A method for displaying a barrage message based on a portrait screen display and related products
By using a message count prediction model in portrait mode, the bullet comments in cloud meetings are displayed reasonably, solving the problem of bullet comments obscuring content and improving the browsing experience and efficiency of cloud meetings.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN LEBO SCI & TECH CO LTD
- Filing Date
- 2022-07-19
- Publication Date
- 2026-07-24
AI Technical Summary
In cloud meetings, a large number of bullet comments may obscure the content displayed on the page, affecting the browsing experience for participants and reducing the efficiency of the cloud meeting process.
A vertical screen-based display method is adopted, which uses a message quantity prediction model to predict the number of bullet comments in the target cloud meeting and displays the bullet comments in the target display area to avoid obscuring important content.
In portrait mode, display bullet comments appropriately to ensure that the browsing experience of participants is not affected and to improve the efficiency of cloud meetings.
Smart Images
Figure CN115269080B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer technology, and in particular to a method for displaying bullet screen messages based on vertical screen display and related products. Background Technology
[0002] With the rapid development of internet technology and the rapid increase in business activity, online cloud meetings have become a new form of office work. In order to improve the interactivity of cloud meetings and thus promote their progress, current cloud meeting systems often allow participants to send bullet comments on the content of media files.
[0003] Due to the rapid rise and widespread adoption of cloud conferencing, the number of participants in cloud meetings is showing a significant upward trend. Consequently, cloud meetings with a large number of participants may receive a large number of bullet comments (or "bullet comments") during the meeting. Therefore, if a large number of bullet comments appear on the media file display page, and these bullet comments appear anywhere on the page, obscuring the content, this will undoubtedly affect the viewing experience for participants and reduce the efficiency of the cloud meeting process. Summary of the Invention
[0004] This application provides a method and related products for displaying bullet comments based on vertical screen display. Implementing this application ensures that media files have a better browsing effect.
[0005] In a first aspect, embodiments of this application provide a method for displaying bullet screen messages based on a vertical screen display, applied to a server, wherein the server is communicatively connected to a terminal device, and the terminal device is a device for conducting cloud conferencing. The method includes:
[0006] Obtain the media file display method and the meeting attributes of the target cloud meeting from the terminal device;
[0007] Determine whether the media files are displayed in portrait mode;
[0008] If the media files are displayed in portrait mode, the meeting attributes are input into the message count prediction model to obtain the predicted message count for the target cloud meeting.
[0009] If the predicted number of messages is greater than the preset number of messages, then the bullet screen messages will be displayed in the target display area of the media file of the target cloud meeting. The bullet screen messages are messages sent during the target cloud meeting.
[0010] Secondly, embodiments of this application provide a bullet screen message display device based on vertical screen display, applied to a server, wherein the server is communicatively connected to a terminal device, and the terminal device is a device for conducting cloud conferencing. The device includes:
[0011] The acquisition unit is used to obtain the media file display method and the meeting attributes of the target cloud meeting from the terminal device;
[0012] The determination unit is used to determine whether the media file is displayed in portrait mode.
[0013] The model unit is used to input the meeting attributes into the message count prediction model if the media file is displayed in portrait mode, so as to obtain the predicted message count of the target cloud meeting.
[0014] The display unit is used to determine to display bullet comments in the target display area of the media file of the target cloud meeting if the predicted number of messages is greater than the preset number of messages. The bullet comments are messages sent during the target cloud meeting.
[0015] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, and computer-executable instructions stored in the memory and executable on the processor. When the computer-executable instructions are executed, the electronic device performs some or all of the steps described in any method of the first aspect of this application.
[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions that, when executed on a communication device, cause the communication device to perform some or all of the steps described in any method of the first aspect of this application.
[0017] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.
[0018] As can be seen, in this embodiment, the media file display method and the meeting attributes of the target cloud meeting are obtained from the terminal device; it is determined whether the media file display method is a portrait display method; if the media file display method is a portrait display method, the meeting attributes are input into the message quantity prediction model to obtain the predicted message quantity of the target cloud meeting; if the predicted message quantity is greater than the preset message quantity, it is determined to display bullet comments in the target display area of the media file of the target cloud meeting. The bullet comments are messages sent during the target cloud meeting. By using the method of this embodiment, when the media file display method is a portrait display method and the predicted message quantity of the target cloud meeting is greater than the preset message quantity, a target display area is determined in the media file of the target cloud meeting, and bullet comments are displayed in the target display area, thereby avoiding visual obstruction of the content information included in the media file display page by the bullet comments and affecting the browsing experience of the participants. Attached Figure Description
[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 This is a schematic diagram of the architecture of the cloud conferencing system used in the embodiments of this application;
[0021] Figure 2 This is a flowchart illustrating a method for displaying bullet comments based on a vertical screen display, as provided in an embodiment of this application.
[0022] Figure 3 This is an example schematic diagram of a method for displaying bullet screen messages based on a vertical screen display provided in an embodiment of this application;
[0023] Figure 4 This is an example diagram illustrating another method for displaying bullet comments based on a vertical screen display, provided in an embodiment of this application.
[0024] Figure 5 This is an example diagram illustrating another method for displaying bullet comments based on a vertical screen display, provided in an embodiment of this application.
[0025] Figure 6 This is an example diagram illustrating another method for displaying bullet comments based on a vertical screen display, provided in an embodiment of this application.
[0026] Figure 7 This is a schematic diagram of the structure of a bullet screen message display device based on vertical screen display provided in an embodiment of this application;
[0027] Figure 8 This is a schematic diagram of the server structure of the hardware operating environment of an electronic device provided in an embodiment of this application. Detailed Implementation
[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.
[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.
[0030] The application scenarios involved in the embodiments of this application are described below with reference to the accompanying drawings.
[0031] Figure 1 This is a schematic diagram of the architecture of the cloud conferencing system used in the embodiments of this application. Figure 1 As shown, the cloud conferencing system includes a server and a database. The first end of the server is connected to a first local device and a second local device, and the second end of the server is connected to the database.
[0032] The first local device refers to the terminal device used by the cloud meeting creator in the cloud meeting. It is used to send a cloud meeting creation request to the server when it receives the cloud meeting creation instruction initiated by the cloud meeting creator. In specific implementation, the cloud meeting creation instruction and cloud meeting creation request may include the cloud meeting attribute information, including the meeting type, the number of participants, the job level of the participants, etc. The first local device includes the user's terminal device or screen projection device.
[0033] The second local device refers to the terminal device used by the cloud meeting host. Upon receiving a command from a target participant to acquire the hosting rights, the host sends a cloud meeting hosting request to the server. After receiving approval from the server, the target participant becomes the cloud meeting host. The host then gains control of the cloud meeting control desktop through the second local device, enabling them to display shared content and explanations. Shared content refers to the information uploaded by participants to the cloud meeting system's database. Explanation information includes at least one of the following: editing information, annotations, and voice information. The objects directly associated with the explanation information include the shared content itself or the electronic whiteboard created during the explanation. The cloud meeting control desktop displays at least one shared content item. A single cloud meeting host can input explanation information for one or more shared content items, and one or more hosts can input explanation information for a single shared content item. In practice, the cloud meeting host can delete comments sent by other participants. The second local device includes the user's terminal device or screen projection device.
[0034] The third local device refers to the terminal device used by participants other than the cloud meeting creator and host. It is used to view the shared content and explanations on the cloud meeting control desktop. Participants can send bullet comments through their terminal devices and view bullet comments sent by other participants on the cloud meeting control desktop. The third local device includes the user's terminal device.
[0035] The server is used to create a cloud meeting group in the cloud after receiving a cloud meeting creation request from the first local device, so that participants in the cloud meeting can join the cloud meeting through their local devices. In specific implementation, the server can be a cloud server.
[0036] The database is used to store the meeting data of the cloud meeting. The meeting data includes control plane data and data plane data. In a specific implementation, the database can be a cloud space database.
[0037] In practice, the shared content can be office document files (including Word, PPT, Excel, etc.), CAD drawing files, audio files, video files, or split-screen mirrors and screen recordings from the user's local device. The identities of the cloud meeting creator, cloud meeting host, and other participants are interchangeable. That is, the cloud meeting creator can also be the cloud meeting host and can become another participant by transferring the hosting rights. Similarly, the first local device, the second local device, and the third local device can also switch between each other based on the user's identity in the cloud meeting.
[0038] Based on this, this application provides a method for displaying bullet screen messages based on vertical screen display, applied to a server, wherein the server and a terminal device are connected for communication, and the terminal device is a device for conducting cloud conferencing. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a flowchart illustrating a method for displaying bullet comments based on a vertical screen display, as provided in an embodiment of this application. Figure 2 As shown, the method includes the following steps:
[0039] 101: Obtain the media file display method and the meeting attributes of the target cloud meeting from the terminal device.
[0040] In practice, the server can be a cloud server.
[0041] In specific implementations, terminal devices can be electronic devices such as smartphones, tablets, personal digital assistants, and wearable devices.
[0042] Among them, media files can be office document files (including Word, PPT, Excel, etc.), CAD drawing files, audio files, video files, or screen mirroring and screen recording content from the user's local device.
[0043] In practice, the meeting attributes of the target cloud meeting can include information such as the meeting type, the number of participants, and the job titles of the participants.
[0044] 102: Determine whether the media file is displayed in portrait mode.
[0045] Among them, the vertical screen display mode refers to the display of media files by placing the terminal device vertically. In the vertical screen display mode, the horizontal length of the cloud meeting control desktop is less than the vertical length.
[0046] In specific implementations, the portrait display method can include both a portrait display method where the media file is not displayed in full screen and a portrait display method where the media file is displayed in full screen.
[0047] For example, please refer to Figure 3 , Figure 3 This is an example schematic diagram illustrating a method for displaying bullet comments based on a vertical screen display, as provided in an embodiment of this application. Figure 3 As shown in (a), when the terminal device is displayed in portrait mode, the initial interface of the cloud meeting discussion is a non-full-screen portrait display of media files. In this interface, in addition to the media file display page, there is other meeting content information and operable buttons. If the full-screen display button is clicked in the non-full-screen portrait display interface, then... Figure 3 As shown in (b), the media file will be displayed in a full-screen portrait mode, in which the media file display page will occupy the entire content of the terminal device screen.
[0048] 103: If the media files are displayed in portrait mode, input the meeting attributes into the message count prediction model to obtain the predicted message count for the target cloud meeting.
[0049] In the specific implementation of the message quantity prediction model, it can be a regression analysis prediction model. In the regression analysis prediction model, the information included in the meeting attributes is the independent variable, and the predicted message quantity of the target cloud meeting is the dependent variable.
[0050] The predicted message count for the target cloud meeting refers to the number of bullet comments that the message count prediction model outputs based on the input meeting attributes, indicating the potential number of bullet comments received in the target cloud meeting. In a specific implementation, the predicted message count can refer to the total number of bullet comments that may appear across all display pages of the media file.
[0051] 104: If the predicted number of messages is greater than the preset number of messages, then the bullet screen messages will be displayed in the target display area of the media file of the target cloud meeting. The bullet screen messages are messages sent during the target cloud meeting.
[0052] The preset message count can be 30, 50, 70, or other values.
[0053] In practice, the target display area can be a background section in each display page of the media file that does not contain content information, or it can extend from the background section that does not contain content information to the surrounding sections that do not contain content information of greater importance.
[0054] In practical implementation, due to the real-time and interactive nature of bullet comments, their display on the media file presentation page will inevitably obscure part of the page and attract the attention of cloud meeting participants. Clearly, an excessive number of bullet comments will reduce the browsing experience of the media file presentation page and hinder the progress of the cloud meeting. Therefore, when the predicted number of messages is greater than the preset number, the bullet comments are displayed in the target display area of the media file in the target cloud meeting. Conversely, when the predicted number of messages is less than or equal to the preset number, the impact of fewer bullet comments on the browsing experience of the media file presentation page is smaller; therefore, in this case, the bullet comments can be displayed in the initial preset display area of the media file.
[0055] Bullet comments refer to the commentary text posted by conference participants on their own devices in response to the content displayed on the media file presentation page. In practice, the text display direction of bullet comments on the media file presentation page can be either horizontal or vertical.
[0056] For example, assuming the preset message count is 50, please refer to... Figure 4 , Figure 4 This is an example diagram illustrating another method for displaying bullet comments based on a vertical screen display, as provided in the embodiments of this application. Figure 4 As shown, the server obtains the media file display method and the meeting attributes of the target cloud meeting from the terminal device. The server determines that the media file display method is a portrait display method. Therefore, the server inputs the meeting attributes into the message quantity prediction model and obtains a predicted message quantity of 80 for the target cloud meeting. It can be seen that the predicted message quantity is greater than the preset message quantity. Therefore, the server determines to display the bullet screen messages sent from the terminal devices of the participants during the target cloud meeting in the target display area of the media file of the target cloud meeting.
[0057] As can be seen, in this embodiment, the media file display method and the meeting attributes of the target cloud meeting are obtained from the terminal device; it is determined whether the media file display method is a portrait display method; if the media file display method is a portrait display method, the meeting attributes are input into the message quantity prediction model to obtain the predicted message quantity of the target cloud meeting; if the predicted message quantity is greater than the preset message quantity, it is determined to display bullet comments in the target display area of the media file of the target cloud meeting. The bullet comments are messages sent during the target cloud meeting. By using the method of this embodiment, when the media file display method is a portrait display method and the predicted message quantity of the target cloud meeting is greater than the preset message quantity, a target display area is determined in the media file of the target cloud meeting, and bullet comments are displayed in the target display area, thereby avoiding visual obstruction of the content information included in the media file display page by the bullet comments and affecting the browsing experience of the participants.
[0058] In one possible example, determining to display the bullet screen message in the target display area of the media file of the target cloud meeting includes:
[0059] Obtain the content information of the target display page, which is one of the multiple display pages included in the media file;
[0060] Based on the content information of the target display page, obtain the content area of at least one content section included in the target display page;
[0061] Determine the thematic relevance between each content segment in at least one content segment and the target cloud meeting;
[0062] Identify the uncovered areas in the target display page. The uncovered areas are page areas that are not covered by at least one content section included in the target display page.
[0063] The target display area is determined based on the thematic relevance between the content information of each content segment and the target cloud meeting, as well as the uncovered areas in the target display page. The bullet screen message is then displayed in the target display area of the media file in the target cloud meeting.
[0064] The content information displayed on the target page can include text, images, and audio information in its specific implementation.
[0065] The target display page includes at least one content section, which in a specific implementation refers to a section on the target display page that explains a certain content theme or title; the content area of at least one content section, in a specific implementation refers to the location area on the target display page corresponding to the content section.
[0066] Specifically, determining the thematic relevance between each content segment and the target cloud meeting involves matching the content pointed to by each content segment with the thematic content pointed to by the target cloud meeting to determine the thematic relevance between each content segment and the target cloud meeting. The higher the matching degree between the content pointed to by the two, the higher the thematic relevance.
[0067] Specifically, the target display area is determined based on the thematic relevance between the content information of each content segment and the target cloud meeting, as well as the uncovered areas in the target display page. In practice, this can be achieved by prioritizing the display of bullet comments on content segments with lower thematic relevance to the target cloud meeting, in addition to the uncovered areas. In other words, the target display area is determined by extending from the uncovered areas to the content areas where content segments with low thematic relevance are located, thereby avoiding the impact on the browsing experience caused by important content segments with high thematic relevance to the target cloud meeting being covered by a large number of bullet comments.
[0068] As can be seen, in this embodiment, by obtaining the content information of the target display page and determining the content area of at least one content section included in the target display page based on the content information, the thematic relevance between each content section and the target cloud meeting is determined, and the uncovered areas in the target display page not covered by each content section are determined. Finally, the target display area is determined based on the thematic relevance between the content information of each content section and the target cloud meeting, and the uncovered areas in the target display page. The bullet comments are then displayed in the target display area of the media file in the target cloud meeting. This allows the target display area of the target display page to be determined based on the thematic relevance between the content section and the target cloud meeting, thereby avoiding a large number of bullet comments covering important content sections and causing obstruction, which would affect the browsing experience.
[0069] In some application scenarios, the different types of content information corresponding to the content sections included on the media file display page may all have a certain degree of thematic relevance to the cloud meeting. Furthermore, the audio information displayed on the page may also have a certain degree of thematic relevance to the cloud meeting. Therefore, this application embodiment provides another method for displaying bullet screen messages based on vertical screen display, as follows:
[0070] In a possible example, the above determination of the topic relevance between each content segment and the target cloud meeting includes:
[0071] Determine the thematic relevance between each content section and the target cloud meeting based on the matching degree between the content information of each content section and the target cloud meeting; and / or obtain the target audio information of the target cloud meeting under the target display page;
[0072] Perform speech recognition on the target speech information and extract at least one target keyword from the target speech information;
[0073] Determine the thematic relevance between each content section and the target cloud meeting based on the total number of target keywords included in each content section.
[0074] Specifically, the thematic relevance between each content segment and the target cloud meeting is determined based on the matching degree between the content information of each content segment and the target cloud meeting. In practice, the higher the matching degree between the content information of the content segment in the target display page and the target cloud meeting, the higher the thematic relevance between the content segment and the target cloud meeting.
[0075] If the content information is image information, in the specific implementation, feature description information can be obtained by obtaining the text description information of the image information and / or performing feature recognition on the image information, and then the text description information and / or feature description information of the image information can be matched with the topic relevance between the target cloud meeting.
[0076] In the specific implementation, the target voice information under the target display page can refer to the voice information sent in real time by the participants of the target cloud meeting under the target display page, or it can refer to the voice information included in the voice audio embedded in the target display page.
[0077] This involves performing speech recognition on the target speech information and extracting at least one target keyword from it. In practice, speech recognition models such as the GMM-HMM model can be used to perform speech recognition on the target speech information and extract the target keyword.
[0078] In practice, the more keywords a voice message contains that successfully match the content sections on the display page, the closer the content of the voice message is to the content of the display page. Therefore, the thematic relevance between each content section and the target cloud meeting is determined based on the total number of target keywords included in each content section. Furthermore, the more target keywords a content section contains, the higher its thematic relevance to the target cloud meeting.
[0079] As can be seen, in this embodiment, when determining the topic relevance between each content segment and the target cloud meeting, the topic relevance between each content segment and the target cloud meeting is determined based on the matching degree between the content information of each content segment and the target cloud meeting; and / or speech recognition is performed on the target audio information obtained under the target display page of the target cloud meeting to extract at least one keyword from the target audio information, and the topic relevance between each content segment and the target cloud meeting is determined based on the total number of target keywords included in each content segment. Therefore, even when the content information types corresponding to multiple content segments included in the target display page are different, the topic relevance between each content segment and the target cloud meeting can still be determined, improving the intelligence and flexibility of the process for determining the target display area for displaying bullet screen messages.
[0080] In a possible example, the target display area is determined based on the topic relevance between the content information of each content section and the target cloud meeting, as well as the uncovered areas in the target display page, including:
[0081] Identify a target uncovered area whose region is larger than a first preset range within the uncovered area;
[0082] If the target uncovered area is a single area, then the target uncovered area is determined as the target display area; if the target uncovered area is multiple areas, then the target uncovered area closest to the target content section is determined as the target display area, where the target content section has the greatest thematic relevance to the target cloud meeting.
[0083] In a specific implementation, the first preset range can be a range relative to the uncovered area. For example, the first preset range can be 20%, 40%, 60% or other sizes of the uncovered area.
[0084] In practice, during a cloud meeting, the content section on the display page that is most relevant to the theme of the cloud meeting tends to attract more attention from participants. If the bullet comments are displayed far away from the content section with the highest thematic relevance, it will undoubtedly cause the participants' attention to be distracted, thus reducing the efficiency of the cloud meeting. Therefore, if there are multiple areas that are not covered by the target, the target content section with the highest thematic relevance to the target cloud meeting is determined to be the nearest uncovered area as the target display area.
[0085] For example, please refer to Figure 5 , Figure 5 This is an example diagram illustrating another method for displaying bullet comments based on a vertical screen display, as provided in the embodiments of this application. Figure 5As shown in (a), if it is determined that the target uncovered area with a range larger than the first preset range is only a single target uncovered area A, then target uncovered area A is determined as the target display area for displaying bullet screen messages; Figure 5 As shown in (b), if it is determined that there are three target uncovered areas with a range greater than the first preset range: target uncovered area B, target uncovered area C, and target uncovered area D, and the target uncovered area with the highest thematic relevance to the target cloud meeting is the closest target uncovered area B, then target uncovered area B is determined as the target display area for displaying bullet screen messages.
[0086] As can be seen, in this embodiment, by determining a target uncovered area whose range is larger than a first preset range, and when the target uncovered area is a single area, it is determined as the target display area; while when there are multiple target uncovered areas, the target uncovered area closest to the target content section with the highest thematic relevance to the target cloud meeting is determined as the target display area. Thus, bullet screen messages can be preferentially displayed in the uncovered area near the target content section with the highest thematic relevance to the target cloud meeting, improving the intelligence and flexibility of the process for determining the target display area for displaying bullet screen messages, thereby ensuring a better browsing experience for the target display page during the target cloud meeting.
[0087] In some application scenarios, meetings may involve prolonged periods spent on the same page or multiple returns to that page. For such pages, participants are already familiar with the content and may be more interested in the bullet comments (or comments) sent by other participants. Therefore, the display area for these bullet comments can be appropriately expanded to show more messages. Thus, this application provides another method for displaying bullet comments in portrait mode, as follows:
[0088] In one possible example, the above method also includes:
[0089] Detect the number of times the target display page is displayed in the target cloud meeting;
[0090] When the number of times the target page is displayed exceeds the preset number, obtain the historical dwell time of the target page.
[0091] The target extension coefficient is determined based on the number of times the target is displayed and the historical dwell time.
[0092] Based on the target extension coefficient, the target display area of the target display page is extended to obtain the extended target display area.
[0093] In the specific implementation, the target display count refers to the total number of times the target display page is viewed.
[0094] The preset number of times can be 2, 3, 5 or other numbers in the specific implementation.
[0095] In the specific implementation, the historical dwell time of the target display page refers to the total dwell time corresponding to the total number of dwell times on the target display page.
[0096] The target extension coefficient is determined based on the number of times the target page is displayed and the historical dwell time. In practice, since cloud meeting participants are highly familiar with the content of a page when it is displayed multiple times or spent for extended periods, even if bullet comments partially obscure the content, it will not excessively affect their ability to interpret the information. Therefore, the more times the target page is displayed and the longer the historical dwell time, the larger the target extension coefficient. Furthermore, the target extension coefficient can be determined by weighted summation of the number of times the target page is displayed and the historical dwell time, resulting in the dwell coefficient of the target page. The target extension coefficient corresponding to the target page can then be determined based on this dwell coefficient.
[0097] Specifically, based on the target extension coefficient, the target display area of the target page is extended. In practice, the larger the target extension coefficient, the greater the extension of the target display area. The target extension coefficient can be represented by a numerical value from 0 to 1, thus the size of the extended target display area = (1 + target extension coefficient) * size of the target display area. Alternatively, it can be represented by a percentage from 0 to 100%, thus the size of the extended target display area = (100% + target extension coefficient) * size of the target display area.
[0098] For example, please refer to Figure 6 , Figure 6 This is an example diagram illustrating another method for displaying bullet comments based on a vertical screen display, as provided in the embodiments of this application. Figure 6 As shown in (a), when the target display page has not yet reached the preset number of target displays in the target cloud meeting, the size of the target display area used to display bullet screen messages is X; assuming the target extension coefficient is represented by a numerical form of 0 to 1, such as Figure 6As shown in (b), when the number of times the target display page is displayed in the target cloud meeting exceeds the preset number, the historical dwell time of the target display page is obtained, and the target extension coefficient is determined to be 0.5 based on the number of target displays and the historical dwell time. Then, the target display area of the target display page is extended based on the target extension coefficient of 0.5, and the size of the extended target display area is obtained as follows: (1 + target extension coefficient) * target display area = (1 + 0.5) * X = 1.5X. It can be seen that the size of the extended target display area is 1.5X, which can display more bullet screen messages due to its larger size.
[0099] As can be seen, in this embodiment, the target display page is displayed multiple times in the target cloud meeting. When the number of target displays exceeds a preset number, the historical dwell time of the target display page is obtained. A target extension coefficient is determined based on the number of target displays and the historical dwell time. Finally, the target display area of the target display page is extended according to the target extension coefficient to obtain the extended target display area. Therefore, when cloud meeting participants are familiar with the content of a display page, extending the target display area allows cloud meeting participants to interpret the content information in conjunction with more bullet comments, improving the intelligence and flexibility of the process for determining the bullet comment display area.
[0100] In one possible example, the above method also includes:
[0101] Identify the target popular bullet comments, which are the bullet comments with the most clicks in the expanded target display area;
[0102] Determine the target subsequent related pages corresponding to the target display page. The target subsequent related pages are those pages whose thematic relevance to the target display page is greater than the preset relevance.
[0103] Display the target's popular bullet comments on the target's subsequent related pages; or generate content entries corresponding to the target's popular bullet comments on the target's subsequent related pages.
[0104] In this process, determining the target subsequent related pages corresponding to the target display page can be achieved by first analyzing the theme of each display page included in the media file, determining the theme of each display page, and then matching the themes of each display page with those of other display pages to determine the degree of theme relevance between each display page and other display pages.
[0105] The preset correlation degree can be 70%, 75%, 80%, or other correlation degrees.
[0106] Specifically, displaying the target's popular bullet comments on the target's subsequent related pages means, in practice, showing the target's popular bullet comments again on the target's subsequent related pages; generating content entries corresponding to the target's popular bullet comments on the target's subsequent related pages means, in practice, directly generating the content entries of the target's popular bullet comments on the target's subsequent related pages as one of the content information included in the target's subsequent related pages, based on the content of the target's popular bullet comments. Furthermore, the content entries of the target's popular bullet comments can be saved, so that when the media file is displayed again, the content entries of the target's popular bullet comments will still be displayed on the target's subsequent related pages.
[0107] As can be seen from the embodiments of this application, the bullet screen message with the most clicks in the extended target display area is determined as the target popular bullet screen message, and the subsequent pages with a topic relevance greater than a preset relevance with the target display page are determined as the target subsequent related pages corresponding to the target display page. This allows the target popular bullet screen message to be displayed on the target subsequent related pages, or content entries corresponding to the target popular bullet screen message to be generated on the target subsequent related pages. Therefore, for target popular bullet screen messages with high-quality content that are most clicked and viewed by cloud meeting participants, they can appear on target subsequent related display pages with a high topic relevance to the target display page. This allows cloud meeting participants to further advance the cloud meeting process based on the cloud meeting topic by referring to the target subsequent related pages, significantly improving the intelligence and flexibility of the bullet screen message display process.
[0108] In some application scenarios, if a large number of bullet screen messages with a high degree of content repetition appear simultaneously on the display page within a short period of time, it will not only obscure the content information on the display page, but also significantly impact the browsing experience of cloud meeting participants. Therefore, this application embodiment provides another method for displaying bullet screen messages based on portrait screen display, as follows:
[0109] In one possible example, the above method also includes:
[0110] Get the number of multiple bullet screen message entries included in the bullet screen messages received within a preset time, and the content of each bullet screen message entry in the multiple bullet screen message entries;
[0111] Based on the content of each bullet comment message, determine the content repetition rate of multiple bullet comment message messages;
[0112] If the number of multiple bullet screen message entries is greater than the preset number of entries and the content repetition rate is greater than the preset repetition rate, then obtain the sender's permission level corresponding to each bullet screen message entry.
[0113] Identify the target bullet screen message entry. The target bullet screen message entry is the bullet screen message entry whose sender's permission level is greater than the preset permission level.
[0114] Delete all other bullet screen messages within a preset distance from the target bullet screen message.
[0115] The preset time can be 0.5 seconds, 2 seconds, or other times.
[0116] In the specific implementation, the bullet screen messages received within the preset time can refer to bullet screen messages that have been sent to the server by various terminal devices within the preset time but have not yet been displayed on the target display page, or bullet screen messages that have been displayed on the target display page within the preset time.
[0117] The preset number of entries can be 5, 8, 10, or other numbers.
[0118] The preset repetition rate can be 80%, 90%, or other repetition rates.
[0119] In practice, the content repetition rate among multiple bullet screen message entries can be achieved by keyword recognition and matching between bullet screen message entries.
[0120] In this context, the sender's permission level can be either the sender's meeting credit rating or their job title. Furthermore, obtaining the sender's permission level for each bullet screen message can be achieved by retrieving the user identifier representing the user's identity for each bullet screen message, and then using that user identifier to determine the associated sender's permission level.
[0121] As can be seen in this embodiment, when there are many bullet screen message items and the content repetition rate is high on the target display page, other bullet screen message items near the target bullet screen message item whose sender's permission is greater than the preset permission level are deleted. In this way, cloud meeting participants can focus their attention on the target bullet screen message item and avoid being distracted by a large number of other repetitive bullet screen message items. By improving the intelligence and flexibility of the bullet screen display process, the browsing effect of bullet screen message display on the target display page is guaranteed.
[0122] In a possible example, the training process of the above message quantity prediction model is as follows:
[0123] Obtain the training dataset, which consists of the historical meeting attributes of multiple historical cloud meetings. The historical meeting attributes include meeting information that may affect the total number of bullet comments in the historical cloud meetings.
[0124] Input the training dataset into the target prediction model to obtain the number of training and prediction messages for each historical cloud meeting in multiple historical cloud meetings;
[0125] The training prediction message count and the actual message count of each historical cloud meeting are input into the target loss function, and the target loss value is calculated based on the target loss function.
[0126] If the target loss value is greater than the preset loss value, detect loss anomaly information in the historical meeting attributes. Loss anomaly information refers to meeting information that causes the target loss value to be greater than the preset loss value.
[0127] Replace the loss anomaly information with alternative meeting information to obtain a new training dataset. Repeat the process of inputting the new training dataset into the target prediction model and obtaining the number of predicted messages until the target loss value between the training predicted message number and the actual message number is less than or equal to the preset loss value. Then, determine the multiple meeting information included in the new training dataset as meeting attributes, and the target prediction model including meeting attributes as model parameter information is the message number prediction model.
[0128] In the implementation of historical cloud meeting attributes, these attributes may include meeting attributes that may affect the number of bullet comments in the cloud meeting. Specifically, these attributes may include the cloud meeting topic type, the number of participants, the job titles of the participants, or other content.
[0129] The target loss function includes the Softmax cross-entropy loss function.
[0130] In this process, detecting loss anomalies in historical meeting attributes can be achieved using standardized regression coefficients to identify key items within these attributes that cause the target deviation value to exceed a preset deviation value. Standardized regression coefficients are obtained by simultaneously standardizing the independent and dependent variables in the target loss function. The independent variable is the historical meeting attribute of each historical cloud meeting, and the dependent variable is the number of training and prediction messages for each historical cloud meeting. Standardization eliminates the influence of differences in units and orders of magnitude, making different variables comparable. Therefore, standardized regression coefficients can be used to compare the effects of different independent variables on the dependent variable, thereby identifying loss anomalies in the historical meeting attributes.
[0131] As can be seen, the training process of the message quantity prediction model provided in this application embodiment can only guarantee the accuracy of the model's prediction of bullet screen messages if the meeting attributes that truly affect the total number of bullet screen messages in the cloud meeting are determined and these meeting attributes are applied to the message quantity prediction model. Furthermore, using the message quantity prediction model trained using the training process provided in this application embodiment to predict the number of bullet screen messages can free up manpower while ensuring that bullet screen messages are displayed in appropriate positions on the target display page, thus ensuring the browsing effect of media files.
[0132] With the above Figure 2 The embodiments shown are consistent; please refer to [link / reference]. Figure 7 , Figure 7 This is a schematic diagram of the structure of a bullet screen message display device based on vertical screen display provided in an embodiment of this application, as shown below. Figure 7 As shown:
[0133] A vertical screen-based bullet screen message display device is applied to a server, which communicates with a terminal device, the terminal device being a device for conducting cloud conferencing. The device includes:
[0134] The acquisition unit 201 is used to acquire the media file display method and the meeting attributes of the target cloud meeting from the terminal device.
[0135] Unit 202 is used to determine whether the media file is displayed in portrait mode.
[0136] Model unit 203 is used to input meeting attributes into the message quantity prediction model if the media file is displayed in portrait mode, so as to obtain the predicted message quantity of the target cloud meeting.
[0137] Display unit 204 is used to determine to display bullet comments in the target display area of the media file of the target cloud meeting if the predicted number of messages is greater than the preset number of messages. The bullet comments are messages sent during the target cloud meeting.
[0138] As can be seen, in the apparatus provided in this application embodiment, the media file display method and the meeting attributes of the target cloud meeting are obtained from the terminal device; it is determined whether the media file display method is a portrait display method; if the media file display method is a portrait display method, the meeting attributes are input into the message quantity prediction model to obtain the predicted message quantity of the target cloud meeting; if the predicted message quantity is greater than the preset message quantity, it is determined to display bullet comments in the target display area of the media file of the target cloud meeting, and the bullet comments are messages sent during the target cloud meeting. Using the apparatus of this application embodiment, when the media file display method is a portrait display method and the predicted message quantity of the target cloud meeting is greater than the preset message quantity, a target display area is determined in the media file of the target cloud meeting, and bullet comments are displayed in the target display area, thereby avoiding visual obstruction of the content information included in the media file display page by the bullet comments and affecting the browsing experience of the participants.
[0139] Specifically, in this embodiment, the functional units of the vertical screen-based bullet screen message display device can be divided according to the above method example. For example, each function can be divided into its own functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.
[0140] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.
[0141] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.
[0142] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.
[0143] If the integrated units described above are implemented as software program modules and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0144] With the above Figure 2 Consistent with the embodiments shown, this application provides an electronic device. Please refer to [link to relevant documentation]. Figure 8 , Figure 8 This is a schematic diagram of the server structure of the hardware operating environment of an electronic device provided in an embodiment of this application, as shown below. Figure 8 As shown, the electronic device includes a processor, a memory, and computer-executable instructions stored in the memory and executable on the processor. When the computer-executable instructions are executed, they cause the electronic device to perform steps including any of the steps of a bullet screen message display method based on a portrait screen display.
[0145] The processor is the CPU (Central Processing Unit).
[0146] The memory can be, optionally, high-speed RAM or stable memory, such as disk storage.
[0147] Those skilled in the art will understand that Figure 8 The server structure shown is not intended to limit it and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0148] like Figure 8As shown, the memory may include an operating system, a network communication module, and computer execution instructions for a vertical screen-based bullet screen message display method. The operating system manages and controls server hardware and software resources, supporting the execution of computer instructions. The network communication module enables communication between various components within the memory, as well as communication with other hardware and software within the server. Communication can use any communication standard or protocol, including but not limited to GSM (Global System for Mobile communication), GPRS (General Packet Radio Service), CDMA2000 (Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), etc.
[0149] exist Figure 8 In the server shown, the processor is used to execute computer execution instructions for personnel management stored in the memory to achieve the following steps: obtain the media file display mode and the meeting attributes of the target cloud meeting from the terminal device; determine whether the media file display mode is a portrait display mode; if the media file display mode is a portrait display mode, input the meeting attributes into the message quantity prediction model to obtain the predicted message quantity of the target cloud meeting; if the predicted message quantity is greater than the preset message quantity, determine to display bullet screen messages in the target display area of the media file of the target cloud meeting, and the bullet screen messages are messages sent during the target cloud meeting.
[0150] For specific implementation details of the server involved in this application, please refer to the various embodiments of the above-described method for displaying bullet screen messages based on vertical screen display, which will not be elaborated here.
[0151] This application provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a communication device, the communication device performs the following steps: obtaining the media file display method and the meeting attributes of the target cloud meeting from a terminal device; determining whether the media file display method is a portrait display method; if the media file display method is a portrait display method, inputting the meeting attributes into a message quantity prediction model to obtain the predicted message quantity of the target cloud meeting; if the predicted message quantity is greater than a preset message quantity, determining to display bullet comments in the target display area of the media file of the target cloud meeting, wherein the bullet comments are messages sent during the target cloud meeting. The aforementioned computer includes an electronic device.
[0152] Electronic terminal devices include mobile phones, tablets, personal digital assistants, wearable devices, etc.
[0153] The computer-readable storage medium can be an internal storage unit of the electronic device described in the above embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer-executable instructions and other computer-executable instructions and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
[0154] For specific implementations of the computer-readable storage medium involved in this application, please refer to the various embodiments of the above-described method for displaying bullet screen messages based on vertical screen display, which will not be repeated here.
[0155] This application provides a computer program product, which includes a computer program operable to enable the computer to perform some or all of the steps of any of the vertical screen-based bullet screen message display methods described in the above method embodiments. The computer program product may be a software installation package.
[0156] It should be noted that, for the sake of simplicity, each of the aforementioned embodiments of the bullet screen message display method based on vertical screen display is described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to this application.
[0157] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principle and implementation of a bullet screen message display method based on vertical screen display. The description of the above embodiments is only for the purpose of helping to understand the method and its core ideas of this application. At the same time, for those skilled in the art, based on the idea of a bullet screen message display method based on vertical screen display of this application, there will be changes in the specific implementation and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
[0158] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.
[0159] Those skilled in the art will understand that all or part of the steps in the various methods of any of the above-described methods for displaying bullet screen messages based on vertical screen display can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0160] Obviously, those skilled in the art can make various modifications and variations to the method for displaying bullet screen messages based on vertical screen display provided in this application without departing from the spirit and scope of this application. Therefore, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.
Claims
1. A method for displaying bullet screen messages based on vertical screen display, characterized in that, Applied to a server, wherein the server is communicatively connected to a terminal device, the terminal device being a device for conducting cloud conferencing, the method includes: Obtain the media file display method and the meeting attributes of the target cloud meeting from the terminal device; Determine whether the media file is displayed in portrait mode; If the media file is displayed in portrait mode, then the meeting attributes are input into the message quantity prediction model to obtain the predicted message quantity of the target cloud meeting. If the predicted number of messages is greater than the preset number of messages, then it is determined that bullet comments will be displayed in the target display area of the media file of the target cloud meeting. The bullet comments are messages sent during the target cloud meeting. The step of determining to display the bullet screen message in the target display area of the media file in the target cloud meeting includes: Obtain the content information of the target display page, wherein the target display page is one of the multiple display pages included in the media file; Based on the content information of the target display page, the content area of at least one content section included in the target display page is obtained; Determine the thematic relevance between each content segment in the at least one content segment and the target cloud meeting; Identify the uncovered area in the target display page, wherein the uncovered area is a page area that is not covered by any of the at least one content module included in the target display page; The target display area is determined based on the thematic relevance between the content information of each content section and the target cloud meeting, as well as the uncovered area in the target display page, and bullet comments are displayed in the target display area of the media file of the target cloud meeting.
2. The method according to claim 1, characterized in that, Determining the thematic relevance between each content segment and the target cloud meeting includes: The thematic relevance between the content area of each content segment and the target cloud meeting is determined based on the matching degree between the content information of each content segment and the target cloud meeting; and / or Obtain the target audio information of the target cloud meeting on the target display page; Perform speech recognition on the target speech information and extract at least one target keyword from the target speech information; Based on the total number of target keywords included in each content section, the thematic relevance between the content area of each content section and the target cloud meeting is determined.
3. The method according to claim 2, characterized in that, The step of determining the target display area based on the topic relevance between the content information of each content segment and the target cloud meeting, and the uncovered areas in the target display page, includes: Identify a target uncovered area whose region is larger than a first preset range within the uncovered region; If the target uncovered area is a single area, then the target uncovered area is determined as the target display area; if the target uncovered area is multiple areas, then the target uncovered area closest to the target content section is determined as the target display area, wherein the target content section has the greatest thematic relevance to the target cloud meeting.
4. The method according to claim 1, characterized in that, The method further includes: The number of times the target display page is displayed in the target cloud meeting is detected. When the number of times the target is displayed exceeds a preset number, the historical dwell time of the target display page is obtained; The target extension coefficient is determined based on the number of times the target is displayed and the historical dwell time. Based on the target extension coefficient, the target display area of the target display page is extended to obtain the extended target display area.
5. The method according to claim 4, characterized in that, The method further includes: Identify the target popular bullet screen message, which is the bullet screen message with the most clicks in the extended target display area; Determine the target subsequent related page corresponding to the target display page. The target subsequent related page is a subsequent page whose thematic relevance to the target display page is greater than a preset relevance. The target's popular bullet screen messages are displayed on the target's subsequent associated pages; or content entries corresponding to the target's popular bullet screen messages are generated on the target's subsequent associated pages.
6. The method according to claim 1, characterized in that, The method further includes: Obtain the number of multiple bullet screen message entries included in the bullet screen messages received within a preset time, and the content of each bullet screen message entry in the multiple bullet screen message entries; Based on the content of each bullet screen message item, determine the content repetition rate of the multiple bullet screen message items; If the number of the multiple bullet screen message entries is greater than the preset number of entries, and the content repetition rate is greater than the preset repetition rate, then obtain the sender permission level corresponding to each bullet screen message entry; Determine the target bullet screen message entry, wherein the target bullet screen message entry is a bullet screen message entry whose sender's permission level is greater than a preset permission level; Delete all other bullet screen message entries within a preset distance of the target bullet screen message entry.
7. The method according to any one of claims 1-6, characterized in that, The training process of the message quantity prediction model is as follows: Obtain a training dataset, which consists of historical meeting attributes from multiple historical cloud meetings. These historical meeting attributes include meeting information that may affect the total number of bullet comments in the historical cloud meetings. Input the training dataset into the target prediction model to obtain the number of training prediction messages for each historical cloud meeting in the multiple historical cloud meetings; The training and prediction message count of each historical cloud meeting and the actual message count of that historical cloud meeting are input into the target loss function, and the target loss value is calculated based on the target loss function. If the target loss value is greater than the preset loss value, detect loss anomaly information in the historical meeting attributes. The loss anomaly information is the meeting information that causes the target loss value to be greater than the preset loss value. Replace the loss anomaly information with alternative meeting information to obtain a new training dataset. Repeat the process of inputting the new training dataset into the target prediction model and obtaining the number of predicted messages until the target loss value between the number of trained predicted messages and the actual number of messages is less than or equal to the preset loss value. Then, determine the multiple meeting information included in the new training dataset as the meeting attributes, and the target prediction model including the meeting attributes as model parameter information is the message number prediction model.
8. A bullet screen message display device based on vertical screen display, characterized in that, Applied to a server, the server is communicatively connected to a terminal device, the terminal device being a device for conducting cloud conferencing, the device comprising: The acquisition unit is used to acquire the media file display method and the meeting attributes of the target cloud meeting from the terminal device; The determining unit is used to determine whether the media file is displayed in a portrait orientation. The model unit is used to input the meeting attributes into the message quantity prediction model to obtain the predicted message quantity of the target cloud meeting if the media file is displayed in the vertical screen mode. The display unit is configured to determine, if the number of predicted messages is greater than the number of preset messages, to display bullet comments in the target display area of the media file of the target cloud meeting, wherein the bullet comments are messages sent during the target cloud meeting. The step of determining to display the bullet screen message in the target display area of the media file in the target cloud meeting includes: Obtain the content information of the target display page, wherein the target display page is one of the multiple display pages included in the media file; Based on the content information of the target display page, the content area of at least one content section included in the target display page is obtained; Determine the thematic relevance between each content segment in the at least one content segment and the target cloud meeting; Identify the uncovered area in the target display page, wherein the uncovered area is a page area that is not covered by any of the at least one content module included in the target display page; The target display area is determined based on the thematic relevance between the content information of each content section and the target cloud meeting, as well as the uncovered area in the target display page, and bullet comments are displayed in the target display area of the media file of the target cloud meeting.
9. An electronic device, characterized in that, The electronic device includes a processor, a memory, and computer-executable instructions stored in the memory and executable on the processor, which, when executed, cause the electronic device to perform the method of any one of claims 1-7.