Live video generation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a live video generation method and device, equipment and a storage medium. The method comprises the steps that if it is detected that a live broadcast explanation state of a first object corresponding to a live broadcast room is an explanation state, a first live broadcast video clip is acquired from live broadcast content of the live broadcast room, and the first live broadcast video clip comprises content related to the first object in the live broadcast content; and if the first live video clip satisfies the recommendation condition, generating a first media content, the first media content at least comprising the first live video clip. Therefore, the live broadcast video clip corresponding to the explanation object can be automatically generated in the live broadcast process.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and particularly to methods, apparatuses, devices, and computer-readable storage media for live video generation. Background Art

[0002] Currently, more and more platforms (such as applications, websites, etc.) are designed to provide various services to users. For example, users can publish, browse, and view various types of multimedia content (such as videos) on the platform. For example, users can also live broadcast or watch live broadcasts on the platform. The live broadcast content may include content related to at least one object (such as explanatory content for at least one object). Summary of the Invention

[0003] In a first aspect of the present disclosure, there is provided a method for live video generation. The method includes: if it is detected that the live explanation state of a first object corresponding to a live broadcast room is the ongoing explanation state, obtaining a first live video segment from the live broadcast content of the live broadcast room, the first live video segment including content related to the first object in the live broadcast content; and if the first live video segment meets the recommendation condition, generating first media content, the first media content including at least the first live video segment.

[0004] In a second aspect of the present disclosure, there is provided an apparatus for live video generation. The apparatus includes: a video segment obtaining module configured to, if it is detected that the live explanation state of a first object corresponding to a live broadcast room is the ongoing explanation state, obtain a first live video segment from the live broadcast content of the live broadcast room, the first live video segment including content related to the first object in the live broadcast content; and a media content generating module configured to, if the first live video segment meets the recommendation condition, generate first media content, the first media content including at least the first live video segment.

[0005] In a third aspect of the present disclosure, there is provided an electronic device. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by the at least one processing unit, cause the device to execute the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, there is provided a computer-readable storage medium. A computer program is stored on the computer-readable storage medium and can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the content described in this part is not intended to define the key features 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In conjunction with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where:

[0009] Figure 1 FIG. [0000022] is a schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figures 2A to 2D FIG. [0000025] is a schematic diagram showing an example page for live video clip management according to some embodiments of the present disclosure;

[0011] Figures 3A to 3C FIG. [0000028] is a schematic diagram showing an example page according to some embodiments of the present disclosure;

[0012] Figure 4A FIG. [0000031] is a schematic diagram showing an example of a content recommendation page according to some embodiments of the present disclosure;

[0013] Figure 4B FIG. [0000034] is a schematic diagram showing an example of a live page according to some embodiments of the present disclosure;

[0014] Figure 5 FIG. [0000037] is a flowchart showing an example process for live video generation according to some embodiments of the present disclosure;

[0015] Figure 6 FIG. [0000040] is a schematic block diagram showing a device for live video generation according to some embodiments of the present disclosure; and

[0016] Figure 7 FIG. [0000043] is a block diagram of an electronic device capable of implementing multiple embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the scope of protection of the present disclosure.

[0018] In the description of the embodiments of the present disclosure, the term "including" and its similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". There may also be other explicit and implicit definitions hereinafter.

[0019] In this article, unless explicitly stated, performing a step "in response to A" does not mean that the step is immediately performed after "A", but may include one or more intermediate steps.

[0020] It can be understood that the data involved in the technical solution (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions.

[0021] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, usage scopes, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained through appropriate means according to the relevant laws and regulations.

[0022] For example, when receiving a user's active request, a prompt message is sent to the user to clearly prompt the user that the operation requested by the user will require obtaining and using the user's personal information, so that the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, an application program, a server or a storage medium that performs the operations of the technical solution of the present disclosure according to the prompt message.

[0023] As an optional but non-limiting implementation manner, the manner of sending a prompt message to the user in response to receiving the user's active request may be, for example, in the form of a pop-up window, and the prompt message may be presented in text in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0024] It can be understood that the above process of notifying and obtaining the user's authorization is only illustrative and does not limit the implementation manner of the present disclosure, and other manners that meet the relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0025] Figure 1FIG. is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In environment 100, user 110 can create and publish various types of multimedia content through an associated terminal device 120. User 110 can also establish a live broadcast room through the associated terminal device 120 and provide live broadcast content, etc. In some scenarios, user 110 is also referred to as, for example, the publisher of the live broadcast content and / or the host user, live broadcaster, or manager of the live broadcast room, etc.

[0026] One or more users 130-1, 130-2, ……, 130-N can view the multimedia content published by user 110 through their respective associated terminal devices 140-1, 140-2, ……, 140-N, or view the live broadcast of user 110 and participate in the interaction in the live broadcast room, etc. For ease of discussion, users 130-1, 130-2, ……, 130-N can be collectively referred to or individually referred to as user 130, and terminal devices 140-1, 140-2, ……, 140-N can be collectively referred to or individually referred to as terminal device 140. In some scenarios, user 130 can also be referred to as the audience, listener, viewer, or participant of the multimedia content / live broadcast room.

[0027] It should be understood that although Figure 1 only a single host user is shown, in some embodiments, there can be multiple host users initiating a live broadcast in a certain live broadcast room.

[0028] In some embodiments, applications capable of providing multimedia services can be installed respectively in terminal device 120 and terminal device 140, or websites capable of providing multimedia services can be accessed. Multimedia services can include, for example, live broadcast services. User 110 and user 130 can operate terminal device 120 and terminal device 140 to access the corresponding applications or websites.

[0029] Accordingly, terminal device 120 and terminal device 140 can present various corresponding pages, such as content browsing pages, content recommendation pages, live broadcast pages, etc. The live broadcast page can provide, for example, the live broadcast content of the live broadcast room, such as audio live broadcast content or video live broadcast content, etc.

[0030] In some embodiments, the terminal device 120 and the terminal device 140 can also communicate with the server 150 via the network 152 to implement the supply of multimedia services. The server 150 can provide functions such as management, configuration, and maintenance of applications or websites. Note that the terminal device 120 can also present multimedia content published by other users based on the operations of the user 110, or watch the live broadcasts of other users and participate in the interactions in the live broadcast rooms, etc., and the terminal device 140 can also publish various types of multimedia content based on the operations of the user 130, or establish a live broadcast room and provide live broadcast content, etc. In the following, the operations described with reference to the terminal device 120 can be similarly implemented on the terminal device 140, and the operations described with reference to the terminal device 140 can also be similarly implemented on the terminal device 120.

[0031] The terminal device 120 and the terminal device 140 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, television receivers, radio broadcast receivers, e-book devices, game devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal devices 120, 140 can also support any type of user interface (such as a "wearable" circuit, etc.). The server 150 can be various types of computing systems / servers capable of providing computing capabilities, including but not limited to mainframes, edge computing nodes, computing devices in a cloud environment, and the like.

[0032] It should be understood that the structures and functions of the various elements in the environment 100 are described only for exemplary purposes, without implying any limitation on the scope of the present disclosure.

[0033] As briefly mentioned above, users can publish, browse, and view various types of multimedia content on the platform. For example, users can also watch live broadcasts or replays of live broadcast content on the platform. Traditionally, for viewer users browsing live broadcasts, only when the user browses the live broadcast content in the live broadcast room, the terminal device can present a live video clip of a certain object in the live broadcast content on the page of the application in response to the user's operation. In addition, when the viewer user does not enter the live broadcast room, the terminal device can only present a preview of the live broadcast room on the content recommendation page of the viewer user, and cannot present the live broadcast content in the live broadcast room. This can affect the promotion of the live broadcast room.

[0034] According to an embodiment of the present disclosure, an improved solution for live video generation is proposed. In this solution, if it is detected that the live explanation state of the first object corresponding to the live broadcast room is the state of being in the process of explanation, a first live video segment is obtained from the live content of the live broadcast room, and the first live video segment includes the content related to the first object in the live content. If the first live video segment meets the recommendation conditions, a first media content is generated, and the first media content includes at least the first live video segment.

[0035] Thus, during the live broadcast, the live video segments of the object being explained can be automatically and real-time distributed to users, which can attract users interested in the live content to join the live broadcast room and help improve the access effect of the live broadcast room.

[0036] The exemplary embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0037] For ease of understanding, some examples will first be described in combination with the example pages of Figures 2A to 4B . It should be understood that the pages shown in the drawings are only examples, and various page designs may actually exist. The various graphic elements in the pages may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and there may also be one or more other elements. The embodiments of the present disclosure are not limited in this regard. The following will describe the exemplary embodiments with reference to the environment of Figure 1 . Figures 2A to 4B The page shown can be presented by the terminal device 110.

[0038] It should be noted that in this article, the operations performed by the terminal device (such as the terminal device 120 and / or the terminal device 140) can specifically be performed by means of relevant application programs installed locally. In some embodiments, certain operations may require the support of a server (such as the server 150) or other devices to complete. For ease of understanding, the following will take the terminal device itself performing the operations as an example for exemplary description.

[0039] For the host user (such as the user 110), the corresponding terminal device (such as the terminal device 120) can obtain the first live video segment from the live content of the live broadcast room. In the embodiments of the present disclosure, the terminal device 120 obtains the first live video segment from the live content of the live broadcast room in response to detecting that the live explanation state of the first object corresponding to the live broadcast room is the state of being in the process of explanation. The live explanation state can, for example, include the state of not being explained, the state of being in the process of explanation, the state of the explanation ending, etc., and the present disclosure does not limit the specific live explanation state. If it is detected that the live explanation state of the first object corresponding to the live broadcast room is the state of being in the process of explanation, the terminal device 120 can determine that the first object is currently being explained in the live broadcast room.

[0040] The first live video segment includes the content related to the first object in the live content. The first live video segment may, for example, include a video segment. In some embodiments, the first live video segment may include the explanatory content of the first object in the entire live content. In this document, the first object and the second object mentioned later, etc., all refer to the objects for which introductions, descriptions, or other relevant information are given on the application page. An object may refer to an entity object, a virtual object, etc., including but not limited to entity goods, virtual goods, services, etc.

[0041] Regarding the specific manner of obtaining the first live video segment, in some embodiments, the terminal device 120 may respond to detecting that the live explanation status of the first object is the ongoing explanation status and start obtaining the live content of the live room. The terminal device 120 may then respond to detecting that the live explanation status of the first object is the explanation end status and determine the obtained live content as the first live video segment.

[0042] Exemplarily, during the live state of the live room, the terminal device 120 may respond to detecting the start of the explanation for the first object (i.e., the live explanation status of the first object is the ongoing explanation status), record a live video segment from the live content, and respond to detecting the end of the explanation for the first object (i.e., the live explanation status of the first object is the explanation end status), and obtain the recorded live video segment as the first live video segment. In this case, in some embodiments, during the live state of the live room, the terminal device 120 may, for example, present an explanation control associated with each object in the live room. The terminal device 120 may respond to detecting a trigger operation on the first explanation control for the first object (including but not limited to click operation, long press operation, double click operation, swipe operation, etc.) and determine that the start of the explanation for the first object is detected.

[0043] Exemplarily, the live explanation status of an object may also be determined by automatically analyzing the live content. In some embodiments, the terminal device 120 may, for example, respond to detecting a trigger operation on the explanation control corresponding to the second object in the live room and determine that the explanation for the first object has ended (i.e., the live explanation status of the first object is the explanation end status) and the start of the explanation for other objects. The terminal device 120 may also, for example, present an explanation end control during the explanation of the first object. The terminal device 120 may respond to receiving a trigger operation on this explanation end control and determine that the explanation for the first object has ended. The present disclosure does not limit the specific manner of detecting the start and end of the explanation.

[0044] In some embodiments, during the live broadcast in the live broadcast room, the terminal device 120 may, in response to detecting the start of the explanation of the first object (i.e., the live broadcast explanation state of the first object is the state of being explained), record a live video segment from the live broadcast content, and in response to detecting that the duration of the acquired live broadcast content reaches a preset duration, obtain the recorded live video segment as the first live video segment. Here, the preset duration may be a duration preset by the host user (such as user 110) of the live broadcast room, a duration preset by the background staff of the application 120, or a duration automatically determined by the terminal device 120, etc. Exemplarily, if the preset duration is 1 minute, the terminal device 120 may, in response to detecting that the duration of the acquired live broadcast content reaches 1 minute, obtain the recorded live video segment as the first live video segment.

[0045] In some embodiments, before obtaining the first live video segment from the live broadcast content of the live broadcast room, the terminal device 120 may further determine whether the permission to obtain the live video segment of the live broadcast room is enabled. The permission for the live video segment may include, for example, the permission to obtain and push the live video segment of the live broadcast content. If it is determined that the permission to obtain the live video segment of the live broadcast room is enabled, the terminal device 120 may obtain the first live video segment from the live broadcast content of the live broadcast room. Exemplarily, the user 110 may set the permissions of the live broadcast room (the permissions of the live broadcast room may include multiple permissions, and the live video segment permission is included in these multiple permissions) before and / or during the live broadcast. For example, before the live broadcast starts, the user 110 may set the permissions of the live broadcast room by triggering a setting control on the page for object management (such as the commodity management page). During the live broadcast, the user 110 may set the permissions of the live broadcast room by triggering a setting control on the page for object presentation (such as the commodity list page). The terminal device 120 may determine the permissions of the live broadcast room based on the user's settings.

[0046] As Figures 2A to 2D shown, before the live broadcast starts, the terminal device 120 may present Figure 2A the page 200 shown. The page 200 may be, for example, a commodity management page. The page 200 includes a setting control 201. The terminal device 120 may, in response to receiving a trigger operation for the setting control 201, present the page 200 as shown in Figure 2B shown. Figure 2B The page 200 shown in

[0047] presents a setting page 210. The setting page 210 presents multiple entrances for setting the permissions of the live broadcast room. Figure 2C The terminal device 120 may, in response to receiving a trigger operation for the entrance for setting the permission for the live video segment (such as the entrance 211), present the page 200 as shown inFigure 2C On the page 200 shown, there is a page 220 for setting the permissions of the live video clip. The permissions of the live video clip can also include multiple permissions (such as the recording permission for the live video clip, the publishing permission for the live video clip, the playback permission for the live video clip, etc.). The page 220 can provide on / off controls for multiple permissions of the live video clip (for example, including the on / off control 222 for setting the recording permission and the publishing permission for the live video clip). The terminal device 120 can, for example, determine whether the permission to obtain the live video clip of the live broadcast room is enabled in response to receiving a triggering operation on the on / off control 222. For example, the terminal device 120 can determine that the permission to obtain the live video clip of the live broadcast room is enabled in response to receiving an enabling operation on the on / off control 222. The terminal device 120 can then obtain the first live video clip from the live content of the live broadcast room.

[0048] The terminal device 120 can also present a details control in association with at least one of the multiple operation controls, for example. The terminal device 120 can switch to a details description page presenting the details of the permission / operation control corresponding to the details control in response to receiving a triggering operation on the details control. Exemplarily, as Figure 2C shown, the terminal device 120 can present a details control 221 in association with the description information of the on / off control 222 (the description information of each on / off control can, for example, indicate its corresponding permission). The terminal device 120 can switch to presenting Figure 2D the page 200 shown. Figure 2D The page 200 shown includes a details description page 230 of the on / off control 222. The details description page 230 can, for example, present the detailed description information of the on / off control 222 (such as the detailed description information of its corresponding permission).

[0049] After obtaining the first live video segment corresponding to the first object from the live content, the terminal device 120 may determine whether the first live video segment meets the recommendation conditions, and generate the first media content when the first live video segment meets the recommendation conditions. The first media content includes at least the first live video segment. Any user browsing the first media content can access the live room of the user 110 by triggering the viewing entry. In some embodiments, the first media content may further include text content. The text content may be determined, for example, based on the content in the first live video segment and / or the preset text content. In some embodiments, the preset text content may be preset by relevant users (such as the anchor user in the live room, the background staff of the live application, etc.), or automatically determined by the terminal device 120 based on historical data, etc. For example, the preset text content may include the name, topic, etc. preset by the anchor user.

[0050] In some embodiments, the recommendation conditions may include that the relevance between the first live video segment and the first object meets a preset relevance threshold. The preset relevance threshold here may be preset by relevant users (such as the anchor user in the live room, the background staff of the live application, etc.), or automatically determined by the terminal device 120 based on historical data, etc. The terminal device 120 may determine the relevance between the first live video segment and the first object, for example, based on a predetermined rule or with the help of a model. The terminal device 120 may then compare the determined relevance with the preset relevance threshold to determine whether the relevance between the first live video segment and the first object meets the preset relevance threshold. The terminal device 120 may, for example, determine that the relevance between the first live video segment and the first object meets the preset relevance threshold in response to the relevance between the first live video segment and the first object being greater than the preset relevance threshold. The terminal device 120 may then determine that the first live video segment meets the recommendation conditions and generate the first media content based at least on the first live video segment. In this way, media content can be generated based on the live video segment strongly related to the object being explained.

[0051] In some embodiments, the recommendation conditions may further include one or more of the following: the duration of the first live video segment meets a preset duration threshold, the content quality of the first live video segment meets a preset quality threshold, and the number of the published live video segments related to the first object in the live room does not exceed a preset number threshold. Similarly, the preset duration threshold, preset quality threshold, preset number threshold, etc. here may be preset by relevant users (such as the anchor user in the live room, the background staff of the live application, etc.), or automatically determined by the terminal device 120 based on historical data, etc.

[0052] The terminal device 120 can also, for example, determine the content quality of the first live video segment based on a predetermined rule or with the aid of a model. The terminal device 120 can then compare the determined content quality of the first live video segment with a preset quality threshold to determine whether the content quality of the first live video segment meets the preset quality threshold. For example, the terminal device 120 can determine that the content quality of the first live video segment meets the preset quality threshold in response to the content quality of the first live video segment being greater than the preset quality threshold. In this way, media content can be generated based on live video segments with higher explanation quality or value.

[0053] The terminal device 120 can also directly obtain the duration of the first live video segment. For example, the terminal device 120 can compare the duration of the first live video segment with a preset duration threshold to determine whether the duration of the first live video segment is the preset duration threshold. For example, the terminal device 120 can determine that the duration of the first live video segment meets the preset duration threshold in response to the duration of the first live video segment being greater than the preset duration threshold. In this way, media content can be generated based on live video segments with an appropriate explanation duration. In some embodiments, the preset duration threshold can further include a first threshold and a second threshold. The first threshold indicates a lower limit for constraining the duration of the live video segment, and the second threshold indicates an upper limit for constraining the duration of the live video segment. In this case, the terminal device 120 can determine that the duration of the first live video segment meets the preset duration threshold in response to the duration of the first live video segment being between the first threshold and the second threshold (e.g., greater than the first threshold and less than the second threshold). In this way, it is possible to avoid generating media content based on overly long or short video segments, so as not to affect the content quality of the generated media content.

[0054] In some embodiments, the terminal device 120 can also directly determine the number of published live video segments in the live broadcast room that are related to the first object. For example, the recommendation condition can be configured such that for a specific live broadcast room, live video segments related to the same object are allowed to be pushed once or a certain number of times (a preset value). That is, for the same object, one or several media contents are generated. In this way, if one or several live contents including the first object have been generated previously, then it may not be possible to generate the first media content based on the currently obtained first live video segment. Of course, the preset number threshold for the same object can be configured according to actual application needs, and the embodiments of the present disclosure do not limit this.

[0055] In some embodiments, during the live broadcast state of the live broadcast room (i.e., during the live broadcast state of the live broadcast room), the terminal device 120 can further publish the first media content so as to display the first media content in the content recommendation pages of at least one user. In some embodiments, the first media content is published as content associated with the host user of the live broadcast room (such as user 110). For example, the first media content can be published as content created by user 110.

[0056] It should be noted that the above-mentioned first object is any one of the multiple objects corresponding to the live broadcast room. The terminal device 120 can, during the live broadcast state of the live broadcast room, obtain a live video segment associated with any object from the live broadcast content of the live broadcast room, and publish the media content including the live video segment and the viewing entrance corresponding to the live broadcast room to the content recommendation pages of at least one user. In some embodiments, the corresponding media content is published to the content recommendation page only when it is determined that the live video segment meets the corresponding recommendation conditions. Exemplarily, in some embodiments, the terminal device 120 can also obtain a second live video segment from the live broadcast content of the live broadcast room, and the second live video segment includes content related to the second object in the live broadcast content. The terminal device 120 can, for example, generate second media content of the second live video segment in response to determining that the second live video segment meets the recommendation conditions. The terminal device 120 can further publish the second media content to the content recommendation pages of at least one user during the live broadcast state of the live broadcast room. The second media content can also include the viewing entrance corresponding to the live broadcast room for facilitating access to the live broadcast room. The at least one user to whom the second media content is published and the at least one user to whom the first media content is published can include different users. That is, during the live broadcast state of the live broadcast room, the terminal device 120 can obtain live video segments associated with any number of objects and publish the at least one obtained live video segment to the content recommendation pages of different users.

[0057] In some embodiments, in response to detecting that the live broadcast room is in the live broadcast end state (i.e., the live broadcast of the live broadcast room ends), the terminal device 120 can stop publishing the first media content. In this case, the first media content including the first live video segment will not be displayed in the recommendation page of the user. The publishing operation for the first live video segment (i.e., the publishing operation for the first media content) is performed during the live broadcast state of the live broadcast room.

[0058] Regarding the specific manner of determining whether a live broadcast room is in an ended state, in some embodiments, the terminal device 120 may determine that the live broadcast room is in an ended state in response to the stop of the live broadcast room. In some embodiments, the terminal device 120 may also determine whether the live broadcast room is in an ended state based on the attribute value of the first object. The attribute value of the first object here may be, for example, the price of the first object. The terminal device 120 may detect the price of the first object in real time, and determine that the live broadcast room is in an ended state when the current price of the first object is higher than the price of the first object in the first live video segment. It can be understood that the terminal device 120 may also determine whether the live broadcast room is in an ended state through any appropriate strategy, and the present disclosure does not limit the specific determination manner.

[0059] In some embodiments, the terminal device 120 may also present a first media content including the first live video segment on the live content aggregation page of the user 110. As Figure 3A well as Figure 3B shown, the terminal device 120 may also present the user home page of the user 110 (such as page 300A). An entry 301 for the live content aggregation page may be presented on the page 300A. The terminal device 120 may present Figure 3B the page 300B shown in response to detecting a trigger operation for the entry 301. The page 300B is the live content aggregation page of the user 110. At least one media content associated with the live broadcast room of the user 110 (such as media content 310, media content 320, media content 330) may be presented on the page 300B. Each of the at least one media content may include a live video segment associated with a certain object. For example, the page 300B may present a first media content including the first live video segment. After the first media content is published, the host user can always view the published media content from the live content aggregation page regardless of whether the live broadcast room is in a live state or an ended state.

[0060] In the live content aggregation page, the terminal device 120 may, for example, switch to present a browsing page of the media content in response to receiving a trigger operation from the user 110 for a certain media content related to the live content. Exemplarily, the terminal device 120 may switch to present Figure 3C the browsing page 300C of the media content 310 shown in response to receiving a trigger operation for the media content 310. A viewing entry 340 for the object corresponding to the media content 310 may be presented on the browsing page 300C. The terminal device 120 may, for example, switch to present a details page of the object in response to detecting a trigger operation for the viewing entry 340.

[0061] The above describes the provision of live video clips on the side of the host user and related embodiments. Correspondingly, in the embodiments of the present disclosure, for a viewer user (such as user 130), the corresponding terminal device (such as terminal device 140) obtains a first live video clip of the live content in the live room during the live state of the live room. The first live video clip includes the content related to the first object in the live content. The first live video clip may include, for example, a video clip. In some embodiments, the first live video clip may include the explanatory content of the first object in the entire live content. This first live video clip may be sent by a server (such as server 150) to terminal device 140, for example. After terminal device 140 obtains the first live video clip, it presents the first media content in the content recommendation page of user 130. The first media content includes the first live video clip. It can be understood that user 130 here is any one of at least one user to whom the above terminal device 120 is sent. In some embodiments, the first media content is published as content associated with the host user (such as user 110) of the live room. For example, the first media content may be published as content created by user 110.

[0062] The viewing entrance included in the first media content can be any suitable viewing entrance related to the live room. The viewing entrance corresponding to the live room can be used to access the page corresponding to the live room. For example, the viewing entrance included in the first media content can be a specific operation control, the avatar of the host user (such as user 110), and so on. The present disclosure does not limit the specific viewing entrance. Exemplarily, as Figure 4A shown, terminal device 140 can present page 400A to user 130. Page 400A is the content recommendation page of user 130. The first live video clip of the first object and the viewing entrance 401 are presented on page 400A. The avatar 402 of the host user and at least one operation control for the first media content are also presented on page 400A. Both the viewing entrance 401 and the avatar 402 here can be regarded as the viewing entrances for the live room.

[0063] As described above, the terminal device of the host user only publishes the first live video clip to at least one user during the live state of the live room. Therefore, the terminal device (such as terminal device 140) of the viewer user (such as user 130) can only present the first media content in the content recommendation page (such as page 400A) of user 130 during the live state of the live. In this case, terminal device 140 can jump from the content recommendation page (that is, page 400A) to the live page corresponding to the live room in response to detecting a trigger operation on the viewing entrance (viewing entrance 401 and / or avatar 402).

[0064] In some embodiments, the terminal device 140 may directly present the live page in response to the content related to the first object in the live room being live. In other embodiments, the terminal device 140 may also superimpose the object window and / or the details page of the first object on the live page in response to the content related to the first object in the live room not being live. The object window here may include details page entrances of multiple objects, and the multiple objects include at least the first object. For example, Figure 4B As shown, the terminal device 140 can jump from the content recommendation page (i.e., page 400A) to the live broadcast page corresponding to the live broadcast room (i.e., page 400B) in response to the content related to the first object in the live broadcast room not being broadcast live. The terminal device 400B can be superimposed with an object window 410. The object window 410 includes a plurality of detail page entrances of each object (e.g., entrance 411-1, entrance 411-2, entrance 411-3, etc.). The plurality of objects include the first object (e.g., the object corresponding to entrance 411-1).

[0065] In some embodiments, the terminal device 140 may, in response to detecting a trigger operation for a viewing entry in the first media content, present the details page entry (i.e., entry 411-1) corresponding to the first object at the top of the object window of the live page. Alternatively or additionally, in some embodiments, if the live studio is currently explaining any object other than the first object, the terminal device 140 may also present the details page entry corresponding to the currently explained object at the top of the object window of the live page, and present the details page entry corresponding to the first object below the details page entry. For example, if the live studio is currently explaining any object other than the first object, the terminal device 140 may present the details page entry corresponding to the currently explained object in the first position of the object window, and present the details page entry corresponding to the first object in the second position of the object window.

[0066] In some embodiments, in order to allow the user 130 to know the first object conveniently and quickly, the terminal device 140 can also present a preset label (e.g., label 412) at the entrance to the details page of the first object (i.e., entrance 411-1) in the object window. Thus, the user can more easily notice the first object in the object window by specially marking the entrance to the details page of the first object. The label 412 here can always be presented at the entrance to the details page of the first object, or, in response to switching to the live broadcast page, the label 412 is presented at the entrance 411-1, and in response to the presentation time of the label 412 reaching the preset time, the presentation of the label 412 is cancelled.

[0067] In some embodiments, when jumping from the first media content on the content recommendation page to the live broadcast room, the Figure 4BRather than presenting the object window 410 shown, a details page of the first object is presented after switching to the live streaming room. For example, at least a part of the details page can be superimposed and presented on the live streaming room page in a manner similar to the object window 410. In this way, the details content of the first object that the user may be more interested in can be directly presented to the user. In some embodiments, alternatively, when accessing the live streaming room from the first media content on the content recommendation page, only the live streaming room page may be presented to facilitate the user to watch the current live streaming content, without superimposing and presenting object-related information. The user can trigger corresponding interactions on the live streaming room page as needed.

[0068] The presentation of the first media content including the first live video segment on the viewer user side has been discussed above. For the release of different live video segments in the same live streaming room, they can all be presented on the viewer user side in a similar manner and have similar interaction methods.

[0069] In summary, according to the embodiments of the present disclosure, a live video segment corresponding to an explanation object can be automatically generated during the live streaming. The generated live video segment can be used for automatic and real-time distribution to users as needed, which can attract users interested in the live streaming content to join the live streaming room and help improve the access effect of the live streaming room.

[0070] Figure 5 A flowchart of an example process 500 for live video generation according to some embodiments of the present disclosure is shown. The process 500 can be implemented at the terminal device of the host user (such as the terminal device 120). The following refers to Figure 1 Describe the process 500.

[0071] In block 510, if it is detected that the live explanation status of the first object corresponding to the live streaming room is the ongoing explanation status, the terminal device obtains the first live video segment from the live streaming content of the live streaming room, and the first live video segment includes the content related to the first object in the live streaming content.

[0072] In block 520, if the first live video segment meets the recommendation conditions, the terminal device generates the first media content, and the first media content includes at least the first live video segment.

[0073] In some embodiments, the process 500 further includes: during the live streaming state of the live streaming room, publishing the first media content so as to display the first media content in the content recommendation pages of at least one user.

[0074] In some embodiments, the first media content further includes text content, and the text content is determined based on at least one of the following: the content in the first live video segment, the pre-set text content.

[0075] In some embodiments, the recommendation condition includes that the relevance between the first live video segment and the first object meets a preset relevance threshold.

[0076] In some embodiments, the recommendation condition further includes at least one of the following: the duration of the first live video segment meets a preset duration threshold, the content quality of the first live video segment meets a preset quality threshold, and the number of published live video segments related to the first object in the live room does not exceed a preset number threshold.

[0077] In some embodiments, obtaining the first live video segment from the live content of the live room includes: if it is detected that the live explanation state of the first object is the ongoing explanation state, starting to obtain the live content of the live room; and if it is detected that the live explanation state of the first object is the explanation end state or it is detected that the duration of the obtained live content reaches a preset duration, determining the obtained live content as the first live video segment.

[0078] In some embodiments, obtaining the first live video segment from the live content of the live room includes: determining whether the permission to obtain the live video segment of the live room is enabled; and if it is determined that the permission to obtain the live video segment of the live room is enabled, obtaining the first live video segment from the live content of the live room.

[0079] In some embodiments, the first object is any one of multiple objects corresponding to the live room.

[0080] In some embodiments, process 500 further includes: if it is detected that the live room is in the live end state, stopping the publication of the first media content.

[0081] In some embodiments, process 500 further includes: presenting the first media content on the live content aggregation page of the host user in the live room.

[0082] Embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 6 A schematic structural block diagram of a device 600 for live video generation according to some embodiments of the present disclosure is shown. Device 600 can be implemented as or included in a terminal device (such as terminal device 120). Each module / component in device 600 can be implemented by hardware, software, firmware, or any combination thereof.

[0083] As Figure 6As shown, the device 600 includes a video clip acquisition module 610 configured to, if it is detected that the live explanation status of the first object corresponding to the live broadcast room is the ongoing explanation status, acquire a first live video clip from the live content of the live broadcast room, where the first live video clip includes the content related to the first object in the live content. The device 600 further includes a media content generation module 620 configured to, if the first live video clip meets the recommendation conditions, generate first media content, where the first media content at least includes the first live video clip.

[0084] In some embodiments, the device 600 further includes: a media content publishing module configured to, during the period when the live broadcast room is in the live state, publish the first media content so as to display the first media content in the content recommendation pages of at least one user.

[0085] In some embodiments, the first media content further includes text content determined based on at least one of the following: the content in the first live video clip, the pre-set text content.

[0086] In some embodiments, the recommendation conditions include that the relevance between the first live video clip and the first object meets a preset relevance threshold.

[0087] In some embodiments, the recommendation conditions further include at least one of the following: the duration of the first live video clip meets a preset duration threshold, the content quality of the first live video clip meets a preset quality threshold, and the number of the already published live video clips related to the first object in the live broadcast room does not exceed a preset number threshold.

[0088] In some embodiments, the video clip acquisition module 610 is further configured to: if it is detected that the live explanation status of the first object is the ongoing explanation status, start acquiring the live content of the live broadcast room; and if it is detected that the live explanation status of the first object is the end of explanation status or it is detected that the duration of the acquired live content reaches a preset duration, determine the acquired live content as the first live video clip.

[0089] In some embodiments, the video clip acquisition module 610 is further configured to: determine whether the permission to acquire the live video clip of the live broadcast room is enabled; and if it is determined that the permission to acquire the live video clip of the live broadcast room is enabled, acquire the first live video clip from the live content of the live broadcast room.

[0090] In some embodiments, the first object is any one of the multiple objects corresponding to the live broadcast room.

[0091] In some embodiments, the device 600 further includes: a stop publishing module configured to, if it is detected that the live broadcast room is in the live end state, stop publishing the first media content.

[0092] In some embodiments, the apparatus 600 further includes: a content presentation module configured to present first media content in a live content aggregation page of a host user in a live broadcast room.

[0093] The units and / or modules included in the apparatus 600 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to the machine-executable instructions, some or all of the units and / or modules in the apparatus 600 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0094] Figure 7 The block diagram of an electronic device 700 capable of implementing one or more embodiments of the present disclosure is shown. It should be understood that Figure 7 The illustrated electronic device 700 is merely exemplary and should not impose any limitation on the functions and scope of the embodiments described herein. Figure 7 The illustrated electronic device 700 can be used to implement Figure 1 the terminal devices 120, 140 and / or the server 150, or Figure 6 the apparatus 600.

[0095] As Figure 7 shown, the electronic device 700 is in the form of a general-purpose electronic device. The components of the electronic device 700 can include, but are not limited to, one or more processors or processing units 710, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processing unit 710 can be an actual or virtual processor and is capable of performing various processes according to the programs stored in the memory 720. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing ability of the electronic device 700.

[0096] The electronic device 700 generally includes multiple computer storage media. Such media can be any available media accessible to the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 can be volatile memory (such as registers, caches, random access memory (RAM)), non-volatile memory (such as read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 can be removable or non-removable media and can include machine-readable media, such as a flash drive, a magnetic disk, or any other media that can be capable of storing information and / or data and can be accessed within the electronic device 700.

[0097] The electronic device 700 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in Figure 7 it, a disk drive for reading from or writing to a removable, non-volatile magnetic disk (such as a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk can be provided. In these cases, each drive can be connected to a bus (not shown) by one or more data media interfaces. The memory 720 can include a computer program product 725 having one or more program modules that are configured to perform the various methods or actions of the various embodiments of the present disclosure.

[0098] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented by a single computing cluster or multiple computer machines that are capable of communicating via a communication connection. Thus, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, network personal computers (PCs), or another network node.

[0099] The input device 750 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 760 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 can also communicate with one or more external devices (not shown) as needed via the communication unit 740, external devices such as storage devices, display devices, etc., communicate with one or more devices that enable a user to interact with the electronic device 700, or communicate with any device that enables the electronic device 700 to communicate with one or more other electronic devices (such as a network card, a modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0100] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, and the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is further provided, the computer program product being tangibly stored on a non-transitory computer-readable medium and including computer-executable instructions, and the computer-executable instructions being executed by a processor to implement the method described above.

[0101] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0102] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is produced that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause a computer, a programmable data processing device, and / or other devices to work in a specific manner. Thus, the computer-readable medium storing the instructions includes a manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0103] The computer-readable program instructions can be loaded onto a computer, other programmable data processing device, or other device, such that a series of operational steps are performed on the computer, other programmable data processing device, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing device, or other device implement the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0105] The implementations of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The choice of terms used herein is intended to best explain the principles of the implementations, the practical application, or the improvement of the technology in the market, or to enable other ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A method for live video generation, comprising: If it is detected that the live explanation status of the first object corresponding to the live broadcast room is the ongoing explanation status, obtain a first live video segment from the live content of the live broadcast room, where the first live video segment includes the content related to the first object in the live content; and If the first live video segment meets the recommendation conditions, generate first media content, where the first media content at least includes the first live video segment.

2. The method according to claim 1, further comprising: During the period when the live broadcast room is in the live state, publish the first media content so as to display the first media content in the content recommendation pages of at least one user, where the first media content further includes a viewing entry corresponding to the live broadcast room.

3. The method according to claim 1, where the first media content further includes text content, and the text content is determined based on at least one of the following: the content in the first live video segment, and the pre-set text content.

4. The method according to claim 1, where the recommendation conditions include that the relevance between the first live video segment and the first object meets a preset relevance threshold; where the recommendation conditions further include at least one of the following: The duration of the first live video segment meets a preset duration threshold, The content quality of the first live video segment meets a preset quality threshold, The number of the already published live video segments related to the first object in the live broadcast room does not exceed a preset number threshold.

5. The method according to claim 1, where obtaining the first live video segment from the live content of the live broadcast room comprising: If it is detected that the live explanation status of the first object is the ongoing explanation status, start obtaining the live content of the live broadcast room; and If it is detected that the live explanation status of the first object is the end of explanation status or it is detected that the duration of the obtained live content reaches a preset duration, determine the obtained live content as the first live video segment.

6. The method according to claim 1, where obtaining the first live video segment from the live content of the live broadcast room comprising: Determine whether the permission to obtain the live video segment of the live broadcast room is enabled; and If it is determined that the permission to obtain the live video segment of the live broadcast room is enabled, obtain the first live video segment from the live content of the live broadcast room.

7. The method according to claim 1, where the first object is any one of the multiple objects corresponding to the live broadcast room; and / or where the method further comprising: Present the first media content in the live content aggregation page of the host user of the live broadcast room.

8. The method according to claim 2, further comprising: If it is detected that the live broadcast room is in the live end state, stop publishing the first media content.

9. An apparatus for live video generation, comprising: A video clip acquisition module, configured to, if it is detected that the live explanation state of the first object corresponding to the live broadcast room is the live explanation state, acquire a first live video clip from the live content of the live broadcast room, where the first live video clip includes content related to the first object in the live content; and A media content generation module, configured to, if the first live video clip meets the recommendation conditions, generate first media content, where the first media content at least includes the first live video clip.

10. An electronic device, comprising: At least one processing unit; and At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, having stored thereon a computer program, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8.

Images