terminal sends the welfare distribution information to the viewing user terminal, the viewing user terminal generates a welfare display interface according to the welfare distribution information, and displays the welfare display interface on the video playback interface.

[0081] Alternatively, the anchor can fill in the welfare distribution information through the live broadcast user terminal, and the live broadcast user terminal sends the welfare distribution information filled in by the anchor to the server terminal. The server terminal can directly generate a welfare display interface based on the welfare distribution information, and send the welfare display interface to the viewing user terminal, and the viewing user terminal displays the welfare display interface on the video playback interface.

[0082] In practical applications, see Figure 5 , Figure 5 A schematic diagram of generating a resource display interface in a video processing method provided according to an embodiment of the present specification is shown. Figure 5 As shown, the anchor can fill in the welfare plan on the live broadcast user side. The welfare plan can be filled in in the form of a table. The welfare in the welfare plan can include red envelopes, shopping coupons and lucky draws. The welfare distribution information can include the start time, end time and number of red envelopes, the start time, end time and amount of shopping coupons, and the start time, end time and prize content of lucky draws. In addition, the server can classify and aggregate the welfare plan to generate a welfare panorama (i.e., the content displayed in the welfare display interface). The welfare panorama can include the start time of each welfare, and the welfare panorama also includes a detail display control. The viewing user can click the detail display control to view the welfare details (i.e., welfare distribution information).

[0083] See also Figure 6 , Figure 6 A schematic diagram of a resource display interface in a video processing method provided according to an embodiment of this specification is shown. Figure 6As shown, a live broadcast program list can be displayed in the video playback interface. Click the "Live Broadcast Benefits" control in the live broadcast program list to enter the resource display interface. In the resource display interface, the start time of each benefit in the benefit plan filled in by the anchor is displayed, including live lottery, live coupon issuance and live red envelope. The start time of each benefit is displayed according to the timeline. For example, the timeline may include 10:10, 10:20, 10:30, 10:40 and 10:50. The benefits that have been issued are displayed as "expired". For the ongoing benefits, "Go to draw", "Go to get coupons" and "Go to grab red envelopes" can be displayed respectively. Taking the live coupon issuance as an example, the viewing user can click the "Go to get coupons" control. The viewing user end pulls up the coupon receiving interface according to the user's click instruction. The user can click the "Follow and receive" control to complete the coupon receiving action. At this time, the video live broadcast interface will display "Coupon Received Successfully" and display the "Go to Use" control. In addition, by reading the live broadcast plan data, the host's subsequent welfare distribution events can be displayed. If the live broadcast plan is changed in real time, the corresponding welfare distribution time will also be changed in real time.

[0084] In summary, by generating a welfare display interface, users can understand the welfare that will be distributed in the live broadcast room.

[0085] In addition, after displaying the resource display interface on the video playback interface, the method further includes: Sending a click instruction for a reservation control on the resource display interface to the server; Receive resource reminder information sent by the server in response to the click instruction, wherein the resource reminder information is generated by the server in response to the click instruction and is sent when the current moment is determined to be the resource issuance moment according to the resource issuance information.

[0086] The resource reminder information can be understood as the reminder information that the benefits are about to be issued. The resource issuance time can be understood as the benefit issuance time filled in by the aforementioned anchor.

[0087] Combined with the above Figure 5 It can be seen that users in the live broadcast room can make reservations for the desired benefits in advance, and reminder information will be pushed to the user when the time for the benefit to be issued is reached. Specifically, the user can send a click instruction for the reservation control of a benefit to be issued in the benefit display interface to the server through the viewing user end. In response to the click instruction, the server generates the benefit reminder information corresponding to the benefit to be issued, and when it is determined that the current time is the time for the benefit to be issued, the benefit reminder information is sent to the viewing user end. The viewing user end can receive the benefit reminder information and display the benefit reminder information on the interface of the viewing user end, so that the user can receive the benefit reminder information regardless of whether he is in the live broadcast room or not.

[0088] In actual applications, users can click the "Remind Me" control for the benefits they are interested in, and when the host distributes the benefits, a push notification will be sent to the user.

[0089] In summary, by pushing resource reminder information to the viewing user end, users can be informed of the welfare distribution time in a timely manner regardless of whether they are in the live broadcast room, thereby preventing users from missing out on the welfare distribution they are interested in, and further improving the user experience.

[0090] In addition, the method further comprises: When it is determined that the video to be processed is a video explaining the target object, determining the explained object at the current moment; Determining object attribute information and object explanation information corresponding to the explained object according to the explanation video; The object attribute information and the object explanation information are displayed on the video playback interface.

[0091] Among them, the target object can be understood as the product that the anchor promotes. The target object can include the explained object, and the explained object can be understood as the product that the anchor has explained. The object attribute information can be understood as the attribute information of the product, which can include the product picture, product price, product title and product label, etc. The object explanation information can be understood as the product information of the anchor's explanation of the product. The explained object at the current moment can be understood as the explained object that the user wants to watch the explanation video at the current moment.

[0092] Specifically, when it is determined that the video to be processed is an explanation video for the product promoted by the anchor, the explained product that the user wants to review can be determined in response to the user's video review instruction for the explained product, and the product attribute information and product explanation information of the explained product can be determined based on the explanation video, and the product attribute information and product explanation information can be displayed on the video playback interface. In addition, the target explanation video that explains the explained product can be cropped from the explanation video, and the target explanation video can be displayed on the video playback interface and played.

[0093] In addition, the product attribute information and the product explanation information may be summarized into key information to generate product summary information corresponding to the product attribute information and the product explanation information, and the product summary information may be displayed on the video playback interface.

[0094] In practical applications, see Figure 7 , Figure 7 FIG. 1 is a schematic diagram showing the generation of product summary information in a video processing method provided according to an embodiment of this specification. Figure 7As shown, the anchor can initiate explanations through the live broadcast user terminal, record the live broadcast video of the anchor's explanation, and convert the audio corresponding to the recorded live broadcast video into video text through ASR technology, store the video text in the database, and obtain the anchor's product explanation information on the explained product from the video text, and obtain the product attribute information of the explained product displayed on the product shopping platform, input the product explanation information and product attribute information into the summary extraction model, obtain the product summary information corresponding to the product explanation information and product attribute information, and store the product summary information. In response to the user's video review instruction for the explained product, the product summary information of the explained product is obtained from the database and displayed to the user. In response to the user's reservation instruction for the unexplained product, when it is determined that the anchor will explain the unexplained product, the user who made the reservation for the explanation can be contacted, and the product explanation reminder information can be sent to the user.

[0095] In summary, by displaying the product attribute information and product explanation information of the explained products, users no longer need to look for relevant content of the explained products in the live video, which assists users in making decisions, saves users' time in watching and replaying, and ensures user experience.

[0096] Then, when it is determined that the video to be processed is an explanation video for the target object, the method further includes: Determine the unexplained objects at the current moment; Sending a click instruction for a reservation control of the unexplained object to the server; The object explanation reminder information is received from the server according to the click instruction, wherein the object explanation reminder information is sent by the server when determining to explain the unexplained object.

[0097] Among them, the unexplained objects can be understood as products that the anchor has not explained. The object explanation reminder information can be understood as information used to remind that the product explanation is about to begin.

[0098] Specifically, the video playback interface of the viewing user terminal can display the unexplained products at the current moment. The viewing user terminal sends a click instruction for the reservation control of the unexplained product to the server terminal. The server terminal generates product explanation reminder information in response to the click instruction, and when it is determined that the unexplained product is about to be explained, the product explanation reminder information is sent to the viewing user terminal. The viewing user terminal can display the product explanation reminder information on the viewing user terminal interface.

[0099] In practical applications, see Figure 8 , Figure 8 A schematic diagram of a product interface to be explained in a video processing method provided according to an embodiment of the present specification is shown. Figure 8As shown, a live broadcast program list can be displayed in the video playback interface. Click the "Appointment for Explanation" control in the live broadcast program list to enter the interface of products to be explained. Unexplained products and corresponding appointment controls can be displayed in the interface of products to be explained. The user can click the appointment control corresponding to an unexplained product. The viewing user end can generate a successful appointment message "The message has been sent, and you will be notified when the product begins to be explained", and display the successful appointment message to the user. When the anchor starts to explain the product, the interface of the viewing user end can pop up a product explanation reminder message "The explanation of the product you have booked has started", and the user can click the product explanation reminder message to enter the live broadcast room.

[0100] In summary, by providing users with product explanation appointment services, users can avoid missing out on product explanations of interest and further ensure user experience.

[0101] To summarize, the above method obtains key video information of the video to be processed by extracting information from the video to be processed played in the video playback interface. The key video information can be displayed in the information display interface. In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface can be displayed according to a preset display style, and / or the video playback interface can be switched to the information display interface to realize the display of the key video information in the information display interface. The key video information of the video to be processed is displayed without affecting the user's viewing of the video to be processed, so that the user can determine the relevant content of the video to be processed based on the key video information, so that the user can understand the video content of the video to be processed without spending a lot of time, thereby improving the user's video viewing experience. The following combination Fig. 9 , taking the application of the video processing method provided in this specification in live video as an example, the video processing method is further described. Fig. 9 A processing flow chart of a video processing method provided by an embodiment of the present specification is shown, which specifically includes the following steps.

[0102] Step 902: The user enters the live broadcast room through the viewing user terminal, and starts playing the live video in the live broadcast room through the video playback interface of the viewing user terminal.

[0103] Step 904: The user clicks on the "Live Program List" entry in the video playback interface to enter the Live Program List interface.

[0104] Specifically, the live broadcast program list interface includes the "What is the host talking about" control, the "Live broadcast benefits" control and the "Appointment for explanation" interface.

[0105] Step 906: The user clicks the "What is the host talking about" control in the live broadcast program list interface to enter the information display interface.

[0106] Specifically, the information display interface is used to display the video summary information of the live video and the cover image of the key video clip. At this time, the information display interface and the video playback interface are displayed synchronously. When the user clicks the cover image, the live program list interface switches to the information display interface, and the key video clip is displayed and played on the information display interface. When the user clicks the "Return to Live Room" control in the information display interface, the information display interface switches to the video playback interface.

[0107] Step 908: The user clicks the "Live Broadcast Benefits" control in the live broadcast program list interface to enter the benefits display interface.

[0108] Step 910: The user clicks the "Book Explanation" control in the live broadcast program list interface to enter the interface of the product to be explained.

[0109] Specifically, the user can review the products that have been explained and make reservations for the products that have not been explained on the interface of the products to be explained.

[0110] Corresponding to the above method embodiment, this specification also provides a video processing device embodiment, Fig.10 FIG. 2 shows a schematic diagram of the structure of a video processing device provided by an embodiment of the present specification. Fig.10 As shown, the device comprises: The determination module 1002 is configured to determine the video to be processed played in the video playback interface, extract information from the video to be processed, and obtain key video information of the video to be processed, wherein the key video information is displayed in the information display interface; The display module 1004 is configured to respond to the information acquisition instruction for the video playback interface, display the video playback interface and the information display interface according to a preset display style, and / or switch the video playback interface to the information display interface.

[0111] In an optional embodiment, the key video information includes video summary information of the video to be processed; The determining module 1002 is further configured to: Extract summary information of the video to be processed to obtain video summary information of the video to be processed.

[0112] In an optional embodiment, the determining module 1002 is further configured to: Performing text conversion on the video to be processed to obtain a video text corresponding to the video to be processed; The summary information of the video text is extracted by using the summary extraction model to obtain the video summary information of the video to be processed.

[0113] In an optional embodiment, the determining module 1002 is further configured to: Using the summary extraction model, extracting summary information from the video text multiple times to obtain multiple video summary information of the video to be processed; Using a summary evaluation model, evaluating the plurality of video summary information to obtain evaluation results corresponding to the plurality of video summary information; According to the evaluation result, target video summary information whose evaluation result meets a preset evaluation condition is determined from the multiple video summary information as the video summary information of the video to be processed.

[0114] In an optional embodiment, the key video information includes a key video segment of the video to be processed; The determining module 1002 is further configured to: Performing interactive video extraction on the video to be processed to obtain interactive video segments in the video to be processed and interactive data corresponding to the interactive video segments; The interactive video segment whose interactive data meets the preset interactive condition is determined as the key video segment of the video to be processed.

[0115] In an optional embodiment, the determining module 1002 is further configured to: Determine multiple playback time periods for playing the video to be processed; According to the multiple play time periods, extract interactive videos from the video to be processed, and determine interactive video segments corresponding to each play time period of the video to be processed in the multiple play time periods, and interactive data corresponding to the interactive video segments; According to the interactive video segments corresponding to each of the multiple playback time periods and the interactive data corresponding to the interactive video segments, the interactive video segments corresponding to the target playback time periods whose interactive data meet the preset interactive conditions are determined as the key video segments of the video to be processed.

[0116] In an optional embodiment, the display module 1004 is further configured to: Synchronously displaying the video playback interface and the information display interface according to a preset display style in which the interfaces partially overlap; or According to the preset display style in which the interfaces are arranged in sequence, the video playback interface and the information display interface are displayed synchronously.

[0117] In an optional embodiment, the video to be processed is a live video; The display module 1004 is further configured to: Receiving resource distribution information sent by the server, wherein the resource distribution information is obtained according to data filled in by the live broadcast user of the live broadcast video; A resource display interface is generated according to the resource distribution information, and the resource display interface is displayed on the video playback interface.

[0118] In an optional embodiment, the display module 1004 is further configured to: Sending a click instruction for a reservation control on the resource display interface to the server; Receive resource reminder information sent by the server in response to the click instruction, wherein the resource reminder information is generated by the server in response to the click instruction and is sent when the current moment is determined to be the resource issuance moment according to the resource issuance information.

[0119] In an optional embodiment, the display module 1004 is further configured to: When it is determined that the video to be processed is a video explaining the target object, determining the explained object at the current moment; Determining object attribute information and object explanation information corresponding to the explained object according to the explanation video; The object attribute information and the object explanation information are displayed on the video playback interface.

[0120] In an optional embodiment, the display module 1004 is further configured to: Determine the unexplained objects at the current moment; Sending a click instruction for a reservation control of the unexplained object to the server; The object explanation reminder information is received from the server according to the click instruction, wherein the object explanation reminder information is sent by the server when determining to explain the unexplained object.

[0121] The above-mentioned device obtains key video information of the video to be processed by extracting information from the video to be processed played in the video playback interface. The key video information can be displayed in the information display interface. In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface can be displayed according to a preset display style, and / or the video playback interface can be switched to the information display interface to realize the display of the key video information on the information display interface. The key video information of the video to be processed is displayed without affecting the user's viewing of the video to be processed, so that the user can determine the relevant content of the video to be processed based on the key video information, so that the user can understand the video content of the video to be processed without spending a lot of time, thereby improving the user's video viewing experience. The above is a schematic scheme of a video processing device of this embodiment. It should be noted that the technical scheme of the video processing device and the technical scheme of the above video processing method belong to the same concept, and the details not described in detail in the technical scheme of the video processing device can be referred to the description of the technical scheme of the above video processing method.

[0122] Corresponding to the above method embodiment, this specification also provides a video processing system embodiment. Fig.11 FIG. 2 shows a schematic diagram of the structure of a video processing system provided by an embodiment of the present specification. Fig.11 As shown, the video processing system 1100 includes a viewing user terminal 1102 and a server terminal 1104 for the video to be processed, wherein: The viewing user terminal 1102 is configured to determine the video to be processed played in the video playback interface, and send the video to be processed to the server terminal 1104; The server 1104 is configured to extract information from the video to be processed, obtain key video information of the video to be processed, and send the key video information to the viewing user terminal 1102, wherein the key video information is displayed on the information display interface of the viewing user terminal; The viewing user terminal 1102 is also configured to respond to an information acquisition instruction for the video playback interface, display the video playback interface and the information display interface according to a preset display style, and / or switch the video playback interface to the information display interface.

[0123] The above-mentioned system obtains key video information of the video to be processed by extracting information from the video to be processed played in the video playback interface. The key video information can be displayed in the information display interface. In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface can be displayed according to a preset display style, and / or the video playback interface can be switched to the information display interface to realize the display of the key video information in the information display interface. The key video information of the video to be processed is displayed without affecting the user's viewing of the video to be processed, so that the user can determine the relevant content of the video to be processed based on the key video information, so that the user can understand the video content of the video to be processed without spending a lot of time, thereby improving the user's video viewing experience. The above is a schematic scheme of a video processing system of this embodiment. It should be noted that the technical scheme of the video processing system and the technical scheme of the above video processing method belong to the same concept, and the details not described in detail in the technical scheme of the video processing system can be referred to the description of the technical scheme of the above video processing method.

[0124] Fig.12The block diagram of a computing device 1200 according to one embodiment of the present specification is shown. The components of the computing device 1200 include but are not limited to a memory 1210 and a processor 1220. The processor 1220 is connected to the memory 1210 via a bus 1230, and the database 1250 is used to store data.

[0125] The computing device 1200 also includes an access device 1240 that enables the computing device 1200 to communicate via one or more networks 1260. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 1240 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, a near field communication (NFC) interface, and the like.

[0126] In one embodiment of the present application, the above components of the computing device 1200 and Fig.12 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Fig.12 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of the present application. Those skilled in the art may add or replace other components as needed.

[0127] The computing device 1200 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 1200 may also be a mobile or stationary server.

[0128] The processor 1220 is used to execute the following computer program / instructions, which implement the steps of the above method when executed by the processor.

[0129] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computing device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0130] An embodiment of the present specification further provides a computer-readable storage medium storing a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0131] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the computer-readable storage medium embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0132] An embodiment of the present specification also provides a computer program product, including a computer program / instruction, which implements the steps of the above method when executed by a processor.

[0133] The above is a schematic solution of a computer program product of this embodiment. It should be noted that the technical solution of the computer program product and the technical solution of the above method belong to the same concept, and the details not described in detail in the technical solution of the computer program product can be referred to the description of the technical solution of the above method.

[0134] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0135] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0136] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0137] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0138] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A video processing method, comprising: Determine the video to be processed played in the video playback interface, extract information from the video to be processed, and obtain key video information of the video to be processed, wherein the key video information is displayed in the information display interface; In response to the information acquisition instruction for the video playback interface, the video playback interface and the information display interface are displayed according to a preset display style, and / or the video playback interface is switched to the information display interface.

2. The method according to claim 1, wherein the key video information includes video summary information of the video to be processed; The extracting information from the video to be processed to obtain key video information of the video to be processed includes: Extract summary information of the video to be processed to obtain video summary information of the video to be processed.

3. According to the method of claim 2, extracting summary information of the video to be processed to obtain video summary information of the video to be processed comprises: Performing text conversion on the video to be processed to obtain a video text corresponding to the video to be processed; The summary information of the video text is extracted by using the summary extraction model to obtain the video summary information of the video to be processed.

4. The method according to claim 3, wherein the extracting summary information from the video text using a summary extraction model to obtain video summary information of the video to be processed comprises: Using the summary extraction model, extracting summary information from the video text multiple times to obtain multiple video summary information of the video to be processed; Using a summary evaluation model, evaluating the plurality of video summary information to obtain evaluation results corresponding to the plurality of video summary information; According to the evaluation result, target video summary information whose evaluation result meets a preset evaluation condition is determined from the multiple video summary information as the video summary information of the video to be processed.

5. The method according to claim 1, wherein the key video information comprises a key video segment of the video to be processed; The extracting information from the video to be processed to obtain key video information of the video to be processed includes: Performing interactive video extraction on the video to be processed to obtain interactive video segments in the video to be processed and interactive data corresponding to the interactive video segments; The interactive video segment whose interactive data meets the preset interactive condition is determined as the key video segment of the video to be processed.

6. According to the method of claim 5, the step of extracting interactive video from the video to be processed to obtain interactive video segments in the video to be processed and interactive data corresponding to the interactive video segments comprises: Determine multiple playback time periods for playing the video to be processed; According to the multiple play time periods, extract interactive videos from the video to be processed, and determine interactive video segments corresponding to each play time period of the video to be processed in the multiple play time periods, and interactive data corresponding to the interactive video segments; The step of determining the interactive video segment whose interactive data satisfies the preset interactive condition as the key video segment of the video to be processed includes: According to the interactive video segments corresponding to each of the multiple playback time periods and the interactive data corresponding to the interactive video segments, the interactive video segments corresponding to the target playback time periods whose interactive data meet the preset interactive conditions are determined as the key video segments of the video to be processed.

7. The method according to any one of claims 1 to 6, wherein displaying the video playback interface and the information display interface according to a preset display style comprises: Synchronously displaying the video playback interface and the information display interface according to a preset display style in which the interfaces partially overlap; or According to the preset display style in which the interfaces are arranged in sequence, the video playback interface and the information display interface are displayed synchronously.

8. The method according to claim 1, wherein the video to be processed is a live video; The method further comprises: Receiving resource distribution information sent by the server, wherein the resource distribution information is obtained according to data filled in by the live broadcast user of the live broadcast video; A resource display interface is generated according to the resource distribution information, and the resource display interface is displayed on the video playback interface.

9. The method according to claim 8, wherein after displaying the resource display interface on the video playback interface, the method further comprises: Sending a click instruction for a reservation control on the resource display interface to the server; Receive resource reminder information sent by the server in response to the click instruction, wherein the resource reminder information is generated by the server in response to the click instruction and is sent when the current moment is determined to be the resource issuance moment according to the resource issuance information.

10. The method according to claim 1, further comprising: When it is determined that the video to be processed is a video explaining the target object, determining the explained object at the current moment; Determining object attribute information and object explanation information corresponding to the explained object according to the explanation video; The object attribute information and the object explanation information are displayed on the video playback interface.

11. The method according to claim 10, wherein when it is determined that the video to be processed is an explanation video for a target object, the method further comprises: Determine the unexplained objects at the current moment; Sending a click instruction for a reservation control of the unexplained object to the server; The object explanation reminder information is received from the server according to the click instruction, wherein the object explanation reminder information is sent by the server when determining to explain the unexplained object.

12. A video processing system, comprising a viewing user end and a server end for a video to be processed, wherein: The viewing user terminal is configured to determine the video to be processed played in the video playback interface, and send the video to be processed to the server terminal; The server is configured to extract information from the video to be processed, obtain key video information of the video to be processed, and send the key video information to the viewing user terminal, wherein the key video information is displayed on the information display interface of the viewing user terminal; The viewing user terminal is also configured to respond to an information acquisition instruction for the video playback interface, display the video playback interface and the information display interface according to a preset display style, and / or switch the video playback interface to the information display interface.

13. A computing device comprising: Memory and processor; The memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions. When the computer programs / instructions are executed by the processor, the steps of the method described in any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium storing a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

15. A computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

Images