CN113347498A

CN113347498A - Video playing method and device and computer readable storage medium

Info

Publication number: CN113347498A
Application number: CN202110595368.7A
Authority: CN
Inventors: 王晨
Original assignee: Beijing IQIYI Science and Technology Co Ltd
Current assignee: Beijing IQIYI Science and Technology Co Ltd
Priority date: 2021-05-28
Filing date: 2021-05-28
Publication date: 2021-09-03

Abstract

The invention provides a video playing method and device and a computer readable storage medium, and belongs to the technical field of computers. The method comprises the steps of sending first indication information to a client, and indicating the client to output content interaction options in the process of playing a target video; then, receiving user interaction data from the client, and determining a target branch scenario corresponding to a branch node based on the user interaction data; the user interaction data is determined by the client based on the content interaction option, and the user interaction data is used for indicating the personalized preference of the user for the currently played video content. After the target branching scenario is determined, second indication information is sent to the client to indicate the client to automatically play the target branching scenario at the branching node, and a user does not need to manually select the branching scenario at the playing node of the branching scenario, so that the continuity of video playing is ensured.

Description

Video playing method and device and computer readable storage medium

Technical Field

The present invention relates to the field of computer technologies, and in particular, to a video playing method and apparatus, and a computer-readable storage medium.

Background

With the development of network video platforms, people can search and play various videos at any time through various terminal devices. While video resources are more and more abundant, entertainment and interactivity of videos are more and more concerned by users, and an interactive video named interactive drama is produced. At least two branch scenarios exist in the interactive drama at different time points, and when a user watches the interactive drama, the user can select any one of the branch scenarios to watch the interactive drama.

However, currently, the branching scenario selected by the user is usually played after the user manually selects the branching scenario, and before the user makes a selection, the terminal cannot determine which branching scenario is played, and the video is in a pause playing state, which affects the continuity of video playing.

Disclosure of Invention

The invention provides a video playing method, a video playing device and a computer readable storage medium, which are used for solving the problem that the video playing method in the prior art needs a user to manually select a branch scenario and the selection operation of the user on the branch scenario can cause the video playing to be discontinuous to a certain extent.

According to a first aspect of the present invention, there is provided a video playing method applied to a server, the method including:

sending first indication information to a client, wherein the first indication information is used for indicating the client to output content interaction options in the target video playing process;

receiving user interaction data from the client, the user interaction data being determined by the client based on the content interaction options, the user interaction data being used to indicate a user's personalized preference for currently playing video content;

determining a target branch scenario corresponding to the branch node based on the user interaction data;

and sending second indication information to the client, wherein the second indication information is used for indicating the client to play the target branching scenario at the branching node.

The invention also provides another video playing method which is applied to a client side and comprises the following steps:

receiving first indication information from a server, and outputting content interaction options in the target video playing process;

determining user interaction data according to the interaction operation aiming at the content interaction option, wherein the user interaction data is used for indicating the personalized preference of a user on the currently played video content;

sending the user interaction data to the server so that the server determines a target branching scenario corresponding to a branching node according to the user interaction data;

receiving second indication information from the server;

and playing the target branching scenario at the branching node according to the second indication information.

According to a second aspect of the present invention, there is provided a video playing apparatus applied to a server, the apparatus including:

the first sending module is used for sending first indication information to a client, wherein the first indication information is used for indicating the client to output content interaction options in the target video playing process;

a first receiving module, configured to receive user interaction data from the client, where the user interaction data is determined by the client based on the content interaction option, and the user interaction data is used to indicate a personalized preference of a user for currently played video content;

the first processing module is used for determining a target branch scenario corresponding to the branch node based on the user interaction data;

and the second sending module is used for sending second indication information to the client, wherein the second indication information is used for indicating the client to play the target branching scenario at the branching node.

The invention also provides another video playing device, which is applied to a client side, and the device comprises:

the second receiving module is used for receiving the first indication information from the server and outputting content interaction options in the target video playing process;

the second processing module is used for determining user interaction data according to the interaction operation aiming at the content interaction option, and the user interaction data is used for indicating the personalized preference of a user on the currently played video content;

the third sending module is used for sending the user interaction data to the server so that the server can determine a target branching scenario corresponding to a branching node according to the user interaction data;

the third receiving module is used for receiving second indication information from the server;

and the playing module is used for playing the target branching scenario at the branching node according to the second indication information.

According to a third aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the video playback method as defined in any one of the first aspects.

Aiming at the prior art, the invention has the following advantages:

the method comprises the steps of sending first indication information to a client, indicating the client to output a content interaction option in a target video playing process, and receiving user interaction data determined by the client based on the content interaction option, wherein the user interaction data is used for indicating the personalized preference of a user to the currently played video content; furthermore, based on the user interaction data, a target branching scenario corresponding to the branching node is determined, second indication information is sent to the client, the client is indicated to play the target branching scenario at the branching node, the user does not need to manually select the branching scenario at the branching node of the target video, and the continuity of video playing and the interestingness of the branching scenario are guaranteed. In addition, the content interaction option in the embodiment of the invention is different from the selection option of the branching scenario, can be displayed in the process of playing the target video, does not influence the normal playing of the target video, does not cause the conditions of video playing interruption and the like, and determines the preference of the user through an option interaction mode on the premise of ensuring the normal playing of the video and is used for guiding the selection of the branching scenario at the subsequent branching node. Therefore, the video playing method provided by the embodiment of the invention can automatically determine the target branching scenario to be played according to the selection operation of the user on the content interaction option under the condition of not influencing the normal playing of the video, thereby ensuring the continuity of video playing and the interest of the branching scenario.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 is a flowchart illustrating steps of a video playing method according to an embodiment of the present invention;

fig. 2 is a schematic diagram of a target video playing interface according to an embodiment of the present invention;

fig. 3 is an interaction flowchart of a video playing method according to an embodiment of the present invention;

FIG. 4 is a flowchart illustrating steps of another video playing method according to an embodiment of the present invention;

fig. 5 is a block diagram of a video playing apparatus according to an embodiment of the present invention;

fig. 6 is a block diagram of another video playing apparatus according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

The embodiment of the invention is applied to the scene of interactive video.

Specifically, the target video mentioned in the embodiments of the present invention is an interactive video including a branch node, such as an interactive movie, an interactive art, an interactive television, and the like. The branching node of the target video includes at least two branching scenarios, and different branching scenarios will lead to different final outcomes. And when the target video is played to the branch node, playing the target branch scenario determined in at least two branch scenarios of the branch node. In order to identify the branching scenario corresponding to the target video, the target video and the branching scenario having a corresponding relationship may be provided with identifiers having the same information, for example, for the target video a, the video identifier may be set as video a, the target video a corresponds to two branching scenarios, namely, the branching scenario a1 and the branching scenario a2, then the scenario identifier of the branching scenario a1 may be set as video a-branch 1, the scenario identifier of the branching scenario a2 may be set as video a-branch 2, the video identifier of the target video and the scenario identifier of the branching scenario are compared, and if the two items have the same information, it is indicated that the branching scenario corresponding to the scenario identifier is the branching scenario corresponding to the target video. Or, the video identifier of the target video is used as an index key, the scenario identifier of the branching scenario corresponding to the target video is used as an index value, the corresponding relation between the index key and the index value is pre-established, and then the branching scenario corresponding to the target video is inquired according to the pre-established corresponding relation. In this regard, the embodiment of the present invention is not particularly limited as long as the correspondence between the target video and the branching scenario can be determined.

The interactive video is a video type which is strongly interactive with the user, and needs to interact with the user when being played to a branch node to select a scenario which is more in line with the user tendency. For example, a branch interaction option is presented at a branch node, and a user may choose a different branch scenario based on the branch interaction option. In other words, when different users watch the interactive video, the choices of the branch nodes may be different, and the users can obtain the plot experience more fitting the self-mind.

However, such a way that the user directly chooses to enter the branching scenario may feel too intrusive to the user. For example, a user may not want to select the scenario, but wants to have an interactive video experience, in this case, the method of selecting the scenario based on the branch interactive option will give the user a feeling of forcing the user to select which path to go after arriving at the intersection, and cannot meet the interactive requirements of the user, so that the user experience is poor.

Based on the scene problems, the design idea is given as follows: and analyzing the content of the interactive drama, extracting content elements in the interactive drama, generating content interactive options related to the content of the interactive drama according to the content elements, and associating the content interactive options with corresponding playing time points. In the interactive play process, displaying content interaction options and collecting user interaction data of a user on the content interaction options, analyzing personalized preference of the user on interactive play content according to the user interaction data, then automatically determining a target branching scenario for the user according to the personalized preference of the user, and automatically playing the target branching scenario at a branching node, so that different users can unconsciously watch a whole set of interactive plays customized for the users. Moreover, for the same interactive drama, the branching dramas or the ending situations seen by a plurality of users are different, so that the interest and the discussion performance of the interactive drama are increased.

Based on the foregoing inventive concept, an embodiment of the present invention provides a video playing method. Fig. 1 is a flowchart of steps of a video playing method according to an embodiment of the present invention, and as shown in fig. 1, the method is applied to a server, and specifically may include:

step 101, sending first indication information to a client, where the first indication information is used to indicate the client to output a content interaction option in a target video playing process.

And 102, receiving user interaction data from the client, wherein the user interaction data is determined by the client based on the content interaction option, and the user interaction data is used for indicating the personalized preference of the user on the currently played video content.

And 103, determining a target branching scenario corresponding to the branching node based on the user interaction data.

And 104, sending second indication information to the client, wherein the second indication information is used for indicating the client to play the target branching scenario at the branching node.

It should be noted that the content interaction option in the embodiment of the present invention is determined according to the video content located before the branch node in the target video, and includes a descriptive language related to the video content of the target video. Different from the prior art, the interactive node before the branch node is provided with the branch interactive option, the branch interactive option directly corresponds to the branch scenario, and when the interactive play is played to the branch node, the user can continue playing after manually selecting the branch interactive option, so that the playing pause of the interactive play can occur, and the user experience is influenced; the content interaction options in the embodiment of the invention are not related to all the branch scenarios, but related to the video content before the branch nodes, so that the branch scenarios manually selected by the user are not needed, and the output nodes of the content interaction options are positioned before the branch nodes, so that the consistency of interactive play is not influenced.

In an actual implementation scenario, the description language of the content interaction option generally has a certain tendency, and the personalized preference of the user for the currently played video content can be reflected through the user interaction data of the user for the content interaction option. The content interaction options may include at least two options, each option corresponding to a preference. For example, for a target video a, the video content is "hero love, but men and women love, mermer guard", and the server determines that the content interaction options corresponding to the target video a according to the video content of the target video are as follows: option 1 "admirable maiden has such guardian", option 2 "men are sad, love but not.

Alternatively, the content interaction option may include at least one interactive question, and any one interactive question also corresponds to at least two interactive answers. For example, the interaction problem corresponding to the target video a is: "is this acquaintance of male two worth? ", the corresponding interactive answers include: answer 1 "worth", answer 2 "love but not, sadness", and so on. Referring to fig. 2, a schematic diagram of a target video playing interface provided by an embodiment of the present invention is shown, where interaction problems corresponding to content interaction options of a target video are: "can you understand the practice of men and women? ", the corresponding interactive answers include: answer 1 "can, true love", answer 2 "a person does". It can be seen that each interactive answer corresponds to a video content preference, and according to the interactive answer selected by the user, the personalized preference of the user for the currently played content of the target video can be determined.

For the specific expression form of the content interaction option, the embodiment of the present invention is not particularly limited, as long as the personalized preference of the user for the currently played video content can be reflected based on the user interaction data of the user for the content interaction option.

The user interaction data may be determined based on the user's interaction with the content options, i.e., selection of the options or interactive answers. The user interaction data in the embodiment of the present invention is used to reflect specific options or interaction answers of the content interaction options selected by the user, and may include, but is not limited to, at least one of the following: the video identification of the target video corresponding to the content interaction option, the option identification of the content interaction option, or the answer identification of the content interaction option, etc.

It should be noted that the user interaction data in the embodiment of the present invention is different from user behavior data determined according to behaviors of a user in clicking, posting a pop-up screen, commenting, likes, browsing time, clicking speed, a user's facial expression, shaking, blowing, and the like for a target video. The user behavior data and the video content are not directly related, if the personalized preference of the user for the target video is determined according to the user behavior data, the video content needs to be further analyzed, the preference of the user for the video content can be predicted by combining the user behavior data, and the prediction result is often inaccurate. In the embodiment of the invention, because the content interaction options are related to the video content of the target video, the user interaction data can intuitively reflect the personalized preference of the user to the video content, so that the target branching scenario of the branching node can be determined based on the user interaction data, and the branching scenario conforming to the personalized preference of the user is played for the user.

In the embodiment of the invention, the server side sends the first indication information to the client side to indicate the client side to output the content interaction options corresponding to the target video in the playing process of the target video, so that a user can perform interaction operation on the content interaction options through the client side. As shown in fig. 2, after receiving the first indication information, the client may pop up a floating window in the playing interface of the target video, and display the content interaction option in the floating window, where the target video is in a normal playing state, and the situation of playing suspension due to the content interaction option is avoided, that is, the continuity of playing the target video is not affected.

In an embodiment, in order to further reduce the occlusion that the content interaction option is playing content, on the basis of any of the foregoing embodiments, the transparency of the floating window may be further set, so that the floating window is displayed in a semi-transparent form.

In another embodiment, on the basis of any one of the foregoing embodiments, a display time of the content interaction option may be further set, and if the user does not perform an interaction operation on the content interaction option within the preset display time, the output of the content interaction option may be ended. The situation that the content interaction options are displayed on the video playing page for a long time is avoided, and the adverse effect on the user's view caused by the situation is avoided.

In another embodiment, on the basis of any one of the foregoing embodiments, the display position of the content interaction option may be further set at an edge position such as a lower right corner or a lower left corner of the playing interface of the target video, so as to reduce the occlusion of the playing content as much as possible.

And the client generates user interaction data according to the interaction operation of the user aiming at the content interaction option and sends the user interaction data to the server. Because the content interaction options in the embodiment of the invention are determined according to the video content of the target video, the client can indicate the personalized preference of the user on the currently played video content based on the user interaction data determined by the content interaction options.

After receiving the user interaction data from the client, the server can determine a target branching scenario corresponding to the branching node according to the user interaction data. Specifically, the server may determine a branching scenario with scenario content matching with the personalized preference of the user as the target branching scenario by performing content analysis on each branching scenario corresponding to the branching node of the target video. And after determining the target branching scenario corresponding to the branching node, the server sends second indication information to the client, and the client is indicated to automatically play the target branching scenario at the branching node.

In the video playing method provided in the embodiment of the present invention, the interaction among the user, the client and the server is involved, referring to fig. 3, an interaction flowchart of the video playing method according to the embodiment of the present invention is shown, and the following will describe in detail the implementation process of the present invention with reference to fig. 3.

First, a user performs a playing operation on a target video presented in a client, for example, a clicking operation on the target video, a touching operation on a playing control, and the like. The client determines a video which the user wants to watch according to the playing operation of the user, determines the video as a target video under the condition that the video corresponds to the branching scenario, and sends the video identifier of the target video to the server. The video identifier of the target video is the unique identity identifier of the target video, and the video identifier of the target video can be determined according to the episode name of the interactive episode corresponding to the target video, the episode to which the target video belongs, and the like, which is not particularly limited in the embodiment of the present invention.

After receiving the video identification of the target video sent by the client, the server searches the target video corresponding to the video identification in the database, and determines the content interaction option corresponding to the target video according to the video content currently or to be played by the target video. Specifically, the server can read the playing progress of the target video in real time, determine the content of the currently played video according to the current playing progress of the target video, and further determine the content interaction option; or, the client sends the playing progress of the target video to the server, and then the server determines the currently played video content according to the current playing progress of the target video, so as to determine the content interaction option. And after the server side determines the content interaction options corresponding to the target video, sending the determined content interaction options to the client side.

After receiving the first indication information sent by the server, the client outputs a content interaction option for a user to select in the process of playing the target video.

The user performs an interactive operation on the content interaction options displayed by the client, for example, a click operation on an interactive answer of the content interaction options. The client determines user interaction data of a user aiming at the content interaction option according to the received interaction operation, the user interaction data are sent to the server, and the server determines a target branch scenario corresponding to a branch node of the target video according to the user interaction data.

And after the server side determines the target branching scenario, sending a second indication message to the client side. And the client automatically plays the target branching scenario to the user when the target video is played to the branching node according to the received second indication message.

In the embodiment of the invention, the server side sends first indication information to the client side to indicate the client side to output content interaction options in the playing process of the target video, determines the target branch scenario corresponding to the branch node of the target video according to the received user interaction data, and then sends second indication information to the client side to indicate the client side to play the target branch scenario at the branch node without manually selecting the target branch scenario by a user. In addition, the preference tag of the user is determined according to the selection operation of the user on the content interaction option, the content interaction option is determined according to the video content of the target video, the user interaction data generated after the user performs the interaction operation aiming at the content interaction option can indicate the personalized preference of the user on the currently played video content, and the target branching scenario determined according to the user interaction data in the embodiment of the invention is in accordance with the personalized preference of the user. Therefore, the video playing method provided by the embodiment of the invention can automatically play the target branching scenario at the branching node of the branching scenario without manually selecting the branching scenario by the user, and can determine the target branching scenario corresponding to the branching node according to the user preference, thereby automatically playing the branching scenario conforming to the personalized preference of the user for the user.

In the embodiment of the invention, the server can automatically determine the content interaction options corresponding to the target video according to the playing progress of the target video; or a technician determines the content interaction options of the target video in advance according to the video content of the target video, stores the content interaction options of the target video in a server in advance, and sends first indication information for indicating the client to output the content interaction options to the client according to the playing progress of the target video.

In an optional embodiment of the present invention, taking the example that the server automatically determines the content interaction option corresponding to the target video, before sending the first indication information to the client in step 101, the method further includes:

step S11, analyzing a video segment positioned in front of a branch node in a target video to obtain a characteristic set of the video segment;

and step S12, determining the content interaction option corresponding to the video segment according to the feature set.

In the embodiment of the invention, the server side can determine the characteristic set of the video segment by analyzing the video segment positioned in front of the branch node in the target video, and further determine the content interaction option of the target video according to the characteristic set of the video segment.

Wherein the feature set comprises: at least one of a video identification, a time identification, an environment identification, a content tag, an event type, a main character of the video segment.

It should be noted that the feature set in the embodiment of the present invention is used to characterize the video features of the video segment, and specifically may include at least one of a time tag, an event tag, a person tag, and a scene tag of the video segment. The server side can determine the feature set of the video segment by analyzing the video content of the video segment from multiple dimensions such as language, characters, objects, scenes and the like.

The time tag is used for representing the playing time of the video segment in the interactive scenario, and the starting time point and the ending time point of the target video can be used as the time tag of the video segment; the playing time period of the video segment may also be divided into several time periods, and corresponding tags are respectively set for each time period, and a tag corresponding to the time period matching the playing time of the video segment is used as the time tag of the video segment, for example, the total playing time of the interactive drama is divided into 3 time periods, and a different color tag is set for each time period, for example, the tag of the time period 1 is red, the tag of the time period 2 is yellow, the tag of the time period 3 is blue, and the playing time of the video segment a matches the time period 2, so that the yellow tag is used as the time tag of the video segment a.

The event tag is used to represent an event type of a scenario event corresponding to the video segment, and the event tag may be a simple descriptive language of the scenario event, such as "emotional break", "birthday", "family party", "martial arts and forest meeting", and the like.

The character tags are used to represent main characters of the scenario events corresponding to the video segments, such as "male and female masters", "male and female parents", and the like. The server side can perform feature recognition on each character role appearing in the video frequency band according to the character setting of the interactive drama, and determine the character tag of the video frequency band. And corresponding character tags can be set for each character role in the video band in advance according to the character setting of the interactive drama.

The scene labels are used for representing environment information of the scenario events corresponding to the video segments, such as "meeting room", "premium restaurant", "amusement park", and the like. The server side can identify background information in the video band by performing picture analysis on the video frame of the video band, so as to determine the scene label of the video band.

In the embodiment of the present invention, after the server determines the feature set of the video segment, a scenario tag of the video segment may be further generated according to the feature set of the video segment, where the scenario tag is used to briefly summarize video content of the video segment. For example, for a video segment a, the feature set thereof includes a character tag "men and two" and an event tag "relationship between men and women who are intentionally picked up", then, from the feature set of the video segment a, a scenario tag "relationship between men and women who are intentionally picked up" may be generated. Furthermore, after the plot label of the video segment is determined, the content interaction option meeting the grammar semantic specification is generated according to the content expressed by the plot label by carrying out grammar semantic analysis on the plot label.

After the server side determines the scenario label corresponding to the video segment according to the feature set of the video segment, semantic analysis can be further performed on the scenario label to determine an event type and/or a main character corresponding to the scenario label, and then a content interaction option corresponding to the video segment is determined according to the determined event type and/or the main character. For example, if the scenario tag of the video segment a is "relationship between men and women who intentionally pick up two men and women", and the scenario tag is subjected to scenario analysis, the event type corresponding to the scenario tag is determined to be "picking separation", and the main character is "men and two", then the interaction problem of content interaction options can be generated according to the determined event type and the main character, "can understand the practice of men and two? ", and the interactive answer to the content interaction option: answer 1 "understand", answer 2 "do your own", etc. Each content interaction option can correspond to at least two interaction answers, and different interaction answers represent different trends, so that when a user performs interaction operation on the content interaction options, the personalized preference of the user on the currently played video content can be determined according to the user interaction data.

In an optional embodiment of the present invention, a pre-trained neural network model may also be utilized to process a feature set of a video segment to obtain a content interaction option corresponding to the video segment, and the determining, according to the feature set, the content interaction option corresponding to the video segment in step S12 includes:

and processing the feature set based on a pre-trained content interaction option generation model to obtain the content interaction options corresponding to the video segment.

In the embodiment of the invention, the content interaction option generation model can be trained in advance, and the feature set of the video segment is processed according to the trained content interaction option generation model, so that the content interaction option corresponding to the video segment can be directly obtained, and the generation efficiency of the content interaction option is improved.

Specifically, a training sample set including a feature set of a video segment and a target content interaction option corresponding to the feature set is obtained, iterative training is performed on a content interaction option generation model based on the training sample set, in each round of training, a loss value of the content interaction option generation model is determined according to an output result of the content interaction option generation model and the target content interaction option in the training sample set, and model parameters of the content interaction option generation model are adjusted according to the loss value until the loss value meets a convergence condition, so that a trained content interaction option generation model is obtained.

In an optional embodiment of the present invention, when determining the target branching scenario corresponding to the branching node based on the user interaction data, the user interaction data may be analyzed first to determine the personalized preference of the user for the currently played video content, and then the target branching scenario corresponding to the branching node is determined according to the personalized preference of the user: step 103, determining a target branching scenario corresponding to the branching node based on the user interaction data includes:

step S21, based on the user interaction data, determining the personalized preference of the user to the currently played video content;

and step S22, determining the target branching scenarios corresponding to the branching nodes according to the matching degree of each branching scenario corresponding to the branching node and the personalized preference.

The content interaction option in the embodiment of the invention is determined according to the video content of the target video, the user interaction data is determined according to the interaction operation executed by the user on the content interaction option, and the personalized preference of the user on the currently played video content can be determined by further analyzing the user interaction data.

Therefore, in the embodiment of the present invention, the matching degree between each branching scenario corresponding to a branching node and the personalized preference of the user is respectively determined, and the target branching scenario corresponding to the branching node is determined according to the matching degree. Specifically, the branching scenario with the matching degree with the personalized preference of the user greater than a preset threshold is determined as the target branching scenario.

In an optional embodiment of the present invention, the target video includes at least one video segment, each video segment corresponds to at least one content tag, and the determining, based on the user interaction data, the personalized preference of the user for the currently played video content in step S21 includes:

substep S211, comparing the output time of the content interaction option with the playing time of each video segment, and determining the video segment corresponding to the content interaction option;

substep S212, determining a scoring dimension corresponding to the content interaction option according to the content label of the video segment corresponding to the content interaction option, wherein the scoring dimension is in one-to-one correspondence with the content label;

substep S213, determining the scoring value of the user on the scoring dimension according to the user interaction data;

and a substep S214, if the score value on the scoring dimension meets a preset condition, determining that the content tag is a preference tag of the user for the target video.

The video segment of the target video can be any segment of video located before the branch node in the target video. The content label of the video segment is used for characterizing the video content of the video segment, and the content label can be descriptive language of the video content, such as "love of chief role of male and female, but love of chief role of male and female, silently guard", "love of chief role of female is too late, force of male is strong, two intentions of male are teased, misunderstanding between chief roles of male and female is deepened", and the like.

The user interaction data may include a video identifier of a target video corresponding to the content interaction option, and an option identifier of the content interaction option. If the content interaction options comprise an interaction question and at least two interaction answers, the user interaction data further comprises answer identifications of the interaction answers.

After receiving the user interaction data aiming at the content interaction option, the server can determine a target video corresponding to the content interaction option according to the video identification in the user interaction data, and then compare the output time of the content interaction option with the playing time of each video segment in the target video to determine the video segment corresponding to the content interaction option. Specifically, if the playing time of the video segment includes the output option of the content interaction option, it is determined that the video segment is the video segment corresponding to the content interaction option.

In the embodiment of the invention, the user interaction data is determined according to the interaction operation of the user for the content interaction option, the language of the content interaction option generally has a tendency, and different content interaction options represent different positions for the video content. By analyzing the user interaction data and the content label of the video segment corresponding to the content interaction option, the video content preference of the user for the content label can be determined, so that the personalized preference of the user for the currently played video content can be determined.

Each content tag corresponds to a scoring dimension, and the scoring dimension of the content tag can be used as the scoring dimension of the content interaction option corresponding to the content tag. The specific options of each content interaction option or the interaction answers of the content interaction options correspond to different scoring values. According to the user interaction data of the user aiming at the content interaction option, the scoring value of the user on the scoring dimension corresponding to the content interaction option can be determined.

If a video segment corresponds to a plurality of content interaction options, the content tag of the video segment can be simultaneously used as the content tag corresponding to each content interaction option of the video segment, that is, each content interaction option of the video segment corresponds to the same scoring dimension. Different weight values can be set for different content interaction options on the same grading dimension, and the grading value corresponding to each content interaction option selected by the user on the grading dimension is determined according to the user interaction data; and then determining the scoring value of the user in the scoring dimension according to the weighting value and the scoring value of each content interaction option. For example, the user performs a selection operation on both content interaction option 1 and content interaction option 2 of video segment a, and content interaction option 1 and content interaction option 2 correspond to the same scoring dimension B1, where the weight value of content interaction option 1 in scoring dimension B1 is w1, and the weight value of content interaction option 2 in scoring dimension B1 is w 2. And determining that the score value of the content interaction option 1 selected by the user is v1 and the score value of the content interaction option 2 is v2 according to the user interaction data, and then the score value S of the user in the scoring dimension B1 is w1 v1+ w2 v 2.

If the video segment corresponds to at least two content tags, the content interaction option corresponding to the video segment corresponds to at least two scoring dimensions. Different weight values can be set on different scoring dimensions for the same content interaction option, then the scoring value of the content interaction option selected by the user on each scoring dimension is determined according to the user interaction data, and the scoring value vector of the user is obtained according to the scoring value of the content interaction option on each scoring dimension and the weighting value of the content interaction option on each scoring dimension. For example, the server determines that the scoring dimensions corresponding to the content interaction option 1 are B1, B2 and B3. Wherein, the weight value of the content interaction option 1 in the scoring dimension B1 is m1, the weight value in the scoring dimension B2 is m2, and the weight value in the scoring dimension B3 is m 3. The value of the content interaction option 1 on the scoring dimension B1 is determined to be v1, the value of the score on the scoring dimension B2 is determined to be v2, and the value of the score on the scoring dimension B3 is determined to be v3 according to the user interaction data. Then, the score value vector of the user may be determined to be (m1 × v1, m2 × v2, m3 × v 3).

According to the scoring value of the user on the scoring dimension corresponding to the content interaction option or the scoring value vector of the user, the preference label of the user on the target video can be determined. Specifically, the content tag corresponding to the scoring dimension whose score value exceeds the preset threshold value may be used as the preference tag of the user, or a corresponding relationship between the scoring dimension corresponding to the content tag and the preference tag of the user may be preset, and then the preference tag of the user is determined according to the corresponding relationship and the score value of the user.

In the embodiment of the present invention, the content interaction option may be composed of at least two options, or may be composed of one interaction question and at least two interaction answers.

If the content interaction options comprise at least two options, the scoring value of each option on the scoring dimension corresponding to the content tag of the video segment can be preset, and then the scoring value of the user on the scoring dimension corresponding to the content tag is determined according to the options selected by the user.

If the content interaction options comprise preset interaction questions and interaction answers, wherein each interaction question corresponds to at least two interaction answers, the interaction answer selected for the interaction question is determined according to the user interaction data, then the score value corresponding to the user answer selected by the user is determined according to a preset score scale, and the score value of the user in the score dimension corresponding to the content label can be determined according to the score value and the weight value of the interaction question in the score dimension corresponding to the content label.

The preset scoring scale comprises scoring values of all interactive answers corresponding to all interactive questions on scoring dimensions corresponding to all content labels. Referring to table 1, a preset rating scale according to an embodiment of the present invention is shown:

TABLE 1

In table 1, "1" indicates that the user prefers the content indicated by the corresponding content tag, "-1" indicates that the user dislikes the content indicated by the corresponding content tag, and "0" indicates that the interaction problem is not related to the content tag. With the content label B1 of the target video as "love of chief role of man and woman, but love of man and woman in mind, acquiescent guard", the interaction problem Q1 is "worth doing this acquiescent payment of man and woman? ", the interactive answer Q1-a1 is" worth ", the interactive answer Q2-a2 is" love but not get, sadness ", for example, if it is determined that the interactive answer selected by the user for the interactive question Q1 is Q1-a1 according to the user interaction data, it may be determined that the score value corresponding to the interactive answer selected by the user is 1 according to table 1. Assuming that the weight value of the interaction question Q1 is m1, the score value m1 × 1 ═ m1 of the user in the scoring dimension corresponding to the content tag B1.

In practical application, a preset rating scale may be determined according to specific requirements and specific contents of the content tags and the content interaction options, which is not specifically limited in the embodiment of the present invention.

In an optional embodiment of the present invention, the feature tag corresponding to each branching scenario may be predetermined, and then the feature tag of each branching scenario is compared with the preference tag of the user to determine the target branching scenario: step S22, determining the target branching scenario corresponding to the branch node according to the matching degree of each branching scenario corresponding to the branch node and the personalized preference, includes:

the substep S221, obtaining a feature label of each branch scenario corresponding to the branch node;

a substep S222, calculating a matching degree between the feature tag of each branching scenario and the preference tag of the user for the target video according to the feature tag of each branching scenario;

and a substep S223 of determining the target branching scenario according to the matching degree of the feature tag of each branching scenario and the preference tag.

Specifically, a corresponding relationship between the target video and the branching scenario may be established in advance, for example, a corresponding relationship between a video identifier of the target video and the branching scenario is established, and a feature tag of each branching scenario is recorded. The server side can inquire the branch scenarios corresponding to the video identification in the database according to the video identification of the target video, and determine the feature tag of each branch scenario.

The manner of determining the feature tags of the branching scenarios is similar to the method of determining the scenario tags of the target videos: analyzing the plot content of the branch plot from multiple dimensions such as languages, characters, objects, scenes and the like to obtain a feature set of the branch plot, and then generating a feature tag of the branch plot according to the feature set of the branch plot.

After the server determines the feature tags of the branch scenarios corresponding to the target video, the preference tags of the user to the target video are compared with the feature tags of each branch scenario respectively, and the target branch scenarios are determined according to the comparison result. Specifically, the similarity between the feature tag of the branching scenario and the preference tag of the user for the target video may be calculated, and the branching scenario corresponding to the feature tag with the highest similarity to the preference tag is determined as the target branching scenario, so that the determined target branching scenario best meets the user preference.

In an optional embodiment of the present invention, the feature tag of the branching scenario may be set manually, or the feature tag of the branching scenario may be determined automatically by the service segment through content analysis of the branching scenario. In any way, the feature tag of the branching scenario may be stored in a preset database in advance, and the obtaining the feature tag of each branching scenario corresponding to the branching node in sub-step S221 includes:

a11, under the condition of receiving a branching scenario query request, acquiring a video identifier of the target video from the branching scenario query request;

a12, obtaining the feature label of each branching scenario corresponding to the branching node from a preset database according to the video identification.

In the embodiment of the present invention, when the current playing progress of the target video approaches to a branching node of a branching scenario, the client may send a branching scenario query request to the server to obtain the target branching scenario to be played.

And the server receives the branching scenario query request sent by the client, responds, and acquires the feature tag of each branching scenario corresponding to the target video from a preset database according to the video identifier of the target video contained in the branching scenario query request so as to determine the target branching scenario matched with the preference tag of the user according to the feature tag of the branching scenario.

In an optional embodiment of the present invention, on the basis of determining the target branching scenario according to the user interaction data for the content interaction option, user behavior data may be further introduced, and the target branching scenario is determined according to the user interaction data and the user behavior data together. Step 103, before determining the target branching scenario corresponding to the branching node based on the user interaction data, the method further includes:

step S31, obtaining user attribute data and/or user behavior data, wherein the user behavior data is determined by the user behavior of the user on the client;

step 103, determining a target branching scenario corresponding to the branching node based on the user interaction data includes:

step S32, determining the personalized preference of the user for the currently played video content based on the user interaction data and the user behavior data;

and step S33, determining the target branching scenarios corresponding to the branching nodes according to the matching degree of each branching scenario corresponding to the branching node and the personalized preference.

Wherein the user attribute data may include basic data such as gender, age, avatar, and/or portrait of the user. The user representation may be analyzed based on user behavior and underlying data. The user behavior data is determined by the client according to the user behavior of the user for the target video, and the user behavior data comprises at least one of click, browsing time, click speed, shake-shake, blow-blow, user facial expression, comment content, barrage content, praise object, play progress adjustment information and play speed adjustment information of the user for the target video.

It should be noted that the user attribute data and the user behavior data may be obtained from a server or a client. The client is not limited to the client currently used by the user for watching the target video, and may be another client used by the user. In other words, the user attribute data and user behavior data may include network data of the user on any client.

In the embodiment of the invention, the personalized preference of the user on the currently played video content can be determined according to the user behavior data and the user interaction data aiming at the content interaction options. For example, the weight value of the scoring dimension corresponding to the content tag may be adjusted according to the user behavior data of the user for the target video. For example, for a video segment a, the content label B1 is "the female is left without, and male and female forces are forced, and the user accelerates the playing speed when playing the target video, which indicates that the user does not like the content corresponding to the content label B1, so that the weight value of the scoring dimension corresponding to the content label B1 can be reduced, and the influence of the scoring value of the scoring dimension corresponding to the content label B1 on the overall scoring value of the user can be reduced. Or, the user behavior data contains many comment information about the scenario content described by the content tag B1, which indicates that the user is interested in the scenario related to the content tag, and the weight of the scoring dimension corresponding to the content tag B1 may be increased.

According to the embodiment of the invention, the behavior of the user aiming at the target video is analyzed in a multi-dimensional way by combining the user behavior data and the user interaction data of the user aiming at the target video, the score value of the user on the scoring dimension corresponding to the content label is comprehensively determined, the accuracy of the score value can be improved, the accuracy of the personalized preference of the user aiming at the target video determined according to the score value is further improved, and the determined target branching scenario is more in line with the preference of the user.

In summary, the video playing method provided in the embodiment of the present invention may instruct the client to output the content interaction option in the target video playing process by sending the first instruction information to the client, and receive the user interaction data determined by the client based on the content interaction option, where the user interaction data is used to instruct the user about the personalized preference of the currently played video content; furthermore, based on the user interaction data, a target branching scenario corresponding to the branching node is determined, second indication information is sent to the client, the client is indicated to play the target branching scenario at the branching node, the user does not need to manually select the branching scenario at the branching node of the target video, and the continuity of video playing and the interestingness of the branching scenario are guaranteed.

In addition, the content interaction option in the embodiment of the invention is different from the selection option of the branching scenario, can be displayed in the process of playing the target video, does not influence the normal playing of the target video, does not cause the conditions of video playing interruption and the like, and determines the preference of the user through an option interaction mode on the premise of ensuring the normal playing of the video and is used for guiding the selection of the branching scenario at the subsequent branching node. Therefore, the video playing method provided by the embodiment of the invention can automatically determine the target branching scenario to be played according to the selection operation of the user on the content interaction option under the condition of not influencing the normal playing of the video, thereby ensuring the continuity of video playing and the interest of the branching scenario.

Fig. 4 is a flowchart of steps of another video playing method provided in an embodiment of the present invention, and as shown in fig. 4, the method is applied to a client, and specifically may include:

step 401, receiving first indication information from a server, and outputting a content interaction option in the target video playing process.

Step 402, determining user interaction data according to the interaction operation aiming at the content interaction option, wherein the user interaction data is used for indicating the personalized preference of the user to the currently played video content.

Step 403, sending the user interaction data to the server, so that the server determines a target branching scenario corresponding to a branching node according to the user interaction data.

And step 404, receiving second indication information from the server.

And step 405, playing the target branching scenario at the branching node according to the second indication information.

In the embodiment of the invention, the target video is an interactive video comprising branch nodes, such as an interactive movie, an interactive art, an interactive television and the like. The branching node of the target video includes at least two branching scenarios, and different branching scenarios will lead to different final outcomes. And when the target video is played to the branch node, playing the target branch scenario determined in at least two branch scenarios of the branch node. The client serves as video playing equipment, and after first indication information sent by the server is received, content interaction options corresponding to the target video are output in the playing process of the target video, so that a user can perform interaction operation on the content interaction options through the client.

It should be noted that the content interaction option in the embodiment of the present invention is determined according to the video content located before the branch node in the target video, and includes a descriptive language related to the video content of the target video. Different from the prior art, interactive options are set at interactive nodes positioned in front of the branch nodes, the interactive options correspond to the branch scenarios of the branch nodes one by one, and then target branch scenarios to be played by the branch nodes are determined according to the interactive options selected by a user.

Alternatively, the content interaction options may include one interaction question and at least two interaction answers, and the interaction question corresponding to the target video a is: "is this acquaintance of male two worth? ", the corresponding interactive answers include: answer 1 "worth", answer 2 "love but not, sadness", etc. For the specific expression form of the content interaction option, the embodiment of the present invention is not particularly limited, as long as the personalized preference of the user for the currently played video content can be reflected based on the user interaction data of the user for the content interaction option.

When the client displays the content interaction option, a floating window can be popped out from the playing interface of the target video, the content interaction option is displayed in the floating window, and the target video is in a normal playing state, so that the playing continuity of the target video is not affected. And, in order to further reduce the occlusion that the content interaction option is playing content, the transparency of the floating window may be increased. Or, setting the display time of the content interaction option, and if the user does not select the content interaction option within the preset display time, ending the display of the content interaction option. The display position of the content interaction option can be set at the edge position of the lower right corner or the lower left corner of the playing interface of the target video, so that the shielding of the played content is reduced as much as possible.

And the client generates user interaction data according to the interaction operation of the user aiming at the content interaction option. The user interaction data is used for reflecting specific options or interaction answers selected by the user, and may include video identifiers of target videos corresponding to the content interaction options and option identifiers of the content interaction options. After determining the user interaction data of the user aiming at the content interaction option, the client sends the user interaction data to the server, and provides basis for the server to determine the preference label of the user aiming at the target video. Specifically, the server determines a target branching scenario corresponding to the branching node according to the received user interaction data, and sends second indication information to the client, so that the client is indicated to automatically play the target branching scenario at the branching node of the target video, and the user does not need to manually select the target branching scenario. In addition, the target branching scenario in the embodiment of the invention is determined by the server according to the user interaction data of the user aiming at the content interaction option, the content interaction option is related to the video content of the target video, the preference of the user aiming at the target video can be determined according to the selection operation of the user on the content interaction option, and then the branching scenario according with the preference of the user is determined to be used as the target branching scenario and played at the client. Therefore, the video playing method provided by the embodiment of the invention can automatically play the branching scenario at the playing node of the branching scenario without manually selecting the branching scenario by the user, and can play the branching scenario according to the preference of the user.

In an optional embodiment of the present invention, whether to continue outputting the content interaction option may be determined according to an output duration of the content interaction option. After outputting the content interaction option in the target video playing process in step 401, the method further includes:

step P11, counting the output duration of the content interaction options;

and step P12, if the output duration of the content interaction option meets a preset value, stopping outputting the content interaction option.

In order to reduce the influence of the content interaction option on the target video playing content, the embodiment of the invention can also count the output time of the content interaction option, and stop outputting the content interaction option when the output time of the content option exceeds the preset value.

In an optional embodiment of the present invention, the content interaction option includes at least two interaction answers, and the determining 402 user interaction data according to the interaction operation for the content interaction option includes:

step P21, collecting the interaction operation information of the user aiming at the content interaction option;

and step P22, determining the interactive answer selected by the user and the answer identifier of the interactive answer according to the interactive operation information to obtain user interactive data.

In the embodiment of the present invention, the content interaction option may be composed of at least two options, or may be composed of one interaction question and at least two interaction answers. For example, for the target video a, the related scenario is "love of principals of men and women, but men and women are loved by principals of men and women, and silently guardian", and the server determines that the content interaction options corresponding to the target video a according to the feature set thereof are: option 1 "admirable female owner has such guardian", option 2 "men are sad, love but not get"; or, the interaction problem corresponding to the target video a is as follows: "is this acquaintance of male two worth? ", the corresponding interactive answers include: answer 1 "worth", answer 2 "love but not, sadness", etc.

For the content interaction options comprising at least two interaction answers, a corresponding answer identifier can be preset for each interaction answer, so that when the interaction operation of the user for the content interaction options is received, the answer identifier of the interaction answer selected by the user is determined according to the interaction operation, and the user interaction data is generated according to the answer identifier, so that the server side can determine the target branching scenario according to the user interaction data.

In an optional embodiment of the present invention, on the basis of determining the target branching scenario according to the user interaction data for the content interaction option, user behavior data may be further introduced, and the target branching scenario is determined according to the user interaction data and the user behavior data together. After the step 403 of sending the user interaction data to the server, the method further includes:

step P31, determining user behavior data according to the user behavior of the user on the client;

and step P32, sending the user behavior data to the server, so that the server determines the personalized preference of the user for the currently played video content according to the user interaction data and the user behavior data.

The user behavior data is determined by the client according to the user behavior of the user for the target video, and the behavior data comprises at least one of comment content, barrage content, a praise object, playing progress adjustment information and playing speed adjustment information.

In the embodiment of the invention, the personalized preference of the user on the currently played video content can be determined according to the user behavior data and the user interaction data aiming at the content interaction options.

After receiving the preset behavior data sent by the client, the server can adjust the weighted value of the scoring dimensionality corresponding to the content label according to the user behavior data of the user for the target video. For example, for a video segment a, the content label B1 is "the female is left without, and male and female forces are forced, and the user accelerates the playing speed when playing the target video, which indicates that the user does not like the content corresponding to the content label B1, so that the weight value of the scoring dimension corresponding to the content label B1 can be reduced, and the influence of the scoring value of the scoring dimension corresponding to the content label B1 on the overall scoring value of the user can be reduced. Or, the user behavior data contains many comment information about the scenario content described by the content tag B1, which indicates that the user is interested in the scenario related to the content tag, and the weight of the scoring dimension corresponding to the content tag B1 may be increased.

According to the embodiment of the invention, the behavior of the user aiming at the target video is subjected to multi-dimensional analysis by combining the user behavior data and the user interaction data of the user aiming at the target video, the personalized preference of the user aiming at the target video is comprehensively determined, the accuracy of the determined personalized preference is improved, and the finally determined target branching scenario is more in line with the preference of the user.

In an optional embodiment of the present invention, before the receiving the second indication information from the server in step 404, the method further includes: and sending a branching scenario query request to the server, wherein the branching scenario query request comprises the video identifier of the target video, so that the server determines the target branching scenario corresponding to the target video according to the video identifier.

In the playing process of the target video, the client side can send a branching scenario query request to the server side so as to obtain the target branching scenario to be played. The video identifier of the target video can be carried in the branching scenario inquiry request sent by the client, so that the server can determine the target branching scenario corresponding to the target video according to the video identifier after receiving the branching scenario inquiry request.

In summary, the video playing method provided in the embodiment of the present invention may output the content interaction option in the target video playing process according to the first indication information by receiving the first indication information from the server, determine the user interaction data according to the interaction operation for the content interaction option, and then send the user interaction data to the server, so that the server determines the target branching scenario corresponding to the branch node according to the user interaction data, and receives the second indication information from the server, automatically play the target branching scenario at the branch node, without manually selecting the branch scenario at the branch node of the target video by the user, thereby ensuring continuity of video playing and interestingness of the branch scenario. In addition, the content interaction options in the embodiment of the invention can be displayed in the process of playing the target video, and the normal playing of the target video is not influenced. Therefore, the video playing method provided by the embodiment of the invention can automatically determine the target branching scenario to be played according to the selection operation of the user on the content interaction option under the condition of not influencing the normal playing of the video, thereby ensuring the continuity of video playing and the interest of the branching scenario.

Fig. 5 is a block diagram of a video playing apparatus according to an embodiment of the present invention, where the video playing apparatus is applied to a server, and as shown in fig. 5, the apparatus 50 may include:

a first sending module 501, configured to send first indication information to a client, where the first indication information is used to indicate that the client outputs a content interaction option in a target video playing process;

a first receiving module 502, configured to receive user interaction data from the client, where the user interaction data is determined by the client based on the content interaction option, and the user interaction data is used to indicate a personalized preference of a user for currently played video content;

a first processing module 503, configured to determine, based on the user interaction data, a target branching scenario corresponding to a branching node;

a second sending module 504, configured to send second indication information to the client, where the second indication information is used to indicate the client to play the target branching scenario at the branch node.

Optionally, the apparatus 50 further comprises:

the characteristic set determining module is used for analyzing the video segments positioned in front of the branch nodes in the target video to obtain the characteristic set of the video segments;

and the content interaction option determining module is used for determining the content interaction option corresponding to the video segment according to the feature set.

Optionally, the content interaction option determining module includes:

and the content interaction option determining submodule is used for processing the feature set based on a pre-trained content interaction option generation model to obtain a content interaction option corresponding to the video segment.

Optionally, the feature set includes: at least one of a video identification, a time identification, an environment identification, a content tag, an event type, a main character of the video segment.

Optionally, the first processing module 503 includes:

the personalized preference determining submodule is used for determining the personalized preference of the user to the currently played video content based on the user interaction data;

and the target branch scenario determining submodule is used for determining the target branch scenarios corresponding to the branch nodes according to the matching degree of each branch scenario corresponding to the branch node and the personalized preference.

Optionally, the target video includes at least one video segment, each video segment corresponds to at least one content tag, and the personalized preference determining sub-module includes:

the video segment determining unit is used for comparing the output time of the content interaction option with the playing time of each video segment and determining the video segment corresponding to the content interaction option;

the first personalized preference determining unit is used for determining scoring dimensionality corresponding to the content interaction options according to content labels of video segments corresponding to the content interaction options, and the scoring dimensionality corresponds to the content labels one to one;

the scoring value determining unit is used for determining the scoring value of the user on the scoring dimension according to the user interaction data;

and the preference tag determining unit is used for determining the content tag as a preference tag of the user for the target video if the score value on the scoring dimension meets a preset condition.

Optionally, the target branching scenario determination sub-module includes:

the characteristic label acquisition unit is used for acquiring a characteristic label of each branching scenario corresponding to the branching node;

the matching degree determining unit is used for calculating the matching degree of the feature label of each branch scenario and the preference label of the user for the target video according to the feature label of each branch scenario;

and the target branching scenario determining unit is used for determining the target branching scenario according to the matching degree of the feature tag of each branching scenario and the preference tag.

Optionally, the feature tag obtaining unit includes:

the video identifier acquisition subunit is used for acquiring the video identifier of the target video from the branching scenario query request under the condition that the branching scenario query request is received;

and the feature tag obtaining subunit is used for obtaining the feature tag of each branching scenario corresponding to the branching node from a preset database according to the video identifier.

Optionally, the apparatus 50 further comprises:

the user behavior data receiving module is used for acquiring user attribute data and/or user behavior data, and the user behavior data is determined by the user behavior of the user on the client;

the first processing module comprises:

a second personalized preference determining submodule, configured to determine a personalized preference of the user for the currently played video content based on the user interaction data and the user behavior data;

and the second target branching scenario determining submodule is used for determining the target branching scenario corresponding to the branching node according to the matching degree of each branching scenario corresponding to the branching node and the personalized preference.

Optionally, the user behavior data includes at least one of comment content, barrage content, a praise object, play progress adjustment information, and play speed adjustment information.

Fig. 6 is a block diagram of another video playing apparatus according to an embodiment of the present invention, where the video playing apparatus is applied to a client, and as shown in fig. 6, the apparatus 60 may include:

a second receiving module 601, configured to receive first indication information from a server, and output a content interaction option in the target video playing process;

a second processing module 602, configured to determine user interaction data according to an interaction operation for the content interaction option, where the user interaction data is used to indicate a personalized preference of a user for currently played video content;

a third sending module 603, configured to send the user interaction data to the server, so that the server determines a target branching scenario corresponding to a branching node according to the user interaction data;

a third receiving module 604, configured to receive second indication information from the server;

Optionally, the apparatus 60 further comprises:

the output time counting module is used for counting the output time of the content interaction options;

and the output control module is used for stopping outputting the content interaction option if the output time of the content interaction option exceeds a preset value.

Optionally, the content interaction option includes at least two interaction answers, and the second processing module 602 includes:

the interactive manipulation receiving submodule is used for receiving the interactive manipulation of the user aiming at the content interactive option;

the interactive answer determining sub-module is used for determining the interactive answer selected by the user and the answer identifier of the interactive answer according to the interactive operation;

and the user interaction data determining submodule is used for determining user interaction data corresponding to the interaction operation according to the answer identifier of the interaction answer selected by the user.

Optionally, the apparatus 60 further comprises:

and the branching scenario query request sending module is used for sending a branching scenario query request to the server, wherein the branching scenario query request comprises the video identifier of the target video, so that the server determines the target branching scenario corresponding to the target video according to the video identifier.

Optionally, the apparatus 60 further comprises:

the user behavior data determining module is used for determining user behavior data according to the user behavior of the user on the client;

and the user behavior data sending module is used for sending the user behavior data to the server so that the server determines the personalized preference of the user on the currently played video content according to the user interaction data and the user behavior data.

Optionally, the behavior data includes at least one of comment content, barrage content, a praise object, play progress adjustment information, and play speed adjustment information.

For the above device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, refer to the partial description of the method embodiment.

In addition, an embodiment of the present invention further provides a video playing system, where the system includes: a server and a client. The server is configured to implement each process of the video playing method embodiment on the server side, and the client is configured to implement each process of the video playing method embodiment on the client side.

Embodiments of the present invention also provide a device for video playback, the device comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs configured to be executed by the one or more processors comprise instructions for performing the video playback method.

The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the video playing method embodiment, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.

As is readily imaginable to the person skilled in the art: any combination of the above embodiments is possible, and thus any combination between the above embodiments is an embodiment of the present invention, but the present disclosure is not necessarily detailed herein for reasons of space.

The video playback methods provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The structure required to construct a system incorporating aspects of the present invention will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of an operation execution method according to an embodiment of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A video playing method is applied to a server side, and the method comprises the following steps:

2. The method of claim 1, wherein before sending the first indication information to the client, the method further comprises:

analyzing a video segment positioned in front of a branch node in a target video to obtain a characteristic set of the video segment;

and determining the content interaction option corresponding to the video segment according to the feature set.

3. The method according to claim 2, wherein said determining a content interaction option corresponding to said video segment according to said feature set comprises:

4. The method of claim 2 or 3, wherein the feature set comprises: at least one of a video identification, a time identification, an environment identification, a content tag, an event type, a main character of the video segment.

5. The method according to any one of claims 1-4, wherein the determining a target branching scenario corresponding to a branching node based on the user interaction data comprises:

determining personalized preferences of the user for currently played video content based on the user interaction data;

and determining the target branch scenarios corresponding to the branch nodes according to the matching degree of each branch scenario corresponding to the branch node and the personalized preference.

6. The method of claim 5, wherein the target video comprises at least one video segment, each video segment corresponding to at least one content tag, and wherein determining the personalized preferences of the user for the currently playing video content based on the user interaction data comprises:

comparing the output time of the content interaction option with the playing time of each video segment, and determining the video segment corresponding to the content interaction option;

determining scoring dimensions corresponding to the content interaction options according to content labels of video segments corresponding to the content interaction options, wherein the scoring dimensions correspond to the content labels one to one;

determining the scoring value of the user on the scoring dimension according to the user interaction data;

and if the score value on the scoring dimension meets a preset condition, determining that the content tag is a preference tag of the user for the target video.

7. The method according to claim 5, wherein the determining the target branching scenario corresponding to the branching node according to the matching degree of each branching scenario corresponding to the branching node and the personalized preference includes:

acquiring a feature tag of each branch scenario corresponding to the branch node;

according to the feature tag of each branch scenario, calculating the matching degree of the feature tag of each branch scenario and the preference tag of the user for the target video;

and determining the target branching scenarios according to the matching degree of the characteristic labels of each branching scenario and the preference labels.

8. The method according to claim 7, wherein the obtaining of the feature tag of each branching scenario corresponding to the branching node comprises:

under the condition that a branching scenario query request is received, acquiring a video identifier of the target video from the branching scenario query request;

and acquiring the feature label of each branching scenario corresponding to the branching node from a preset database according to the video identifier.

9. The method according to any one of claims 1-4, wherein before determining the target branching scenario corresponding to the branching node based on the user interaction data, the method further comprises:

acquiring user attribute data and/or user behavior data, wherein the user behavior data is determined by the user behavior of the user on a client;

the determining the target branching scenario corresponding to the branching node based on the user interaction data includes:

determining personalized preferences of the user for currently playing video content based on the user interaction data and the user behavior data;

10. The method of claim 9, wherein the user behavior data comprises at least one of comment content, barrage content, a praise object, play progress adjustment information, and play speed adjustment information.

11. A video playing method is applied to a client side, and the method comprises the following steps:

receiving second indication information from the server;

12. The method of claim 11, wherein after outputting the content interaction option during the target video playback, the method further comprises:

counting the output duration of the content interaction options;

and if the output duration of the content interaction option meets a preset value, stopping outputting the content interaction option.

13. The method of claim 11, wherein the content interaction option comprises at least two interaction answers, and wherein determining user interaction data according to the interaction operation for the content interaction option comprises:

acquiring interaction operation information of a user aiming at the content interaction option;

and determining the interactive answer selected by the user and the answer identifier of the interactive answer according to the interactive operation information to obtain the user interactive data.

14. A video playback system, the system comprising:

a service end and a client end, wherein,

the server is used for executing the video playing method according to any one of claims 1 to 10;

the client is configured to execute the video playing method according to any one of claims 11 to 13.

15. A video playing apparatus, applied to a server, the apparatus comprising:

16. A video playing apparatus, applied to a client, the apparatus comprising:

17. An apparatus for video playback, the apparatus comprising the apparatus including a memory, and one or more programs, wherein the one or more programs are stored in the memory, and wherein execution of the one or more programs by the one or more processors comprises instructions for performing the video playback method of any of claims 1-13.

18. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements a video playback method as claimed in any one of claims 1 to 13.