Video stream playback control method, device and storage medium

Abstract

An embodiment of the present application provides a video stream playback control method, device, apparatus, and storage medium. The method includes the steps of: stopping playback of a first video stream when a man-machine interaction entrance invocation trigger condition is met, and invoking a man-machine interaction entrance for the first video stream while displaying the playback screen of the first video stream; and obtaining target feedback information through the man-machine interaction entrance or closing the man-machine interaction entrance after receiving a command to close the man-machine interaction entrance and playing a second video stream different from the first video stream, where the target feedback information includes feedback information for the first video stream. According to the method, by invoking the man-machine interaction entrance for the first video stream while displaying the playback screen of the first video stream to obtain feedback information, it is possible to obtain more accurately tailored feedback for the user's currently playing the first video stream.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims priority to a Chinese patent application bearing application number 202010287736.7, filed on April 13, 2020, for the invention entitled "Video stream playback control method, device, and storage medium," the entire contents of which are incorporated herein by reference. The embodiments of the present application relate to the technical field of video stream playback control, and in particular to a video stream playback control processing method, device, and storage medium. [Background technology]

[0002] With the development of Internet technology, video stream playback applications executed on terminal devices are widely used. In the prior art, it is common to collect feedback information, such as satisfaction level, from users on video streams based on whether or not the users have watched a video in its entirety. However, such feedback information is relatively low in accuracy, and such feedback information is not fully utilized in the prior art. Summary of the Invention [Problem to be solved by the invention]

[0003] The embodiments of the present application further provide a video stream playback control method, device, and storage medium, so as to achieve the objective of accurately obtaining a user's feedback on the played video stream in a targeted manner, and to avoid the man-machine interface from interrupting the playing video stream, thereby affecting the video playback effect. [Means for solving the problem]

[0004] In a first aspect, an embodiment of the present application comprises: stopping playback of the first video stream when a man-machine interaction entrance call trigger condition is satisfied, and calling a man-machine interaction entrance for the first video stream while displaying a playback screen of the first video stream; and after obtaining target feedback information through the man-machine interaction entrance or receiving a command to close the man-machine interaction entrance, closing the man-machine interaction entrance and playing a second video stream different from the first video stream, wherein the target feedback information includes feedback information for the first video stream.

[0005] According to the method provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user's feedback for the currently played first video stream can be obtained more accurately and according to the goal. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is paused (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the playing video stream, since the playback of the first video stream is stopped in this process. In addition, the playback screen of the stopped first video stream in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0006] The implementation of selectively playing a second video stream different from the first video stream may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information or an instruction to close the man-machine interaction entrance.

[0007] According to the method provided by the embodiment of the present application, the video stream continues to be played in response to obtaining target feedback information or a command to close the man-machine interaction entrance, i.e., after the user inputs feedback information or closes the man-machine interaction entrance, the application automatically continues to play the second video stream, thereby realizing a seamless transition between the man-machine interaction process and the automatic continuous playback operation, and improving the smoothness of video playback.

[0008] According to any of the above method embodiments, the second video stream to be played and / or the at least one video stream to be subsequently played are determined in response to target feedback information.

[0009] According to the method provided by the embodiment of the present application, a video stream is recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entry point for obtaining the user's interest level in the first video stream, the target feedback information can generally accurately reflect the user's interest level in the first video stream, so recommending the video stream in real time based on the target feedback information can further improve the accuracy of video recommendation.

[0010] In addition, according to the method provided by the embodiment of the present application, in order to be able to recommend a video stream in real time based on the target feedback information, it may be necessary to obtain more abundant feedback contents, for example, by setting multiple feedback questions or setting multiple options for one feedback question, which requires occupying a relatively larger display area.As described above, according to the method provided by the embodiment of the present application, when a man-machine interaction entrance is called, the playback of the video stream is paused, so that when the man-machine interaction entrance is a man-machine interface, even if a relatively large man-machine interface is displayed, it will not block the video stream being played and affect the playback effect of the video stream.

[0011] According to any of the above method embodiments, the man-machine interaction entrance call trigger condition is: receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a repeated playback number threshold; and The first video stream has been played; and a particular target object is detected during playback of the first video stream; and The first video stream may be played up to the particular time node.

[0012] In practical application, the method provided by the embodiment of the present application supports flexibly configuring the man-machine interaction entrance call trigger conditions to meet product requirements.

[0013] In one embodiment, the terminal device can configure the reception of a video stream switching command as a trigger condition for calling a man-machine interaction entrance, and upon receiving the video stream switching command, call the man-machine interaction entrance in response to the command. Such an implementation of calling the man-machine interaction entrance does not interrupt the first video stream being played, and can reduce interference with the video stream playback.

[0014] In one embodiment, the terminal device can configure the completion of the first video stream playback as a trigger condition for calling a man-machine interaction entrance, and when the first video stream playback is completed, call the man-machine interaction entrance. This implementation of calling the man-machine interaction entrance does not interrupt the first video stream being played, and can reduce interference with the video stream playback.

[0015] Taking a short video playback application as an example, in a non-automatic playback mode, a general video stream playback control process is configured to repeatedly play a current video stream when a video stream switching command is not detected, and to switch to a next video stream when a video stream switching command is detected. In a scene where a current video stream is repeatedly played when there is no video stream switching command, the repeated playback of the current video stream does not mean that the user is more interested in the content of the video stream, but may be caused by the user switching the video stream due to a change of interest or forgetting to close it. In such a case, in one embodiment, the terminal device may configure the number of repeated playbacks of a first video stream reaching a repeated playback count threshold as a man-machine interaction entry trigger condition, and when the number of repeated playbacks of the first video stream reaches the repeated playback count threshold, the terminal device may call up a man-machine interaction entry to request feedback information on the video stream from the user, which not only improves the accuracy of the feedback information but also contributes to the accuracy of the use of the feedback information in the future, for example, improves the accuracy of the user recommending a video stream based on the feedback information.

[0016] In a second aspect, the present application provides an embodiment comprising: a first playback control module configured to stop playback of the first video stream and call a man-machine interaction entrance for the first video stream while displaying a playback screen of the first video stream when a man-machine interaction entrance call trigger condition is satisfied; and a second playback control module configured to obtain target feedback information through the man-machine interaction entrance or to close the man-machine interaction entrance and play a second video stream different from the first video stream after receiving a command to close the man-machine interaction entrance, where the target feedback information includes feedback information for the first video stream.

[0017] According to the terminal device provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user can obtain feedback for the first video stream currently being played more accurately and according to the goal. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is paused (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the playing video stream, since the playback of the first video stream is stopped in this process. In addition, the playback screen of the first video stream stopped in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0018] Optionally, the second playback control module may play a second video stream different from the first video stream, in one implementation, comprising: The method may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information or the command to close the man-machine interaction portal.

[0019] According to the terminal device provided by the embodiment of the present application, the video stream continues to be played in response to obtaining target feedback information or a command to close the man-machine interaction entrance, that is, after the user inputs feedback information or closes the man-machine interaction entrance, the application automatically continues to play the second video stream without the user needing to manually trigger it, thereby realizing a seamless transition between the man-machine interaction process and the automatic continuous playback operation, and improving the smoothness of video playback.

[0020] According to any of the above terminal device embodiments, the second video stream to be played and / or the at least one video stream to be played later is determined in response to target feedback information.

[0021] According to the terminal device provided by the embodiment of the present application, the video stream is recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information generally reflects the user's interest level in the first video stream accurately, so that the video stream is recommended in real time based on the target feedback information, and the accuracy of video recommendation can be further improved.

[0022] In addition, in order to enable the terminal device provided by the embodiment of the present application to recommend a video stream in real time based on the target feedback information, it may be necessary to obtain more abundant feedback contents, for example, by setting multiple feedback questions or setting multiple options for one feedback question, which requires occupying a relatively larger display area.As described above, in the terminal device provided by the embodiment of the present application, when a man-machine interaction entrance is called, the playback of the video stream is paused, so that when the man-machine interaction entrance is a man-machine interface, even if a relatively large man-machine interface is displayed, it will not block the video stream being played and affect the playback effect of the video stream.

[0023] According to any of the above terminal device embodiments, the man-machine interaction entrance call trigger condition is: receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a repeated playback number threshold; and The first video stream has been played; and a particular target object is detected during playback of the first video stream; and The first video stream may be played up to the particular time node.

[0024] In practical application, the terminal device provided by the embodiment of the present application can support flexibly configuring the man-machine interaction entrance call trigger conditions to meet product requirements.

[0025] In one embodiment, the terminal device can configure the reception of a video stream switching command as a man-machine interaction entrance trigger condition, and upon receiving the video stream switching command, call the man-machine interaction entrance in response to the command. Such an implementation of calling the man-machine interaction entrance does not interrupt the first video stream being played, and can reduce interference with the video stream playback.

[0026] In one embodiment, the terminal device can configure the completion of the first video stream playback as a man-machine interaction entrance trigger condition, and when the first video stream playback is completed, call the man-machine interaction entrance. This implementation of calling the man-machine interaction entrance does not interrupt the first video stream being played, and can reduce interference with the video stream playback.

[0027] Taking a short video playback application as an example, in a non-automatic playback mode, a general video stream playback control process is configured to repeatedly play a current video stream when a video stream switching command is not detected, and to switch to a next video stream when a video stream switching command is detected. In a scene where a current video stream is repeatedly played when there is no video stream switching command, the repeated playback of the current video stream does not mean that the user is more interested in the content of the video stream, but may be caused by the user switching the video stream due to a change of interest or forgetting to close it. In such a case, in one embodiment, the terminal device may configure the number of repeated playbacks of a first video stream reaching a repeated playback count threshold as a man-machine interaction entry trigger condition, and when the number of repeated playbacks of the first video stream reaches the repeated playback count threshold, the terminal device may call up a man-machine interaction entry to request feedback information on the video stream from the user, which not only improves the accuracy of the feedback information but also contributes to the accuracy of the use of the feedback information in the future, for example, improves the accuracy of the user recommending a video stream based on the feedback information.

[0028] In a third aspect, the present application provides an embodiment comprising: There is provided an electronic device comprising: a memory for storing a program for performing the method according to each method embodiment of the first aspect; and a processor arranged to execute the program stored in the memory.

[0029] According to the electronic device provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user can obtain feedback for the first video stream currently being played more accurately and according to the goal. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is paused (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback of the first video stream is stopped in this process, so that the playback effect is not affected by blocking the video stream being played. In addition, the playback screen of the first video stream stopped in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0030] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a program for executing the method according to each embodiment of the first aspect.

[0031] According to the program stored in the computer-readable storage medium provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user's feedback for the currently played first video stream can be obtained more accurately and according to the goal. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is paused (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the playing video stream, since the playback of the first video stream is stopped in this process. In addition, the playback screen of the stopped first video stream in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0032] The embodiments of the present application provide a video stream playback control method, device and storage medium to achieve the objective of recommending a video stream in real time according to target feedback information.

[0033] In a fifth aspect, the present application provides an embodiment comprising: calling a man-machine interaction entrance for the first video stream currently being played when a man-machine interaction entrance calling trigger condition is satisfied, and obtaining target feedback information through the man-machine interaction entrance, the target feedback information including feedback information for the first video stream; and after obtaining the target feedback information, playing a second video stream different from the first video stream, wherein the second video stream to be played and / or at least one video stream to be subsequently played are determined according to the target feedback information.

[0034] According to the method provided by the embodiment of the present application, it is possible to obtain target feedback information accurately according to the target, and recommend video streams in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video streams can be recommended according to the target feedback information when the video streams are continuously played, thereby improving the real-timeness of video recommendation and user experience. In the case of a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information generally accurately reflects the user's interest level in the first video stream, so that the video streams can be recommended in real time based on the target feedback information, thereby further improving the accuracy of video recommendation.

[0035] Optionally, an implementation of playing a second video stream different from the first video stream after obtaining the target feedback information may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information.

[0036] According to the method provided by the embodiment of the present application, the second video stream is automatically played in response to obtaining the target feedback information, so as to realize a seamless transition between the man-machine interaction process and the automatic video stream playing operation, and improve the smoothness of the video playing. Moreover, when the second video stream is determined according to the target feedback information, the embodiment of the present application further responds quickly to the user's feedback, so as to further improve the user's usage experience.

[0037] Optionally, according to the method provided by the embodiment of the present application, when the man-machine interaction entrance calling trigger condition is met, the method further includes stopping the playback of the first video stream, and invoking the man-machine interaction entrance in response to this may include the steps of: calling the man-machine interaction entrance while displaying the playback screen of the first video stream; and after receiving a command to close the man-machine interaction entrance, closing the man-machine interaction entrance and playing the second video stream.

[0038] According to the method provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user's feedback for the currently played first video stream can be obtained more accurately and according to the goal. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the playing video stream, since the playback of the first video stream is stopped in this process. In addition, the playback screen of the stopped first video stream in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0039] In a sixth aspect, the present application provides an embodiment comprising: a man-machine interaction entrance calling module configured to call a man-machine interaction entrance for a first video stream currently being played when a man-machine interaction entrance calling trigger condition is satisfied, and obtain target feedback information through the man-machine interface, the target feedback information including feedback information for the first video stream; The present invention provides a terminal device comprising: a video stream playback module configured to play a second video stream different from the first video stream after obtaining target feedback information, wherein the second video stream to be played and / or at least one video stream to be subsequently played are determined depending on the target feedback information.

[0040] According to the terminal device provided by the embodiment of the present application, it is possible to obtain the target feedback information accurately according to the target, and recommend the video stream in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and the user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information can generally accurately reflect the user's interest level in the first video stream, so that the video stream can be recommended in real time based on the target feedback information, thereby further improving the accuracy of video recommendation.

[0041] Optionally, an implementation in which the video playback module plays a second video stream different from the first video stream after obtaining the target feedback information may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information.

[0042] The terminal device provided by the embodiment of the present application automatically plays the second video stream in response to obtaining the target feedback information, thereby realizing a seamless transition between the man-machine interaction process and the automatic video stream playback operation, and improving the smoothness of video playback. In addition, when the second video stream is determined according to the target feedback information, the embodiment of the present application further responds quickly to the user's feedback, thereby further improving the user's usage experience.

[0043] Optionally, when a man-machine interaction entrance calling trigger condition is met, the video stream playing module further stops playing the first video stream, and in response, the implementation of the man-machine interaction entrance calling module calling the man-machine interaction entrance may include calling the man-machine interaction entrance while displaying the playback screen of the first video stream. Note that, after the man-machine interaction entrance calling module receives a command to close the man-machine interaction entrance, it closes the man-machine interaction entrance, and the video stream playing module plays a second video stream, and the target feedback information includes feedback information for the first video stream.

[0044] According to the terminal device provided by the embodiment of the present application, in the process of calling a man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and after closing the man-machine interaction entrance, the video stream is automatically continued to be played (i.e., the second video stream is played), so that even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback of the first video stream is stopped during this process, so that the playback effect is not affected by blocking the video stream being played. In addition, during the process of stopping and continuing the playback of the first video stream, the playback screen of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display manner is intuitive and simple.

[0045] In a seventh aspect, the present application provides an embodiment comprising: There is further provided an electronic device comprising: a memory for storing a program for performing the method according to each method embodiment of the fifth aspect; and a processor arranged to execute the program stored in the memory.

[0046] According to the electronic device provided by the embodiment of the present application, it is possible to obtain target feedback information accurately according to the target, and recommend a video stream in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information can generally accurately reflect the user's interest level in the first video stream, so that the video stream can be recommended in real time based on the target feedback information, thereby further improving the accuracy of video recommendation.

[0047] In an eighth aspect, an embodiment of the present application further provides a computer-readable storage medium having stored thereon a program for carrying out the method according to any of the embodiments of the fifth aspect. Effect of the Invention

[0048] According to the program stored in the computer-readable storage medium provided by the embodiment of the present application, it is possible to obtain the target feedback information accurately according to the target, and recommend the video stream in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and the user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information can generally accurately reflect the user's interest level in the first video stream, so that the video stream can be recommended in real time based on the target feedback information, thereby further improving the accuracy of video recommendation. [Brief description of the drawings]

[0049] [Figure 1] 4 is a flowchart of a video stream playback control method provided by an embodiment of the present application; [Diagram 2] FIG. 2 is a display schematic diagram of a man-machine interface and a video stream playback window interface provided by an embodiment of the present application; [Figure 3A] FIG. 2 is a display schematic diagram of a man-machine interface and a video stream playback window interface provided by another embodiment of the present application; [Figure 3B] FIG. 11 is a schematic diagram of a video stream playback window interface with the display scale restored according to another embodiment of the present application; [Figure 4] 4 is a flowchart of a video stream playback control method provided by another embodiment of the present application; [Diagram 5] FIG. 2 is a block diagram of a terminal device provided according to an embodiment of the present application; [Figure 6] FIG. 2 is a block diagram of a terminal device provided according to another embodiment of the present application; [Figure 7] FIG. 1 is a schematic diagram illustrating the configuration of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0050] In order to better understand the above technical means, the technical means of the embodiments of the present application are described in detail below with reference to the drawings and specific examples, so that it can be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical means of the embodiments of the present application, and do not limit the technical means of the present application. The embodiments of the present application and the technical features in the embodiments may be combined with each other when there is no contradiction.

[0051] The embodiment of the present application provides a video stream playback control method applied to video playback scenes in which video data is distributed in a streaming manner, including, but not limited to, short video playback scenes, long video playback scenes, and live video distribution scenes. In the embodiment of the present application, the video stream includes video data transmitted in a streaming manner, and the video stream division method is not limited in the embodiment of the present application, and the first video stream, the second video stream, etc. are distinguished by defining the video stream division method according to the product requirements in actual applications. For example, when playing a video file of a certain length (including short video playback or other types of video playback), one video file may be defined as one video stream, one video file may be divided into several video segments in a predetermined manner (for example, a movie video may be divided into several video segments according to the progress of the plot), and each video segment may be one video stream, and in the case of live video distribution, the entire video playback process may be divided into several video segments according to the live distribution content or time, and each video segment may be one video stream. Examples include, but are not limited to, the following.

[0052] The video playback control method provided by the embodiment of the present application can be realized by a terminal device implementing a browser or a video stream playback application, and includes the following steps 101, 102, 103 and 104, as shown in FIG. 1.

[0053] In step 101, if a man-machine interaction entrance call trigger condition is met, the playback of the first video stream is stopped.

[0054] In step 102, a man-machine interaction entrance is called while displaying the playback screen of the first video stream.

[0055] As described above, the calling of the man-machine interaction entrance is executed when the man-machine interaction entrance calling trigger condition is satisfied. However, in the embodiment of the present application, the time order between the stopping of playback of the first video stream and the calling of the man-machine interaction entrance is not limited, and in actual application, the user generally cannot be aware of the time order relationship between the stopping of playback of the first video stream and the calling of the man-machine interaction entrance.

[0056] Here, the man-machine interaction inlet includes, but is not limited to, at least one of a man-machine interface and a man-machine interaction voice module, which has at least a voice playback function and a voice collection function, and further includes a voice recognition function or a function of transmitting the collected voice signal and obtaining the voice recognition result.

[0057] In practical application, the trigger conditions for calling the man-machine interaction entrance can be flexibly configured according to product requirements.

[0058] In step 103, after obtaining target feedback information through the man-machine interaction entrance or receiving a command to close the man-machine interaction entrance, the man-machine interaction entrance is closed.

[0059] In step 104, a second video stream different from the first video stream is played, and the target feedback information includes feedback information for the first video stream.

[0060] As described above, playing the second video stream is executed after obtaining target feedback information through the man-machine interaction entrance or receiving a command to close the man-machine interaction entrance, but in the embodiment of the present application, the time order of playing the second video stream and closing the man-machine interaction entrance is not limited, and in actual application, the user generally cannot be aware of the time order relationship between playing the second video stream and closing the man-machine interaction entrance.

[0061] Here, if the man-machine interaction entry is a man-machine interface, in an implementation form in which the man-machine interaction entry is called while displaying the playback screen of the first video stream, the man-machine interface 202 may be displayed overlapping the video stream playback window interface 201 as shown in Fig. 2, or the video stream playback window interface 201 may be compressed (equal or non-equal ratio compression) and displayed in the first display area 301, and the man-machine interface 202 may be displayed in the second display area 302, and the display area of ​​the terminal device may include the first display area 301 and the second display area 302, but is not limited thereto. The playback screen of the first video stream (not shown) is displayed in the above-mentioned video stream playback window interface of the browser or application, and is therefore compressed by compressing the video stream playback window interface 201.

[0062] Here, if the video stream playback window interface is compressed and displayed while the man-machine interface is continuously displayed, as shown in FIG. 3B, the display scale of the video stream playback window interface 201 is restored when the second video stream is played, that is, the display scale of the playback screen (not shown) of the second video stream is restored.

[0063] Here, the second video stream may be automatically played immediately after obtaining the target feedback information or receiving a command to close the man-machine interaction entrance, or the second video stream may be played in response to a video stream playback command after obtaining the target feedback information or receiving a command to close the man-machine interaction entrance.

[0064] According to the method provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, thereby making it possible to obtain feedback for the first video stream currently being played by the user more accurately and according to the goal; furthermore, in the process of calling the man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and the man-machine interaction entrance is closed and then the video stream continues to be played (i.e., the second video stream is played). Therefore, even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback of the first video stream is stopped during this process, so that the playback effect is not affected by blocking the video stream being played. In addition, the playback screen of the first video stream that is stopped during the first video stream playback stop duration process is still displayed, which can indicate that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple. Furthermore, this means that the playback window does not need to be closed or skipped. Therefore, when playing the second video stream, there is no need to open or skip the playback window to display the second video stream, and the smoothness of the video stream playback is ensured.

[0065] In practical application, there are various implementation forms of obtaining target feedback information through man-machine interaction entry. In one implementation form, the man-machine interaction entry includes a man-machine interface, which displays feedback request information for the first video stream, and further displays a target feedback information input control, and obtains target feedback information through the target feedback information input control, which can be a text box control, a selection control, a voice signal collection control, an image collection control, etc.

[0066] In the embodiment of the present application, the specific content and expression format of the feedback request information are not limited. The expression format of the feedback request information may include graphic control, text control, selection control, etc. The content of the target feedback information may include, but is not limited to, requesting to rate the first video stream, asking whether the first video stream is interesting, checking the smoothness of the playback of the first video stream, checking the playback screen quality of the first video stream, etc., and the present disclosure is not limited thereto.

[0067] In practical application, after the terminal calls the man-machine interaction entrance, the user can also refuse to input the target feedback information. For example, the terminal device generates a command to close the man-machine interaction entrance in response to the user's action when the user refuses to input the target feedback information, and the video stream playback browser or application closes the man-machine interaction entrance in response to the command, but this is not limited thereto. Taking the above-mentioned man-machine interaction entrance as an example including a man-machine interface, in one implementation form, feedback request information for the first video stream is displayed on the man-machine interface, and further a control for instructing to close the interface and a control for instructing to ignore the feedback request information are displayed. When a user performs an operation to trigger the control for instructing to close the interface or an operation to trigger the control for instructing to ignore the feedback request information, the trigger operation becomes a command to close the man-machine interaction entrance, or the terminal device generates a command to close the man-machine interaction entrance in response to the trigger operation, and the video stream playback browser or application closes the man-machine interface in response to the command. For example, in a case where the man-machine interaction entrance includes a man-machine interface, in another implementation form, feedback request information for the first video stream is displayed on the man-machine interface, and the video stream playback browser or application further collects facial images and / or gesture images of the user through an image collection module of the terminal device, and when the user makes a facial expression, wink or gesture instructing to close the interface, or a facial expression, wink or gesture instructing to ignore the feedback request information, the operation becomes a command to close the man-machine interaction entrance, or the terminal device generates a command to close the man-machine interaction entrance in response to the operation, and the video stream playback browser or application closes the man-machine interface in response to the command.For example, the above-mentioned man-machine interaction entrance includes a man-machine interface. In another implementation form, the man-machine interface displays feedback request information for the first video stream, and the video stream playback browser or application can further collect the user's voice signal through a voice collection module of the terminal device, and recognize the voice signal to obtain a voice recognition result. If the voice recognition result instructs to close the man-machine interaction entrance or instructs to ignore the feedback request information, the voice recognition result becomes an instruction to close the man-machine interaction entrance, or the terminal device generates an instruction to close the man-machine interaction entrance in response to the voice recognition result, and the video stream playback browser or application closes the man-machine interface in response to the instruction. For example, taking the man-machine interaction entrance as including an audio man-machine interaction audio module, in one implementation form, after being called, the man-machine interaction audio module plays feedback request information for the first video stream in the form of audio, and collects the user's voice signal, thereby recognizing the voice signal to obtain a voice recognition result, and if the voice recognition result instructs to close the man-machine interaction entrance or instructs to ignore the feedback request information, the voice recognition result becomes an instruction to close the man-machine interaction entrance, or the terminal device generates an instruction to close the man-machine interaction entrance in response to the voice recognition result, and the video stream playback browser or application closes the man-machine interaction entrance in response to the instruction.For example, in another implementation, the man-machine interaction entrance includes an audio man-machine interaction audio module, after being called, the man-machine interaction audio module plays feedback request information for the first video stream in the form of audio, and the video stream playback browser or application further collects facial images and / or gesture images of the user through an image collection module of the terminal device, and when the user makes an expression, wink or gesture instructing to close the interface, or an expression, wink or gesture instructing to ignore the feedback request information, the operation becomes an instruction to close the man-machine interaction entrance, or the terminal device generates an instruction to close the man-machine interaction entrance in response to the action, and the video stream playback browser or application closes the man-machine interaction entrance in response to the instruction.

[0068] After the user inputs and submits the target feedback information, the terminal device can obtain the target feedback information through the man-machine interaction entrance, in which case the action of obtaining the target feedback information can be regarded as an instruction to close the man-machine interaction entrance, or the terminal device generates an instruction to close the man-machine interaction entrance in response to the action, and the video stream playback browser or application closes the man-machine interaction entrance in response to the instruction.

[0069] A waiting time can be set so as not to affect the video stream playback when the user does not input the target feedback information or refuses to input the target feedback information, and when the waiting time is over, the man-machine interaction entrance is closed and the video stream continues to be played. In this case, the passing of the waiting time may be regarded as a command to close the man-machine interaction entrance, or the terminal device generates a command to close the man-machine interaction entrance in response to the passing of the waiting time, and the video stream playback browser or application closes the man-machine interaction entrance in response to the command.

[0070] As mentioned above, the implementation of playing a second video stream different from the first video stream may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information or an instruction to close the man-machine interaction entrance.

[0071] According to the method provided by the embodiment of the present application, the video stream continues to be played in response to obtaining target feedback information or a command to close the man-machine interaction entrance, i.e., after the user inputs and submits the target feedback information or closes the man-machine interaction entrance, the application automatically plays the second video stream, thereby realizing a seamless transition between the man-machine interaction process and the automatic continuous playback operation, and improving the smoothness of video playback.

[0072] According to any of the above method embodiments, the second video stream to be played and / or the at least one video stream to be subsequently played are determined in response to target feedback information.

[0073] In one implementation, the terminal device determines the second video stream to be played and / or at least one video stream to be played later according to the target feedback information. Meanwhile, according to the method provided by the embodiment of the present application, the target feedback information may be further input into a pre-trained video stream recommendation model, and the second video stream to be played and / or at least one video stream to be played later may be determined according to the output of the video stream recommendation model, and the terminal device plays the determined second video stream to be played and / or at least one video stream to be played later after obtaining the target feedback information through the man-machine interaction portal or receiving a command to close the man-machine interaction portal. In another implementation form, the terminal device transmits the acquired target feedback information to the network device in real time, and the network device or another terminal device (which transfers the target feedback information to the terminal device in real time) determines the second video stream to be played and / or at least one video stream to be played later, and transmits the determined result to the terminal device in real time, and the terminal device obtains the target feedback information through the man-machine interaction entrance or plays the determined second video stream to be played and / or at least one video stream to be played later after receiving a command to close the man-machine interaction entrance.

[0074] In one implementation, the video stream to be played is kept according to the video stream sequence, and the video stream to be played in the video stream sequence is preloaded, thus the terminal device can add the acquired video stream to be played to the video stream sequence after obtaining the video stream to be played (including the second video stream and / or at least one video stream to be played later) determined by the target feedback information, specifically, the terminal device can add the acquired video stream to be played to the front of the video stream sequence to play the video stream preferentially. In another implementation, the terminal device does not need to keep the video stream to be played according to the video stream sequence, and thus does not need to preload the video stream to be played, and the video stream to be played is determined and loaded in real time, thus the terminal device loads and plays the video stream in real time after obtaining the video stream to be played determined by the target feedback information.

[0075] According to the method provided by the embodiment of the present application, a video stream is recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entry point for obtaining the user's interest level in the first video stream, the target feedback information can generally accurately reflect the user's interest level in the first video stream, so recommending the video stream in real time based on the target feedback information can further improve the accuracy of video recommendation.

[0076] In addition, according to the method provided by the embodiment of the present application, in order to be able to recommend a video stream in real time based on the target feedback information, it may be necessary to obtain more abundant feedback contents, for example, multiple feedback questions may be set, or multiple options may be set for one feedback question, so that a relatively larger display area needs to be occupied.As mentioned above, according to the method provided by the embodiment of the present application, when a man-machine interaction entrance is called, the playback of the video stream is stopped, so that when the man-machine interaction entrance is a man-machine interface, even if a relatively large man-machine interface is displayed, it will not block the video stream being played and affect the playback effect of the video stream.

[0077] According to any of the above method embodiments, the man-machine interaction entrance call trigger condition is: receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a repeated playback number threshold; and The first video stream has been played; and a particular target object is detected during playback of the first video stream; and The first video stream may be played up to the particular time node.

[0078] In practical application, the method provided by the embodiment of the present application supports flexibly configuring the man-machine interaction entrance call trigger conditions to meet product requirements.

[0079] In one embodiment, receiving a video stream switching command may be configured as a trigger condition for invoking a man-machine interaction entrance. When the terminal device receives the video stream switching command, the terminal device will call the man-machine interaction entrance in response to the command. This implementation of invoking the man-machine interaction entrance not only does not interrupt the first video stream being played, but also reduces the disruption to the video stream playback. Wherein, the video stream switching command may include, but is not limited to, a touch control gesture to instruct the video stream to be switched, a voice command to instruct the video stream to be switched, or a facial feature to instruct the video stream to be switched.

[0080] In one embodiment, the completion of the first video stream playback may be configured as the trigger condition for calling the man-machine interaction entrance. When the first video stream playback is completed, the terminal device calls the man-machine interaction entrance. This implementation of calling the man-machine interaction entrance not only does not interrupt the first video stream being played, but also reduces the interference with the video stream playback. In practical applications, the condition for the completion of the first video stream playback can be defined as required. Taking short video playback as an example, the playback control logic may define the completion of first video stream playback as the completion of the first playback of the first video stream in a non-automatic playback mode when no switching command or other playback stop command (e.g., an interface skip command) is received and the terminal device automatically repeats playing the current video when the first playback of the first video stream is completed; and may define the completion of first video stream playback as the completion of the current playback of the first video stream in an automatic playback mode when no switching command or other playback stop command (e.g., an interface skip command) is received and the terminal device automatically plays the next video when the current playback of the first video stream is completed.

[0081] Taking a short video playback application as an example, in a non-automatic playback mode, a general video stream playback control process is configured to repeatedly play a current video stream when a video stream switching command is not detected, and to switch to a next video stream when a video stream switching command is detected. In a scene where a current video stream is repeatedly played when there is no video stream switching command, the repeated playback of the current video stream does not mean that the user is more interested in the content of the video stream, but may be caused by the user switching the video stream due to a change of interest or forgetting to close it. In this case, the man-machine interaction entrance trigger condition may further be set as the number of repeated playbacks of the first video stream reaching a repeat playback number threshold, and when the number of repeated playbacks of the first video stream reaches the repeat playback number threshold, the terminal device calls a man-machine interaction entrance to request feedback information on the video stream from the user, which not only improves the accuracy of the feedback information but also contributes to the accuracy of the use of the feedback information in the future, for example, improves the accuracy of the user recommending a video stream based on the feedback information.

[0082] In one embodiment, the detection of a specific target object during the playback of the first video stream may be configured as a trigger condition for invoking a man-machine interaction entrance, so that feedback information can be obtained for the specific target object in the video stream. In one embodiment, the terminal device can detect in real time whether a specific target object is included in the currently played video stream, and when the specific target object is detected during the playback of the first video stream, trigger the invocation of a man-machine interaction entrance to obtain target feedback information of the user. In the method provided by the embodiment of the present application, the determination timing of whether the specific target object is included in the first video stream is not limited, for example, the determination of whether the specific target object is included in the first video stream can be performed when the browser or application starts to load or play the first video stream. In the method provided by the embodiment of the present application, the implementation means of determining whether the specific target object is included in the first video stream is also not limited, for example, the terminal device can read label information of the first video stream and determine whether the first video stream includes a specific foreground target according to the label information.

[0083] In one embodiment, the first video stream may be played up to a specific time node as a trigger condition for the man-machine interaction entrance. For example, for a first video stream with a length of t, the specific time node may be set at 0.5t, that is, when the first video stream is played up to the time of 0.5t, the invocation of the man-machine interaction entrance is triggered to obtain the user's target feedback information. As can be understood by those skilled in the art, the specific time node may be set according to actual requirements, and is not limited by the present disclosure.

[0084] In addition, other man-machine interaction entrance call trigger conditions can be flexibly arranged according to product requirements. For example, the man-machine interaction entrance call trigger conditions may further include detection of a predetermined touch control gesture in a predetermined touch control area, detection of a predetermined voice command, detection of a predetermined facial feature, etc., and are not limited by the present disclosure.

[0085] When it is necessary to suppress the frequency of collecting feedback information so as to reduce the influence on video stream playback, a prohibited time zone may be set, and a man-machine interaction entrance is not called during the prohibited time zone, whereas being outside the prohibited time zone is set as a precondition to be satisfied for calling the man-machine interaction entrance.

[0086] Optionally, when a prerequisite to be satisfied for invoking the man-machine interaction entrance includes being outside a prohibited time period, the method provided by the embodiment of the present application may further include a step of detecting a trigger event for the prohibited time period and resetting a timer corresponding to the prohibited time period, where if the timer has not timed out it means that the prohibited time period is in effect, and if the timer has timed out it means that the prohibited time period is outside the prohibited time period.

[0087] Here, the prohibition time period may include multiple time periods, and thus each time period may correspond to one timer, and each time period may correspond to a trigger event.

[0088] In practical application, the trigger event for the prohibited time period can be flexibly arranged according to product requirements. In one implementation, for the same viewing target, if it is assumed that the man-machine interaction entrance has only been called once within X days to obtain target feedback information, then the trigger event corresponding to the prohibited time period includes resetting the timer corresponding to the time period after obtaining the target feedback information. In another implementation, for the same viewing target, if it is assumed that the viewing target has not input the target feedback information consecutively or cumulatively Y times, then the trigger event corresponding to the prohibited time period includes the number of times the target feedback information has not been input consecutively or cumulatively reaching a set threshold, then each time the man-machine interaction entrance is called, if the man-machine interaction entrance is called this time but the target feedback information cannot be obtained, the count value of the number of times the target feedback information has not been input consecutively or cumulatively is accumulated, and when the count value reaches a set threshold, the timer corresponding to the time period is reset.

[0089] According to the method provided by the embodiment of the present application, whether the prohibited time period is reached is determined according to whether the timer corresponding to the prohibited time period has expired, and the implementation is simple and effective, and the timer can be reset by detecting a trigger event corresponding to the prohibited time period, so as to ensure that the timer accurately reflects the prohibited time period.

[0090] In addition to determining whether or not it is within a prohibited time period by setting a timer, the setting of a prohibited time period can also be realized by setting an identification information corresponding to the prohibited time period. In one implementation, for the same viewing target, if it is assumed that the man-machine interaction entrance has been called only once within X days to obtain target feedback information, then prohibition identification information is set to indicate whether or not the target feedback information of the current viewing target has been obtained within a predetermined time period (e.g., within X days). In another implementation, for the same viewing target, if it is assumed that the viewing target has not input target feedback information consecutively or cumulatively Y times, then prohibition identification information is set to indicate whether or not the current viewing target has not input target feedback information consecutively or cumulatively Y times.

[0091] The embodiment of the present application is a video stream playback control method that can be implemented by a terminal device that has a browser or a video stream playback application installed, as shown in FIG. Step 401: when a man-machine interaction entry calling trigger condition is satisfied, calling a man-machine interaction entry for a first video stream currently being played and obtaining target feedback information through the man-machine interaction entry, the target feedback information including feedback information for the first video stream; The present invention further provides a video stream playback control method, comprising: a step 402 of playing a second video stream different from the first video stream after obtaining the target feedback information, wherein the second video stream to be played and / or at least one video stream to be subsequently played are determined according to the target feedback information.

[0092] According to the method provided by the embodiment of the present application, a video stream is recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entry point for obtaining the user's interest level in the first video stream, the target feedback information generally accurately reflects the user's interest level in the first video stream, so by recommending the video stream in real time based on the target feedback information, the accuracy of video recommendation can be further improved.

[0093] Optionally, an implementation of playing a second video stream different from the first video stream after obtaining the target feedback information may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information.

[0094] According to the method provided by the embodiment of the present application, the second video stream is automatically played in response to obtaining the target feedback information, so as to realize a seamless transition between the man-machine interaction process and the automatic video stream playing operation, and improve the smoothness of the video playing. Moreover, when the second video stream is determined according to the target feedback information, the embodiment of the present application further responds quickly to the user's feedback, so as to further improve the user's usage experience.

[0095] Optionally, according to the method provided by the embodiment of the present application, when the man-machine interaction entrance calling trigger condition is met, the method further includes stopping the playback of the first video stream, and invoking the man-machine interaction entrance in response to this may include the steps of: calling the man-machine interaction entrance while displaying the playback screen of the first video stream; and after receiving a command to close the man-machine interaction entrance, closing the man-machine interaction entrance and playing the second video stream.

[0096] According to the method provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user's feedback for the currently played first video stream can be obtained more accurately and according to the goal. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the playing video stream, since the playback of the first video stream is stopped in this process. In addition, the playback screen of the stopped first video stream in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0097] For the specific implementation and detailed content of the method, reference can be made to the description of the above method embodiment, and detailed description thereof will be omitted here.

[0098] Based on the same inventive concept as the method shown in Fig. 1, an embodiment of the present application provides a terminal device, which may include a first playback control module 501 and a second playback control module 502 as shown in Fig. 5, each of which can respectively perform each step / function of the video stream playback control method described above with reference to Fig. 1-3. The main functions of each component of the terminal device are described below, and the details already described above will be omitted.

[0099] the first playback control module 501 is configured to stop playback of the first video stream and call a man-machine interaction entrance for the first video stream while displaying a playback screen of the first video stream when a man-machine interaction entrance call trigger condition is satisfied; The second playback control module 502 is configured to obtain target feedback information through the man-machine interaction entrance or close the man-machine interaction entrance and play a second video stream different from the first video stream after receiving a command to close the man-machine interaction entrance, where the target feedback information includes feedback information for the first video stream.

[0100] According to the terminal device provided by the embodiment of the present application, while displaying the playback screen of the first video stream, a man-machine interaction entrance for the first video stream is called to obtain feedback information, so that the user can obtain feedback for the first video stream currently being played more accurately and according to the goal. In addition, according to the terminal device provided by the embodiment of the present application, in the process of calling the man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the video stream being played, since the playback of the first video stream is stopped in this process. In addition, the playback screen of the first video stream stopped in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0101] Optionally, the second playback control module may play a second video stream different from the first video stream, in one implementation, comprising: The method may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information or the command to close the man-machine interaction portal.

[0102] According to the terminal device provided in the embodiment of the present application, the video stream continues to be played in response to obtaining target feedback information or a command to close the man-machine interaction entrance, i.e., after the user inputs feedback information or closes the man-machine interaction entrance, the application automatically continues to play the second video stream, thereby realizing a seamless transition between the man-machine interaction process and the automatic continuous playback operation, and improving the smoothness of video playback.

[0103] According to any of the above terminal device embodiments, the second video stream to be played and / or the at least one video stream to be played later is determined in response to target feedback information.

[0104] According to the terminal device provided by the embodiment of the present application, the video stream is recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information generally reflects the user's interest level in the first video stream accurately, so that the video stream is recommended in real time based on the target feedback information, and the accuracy of video recommendation can be further improved.

[0105] In addition, according to the terminal device provided by the embodiment of the present application, in order to recommend a video stream in real time according to the target feedback information, it may be necessary to obtain more abundant feedback contents, for example, by setting multiple feedback questions or setting multiple options for one feedback question, which requires occupying a relatively larger display area.As described above, according to the terminal device provided by the embodiment of the present application, when a man-machine interaction entrance is called, the playback of the video stream is stopped, so that when the man-machine interaction entrance is a man-machine interface, even if a relatively large man-machine interface is displayed, it will not block the video stream being played and affect the playback effect of the video stream.

[0106] According to any of the above terminal device embodiments, the man-machine interaction entrance call trigger condition is: receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a repeated playback number threshold; and The first video stream has been played; and a particular target object is detected during playback of the first video stream; and The first video stream may be played up to the particular time node.

[0107] In practical application, the terminal device provided by the embodiment of the present application can support flexibly configuring the man-machine interaction entrance call trigger conditions to meet product requirements.

[0108] In one embodiment, the terminal device can configure the reception of a video stream switching command as a man-machine interaction entrance trigger condition, and upon receiving the video stream switching command, call the man-machine interaction entrance in response to the command. Such an implementation of calling the man-machine interaction entrance does not interrupt the first video stream being played, and can reduce interference with the video stream playback.

[0109] In one embodiment, the terminal device can configure the completion of the first video stream playback as a man-machine interaction entrance trigger condition, and when the first video stream playback is completed, call the man-machine interaction entrance. This implementation of calling the man-machine interaction entrance does not interrupt the first video stream being played, and can reduce interference with the video stream playback.

[0110] Taking a short video playback application as an example, in a non-automatic playback mode, a general video stream playback control process is configured to repeatedly play a current video stream when a video stream switching command is not detected, and to switch to a next video stream when a video stream switching command is detected. In a scene where a current video stream is repeatedly played when there is no video stream switching command, the repeated playback of the current video stream does not mean that the user is more interested in the content of the video stream, but may be caused by the user switching the video stream due to a change of interest or forgetting to close it. In such a case, in one embodiment, the terminal device may configure the number of repeated playbacks of a first video stream reaching a repeated playback count threshold as a man-machine interaction entry trigger condition, and when the number of repeated playbacks of the first video stream reaches the repeated playback count threshold, the terminal device may call up a man-machine interaction entry to request feedback information on the video stream from the user, which not only improves the accuracy of the feedback information but also contributes to the accuracy of the use of the feedback information in the future, for example, improves the accuracy of the user recommending a video stream based on the feedback information.

[0111] In one embodiment, the detection of a specific target object during the playback of the first video stream may be configured as a trigger condition for invoking a man-machine interaction entrance, so that feedback information can be obtained for the specific target object in the video stream. In one embodiment, the terminal device can detect in real time whether a specific target object is included in the currently played video stream, and when the specific target object is detected during the playback of the first video stream, trigger the invocation of a man-machine interaction entrance to obtain target feedback information of the user. In the method provided by the embodiment of the present application, the determination timing of whether the specific target object is included in the first video stream is not limited, for example, the determination of whether the specific target object is included in the first video stream can be performed when the browser or application starts to load or play the first video stream. In the method provided by the embodiment of the present application, the implementation means of determining whether the specific target object is included in the first video stream is also not limited, for example, the terminal device can read label information of the first video stream and determine whether the first video stream includes a specific foreground target according to the label information.

[0112] In one embodiment, the first video stream may be played up to a specific time node as a trigger condition for the man-machine interaction entrance. For example, for a first video stream with a length of t, the specific time node may be set at 0.5t, that is, when the first video stream is played up to the time of 0.5t, the invocation of the man-machine interaction entrance is triggered to obtain the user's target feedback information. As can be understood by those skilled in the art, the specific time node may be set according to actual requirements, and is not limited by the present disclosure.

[0113] In addition, other man-machine interaction entrance call trigger conditions can be flexibly arranged according to product requirements. For example, the man-machine interaction entrance call trigger conditions may further include detection of a predetermined touch control gesture in a predetermined touch control area, detection of a predetermined voice command, detection of a predetermined facial feature, etc., and are not limited by the present disclosure.

[0114] When it is necessary to suppress the frequency of collecting feedback information so as to reduce the influence on video stream playback, a prohibited time zone may be set, and a man-machine interaction entrance is not called during the prohibited time zone, whereas being outside the prohibited time zone is set as a precondition to be satisfied for calling the man-machine interaction entrance.

[0115] Optionally, when a prerequisite to be satisfied for invoking the man-machine interaction entrance includes being outside a prohibited time period, the method provided by the embodiment of the present application may further include a step of detecting a trigger event for the prohibited time period and resetting a timer corresponding to the prohibited time period, where if the timer has not timed out it means that the prohibited time period is in effect, and if the timer has timed out it means that the prohibited time period is outside the prohibited time period.

[0116] Based on the same inventive concept as the method shown in Fig. 4, an embodiment of the present application provides a terminal device, which may include a man-machine interaction entry calling module 601 and a video stream playing module 602, as shown in Fig. 6, each of which can respectively execute each step / function of the video stream playing control method described above with reference to Fig. 2-4. The main functions of each component of the terminal device are described below, and the details already described above will be omitted.

[0117] the man-machine interaction entrance calling module 601 is configured to call a man-machine interaction entrance for the first video stream currently being played when a man-machine interaction entrance calling trigger condition is met, and obtain target feedback information through the man-machine interface, the target feedback information including feedback information for the first video stream; The video stream playback module 602 is configured to play a second video stream different from the first video stream after obtaining the target feedback information, and the second video stream to be played and / or the at least one video stream to be played later are determined according to the target feedback information.

[0118] According to the terminal device provided by the embodiment of the present application, the video stream is recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information can generally accurately reflect the user's interest level in the first video stream, so by recommending the video stream in real time based on the target feedback information, the accuracy of video recommendation can be further improved.

[0119] Optionally, an implementation of playing a second video stream different from the first video stream after the video playback module obtains the target feedback information may include, but is not limited to, automatically playing the second video stream in response to obtaining the target feedback information.

[0120] According to the terminal device provided in the embodiment of the present application, the second video stream can be automatically played in response to obtaining target feedback information, thereby realizing a seamless transition between the man-machine interaction process and the automatic video stream playback operation, and improving the smoothness of video playback.

[0121] Optionally, when a man-machine interaction entrance calling trigger condition is met, the video stream playing module further stops playing the first video stream, and in response, the implementation of the man-machine interaction entrance calling module calling the man-machine interaction entrance may include calling the man-machine interaction entrance while displaying the playback screen of the first video stream. Note that, after the man-machine interaction entrance calling module receives a command to close the man-machine interaction entrance, it closes the man-machine interaction entrance, and the video stream playing module automatically plays the second video stream, and the target feedback information includes feedback information for the first video stream.

[0122] According to the terminal device provided by the embodiment of the present application, in the process of calling a man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and after closing the man-machine interaction entrance, the video stream is automatically continued to be played (i.e., the second video stream is played), so that even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback of the first video stream is stopped during this process, so that the playback effect is not affected by blocking the video stream being played. In addition, during the process of stopping and continuing the playback of the first video stream, the playback screen of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display manner is intuitive and simple.

[0123] The above modules may be implemented as software components executed on one or more common processors, or as hardware performing certain functions or a combination thereof, such as programmable logic devices and / or application specific integrated circuits. In some embodiments, these modules may be embodied in the form of a software product storable in a non-volatile storage medium, including for causing a computing device (e.g., a personal computer, a server, a network device, a mobile terminal, etc.) to perform the method according to the embodiment of the present invention. In one embodiment, the above modules may be further implemented in a single device or distributed across multiple devices. The functions of these modules may be combined with each other or further divided into multiple sub-modules.

[0124] The terminal device in each of the above embodiments may include a smartphone, a personal digital assistant, a tablet computer, a wearable device with a display, an in-vehicle computer, a smart speaker, a personal computer, and the like.

[0125] As will be apparent to those skilled in the art, for ease and simplicity of explanation, the specific operating processes of the above-mentioned terminal equipment modules may be referred to the corresponding processes in the method embodiments, and detailed explanations will be omitted here.

[0126] Based on the same inventive concept as the method, the embodiment of the present application includes: Further provided is an electronic device comprising a memory for storing a program for performing the method according to each of the above method embodiments, and a processor arranged to execute the program stored in the memory. When the program instructions stored in the memory are executed by the processor, the processor performs the method according to each of the above method embodiments and realizes the corresponding module in the terminal device according to the embodiment of the present invention. The processor may include a central processing unit (CPU) or other type of processing unit having data processing capability and / or instruction execution capability, and may control other components in the electronic device to perform desired functions. The memory may include one or more computer program products, which may include various types of computer readable storage media, such as, for example, volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored in the computer readable storage medium, and the processor may execute the program instructions to realize the functions of the above-mentioned embodiments of the present disclosure and / or other desired functions.

[0127] 1 is realized by the electronic device provided according to the embodiment of the present application, the playback screen of the first video stream is displayed, and the feedback information is obtained by calling the man-machine interaction entrance for the first video stream, so that the user's feedback for the currently played first video stream can be obtained more accurately according to the target. In addition, in the process of calling the man-machine interaction entrance, the playback of the video stream is stopped (i.e., the playback of the first video stream is stopped), and the video stream is continued to be played after closing the man-machine interaction entrance (i.e., the second video stream is played). Even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback of the first video stream is stopped in this process, so that the playback effect is not affected by blocking the currently played video stream. In addition, the playback screen of the stopped first video stream in the process of stopping and continuing the playback of the first video stream is still displayed, indicating that the called man-machine interaction entrance is for the first video stream, and the display method is intuitive and simple.

[0128] By implementing the method shown in FIG. 5 using the electronic device provided by the embodiment of the present application, the video stream can be recommended in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and the user experience. If it is a man-machine interaction entrance for obtaining the user's interest level in the first video stream, the target feedback information generally accurately reflects the user's interest level in the first video stream, so that the video stream can be recommended in real time based on the target feedback information, thereby further improving the accuracy of video recommendation.

[0129] The electronic device provided by the embodiments of the present application may include a terminal device, and as shown in FIG. 7, the terminal device not only has a processor and a memory, but also has an input device (e.g., a touch panel, a camera, a microphone, etc.), an output device (e.g., a display, a speaker, etc.), a communication module, and a power module.

[0130] Wherein, the memory, the input device, the output device, the communication module, and the power supply module are connected to the processor via a serial port, a bus, or a USB interface, where for a single-processor terminal device, the processor is a CPU (Central Processing Unit), for a dual-processor terminal device, the processor includes a main processor and a sub-processor, where the main processor executes an application to realize the method provided by the embodiment of the present invention, and when communication with the outside is required, the sub-processor controls and cooperates with the communication module to realize it, for a terminal device equipped with a GPU (Graphics Processing Unit) and a CPU, the processor refers to the GPU and the CPU, and the GPU and the CPU cooperate with each other or are used alone to realize the method provided by the embodiment of the present application.

[0131] Among them, the memory of the terminal device may include, but is not limited to, Flash memory, RAM (random access memory), ROM (read only memory), etc. The RAM is mainly for storing programs and data when the terminal device is operating, and any programs to be executed or data to be processed must be stored in the RAM. The ROM is mainly for inspecting the configuration status of the operating system of the terminal device and providing the most basic input / output (I / O) programs. Flash memory is a long-life non-volatile memory (it can retain stored data information even when the power is turned off), and data is deleted in units of fixed blocks rather than in units of single bytes. Since Flash memory can store data even when the power is turned off, it is generally used to store setting information such as the setting information of a mobile phone by a user.

[0132] It should be noted that different terminal devices (such as a single-processor smartphone, a dual-processor smartphone, a smart wearable device, a tablet computer, etc.) may have more or less hardware configurations than the terminal device shown in FIG. 7, but as long as they have memory and a processor and can realize the functions of the above method embodiments, they are all within the scope of protection of the present disclosure.

[0133] Based on the same inventive concept as the method, an embodiment of the present application further provides a computer-readable storage medium storing a program for performing the method according to each of the above embodiments.

[0134] 1 is realized by a program stored in a computer-readable storage medium provided in the embodiment of the present application, the video stream playback is stopped (i.e., the first video stream playback is stopped) during the process of calling a man-machine interaction entrance, and the video stream continues to be played (i.e., the second video stream is played) after the man-machine interaction entrance is closed, so that even if the man-machine interaction entrance blocks the playback screen of the first video stream, the playback effect is not affected by blocking the video stream being played because the playback of the first video stream is stopped during this process. In addition, the playback screen of the first video stream is still displayed during the process of stopping and continuing the playback of the first video stream, indicating that the called man-machine interaction entrance is for the first video stream, and the display manner is intuitive and simple.

[0135] The method shown in FIG. 4 can be implemented by a program stored in a computer-readable storage medium provided by the embodiment of the present application to recommend a video stream in real time based on the target feedback information. The faster the calculation speed of the recommendation model calculated based on the target feedback information, the faster the video stream can be recommended according to the target feedback information when the video stream continues to be played, thereby improving the real-timeness of video recommendation and the user experience. If it is a man-machine interaction entry point for obtaining the user's interest level in the first video stream, the target feedback information generally accurately reflects the user's interest level in the first video stream, so that the video stream can be recommended in real time based on the target feedback information to further improve the accuracy of video recommendation.

[0136] This specification is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, whereby the instructions executed by the processor of the computer or other programmable data processing apparatus create a device for implementing the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0137] These computer program instructions may be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory create an article of manufacture including an instruction device that implements the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0138] These computer program instructions may be loaded into a computer or other programmable data processing apparatus to cause the computer or other programmable data processing apparatus to perform a series of operational steps to generate a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowcharts and / or one or more blocks of the block diagrams.

[0139] Although the preferred embodiments of the present specification have been described, those skilled in the art may make further changes and modifications to these embodiments upon grasping the basic inventive concept. Therefore, the appended claims are intended to encompass the preferred embodiments and all changes and modifications within the scope of the present specification.

[0140] It is obvious that those skilled in the art can make various modifications and variations to the present specification without departing from the spirit and scope of the present specification. Thus, if these modifications and variations of the present specification are within the scope of the claims of the present specification and equivalent technical scope, the present specification is intended to include these modifications and variations.

Claims

1. a step of stopping playback of a first video stream and invoking a man-machine interaction entrance for the first video stream while displaying a playback screen of the first video stream when a man-machine interaction entrance calling trigger condition is satisfied, the man-machine interaction entrance including a man-machine interaction interface and / or a man-machine interaction voice module; obtaining target feedback information through the man-machine interaction entrance or after receiving a command to close the man-machine interaction entrance, closing the man-machine interaction entrance and playing a second video stream different from the first video stream, wherein the target feedback information includes feedback information for the first video stream; The man-machine interaction entrance call trigger condition includes: receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a threshold number of repeated playbacks; and the playback of the first video stream is completed; and a particular target object is detected during playback of the first video stream; and the first video stream has been played up to a specific time node.

2. The step of playing a second video stream different from the first video stream includes:

2. The method of claim 1, further comprising the step of automatically playing the second video stream in response to obtaining the target feedback information or a command to close the human-machine interaction portal.

3. 2. The method of claim 1, wherein the second video stream to be played and / or the at least one video stream to be played at a later time are determined in response to the target feedback information.

4. calling a man-machine interaction entrance for a first video stream currently being played when a man-machine interaction entrance calling trigger condition is satisfied, and obtaining target feedback information through the man-machine interaction entrance, the target feedback information includes feedback information for the first video stream, and the man-machine interaction entrance includes a man-machine interaction interface and / or a man-machine interaction voice module; after obtaining the target feedback information, playing a second video stream different from the first video stream, wherein the second video stream to be played and / or at least one video stream to be subsequently played are determined in response to the target feedback information; The man-machine interaction entrance call trigger condition includes: receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a threshold number of repeated playbacks; and the playback of the first video stream is completed; and a particular target object is detected during playback of the first video stream; and the first video stream has been played up to a specific time node.

5. After obtaining the target feedback information, the step of playing a second video stream different from the first video stream includes:

5. The method of claim 4, further comprising the step of automatically playing the second video stream in response to obtaining the target feedback information.

6. a first playback control module configured to stop playback of a first video stream and call a man-machine interaction entrance for the first video stream while displaying a playback screen of the first video stream when a man-machine interaction entrance calling trigger condition is satisfied, the first playback control module including a man-machine interaction interface and / or a man-machine interaction voice module; a second playback control module configured to obtain target feedback information through the man-machine interaction portal or to close the man-machine interaction portal after receiving a command to close the man-machine interaction portal, and to play a second video stream different from the first video stream, where the target feedback information includes feedback information for the first video stream; The man-machine interaction entrance call trigger condition is receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a threshold number of repeated playbacks; and the playback of the first video stream is completed; and a particular target object is detected during playback of the first video stream; and the first video stream having been played up to a specific time node.

7. a man-machine interaction entrance calling module configured to call a man-machine interaction entrance for a first video stream currently being played when a man-machine interaction entrance calling trigger condition is met, and obtain target feedback information by the man-machine interaction entrance, the target feedback information including feedback information for the first video stream, and the man-machine interaction entrance including a man-machine interaction interface and / or a man-machine interaction voice module; a video stream playback module configured to play a second video stream different from the first video stream after obtaining the target feedback information, wherein the second video stream to be played and / or at least one video stream to be subsequently played are determined depending on the target feedback information; The man-machine interaction entrance call trigger condition is receiving a video stream switching command; the number of repeated playbacks of the first video stream reaches a threshold number of repeated playbacks; and the playback of the first video stream is completed; and a particular target object is detected during playback of the first video stream; and the first video stream having been played up to a specific time node.

8. A memory for storing a program for executing the method according to any one of claims 1 to 5; a processor arranged to execute a program stored in the memory.

9. A computer-readable storage medium storing a program for executing the method according to any one of claims 1 to 5.

Images