Video playing method, program product, electronic equipment and storage medium

Abstract

The invention discloses a video playing method, a program product, electronic equipment and a storage medium. The video playing method comprises the following steps: collecting interaction information of a first member of a video synchronous playing group in a playing process of a first video; determining a plot node corresponding to the interaction information in the first video; according to the plot node and the playing progress of the first video played by the terminal equipment of the second member of the video synchronous playing group, performing spoken risk assessment on the second member to obtain an assessment result; and determining a presentation position of the interaction information in the first video played by the terminal device of the second member according to the evaluation result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a video playing method, a program product, an electronic device and a storage medium. BACKGROUND

[0002] Online video platforms generally support an online synchronous viewing function, allowing multiple users to simultaneously watch the same video content on different terminals and communicate in real time through text chat or voice.

[0003] In related technologies, user chat information may cause spoilers (plot revelation) or plot misplacement, which affects the viewing experience of users who have not yet watched subsequent plot content. SUMMARY

[0004] Therefore, the present application provides a video playing method, a program product, an electronic device and a storage medium.

[0005] The technical scheme of the present application is implemented as follows: On the one hand, the present application provides a video playing method, which comprises: collecting interaction information of a first member of a video synchronous playing group in a playing process of a first video; determining a plot node corresponding to the interaction information in the first video; performing spoiler risk assessment on a second member of the video synchronous playing group according to the plot node and a playing progress of the first video played by a terminal device of the second member, to obtain an assessment result; determining a presentation position of the interaction information in the first video played by the terminal device of the second member according to the assessment result.

[0006] In an embodiment, the determination of the plot node corresponding to the interaction information in the first video comprises: performing semantic analysis on the interaction information to obtain a semantic analysis result; searching for a plot node matching the semantic analysis result in a plot knowledge graph of the first video.

[0007] In an embodiment, the method further comprises: performing structured processing on the first video to obtain one or more of a plot action, a plot character, a keyword, and a plot time point; constructing the plot knowledge graph according to the one or more of the plot action, the plot character, the keyword, and the plot time point.

[0008] In an embodiment, the spoiler risk assessment on the second member according to the plot node and the playing progress of the first video played by the terminal device of the second member of the video synchronous playing group comprises: determining a time difference between the time point corresponding to the plot node and the playing progress of the first video played by the terminal device of the second member; if the time difference is greater than a first preset time length, determining that the assessment result is a first risk level; if the time difference is greater than a second preset time length and less than the first preset time length, determining that the assessment result is a second risk level; the first preset time length is greater than the second preset time length; if the time difference is less than the second preset time length, determining that the assessment result is a third risk level; wherein the first risk level is higher than the second risk level, and the second risk level is higher than the third risk level.

[0009] In an embodiment, the method further comprises: if the assessment result is the first risk level, determining that the presentation position is a video frame corresponding to the plot node in the first video; if the assessment result is the second risk level, monitoring the playing progress of the second member, if the playing progress of the second member reaches the time point corresponding to the plot node within a third preset time length, determining that the presentation position is the video frame corresponding to the plot node; if the playing progress of the second member does not reach the time point corresponding to the plot node within the third preset time length, the assessment result is changed to the first risk level; if the assessment result is the third risk level, determining that the presentation position is a video frame corresponding to the playing progress of the first video when the second member receives the interaction information.

[0010] In an embodiment, the method further comprises: determining the playing progress of each member of the video synchronous playing group; if the progress deviation between the playing progress of the second member and the playing progress of the first member is greater than a threshold value, initiating a progress synchronization suggestion to the terminal device of the second member; the playing progress of the first member is greater than the playing progress of the second member; if the indication information of the second member triggering the consent progress synchronization is obtained, synchronously adjusting the playing progress of the second member to be consistent with the playing progress of the first member.

[0011] In an embodiment, the method further comprises: If it is detected that the second member is in a non-watching state, detecting whether the video content of a first video about to be played by the terminal device of the second member is high-heat content or conforms to the preference of the second member; If the video content of the first video about to be played by the terminal device of the second member is high-heat content or conforms to the preference of the second member, sending pause playing suggestion information to the terminal devices of the other members of the video synchronous playing group; According to the voting information of all the members, determining whether to pause playing the first video, the voting information indicating whether to pause playing.

[0012] In another aspect, the embodiments of the present application also provide a computer program product, comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the video playing method.

[0013] In another aspect, the embodiments of the present application provide an electronic device, comprising a processor and a memory, which are connected to each other, wherein the memory is configured to store a computer program, the computer program comprising program instructions, and the processor is configured to invoke the program instructions to execute the steps of the video playing method provided by the first aspect of the embodiments of the present application.

[0014] In another aspect, the embodiments of the present application provide a computer readable storage medium, comprising: the computer readable storage medium storing a computer program. The computer program, when executed by a processor, implements the steps of the video playing method provided by the first aspect of the embodiments of the present application.

[0015] The embodiments of the present application determine the corresponding plot node of the interaction information in the first video by collecting the interaction information of the first member of the video synchronous playing group in the playing process of the first video, perform plot revealing risk assessment on the second member according to the plot node and the playing progress of the first video played by the terminal device of the second member, and obtain an assessment result. According to the assessment result, the presentation position of the interaction information in the first video played by the terminal device of the second member is determined. The embodiments of the present application present the interaction information at a suitable position through plot revealing risk assessment, which can effectively avoid plot revealing and plot dislocation discussion interference, and effectively protect the viewing rhythm of each member. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is an implementation flow diagram of a video playing method provided by the embodiments of the present application; Figure 2 is an architecture diagram of an online synchronous interactive screening hall system provided by the embodiments of the present application; Figure 3 is a schematic diagram of a video bullet screen processing flow provided by an embodiment of the present application; Figure 4 is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0018] Online video platforms generally have the demand for geographically asynchronous viewing, and each video platform is actively laying out social viewing functions. The online synchronous viewing function in the related technology mainly includes the following contents: 1. The server maintains the video playback progress of all users based on a unified timestamp; 2. If a user operates the playback control (such as pause, fast forward, jump), other users are automatically synchronized to the same progress; 3. The chat function is an independent module and is not coupled with video playback. The text or voice messages sent by the user are not associated with the current plot content; 4. The playback state and viewing rhythm difference between users need to rely on human coordination and do not have intelligent recognition and automatic processing mechanisms.

[0019] In summary, the related technology has the following defects: 1. The related technology adopts a "strong progress synchronization" strategy, all users must be synchronized in playback progress, and there is a lack of judgment on individual state, plot structure or user preference, which can easily lead to: Users are forced to play in the case of leaving, not being ready, etc., affecting the experience; Users miss key plot content and cannot effectively catch up with the progress.

[0020] 2. The user chat information in the related technology is not associated or managed with the video content, which can easily lead to: "Plot spoilers" between unsynchronized viewers; All messages are synchronized without screening and delay, lacking differentiated control; Unable to identify and correct discussion content that does not match the timeline.

[0021] 3. The playback control in the related technology highly depends on communication and coordination between users, and is not sufficient for the following scenarios: Users temporarily leave; The exciting plot is coming; Inconsistency of multiple interest points.

[0022] Embodiments of the present application aim to solve the following technical problems in the process of multiple online video synchronous watching: 1. Inconsistent viewing experience caused by different playing progress: related technologies lack the ability to identify and analyze user state and behavior, which can easily cause playing rhythm misalignment in multiple collaborative scenarios, affecting the experience.

[0023] 2. The problem of spoilers or plot misalignment caused by user chat: chat information under different progress can easily produce spoilers and misaligned discussions, lacking intelligent identification and display mechanisms.

[0024] 3. Lack of intelligent judgment in playing control: existing synchronization mechanisms cannot pause or cooperatively play according to user individual preferences, real-time state and plot importance.

[0025] 4. Overload of interactive information and picture interference: traditional input and output methods lead to cumbersome user input, large display area occupying screen space, and affect the sense of immersion.

[0026] 5. Lack of intelligent regulation ability for user preferences and plot structure: existing systems do not have synchronization judgment and coordination mechanisms based on plot semantics, time points and individual behavior.

[0027] In view of the above shortcomings of the related art, the embodiments of the present application provide a video playing method. In order to explain the technical solutions of the present application, the following will be described by specific embodiments.

[0028] Figure 1 is a flowchart of the implementation of a video playing method provided by the embodiments of the present application, the execution subject of the video playing method is an electronic device, for example, the execution subject can be a terminal device of a member in a video synchronous playing group. Referring to Figure 1 , the video playing method comprises: S101, collecting the interaction information of a first member of a video synchronous playing group in the playing process of a first video.

[0029] Among them, the video synchronous playing group includes multiple members, and the terminal devices corresponding to each member in the group play the same first video.

[0030] The embodiments of the present application can be applied to the terminal device of each member of the video synchronous playing group, for example, the execution subject of the embodiments of the present application can be the terminal device of the first member.

[0031] The embodiment can be deployed on a terminal device in the form of an application (Application, APP), or deployed on a terminal device through an AI Agent (Intelligent Agent). The AI Agent (also known as an artificial intelligence agent) is an intelligent entity capable of perceiving the environment, making decisions, and performing actions. When a member joins a video synchronous playback group, the terminal device of the member automatically starts the AI Agent, and the AI Agent collects interactive information sent by each member in real time.

[0032] In the embodiment, the AI Agent can be responsible for analyzing the user state (pausing playback), collecting the playback progress, collecting the chat content, and executing the playback progress synchronization and content control strategy.

[0033] Members in the video synchronous playback group can send interactive information (voice or text) for chatting, and the embodiment will intercept the interactive information of the first member and not directly display it.

[0034] The embodiment can be executed by the terminal device of the first member who sends the interactive information, or by the second member, which is any member in the video synchronous playback group except the first member.

[0035] S102, determine the corresponding plot node of the interactive information in the first video.

[0036] For example, the interactive information is subjected to semantic analysis, and keywords are extracted therefrom. For example, the first member says, “Wow, I didn't expect the murderer to be the butler!” by voice. First, the voice needs to be converted into text, and then keywords are extracted from the text through a keyword extraction algorithm.

[0037] For example, the interactive information is subjected to plot action recognition, and keywords such as “kill”, “reveal”, and “death” can be extracted.

[0038] The interactive information is subjected to character object recognition, and keywords such as “butler”, “main character”, and “murderer” can be extracted.

[0039] The interactive information is subjected to time clue matching, and keywords such as “last”, “ending”, and “just now” can be extracted.

[0040] The interactive information is subjected to emotion intensity evaluation, and exclamation words and tone words are extracted therefrom.

[0041] Video structuring is a technology of extracting multi-level features and performing semantic analysis on people, vehicles, and objects in a video through artificial intelligence technology, and converting unstructured video data into searchable structured information. The video content of the first video can be subjected to structured analysis in advance, and plot nodes, characters, and keywords are extracted.

[0042] Then, a plot node matching the keywords can be found in the structured analysis result of the first video, for example, by querying the keywords "butler" and "murderer", a plot node at 22:15 in the first video is matched.

[0043] In S103, a spoiler risk of the second member is evaluated according to the plot node and the playing progress of the first video played by the terminal device of the second member in the video synchronous playing group, and an evaluation result is obtained.

[0044] Here, the terminal device of each member in the video synchronous playing group can actively report the playing progress of the first video played to the server, and can obtain the playing progress of all members from the server.

[0045] In an embodiment, the time difference between the playing progress of the second member and the plot node, i.e., how long the terminal device of the second member needs to play to reach the plot node, can be determined. For example, the playing progress of the second member is 18:30, and the time difference between the plot node at 22:15 is 3:45. If the time difference is greater than a threshold, it means that the user has not watched the plot content of the plot node, and there is a spoiler risk. The evaluation result can be determined as high spoiler risk. If it is lower than the threshold, the evaluation result can be determined as low spoiler risk or no spoiler risk.

[0046] In an embodiment, it can be determined whether the plot node involves important plot / interesting plot / high-heat plot. If not, even if the time difference between the playing progress of the second member and the plot node is greater than the threshold, the evaluation result can be determined as no spoiler risk or low spoiler risk.

[0047] In S104, the presentation position of the interactive information in the first video played by the terminal device of the second member is determined according to the evaluation result.

[0048] Here, the presentation position can refer to the timestamp of the first video, for example, the presentation position is set to 22:15, and the interactive information is presented when the playing progress of the second member reaches 22:15.

[0049] If the evaluation result is high spoiler risk, the interactive information cannot be presented to the second member in advance, and a display strategy of delayed display can be adopted, i.e., the interactive information can be presented on the screen of the first video played by the terminal device of the second member when the playing progress of the second member reaches the plot node. That is, when the playing progress of the second member reaches 22:15, the interactive information is displayed on the screen of the first video played by the terminal device of the second member.

[0050] The interaction information can be pre-embedded in the first video at a position of 22 minutes and 15 seconds, and when the terminal device of the second member plays to 22 minutes and 15 seconds, the pre-embedded interaction information is automatically presented.

[0051] If the evaluation result is a low spoiler risk, the interaction information can be immediately displayed on the screen of the first video played by the terminal device of the second member, or the interaction information can be presented on the screen of the first video played by the terminal device of the second member when the play progress of the second member reaches the plot node.

[0052] If the evaluation result is a low spoiler risk, the interaction information can be immediately displayed on the screen of the first video played by the terminal device of the second member, or the interaction information can be presented on the screen of the first video played by the terminal device of the second member when the play progress of the second member reaches the plot node.

[0053] The embodiment of the present application collects the interaction information of the first member of the video synchronous playback group in the playback process of the first video, determines the corresponding plot node of the interaction information in the first video, and performs spoiler risk evaluation on the second member according to the plot node and the playback progress of the first video played by the terminal device of the second member of the video synchronous playback group, to obtain an evaluation result. According to the evaluation result, the presentation position of the interaction information in the first video played by the terminal device of the second member is determined. The embodiment of the present application presents the interaction information at a suitable position through spoiler risk evaluation, which can effectively avoid spoiler and plot misalignment discussion interference, and effectively protect the viewing rhythm of each member.

[0054] In an embodiment, the determination of the corresponding plot node of the interaction information in the first video comprises: performing semantic analysis on the interaction information to obtain a semantic analysis result; searching for a plot node matching the semantic analysis result in the plot knowledge graph of the first video.

[0055] Semantic analysis is one of the important tasks in the field of natural language processing, aiming to convert natural language into formal semantic representation, so that machines can understand and process the meaning of sentences.

[0056] By performing semantic analysis on the interaction content, the interaction content can be converted into a semantic representation, and a plot node matching the semantic representation can be searched in the plot knowledge graph.

[0057] In an embodiment, the method further comprises: performing structured processing on the first video to obtain one or more of plot actions, plot characters, keywords, and plot time points; constructing the plot knowledge graph according to one or more of the plot actions, plot characters, keywords, and plot time points.

[0058] Here, the plot knowledge graph of the first video is constructed in advance. The knowledge graph can be understood as a graph structure, in which nodes represent entities (such as people, places, events, etc.), and edges represent attributes or relationships (such as attributes, categories, attribute values, etc.). The knowledge graph can contain various types of information, such as text, images, audio, video, etc.

[0059] By structuring the first video, key features such as plot actions, plot characters, keywords, and plot time points in the first video can be extracted. These key features can be used to construct a plot knowledge graph.

[0060] The pre-constructed plot knowledge graph of the first video can be stored in the terminal device of each member of the video synchronous playback group.

[0061] If the user input interaction information is voice, voice recognition is required first. The voice can be converted to text through the Whisper model. Whisper is a voice-to-text model.

[0062] Semantic understanding of the text can be performed through a bidirectional pre-training language model (Bidirectional Encoder Representations from Transformers, BERT).

[0063] Key words can be extracted from the text through a named entity recognition (Named Entity Recognition, NER) model. NER can identify entities with specific meanings in the text, including names, place names, organization names, and proper nouns.

[0064] Real-time bidirectional communication between the terminal device and the server can be achieved through the WebSocket protocol. Real-time audio and video communication between members can be achieved through the WebRTC (Web Real-Time Communications, WebRTC) protocol, which is used for state synchronization of the synchronous viewing room.

[0065] In some embodiments, the plot spoiler risk assessment of the second member according to the plot node and the playback progress of the first video played by the terminal device of the second member of the video synchronous playback group includes: Determining the time difference between the time point corresponding to the plot node and the playback progress of the first video played by the terminal device of the second member; If the time difference is greater than a first preset time length, the evaluation result is determined to be a first risk level; if the time difference is greater than a second preset time length and less than the first preset time length, determining that the evaluation result is a second risk level; the first preset time length is greater than the second preset time length; if the time difference is less than the second preset time length, determining that the evaluation result is a third risk level; wherein the first risk level is higher than the second risk level, and the second risk level is higher than the third risk level.

[0066] wherein the first risk level is a high risk, the second risk level is a medium risk, and the third risk level is a low risk.

[0067] For example, the playing progress of member A is 18 minutes and 30 seconds, the time point corresponding to the plot node is 22 minutes and 15 seconds, and the time difference is 3 minutes and 45 seconds.

[0068] For example, the first preset time length is 3 minutes, and the second preset time length is 1 minute. Since the time difference (3 minutes and 45 seconds) is greater than the first preset time length (3 minutes), it is determined that the evaluation result is the first risk level.

[0069] For example, the playing progress of member C is 19 minutes and 45 seconds, the time point corresponding to the plot node is 22 minutes and 15 seconds, and the time difference is 2 minutes and 30 seconds. The time difference is greater than 1 minute but less than 3 minutes, so it is determined that the evaluation result is the second risk level.

[0070] For example, member B is a member who sends the interaction information. Assuming that the playing progress of member B is 20 minutes and 00 seconds, and the time difference is 2 minutes and 15 seconds, although the time difference is greater than 1 minute, since member B is the sender of the interaction information, there is no situation of spoiler himself, so it is determined that the evaluation result is no risk.

[0071] Therefore, for the member who sends the interaction information, the evaluation result is set as the third risk level or no risk by default.

[0072] In an embodiment, the determining, according to the evaluation result, of the presentation position of the interaction information in the first video played by the terminal device of the second member comprises: in the case that the evaluation result is the first risk level, determining that the presentation position is the video frame corresponding to the plot node in the first video; in the case that the evaluation result is the second risk level, monitoring the playing progress of the second member. If the playing progress of the second member reaches the time point corresponding to the plot node within a third preset time length, it is determined that the presentation position is the video frame corresponding to the plot node. If the playing progress of the second member does not reach the time point corresponding to the plot node within the third preset time length, the evaluation result is changed to the first risk level; In a case where the evaluation result is the third risk level, the presentation position is determined as a video picture corresponding to a play progress of the first video when the second member receives the interaction information.

[0073] For the member A of the high risk (the first risk level), the interaction information is not displayed to the member A immediately, but is presented to the member A (presented on a video picture corresponding to a plot node) when the play progress of the member A reaches the plot node. Before this, the user can be prompted: “There is a comment about the subsequent plot, which will be displayed at the right time”.

[0074] For the member C of the medium risk (the second risk level), a 30-second (the third preset time length) delay is set, the play progress of the member C is monitored, and if the member C catches up with the plot node within 30 seconds, the interaction information is normally displayed, otherwise, the high risk processing is performed.

[0075] The interaction information can be set as a progress point pop-up window. For example, the time point corresponding to the plot node is 22:15, when the interaction information exists, for the member A and the member C, the pop-up window is displayed at the exact time of 22:15, and the pop-up window content is: “

User B just said

[0076] For the member of the low risk, the interaction information can be directly displayed.

[0077] The embodiment effectively avoids the interference of the plot exposure and the plot mispositioned discussion, can delay, block or prompt the high risk content, and effectively guarantees the viewing rhythm of the members.

[0078] In an embodiment, the method further includes: determining the play progress of each member of the video synchronous playing group; if the progress deviation of the play progress of the second member and the play progress of the first member is greater than a threshold value, initiating a progress synchronization suggestion to the terminal device of the second member; the play progress of the first member is greater than the play progress of the second member, if the indication information of the consent progress synchronization triggered by the second member is acquired, the play progress of the second member is adjusted to be consistent with the play progress of the first member.

[0079] In the embodiment, a plurality of members join the same virtual viewing room through terminal devices, the system establishes a state channel between the terminal devices based on a long connection mechanism, and each terminal device of a member regularly reports a play state (playing / pausing / timestamp) and a user active state.

[0080] The playback progress of each member is aggregated, and for a member whose playback progress lags too much, a "smart synchronization suggestion" is triggered, and the terminal device of the second member automatically proposes a playback progress operation, which the second member can choose to accept or reject.

[0081] Considering the progress offset caused by differences in different member devices, networks, etc., the embodiment introduces a playback progress drift tolerance mechanism. For example, the AI Agent locally maintains a user playback progress deviation sliding window (such as ± 3 seconds), and combines the playback status of other members in the room to determine whether the current status needs synchronization suggestion.

[0082] That is, no synchronization suggestion is needed within ± 3 seconds, and if it exceeds ± 3 seconds, synchronization suggestion is needed.

[0083] If it is found that a member lags significantly (exceeds ± 3 seconds), a synchronization suggestion is initiated through the aiAgent, including: prompting the member to play at high speed; intelligently pushing a "key plot summary popup", and clicking the popup can play the plot text summary and synchronize the video progress. The plot text summary refers to the summary of the video content corresponding to the playback progress deviation.

[0084] In an embodiment, the method further comprises: If it is detected that the second member is in a non-viewing state, detecting whether the video content of a first video about to be played by the terminal device of the second member is high-heat content or conforms to the preferences of the second member; If the video content of the first video about to be played by the terminal device of the second member is high-heat content or conforms to the preferences of the second member, sending pause play suggestion information to the terminal devices of the other members of the video synchronous playback group; According to the voting information of all members, it is determined whether to pause playing the first video, and the voting information indicates whether to pause playing.

[0085] For example, member pausing playing, member's line of sight not being aligned with the screen, member leaving the seat (based on camera state detection or voice prompt), can all be considered to be in a non-viewing state.

[0086] For example, "key plot segments" in the first video can be marked through user behavior data (comment density, play dwell time, scoring heat, etc.) and platform content labels.

[0087] The AI Agent queries whether the upcoming plot segment belongs to "high-heat content" or "user preference object appears", and if the upcoming plot segment belongs to "high-heat content" or "user preference object appears", the AI Agent automatically issues a "pause suggestion".

[0088] All member terminals will receive a prompt: "The second member is temporarily away, and the exciting scene is about to be played. Do you want to wait?" Members can choose "wait" or "continue playing", and the AI Agent automatically executes the pause or play according to the room voting strategy.

[0089] After the second member resumes playing, the AI Agent automatically notifies other member terminals to synchronize the recovery.

[0090] This embodiment can effectively ensure that key plots are not interrupted, and improve the viewing quality and immersion.

[0091] In an embodiment, when a member is detected to be in a non-viewing state, the AI Agent determines whether the next plot is a key content (such as a high-rated, favorite actor appearing), and if it is a key content, it can automatically pause and send a prompt to other members.

[0092] In an embodiment, for member interaction input, voice input can be provided instead of traditional text box input, and output information can be displayed in the form of an intelligent floating window, which automatically disappears after display, and is displayed according to information priority and viewing state to avoid picture interference.

[0093] As shown in Figure 2 , the Figure 2 is a schematic diagram of an online synchronous interactive screening hall system provided by an embodiment of the present application, which includes: User terminal module: used for playing video, collecting voice input, text input, displaying pop-up window, uploading user state (combined with camera, behavior data), etc. AI Agent module (AI Agent): resides in each member's terminal, used for analyzing user state, progress, chat content, and executing synchronization and content control strategy. Viewing session control module: resides on the side, responsible for multi-user state coordination, instruction broadcasting, decision log recording. Multi-modal input and output interaction module: including voice recognition input, pop-up window display output, etc., used to enhance interactive experience. Plot knowledge graph module: structurally annotates video resources, extracts plot nodes, characters, keywords, etc., used for plot understanding and alignment. User behavior modeling and preference learning module: used for learning user interaction habits and preferences, optimizing synchronization strategy and interactive experience. The system records the interactive behavior preferences of members (such as whether they are willing to pause and wait for others), which are used for recommending personalized synchronization strategies next time, and continuously optimizing interactive experience.

[0094] The viewing session control module is responsible for aggregating the state and determining whether there is a significant progress deviation among the members. If the deviation exceeds a set threshold, a "smart synchronization suggestion" is triggered, and the AI Agent proposes a playback progress alignment operation. The user can choose to accept or reject it.

[0095] In an embodiment, members can make real-time comments and discuss the plot in the form of voice or text. All inputs are first intercepted by the local AI Agent and subjected to semantic analysis. The AI Agent, in combination with the plot knowledge graph, identifies the plot segments and their corresponding time points contained in the user's speech. If a member has not yet watched the plot segment (i.e., there is a risk of "spoilers"), the AI Agent automatically takes the following measures: after the receiving end plays to that segment, the original chat content is presented in a pop-up window, ensuring a coherent experience.

[0096] In an embodiment, this embodiment supports voice input as the main input channel, avoiding the interruption of traditional text input during viewing. The output content (such as chat information, system prompts, and plot node pushes) is displayed in a "floating pop-up" manner, with the following characteristics: Time sensitivity management: based on plot node display and delayed disappearance mechanism to avoid obscuring the screen; Priority scheduling mechanism: high-priority content (such as voting requests and spoiler alerts) is forced to display, and ordinary comments can be handled silently; Backtracking dotting: users can see historical interaction pop-ups when rewinding or replaying, enhancing plot understanding and interaction recall.

[0097] In an embodiment, the system continuously records user operation behavior and interaction preferences (such as whether they are willing to wait for others or whether they mind spoilers) during viewing. The user behavior modeling and preference learning module establishes a personalized synchronization preference model for each user. The AI Agent automatically determines the optimal playback synchronization strategy based on the user's historical behavior during subsequent viewing: For example: member A is used to independent playback, so the synchronization mechanism is triggered less frequently; Member B prefers plot synchronization discussion, so the spoiler control mechanism is strengthened; Support for sharing personalized strategies to the room improves overall viewing collaboration efficiency and user satisfaction.

[0098] Reference Figure 3 , Figure 3 is a schematic diagram of a video bullet screen processing flow provided by an embodiment of the present application, including an input processing stage, a semantic analysis stage, and a display control stage.

[0099] The input processing stage includes: S301, the user inputs content.

[0100] S302, determine whether the input type is voice or text.

[0101] S303A, if the input type is voice, perform voice recognition processing; S303B, if the input type is text, perform text preprocessing.

[0102] S304, standardize the processed text.

[0103] The semantic analysis stage includes: S305, semantic analysis.

[0104] S306, entity recognition.

[0105] S307, plot timeline matching.

[0106] By searching for related plots in the plot knowledge graph through entities, the plot node at 22 minutes and 15 seconds of the film is matched, and it is identified as an important plot revelation point.

[0107] S308, calculate the time deviation.

[0108] Calculate the time difference between the current playback progress of the member and the plot node.

[0109] The display control stage includes: S309, risk level judgment.

[0110] S310, when the risk is low, the user input content can be directly displayed.

[0111] S311, when the risk is medium, set a delay display.

[0112] S312, when the risk is high, dot storage, and wait for the corresponding plot node to be displayed.

[0113] S313, generate pop-up content.

[0114] The pop-up content includes user input content and input time.

[0115] In summary, the application scenario of preventing plot revelation mainly includes five stages.

[0116] The first stage is content capture and preprocessing.

[0117] Real-time input monitoring, local AI Agent collects user input content in real time, the system immediately intercepts and does not directly send to other users. Then perform preliminary content classification (ordinary chat [greetings, casual conversation], plot-related comments, playback control instructions, emotional expression).

[0118] The second stage is AI semantic depth analysis.

[0119] Keyword extraction and plot knowledge graph matching, match the plot node in the film through keywords.

[0120] Third stage, spoiler risk assessment, member progress difference analysis. According to the time difference between the member's play progress and the plot node, risk assessment is carried out.

[0121] Fourth stage, intelligent processing strategy execution High-risk content processing blocking mechanism: the content is not displayed immediately, and the system generates a placeholder prompt: "There is a comment about the subsequent plot, which will be displayed at the right time".

[0122] Medium-risk content processing delayed display strategy: set a 30-second delay, monitor the member's play progress, if the progress is caught up within 30 seconds, it will be displayed normally, otherwise it will be converted to high-risk processing.

[0123] Low-risk can be directly displayed.

[0124] Fifth stage: intelligent pop-up display mechanism.

[0125] When the user plays to the plot node, the pop-up prompt is displayed at the exact moment, and the pop-up content includes user input content and input time.

[0126] The spoiler prevention mechanism can automatically adjust the spoiler filtering strength combined with user preference modeling results to realize differentiated experience for members.

[0127] In an embodiment, the system can continuously collect the following user behavior data: Play / pause frequency; Voice / cast interactive behavior; Synchronous response willingness; AI Agent combines model to determine user inclination: Members who like "fast-paced single viewing" can adopt weak synchronization + weak interaction; Members who like "spoiler warning + group pause" can adopt strong synchronization + strong control; This embodiment can coordinate strategy dynamic evolution, adapt to multiple types of user coordination mode, and improve overall satisfaction.

[0128] The embodiment of the present application improves the consistency and immersion of multi-person synchronous viewing, solves the problem of inconsistent playback progress and manual coordination through AI active judgment and intelligent synchronization logic, effectively avoids spoilers and plot misplacement discussion interference, AI judges based on semantics and timeline, delays, blocks or prompts high-risk content, effectively ensures the viewing rhythm, enhances the intelligence and individualization of playback control, the system can intelligently judge whether to pause or continue playing based on user behavior and plot structure, and automatically adapts to user needs, reduces input and display interference, optimizes interactive experience, voice input, intelligent pop-up output design, maintains interactive efficiency while not disturbing the main viewing area. The system has the ability of continuous learning and evolution, records user behavior and feedback, trains AI Agent to provide intelligent synchronization strategies that meet the preferences of the group.

[0129] The embodiment of the present application solves the core pain points (progress is not synchronized, spoilers interfere) in the existing synchronous viewing, the AI-driven intelligent synchronization mechanism has universality, and the multi-modal interaction design meets the future development trend of video socialization, which can improve user stickiness and activity, and helps to build a video socialization ecosystem.

[0130] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0131] It should be understood that when used in the present specification and the appended claims, the terms "comprise" and "include" indicate the presence of described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0132] It should be noted that the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0133] In addition, in the embodiments of the present application, "first", "second", etc. are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0134] The method of the above embodiment can be realized by a processor in an electronic device, such as a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU), or a programmable gate array (FPGA).

[0135] The video playing method described in the application can be run in the form of a container or a virtual machine. Of course, it is not limited to the form of an image file, and any software form that can implement the video playing method described in the application is within the protection scope of the application.

[0136] Based on the hardware implementation of the program modules and in order to implement the method of the embodiments of the application, the embodiments of the application further provide an electronic device, which can be a terminal device of the first member and the second member. Figure 4 A schematic diagram of the hardware composition structure of the electronic device of the embodiments of the application is shown in FIG. 1. Figure 4 As shown in FIG. 1, the electronic device includes: a communication interface, which can interact with other devices such as network devices and the like; a processor connected with the communication interface to implement information interaction with other devices, used to run a computer program to execute the method provided by one or more technical solutions of the electronic device. The computer program is stored on the memory.

[0137] Of course, in actual application, various components in the electronic device are coupled together through a bus system. It can be understood that the bus system is used to realize the connection and communication between the components. The bus system includes a data bus, a power supply bus, a control bus and a state signal bus. However, in order to clearly illustrate, all kinds of buses are marked as a bus system in the description. Figure 4

[0138] The memory in the embodiments of the application is used to store various types of data to support the operation of the electronic device. Examples of the data include any computer program used to operate on the electronic device.

[0139] ​It can be understood that the memory can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example and not limitation, many forms of RAM can be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), sync link dynamic random access memory (SLDRAM), direct rambus random access memory (DRRAM).The memory described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable type of memory.

[0140] The method disclosed in the embodiments of the present application can be applied in a processor or implemented by the processor. The processor can be an integrated circuit chip having a processing capability. In the implementation process, each step of the method can be completed by integrated logic circuits or instructions in the form of software in the processor. The processor can be a general processor, a DSP, or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The processor can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application. The general processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the hardware decoding processor can be directly embodied to execute the foregoing steps, or the foregoing steps can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory. The processor reads the program in the memory and combines the hardware to complete the steps of the foregoing method.

[0141] Alternatively, the processor implements the corresponding procedures realized by the electronic device in each method of the embodiments of the present application when executing the program. For brevity, details are not described herein.

[0142] In the exemplary embodiments, the embodiments of the present application also provide a computer program product, which includes a computer program executable by the processor of the electronic device to complete the steps described in the embodiments of the present application.

[0143] In the exemplary embodiments, the embodiments of the present application also provide a storage medium, i.e., a computer storage medium, specifically a computer readable storage medium, for example, including a first memory storing a computer program, which can be executed by the processor of the electronic device to complete the steps described in the foregoing method. The computer readable storage medium can be FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disc, or CD-ROM, etc.

[0144] In several embodiments provided in the present application, it should be understood that the disclosed apparatus, electronic device and method can be implemented in other manners. The above described apparatus embodiments are merely exemplary. For example, the division of the units is merely a logical function division. There can be another division manner for the actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0145] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or distributed on multiple network units; part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0146] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0147] Those of ordinary skill in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by a program instructing related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program executes the steps of the above-mentioned method embodiments when executed; and the foregoing storage medium includes mobile storage devices, ROM, RAM, magnetic discs or optical discs and various storage media that can store program codes.

[0148] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes mobile storage devices, ROM, RAM, magnetic discs or optical discs and various storage media that can store program codes.

[0149] It should be noted that the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0150] In addition, in the examples of the present application, "first", "second", and the like are used to distinguish similar objects, and are not necessarily used to describe a particular order or sequence.

[0151] The above description is merely a specific implementation of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, and all such changes or replacements should be covered within the scope of protection of the present application. Therefore, the scope of protection of the present application should be subject to the scope of protection of the claims.

Claims

1. A video playback method, characterized in that, The method includes: Collect interactive information from the first member of the synchronized video playback group during the playback of the first video; Determine the plot node in the first video corresponding to the interactive information; Based on the plot nodes and the playback progress of the first video played on the terminal device of the second member of the video synchronization playback group, a spoiler risk assessment is performed on the second member, and an assessment result is obtained. Based on the evaluation results, the presentation position of the interactive information in the first video played on the second member's terminal device is determined.

2. The method according to claim 1, characterized in that, Determining the plot node corresponding to the interactive information in the first video includes: Perform semantic analysis on the interaction information to obtain the semantic analysis results; Search the plot knowledge graph of the first video for plot nodes that match the semantic analysis results.

3. The method according to claim 2, characterized in that, The method further includes: The first video is structured to obtain one or more of the following: plot actions, plot characters, keywords, and plot time points. Construct the plot knowledge graph based on one or more of the plot actions, plot characters, keywords, and plot time points.

4. The method according to claim 1, characterized in that, The step of assessing the spoiler risk for the second member based on the plot points and the playback progress of the first video played on the terminal device of the second member of the synchronized video playback group includes: Determine the time difference between the time point corresponding to the plot node and the playback progress of the first video played on the terminal device of the second member; If the time difference is greater than the first preset duration, the assessment result is determined to be the first risk level; If the time difference is greater than the second preset duration and less than the first preset duration, then the assessment result is determined to be the second risk level; the first preset duration is greater than the second preset duration. If the time difference is less than the second preset duration, the assessment result is determined to be the third risk level; wherein the first risk level is higher than the second risk level, and the second risk level is higher than the third risk level.

5. The method according to claim 4, characterized in that, Determining the presentation position of the interactive information in the first video played on the second member's terminal device based on the evaluation result includes: If the assessment result is the first risk level, the presentation location is determined to be the video frame corresponding to the plot node in the first video; If the assessment result is the second risk level, the playback progress of the second member is monitored. If the playback progress of the second member reaches the time point corresponding to the plot node within the third preset time period, the presentation position is determined to be the video screen corresponding to the plot node. If the playback progress of the second member does not reach the time point corresponding to the plot node within the third preset time period, the assessment result is changed to the first risk level. If the assessment result is the third risk level, the presentation position is determined to be the video frame corresponding to the playback progress of the first video when the second member receives the interaction information.

6. The method according to claim 1, characterized in that, The method further includes: Determine the playback progress of each member of the video synchronization playback group; If the playback progress of the second member deviates from that of the first member by more than a threshold, a progress synchronization suggestion is sent to the terminal device of the second member; the playback progress of the first member is greater than that of the second member. If the second member triggers an indication to synchronize the playback progress, the playback progress of the second member will be synchronized to match that of the first member.

7. The method according to claim 1, characterized in that, The method further includes: If it is detected that the second member is not in a viewing state, then it is detected whether the video content of the first video that the second member's terminal device is about to play is highly popular content or whether it matches the second member's preferences; If the video content of the first video that the second member's terminal device is about to play is highly popular or matches the second member's preferences, then a pause playback suggestion message is sent to the terminal devices of other members in the video synchronization playback group; Based on the voting information of all members, determine whether to pause the playback of the first video, wherein the voting information indicates whether to pause playback.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the video playback method as described in any one of claims 1 to 7.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the video playback method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the steps of the video playback method as described in any one of claims 1 to 7.

Images