Video bullet screen reading method, electronic device and storage medium

Abstract

Embodiments of the present application relate to the technical field of Internet video, and particularly relate to a video bullet screen reading method, an electronic device and a storage medium. The bullet screen reading method provided by the embodiments of the present application can acquire bullet screen attributes of each bullet screen appearing within a preset time in a video playing process, wherein the bullet screen attributes include the number of words, semantic content and / or repetitiveness of the bullet screen; the electronic device inputs the bullet screen attributes of each bullet screen to a preset reading matching model, so that the reading matching model determines a bullet screen that needs to be read among the bullet screens according to the bullet screen attributes of each bullet screen; and reads the bullet screen that needs to be read through an audio output unit. In the embodiments, the electronic device can selectively read the bullet screen according to the bullet screen attributes, without reading all the bullet screens one by one, thereby improving the efficiency of bullet screen reading and enhancing user experience.

Description

Technical Field

[0001] This application relates to the field of Internet video technology, and in particular to a method for reading video bullet comments, an electronic device, and a storage medium. Background Technology

[0002] "Bullet comments" refer to a phenomenon where numerous comments, presented as subtitles, appear on the screen alongside the video while it's playing. The comments scrolling across the top of the video like a barrage of bullets, hence the name. Bullet comments appear in real-time on the video, allowing viewers to see both their own and other viewers' comments. This creates a new form of online social interaction based on video viewing and centered around the video content.

[0003] Among the audience of video services, the blind are a relatively unique group. They also have the need to watch (listen) videos and hope that while they can understand video information by "listening", they can further understand the bullet screen information and experience or even participate in the video bullet screen interaction.

[0004] When a large number of bullet comments appear instantly, it would be extremely time-consuming for electronic devices to read them aloud one by one. For example, if 50 bullet comments appear within one second of a video, and each bullet comment takes 5 seconds to read, it would take 250 seconds to read them all. In the 250 seconds following that moment, the video content would have already become detached from the bullet comments. Summary of the Invention

[0005] This application provides a method, electronic device, and storage medium for reading video bullet comments, which can selectively read bullet comments based on their attributes, thereby improving the efficiency of bullet comment reading.

[0006] To address the aforementioned technical problems, the embodiments of this application provide the following technical solutions:

[0007] In a first aspect of this application, a method for reading aloud video comments is provided. The method includes: during video playback, acquiring the comment attributes of each comment appearing within a preset time period, the comment attributes including the number of characters, semantic content, and / or repetition of the comment; inputting the comment attributes of each comment into a preset reading matching model, so that the reading matching model determines the comment to be read aloud based on the comment attributes of each comment; and reading the comment to be read aloud through an audio output unit. In this embodiment, the electronic device can selectively read aloud comments based on their attributes, eliminating the need to read all comments one by one, thereby improving the efficiency of comment reading and enhancing the user experience.

[0008] In some implementations, the method further includes: acquiring all bullet comments appearing in the video; generating a text document based on all bullet comments appearing in the video, the text document including the bullet comment text of each bullet comment; receiving user operations on the bullet comment text; and, in response to the user operations, reading the bullet comment text aloud through the audio output unit.

[0009] In some implementations, the bullet screen attributes also include bullet screen ratings. The step of obtaining the bullet screen attributes of each bullet screen that appears within a preset time period includes: inputting each bullet screen that appears within the preset time period into a preset bullet screen rating model to obtain the bullet screen rating of each bullet screen.

[0010] In some implementations, before inputting each bullet comment appearing within the preset time into the preset bullet comment rating model, the method further includes: obtaining the preset bullet comment rating model, which includes: recording the dwell time of the focus on the bullet comment text of each bullet comment in the text document; obtaining the bullet comment rating corresponding to the dwell time; and training the initial bullet comment rating model with each bullet comment and the bullet comment rating corresponding to each bullet comment to obtain a trained bullet comment rating model, wherein the trained bullet comment rating model is the preset bullet comment rating model.

[0011] In some implementations, obtaining the bullet screen rating corresponding to the dwell time includes: if the dwell time is greater than a preset time threshold, then obtaining the bullet screen rating corresponding to the dwell time.

[0012] In some implementations, the step of reading the bullet comments that need to be read aloud through the audio output unit includes: determining the publisher of each bullet comment among the bullet comments that need to be read aloud; if at least two adjacent bullet comments have the same publisher, then merging the at least two adjacent bullet comments into a combined bullet comment; and reading the combined bullet comment aloud through the audio output unit.

[0013] In some implementations, obtaining the bullet screen attributes of each bullet screen that appears within a preset time period during video playback includes: obtaining the number of bullet screens that appear within a preset time period during video playback; if the number of bullet screens exceeds a preset threshold, then obtaining the bullet screen attributes of each bullet screen that appears within the preset time period.

[0014] In a second aspect of this application, a bullet screen reading device is also provided, applied to an electronic device. The device includes: a first acquisition module, configured to acquire bullet screen attributes of each bullet screen appearing within a preset time period during video playback, the bullet screen attributes including the number of characters, semantic content, and / or repetition of the bullet screen; an input module, configured to input the bullet screen attributes of each bullet screen to a preset reading matching model to obtain a ruling result corresponding to each bullet screen attribute, wherein the reading matching model is used to decide whether the bullet screen corresponding to the bullet screen attribute needs to be read aloud based on the bullet screen attribute; and a reading module, configured to determine, based on the ruling result, the bullet screens that need to be read aloud among the various bullet screens, and read the bullet screens that need to be read aloud through an audio output unit.

[0015] In a third aspect of this application, an electronic device is also provided, the electronic device comprising: a processor and a memory storing instructions, the instructions, when executed by the processor, causing the electronic device to perform the method described in the first aspect.

[0016] In a fourth aspect of this application, a computer-readable storage medium is also provided, the computer-readable storage medium storing instructions that, when executed by an electronic device, cause the electronic device to perform the method described in the first aspect.

[0017] It should be understood that the description in the Summary of the Invention section is not intended to limit the key or essential features of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments of the present invention will be briefly described below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0019] Figure 1 This is a schematic diagram of the hardware structure of an electronic device for performing a video bullet screen reading method according to an embodiment of this application;

[0020] Figure 2 This is a flowchart illustrating a video bullet screen reading method provided in one embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the structure of a text document provided in one embodiment of this application;

[0022] Figure 4This is a schematic diagram of the structure of a video bullet screen reading device provided in one embodiment of this application;

[0023] Figure 5 This is a schematic diagram of the structure of a video bullet screen reading device provided in another embodiment of this application. Detailed Implementation

[0024] The principles and spirit of this disclosure will be described below with reference to several exemplary embodiments illustrated in the accompanying drawings. It should be understood that these specific embodiments are described merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art.

[0025] As used herein, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects and are used only to distinguish the objects referred to, without implying a particular spatial order, temporal order, order of importance, etc., of the objects referred to.

[0026] Figure 1 A schematic diagram of the structure of the electronic device 100 is shown as an example. For example... Figure 1 As shown, the electronic device 100 may include a processor 11, a memory 12, an audio output unit 13, and a display screen 14. The electronic device may be, for example, a smartphone, tablet computer, or laptop computer.

[0027] It should be understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be hardware, software, or a combination of software and hardware.

[0028] Processor 11 and memory 12 can be connected via a bus or other means. Figure 1 Taking the example of a connection between China and Israel via a bus.

[0029] The memory 12, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 11 executes various functional applications and data processing of the inkjet printer by running the non-volatile software programs, instructions, and modules stored in the memory 12, thereby implementing the methods provided in any embodiment of this application.

[0030] The memory 12 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the inkjet printer, etc. Furthermore, the memory 12 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 12 may optionally include memory remotely located relative to the processor 11, and these remote memories may be connected to the controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The electronic device 100 can implement the bullet screen reading function through the audio output unit 13, etc. The audio output unit 13 can specifically be a speaker. A speaker, also called a "loudspeaker", is used to convert audio electrical signals into sound signals.

[0032] The display screen 14 can be used to display information input by the user or information provided to the user (such as images, videos, etc.) and various menus of the electronic device 100. In other embodiments, the display screen 14 can also accept user input, such as user touch operations; display the application's interface, etc. The display screen 140 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a quantum dot light-emitting diode (QLED), etc.

[0033] The following describes in detail the solution provided by the embodiments of the present invention in the above-mentioned electronic device 100.

[0034] Please see Figure 2 , Figure 2 The process of a video comment reading method is illustrated, such as... Figure 2 As shown, the method includes the following steps:

[0035] Step 21: During the playback of the video, obtain the bullet screen attributes of each bullet screen that appears within a preset time. The bullet screen attributes include the number of characters, semantic content, and / or repetition of the bullet screen.

[0036] Step 22: Input the bullet screen attributes of each bullet screen into a preset reading matching model to obtain the adjudication result corresponding to each bullet screen attribute. The reading matching model is used to adjudicate whether the bullet screen corresponding to the bullet screen attribute needs to be read aloud based on the bullet screen attribute.

[0037] The video in this embodiment can be either a live stream or a non-live stream. Non-live stream videos can be, for example, online TV shows or movies. During video playback, when the video's bullet comment function is enabled, commentary subtitles, or bullet comments, will pop up on the video image. The electronic device can acquire all bullet comments appearing within a preset time and determine the attributes of each bullet comment. The preset time can be any suitable time, such as 0.5s, 1s, or 1.5s. When the preset time is 1s, the electronic device can acquire all bullet comments appearing on the video within each 1-second interval. Bullet comment attributes specifically include the number of characters, semantic content, and / or repetition of the bullet comments.

[0038] After acquiring the attributes of the bullet comments, the electronic device inputs these attributes into a preset reading matching model to obtain a decision result corresponding to the bullet comment attributes. The reading matching model is used to decide whether the bullet comment corresponding to the given attribute needs to be read aloud. The decision result is either read aloud or not read aloud. A technician can pre-acquire training data for the reading matching model and input this data into the electronic device. This training data includes multiple bullet comment attributes and their corresponding decision results. The electronic device uses the training data to train the initial reading matching model, thereby obtaining the trained reading matching model, which is the preset reading matching model in this embodiment.

[0039] Specifically, in some embodiments, the repetition in the bullet screen attribute refers to the repetition of text content. Repetition can specifically be the number of repetitions. For example, if three bullet screens with identical content appear sequentially within a preset time period—the first bullet screen, the second bullet screen, and the third bullet screen—then, since the first bullet screen appears for the first time, its repetition count is 0; since the second bullet screen appears for the second time, its text content is repeated once with the first bullet screen, so the first bullet screen's repetition count is 1; similarly, since the third bullet screen appears for the third time, its text content is repeated once with both the first and second bullet screens, so the third bullet screen's repetition count is 2. If the repetition count of a bullet screen is not 0, the corresponding decision for that bullet screen is not to be read aloud. Therefore, this embodiment allows electronic devices to avoid reading repeatedly appearing bullet screens, improving bullet screen reading efficiency.

[0040] In some embodiments, to make it easier for users to listen to all the bullet comments that appear in the entire video, the electronic device can also acquire all the bullet comments that appear in the video; generate a text document based on all the bullet comments that appear in the video, the text document including the bullet comment text of each bullet comment; the electronic device receives user operations on the bullet comment text; and then, in response to the user operations, the electronic device reads the bullet comment text aloud through the audio output unit. Figure 3 An example diagram illustrating the structure of a text document is provided, such as... Figure 3 As shown, each line of text in the text document 300 is a bullet comment text 301 corresponding to a bullet comment. The focus 302 is positioned at the bullet comment text currently selected by the user. The user can use gestures such as clicking, swiping up, or swiping down to keep the focus on different bullet comment texts. When the user selects the focus, the electronic device can play the audio of the bullet comment text through the audio output unit, thereby realizing the reading of the bullet comment.

[0041] In some embodiments, the bullet screen attributes also include bullet screen ratings. When a bullet screen rating is not lower than a preset score threshold, the corresponding decision is to read it aloud; when a bullet screen rating is lower than the preset score threshold, the corresponding decision is not to read it aloud. Specifically, the electronic device can input each bullet screen that appears within a preset time period into a preset bullet screen rating model to obtain the bullet screen rating for each bullet screen.

[0042] Specifically, the electronic device can acquire training data for the bullet screen rating model. This training data includes the dwell time of the focus on each bullet screen text in the text document and the corresponding bullet screen rating for that dwell time. The electronic device can also perform embedded monitoring on the text document to record the dwell time of the focus on each bullet screen. In some embodiments of this application, if the dwell time is greater than a preset time threshold, the electronic device acquires the bullet screen rating corresponding to that dwell time. The preset time threshold may be, for example, 2s, 3s, or 4s. The electronic device trains the initial bullet screen rating model based on each bullet screen and its corresponding bullet screen rating, thereby obtaining the trained bullet screen rating model. The trained bullet screen rating model is the preset bullet screen rating model. Dwell time reflects the user's reading time of the bullet screen text. Generally, the longer the focus dwells on a bullet screen text, the more interested the user is in that bullet screen text. Therefore, the longer the dwell time, the higher the corresponding bullet screen rating.

[0043] Step 23: Based on the ruling result, determine the bullet comments that need to be read aloud from each bullet comment, and read the bullet comments that need to be read aloud through the audio output unit.

[0044] In some embodiments, the electronic device can determine which bullet comments need to be read aloud based on the ruling result, and read the bullet comments needing to be read aloud through an audio output unit. The electronic device generates bullet comment audio based on the bullet comments with a ruling result of "read aloud", and plays the bullet comment audio through the audio output unit. For bullet comments with a ruling result of "do not read aloud", the electronic device does not read the bullet comments.

[0045] In some embodiments, when the bullet comments are bullet comments of non-live video, the electronic device can also determine the publisher of each bullet comment in the bullet comments that need to be read aloud; if the publisher of at least two adjacent bullet comments is the same, then the at least two adjacent bullet comments are merged into a combined bullet comment; and the combined bullet comment is read aloud through the audio output unit.

[0046] The bullet screen reading method provided in this application embodiment can acquire the bullet screen attributes of each bullet screen appearing within a preset time during video playback. These attributes include the number of characters, semantic content, and / or repetition. The electronic device inputs these attributes into a preset reading matching model, enabling the model to determine which bullet screens need to be read aloud based on their attributes. The audio output unit then reads the selected bullet screens aloud. In this embodiment, the electronic device can selectively read bullet screens based on their attributes, eliminating the need to read every single bullet screen, thus improving reading efficiency and enhancing user experience. It also effectively prevents the bullet screen from becoming detached from the video content after reading.

[0047] Please see Figure 4 This application also provides a video bullet screen reading device, such as... Figure 4 As shown, the device 400 further includes: a first acquisition module 401, an input module 402, and a reading module 403. The first acquisition module 401 is used to acquire the bullet screen attributes of each bullet screen appearing within a preset time period during video playback. The bullet screen attributes include the number of characters, semantic content, and / or repetition of the bullet screen. The input module 402 is used to input the bullet screen attributes of each bullet screen into a preset reading matching model to obtain a ruling result corresponding to each bullet screen attribute. The reading matching model is used to decide whether the bullet screen corresponding to the bullet screen attribute needs to be read aloud based on the bullet screen attribute. The reading module 403 is used to determine the bullet screens that need to be read aloud based on the ruling result and read the bullet screens that need to be read aloud through an audio output unit.

[0048] Please see Figure 5 In some embodiments, the device 400 further includes a second acquisition module 404, a generation module 405, a receiving module 406, and a reading module 407. The second acquisition module 404 is used to acquire all the bullet comments appearing in the video. The generation module 405 is used to generate a text document based on all the bullet comments appearing in the video, the text document including the bullet comment text of each bullet comment; the receiving module 406 is used to receive user operations on the bullet comment text; and the reading module 407 is used to read the bullet comment text aloud through the audio output unit in response to the user operations.

[0049] In some embodiments, the first acquisition module 401 is specifically used to: input each bullet comment that appears within the preset time period into a preset bullet comment rating model, thereby obtaining the bullet comment rating of each bullet comment.

[0050] Please see Figure 5 In some embodiments, the device 400 further includes a third acquisition module 408. The third acquisition module 408 is specifically used to acquire a preset bullet screen rating model. Acquiring the preset bullet screen rating model includes: recording the dwell time of the focus on each bullet screen text in the text document; acquiring the bullet screen rating corresponding to the dwell time; and training the initial bullet screen rating model using each bullet screen and its corresponding bullet screen rating to obtain a trained bullet screen rating model, wherein the trained bullet screen rating model is the preset bullet screen rating model.

[0051] In some embodiments, obtaining the bullet screen rating corresponding to the dwell time includes: if the dwell time is greater than a preset time threshold, then obtaining the bullet screen rating corresponding to the dwell time.

[0052] In some embodiments, the reading module 403 is specifically used to: determine the publisher of each bullet comment in the bullet comments that need to be read aloud; if the publishers of at least two adjacent bullet comments are the same, then merge the at least two adjacent bullet comments into a combined bullet comment; and read the combined bullet comment aloud through the audio output unit.

[0053] In some embodiments, the first acquisition module 401 is further configured to: acquire the number of bullet comments appearing within a preset time during video playback; if the number of bullet comments exceeds a preset threshold, acquire the bullet comment attributes of each bullet comment appearing within the preset time.

[0054] This application also provides a computer-readable storage medium storing computer-executable instructions that are executed by one or more processors, for example... Figure 1 One of the processors 11 can enable the one or more processors to perform the methods in any of the above method embodiments, for example, to perform the methods described above. Figure 2 Steps 21 to 23 of the method; implementation Figure 4 Modules 401-403 Figure 5 The functions of modules 401-408 in the document.

[0055] This application also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium. The computer program includes program instructions that, when executed by a machine, cause the machine to perform the methods described above. For example, the above-described... Figure 2 Steps 21 to 23 of the method; implementation Figure 4 Modules 401-403 Figure 5 The functions of modules 401-408 in the document.

[0056] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0057] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software and a general-purpose hardware platform, or of course, using hardware. Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; under the concept of the present invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the present invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for reading video bullet comments aloud, characterized in that, The method includes: During video playback, obtain the number of bullet comments that appear within each preset time period; If the number of bullet comments exceeds a preset threshold, then the bullet comment attributes of each bullet comment appearing within the preset time period are obtained. The bullet comment attributes include the number of characters, semantic content, and repetition of the bullet comments. The bullet screen attributes of each bullet screen are input into a preset reading matching model to obtain the adjudication result corresponding to each bullet screen attribute. The reading matching model is used to adjudicate whether the bullet screen corresponding to the bullet screen attribute needs to be read aloud based on the bullet screen attribute. Based on the aforementioned ruling, the bullet comments that need to be read aloud are determined from each bullet comment. In the bullet comments that need to be read aloud, identify the poster of each bullet comment; If at least two adjacent bullet comments are posted by the same person, then the at least two adjacent bullet comments will be merged into a single combined bullet comment. The combined bullet comments are read aloud through the audio output unit.

2. The method according to claim 1, characterized in that, The method further includes: Get all the bullet comments that appear in the video; A text document is generated based on all the bullet comments that appear in the video, and the text document includes the bullet comment text of each bullet comment; Receive user actions regarding the bullet screen text; In response to the user's operation, the audio output unit reads the bullet screen text aloud.

3. The method according to claim 2, characterized in that, The bullet screen attributes also include bullet screen ratings, and the process of obtaining the bullet screen attributes of each bullet screen appearing within a preset time period includes: Each bullet comment that appears within the preset time period is input into a preset bullet comment rating model to obtain a bullet comment rating for each bullet comment.

4. The method according to claim 3, characterized in that, Before inputting each bullet comment appearing within the preset time period into the preset bullet comment rating model, the method further includes: Obtaining a preset bullet comment rating model, wherein obtaining the preset bullet comment rating model includes: Record the duration of focus on each bullet comment text in the text document; Obtain the bullet screen rating corresponding to the dwell time; The initial bullet comment rating model is trained by using each bullet comment and its corresponding score in each bullet comment to obtain the trained bullet comment rating model, which is the preset bullet comment rating model.

5. The method according to claim 4, characterized in that, The process of obtaining the bullet screen rating corresponding to the dwell time includes: If the dwell time is greater than a preset time threshold, then the bullet screen rating corresponding to the dwell time is obtained.

6. A bullet screen reading device, applied to electronic devices, characterized in that, The device includes: The first acquisition module is used to acquire the number of bullet comments appearing within each preset time period during the playback of the video; if the number of bullet comments exceeds a preset number threshold, the module acquires the bullet comment attributes of each bullet comment appearing within the preset time period, the bullet comment attributes including the number of characters, semantic content, and repetition of the bullet comment. An input module is used to input the attributes of each bullet screen into a preset reading matching model to obtain the adjudication result corresponding to each bullet screen attribute. The reading matching model is used to adjudicate whether the bullet screen corresponding to the bullet screen attribute needs to be read aloud based on the bullet screen attribute. The reading module is used to determine, based on the adjudication result, which bullet comments need to be read aloud from among the various bullet comments, determine the publisher of each bullet comment from among the bullet comments that need to be read aloud, and if at least two adjacent bullet comments have the same publisher, then merge the at least two adjacent bullet comments into a combined bullet comment, and read the combined bullet comment aloud through the audio output unit.

7. An electronic device, characterized in that, The electronic device includes a processor and a memory storing instructions, which, when executed by the processor, cause the electronic device to perform the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed by an electronic device, cause the electronic device to perform the method according to any one of claims 1-5.

Images