Bullet screen publishing method and device, computer device and computer readable storage medium

Abstract

The application discloses a method and device for publishing a barrage, computer equipment and a computer readable storage medium, and belongs to the technical field of computers. According to the application, keyword recognition is performed on a video and a barrage played on a playing interface, a barrage publishing step is automatically triggered when a target keyword is recognized, and the terminal automatically publishes a barrage corresponding to the target keyword on the playing interface without manual operation of a user. Therefore, the application can effectively simplify the operation steps of the user when publishing the barrage, reduce the time consumption of barrage publishing, improve the human-computer interaction efficiency in the barrage publishing process, and avoid affecting the process of the user watching the video.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer device, and computer-readable storage medium for publishing bullet comments. Background Technology

[0002] Bullet comments are commentary texts that can be overlaid on the video screen. Users can express their viewing experience by posting bullet comments while watching the video, and they can also see bullet comments posted by other users at the current video playback time. Users can communicate and interact with each other through bullet comments.

[0003] Currently, users typically edit and post bullet comments manually. This method requires users to manually input a lot of text, making the process complex and time-consuming, which can negatively impact the user's video viewing experience. Summary of the Invention

[0004] This application provides a method, apparatus, computer device, and computer-readable storage medium for publishing bullet comments, which can reduce the complexity and time consumption of bullet comment publishing operations. The technical solution is as follows: On the one hand, a method for posting bullet comments is provided, which includes: Play the target video on the playback interface; During the playback of the target video, keyword recognition is performed on at least one item in the target video and the corresponding bullet comments; In response to the inclusion of target keywords in the target video or the bullet comments, the target account's target bullet comments are displayed on the playback interface, and the target bullet comments correspond to the target keywords.

[0005] On the one hand, a bullet screen publishing device is provided, the device comprising: The video playback module is used to play the target video on the playback interface; The keyword recognition module is used to identify at least one keyword from the target video and its corresponding bullet comments during the playback of the target video. The bullet screen display module is used to automatically send target bullet screens from the target account in response to the target video or the bullet screen containing target keywords, and display the target bullet screens on the playback interface. The target bullet screens correspond to the target keywords.

[0006] In one possible implementation, the bullet screen display module is used for: The playback interface displays the target bullet screen moving along a custom trajectory.

[0007] In one possible implementation, the custom trajectory is determined based on any of the following methods: In response to a trajectory drawing operation, the custom trajectory is determined based on the trajectory drawn by the trajectory drawing operation; In response to the selection operation of the candidate motion trajectory, the selected candidate motion trajectory is determined as the custom trajectory; The preset motion trajectory is set as the custom motion trajectory.

[0008] In one possible implementation, the target keyword corresponds to at least two bullet comments; The device also includes a determining module for: The playback interface displays at least two bullet comments corresponding to the target keyword; The selected bullet comment from at least two bullet comments is identified as the target bullet comment.

[0009] In one possible implementation, the keyword recognition module includes: The `get` submodule is used to retrieve the account level of the currently logged-in target account; The identification submodule is used to identify keywords in at least one of the target video and the corresponding bullet comments during the playback of the target video in response to the account level meeting the reference conditions.

[0010] In one possible implementation, the identification submodule is used for: In response to the account level meeting the reference condition, at least one keyword corresponding to the target account is obtained, and each keyword corresponds to at least one bullet comment; During the playback of the target video, based on at least one keyword, keyword recognition is performed on at least one item in the target video and the corresponding bullet comments.

[0011] In one possible implementation, the keyword recognition module includes at least one of the following: The first submodule is used to perform keyword recognition on the video frames of the target video. The second submodule is used to perform keyword recognition on the subtitle data carried by the target video; The third submodule is used to perform keyword recognition on the audio data of the target video; The fourth submodule is used to identify keywords in the bullet screen.

[0012] In one possible implementation, the first submodule is used for: Character recognition is performed on the target area of ​​the video frame to obtain the first text information displayed in the target area; Match the first text information with at least one keyword; In response to the first text information successfully matching any keyword, it is determined that the target video includes the target keyword.

[0013] In one possible implementation, the keyword recognition module is used for: Retrieve the keyword matching method corresponding to the currently logged-in target account; In response to the fact that the keyword matching method is video matching, keyword recognition is performed on at least one of the audio data, video frame and subtitle data of the target video; In response to the keyword matching method being bullet screen matching, keyword recognition is performed on the bullet screen.

[0014] In one possible implementation, the device further includes: The interface display module is used to display the keyword setting interface in response to the keyword setting operation. The keyword setting interface includes an information display area and an information addition area. The storage module is used to store the keywords added in the information addition area and the corresponding bullet comments in response to the information addition operation in the information addition area; This interface display module is used to display the added keyword in the information display area, or to display the added keyword and the corresponding bullet comments in the information display area.

[0015] In one possible implementation, the interface display module is used for: Based on the target account's account level, determine the threshold for the number of keywords that can be added; If the number of keywords corresponding to the target account is less than the threshold, the information addition area in the keyword settings interface will be displayed as allowed to be added. When the number of keywords corresponding to the target account equals the threshold, the information addition area in the keyword settings interface is displayed as prohibited from being added.

[0016] In one possible implementation, the information addition operation includes any of the following: Input operations in this information addition area; The option to select from the candidates displayed in the information addition area is either a candidate keyword or a candidate bullet comment.

[0017] In one possible implementation, the storage module is used for: In response to the information addition operation in the information addition area, the bullet comments added in the information addition area are identified; If no sensitive words are detected in the bullet comment, the keywords added in the information addition area and the bullet comments corresponding to those keywords will be stored.

[0018] In one possible implementation, the device further includes: The information display module is used to display a target prompt message when the number of keywords corresponding to the target account is less than the number threshold. This target prompt message is used to prompt the user to add keywords and corresponding bullet comments.

[0019] On one hand, a computer device is provided, the computer device including one or more processors and one or more memories, the one or more memories storing at least one computer program, the at least one computer program being loaded and executed by the one or more processors to perform the operations performed by the bullet screen publishing method.

[0020] On the one hand, a computer-readable storage medium is provided, which stores at least one computer program, which is loaded and executed by a processor to implement the operations performed by the bullet screen publishing method.

[0021] On one hand, a computer program product is provided, comprising at least one computer program stored in a computer-readable storage medium. A processor of a computer device reads the at least one computer program from the computer-readable storage medium and executes the at least one computer program, causing the computer device to perform the operations performed by the aforementioned bullet screen publishing method.

[0022] The technical solution provided in this application embodiment identifies keywords in the video and bullet comments played on the playback interface. When a target keyword is identified, the bullet comment publishing step is automatically triggered. The terminal automatically publishes the bullet comment corresponding to the target keyword on the playback interface without requiring manual operation by the user. This effectively simplifies the user's operation steps when publishing bullet comments, reduces the time spent publishing bullet comments, improves the human-computer interaction efficiency of the bullet comment publishing process, and avoids the bullet comment publishing process affecting the user's video viewing process. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0024] Figure 1 This is a schematic diagram of the implementation environment of a bullet screen publishing method provided in an embodiment of this application; Figure 2 This is a flowchart of a bullet screen publishing method provided in an embodiment of this application; Figure 3 This is a flowchart illustrating a method for setting keywords and bullet comments according to an embodiment of this application; Figure 4 This is a schematic diagram of a playback interface provided in an embodiment of this application; Figure 5 This is a schematic diagram of a keyword setting interface provided in an embodiment of this application; Figure 6 This is a flowchart of a method for setting a threshold number of keywords provided in an embodiment of this application; Figure 7 This is a flowchart illustrating a method for adding keywords and bullet comments, as provided in an embodiment of this application. Figure 8 This is a flowchart of a bullet screen publishing process provided in an embodiment of this application; Figure 9 This is a schematic diagram illustrating a bullet screen display effect provided in an embodiment of this application; Figure 10 This is a flowchart of a bullet screen publishing method provided in an embodiment of this application; Figure 11 This is a schematic diagram of the structure of a bullet screen publishing device provided in an embodiment of this application; Figure 12 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application; Figure 13 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.

[0027] Figure 1 This is a schematic diagram illustrating the implementation environment of a bullet screen publishing method provided in an embodiment of this application. See also... Figure 1 The implementation environment includes terminal 110 and server 140.

[0028] The terminal 110 has a target application installed and running that supports video playback and bullet screen commenting. For example, the target application is a video application, a live streaming application, a browser application, etc. Exemplarily, the terminal 110 is a device used by any user, and the user's target account is logged in. Optionally, the terminal 110 can be a smartphone, tablet, laptop, e-book reader, MP3 (Moving Picture Experts Group Audio Layer III) player, MP4 (Moving Picture Experts Group Audio Layer IV) player, laptop computer, desktop computer, smart TV, smart in-vehicle device, etc. This application embodiment does not limit the scope of the application to this type of device.

[0029] Server 140 is the backend server for the target application, used to provide backend services for the target application. Optionally, server 140 may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. This application embodiment does not limit this.

[0030] Optionally, the terminal 110 and the server 140 are directly or indirectly connected via wired or wireless communication. Those skilled in the art will understand that the number of terminals can be more or less; for example, there can be only one terminal, or dozens or hundreds, or even more. This application embodiment does not limit the number and type of terminals in the above-described implementation environment.

[0031] The aforementioned terminals and servers can form a blockchain system, with both terminals and servers serving as node devices within the blockchain system. The aforementioned video data and bullet screen data can both be stored in the blockchain.

[0032] Figure 2 This is a flowchart illustrating a bullet screen posting method provided in an embodiment of this application. In one possible implementation, the method is executed by a terminal in the aforementioned implementation environment. In this embodiment, the terminal is used as the execution subject to describe the bullet screen posting method. See [link to relevant documentation]. Figure 2 In one possible implementation, this embodiment includes the following steps: 201. The terminal plays the target video on the playback interface.

[0033] In some embodiments, the terminal has a target application installed and running, which provides video playback and bullet comment posting functions, and the playback interface is the interface within the target application. In some embodiments, the playback interface may also be a target webpage that provides video playback and bullet comment posting functions; this application embodiment does not limit this. Optionally, the target video played by the playback interface may be a pre-recorded video or a live video; this application embodiment does not limit this.

[0034] 202. During the playback of the target video, the terminal performs keyword recognition on at least one of the target video and the corresponding bullet comments.

[0035] In this embodiment, the terminal can perform keyword recognition on at least one of the target video and the bullet comments, with each keyword corresponding to at least one bullet comment. The at least one keyword used for matching is either user-set or pre-set in the target application. For example, the keyword might be a trending internet term, and the corresponding bullet comments could be comments related to that trending term. For instance, if the keyword is "excavator," the corresponding bullet comments would be internet slang related to excavators. This embodiment does not limit the content of the keywords and bullet comments.

[0036] In one possible implementation, in response to the start of playback of the target video, the terminal performs keyword recognition on at least one of the target video and the bullet comments. For example, the terminal matches the lines of the target video or the bullet comments with at least one keyword to determine whether the target video or the bullet comments match a certain keyword.

[0037] 203. In response to the target video or the bullet screen containing the target keyword, the terminal automatically sends the target account's bullet screen and displays the target bullet screen on the playback interface. The target bullet screen corresponds to the target keyword.

[0038] The target account is the account currently logged into on the terminal. The target account can be the account of the user currently watching the target video, or it can be the account of other users. This application embodiment does not limit this.

[0039] In one possible implementation, in response to the target video or bullet screen hitting any of the at least one keyword, the terminal determines the target keyword as the target keyword and automatically sends the target bullet screen corresponding to the target keyword, thereby enabling the target bullet screen to be automatically published and displayed in the video playback interface without the user having to perform any manual operation.

[0040] The technical solution provided in this application embodiment identifies keywords in the video and bullet comments played on the playback interface. When a target keyword is identified, the bullet comment publishing step is automatically triggered. The terminal automatically publishes the bullet comment corresponding to the target keyword on the playback interface without requiring manual operation by the user. This effectively simplifies the user's operation steps when publishing bullet comments, reduces the time spent publishing bullet comments, improves the human-computer interaction efficiency of the bullet comment publishing process, and avoids the bullet comment publishing process affecting the user's video viewing process.

[0041] The above embodiments are a brief introduction to the technical solution of this application. Figure 3 This is a flowchart illustrating a method for setting keywords and bullet comments according to an embodiment of this application. The following is in conjunction with... Figure 3 This section provides a detailed explanation of the keywords and bullet comment settings involved in the bullet comment posting process. See [link / reference]. Figure 3 In one possible implementation, this embodiment includes the following steps: 301. The terminal displays the playback interface.

[0042] The playback interface refers to the playback interface corresponding to any video. For example, the playback interface includes settings controls, through which users can set relevant parameters for video playback and bullet screen display. In this embodiment, users can also set at least one keyword and its corresponding bullet screen comments through the settings controls. Figure 4 This is a schematic diagram of a playback interface provided in an embodiment of this application, such as... Figure 4 As shown in Figure (a), the playback interface includes a settings control 401. In response to a trigger operation on the settings control 401, the terminal displays a settings interface 402 in the first area of ​​the playback interface. For example, the settings interface 402 includes a settings area 403 for video playback-related parameters and a bullet screen settings control 404. Optionally, the relevant references for video playback include playback speed, aspect ratio, and screen brightness, etc., which are not limited in this embodiment. The trigger operation can be a click operation, a long press operation, etc., which are not limited in this embodiment. The first area can be any area within the playback interface. Figure 4As shown in Figure (b), in one possible implementation, in response to a trigger operation on the bullet screen setting control 404, the terminal displays a bullet screen setting interface 405. This interface includes a setting area 406 for relevant parameters of the bullet screen display. For example, these parameters include the type of bullet screen that can be displayed, the number of lines to display, and the font size of the bullet screen. This embodiment does not limit the specific parameters. In this embodiment, the bullet screen setting interface 405 also includes an automatic bullet screen posting setting control 407. Users can set at least one keyword and the corresponding bullet screens for each keyword through this control. It should be noted that the above description of the playback interface is merely an exemplary description of one possible implementation, and this embodiment does not limit the style of the playback interface.

[0043] In one possible implementation, the terminal can determine whether a user has the permission to automatically post bullet comments based on the account level of the currently logged-in target account; that is, whether the user can set keywords and bullet comments. For example, the terminal obtains the account level of the currently logged-in target account. If the account level meets the reference condition, the terminal displays the automatic bullet comment posting setting control in the bullet comment settings interface as triggerable, meaning the terminal determines that the user has the permission to automatically post bullet comments and allows the user to set keywords and bullet comments. If the account level does not meet the reference condition, the terminal displays the automatic bullet comment posting setting control in the bullet comment settings interface as non-triggerable, meaning the terminal determines that the user does not have the permission to automatically post bullet comments and does not allow the user to set keywords and bullet comments. The reference condition is set by the developer, and this application embodiment does not limit it. It should be noted that the above step of determining whether a user can set keywords and bullet comments based on account level is an optional step. In some embodiments, users with any account level can set keywords and bullet comments.

[0044] 302. The terminal responds to the keyword setting operation on the playback interface and displays the keyword setting interface.

[0045] by Figure 4Taking the playback interface shown as an example, in one possible implementation, the keyword setting operation is a trigger operation for the automatic bullet comment posting setting control in the bullet comment setting interface. The terminal, in response to the trigger operation of the automatic bullet comment posting setting control, displays the keyword setting interface. For example, the keyword setting interface includes an information display area and an information addition area. The information addition area is used to add keywords and the corresponding bullet comments; the information display area is used to display the added keywords. It should be noted that the above keyword setting operation can also be implemented in other forms, and this application embodiment does not limit this. In one possible implementation, in response to the keyword setting operation, the terminal obtains at least one keyword corresponding to the currently logged-in target account and displays the at least one keyword corresponding to the target account in the information display area of ​​the keyword setting interface. For example, the at least one keyword corresponding to the target account and the corresponding bullet comments are stored in first configuration information. In one possible implementation, in response to the keyword setting operation, the terminal obtains the first configuration information corresponding to the target account and displays the keyword setting interface based on the first configuration information; that is, the terminal reads the at least one keyword from the first configuration information and displays the at least one keyword in the information display area of ​​the keyword setting interface. It should be noted that the aforementioned keywords and corresponding bullet comments can also be stored in other forms, and this application embodiment does not limit this. In some embodiments, the terminal displays at least one keyword corresponding to the target account and the bullet comments corresponding to the at least one keyword in the information display area of ​​the keyword setting interface. For example, in response to the keyword setting operation, the terminal obtains the first configuration information corresponding to the target account, reads the at least one keyword and the corresponding bullet comments from the first configuration information, and displays the at least one keyword and the corresponding bullet comments in the information display area of ​​the keyword setting interface. Optionally, if the terminal does not obtain the keyword corresponding to the target account, it may not display information in the information display area, or it may display a preset keyword in the information display area, or it may display a preset keyword and the corresponding bullet comments in the information display area. It should be noted that this application embodiment does not limit the information displayed in the information display area of ​​the keyword setting interface.

[0046] Figure 5 This is a schematic diagram of a keyword setting interface provided in an embodiment of this application, such as... Figure 5As shown in Figure (a), the keyword setting interface includes an information addition area 501 and an information display area 502. The information addition area 501 includes a keyword addition area 503, a bullet comment addition area 504, and a confirmation addition control 505. The information display area 502 displays the added keywords. It should be noted that the above description of the keyword setting interface is merely an exemplary description of one possible implementation. This application embodiment does not limit the style of the keyword setting interface. In some embodiments, one keyword can correspond to multiple bullet comments, in which case the information addition area includes multiple bullet comment addition areas, such as... Figure 5 As shown in Figure (b) of this application embodiment, users can pre-set keywords and corresponding bullet comments based on their own bullet comment posting needs, or some current internet buzzwords, internet slang, etc. During subsequent video viewing, if a certain keyword is detected in the video's dialogue or bullet comments, the bullet comment corresponding to that keyword will be automatically posted without the need for manual operation by the user, thus realizing the automatic posting of bullet comments.

[0047] In one possible implementation, users with different account levels can set different numbers of keywords. The terminal can display different states on the keyword setting interface based on whether the number of keywords already added by the user has reached the upper limit. For example, in response to the keyword setting operation, the terminal determines the allowed number of keywords threshold based on the account level of the currently logged-in target account. If the number of keywords corresponding to the target account is less than the threshold, the terminal displays the information adding area of ​​the keyword setting interface as allowed to add keywords. If the number of keywords corresponding to the target account is equal to the threshold, the terminal displays the information adding area of ​​the keyword setting interface as prohibited from adding keywords. In one possible implementation, the method for determining the above-mentioned number threshold can be expressed as the following formula (1): count=level*(level+1)(1) Where count represents the number threshold and level represents the account level. In one possible implementation, user accounts are divided into member accounts and regular accounts. For member accounts, the terminal determines the number threshold based on Formula 1 above, and for regular accounts, the terminal sets the number threshold to zero. Figure 6 This is a flowchart illustrating a method for setting a threshold number of keywords according to an embodiment of this application. (See attached flowchart.) Figure 6In response to displaying the playback interface, the terminal executes step 601 to obtain the currently logged-in target account. If the target account is a member account, the terminal executes step 602 to obtain the account level of the target account, and then executes step 603 to determine the number threshold based on the above formula (1). If the target account is a non-member account, the terminal executes step 604 to set the number threshold to zero. It should be noted that the above description of the method for determining the number threshold is merely an exemplary description of one possible implementation. In some embodiments, the number threshold can also be set by the developer, and this application embodiment does not limit this.

[0048] 303. In response to the information addition operation on the keyword setting interface, the terminal stores the keyword added on the keyword setting interface and the corresponding bullet comments.

[0049] In one possible implementation, the information addition operation can be implemented as any of the following: Method 1: This information addition operation is performed by inputting information in the information addition area of ​​the keyword addition interface. Figure 5 Taking the keyword setting interface shown as an example, in one possible implementation, the terminal detects the input operation in the information addition area, obtains the information entered in the keyword addition area of ​​the information addition area as the keyword, and obtains the information entered in the bullet screen addition area of ​​the information addition area as the bullet screen. Optionally, the terminal may also obtain the information entered in the keyword addition area and the bullet screen addition area after detecting the triggering operation of the confirmation addition control in the information addition area; this embodiment of the application does not limit this.

[0050] Implementation Method Two: The information addition operation involves selecting from candidate options displayed in the information addition area. These candidate options can be candidate keywords or candidate bullet comments. In one possible implementation, the terminal displays candidate keywords in the information addition area. In response to the selection of any candidate keyword, the terminal displays the corresponding candidate bullet comments. In response to the selection of any candidate bullet comment, the terminal acquires the selected candidate keyword and the selected candidate bullet comment, using them as the keyword and bullet comment added by the user in the information addition area. The candidate keyword can be determined based on the target video; for example, phrases appearing more than a first threshold in the target video can be used as candidate keywords. Optionally, the candidate keyword can be determined based on the video title of the target video; for example, keyword extraction can be performed on the video title of the target video beforehand to obtain the candidate keyword. Optionally, the candidate keyword can be determined based on trending information; for example, the terminal extracts keywords based on trending information to obtain the candidate keyword. The "hot topic information" refers to information whose search count in the target application or target webpage exceeds a second threshold. Optionally, the "hot topic information" is the video title of a video in the target application or target webpage whose playback count exceeds a third threshold. The first, second, and third thresholds are all set by the developers, and this application embodiment does not limit their implementation. It should be noted that the above description of the method for determining candidate keywords and candidate bullet comments is merely an illustrative example, and this application embodiment does not limit the method for determining candidate keywords and candidate bullet comments.

[0051] It should be noted that the above description of the information addition operation is only an exemplary description. The information addition operation can also be implemented in other ways. For example, the information addition operation includes the selection operation of candidate keywords displayed in the information display area and the bullet screen input operation. This application embodiment does not limit this.

[0052] In this embodiment, the terminal responds to the information addition operation by obtaining the keywords and bullet comments added in the information addition area of ​​the keyword setting interface, and stores the keywords and bullet comments accordingly. In one possible implementation, the keywords and bullet comments can be stored in the first configuration information corresponding to the target account.

[0053] In one possible implementation, before adding the keyword and the bullet comment, the terminal can detect whether the bullet comment corresponding to the keyword contains sensitive words. For example, in response to an information addition operation in the information addition area, the terminal identifies the bullet comment added in the information addition area. For instance, the terminal obtains a list of sensitive words and matches the bullet comment with each sensitive word included in the list. If no sensitive word is identified in the bullet comment, the terminal stores the keyword added in the information addition area and the bullet comment corresponding to that keyword; if a sensitive word is identified in the bullet comment, a first prompt message is displayed, which informs the user that the currently added bullet comment content contains sensitive words, and the user can re-add the bullet comment content. It should be noted that the above method for identifying sensitive words in bullet comment content is merely an exemplary description of one possible implementation, and this application does not limit the specific method used to identify sensitive words.

[0054] It should be noted that step 303 above is an optional step. In some embodiments, the storage step of the keyword and the corresponding bullet comments can be performed by the server. That is, the server associates the keyword and bullet comments added in the keyword setting interface with the target account and stores them in the cloud. When the terminal performs keyword matching based on the target video and bullet comments, it can obtain the keyword and bullet comments corresponding to the target account from the server.

[0055] 304. The terminal will display the added keyword in the information display area of ​​the keyword settings interface.

[0056] In this embodiment of the application, in response to the completion of adding any keyword and its corresponding bullet comments, the terminal displays the keyword in the information display area of ​​the keyword setting interface, or displays the added keyword and its corresponding bullet comments in the information display area.

[0057] In one possible implementation, users can modify added keywords and their corresponding comments by clicking on keywords displayed in the information display area. Figure 5 Taking the keyword setting interface shown as an example, in one possible implementation, the terminal responds to the trigger operation of any keyword in the information display area by displaying the keyword in the keyword addition area of ​​the information addition area, and displays the corresponding bullet comments in the bullet comment addition area of ​​the information addition area. The user can re-edit the content in the keyword addition area and the bullet comment addition area.

[0058] In some embodiments, users can also set a motion trajectory for the bullet comments, which refers to the movement path of the bullet comments on the playback interface when they are published. In one possible implementation, the keyword setting interface further includes a trajectory setting area. Optionally, the trajectory setting area displays at least one selection control corresponding to a motion trajectory, and the motion trajectory indicated by the selected selection control is determined as the motion trajectory corresponding to the bullet comment. Optionally, the trajectory setting area can provide a motion trajectory drawing function, allowing users to draw the motion trajectory corresponding to the bullet comments in the trajectory setting area. It should be noted that the above description of the method for determining the motion trajectory is only an exemplary description of one possible implementation, and the embodiments of this application do not limit the method for determining the motion trajectory of bullet comments. In some embodiments, the above motion trajectory setting operation is set for a specific bullet comment, that is, users can set different motion trajectories for each bullet comment; optionally, the above motion trajectory setting operation is set for all bullet comments, that is, each bullet comment corresponds to the same motion trajectory, and the embodiments of this application do not limit this.

[0059] Figure 7 This is a flowchart of a keyword and bullet screen addition method provided in an embodiment of this application. The following is combined with... Figure 7 This section explains the process of adding the aforementioned keywords and bullet comments. For example... Figure 7 As shown, in one possible implementation, the terminal displays a playback interface. In response to the keyword setting operation, it executes step 701, which involves setting up automatic bullet comment posting. In step 701, the terminal adds keywords and corresponding bullet comments based on user information, and displays the added keywords. The terminal then executes step 702, which involves setting motion trajectories for the bullet comments. The terminal can first determine whether the motion trajectory setting function is enabled. If the motion trajectory setting function is enabled, the terminal can select any preset motion trajectory provided in the target application, or customize and draw a motion trajectory.

[0060] In some embodiments, keywords and bullet comments can be set for a specific video. For example, if a first keyword and a first bullet comment corresponding to the first keyword are set for a target video, then the terminal can automatically publish subsequent bullet comments based on the first keyword and the first bullet comment only when playing the target video. For instance, if the target video is a TV series including multiple episodes, the terminal can trigger keyword recognition based on the first keyword when playing each episode; however, when playing other videos, it is not necessary to perform keyword recognition based on the first keyword in other videos. In some embodiments, keywords and bullet comments can be set for all videos provided in the target application. For example, if a second keyword and a second bullet comment corresponding to the second keyword are set for all videos, then when playing any video in the target application, keyword recognition can be performed based on the second keyword, and a second bullet comment can be automatically published. It should be noted that the embodiments of this application do not limit which videos are set with keywords and bullet comments.

[0061] The technical solution provided in this application allows users to customize keywords and corresponding bullet comments based on their own bullet comment posting needs or current internet buzzwords and slang. During subsequent video playback, if any keyword is included in the video dialogue or bullet comments posted by other users, the terminal will automatically post a bullet comment corresponding to that keyword. This achieves the function of automatically sending bullet comments without manual user operation, reducing the complexity of posting bullet comments during video viewing and improving the user's video viewing experience.

[0062] The above embodiments describe the process of setting keywords and corresponding bullet comments. In this example, during video playback, the terminal can automatically publish bullet comments based on the set keywords and corresponding bullet comments. Figure 8 This is a flowchart of a bullet screen publishing process provided in an embodiment of this application. See also: Figure 8 In one possible implementation, this embodiment includes the following steps: 801. The terminal plays the target video and displays the corresponding bullet comments on the playback interface.

[0063] In one possible implementation, the terminal, in response to a playback command for a target video, acquires the target video and its corresponding bullet comments. The terminal then displays a playback interface and plays the target video on this interface. Based on the playback progress of the target video, bullet comments corresponding to the current playback progress are displayed on the playback interface. The bullet comments displayed on the playback interface are those posted by at least one user while watching the target video. Of course, in some embodiments, the terminal may not display the bullet comments corresponding to the target video while playing it. It should be noted that the embodiments of this application do not limit the display method of the target video and bullet comments.

[0064] 802. The terminal obtains the bullet screen posting permission of the currently logged-in target account.

[0065] In one possible implementation, different users correspond to different bullet screen posting permissions. For example, ordinary users can manually input bullet screen content to post bullet screens, while member users have the permission to automatically post bullet screens. That is, member users can achieve the automatic bullet screen posting function by pre-setting keywords and corresponding bullet screens. In this embodiment, the terminal responds to the playback command of the target video and obtains the current user login status. If the user is currently not logged in, the automatic bullet screen posting function is not enabled, and the terminal does not need to execute steps 803 to 805 below. If the user is currently logged in, the terminal obtains the account level of the currently logged-in target account. If the account level meets the reference condition, the terminal determines that the currently logged-in target account has the permission to automatically post bullet screens, and the terminal continues to execute step 803 below. If the account level does not meet the reference condition, the terminal determines that the currently logged-in target account does not have the permission to automatically post bullet screens, and the terminal does not need to execute steps 803 to 805 below. The reference condition is set by the developer, and this embodiment does not limit it. For example, the reference condition is set to the account level being greater than or equal to the level 1 member level. It should be noted that the terminal can also determine the target account's permission to post bullet comments based on other methods, and this application embodiment does not limit this.

[0066] 803. The terminal responds to the fact that the target account has the permission to automatically post bullet comments and obtains at least one keyword corresponding to the target account.

[0067] In one possible implementation, the terminal, in response to the target account's account level satisfying the reference condition (i.e., the target account having the permission to automatically post bullet comments), obtains at least one keyword corresponding to the target account. In another possible implementation, the at least one keyword is stored in the form of configuration information. Then, in response to the target account's account level satisfying the reference condition, the terminal obtains first configuration information corresponding to the target account. This first configuration information is used to store at least one keyword corresponding to the target account and the bullet comments corresponding to each keyword.

[0068] It should be noted that the above steps for determining the target account's permission to post bullet comments are optional. In some embodiments, any account has the permission to automatically post bullet comments, and the terminal can directly execute the step of obtaining at least one keyword corresponding to the target account.

[0069] In one possible implementation, the terminal displays a target prompt message on the playback interface when the target account is not associated with any keyword, that is, when the first configuration information does not include keywords. This target prompt message prompts the user to add keywords and corresponding bullet comments. Optionally, the terminal displays the target prompt message when the number of keywords corresponding to the target account is less than a threshold number. This threshold number is set by the developer, and this embodiment does not limit its implementation. In another possible implementation, the terminal displays a keyword setting interface in response to the triggering operation of the target prompt message, allowing the user to quickly set keywords and corresponding bullet comments.

[0070] 804. During the playback of the target video, the terminal performs keyword recognition on the target video and at least one item in the bullet comments based on the at least one keyword.

[0071] In one possible implementation, the process of the terminal performing keyword recognition on the target video and at least one of the bullet comments includes at least one of the following video methods.

[0072] Method 1: The terminal performs keyword recognition on the video frame of the target video.

[0073] In some embodiments, the video subtitles are directly added to the video frame, meaning the video subtitles and video frame are merged into a single data stream. In one possible implementation, the terminal performs keyword recognition on the subtitles displayed in the video frame to determine whether a certain keyword is mentioned in the video. For example, the terminal performs character recognition on a target area of ​​the video frame to obtain first text information displayed in that target area, and matches this first text information with the at least one keyword. In response to a successful match between the first text information and any keyword, it is determined that the target video includes the keyword. Here, the target area is the subtitle display area in the video frame; for example, the target area is the lower area of ​​the video frame. This embodiment does not limit the location of the target area. The terminal performs character recognition on the image in the target area, and the recognized first text information is the subtitle of the target video. In one possible implementation, a character recognition model is deployed on the terminal. The aforementioned process of character recognition of the video frame can be performed by this character recognition model, which may be a convolutional neural network model, etc. For example, when the character recognition model performs character recognition, it may include the following steps: First, the terminal preprocesses the captured video frame of the target area, for example, by performing grayscale conversion, noise reduction, and binarized character segmentation on the captured video frame to reduce useless information in the video frame. The preprocessed video frame is a binarized image. Then, the computer device performs feature extraction based on the binarized image to obtain the character features of the characters included in the video frame, and classifies them based on the character features. Finally, based on the character classification results, the characters included in the video frame are obtained, that is, the first text information is obtained. It should be noted that the above description of the character recognition method is only an exemplary description of one possible implementation. The method by which the terminal performs character recognition on the video frame in this application embodiment is not limited.

[0074] In some embodiments, the terminal can identify video frames of the target video to determine whether the content displayed in the video frames matches a certain keyword. For example, the terminal captures video frames of the target video based on a reference frequency, performs image recognition on the captured video frames to obtain the object names of items included in the video frames, and matches the identified object names with at least one keyword. In response to a successful match between the object name and any keyword, it is determined that the target video includes the keyword. For example, if the keyword includes "excavator," and the terminal identifies an excavator in the video frame, it is determined that the target video includes the keyword. In one possible implementation, the terminal is equipped with an image recognition model, and the above-mentioned step of identifying object frames in the video frames can be performed by the image recognition model. For example, the image recognition model is a VGG (Visual Geometry Group) model, a Residual Network model, etc. It should be noted that the embodiments of this application do not limit the method of image recognition model performing image recognition on video frames.

[0075] Implementation Method Two: The terminal performs keyword recognition on the subtitle data carried by the target video. In one possible implementation, the video subtitles can be treated as a separate data stream. When the terminal acquires the target video, it can obtain the subtitle data corresponding to the target video. In this embodiment, the terminal can obtain a segment of subtitle text corresponding to the current playback progress of the target video, match the subtitle text with at least one keyword, and determine the target video package keywords in response to the successful match between the subtitle text and any keyword.

[0076] Implementation Method 3: The terminal performs keyword recognition on the audio data of the target video. In one possible implementation, the terminal, based on the playback progress of the target video, obtains a segment of target audio data corresponding to the current playback progress, performs speech recognition on the segment of target audio data to obtain second text information corresponding to the target audio data, and matches the second text information with at least one keyword. In response to the second text information successfully matching any keyword, it is determined that the target video includes keywords. In another possible implementation, the terminal is equipped with a speech recognition model, and the above-mentioned steps of performing speech recognition on the audio data can be performed by the speech recognition model, which can be a recurrent neural network model, etc. For example, when the speech recognition model performs speech recognition, it may include the following steps: First, the terminal preprocesses and extracts audio features from the target audio data; then, based on the feature extraction results, it obtains the phoneme information included in the target audio data, and determines the characters or words corresponding to the phoneme information based on a dictionary; finally, based on the obtained characters and words, it analyzes the semantics of the entire sentence, adjusts the text structure, and obtains the speech recognition result, that is, obtains the above-mentioned second text information. It should be noted that the method of speech recognition using the speech recognition model is not limited in the embodiments of this application.

[0077] Implementation Method 4: The terminal performs keyword recognition on the bullet screen. In one possible implementation, the terminal obtains at least one bullet screen corresponding to the current playback progress of the target video, and matches each bullet screen with the at least one keyword. In response to any bullet screen successfully matching any keyword, it is determined that the bullet screen includes the keyword.

[0078] It should be noted that the above description of keyword recognition methods is only an exemplary description of several possible implementation methods. In some embodiments, the above recognition methods can be combined arbitrarily. For example, the terminal performs keyword recognition based on the subtitle data carried by the target video and the bullet comments of the target video, or the terminal performs keyword recognition based on the audio data of the target video and the bullet comments of the target video. This application embodiment does not limit this.

[0079] In one possible implementation, the terminal can determine which of the above-mentioned implementation methods to use for keyword matching based on the keyword matching method, wherein the keyword matching method may include video matching and bullet screen matching. In another possible implementation, the terminal obtains the keyword matching method corresponding to the currently logged-in target account. If the keyword matching method is video matching, the terminal performs keyword recognition on at least one of the audio data, video frame, and subtitle data corresponding to the target video based on at least one keyword; that is, at least one of the above-mentioned implementation methods one, two, and three is used. If the keyword matching method is bullet screen matching, the terminal performs keyword recognition on the bullet screen based on at least one keyword; that is, keyword recognition is performed using the above-mentioned implementation method four. Optionally, the keyword matching method can be stored in the form of configuration information. For example, the keyword matching method can be stored in the first configuration information, that is, stored together with the keywords and bullet screens set by the user, or it can be stored in the second configuration information. This application embodiment does not limit this. The keyword matching method described above can be set by the user. For example, the keyword setting interface also includes a method selection control. One method selection control corresponds to one keyword matching method. The user can use the matching method selection control to determine which keyword matching method to use.

[0080] It should be noted that steps 802 to 804 above are steps of identifying keywords in the target video and the bullet comments based on at least one keyword, in response to the account level meeting the reference conditions. In this embodiment, multiple methods can be applied to identify keywords in the target video and bullet comments, ensuring the efficiency and accuracy of keyword identification.

[0081] 805. When the target video or the bullet screen contains the target keyword, the terminal automatically sends the target bullet screen corresponding to the target account and displays the target bullet screen on the playback interface.

[0082] The target bullet comment is the bullet comment corresponding to the target keyword. In one possible implementation, if the target keyword corresponds to at least two bullet comments, the terminal responds to the target video or the bullet comments including the target keyword by displaying at least two bullet comments corresponding to the target keyword on the playback interface, and determining the selected bullet comment among the at least two bullet comments as the target bullet comment.

[0083] In one possible implementation, the terminal responds to the target video or the bullet screen containing the target keyword by controlling the target bullet screen to move along a custom trajectory on the playback interface. Figure 9This is a schematic diagram of a bullet screen display effect provided in an embodiment of this application. The target bullet screen 901 moves according to a custom trajectory 902. The movement mode of the target bullet screen 901 can be as follows: Figure 9 As shown in Figure (a) or as in Figure 9 As shown in Figure (b) above. In one possible implementation, the custom trajectory described above can be determined based on any of the following methods.

[0084] Method 1: The custom trajectory is drawn by the user. That is, the terminal responds to the trajectory drawing operation and determines the custom trajectory based on the trajectory drawn by the operation. The following three examples illustrate the above implementation method: Example 1: In response to the trajectory drawing operation being a continuous swipe operation, the terminal determines the operation trajectory corresponding to the continuous swipe operation as the custom trajectory. Here, a continuous swipe operation refers to an uninterrupted swipe operation. For example, if the terminal displays a bullet screen trajectory drawing interface, and the user performs a continuous swipe operation on this interface, the terminal can directly determine the operation trajectory corresponding to the continuous swipe operation as the custom trajectory, and the terminal can subsequently control the target bullet screen to move along this custom trajectory.

[0085] Example 2: In response to the trajectory drawing operation being an interval sliding operation, the terminal connects multiple operation trajectories corresponding to the interval sliding operation to obtain the custom trajectory. The interval sliding operation includes multiple consecutive sliding operations. For example, the terminal displays a bullet screen trajectory drawing interface. The process of the user performing an interval sliding operation on the bullet screen trajectory drawing interface is also the process of the user performing multiple consecutive sliding operations on the bullet screen trajectory drawing interface. Through this implementation method, the user can divide the drawing of the custom trajectory into multiple parts, allowing for more precise drawing of the custom trajectory. For instance, when the user performs an interval sliding operation on the bullet screen trajectory drawing interface, the terminal determines the position points traversed by each consecutive sliding operation in the interval sliding operation, and connects the position points traversed by each consecutive sliding operation using line segments to obtain a line segment corresponding to each consecutive sliding operation. The line segment can be a straight line or a curve. The terminal connects multiple line segments to obtain the custom trajectory.

[0086] Example 3: In response to the trajectory drawing operation being an interval swipe operation, the terminal determines the multiple operation trajectories corresponding to the interval swipe operation as a custom trajectory. That is, when the swipe operation is an interval swipe operation, the terminal can also directly determine the multiple operation trajectories corresponding to the interval swipe operation as a custom trajectory. Since the multiple operation trajectories are discrete operation trajectories, when the terminal subsequently controls the target bullet screen to move using this custom trajectory, the custom trajectory can move according to the multiple operation trajectories respectively, thus presenting an effect of the target bullet screen "jumping" on the screen.

[0087] It should be noted that the operations on the bullet screen trajectory drawing interface in the above embodiments can be based on user operations on the terminal screen, such as sliding or clicking on the screen. Alternatively, the operations can be based on external input devices of the terminal, such as mice, touchpads, gamepads, and remote controls. Taking a mouse as an example, the user can perform a target operation on the mouse, such as a sliding or clicking operation. The sliding or clicking operation and its corresponding displayed custom trajectory refer to the relevant operations involved in the above embodiments, and will not be repeated here. For example, the target operation is to control the mouse movement, which triggers the mouse to send its position to the terminal. The terminal displays a custom trajectory based on the change in the mouse position. The change in the mouse position maps to the change in the cursor position on the terminal screen. Controlling the movement of the mouse causes the cursor on the terminal to move accordingly, thereby displaying the movement trajectory indicated by the movement, and realizing the drawing of the bullet screen trajectory. In addition, the target operation mentioned above is a sliding or clicking operation. The sliding or clicking operation and its corresponding displayed movement trajectory refer to the relevant operations involved in the above embodiments, and will not be repeated here.

[0088] Method 2: The custom trajectory is selected by the user. That is, in response to the selection operation of the candidate motion trajectory, the terminal determines the selected candidate motion trajectory as the custom motion trajectory. In one possible implementation, the terminal displays a trajectory setting interface with candidate motion trajectories. The terminal detects the user's selection operation on the trajectory setting interface and determines the selected candidate motion trajectory as the custom trajectory. The candidate motion trajectory may be provided by the target application or target webpage, or it may be set by the user; this application embodiment does not limit this.

[0089] Method 3: The preset motion trajectory is determined as the custom motion trajectory. In one possible implementation, the target application or webpage can provide a preset motion trajectory, which can also be user-defined. In response to the user not drawing or selecting a custom trajectory, the preset motion trajectory is determined as the custom trajectory.

[0090] In the embodiments of this application, the aforementioned custom trajectory can be any curve or any straight line, and this application does not limit this. It should be noted that the above description of the method for determining the custom trajectory is merely an exemplary description of one possible implementation, and this application does not limit which specific method is used to determine the custom trajectory.

[0091] In some embodiments, the frequency of automatically published bullet comments can also be limited. In one possible implementation, when the terminal detects a keyword in the target video or bullet comments, it pauses keyword detection for the target video and bullet comments from the current moment, and resumes keyword detection after a first target duration. Optionally, when the terminal detects a third keyword in the target video or bullet comments, it obtains the first detection moment of the third keyword. If the third keyword is detected again at a second detection moment, it obtains the interval between the second detection moment and the first detection moment. If the interval is less than or equal to the second target duration, the automatic bullet comment publishing step is not triggered. If the interval is greater than the second target duration, the bullet comment corresponding to the third keyword is automatically published. The first and second target durations are set by the developers, and this application embodiment does not limit this. In this application embodiment, when a keyword is frequently mentioned in the dialogue or bullet comments of the target video, limiting the frequency of automatically published bullet comments can avoid frequent and repetitive bullet comment publishing, prevent the accumulation of a large number of duplicate bullet comments, and avoid affecting the user's video viewing experience.

[0092] The technical solution provided in this application embodiment identifies keywords in the video and bullet comments played on the playback interface. When a target keyword is identified, the bullet comment publishing step is automatically triggered. The terminal automatically publishes a bullet comment corresponding to the target keyword on the playback interface without requiring the user to manually edit the bullet comment content. This effectively simplifies the user's operation steps when publishing bullet comments, reduces the time spent publishing bullet comments, improves the human-computer interaction efficiency of the bullet comment publishing process, and avoids the bullet comment publishing process affecting the user's video viewing process.

[0093] Figure 10 This is a flowchart of a bullet screen publishing method provided in an embodiment of this application, which is described below in conjunction with... Figure 10 The process of posting the aforementioned bullet comments will be explained. See [link / reference]. Figure 10In one possible implementation, in response to the start of playback of the target video, the terminal first executes step 1001 to check if the user is logged in. If the current user is not logged in, step 1002 is executed, and the automatic posting of bullet comments is not triggered. If the current user is logged in, step 1003 is executed. In step 1003, the terminal determines whether the user's account login meets the reference conditions. If not, step 1002 is executed; if yes, step 1004 is executed. In step 1004, the terminal determines whether keywords are detected based on the target video and bullet comments. If not, step 1002 is executed; if yes, step 1005 is executed. In step 1005, the terminal determines the motion trajectory corresponding to the bullet comments and then executes step 1006 to display the bullet comments based on the motion trajectory. That is, the bullet comments posted this time are displayed on the playback interface and move according to the motion trajectory. The technical solution provided by the embodiments of this application can, on the one hand, reduce the operational complexity of users when posting bullet comments and avoid users repeatedly entering the same bullet comment content. On the other hand, it can also enrich the bullet comments of the video and promote communication and interaction between users.

[0094] All of the above-mentioned optional technical solutions can be combined in any way to form the optional embodiments of this application, and will not be described in detail here.

[0095] Figure 11 This is a schematic diagram of the structure of a bullet screen publishing device provided in an embodiment of this application. See also... Figure 11 The device includes: The video playback module 1101 is used to play the target video on the playback interface; The keyword recognition module 1102 is used to perform keyword recognition on at least one of the target video and the corresponding bullet comments during the playback of the target video. The bullet screen display module 1103 is used to automatically send target bullet screens from the target account in response to the target video or the bullet screen containing target keywords, and to display the target bullet screens on the playback interface. The target bullet screens correspond to the target keywords.

[0096] In one possible implementation, the bullet screen display module 1103 is used for: The playback interface displays the target bullet screen moving along a custom trajectory.

[0097] In one possible implementation, the custom trajectory is determined based on any of the following methods: In response to a trajectory drawing operation, the custom trajectory is determined based on the trajectory drawn by the trajectory drawing operation; In response to the selection operation of the candidate motion trajectory, the selected candidate motion trajectory is determined as the custom trajectory; The preset motion trajectory is set as the custom motion trajectory.

[0098] In one possible implementation, the target keyword corresponds to at least two bullet comments; The device also includes a determining module for: The playback interface displays at least two bullet comments corresponding to the target keyword; The selected bullet comment from at least two bullet comments is identified as the target bullet comment.

[0099] In one possible implementation, the keyword recognition module 1102 includes: The `get` submodule is used to retrieve the account level of the currently logged-in target account; The identification submodule is used to identify keywords in at least one of the target video and the corresponding bullet comments during the playback of the target video in response to the account level meeting the reference conditions.

[0100] In one possible implementation, the identification submodule is used for: In response to the account level meeting the reference condition, at least one keyword corresponding to the target account is obtained, and each keyword corresponds to at least one bullet comment; During the playback of the target video, based on at least one keyword, keyword recognition is performed on at least one item in the target video and the corresponding bullet comments.

[0101] In one possible implementation, the keyword recognition module 1102 includes at least one of the following: The first submodule is used to perform keyword recognition on the video frames of the target video. The second submodule is used to perform keyword recognition on the subtitle data carried by the target video; The third submodule is used to perform keyword recognition on the audio data of the target video; The fourth submodule is used to identify keywords in the bullet screen.

[0102] In one possible implementation, the first submodule is used for: Character recognition is performed on the target area of ​​the video frame to obtain the first text information displayed in the target area; Match the first text information with at least one keyword; In response to the first text information successfully matching any keyword, it is determined that the target video includes the target keyword.

[0103] In one possible implementation, the keyword recognition module 1102 is used for: Retrieve the keyword matching method corresponding to the currently logged-in target account; In response to the fact that the keyword matching method is video matching, keyword recognition is performed on at least one of the audio data, video frame and subtitle data of the target video; In response to the keyword matching method being bullet screen matching, keyword recognition is performed on the bullet screen.

[0104] In one possible implementation, the device further includes: The interface display module is used to display the keyword setting interface in response to the keyword setting operation. The keyword setting interface includes an information display area and an information addition area. The storage module is used to store the keywords added in the information addition area and the corresponding bullet comments in response to the information addition operation in the information addition area; This interface display module is used to display the added keyword in the information display area, or to display the added keyword and the corresponding bullet comments in the information display area.

[0105] In one possible implementation, the interface display module is used for: Based on the target account's account level, determine the threshold for the number of keywords that can be added; If the number of keywords corresponding to the target account is less than the threshold, the information addition area in the keyword settings interface will be displayed as allowed to be added. When the number of keywords corresponding to the target account equals the threshold, the information addition area in the keyword settings interface is displayed as prohibited from being added.

[0106] In one possible implementation, the information addition operation includes any of the following: Input operations in this information addition area; The option to select from the candidates displayed in the information addition area is either a candidate keyword or a candidate bullet comment.

[0107] In one possible implementation, the storage module is used for: In response to the information addition operation in the information addition area, the bullet comments added in the information addition area are identified; If no sensitive words are detected in the bullet comment, the keywords added in the information addition area and the bullet comments corresponding to those keywords will be stored.

[0108] In one possible implementation, the device further includes: The information display module is used to display target prompt information in response to the number of keywords corresponding to the target account being less than a threshold. This prompt information prompts the user to add keywords and corresponding bullet comments. The device provided in this application embodiment identifies keywords in the video and bullet comments played on the playback interface. When a target keyword is identified, the bullet comment publishing step is automatically triggered. The terminal automatically publishes a bullet comment corresponding to the target keyword on the playback interface, eliminating the need for the user to manually edit the bullet comment content. This effectively simplifies the user's operation steps when publishing bullet comments, reduces the time spent publishing bullet comments, improves the human-computer interaction efficiency of the bullet comment publishing process, and avoids the bullet comment publishing affecting the user's video viewing process.

[0109] It should be noted that the above-described bullet screen publishing device is only illustrated by the division of the functional modules described above. In practical applications, the functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the bullet screen publishing device and the bullet screen publishing method embodiments described above belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0110] This application provides a computer device for executing the above-described bullet screen publishing method. The computer device can be implemented as a terminal or a server. Figure 12 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application.

[0111] Typically, terminal 1200 includes one or more processors 1201 and one or more memories 1202.

[0112] Processor 1201 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1201 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1201 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1201 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1201 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0113] The memory 1202 may include one or more computer-readable storage media, which may be non-transitory. The memory 1202 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1202 is used to store at least one computer program, which is executed by the processor 1201 to implement the bullet screen publishing method provided in the method embodiments of this application.

[0114] In some embodiments, the terminal 1200 may also optionally include a peripheral device interface 1203 and at least one peripheral device. The processor 1201, memory 1202, and peripheral device interface 1203 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1203 via a bus, signal line, or circuit board. Specifically, the peripheral device includes at least one of the following: radio frequency circuitry 1204, display screen 1205, camera assembly 1206, audio circuitry 1207, and power supply 1209.

[0115] Peripheral device interface 1203 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1201 and memory 1202. In some embodiments, processor 1201, memory 1202 and peripheral device interface 1203 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1201, memory 1202 and peripheral device interface 1203 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0116] The radio frequency (RF) circuit 1204 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1204 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1204 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1204 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1204 can communicate with other terminals via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: metropolitan area networks (MANs), various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks (WLANs), and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1204 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0117] Display screen 1205 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1205 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1201 for processing. In this case, display screen 1205 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1205, which serves as the front panel of terminal 1200; in other embodiments, there may be at least two display screens, respectively disposed on different surfaces of terminal 1200 or in a folded design; in some embodiments, display screen 1205 may be a flexible display screen, disposed on a curved or folded surface of terminal 1200. Furthermore, display screen 1205 may be configured as a non-rectangular irregular shape, i.e., a non-rectangular screen. Display screen 1205 may be made of materials such as LCD (Liquid Crystal Display) or OLED (Organic Light-Emitting Diode).

[0118] The camera assembly 1206 is used to acquire images or videos. Optionally, the camera assembly 1206 includes a front-facing camera and a rear-facing camera. Typically, the front-facing camera is located on the front panel of the terminal, and the rear-facing camera is located on the back of the terminal. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1206 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm-light flash and a cool-light flash, which can be used for light compensation at different color temperatures.

[0119] The audio circuit 1207 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1201 for processing, or input to the radio frequency circuit 1204 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each positioned at a different location on the terminal 1200. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1201 or the radio frequency circuit 1204 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1207 may also include a headphone jack.

[0120] Power supply 1209 is used to power the various components in terminal 1200. Power supply 1209 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1209 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0121] In some embodiments, the terminal 1200 further includes one or more sensors 1210. The one or more sensors 1210 include, but are not limited to: an acceleration sensor 1211, a gyroscope sensor 1212, a pressure sensor 1213, an optical sensor 1215, and a proximity sensor 1216.

[0122] Accelerometer 1211 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established with terminal 1200. For example, accelerometer 1211 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1201 can control display screen 1205 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1211. Accelerometer 1211 can also be used for games or for acquiring user motion data.

[0123] The gyroscope sensor 1212 can detect the orientation and rotation angle of the terminal 1200. The gyroscope sensor 1212 can work in conjunction with the accelerometer sensor 1211 to collect the user's 3D movements on the terminal 1200. Based on the data collected by the gyroscope sensor 1212, the processor 1201 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0124] The pressure sensor 1213 can be disposed on the side bezel of the terminal 1200 and / or on the lower layer of the display screen 1205. When the pressure sensor 1213 is disposed on the side bezel of the terminal 1200, it can detect the user's grip signal on the terminal 1200, and the processor 1201 can perform left / right hand recognition or quick operation based on the grip signal collected by the pressure sensor 1213. When the pressure sensor 1213 is disposed on the lower layer of the display screen 1205, the processor 1201 can control the operable controls on the UI interface based on the user's pressure operation on the display screen 1205. The operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0125] The optical sensor 1215 is used to collect ambient light intensity. In one embodiment, the processor 1201 can control the display brightness of the display screen 1205 based on the ambient light intensity collected by the optical sensor 1215. Specifically, when the ambient light intensity is high, the display brightness of the display screen 1205 is increased; when the ambient light intensity is low, the display brightness of the display screen 1205 is decreased. In another embodiment, the processor 1201 can also dynamically adjust the shooting parameters of the camera assembly 1206 based on the ambient light intensity collected by the optical sensor 1215.

[0126] The proximity sensor 1216, also known as a distance sensor, is typically mounted on the front panel of the terminal 1200. The proximity sensor 1216 is used to detect the distance between the user and the front of the terminal 1200. In one embodiment, when the proximity sensor 1216 detects that the distance between the user and the front of the terminal 1200 is gradually decreasing, the processor 1201 controls the display screen 1205 to switch from a screen-on state to a screen-off state; when the proximity sensor 1216 detects that the distance between the user and the front of the terminal 1200 is gradually increasing, the processor 1201 controls the display screen 1205 to switch from a screen-off state to a screen-on state.

[0127] Those skilled in the art will understand that Figure 12 The structure shown does not constitute a limitation on terminal 1200 and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0128] The aforementioned computer equipment can also be implemented as a server. Figure 13This is a schematic diagram of a server structure provided in an embodiment of this application. The server 1300 can vary considerably due to different configurations or performance. It may include one or more Central Processing Units (CPUs) 1301 and one or more memories 1302. The one or more memories 1302 store at least one computer program, which is loaded and executed by the one or more processors 1301 to implement the methods provided in the various method embodiments described above. Of course, the server 1300 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The server 1300 may also include other components for implementing device functions, which will not be elaborated here.

[0129] In an exemplary embodiment, a computer-readable storage medium is also provided, such as a memory including at least one computer program, which can be executed by a processor to complete the bullet screen publishing method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0130] In an exemplary embodiment, a computer program product is also provided, comprising at least one computer program stored in a computer-readable storage medium. A processor of a computer device reads the at least one computer program from the computer-readable storage medium and executes the at least one computer program, causing the computer device to perform the operations performed by the above-described bullet screen publishing method.

[0131] In some embodiments, the computer program involved in the present application embodiments may be deployed and executed on a computer device, or executed on multiple computer devices located in one location, or executed on multiple computer devices distributed in multiple locations and interconnected through a communication network. Multiple computer devices distributed in multiple locations and interconnected through a communication network may constitute a blockchain system.

[0132] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0133] The above are merely optional embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for publishing bullet comments, characterized in that, The method includes: Play the target video on the playback interface; Retrieve the pre-set keyword matching method for the currently logged-in target account; In response to the keyword matching method being video matching, during the playback of the target video, keyword recognition is performed on at least one of the audio data and subtitle information corresponding to the current playback progress of the target video; when the subtitles and video frames of the target video are merged into one data stream, the subtitle information is the subtitle displayed in the video frame; when the subtitles of the target video are an independent data stream, the subtitle information is the subtitle text in the subtitle data carried by the target video. In response to the keyword matching method being bullet screen matching, during the playback of the target video, keyword recognition is performed on the bullet screens of the target video that correspond to the current playback progress; In response to the target video or the bullet comments hitting a target keyword in at least one keyword pre-edited by the target account, the target bullet comments pre-edited by the target account and corresponding to the target keyword are automatically sent. The target bullet comments are displayed on the playback interface and move according to a custom trajectory pre-set by the target account. Each bullet comment corresponding to a keyword is pre-edited by the target account on the keyword settings interface for that keyword. The custom trajectories of each bullet comment corresponding to the at least one keyword are different. Different user accounts can set different numbers of keywords. During the editing of keywords and bullet comments on the keyword settings interface, the display state of the keyword settings interface varies depending on whether the number of added keywords has reached the upper limit. In response to the identification of a keyword from the at least one keyword in the target video or the bullet comments, keyword identification of the target video and the bullet comments is paused from the current moment, and keyword identification is restarted after a first target duration. In response to the identification of a third keyword in the target video or the bullet comments, the first identification time of the third keyword is obtained; if the third keyword is identified again at a second identification time, the interval between the second identification time and the first identification time is obtained; if the interval is less than or equal to the second target duration, the automatic bullet comment posting step is not triggered; if the interval is greater than the second target duration, the bullet comment corresponding to the third keyword is automatically posted.

2. The method according to claim 1, characterized in that, The target keyword corresponds to at least two bullet comments; Before automatically sending the target bullet comments pre-edited by the target account and corresponding to the target keywords, the method further includes: At least two bullet comments corresponding to the target keyword are displayed on the playback interface; The selected bullet screen from the at least two bullet screens is identified as the target bullet screen.

3. The method according to claim 1, characterized in that, The process of keyword recognition also includes: Get the account level of the currently logged-in target account; In response to the account level meeting the reference conditions, during the playback of the target video, at least one of the target video and the corresponding bullet comments is identified as keywords.

4. The method according to claim 3, characterized in that, In response to the account level meeting the reference conditions, during the playback of the target video, keyword recognition is performed on at least one of the target video and the corresponding bullet comments, including: In response to the account level meeting the reference condition, at least one keyword corresponding to the target account is obtained, and each keyword corresponds to at least one bullet comment; During the playback of the target video, keyword recognition is performed on at least one of the target video and the corresponding bullet comments based on the at least one keyword.

5. The method according to claim 1, characterized in that, Keyword recognition is performed on the subtitle information of the target video corresponding to the current playback progress, including: Character recognition is performed on the target area of ​​the video frame to obtain the first text information displayed in the target area; Match the first text information with at least one keyword; In response to the first text information successfully matching any keyword, it is determined that the target video includes the target keyword.

6. The method according to claim 1, characterized in that, Before automatically sending a target bullet comment corresponding to the target keyword pre-edited by the target account in response to the target video or the bullet comment hitting at least one target keyword pre-edited by the target account, the method further includes: In response to the keyword setting operation, the keyword setting interface is displayed, which includes an information display area and an information addition area; In response to the information addition operation in the information addition area, the keywords added in the information addition area and the corresponding bullet comments are stored; The added keywords will be displayed in the information display area, or the added keywords and their corresponding bullet comments will be displayed in the information display area.

7. The method according to claim 6, characterized in that, The response to the keyword setting operation, displaying the keyword setting interface, includes: Based on the account level of the target account, determine the threshold for the number of keywords that can be added; If the number of keywords corresponding to the target account is less than the threshold number, the information addition area of ​​the keyword setting interface will be displayed as allowed to add keywords. In response to the number of keywords corresponding to the target account being equal to the number threshold, the information addition area of ​​the keyword setting interface is displayed as a prohibited addition state.

8. The method according to claim 6, characterized in that, The information addition operation includes any of the following: Input operations in the information addition area; The selection operation of the candidate options displayed in the information addition area, wherein the candidate options are candidate keywords or candidate bullet comments.

9. The method according to claim 6, characterized in that, The method of responding to the information addition operation in the information addition area by storing the keywords added in the information addition area and the corresponding bullet comments includes: In response to the information addition operation in the information addition area, the bullet comments added in the information addition area are identified; In response to the absence of any sensitive words in the bullet comments, the keywords added in the information addition area and the bullet comments corresponding to the keywords are stored.

10. The method according to claim 6, characterized in that, Before displaying the keyword setting interface in response to the keyword setting operation, the method further includes: In response to the number of keywords corresponding to the target account being less than a threshold, a target prompt message is displayed, which prompts the user to add keywords and corresponding bullet comments.

11. A bullet screen publishing device, characterized in that, The device includes: The video playback module is used to play the target video on the playback interface; A keyword recognition module is used to obtain a pre-set keyword matching method for the currently logged-in target account; in response to the keyword matching method being video matching, during the playback of the target video, keyword recognition is performed on at least one of the audio data and subtitle information corresponding to the current playback progress of the target video; when the subtitles and video frames of the target video are merged into one data stream, the subtitle information is the subtitle displayed in the video frame; when the subtitles of the target video are an independent data stream, the subtitle information is the subtitle text in the subtitle data carried by the target video; in response to the keyword matching method being bullet screen matching, during the playback of the target video, keyword recognition is performed on the bullet screens corresponding to the current playback progress of the target video; The bullet screen display module is used to automatically send target bullet screens pre-edited by the target account corresponding to the target keyword in response to the target video or the bullet screen hitting at least one target keyword pre-edited by the target account. The target bullet screens are displayed on the playback interface and move according to a custom trajectory pre-set by the target account. Each bullet screen corresponding to a keyword is pre-edited by the target account on the keyword settings interface. The custom trajectories of the bullet screens corresponding to the at least one keyword are different. Different user accounts can set different numbers of keywords. During the editing of keywords and bullet screens on the keyword settings interface, the display state of the keyword settings interface varies depending on whether the maximum number of added keywords has been reached. The device also includes a module for performing the following steps: In response to the identification of a keyword from the at least one keyword in the target video or the bullet comments, keyword identification of the target video and the bullet comments is paused from the current moment, and keyword identification is restarted after a first target duration. In response to the identification of a third keyword in the target video or the bullet comments, the first identification time of the third keyword is obtained; if the third keyword is identified again at a second identification time, the interval between the second identification time and the first identification time is obtained; if the interval is less than or equal to the second target duration, the automatic bullet comment posting step is not triggered; if the interval is greater than the second target duration, the bullet comment corresponding to the third keyword is automatically posted.

12. The apparatus according to claim 11, characterized in that, The target keyword corresponds to at least two bullet comments; the device further includes a determining module, used for: At least two bullet comments corresponding to the target keyword are displayed on the playback interface; The selected bullet screen from the at least two bullet screens is identified as the target bullet screen.

13. The apparatus according to claim 11, characterized in that, The keyword recognition module includes: The `get` submodule is used to retrieve the account level of the currently logged-in target account; The identification submodule is used to identify keywords in at least one of the target video and the corresponding bullet comments during the playback of the target video in response to the account level meeting the reference conditions.

14. The apparatus according to claim 13, characterized in that, The identification submodule is used for: In response to the account level meeting the reference condition, at least one keyword corresponding to the target account is obtained, and each keyword corresponds to at least one bullet comment; During the playback of the target video, keyword recognition is performed on at least one of the target video and the corresponding bullet comments based on the at least one keyword.

15. The apparatus according to claim 11, characterized in that, The keyword recognition module is used for: Character recognition is performed on the target area of ​​the video frame to obtain the first text information displayed in the target area; Match the first text information with at least one keyword; In response to the first text information successfully matching any keyword, it is determined that the target video includes the target keyword.

16. The apparatus according to claim 11, characterized in that, The device further includes: The interface display module is used to display the keyword setting interface in response to the keyword setting operation. The keyword setting interface includes an information display area and an information addition area. The storage module is used to store the keywords added in the information addition area and the corresponding bullet comments in response to the information addition operation in the information addition area; The interface display module is used to display the added keywords in the information display area, or to display the added keywords and corresponding bullet comments in the information display area.

17. The apparatus according to claim 16, characterized in that, The interface display module is used for: Based on the account level of the target account, determine the threshold for the number of keywords that can be added; If the number of keywords corresponding to the target account is less than the threshold number, the information addition area of ​​the keyword setting interface will be displayed as allowed to add keywords. In response to the number of keywords corresponding to the target account being equal to the number threshold, the information addition area of ​​the keyword setting interface is displayed as a prohibited addition state.

18. The apparatus according to claim 16, characterized in that, The information addition operation includes any of the following: Input operations in the information addition area; The selection operation of the candidate options displayed in the information addition area, wherein the candidate options are candidate keywords or candidate bullet comments.

19. The apparatus according to claim 16, characterized in that, The storage module is used for: In response to the information addition operation in the information addition area, the bullet comments added in the information addition area are identified; In response to the absence of any sensitive words in the bullet comments, the keywords added in the information addition area and the bullet comments corresponding to the keywords are stored.

20. The apparatus according to claim 16, characterized in that, The device further includes: The information display module is used to display target prompt information in response to the number of keywords corresponding to the target account being less than a threshold. The target prompt information is used to prompt the user to add keywords and corresponding bullet comments.

21. A computer device, characterized in that, The computer device includes one or more processors and one or more memories, wherein at least one computer program is stored in the one or more memories, and the at least one computer program is loaded and executed by the one or more processors to perform the operations performed by the bullet screen publishing method as described in any one of claims 1 to 10.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to perform the operations performed by the bullet screen publishing method as described in any one of claims 1 to 10.

23. A computer program product comprising at least one computer program stored in a computer-readable storage medium, wherein a processor of a computer device reads the at least one computer program from the computer-readable storage medium, and the processor executes the at least one computer program such that the computer device performs an operation to implement the bullet screen posting method as described in any one of claims 1 to 10.

Images