Methods, devices and electronic equipment for displaying bullet comments
By differentiating between bullet comments with opposite meanings and optimizing the bullet comment display method, the problems of bullet comments obscuring the screen, low interaction efficiency, and poor compatibility in multiple scenarios in existing technologies have been solved, thereby improving the user interaction experience and information density and meeting the personalized needs of different users.
Patent Information
- Application Number
- CN202611130017.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-28
- Publication Date
- 2026-11-17
AI Technical Summary
Existing bullet screen display methods suffer from problems such as obstructing the view, low user interaction efficiency, and lack of personalized adaptation. They cannot provide differentiated services for different users, have poor compatibility in multiple scenarios, low real-time interaction efficiency, and insufficient bullet screen management and matching capabilities.
By identifying users as interactive users, the system acquires and distinguishes between two types of bullet comments with opposite semantics. It uses a multi-dimensional behavioral feature model to identify user types, and combines semantic understanding and the number of supporters to achieve differentiated display and semantic comparison of bullet comments. It also supports bullet comment replies and likes, and optimizes the display method of the bullet comment display area.
It improved user interaction efficiency and engagement, enhanced the scene adaptability of bullet comments, optimized user browsing experience and interaction depth, met the needs of different types of users, and achieved precise and visual dissemination of opinions.
Smart Images

Figure CN123123632A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a method, apparatus and electronic device for displaying bullet comments. Background Technology
[0002] Bullet screen technology allows users to post comments during video playback, with the comments displayed as scrolling subtitles overlaid on the video screen. This feature enables real-time interaction and comment sharing, creating a collective viewing atmosphere, and has now become a standard feature of video platforms. However, existing bullet screen display methods suffer from problems such as bullet screens obstructing the view, low user interaction efficiency, and a lack of personalized adaptation. Summary of the Invention
[0003] This disclosure provides a method, apparatus, electronic device, medium, and computer program product for displaying bullet comments.
[0004] The technical solution disclosed herein is as follows: According to a first aspect of the present disclosure, a method for displaying bullet comments is provided, comprising: determining that a first user is an interactive user; obtaining a first bullet comment set and a second bullet comment set, wherein the first bullet comment set includes a first type of bullet comment, the second bullet comment set includes a second type of bullet comment, and the first type of bullet comment and the second type of bullet comment are semantically opposite; and displaying the first type of bullet comment and the second type of bullet comment differently in a bullet comment display area.
[0005] According to a second aspect of the present disclosure, a bullet screen display device is provided, comprising: an acquisition module, configured to determine that a first user is an interactive user, acquire a first bullet screen set and a second bullet screen set, wherein the first bullet screen set includes a first type of bullet screen, the second bullet screen set includes a second type of bullet screen, and the first type of bullet screen and the second type of bullet screen are semantically opposite; and a display module, configured to distinguish and display the first type of bullet screen and the second type of bullet screen in a bullet screen display area.
[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the bullet screen display method as described in the first aspect of the present disclosure.
[0007] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the bullet screen display method as described in the first aspect of the present disclosure.
[0008] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the bullet screen display method according to a first aspect of the present disclosure.
[0009] The technical solutions provided by the embodiments of this disclosure bring at least the following beneficial effects: In this embodiment, the type of the first user is determined to be an interactive user. A first set of bullet comments and a second set of bullet comments are obtained. The first set of bullet comments includes a first type of bullet comment, and the second set of bullet comments includes a second type of bullet comment. The first type of bullet comment and the second type of bullet comment are semantically opposite. The first type of bullet comment and the second type of bullet comment are displayed separately in the bullet comment display area. Therefore, this disclosure, for interactive users, distinguishes between two types of bullet comments with opposite meanings in the bullet comment display area. This reduces the obstruction and interference of bullet comments on the main content, and enables a direct comparison between the two types of bullet comments with opposite meanings. This is beneficial to improving user interaction efficiency and participation, meeting the needs of different types of users, and enhancing the scene adaptability of bullet comments.
[0010] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.
[0012] Figure 1 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0013] Figure 2 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0014] Figure 3 This is a flowchart illustrating a bullet screen display method according to an exemplary embodiment.
[0015] Figure 4 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0016] Figure 5 This is a flowchart illustrating a bullet screen display method according to an exemplary embodiment.
[0017] Figure 6 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0018] Figure 7 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0019] Figure 8 This is a flowchart illustrating a bullet screen display method according to an exemplary embodiment.
[0020] Figure 9 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0021] Figure 10 This is a flowchart illustrating a bullet screen display method according to an exemplary embodiment.
[0022] Figure 11 This is a schematic diagram illustrating a bullet screen display according to an exemplary embodiment.
[0023] Figure 12 This is a flowchart illustrating a bullet screen display method according to an exemplary embodiment.
[0024] Figure 13 This is a block diagram illustrating a bullet screen display device according to an exemplary embodiment.
[0025] Figure 14 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation
[0026] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.
[0027] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.
[0028] The basic technical principles of bullet comments are as follows: (1) Bullet comment rendering and scrolling control: Bullet comments can scroll at a constant speed in the horizontal or vertical direction, and support customization of basic styles such as font and color; Bullet comment filtering and sorting: Bullet comments are filtered according to time, popularity or keywords to reduce repetitive or low-quality content; Bullet comment anti-obstruction: Bullet comments avoid key areas of the video such as the face of the person through masking technology such as transparent mask. Traditional masking technology relies on static rules or simple image recognition and lacks intelligent dynamic adjustment capabilities.
[0029] In related technologies, the following methods are often used to achieve bullet screen display: (1) Bullet screen anti-occlusion based on artificial intelligence. Dynamic masks are generated through multimodal analysis to make bullet screens bypass important foreground targets in the video. That is, the video stream is sampled, and the buffer is reset using the lens switching detection algorithm; target information is extracted using face detectors, instance segmenters, semantic segmenters and depth estimators, and masks are generated through foreground mask selection algorithms and temporal mask compensation algorithms to ensure that bullet screens do not obscure important areas. However, this method focuses on video content analysis and avoids bullet screen occlusion by identifying key objects in the video, but does not consider differences in user behavior (such as user preferences for bullet screens and interaction habits), and all users adopt the same anti-occlusion rules. (2) Bullet screen diversion based on ring. In the virtual reality (VR) environment, bullet screens are drawn on a ring transparent bullet screen layer outside the video layer, and the position of the bullet screen is calculated by three-dimensional coordinates to achieve physical separation of bullet screens from video content and reduce occlusion. However, this solution relies on the hardware environment (VR), avoids occlusion through spatial layout, lacks adaptation to users' personalized needs (such as not distinguishing user types), and cannot support immersive video experiences in non-VR environments. (3) User behavior-adaptive bullet screen display solution. In mixed reality headsets, bullet screens can dynamically adjust their display position based on user gestures or eye tracking (such as surrounding the user's field of vision), and support special effects bullet screens (such as particle effects). However, this solution relies on specific hardware (mixed reality headsets) and sensors, and the bullet screen adjustment is only based on real-time interaction (such as gestures), without combining user historical behavior for long-term classification and personalized strategy customization (such as automatically adjusting the display mode according to the frequency of user blocking bullet screens).
[0030] For example, for video platform A, the existing bullet screen display is as follows: Figure 1 As shown, multiple horizontal scrolling bullet comments are densely arranged, and the opinions expressed in the bullet comments are fragmented. This not only reduces the user's video viewing experience, but also makes the bullet comment opinions unintuitive and weakens the user's interactivity and sense of participation.
[0031] For example, for video platform A, the existing methods for controlling the display of bullet comments are as follows: Figure 2 As shown, it only supports users to manually adjust the parameters of the bullet comments during the video viewing process. The adjustment dimensions are limited to basic dimensions such as opacity, font size, bullet comment speed, and display area. Not only can it not achieve dynamic adaptation according to video scene and user status, resulting in low efficiency of real-time interaction, but it also has problems such as poor compatibility in multiple scenes and insufficient bullet comment management and matching capabilities.
[0032] In summary, the following problems often exist in the relevant technologies: (1) Lack of user behavior adaptation capability: that is, the existing solutions all rely on video content analysis or hardware characteristics, without considering the user's historical behavior (such as the frequency of sending bullet comments and blocking preferences), resulting in the inability to provide differentiated bullet comment services for different users, limited improvement in user experience, and low utilization of the system resources. For example, users who frequently block bullet comments will still see the bullet comments generated by the basic anti-blocking solution, and the interference cannot be completely eliminated; users who like interaction cannot obtain targeted interaction enhancement functions. (2) Low real-time interaction efficiency: that is, although the existing solutions support dynamic bullet comment adjustment, the interaction process has not been optimized. For example, users need to manually operate (such as gestures) to adjust the bullet comments, which increases the interaction burden, and lacks semantic matching and popularity ranking mechanisms, making it difficult for users to quickly participate in high-quality discussions. (3) Poor multi-scenario compatibility: that is, the existing solutions rely on specific hardware and cannot be applied to immersive video scenarios on ordinary mobile terminals or personal computers (PCs). Anti-blocking solutions based on video analysis are prone to masking errors in complex scenarios (such as fast camera switching), resulting in bullet comments flickering or being accidentally blocked. (4) Insufficient bullet screen management and matching capabilities: The existing solution does not introduce semantic matching and support mechanisms, so users cannot quickly obtain bullet screens that support their own views or content that refutes the other party's views. The lack of bullet screen knockout (KO) mechanism and popularity replacement strategy results in low-quality bullet screens remaining on the interface, affecting the efficiency of clearing the view.
[0033] The following examples illustrate the bullet screen display method, apparatus, and electronic device proposed in this disclosure.
[0034] Figure 3 This is a flowchart illustrating a bullet screen display method provided in an embodiment of the present disclosure.
[0035] like Figure 3 As shown, the bullet screen display method proposed in this embodiment includes the following steps: S301, determine that the type of the first user is an interactive user, obtain the first set of bullet comments and the second set of bullet comments, wherein the first set of bullet comments includes the first type of bullet comments, the second set of bullet comments includes the second type of bullet comments, and the first type of bullet comments and the second type of bullet comments are semantically opposite.
[0036] It should be noted that a pre-trained multi-dimensional behavioral feature model can be used to identify the first user and obtain the type label of the first user to determine whether the first user is an interactive user. The type label includes interactive users and non-interactive users.
[0037] Optionally, the historical behavior data of the first user can be obtained, and the first user can be identified based on the historical behavior data through a multi-dimensional behavior feature model to obtain the type label of the first user, thereby achieving an accurate portrayal of the first user profile.
[0038] It should be noted that historical behavior data includes, but is not limited to, the number of bullet comments sent by the first user in history (reflecting the first user's active participation in bullet comments), the frequency of blocking bullet comments in history (reflecting the first user's tolerance for bullet comments), the number of likes on bullet comments in history (reflecting the first user's preference for liking bullet comments), and the response speed of bullet comment interaction in history (reflecting the first user's enthusiasm for responding to bullet comment content).
[0039] It should be noted that the type of the first user is determined to be an interactive user. When the first user watches the video and the bullet comments are enabled, the first bullet comment set and the second bullet comment set are obtained.
[0040] In this embodiment of the disclosure, semantic understanding is performed on the bullet comments in the bullet comment display area to determine the type of bullet comments, the first number of supporters for each of the first type of candidate bullet comments is obtained, a first set of bullet comments is determined from the first type of candidate bullet comments based on the first number of supporters, the second number of supporters for each of the second type of candidate bullet comments is obtained, and a second set of bullet comments is determined from the first type of candidate bullet comments based on the second number of supporters.
[0041] S302, distinguishes between the first type of bullet comments and the second type of bullet comments in the bullet comment display area.
[0042] It should be noted that this disclosure does not limit the setting of the bullet screen display area. For example, the default setting is 30% of the screen of the first user's device.
[0043] It should be noted that this disclosure does not limit the way the first type of bullet comments and the second type of bullet comments are displayed differently. For example, the first type of bullet comments and the second type of bullet comments can be displayed differently by position; or the first type of bullet comments and the second type of bullet comments can be displayed differently by color.
[0044] For example, regarding video platform A, such as Figure 4 As shown, the first type of bullet comments is displayed in red and the second type in blue in the bullet comment display area. This distinguishes between the first and second types of bullet comments and allows for a direct comparison between them through color differentiation. This satisfies users' need for instant access to group interaction information and avoids information overload by limiting the number of bullet comments. This ensures that users can quickly grasp the core dynamics of group interaction and lays the foundation for subsequent real-time interaction.
[0045] In summary, the bullet screen display method provided in this disclosure determines that the first user is an interactive user, obtains a first bullet screen set and a second bullet screen set, wherein the first bullet screen set includes a first type of bullet screen, and the second bullet screen set includes a second type of bullet screen. The first type of bullet screen and the second type of bullet screen are semantically opposite, and the first type of bullet screen and the second type of bullet screen are displayed separately in the bullet screen display area. Therefore, this disclosure, targeting interactive users, distinguishes between two semantically opposite types of bullet screens in the bullet screen display area, which reduces the obstruction and interference of bullet screens on the main content, and enables a direct comparison of the two semantically opposite types of bullet screens. This is beneficial for improving user interaction efficiency and engagement, meeting the needs of different types of users, and enhancing the scene adaptability of bullet screens.
[0046] Figure 5 This is a flowchart illustrating a bullet screen display method provided in an embodiment of the present disclosure.
[0047] like Figure 5 As shown, the bullet screen display method proposed in this embodiment includes the following steps: S501, determine that the first user is an interactive user, and perform semantic understanding on the bullet comments in the bullet comment display area to determine the type of bullet comments.
[0048] Optionally, a semantic understanding model can be used to perform semantic understanding on the bullet comments in the bullet comment display area. Based on the semantic understanding results, the viewpoint expressed by each bullet comment can be determined, and the bullet comments can be classified into two categories based on semantic opposition to determine the type of bullet comments.
[0049] S502, obtain the first number of supporters for each of the first type of candidate bullet comments, and determine the first bullet comment set from the first type of candidate bullet comments based on the first number of supporters.
[0050] Optionally, the first number of supporters for each of the first type of candidate bullet comments is obtained, the first number of supporters is sorted in descending order, and the top five first type of candidate bullet comments with the highest number of supporters are selected to form the first bullet comment set.
[0051] S503, obtain the second number of supporters for each of the second type of candidate bullet comments, and determine the second bullet comment set from the second type of candidate bullet comments based on the second number of supporters.
[0052] Optionally, the number of second supporters for each of the first type of candidate bullet comments is obtained, the number of second supporters is sorted in descending order, and the top five second type of candidate bullet comments with the highest number of supporters are selected to form the second bullet comment set.
[0053] S504 distinguishes between the first type of bullet comments and the second type of bullet comments in the bullet comment display area.
[0054] S505, extract from the bullet screen display area a second bullet screen that is semantically opposite to the first bullet screen input by the first user's device.
[0055] Optionally, the bullet screen data in the bullet screen display area is captured in real time, and the first bullet screen input by the first user's device is obtained simultaneously. The semantics of the first bullet screen are obtained, and the bullet screen that is semantically opposite to the first bullet screen is taken as the second bullet screen.
[0056] S506, Based on the first and second bullet comments, retrieve a third bullet comment from the bullet comment pool that is semantically similar to the first bullet comment and is used to refute the second bullet comment.
[0057] In this embodiment of the disclosure, the similarity between the first bullet screen and the candidate bullet screens in the bullet screen pool is determined, the conflict degree between the second bullet screen and the candidate bullet screens in the bullet screen pool is determined, and the third bullet screen is determined based on the similarity and conflict degree, as well as the correspondence between the third bullet screen and the second bullet screen.
[0058] Optionally, a semantic matching algorithm can be used to determine the similarity between the first bullet comment and the candidate bullet comments in the bullet comment pool, determine the conflict degree between the second bullet comment and the candidate bullet comments in the bullet comment pool, and use the candidate bullet comments with a similarity greater than or equal to the similarity threshold and a conflict degree greater than the preset conflict degree threshold as the third bullet comment, and construct the correspondence between the second bullet comment and the third bullet comment.
[0059] S507 displays the first and third bullet comments in the first display area of the bullet comment display area.
[0060] S508 displays the second bullet comment in the second display area of the bullet comment display area, where the second bullet comment is displayed one-to-one with the third bullet comment.
[0061] For example, in response to a first user clicking a floating, movable "cheering button" on the video playback interface, based on the first and second bullet comments, a third bullet comment that is semantically similar to the first bullet comment and used to refute the second bullet comment is retrieved from the bullet comment pool. After identifying the third bullet comment, the process enters the multi-area bullet comment presentation stage: for video platform A, such as... Figure 6 As shown, the left side of the bullet comment display area (the first display area) displays the first and third bullet comments, while the right side (the second display area) displays the second bullet comment. The second and third bullet comments are displayed in a one-to-one correspondence, creating a visual presentation with opposite meanings. The third bullet comment is then sent to the user corresponding to the second bullet comment. After 5 seconds, the third bullet comment gradually pushes the second bullet comment out of the video playback interface from the right side of the bullet comment display area, showcasing an animation effect that completely surpasses the third bullet comment. Figure 7 As shown, the third comment pushes the second comment out of the right side of the comment display area of the video playback interface and highlights the third comment to celebrate the victory.
[0062] In this embodiment of the disclosure, a second bullet screen reply sent by the device of the second user associated with the second bullet screen is received, a first bullet screen reply input by the device of the first user is displayed in a first display area, and a second bullet screen reply sent by the device of the second user is displayed in a second display area.
[0063] Optionally, the first bullet screen reply can be displayed in the left area (first display area) of the bullet screen display area, and the second bullet screen reply sent by the second user's device can be displayed in the right area (second display area) of the bullet screen display area.
[0064] It should be noted that, since each bullet comment can receive replies from multiple other users, the replies are sorted according to the order in which they were generated. The most recently entered bullet comment and the latest reply to the first bullet comment are displayed in the left area of the bullet comment display area (the first display area), which enhances users' sense of identity and the continuity of interaction. When the first user submits a reply to the bullet comment displayed in the first display area, the first display area is automatically refreshed and the next unreplyed bullet comment is displayed in chronological order. After a user replies to a bullet comment, the bullet comment reply is automatically sent to core users who hold opposing views or users who initiated related discussions, thus completing the entire process from viewpoint expression and aggregation to targeted interaction. This effectively improves the targeting and depth of participation in bullet comment interaction and achieves the precision and visualization of viewpoint dissemination.
[0065] It should be noted that if no bullet screen operation is detected within a preset time (e.g., 10 seconds), the first type of bullet screen and the second type of bullet screen will continue to be displayed differently in the bullet screen display area.
[0066] In summary, the bullet screen display method provided in this embodiment determines that the first user is an interactive user, performs semantic understanding on the bullet screens in the bullet screen display area to determine the type of bullet screen, obtains the first number of supporters for each of the first type of candidate bullet screens, determines a first bullet screen set from the first type of candidate bullet screens based on the first number of supporters, obtains the second number of supporters for each of the second type of candidate bullet screens, determines a second bullet screen set from the second type of candidate bullet screens based on the second number of supporters, distinguishes between the first type of bullet screens and the second type of bullet screens in the bullet screen display area, extracts a second bullet screen from the bullet screen display area that is semantically opposite to the first bullet screen input by the first user's device, retrieves a third bullet screen from the bullet screen pool that is semantically similar to the first bullet screen and used to refute the second bullet screen based on the first and second bullet screens, displays the first and third bullet screens in the first display area of the bullet screen display area, and displays the second bullet screen in the second display area of the bullet screen display area. Therefore, this disclosure displays the first and third bullet comments in a first display area, and the second bullet comment in a second display area, with the second and third bullet comments displayed one-to-one. This achieves a segmented presentation of bullet comments with opposite meanings, facilitating intuitive browsing and comparison of bullet comment content for users. This optimizes the user browsing experience, enhances the targeting of bullet comment interaction, and deepens user engagement. It achieves precise and visual dissemination of viewpoints.
[0067] Figure 8 This is a flowchart illustrating a bullet screen display method provided in an embodiment of the present disclosure.
[0068] like Figure 8 As shown, the bullet screen display method proposed in this embodiment includes the following steps: S801, determine that the first user is an interactive user, and perform semantic understanding on the bullet comments in the bullet comment display area to determine the type of bullet comments.
[0069] S802, obtain the first number of supporters for each of the first type of candidate bullet comments, and determine the first bullet comment set from the first type of candidate bullet comments based on the first number of supporters.
[0070] S803, obtain the second number of supporters for each of the second type of candidate bullet comments, and determine the second bullet comment set from the first type of candidate bullet comments based on the second number of supporters.
[0071] S804 distinguishes between the first type of bullet comments and the second type of bullet comments in the bullet comment display area.
[0072] S805 responds to the detected danmaku (bullet comment) like operation and determines the fourth danmaku operation performed by the first user based on the danmaku like operation.
[0073] In this embodiment of the disclosure, in response to the detection of a danmaku like operation, the danmaku associated with the danmaku like operation is located to determine the fourth danmaku operated by the first user, that is, the danmaku that the user liked this time.
[0074] S806, based on the semantics of the fourth bullet screen, obtain the set of third bullet screens to be displayed, wherein the set of third bullet screens includes at least one fifth bullet screen that is semantically similar to the first bullet screen.
[0075] Optionally, after determining the fourth bullet comment, the semantics of the fourth bullet comment are determined based on a semantic understanding model. Historical / real-time bullet comments with similar semantics and high popularity are then used as the fifth bullet comment. For example, based on the semantics of the fourth bullet comment, 10 historical / real-time bullet comments that are semantically similar to the fourth bullet comment and have high popularity are used as the fifth bullet comment.
[0076] S807 displays the fifth bullet comment in the bullet comment display area.
[0077] For example, regarding video platform A, such as Figure 9 As shown, the fifth bullet comment is displayed in the bullet comment display area, and the fourth bullet comment is highlighted in the bullet comment display area. After the fifth bullet comment is displayed, the first type of bullet comment and the second type of bullet comment are displayed separately in the bullet comment display area.
[0078] In summary, the bullet screen display method provided in this embodiment determines that the first user is an interactive user, performs semantic understanding on the bullet screens in the bullet screen display area to determine the type of bullet screen, obtains the first number of supporters for each of the first type of candidate bullet screens, determines a first bullet screen set from the first type of candidate bullet screens based on the first number of supporters, obtains the second number of supporters for each of the second type of candidate bullet screens, determines a second bullet screen set from the first type of candidate bullet screens based on the second number of supporters, distinguishes between the first type of bullet screens and the second type of bullet screens in the bullet screen display area, responds to a bullet screen like operation, determines the fourth bullet screen operated by the first user based on the bullet screen like operation, obtains a third bullet screen set to be displayed based on the semantics of the fourth bullet screen, wherein the third bullet screen set includes at least one fifth bullet screen with semantics similar to the first bullet screen, and displays the fifth bullet screen in the bullet screen display area. Therefore, by displaying the fifth bullet comment in the bullet comment display area, this disclosure not only enriches the multi-dimensional presentation of bullet comments, but also provides users with real-time viewpoint references. While ensuring smooth viewing, it effectively improves the information density and social attributes of bullet comments, and makes the originally isolated bullet comment liking behavior generate a wider content linkage effect.
[0079] Figure 10 This is a flowchart illustrating a bullet screen display method provided in an embodiment of the present disclosure.
[0080] like Figure 10 As shown, the bullet screen display method proposed in this embodiment includes the following steps: S1001, determine that the first user is an interactive user, and perform semantic understanding on the bullet comments in the bullet comment display area to determine the type of bullet comments.
[0081] S1002, obtain the first number of supporters for each of the first type of candidate bullet comments, and determine the first bullet comment set from the first type of candidate bullet comments based on the first number of supporters.
[0082] S1003, obtain the second number of supporters for each of the second type of candidate bullet comments, and determine the second bullet comment set from the first type of candidate bullet comments based on the second number of supporters.
[0083] S1004, differentiate between the first type of bullet comments and the second type of bullet comments in the bullet comment display area.
[0084] S1005, in response to the detection of a bullet screen sending operation, obtains the first bullet screen input by the first user.
[0085] It should be noted that the barrage operation is continuously monitored, and in response to the barrage sending operation, the first barrage input by the first user is captured to obtain the first barrage input by the first user.
[0086] S1006, perform semantic understanding on the first bullet comment to determine the type label of the first bullet comment.
[0087] Optionally, the first bullet comment's content can be deeply semantically parsed using the BERT bidirectional pre-trained language model's stance classification algorithm to determine its core viewpoint tag. Then, the BERT stance polarity calculation algorithm can be used to quantify the stance polarity based on the core viewpoint tag, obtaining a stance polarity value. Based on the stance polarity value, the type tag of the first bullet comment can be determined. The stance polarity value range is set to [-1, 1], where a polarity value of -1 indicates complete opposition, and 1 indicates complete support.
[0088] S1007, based on the type tag of the first bullet comment, filter the fourth bullet comment set from the bullet comment pool, the fourth bullet comment set including at least one sixth bullet comment that is semantically opposite to the first bullet comment.
[0089] Optionally, based on the type tag of the first bullet comment, the degree of conflict between the first bullet comment and the candidate bullet comments in the bullet comment pool is determined, the degree of conflict is sorted in descending order to obtain the degree of conflict ranking result, and the candidate bullet comments with the highest degree of conflict in the bullet comment pool are selected as the sixth bullet comment based on the degree of conflict ranking result.
[0090] S1008 displays the first and sixth bullet comments in the bullet comment display area.
[0091] In this embodiment of the disclosure, the popularity of the sixth bullet comment and the degree of conflict between the sixth bullet comment and the third bullet comment are determined. Based on the popularity and degree of conflict of the sixth bullet comment, the display priority of the sixth bullet comment is determined. The sixth bullet comment is displayed in the bullet comment display area according to the display priority. The display styles of the first bullet comment and the sixth bullet comment are different.
[0092] Optionally, the number of likes and their corresponding weight (e.g., set to 0.5), the number of replies and their corresponding weight (e.g., set to 0.3), and the sending time decay coefficient and its corresponding weight (e.g., set to 0.2) of the first comment can be obtained. The popularity of the sixth comment can then be determined based on these factors. For example: Popularity of the sixth comment = Number of likes × 0.5 + Number of replies × 0.3 + Sending time decay coefficient × 0.2.
[0093] Optionally, the weight corresponding to the popularity of the sixth comment (e.g., set to 0.4) and the weight corresponding to the conflict level (e.g., set to 0.6) can be obtained, and the display priority of the sixth comment can be determined based on the weight corresponding to the popularity of the first comment and the weight corresponding to the conflict level. For example: the display priority of the sixth comment = popularity × 0.4 + conflict level × 0.6.
[0094] For example, regarding video platform A, such as Figure 11 As shown, the first bullet comment is displayed in the left area of the bullet comment display area, and the sixth bullet comment is displayed in the right area of the bullet comment display area, so as to achieve precise exposure of conflicting viewpoints and help improve users' interactive participation.
[0095] In this embodiment of the disclosure, in response to the detection of a bullet screen reply operation, based on the type of bullet screen reply operation, the seventh bullet screen to be replied to is determined from the bullet screens currently displayed in the bullet screen display area, and a first bullet screen reply is sent to the device of the third user associated with the seventh bullet screen to be replied to. The first bullet screen reply is a bullet screen reply sent by the device of the first user.
[0096] For example, when a user replies to a bullet comment, the reply can be automatically sent to the sender of the bullet comment via the KO button (achieving one-to-many replies), or a targeted bullet comment can be selected for a targeted reply (achieving one-to-one targeted reply), which is pushed to the target user's personalized message inbox, achieving physical isolation from the public bullet comment stream to enhance bullet comment interaction.
[0097] In this embodiment of the disclosure, the seventh comment that has been replied to is removed from the comment display area, the ninth comment is determined from the eighth comment preloaded to the cache and used to fill the gap, and the ninth comment used to fill the gap is displayed in the comment display area.
[0098] For example, after the targeted delivery of a bullet comment is completed, the KO mechanism of the replied bullet comment is triggered. That is, the original bullet comment is removed from the current display queue and disappears from the interface. In order to maintain the stability of the number of bullet comments displayed, a sliding window replacement algorithm is used to automatically preload the bullet comments that are later in the original ranking into the local cache based on the preset popularity sorting mechanism. The ninth bullet comment is determined from the eighth bullet comment preloaded into the cache and used to fill the gap through a smooth transition animation. This ensures that the queue always maintains 5 dynamically updated lines and that the bullet comment display area always maintains the preset number of contents. At the same time, through the popularity priority filtering mechanism, the bullet comment content with more attention is given a continuous exposure opportunity. This realizes the combination of user behavior and automatic scheduling, optimizes the reasonable allocation of bullet comment display resources, meets the needs of real-time dialogue between users, and avoids the long-term occupation of low-attention content through the popularity control mechanism. Thus, a dynamic balance is established between interactivity and information effectiveness, improving user experience and ensuring the quality of bullet comments.
[0099] In summary, the bullet screen display method provided in this embodiment determines that the first user is an interactive user, performs semantic understanding on the bullet screens in the bullet screen display area to determine the type of bullet screen, obtains the first number of supporters for each of the first type of candidate bullet screens, determines a first bullet screen set from the first type of candidate bullet screens based on the first number of supporters, obtains the second number of supporters for each of the second type of candidate bullet screens, determines a second bullet screen set from the first type of candidate bullet screens based on the second number of supporters, and distinguishes between the first type of bullet screens and the second type of bullet screens in the bullet screen display area. In response to a bullet screen sending operation, the method obtains the first bullet screen input by the first user, performs semantic understanding on the first bullet screen to determine the type tag of the first bullet screen, filters a fourth bullet screen set from the bullet screen pool based on the type tag of the first bullet screen, the fourth bullet screen set includes at least one sixth bullet screen that is semantically opposite to the first bullet screen, and displays the first bullet screen and the sixth bullet screen in the bullet screen display area. Therefore, this disclosure automatically filters semantically contradictory bullet comments based on the type tags of the bullet comments when users send them, and displays them synchronously in the bullet comment display area. This not only makes it convenient for users to intuitively compare content with different stances and optimize the browsing experience, but also guides users to interact in a targeted manner and improves the efficiency of bullet comment interaction.
[0100] Figure 12 This is a flowchart illustrating a bullet screen display method provided in an embodiment of the present disclosure.
[0101] like Figure 12 As shown, the bullet screen display method proposed in this embodiment includes the following steps: S1201, Determine the type of the first user as a non-interactive user, and filter candidate bullet comments that need to be displayed in the bullet comment display area based on the popularity of the bullet comments.
[0102] Optionally, the first user can be identified based on the first user's historical behavior data using a multi-dimensional behavioral feature model to obtain the first user's type label, thereby determining whether the first user is a non-active user.
[0103] For example: Obtain the number of bullet comments sent and the number of likes received by the first user within the past 30 days. Using a pre-trained multi-dimensional behavioral feature model, identify the first user and determine that the ratio of the number of bullet comments sent to the number of videos watched is less than 0.5, and the ratio of the number of likes received to the number of videos watched is also less than 0.5, thus identifying the first user as a non-interactive user. Another example: Obtain the frequency of bullet comment blocking by the first user within the past 30 days. Using a pre-trained multi-dimensional behavioral feature model, identify the first user and determine that the frequency of bullet comment blocking by the first user is greater than 0.9, thus identifying the first user as a non-interactive user.
[0104] Optionally, the system monitors the first user's click on the "Interactive Mode" button, obtains the first user's behavioral data for the past 30 days, and determines the number of times the first user clicked on the interactive mode and the number of videos watched based on the behavioral data. If the ratio between the number of times the first user clicked on the interactive mode and the number of videos watched is greater than a preset threshold (e.g., 0.5), it is determined that the first user's willingness to interact has significantly increased, and the first user is updated from a non-interactive user to an interactive user.
[0105] It should be noted that the first user is identified as a non-interactive user. The popularity of the bullet comments in the current scenario is obtained, and the popularity of the bullet comments is sorted in descending order. Based on the popularity sorting results, candidate bullet comments that need to be displayed in the bullet comment display area are selected.
[0106] For example, if the first user is determined to be a non-interactive user, the popularity of the bullet comments is sorted in descending order. Based on the ranking of the bullet comments, the top 5 bullet comments in the ranking are selected as candidate bullet comments to be displayed in the bullet comment display area.
[0107] S1202, perform deduplication filtering on the candidate bullet comments to obtain the tenth bullet comment.
[0108] It should be noted that, in order to focus on the core popular viewpoints of the candidate bullet comments, a deduplication algorithm can be used to filter the candidate bullet comments to obtain the tenth bullet comment.
[0109] S1203 displays the tenth comment in the comment display area.
[0110] In summary, the bullet screen display method provided in this disclosure determines that the first user is a non-interactive user. Based on the popularity of the bullet screens, candidate bullet screens that need to be displayed in the bullet screen display area are selected. The candidate bullet screens are then deduplicated to obtain the tenth bullet screen, which is then displayed in the bullet screen display area. Therefore, this disclosure, targeting non-interactive users, reduces the obstruction and interference of bullet screens on the main content by displaying the tenth bullet screen in the bullet screen display area. This balances social interaction and immersive viewing experience while ensuring that users can obtain core popular viewpoints in the current scenario. This effectively meets the need for accessing light information, satisfies the needs of different user types, and enhances the scene adaptability of bullet screens.
[0111] Figure 13 This is a block diagram illustrating a bullet screen display device according to an exemplary embodiment.
[0112] like Figure 13 As shown, the bullet screen display device 1000 of this embodiment may specifically include: an acquisition module 100 and a display module 200.
[0113] The acquisition module 100 is used to determine that the type of the first user is an interactive user, and to acquire a first set of bullet comments and a second set of bullet comments, wherein the first set of bullet comments includes a first type of bullet comments, the second set of bullet comments includes a second type of bullet comments, and the first type of bullet comments and the second type of bullet comments are semantically opposite. The display module 200 is used to distinguish between the first type of bullet comments and the second type of bullet comments in the bullet comment display area.
[0114] In one embodiment of this disclosure, the acquisition module 100 is further configured to: perform semantic understanding on the bullet comments in the bullet comment display area to determine the type of bullet comments; acquire the first number of supporters for each of the first type of candidate bullet comments, and determine the first bullet comment set from the first type of candidate bullet comments based on the first number of supporters; acquire the second number of supporters for each of the second type of candidate bullet comments, and determine the second bullet comment set from the second type of candidate bullet comments based on the second number of supporters.
[0115] In one embodiment of this disclosure, after distinguishing and displaying the first type of bullet comments and the second type of bullet comments in the bullet comment display area, the device 1000 is further configured to: extract a second bullet comment from the bullet comment display area that is semantically opposite to the first bullet comment input by the device of the first user; retrieve a third bullet comment from the bullet comment pool that is semantically similar to the first bullet comment and is used to refute the second bullet comment, based on the first bullet comment and the second bullet comment; display the first bullet comment and the third bullet comment in the first display area of the bullet comment display area; and display the second bullet comment in the second display area of the bullet comment display area, wherein the second bullet comment and the third bullet comment are displayed one-to-one.
[0116] In one embodiment of this disclosure, the apparatus 1000 is further configured to: determine the similarity between the first bullet screen and the candidate bullet screens in the bullet screen pool; determine the conflict degree between the second bullet screen and the candidate bullet screens in the bullet screen pool; and determine the third bullet screen and the correspondence between the third bullet screen and the second bullet screen based on the similarity and the conflict degree.
[0117] In one embodiment of this disclosure, the device 1000 is further configured to: receive a second bullet screen reply sent by a device of a second user associated with the second bullet screen; display a first bullet screen reply input by the device of the first user in the first display area; and display a second bullet screen reply sent by the device of the second user in the second display area.
[0118] In one embodiment of this disclosure, after the device 1000 distinguishes and displays the first type of bullet comments and the second type of bullet comments in the bullet comment display area, it is further configured to: in response to detecting a bullet comment like operation, determine the fourth bullet comment operated by the first user based on the bullet comment like operation; obtain a third bullet comment set to be displayed based on the semantics of the fourth bullet comment, wherein the third bullet comment set includes at least one fifth bullet comment with semantics similar to the first bullet comment; and display the fifth bullet comment in the bullet comment display area.
[0119] In one embodiment of this disclosure, after the device 1000 distinguishes and displays the first type of bullet comments and the second type of bullet comments in the bullet comment display area, it is further configured to: in response to listening to a bullet comment sending operation, acquire the first bullet comment input by the first user; perform semantic understanding on the first bullet comment to determine the type tag of the first bullet comment; filter a fourth bullet comment set from the bullet comment pool according to the type tag of the first bullet comment, the fourth bullet comment set including at least one sixth bullet comment that is semantically opposite to the third bullet comment; and display the first bullet comment and the sixth bullet comment in the bullet comment display area.
[0120] In one embodiment of this disclosure, the device 1000 is further configured to: determine the popularity of the sixth bullet comment and the degree of conflict between the sixth bullet comment and the third bullet comment; determine the display priority of the sixth bullet comment based on the popularity and degree of conflict of the sixth bullet comment; and display the sixth bullet comment in the bullet comment display area according to the display priority, wherein the display styles of the first bullet comment and the sixth bullet comment are different.
[0121] In one embodiment of this disclosure, the device 1000 is further configured to: in response to detecting a barrage reply operation, determine the seventh barrage to be replied to from the barrages currently displayed in the barrage display area based on the type of the barrage reply operation; and send a first barrage reply to the device of the third user associated with the seventh barrage to which the first barrage is replied, wherein the first barrage reply is a barrage reply sent by the device of the first user.
[0122] In one embodiment of this disclosure, the device 1000 is further configured to: remove the seventh comment that has been replied to from the bullet screen display area; determine a ninth comment to fill in the gap from the eighth comments preloaded to the cache; and display the ninth comment to fill in the gap in the bullet screen display area.
[0123] In one embodiment of this disclosure, the device 1000 is further configured to: in response to the first user being a non-interactive user, filter candidate bullet comments to be displayed in the bullet comment display area based on the popularity of the bullet comments; perform deduplication filtering on the candidate bullet comments to obtain a tenth bullet comment; and display the tenth bullet comment in the bullet comment display area.
[0124] In the embodiments disclosed herein, the specific manner in which each structure in the bullet screen display device of the above embodiments performs its operation has been described in detail in the embodiments relating to the bullet screen display method, and will not be repeated here.
[0125] The bullet screen display device provided in this embodiment determines that the first user is an interactive user, and obtains a first bullet screen set and a second bullet screen set. The first bullet screen set includes a first type of bullet screen, and the second bullet screen set includes a second type of bullet screen. The first type of bullet screen and the second type of bullet screen are semantically opposite. The first type of bullet screen and the second type of bullet screen are displayed separately in the bullet screen display area. Therefore, this disclosure, for interactive users, distinguishes between two types of bullet screens with opposite meanings in the bullet screen display area. This reduces the obstruction and interference of bullet screens on the main content, and enables a direct comparison between the two types of bullet screens with opposite meanings. This is beneficial for improving user interaction efficiency and participation, meeting the needs of different types of users, and enhancing the scene adaptability of bullet screens.
[0126] Figure 14 This is a block diagram illustrating an electronic device 2000 according to an exemplary embodiment.
[0127] like Figure 14 As shown, the above-mentioned electronic device 2000 includes: The memory 2001 and the processor 2002 are connected by a bus 2003, which connects different components (including the memory 2001 and the processor 2002). The memory 2001 stores a computer program, and when the processor 2002 executes the program, it implements the bullet screen display method of this disclosure embodiment.
[0128] Bus 2003 refers to one or more of several bus architectures, including memory buses or memory controllers, peripheral buses, graphics acceleration ports, processors, or local buses using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0129] Electronic device 2000 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 2000, including volatile and non-volatile media, removable and non-removable media.
[0130] Memory 2001 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 2004 and / or cache memory 2005. Electronic device 2000 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 2006 may be used to read and write non-removable, non-volatile magnetic media (… Figure 14 Not shown; usually referred to as a "hard drive"). Although Figure 14 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 2003 via one or more data media interfaces. Memory 2001 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.
[0131] A program / utility 2008 having a set (at least one) of program modules 2007 may be stored, for example, in memory 2001. Such program modules 2007 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 2007 typically perform the functions and / or methods described in the embodiments of this disclosure.
[0132] Electronic device 2000 can also communicate with one or more external devices 2009 (e.g., keyboard, pointing device, display 2011, etc.), and with one or more devices that enable a user to interact with the electronic device 2000, and / or with any device that enables the electronic device 2000 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 2012. Furthermore, electronic device 2000 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 2013. Figure 14 As shown, network adapter 2013 communicates with other modules of electronic device 2000 via bus 2003. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 2000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0133] The processor 2002 performs various functional applications and data processing by running programs stored in the memory 2001.
[0134] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the bullet screen display method of this disclosure embodiment, and will not be repeated here.
[0135] To implement the above embodiments, this disclosure also proposes a computer-readable storage medium.
[0136] When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the aforementioned bullet screen display method. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.
[0137] The examples in this application may involve user data, data acquisition, and / or use. All of these aspects comply with relevant laws, regulations, and provisions. In the examples of this application, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing each example, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained through appropriate means in accordance with relevant laws and regulations. The specific methods of notification and / or authorization can vary depending on the actual situation and application scenario, and the scope of the solution is not limited in this regard.
[0138] In this manual and the sample solutions, any processing of personal information will be conducted only under legal grounds (such as obtaining the consent of the data subject or being necessary for the performance of a contract) and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.
[0139] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0140] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for displaying bullet comments, characterized in that, The method includes: The type of the first user is determined to be an interactive user. A first set of bullet comments and a second set of bullet comments are obtained, wherein the first set of bullet comments includes a first type of bullet comments and the second set of bullet comments includes a second type of bullet comments. The first type of bullet comments and the second type of bullet comments are semantically opposite. The first type of bullet comments and the second type of bullet comments are displayed differently in the bullet comment display area.
2. The method according to claim 1, characterized in that, The acquisition of the first set of bullet comments and the second set of bullet comments includes: Perform semantic understanding on the bullet comments in the bullet comment display area to determine the type of the bullet comments; Obtain the first number of supporters for each of the first type of candidate bullet comments, and determine the first bullet comment set from the first type of candidate bullet comments based on the first number of supporters; Obtain the second number of supporters for each of the second type of candidate bullet comments, and determine the second bullet comment set based on the second number of supporters from the second type of candidate bullet comments.
3. The method according to claim 1, characterized in that, After distinguishing between the first type of bullet comments and the second type of bullet comments in the bullet comment display area, the method further includes: Extract a second bullet screen from the bullet screen display area that is semantically opposite to the first bullet screen input by the first user's device; Based on the first and second bullet comments, a third bullet comment that is semantically similar to the first bullet comment and is used to refute the second bullet comment is retrieved from the bullet comment pool; The first and third bullet comments are displayed in the first display area of the bullet comment display area; The second bullet screen is displayed in the second display area of the bullet screen display area, wherein the second bullet screen is displayed one-to-one with the third bullet screen.
4. The method according to claim 3, characterized in that, The step of retrieving a third bullet comment from the bullet comment pool that is semantically similar to the first bullet comment and is used to refute the second bullet comment, based on the first bullet comment and the second bullet comment, includes: Determine the similarity between the first bullet screen and the candidate bullet screens in the bullet screen pool; Determine the degree of conflict between the second bullet screen and the candidate bullet screens in the bullet screen pool; Based on the similarity and the conflict, the third bullet screen and the correspondence between the third bullet screen and the second bullet screen are determined.
5. The method according to claim 4, characterized in that, The method further includes at least one of the following operations: Receive the second bullet screen reply sent by the device of the second user associated with the second bullet screen; The first bullet screen reply entered by the first user's device is displayed in the first display area; The second display area displays the second bullet screen reply sent by the device where the second user is located.
6. The method according to claim 1, characterized in that, After distinguishing between the first type of bullet comments and the second type of bullet comments in the bullet comment display area, the method further includes: In response to the detection of a danmaku like operation, the fourth danmaku operation performed by the first user is determined based on the danmaku like operation. Based on the semantics of the fourth bullet screen, a set of third bullet screens to be displayed is obtained, wherein the set of third bullet screens includes at least one fifth bullet screen with semantics similar to the first bullet screen; The fifth bullet screen is displayed in the bullet screen display area.
7. The method according to claim 1, characterized in that, After distinguishing between the first type of bullet comments and the second type of bullet comments in the bullet comment display area, the method further includes: In response to the detection of a bullet screen sending operation, the first bullet screen input by the first user is obtained; Perform semantic understanding on the first bullet comment to determine its type tag; Based on the type tag of the first bullet comment, a fourth bullet comment set is selected from the bullet comment pool, the fourth bullet comment set including at least one sixth bullet comment that is semantically opposite to the third bullet comment; The first and sixth bullet comments are displayed in the bullet comment display area.
8. The method according to claim 7, characterized in that, The display of the sixth bullet comment in the bullet comment display area includes: Determine the popularity of the sixth bullet comment and the degree of conflict between the sixth bullet comment and the third bullet comment; The display priority of the sixth bullet comment is determined based on its popularity and conflict level. The sixth bullet comment is displayed in the bullet comment display area according to the display priority, wherein the display style of the first bullet comment is different from that of the sixth bullet comment.
9. The method according to any one of claims 3 or 8, characterized in that, The method further includes: In response to the detection of a bullet screen reply operation, based on the type of the bullet screen reply operation, the seventh bullet screen that was replied to is determined from the bullet screens currently displayed in the bullet screen display area; Send a first bullet comment reply to the device of the third user associated with the seventh bullet comment that was replied to, wherein the first bullet comment reply is a bullet comment reply sent by the device of the first user.
10. The method according to claim 9, characterized in that, The method further includes: Remove the seventh comment that was replied to from the display area; The ninth bullet is determined from the eighth bullet preloaded into the cache; The ninth bullet comment used to fill in the gap is displayed in the bullet comment display area.
11. The method according to claim 1, characterized in that, The method further includes: The first user is determined to be a non-interactive user. Based on the popularity of the bullet comments, candidate bullet comments that need to be displayed in the bullet comment display area are filtered. The candidate bullet comments are deduplicated to obtain the tenth bullet comment; The tenth bullet comment is displayed in the bullet comment display area.
12. A bullet screen display device, characterized in that, The device includes: The acquisition module is used to determine that the type of the first user is an interactive user, and to acquire a first set of bullet comments and a second set of bullet comments, wherein the first set of bullet comments includes a first type of bullet comments, the second set of bullet comments includes a second type of bullet comments, and the first type of bullet comments and the second type of bullet comments are semantically opposite. The display module is used to differentiate between the first type of bullet comments and the second type of bullet comments in the bullet comment display area.
13. An electronic device, characterized in that, include: processor; Memory for storing the executable instructions of the processor; The processor is configured to execute the instructions to implement the bullet screen display method as described in any one of claims 1-11.
14. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the bullet screen display method as described in any one of claims 1-11.
15. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the bullet screen display method according to any one of claims 1-11.
