Video data distribution method and device, electronic equipment, medium and program product

Abstract

The invention provides a video data distribution method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the field of artificial intelligence, in particular to the technical field of large models, natural language processing and video data processing. According to the implementation scheme, in response to determining that a video call process is ended, a plurality of text segments corresponding to a target video recorded and obtained in the video call process are obtained, and each text segment comprises corresponding timestamp information; in response to a received first distribution operation for the video call content, determining at least one to-be-distributed text segment in the plurality of text segments; in response to the received second distribution operation for the video call content, intercepting at least one corresponding video segment in the target video based on the timestamp information corresponding to the at least one text segment; and generating a processed video based on the at least one video segment, the processed video being used as video call content for distribution.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, particularly to the fields of large models, natural language processing, and video data processing technologies. Specifically, it relates to a video data distribution method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] Artificial intelligence is a discipline that studies how to make computers simulate certain human thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level technologies and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, speech recognition technology, natural language processing technology, and machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0003] Video data processing refers to the process of performing a series of operations on video signals or files to achieve specific purposes. These operations can include from simple video editing, format conversion to complex video analysis and editing, etc. Among them, video editing refers to selecting, deleting, or rearranging specific parts from the original captured video footage to construct a coherent and meaningful story or information stream. Summary of the Invention

[0004] The present disclosure provides a video data distribution method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0005] According to one aspect of the present disclosure, there is provided a video data distribution method, including: in response to determining the end of a video call process, obtaining a plurality of text segments corresponding to a target video recorded during the video call process, where the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding to it in the video; in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments; in response to receiving a second distribution operation for the video call content, based on the timestamp information corresponding to each of the at least one text segment, intercepting at least one video segment corresponding to the at least one text segment in the target video; and generating a processed video based on the at least one video segment, where the processed video is used for distributing as the video call content.

[0006] According to another aspect of the present disclosure, a method for distributing video data is provided, including: in response to determining the end of a video call process, obtaining a plurality of text segments corresponding to a target video recorded during the video call process for display, where the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding to it in the video; in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments; in response to receiving a second distribution operation for the video call content, obtaining a processed video, where the processed video is generated based on at least one video segment, and the at least one video segment is obtained by intercepting in the target video based on the timestamp information and corresponds one-to-one to the at least one text segment; and in response to receiving a fourth distribution operation for the processed video, distributing the processed video.

[0007] According to another aspect of the present disclosure, a video data distribution device is provided, including: a text segment obtaining module configured to, in response to determining the end of a video call process, obtain a plurality of text segments corresponding to a target video recorded during the video call process, where the plurality of text segments are obtained by converting the audio in the video into text through speech recognition, and each text segment includes timestamp information corresponding to it in the video; a first determination module configured to, in response to receiving a first distribution operation for the video call content, determine at least one text segment to be distributed among the plurality of text segments; a video segment intercepting module configured to, in response to receiving a second distribution operation for the video call content, intercept at least one video segment corresponding to the at least one text segment in the target video based on the timestamp information corresponding to each of the at least one text segment; and a video segment merging module configured to generate a processed video based on the at least one video segment, where the processed video is used for distribution as the video call content.

[0008] According to another aspect of the present disclosure, there is provided a video data distribution device, including: a text segment display module configured to, in response to determining the end of a video call, obtain a plurality of text segments corresponding to a target video recorded during the video call for display, where the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding thereto in the video; a second determination module configured to, in response to receiving a first distribution operation for the video call content, determine at least one text segment to be distributed among the plurality of text segments; a video segment acquisition module configured to, in response to receiving a second distribution operation for the video call content, obtain a processed video, where the processed video is generated based on at least one video segment, the at least one video segment is intercepted from the target video based on the timestamp information, and corresponds one-to-one with the at least one text segment; and a video segment distribution module configured to, in response to receiving a fourth distribution operation for the processed video, distribute the processed video.

[0009] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method described in the present disclosure.

[0010] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in the present disclosure.

[0011] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program which, when executed by a processor, implements the method described in the present disclosure.

[0012] According to one or more embodiments of the present disclosure, the content of a user's video call is converted into a text conversation record, and a mapping relationship between the text paragraph and the audio-video timeline is established through natural language understanding, so that the video content can be clipped by screening the text paragraphs, meeting the user's refined selection requirement for the distributed content after the video call recording function; improving the richness of the video interaction function, reducing the user operation complexity, and further enhancing the user experience.

[0013] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. Description of the Drawings

[0014] The accompanying drawings exemplarily illustrate embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0015] Figure 1 FIG. shows a schematic diagram of an exemplary system in which the various methods described herein can be implemented according to an embodiment of the present disclosure;

[0016] Figure 2 FIG. shows a flowchart of a video data distribution method for a server according to an embodiment of the present disclosure;

[0017] Figure 3 FIG. shows a flowchart of a video data distribution method for a client according to an embodiment of the present disclosure;

[0018] Figure 4 FIG. shows a schematic diagram of a client display page according to an embodiment of the present disclosure;

[0019] Figure 5A and 5B FIGS. respectively show schematic diagrams of display pages for determining text segments to be distributed according to an embodiment of the present disclosure;

[0020] Figure 6 and 7 FIGS. respectively show schematic diagrams of video loading pages according to an embodiment of the present disclosure;

[0021] Figure 8 FIG. shows a block diagram of the structure of a video data distribution device for a server according to an embodiment of the present disclosure;

[0022] Figure 9 FIG. shows a block diagram of the structure of a video data distribution device for a client according to an embodiment of the present disclosure; and

[0023] Figure 10 FIG. shows a block diagram of the structure of an exemplary electronic device that can be used to implement the embodiments of the present disclosure. Detailed Embodiments

[0024] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] In the present disclosure, unless otherwise specified, the use of terms such as "first", "second", etc. to describe various elements does not intend to limit the positional relationship, temporal relationship or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, and in certain cases, based on the context description, they may also refer to different instances.

[0026] In the description of the various examples in the present disclosure, the terms used are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or more. In addition, the term "and / or" used in the present disclosure covers any one of the listed items and all possible combinations.

[0027] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 A schematic diagram of an exemplary system 100 in which the various methods and apparatuses described herein can be implemented according to embodiments of the present disclosure is shown. Referring Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105 and 106, a server 120, and one or more communication networks 110 that couple the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105 and 106 can be configured to execute one or more applications.

[0029] In an embodiment of the present disclosure, the server 120 can run one or more services or software applications that enable a method for video data distribution to be executed.

[0030] In certain embodiments, the server 120 can also provide other services or software applications, which can include non-virtual environments and virtual environments. In certain embodiments, these services can be provided as web-based services or cloud services, for example, provided to users of the client devices 101, 102, 103, 104, 105 and / or 106 under a software as a service (SaaS) model.

[0031] In Figure 1In the configuration shown, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or combinations thereof that may be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Thus, Figure 1 is an example of a system for implementing the various methods described herein and is not intended to be limiting.

[0032] Users may use client devices 101, 102, 103, 104, 105, and / or 106 to implement corresponding video data distribution methods, text segment selection, etc. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via this interface. Although Figure 1 only six client devices are depicted, those skilled in the art will be able to understand that the present disclosure may support any number of client devices.

[0033] Client devices 101, 102, 103, 104, 105, and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, gaming systems, thin clients, various messaging devices, sensors, or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT WindowsMobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smartphones, tablets, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Gaming systems may include various handheld gaming devices, Internet-enabled gaming devices, etc. The client device is capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0034] Network 110 can be any type of network well-known to those skilled in the art, which can support data communication using any one of a variety of available protocols (including but not limited to TCP / IP, SNA, IP10, etc.). By way of example only, one or more networks 110 can be a local area network (LAN), an Ethernet-based network, token ring, wide area network (WAN), the Internet, virtual network, virtual private network (VPN), intranet, extranet, blockchain network, public switched telephone network (PSTN), infrared network, wireless network (such as Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0035] Server 120 can include one or more general-purpose computers, dedicated server computers (such as PC (personal computer) servers, UNI10 servers, midrange servers), blade servers, mainframes, server clusters, or any other suitable arrangement and / or combination. Server 120 can include one or more virtual machines running a virtual operating system, or other computing architectures involving virtualization (such as one or more flexible pools of logical storage devices that can be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 can run one or more services or software applications that provide the functions described below.

[0036] The computing units in server 120 can run one or more operating systems including any of the above operating systems as well as any commercially available server operating systems. Server 120 can also run any one of a variety of additional server applications and / or middleware applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0037] In some embodiments, server 120 can include one or more applications to analyze and combine data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 can also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0038] In some embodiments, server 120 can be a server of a distributed system, or a server incorporating blockchain. Server 120 can also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in the cloud computing service system to address the defects of high management difficulty and weak business scalability existing in traditional physical hosts and virtual private server (VPS) services.

[0039] System 100 may also include one or more databases 130. In some embodiments, these databases can be used to store data and other information. For example, one or more of databases 130 can be used to store information such as text information and video files. Databases 130 can reside in various locations. For example, the databases used by server 120 can be local to server 120, or can be remote from server 120 and can communicate with server 120 via a network-based or dedicated connection. Databases 130 can be of different types. In some embodiments, the databases used by server 120 can be, for example, relational databases. One or more of these databases can store, update, and retrieve data to and from the databases in response to commands.

[0040] In some embodiments, one or more of databases 130 can also be used by applications to store application data. The databases used by applications can be different types of databases, such as key-value repositories, object repositories, or conventional repositories supported by a file system.

[0041] Figure 1 System 100 can be configured and operated in various ways to enable the application of the various methods and apparatuses described according to the present disclosure.

[0042] The existing video call recording function cannot meet the user's refined selection requirements for distributed content. For example, when the user wants to remove sensitive information, privacy segments, or irrelevant conversations in the video, they must rely on third-party professional editing software for manual processing, resulting in a certain learning cost. On the other hand, although a few software supports cropping the start and end durations of the video within the software, they lack the intelligent editing ability based on semantic content. Users still need to repeatedly listen to locate the editing points, neither being able to quickly locate the target paragraphs nor being able to select multiple segments in batches, resulting in a high operation threshold and low efficiency, especially being extremely unfriendly to non-professional users.

[0043] Therefore, embodiments according to the present disclosure provide a method for video data distribution for a server side. Figure 2 FIG. shows a flowchart of a method for video data distribution according to an embodiment of the present disclosure, as Figure 2As shown, method 200 includes: in response to determining that the video call process ends, obtaining a plurality of text segments corresponding to a target video recorded during the video call process, where the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding thereto in the video (step 210); in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments (step 220); in response to receiving a second distribution operation for the video call content, based on the timestamp information corresponding to each of the at least one text segment, intercepting at least one video segment corresponding to the at least one text segment in the video call content (step 230); and generating a processed video based on the at least one video segment, where the processed video is used for distribution as the video call content (step 240).

[0044] According to an embodiment of the present disclosure, the content of a user's video call is converted into a text conversation record, and a mapping relationship between the text paragraph and the audio-video timeline is established through natural language understanding, so as to realize video content editing by screening text paragraphs, meeting the user's refined selection requirements for the distributed content after the video call recording function; improving the richness of the video interaction function, reducing the user operation complexity, and further enhancing the user experience.

[0045] In the present disclosure, during and after the video call process, the system's operations of obtaining and processing the video call content are known to all participating users in the video call process and are carried out on the premise of the user's consent. For example, after determining that the user has authorized the system to obtain and process the video call content, the method described in the embodiments of the present disclosure is executed.

[0046] According to some embodiments, obtaining a plurality of text segments corresponding to a target video recorded during the video call process includes: converting the audio in the target video into text and segmenting it through speech recognition technology based on a large language model.

[0047] In some embodiments, after the video call process ends, a large language model can be used to obtain, through speech recognition technology, a plurality of text segments corresponding to a target video recorded during the video call process. The recorded target video includes audio. Therefore, when obtaining the plurality of text segments corresponding to the video call content, the audio in the target video can also be obtained first, and then the audio is converted into text and segmented into a plurality of text segments based on a large language model.

[0048] In the present disclosure, each obtained text segment contains the corresponding timestamp information in the target video. In some examples, the timestamp is used to indicate the time range of each text segment in the target video. Exemplarily, it may include the start time and the end time of each text segment in the corresponding target video, or may include at least one of the start time and the end time and the corresponding time length information.

[0049] In some examples, after obtaining the plurality of text segments, they can be sent to the client and presented to the user. The user can not only view the plurality of text segments, but also perform further operations on the corresponding text segments among them.

[0050] Therefore, according to some embodiments, the method may further include: in response to receiving feedback information for the corresponding text segment among the plurality of text segments, performing reinforcement learning on the large language model based on the feedback information.

[0051] In some examples, feedback information for the corresponding text segment among the plurality of text segments can be obtained, for example, by entering comment information in a preset area of the client display interface, clicking an icon on the client display page, or clicking a preset button on the client, etc. Exemplarily, the icon in the client display interface can be, for example, a like or a dislike.

[0052] Based on the feedback information submitted by the user for the corresponding text segment, the feedback information can be used as training data for the large language model to perform reinforcement training on the large language model and continuously optimize the capabilities of speech recognition and text segmentation. For example, if the user feedbacks that the recognition of a certain text segment is inaccurate, the large language model will pay more attention to similar speech features and semantic scenarios in subsequent learning, improving the accuracy of recognition and the rationality of segmentation.

[0053] In this way, the ability of the large language model to process video call audio content can be continuously improved, providing users with better and more accurate services.

[0054] After obtaining a plurality of text segments, in step 220, in response to receiving a first distribution operation for the video call content, determine at least one text segment to be distributed among the plurality of text segments.

[0055] In some embodiments, the first distribution operation can be implemented, for example, by triggering the "distribution" icon or button on the display page, or by the user's operation to implement selecting all or part of the plurality of text segments in the display page frame.

[0056] In some examples, at least one text segment corresponding to the first distribution operation can be used as at least one text segment to be distributed. For example, when the first distribution operation is implemented by triggering a "distribution" icon or button on a display page, all of the multiple text segments can be used as at least one text segment to be distributed; when the first distribution operation is implemented by a user operation to select all or part of the multiple text segments in the display page, all or part of the selected multiple text segments can be used as at least one text segment to be distributed.

[0057] According to some embodiments, the first distribution operation includes a first trigger operation and a deselection operation. In response to receiving the first distribution operation for video call content, determining at least one text segment to be distributed among the multiple text segments includes: in response to receiving the first trigger operation for the video call content, determining multiple text segments corresponding to the first trigger operation among the multiple text segments and setting them to a selected state; and in response to receiving a deselection operation for a corresponding text segment among the multiple text segments in the selected state, setting the state of the corresponding text segment corresponding to the deselection operation to an unselected state. In this embodiment, the text segments in the selected state are the at least one text segment to be distributed.

[0058] In some examples, when the first distribution operation can include a first trigger operation and a deselection operation, the first trigger operation can be implemented, for example, by triggering a "distribution" icon or button on a display page, or by a user operation to select all or part of the multiple text segments in the display page.

[0059] In some examples, multiple initially to-be-distributed text segments can be determined through the first trigger operation. For example, it can be defaulted that the first trigger operation corresponds to all text segments obtained based on the target video. That is, in response to receiving the first trigger operation, it is defaulted that all text segments are directly set to the selected state. Then, judge the video call content that does not need to be distributed. Then, in response to receiving a deselection operation for a corresponding text segment among the multiple text segments in the selected state, setting the state of the corresponding text segment corresponding to the deselection operation to an unselected state. Thus, it is convenient to customize the video call content to be distributed.

[0060] Since in most cases the content that the user needs to distribute accounts for a relatively large proportion, it can be defaulted that all are selected and then some are deselected. This method can provide a comprehensive initial selection range for the user, facilitating the user to gradually eliminate the content that is not to be distributed from the overall range, thus facilitating user operation, reducing the complexity of user operation, and improving the user experience.

[0061] In the above embodiments, the user can flexibly exclude text segments that do not need to be distributed, thereby accurately determining the content to be finally distributed, meeting the user's personalized distribution requirements for video call content, enhancing the pertinence and effectiveness of content distribution, and reducing the complexity of user operations.

[0062] According to some embodiments, the first distribution operation further includes a selection operation. In response to receiving the first distribution operation for the video call content, determining at least one text segment to be distributed among the multiple text segments further includes: in response to receiving a selection operation for a corresponding text segment in an unselected state, setting the state of the corresponding text segment corresponding to the selection operation to a selected state.

[0063] In some examples, the corresponding text segment can also be switched from an unselected state to a selected state by triggering a corresponding selection operation, so as to achieve the purpose of increasing the text segments to be distributed. In this case, the user can conveniently screen the text segments they want to distribute according to their own needs, and then accurately screen out the video call content they hope to distribute.

[0064] According to some embodiments, the first distribution operation includes a second trigger operation. In response to receiving the first distribution operation for the video call content, determining at least one text segment to be distributed among the multiple text segments includes: in response to receiving a second trigger operation for a first text segment among the multiple text segments, taking the first text segment as at least one text segment to be distributed.

[0065] In the above embodiments, the first text segment can refer to any one of the multiple text segments obtained based on the target video. In some examples, each of the multiple text segments corresponds to a corresponding "forward" icon or button. The user can perform a distribution operation on the content corresponding to the text segment by clicking the "forward" icon or button corresponding to the corresponding text segment. Therefore, the second trigger operation can directly operate on a single text segment, improving the distribution accuracy of the video call content.

[0066] It can be understood that the second trigger operation can also be generated by any other suitable means, which is not limited herein.

[0067] After determining at least one text segment to be distributed, in step 230, in response to receiving a second distribution operation for the video call content, at least one video segment corresponding to the at least one text segment is intercepted in the target video based on the respective timestamp information of the at least one text segment.

[0068] In some embodiments, the second distribution operation may refer to a further confirmation operation after the user selects the text segments to be distributed. For example, after determining at least one text segment to be distributed, an icon for "distributing video" may be generated, and the user can trigger the second distribution operation by operating the icon (such as a click operation). After receiving the second distribution operation for the target video, based on the timestamp information corresponding to the at least one confirmed text segment to be distributed, the required video segment can be quickly and accurately located and intercepted. Thus, in step 240, based on the intercepted at least one video segment, a processed video is obtained. Based on the at least one video segment, for example, a processed video is generated by merging.

[0069] Therefore, based on the timestamp information, it can ensure the exact match between the obtained video content and the selected text segment, meet the user's need to distribute specific video call segments, realize the customized distribution of video call records, enhance the richness of video interaction functions, reduce the user operation complexity, and further improve the user experience.

[0070] According to some embodiments, the processed video includes corresponding link information, and the link information is used to distribute the processed video.

[0071] In this embodiment, the link information may refer to a link generated for the processed video to be distributed. Exemplarily, the distribution operation of the processed video can be realized by copying or forwarding the link information. By generating a link, the video can be distributed in a way of one-key copying or forwarding, which improves the convenience of distribution. And since the original video file is not carried during the process of copying or forwarding the link information, the speed and efficiency of video distribution are also improved.

[0072] According to some embodiments, after determining at least one text segment to be distributed among the multiple text segments, in response to receiving a third distribution operation for the at least one text segment, a processed text is generated based on the at least one text segment, and the processed text is used for distributing as the video call content.

[0073] In some embodiments, the third distribution operation may refer to a further confirmation operation after the user selects the text segments to be distributed. For example, after determining at least one text segment to be distributed, an icon for "distributing text" may be generated, and the user can trigger the third distribution operation by operating the icon (such as a click operation). Based on the at least one text segment, for example, a processed text is generated by merging.

[0074] Through the above embodiments, text content distribution can be achieved. That is, after selecting the text segment to be distributed, the text segment can be directly distributed without further obtaining its corresponding video clip. In this way, different distribution methods are provided, enriching the diversity of distributed content.

[0075] According to some embodiments, the video call process is a video call process between a client user and a large language model.

[0076] Exemplarily, a user can initiate a video call request to the large language model to implement the video call process. In some examples, a user can have a video call with a digital human implemented based on the large language model. Compared with the video call between real human users, the video call process is an analog video call process.

[0077] For example, a user can have a video call with a virtual anchor or an AI social robot, and the virtual anchor or AI social robot provides an immersive experience to the user through video interaction; a user can have a video call with a virtual teacher or a doctor, and the virtual teacher or doctor provides personalized tutoring or diagnosis to the user through real-time video.

[0078] According to an embodiment of the present disclosure, a video data distribution method for a client is also provided. Figure 3 A flowchart showing a video data distribution method according to an embodiment of the present disclosure is as Figure 3 shown. Method 300 includes: in response to determining that the video call process ends, obtaining a plurality of text segments corresponding to a target video recorded during the video call process for display, where the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding to it in the video (step 310); in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments (step 320); in response to receiving a second distribution operation for the video call content, obtaining a processed video, where the processed video is generated based on at least one video segment, and the at least one video segment is intercepted from the target video based on the timestamp information and corresponds one-to-one to the at least one text segment (step 330); and in response to receiving a fourth distribution operation for the processed video, distributing the processed video (step 340).

[0079] According to some embodiments, the content of a user video call is converted into a text conversation record, and a mapping relationship between text paragraphs and the audio-video timeline is established through natural language understanding, so as to realize video content editing by screening text paragraphs, meeting the user's refined selection needs for distributed content after the video call recording function; improving the richness of video interaction functions, reducing the user operation complexity, and further enhancing the user experience.

[0080] In some embodiments, after the video call process ends, the client can obtain multiple text segments corresponding to the target video recorded during the video call process and display them on the display page. By converting the audio in the video into text segments through speech recognition, the video content can be presented in a more intuitive and easy-to-operate manner, facilitating subsequent screening by the user. At the same time, each text segment can be attached with timestamp information, and based on this timestamp information, the corresponding video segment can be accurately located.

[0081] According to some embodiments, the multiple text segments are obtained by converting the audio in the target video into text through speech recognition based on a large language model and then segmenting the text.

[0082] In some embodiments, after the video call process ends, a large language model can be used to obtain multiple text segments corresponding to the target video recorded during the video call process through speech recognition technology. Among them, the recorded target video includes audio. Therefore, when obtaining the multiple text segments corresponding to the video call content, the audio in the target video can also be obtained first, and then the audio is converted into text based on the large language model and segmented to obtain multiple text segments.

[0083] In some examples, after obtaining the multiple text segments, they can be sent to the client and displayed to the user. The user can not only view the multiple text segments but also perform further operations on the corresponding text segments among them. The user can not only view the multiple text segments but also perform further operations on the corresponding text segments among them.

[0084] Therefore, according to some embodiments, obtaining multiple text segments corresponding to the target video recorded during the video call process for display includes: displaying the multiple text segments together with the feedback identifiers corresponding to the multiple text segments one by one.

[0085] In some examples, based on the feedback identifier, feedback information for the corresponding text segment among the multiple text segments can be obtained. For example, the feedback information can be obtained by inputting comment information in a preset area of the client display interface, clicking an icon on the client display page, or clicking a preset button on the client, etc. Exemplarily, the icons in the client display interface can be like a like button, a dislike button, etc.

[0086] Figure 4 A schematic diagram of a client display page according to an embodiment of the present disclosure is shown. As Figure 4 shown, a plurality of obtained text segments (410) are displayed on the display page. The user can input feedback information for a corresponding text segment by clicking on a feedback identifier near the corresponding text segment, such as a like or dislike icon 440.

[0087] Therefore, according to some embodiments, the method may further include: in response to receiving a trigger operation for a feedback identifier corresponding to a second text segment among the plurality of text segments, obtaining feedback information that matches the feedback identifier corresponding to the trigger operation, where the feedback information is used for the large language model for reinforcement learning.

[0088] In some examples, based on the feedback information submitted by the user for a corresponding text segment, the feedback information can be used as training data for the large language model to perform reinforcement training on the large language model and continuously optimize the capabilities of speech recognition and text segmentation. In this way, the ability of the large language model to process video call audio content can be continuously improved, providing users with better and more accurate services.

[0089] After obtaining a plurality of text segments, in step 320, in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments.

[0090] In some embodiments, the first distribution operation can be implemented, for example, by triggering a "distribution" icon or button on the display page, or by a user operation to implement selecting all or part of the plurality of text segments in the display page.

[0091] In some examples, at least one text segment corresponding to the first distribution operation can be used as at least one text segment to be distributed. For example, when the first distribution operation is implemented by triggering a "distribution" icon or button on the display page, all of the plurality of text segments can be used as at least one text segment to be distributed; when the first distribution operation is implemented by a user operation to select all or part of the plurality of text segments in the display page, all or part of the selected plurality of text segments can be used as at least one text segment to be distributed.

[0092] Continuing to refer to Figure 4 , for example, the first distribution operation can be triggered by triggering the "distribution" button on the display page. Alternatively, the first distribution operation can also be triggered by selecting the text segments to be distributed, as Figure 4 shown in the first distribution operation implemented by selection in which text segment 430 is used as the selected text segment to be distributed.

[0093] According to some embodiments, the first distribution operation includes a second triggering operation. In response to receiving the first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments includes: in response to receiving the second triggering operation for the first text segment among the plurality of text segments, taking the first text segment as at least one text segment to be distributed.

[0094] In the above embodiment, the first text segment may refer to any one of the plurality of text segments obtained based on the target video. In some examples, each of the plurality of text segments corresponds to a corresponding "forward" icon or button. The user can perform a distribution operation on the content corresponding to the text segment by clicking the "forward" icon or button corresponding to the corresponding text segment. Therefore, the second triggering operation can be used to directly operate on a single text segment, improving the distribution accuracy of the video call content.

[0095] Continue to refer to Figure 4 , for example, the second triggering operation can be triggered by triggering the "forward" button 420 on the display page. When the second triggering operation for the first text segment 510 among the plurality of text segments is received, the first text segment is determined as the text segment to be distributed.

[0096] It can be understood that the second triggering operation can also be generated by any other suitable means, which is not limited herein.

[0097] According to some embodiments, the first distribution operation includes a first triggering operation and a deselection operation. In response to receiving the first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments includes: in response to receiving the first triggering operation for the video call content, determining a plurality of text segments corresponding to the first triggering operation among the plurality of text segments, where the plurality of text segments corresponding to the first triggering operation respectively correspond to corresponding selection identifiers and their selection identifiers are all in a selected state; in response to receiving the deselection operation for the corresponding text segment among the plurality of text segments in the selected state, switching the selection identifier corresponding to the corresponding text segment corresponding to the deselection operation from the selected state to an unselected state, where the text segments in the selected state are at least one text segment to be distributed.

[0098] In some examples, when the first distribution operation may include a first triggering operation and a deselection operation, the first triggering operation can be implemented, for example, by triggering the "distribution" icon or button on the display page, or by the user's operation to select all or part of the plurality of text segments in the display page.

[0099] In some examples, a plurality of text segments to be initially distributed can be determined through a first trigger operation. For example, it can be defaulted that the first trigger operation corresponds to all text segments obtained based on the target video. That is, in response to receiving the first trigger operation, it is defaulted that all text segments are directly set to the selected state. Then, the video call content that does not need to be distributed is judged. Then, in response to receiving a deselection operation for a corresponding text segment among the plurality of text segments in the selected state, the state of the corresponding text segment corresponding to the deselection operation is set to the unselected state. Thus, it is convenient to customize the video call content to be distributed.

[0100] Figure 5A And 5B respectively show schematic diagrams of display pages for determining text segments to be distributed according to embodiments of the present disclosure. For the convenience of subsequent screening, a selection identifier can be assigned to each text segment. When the first trigger operation is received, the selection identifiers 520 corresponding to the respective multiple text segments 510 corresponding to the first trigger operation are all in the selected state, that is, the corresponding selection boxes are displayed in the selected state "√". In the example where, in response to receiving the first trigger operation, it is defaulted that all text segments are directly set to the selected state, in addition to each selection box corresponding to each text segment being displayed in the selected state "√", a "select all" identifier can also be displayed in this display page, and the "select all" identifier is also in the selected state "√".

[0101] Then, in response to receiving a deselection operation for a corresponding text segment among the plurality of text segments in the selected state, the state of the corresponding text segment corresponding to the deselection operation is set to the unselected state. For example, a deselection operation can be performed on the selection box corresponding to the corresponding text segment in Figure 5A so as to realize the state switch of the corresponding text segment to the unselected state. As shown in Figure 5B , the selection identifier 530 is in the selected state and the selection identifier 540 is in the unselected state.

[0102] Generally, the video content to be distributed may occupy most of the recorded target video. Therefore, at the initial stage of selection, the selection identifiers of each text segment are set to the selected state, so that the user can realize the selection process of the content to be distributed by deselecting the text segments corresponding to a small part of the content, improving the selection efficiency.

[0103] According to some embodiments, the first distribution operation further includes a selection operation. In response to receiving the first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments further includes: in response to receiving a selection operation for a corresponding text segment in the unselected state, switching the selection identifier corresponding to the corresponding text segment corresponding to the selection operation from the unselected state to the selected state.

[0104] Continuing to refer to the appendix Figure 5B , the user can operate on the selection identifier in the unselected state to switch it from the unselected state to the selected state, so as to select the text segment corresponding to the selection identifier as the text segment to be distributed. In this way, the user can flexibly adjust the video call content they want to distribute, reducing the complexity of the user when distributing the video call content.

[0105] According to some embodiments, the method may further include: after determining at least one text segment to be distributed among the multiple text segments, in response to receiving a third distribution operation for the at least one text segment, generating processed text based on the at least one text segment, where the processed text is used for distribution as the video call content.

[0106] In some embodiments, the third distribution operation may refer to a further confirmation operation after the user selects the text segment to be distributed. Through the third distribution operation, the user can achieve the distribution of the corresponding text content in the video call content, enriching the distribution form.

[0107] Continuing to refer to Figure 5B , in some examples, after determining at least one text segment to be distributed, the user can trigger the third distribution operation by clicking on the "Share Text" icon in the operation area 550 on the display page (for example, a click operation), so as to achieve the distribution of the text content.

[0108] According to some embodiments, obtaining the processed video in response to receiving a second distribution operation for the video call content includes: in response to receiving a second distribution operation for the video call content, popping up a video loading page for obtaining the processed video. Implementing at least one of the following operations based on the video loading page: during the process of obtaining the processed video, displaying the loading state information corresponding to the processed video on the video loading page; and after obtaining the processed video, previewing the processed video in the video loading page.

[0109] In some embodiments, the second distribution operation may refer to a further confirmation operation after the user selects the text segment to be distributed. For example, referring to Figure 5B as shown, after determining at least one text segment to be distributed, the user can trigger the second distribution operation by clicking on the "Share Video" icon in the operation area 550 on the display page (for example, a click operation).

[0110] In some embodiments, after receiving a second distribution operation for the target video, a video loading page is popped up for obtaining the processed video. Figure 6and 7 respectively show schematic diagrams of a video loading page according to embodiments of the present disclosure. As Figure 6 shown, during the process of obtaining a video, loading state information (620 and 630) corresponding to the video is displayed on the video loading page 610. Through this loading state information, the user can know that the video is being generated. The video loading page will display the loading state information corresponding to the video, enabling the user to timely understand the progress of video acquisition and avoiding user anxiety due to waiting.

[0111] In some examples, the loading state information (620 and 630) can be displayed in the form of text and / or animation. Further, in some examples, the loading state information can be a simple and intuitive progress bar. Through the filling status of the progress bar, the user can clearly know the completion ratio of video download or processing; it can also be a dynamic loading animation, such as a rotating icon, allowing the user to perceive that the system is processing.

[0112] It can be understood that the above descriptions regarding the second distribution operation and the loading state are merely exemplary and are not limited herein.

[0113] In some embodiments, when the processed video is successfully obtained, the video loading page can have a video preview function. As Figure 7 shown, for example, by clicking on the video play icon or button in the video loading page, the user can directly preview the processed video on this page to check whether the video content meets expectations before actual distribution. For example, it can be checked whether the clipped segments are correct, whether the audio and video are synchronized, etc. If a problem is found, the user can timely adjust the distributed content, thereby effectively avoiding the distribution of incorrect or unsatisfactory videos, further optimizing the distribution process of video call content, and improving the efficiency and satisfaction of the user in distributing videos.

[0114] According to some embodiments, the video loading page includes: a distribution identifier for performing a distribution operation on the processed video, wherein the fourth distribution operation includes a third trigger operation on the distribution identifier, and wherein, in response to receiving a fourth distribution operation for the processed video, performing a distribution operation on the processed video includes: in response to receiving a third trigger operation on the distribution identifier, performing a distribution operation on the processed video based on a distribution method corresponding to the distribution identifier.

[0115] According to some embodiments, the distribution identifier includes at least one of the following items: an identifier for obtaining link information of the processed video, an identifier for downloading the processed video to the local, and an identifier for forwarding the processed video to a preset platform.

[0116] In some examples, asFigure 7 As shown, if the user clicks the "Download Video" button 710, the processed video obtained can be saved to the local storage location specified by the user, facilitating the user to view and use it at any time on the local device; if the user clicks the "Copy Video Link" button 720, the link corresponding to the processed video can be copied to the user's clipboard, so as to facilitate the user to distribute this link to other platforms, such as social software, emails, etc., to achieve the dissemination of the video in different scenarios.

[0117] Through the clear distribution identifier and the corresponding trigger operation, the distribution process of the entire video call content becomes more flexible and diversified. The user can select a suitable distribution method according to their own needs, improving the richness of the video interaction function and enhancing the user experience.

[0118] According to some embodiments, the video call process is a video call process between a client user and a large language model.

[0119] In the present disclosure, the terms and features in the video data distribution method for the client have the same or similar meanings as the related terms and features in the video data distribution method for the server. And, in some embodiments, they have the same or similar implementation manners as those described in the above embodiments, which will not be elaborated here. According to the embodiments of the present disclosure, as Figure 8 shown, a video data distribution device 800 is further provided, including: a text segment acquisition module 810 configured to, in response to determining the end of the video call process, acquire a plurality of text segments corresponding to a target video recorded during the video call process, where the plurality of text segments are obtained by converting the audio in the video into text through speech recognition, and each text segment includes the corresponding timestamp information in the video; a first determination module 820 configured to, in response to receiving a first distribution operation for the video call content, determine at least one text segment to be distributed among the plurality of text segments; a video segment intercepting module 830 configured to, in response to receiving a second distribution operation for the video call content, intercept at least one video segment corresponding to the at least one text segment in the target video based on the timestamp information corresponding to each of the at least one text segment; and a video segment merging module 840 configured to generate a processed video based on the at least one video segment, where the processed video is used for distributing as the video call content.

[0120] Here, the operations of the above respective units 810 to 840 of the video data distribution device 800 are respectively similar to the operations of steps 210 to 240 described above, which will not be elaborated here.

[0121] According to the embodiments of the present disclosure, as Figure 9As shown, a video data distribution device 900 is further provided, including: a text segment display module 910 configured to, in response to determining the end of a video call process, obtain a plurality of text segments corresponding to a target video recorded during the video call process for display, where the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding thereto in the video; a second determination module 920 configured to, in response to receiving a first distribution operation for video call content, determine at least one text segment to be distributed among the plurality of text segments; a video segment acquisition module 930 configured to, in response to receiving a second distribution operation for video call content, obtain a processed video, where the processed video is generated based on at least one video segment, and the at least one video segment is intercepted from the target video based on the timestamp information and corresponds one-to-one to the at least one text segment; and a video segment distribution module 940 configured to, in response to receiving a fourth distribution operation for the processed video, distribute the processed video.

[0122] Here, the operations of the above respective units 910 to 940 of the target video generation device 900 are respectively similar to the operations of steps 310 to 340 described above, and will not be elaborated here.

[0123] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure, etc. of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0124] According to an embodiment of the present disclosure, an electronic device, a readable storage medium, and a computer program product are further provided.

[0125] Reference Figure 10 , the structural block diagram of an electronic device 1000 that can be used as a server or a client of the present disclosure will now be described. It is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present disclosure described herein and / or required.

[0126] As Figure 10As shown, the electronic device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the electronic device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0127] Multiple components in the electronic device 1000 are connected to the I / O interface 1005, including: an input unit 1006, an output unit 1007, a storage unit 1008, and a communication unit 1009. The input unit 1006 can be any type of device capable of inputting information into the electronic device 1000. The input unit 1006 can receive input digital or character information, and generate key signal inputs related to the user settings and / or function controls of the electronic device, and can include but are not limited to a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and / or a remote control. The output unit 1007 can be any type of device capable of presenting information, and can include but are not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1008 can include but are not limited to a magnetic disk, an optical disk. The communication unit 1009 allows the electronic device 1000 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks, and can include but are not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, an 802.11 device, a WiFi device, a WiMa10 device, a cellular communication device, and / or the like.

[0128] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 executes the various methods and processes described above, such as method 101010. For example, in some embodiments, method 101010 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the method 101010 described above may be executed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute method 101010 in any other suitable manner (e.g., by means of firmware).

[0129] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-a-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0130] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0131] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0133] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by 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), the Internet, and a blockchain network.

[0134] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0135] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.

[0136] Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above methods, systems, and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only defined by the authorized claims and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, the steps can be executed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples can be combined in various ways. Importantly, with the evolution of technology, many of the elements described herein can be replaced by equivalent elements that emerge after the present disclosure.

Claims

1. A method for video data distribution, comprising: In response to determining the end of a video call, obtaining a plurality of text segments corresponding to a target video recorded during the video call, wherein the plurality of text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding thereto in the video; In response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments; In response to receiving a second distribution operation for the video call content, based on the timestamp information corresponding to each of the at least one text segment, intercepting at least one video segment corresponding to the at least one text segment in the target video; and Generating a processed video based on the at least one video segment, wherein the processed video is used for distribution as the video call content.

2. The method according to claim 1, wherein The first distribution operation includes a first trigger operation and a deselection operation, and wherein, in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments includes: In response to receiving the first trigger operation for the video call content, determining, among the plurality of text segments, the plurality of text segments corresponding to the first trigger operation and setting their status to a selected state; and In response to receiving a deselection operation for a corresponding text segment among the plurality of text segments in the selected state, setting the status of the corresponding text segment corresponding to the deselection operation to an unselected state, wherein the text segments in the selected state are at least one text segment to be distributed.

3. The method according to claim 2, wherein, The first distribution operation further includes a selection operation, and wherein, in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments further includes: In response to receiving a selection operation for a corresponding text segment in the unselected state, setting the status of the corresponding text segment corresponding to the selection operation to a selected state.

4. The method according to claim 1, wherein, The first distribution operation includes a second trigger operation, and wherein, in response to receiving a first distribution operation for the video call content, determining at least one text segment to be distributed among the plurality of text segments includes: In response to receiving the second trigger operation for a first text segment among the plurality of text segments, taking the first text segment as at least one text segment to be distributed.

5. The method according to any one of claims 1-4, wherein, Obtaining a plurality of text segments corresponding to a target video recorded during the video call includes: converting the audio in the target video into text through speech recognition and segmenting it based on a large language model, wherein the method further includes: in response to receiving feedback information for a target text segment among the plurality of text segments, performing reinforcement learning on the large language model based on the feedback information.

6. The method according to claim 1, wherein, The processed video includes corresponding link information, and the link information is used for distributing the processed video.

7. The method according to any one of claims 1-5, further comprising: After determining at least one text segment to be distributed among the multiple text segments, in response to receiving a third distribution operation for the at least one text segment, generate processed text based on the at least one text segment, where the processed text is used for distribution as the video call content.

8. The method according to claim 1, wherein, The video call process is a video call process between a client user and a large language model.

9. A video data distribution method, comprising: In response to determining the end of a video call process, obtain multiple text segments corresponding to a target video recorded during the video call process for display, where the multiple text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes timestamp information corresponding to it in the video; In response to receiving a first distribution operation for video call content, determine at least one text segment to be distributed among the multiple text segments; In response to receiving a second distribution operation for the video call content, obtain a processed video, where the processed video is generated based on at least one video segment, and the at least one video segment is intercepted from the target video based on the timestamp information and corresponds one-to-one with the at least one text segment; and In response to receiving a fourth distribution operation for the processed video, distribute the processed video.

10. The method according to claim 9, wherein, The first distribution operation includes a first trigger operation and a deselection operation, and in response to receiving a first distribution operation for video call content, determining at least one text segment to be distributed among the multiple text segments includes: In response to receiving the first trigger operation for video call content, determine multiple text segments corresponding to the first trigger operation among the multiple text segments, where the multiple text segments corresponding to the first trigger operation respectively correspond to corresponding selection identifiers and their selection identifiers are all in a selected state; In response to receiving a deselection operation for a corresponding text segment among the multiple text segments in a selected state, switch the selection identifier corresponding to the corresponding text segment corresponding to the deselection operation from the selected state to an unselected state, where the text segments in a selected state are at least one text segment to be distributed.

11. The method according to claim 10, wherein, The first distribution operation further includes a selection operation, and in response to receiving a first distribution operation for video call content, determining at least one text segment to be distributed among the multiple text segments further includes: In response to receiving a selection operation for a corresponding text segment in an unselected state, switch the selection identifier corresponding to the corresponding text segment corresponding to the selection operation from an unselected state to a selected state.

12. The method according to claim 9, wherein, The first distribution operation includes a second trigger operation, and in response to receiving a first distribution operation for video call content, determining at least one text segment to be distributed among the multiple text segments includes: In response to receiving the second trigger operation for the first text segment among the multiple text segments, use the first text segment as at least one text segment to be distributed.

13. The method according to any one of claims 9 - 12, wherein, The multiple text segments are obtained by converting the audio in the target video into text through speech recognition based on a large language model and segmenting the text, where Obtaining multiple text segments corresponding to a target video recorded during the video call for display includes: displaying the multiple text segments together with feedback identifiers corresponding to the multiple text segments one by one, where the method further includes: in response to receiving a trigger operation for a feedback identifier corresponding to a second text segment among the multiple text segments, obtaining feedback information that matches the feedback identifier corresponding to the trigger operation, where the feedback information is used for the large language model to perform reinforcement learning.

14. The method according to claim 9, wherein, Responding to receiving a second distribution operation for video call content and obtaining a processed video includes: in response to receiving a second distribution operation for video call content, popping up a video loading page for obtaining the processed video, where at least one of the following operations is implemented based on the video loading page: During the process of obtaining the processed video, displaying loading state information corresponding to the processed video on the video loading page; and After obtaining the processed video, previewing the processed video in the video loading page.

15. The method according to claim 14, wherein, The video loading page includes: a distribution identifier for performing a distribution operation on the processed video, where the fourth distribution operation includes a third trigger operation on the distribution identifier, and where, in response to receiving a fourth distribution operation for the processed video and performing a distribution operation on the processed video includes: in response to receiving a third trigger operation on the distribution identifier, performing a distribution operation on the processed video based on a distribution method corresponding to the distribution identifier.

16. The method according to claim 15, wherein, The distribution identifier includes at least one of the following items: an identifier for obtaining link information of the processed video, an identifier for downloading the processed video to a local device, and an identifier for forwarding the processed video to a preset platform.

17. The method according to any one of claims 9-16, further includes: After determining at least one text segment to be distributed among the multiple text segments, in response to receiving a third distribution operation for the at least one text segment, obtaining a processed text, where the processed text is generated based on the at least one text segment, and where the processed text is used for distribution as the video call content.

18. The method according to claim 9, wherein, The video call process is a video call process between a client user and a large language model.

19. A video data distribution device includes: A text segment acquisition module configured to, in response to determining that the video call process ends, obtain multiple text segments corresponding to a target video recorded during the video call process, where the multiple text segments are obtained by converting the audio in the video into text through speech recognition, and where each text segment includes timestamp information corresponding to it in the video; A first determination module, configured to determine at least one text segment to be distributed among the multiple text segments in response to receiving a first distribution operation for video call content; A video segment extraction module, configured to extract at least one video segment corresponding to the at least one text segment in the target video based on the timestamp information corresponding to each of the at least one text segment in response to receiving a second distribution operation for video call content; and A video segment merging module, configured to generate a processed video based on the at least one video segment, where the processed video is used for distribution as the video call content.

20. A video data distribution device, comprising: A text segment display module, configured to obtain and display multiple text segments corresponding to a target video recorded during the video call in response to determining the end of the video call process, where the multiple text segments are obtained by converting the audio in the target video into text through speech recognition, and each text segment includes the timestamp information corresponding to it in the video; A second determination module, configured to determine at least one text segment to be distributed among the multiple text segments in response to receiving a first distribution operation for video call content; A video segment obtaining module, configured to obtain a processed video in response to receiving a second distribution operation for video call content, where the processed video is generated based on at least one video segment, and the at least one video segment is extracted from the target video based on the timestamp information and corresponds one-to-one to the at least one text segment; and A video segment distribution module, configured to distribute the processed video in response to receiving a fourth distribution operation for the processed video.

21. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; Wherein The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1-18.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-18.

23. A computer program product comprising a computer program, wherein, The computer program, when executed by a processor, implements the method according to any one of claims 1-18.

Images