Video subtitle display method and device, equipment, medium and program product

Abstract

The invention provides a video subtitle display method and apparatus, a device, a medium and a program product. The method comprises the steps of obtaining a target live video and a target subtitle of the target live video; selecting a display mode of a target subtitle meeting a current playing requirement according to the current playing requirement of a user for the target live video; and adjusting and displaying the target subtitles of the target live video according to the display mode of the target subtitles. According to the method and the device, a plurality of different caption output and display modes are provided, and when the same target video is played, different caption output modes can be selected according to different playing requirements of caption contents, so that the diversification of caption generation and display modes is realized, and all caption display modes can be covered.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent subtitle technology, and in particular to a method, device, equipment, medium and program product for displaying video subtitles. Background Art

[0002] At present, subtitles in the industry are basically displayed in a single line, sentence by sentence format, which is a single display format. Especially when the video commentator speaks at a fast speed, the single line and sentence display of subtitles will cause the subtitle switching frequency to be too fast, causing visual fatigue to the audience. Summary of the invention

[0003] The embodiments of the present application provide a method, apparatus, device, medium and program product for displaying video subtitles to solve the problem of the single format of existing video display subtitles.

[0004] In order to solve the above technical problems, this application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for displaying video subtitles, including:

[0006] Obtain a target live video and target subtitles for the target live video;

[0007] According to the current playback requirement of the user for the target live video, a display mode of the target subtitles that meets the current playback requirement is selected;

[0008] The target subtitles of the target live video are adjusted and displayed according to the display mode of the target subtitles.

[0009] Optionally, the current playback requirement includes: a subtitle accuracy requirement for the currently played content;

[0010] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0011] Selecting a sound-and-character synchronous output mode or a non-sound-and-character synchronous output mode according to the subtitle accuracy requirement of the current playing content of the target live video;

[0012] Among them, in the non-audio-text synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the audio-text synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream.

[0013] Optionally, the non-sound word synchronous output mode includes: an extremely fast subtitle output mode;

[0014] The audio-text synchronous output mode includes any one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the live video source stream increases successively.

[0015] Optionally, the current playback requirement includes: a speech speed requirement for the currently played content;

[0016] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0017] According to the speech speed requirement of the current playback content of the target live video, select a word-by-word output mode or a sentence-by-sentence output mode, and a single-line output mode or a double-line output mode;

[0018] The word-by-word output mode displays all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode displays the final result of the target subtitle transcription;

[0019] The single-line output mode is a display mode of the target subtitles including only one line of subtitles; the double-line output mode is a display mode of the target subtitles including two lines of subtitles.

[0020] Optionally, adjusting and displaying the target subtitles of the target live video according to the display mode of the target subtitles includes:

[0021] Preprocessing the initial subtitles by filtering sensitive words in the subtitles according to the display mode of the target subtitles to obtain preprocessed subtitles;

[0022] The pre-processed subtitles are subjected to standardization processing to remove subtitle interference factors to obtain standardized subtitles; and the standardized subtitles are subjected to intelligent sentence segmentation processing to obtain target subtitles of the target live video.

[0023] Optionally, when the selected target subtitle display mode is a balanced subtitle output mode or a high-precision subtitle output mode;

[0024] After preprocessing the initial subtitles to filter sensitive words in the target subtitle display mode to obtain the preprocessed subtitles, the method further includes:

[0025] Performing subtitle correction detection on the preprocessed subtitles to obtain corrected subtitles.

[0026] In a second aspect, an embodiment of the present application provides a video subtitle display device, including:

[0027] An acquisition module, used to acquire a target live video and target subtitles of the target live video;

[0028] A first processing module, configured to select a display mode of a target subtitle that meets the current playback requirement of the target live video according to the current playback requirement of the user;

[0029] The second processing module is used to adjust and display the target subtitles of the target live video according to the display mode of the target subtitles.

[0030] Optionally, the current playback requirement includes: a subtitle accuracy requirement for the currently played content;

[0031] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0032] Selecting a sound-and-character synchronous output mode or a non-sound-and-character synchronous output mode according to the subtitle accuracy requirement of the current playing content of the target live video;

[0033] Among them, in the non-audio-text synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the audio-text synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream.

[0034] Optionally, the non-sound word synchronous output mode includes: an extremely fast subtitle output mode;

[0035] The audio-text synchronous output mode includes any one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the live video source stream increases successively.

[0036] Optionally, the current playback requirement includes: a speech speed requirement for the currently played content;

[0037] The first processing module comprises:

[0038] A first processing submodule is used to select a word-by-word output mode or a sentence-by-sentence output mode, and a single-line output mode or a double-line output mode according to the speech speed requirement of the current playback content of the target live video;

[0039] The word-by-word output mode displays all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode displays the final result of the target subtitle transcription;

[0040] The single-line output mode is a display mode of the target subtitles including only one line of subtitles; the double-line output mode is a display mode of the target subtitles including two lines of subtitles.

[0041] Optionally, the second processing module includes:

[0042] A preprocessing module, used for preprocessing the initial subtitles by filtering sensitive words in the subtitles according to the display mode of the target subtitles, to obtain preprocessed subtitles;

[0043] A standardization processing module, used for performing standardization processing on the pre-processed subtitles to remove subtitle interference factors, so as to obtain standardized subtitles;

[0044] The intelligent sentence processing module is used to perform intelligent sentence processing on the standardized subtitles to obtain target subtitles for the target live video.

[0045] Optionally, when the selected target subtitle display mode is a balanced subtitle output mode or a high-precision subtitle output mode;

[0046] Also includes:

[0047] The subtitle correction module is used to perform subtitle correction detection on the pre-processed subtitles to obtain corrected subtitles.

[0048] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps in the method for displaying video subtitles as described in any one of the first aspects.

[0049] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps in the method for displaying video subtitles as described in any one of the first aspects are implemented.

[0050] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps in the method for displaying video subtitles as described in any one of the first aspects.

[0051] In the present application, a variety of different subtitle output and display methods are provided, so that according to the current playback requirements of the target live video, a display mode of the target subtitles that meets the current playback requirements can be selected, and the target subtitles of the target live video can be displayed according to the display mode of the target subtitles, thereby realizing the diversification of subtitle generation and display methods, being able to cover all subtitle display forms, and solving the problem of the single display form of existing video subtitles. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Figure 1 is a flow chart of a method for displaying video subtitles provided by an embodiment of the present application;

[0054] Figure 2 It is a schematic diagram of a subtitle display mode of a video subtitle display method provided in an embodiment of the present application;

[0055] Figure 3 It is a schematic diagram of the device structure of a method for displaying video subtitles provided in an embodiment of the present application;

[0056] Figure 4 It is a schematic diagram of short sentence merging processing of a video subtitle display method provided by an embodiment of the present application;

[0057] Figure 5 It is a schematic diagram of sentence splitting and merging processing of a video subtitle display method provided by an embodiment of the present application;

[0058] Figure 6 This is a schematic diagram of subtitle alignment processing of a video subtitle display method provided by an embodiment of the present application;

[0059] Figure 7 It is a schematic diagram of a vertical screen user interface of a method for displaying video subtitles provided in an embodiment of the present application;

[0060] Figure 8 It is a horizontal screen user interface diagram of a method for displaying video subtitles provided in an embodiment of the present application;

[0061] Fig. 9 It is a subtitle correction processing schematic diagram of a video subtitle display method provided by an embodiment of the present application;

[0062] Fig.10 It is a structural schematic diagram of a video subtitle display device provided in an embodiment of the present application;

[0063] Fig.11 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] Please refer to Figure 1 , the embodiment of the present application provides a method for displaying video subtitles, including:

[0066] Step 11: Obtain a target live video and target subtitles of the target live video;

[0067] In the embodiment of the present application, the target live video obtains the target subtitles corresponding to the target live video through the audio transcription device, so that the display mode of the target subtitles can be adjusted according to the current playback requirements of the target live video, thereby realizing the diversification of the generation and display methods of the subtitles;

[0068] Specific data structures include but are not limited to the following structures:

[0069] The word segmentation data structure is named IstWord, where each IstWord is a word segmentation in the transcription result, and the content of the word segmentation can be a character or a word;

[0070] The specific data structure of IstWord is shown in Table 1:

[0071] Table 1

[0072]

[0073] The transcription result data structure, whose structure name is IstResult, is the result returned by the "audio transcription device";

[0074] The specific structure of IstResult is shown in Table 2:

[0075] Table 2

[0076]

[0077]

[0078] Subtitle structure, the structure name is SubtitleResult, the subtitle structure is a data structure at the subtitle sentence level, and is a structural unit for display by the video application front end;

[0079] The specific data of SubtitleResult is shown in Table 3:

[0080] Table 3

[0081]

[0082] Among them, the data structure of LastSubtitleResult is shown in Table 4:

[0083] Table 4

[0084]

[0085] Step 12: According to the current playback requirement of the user for the target live video, a display mode of the target subtitles that meets the current playback requirement is selected;

[0086] In the embodiment of the present application, the user can select the current playback requirements of the target live video according to personal preferences or platform requirements. Specifically, the current playback requirements include: the subtitle accuracy requirements of the currently played content and the speech speed requirements of the currently played content, such as Figure 2 As shown, the display mode of the target subtitles includes at least one of the following: a sound-character synchronous output mode or a non-sound-character synchronous output mode; a word-by-word output mode or a sentence-by-sentence output mode; and a single-line output mode or a double-line output mode; wherein, in the non-sound-character synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the sound-character synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream; the non-sound-character synchronous output mode includes: an ultra-fast subtitle output mode; the sound-character synchronous output mode includes at least one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the live video source stream increases in sequence; the word-by-word output mode is to display all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode is to display the final result of the target subtitle transcription; the single-line output mode is that the display mode of the target subtitles only includes one line of subtitles; the double-line output mode is that the display mode of the target subtitles includes two lines of subtitles.

[0087] When the current playback requirement is a subtitle accuracy requirement for the currently played content;

[0088] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0089] Selecting a sound-and-character synchronous output mode or a non-sound-and-character synchronous output mode according to the subtitle accuracy requirement of the current playing content of the target live video;

[0090] Among them, in the non-audio-text synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the audio-text synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream.

[0091] When the current playback requirement is a speech speed requirement of the currently played content;

[0092] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0093] According to the speech speed requirement of the current playback content of the target live video, select a word-by-word output mode or a sentence-by-sentence output mode, and a single-line output mode or a double-line output mode;

[0094] The word-by-word output mode displays all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode displays the final result of the target subtitle transcription;

[0095] The single-line output mode is a display mode of the target subtitles including only one line of subtitles; the double-line output mode is a display mode of the target subtitles including two lines of subtitles.

[0096] In an embodiment of the present application, a display mode of a target subtitle that meets the current playback requirements can be selected according to the specific playback situation, and the target subtitles of the target live video can be displayed according to the display mode of the target subtitles, thereby realizing diversified generation and display methods of subtitles, and being able to cover all subtitle display forms.

[0097] Step 13: Adjust and display the target subtitles of the target live video according to the display mode of the target subtitles.

[0098] In the present application, please refer to Figure 3 , by sequentially performing subtitle preprocessing on the transcription result IstResult returned from the audio transcription device through a preprocessing module, a target subtitle after the subtitle preprocessing is obtained; then the transcription result standardization processing module performs subtitle standardization processing on the target subtitle after the subtitle preprocessing, and obtains the target subtitle after the subtitle standardization processing; finally, the double-line intelligent sentence processing module performs intelligent sentence processing on the target subtitle after the subtitle standardization processing, and obtains the target subtitle of the target live video to be displayed. By processing the target subtitle, the final effect of the display mode of the target subtitle can be achieved, and the subtitle generation and display methods are diversified, which can cover all subtitle display forms.

[0099] In the embodiment of the present application, a variety of different subtitle output and display methods are provided, and it is possible to select a display mode of a target subtitle that meets the current playback requirements of the target live video according to the current playback requirements of the target live video, and display the target subtitles of the target live video according to the display mode of the target subtitles, thereby realizing diversified generation and display methods of subtitles, being able to cover all subtitle display forms, and solving the problem of a single display form of existing video subtitles.

[0100] In the embodiment of the present application, optionally, the current playback requirement includes: a subtitle accuracy requirement of the currently played content;

[0101] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0102] Selecting a sound-and-character synchronous output mode or a non-sound-and-character synchronous output mode according to the subtitle accuracy requirement of the current playing content of the target live video;

[0103] Among them, in the non-audio-text synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the audio-text synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream.

[0104] In the embodiment of the present application, the audio-text synchronous output mode is to align the timestamps of the audio Predetermined Time System (PTS) in the video with the subtitles, and the sound and text are synchronized; the non-audio-text synchronous output mode is to not align the timestamps of the audio and subtitles in the video, and the subtitles will appear to be a certain time later than the video picture and audio, which is the effect of "simultaneous interpretation";

[0105] The non-audio-character synchronous output mode includes: an ultra-fast subtitle output mode; in the ultra-fast subtitle mode, the subtitles and the video are not aligned, the subtitles will be slower than the video screen and audio by a certain time, and there is no time difference with the main perspective (i.e., the live video source stream);

[0106] The audio-text synchronous output mode includes at least one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the video live source stream increases in sequence; the low-latency subtitle output mode is an intermediate result of displaying subtitles, and the subtitles are timestamped with the video screen and audio, and the time difference with the main viewing angle is 3 seconds; the balanced subtitle output mode is an intermediate result of supporting display / non-display of subtitles, and the subtitles are aligned with the video screen and audio, and the time difference with the main viewing angle is 20 seconds; within this 20-second period, it supports outputting subtitles to a real-time subtitle correction system for correction, thereby improving the accuracy of subtitles; the high-precision subtitle mode is an intermediate result of supporting display / non-display of subtitles, and the subtitles are aligned with the video screen and audio, and the time difference with the main viewing angle is a default of 30 seconds, or a custom time difference (>30 seconds); within this time difference, it supports outputting subtitles to a real-time subtitle correction system for correction, thereby improving the accuracy of subtitles; under high precision, a longer time can be used for subtitle correction, and the subtitle accuracy rate will be higher.

[0107] In the embodiment of the present application, optionally, the non-sound word synchronous output mode includes: an extremely fast subtitle output mode;

[0108] The audio-text synchronous output mode includes any one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the live video source stream increases successively.

[0109] In the embodiment of the present application, optionally, the current playback requirement includes: a speech speed requirement of the currently played content;

[0110] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0111] According to the speech speed requirement of the current playback content of the target live video, select a word-by-word output mode or a sentence-by-sentence output mode, and a single-line output mode or a double-line output mode;

[0112] The word-by-word output mode displays all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode displays the final result of the target subtitle transcription;

[0113] The single-line output mode is a display mode of the target subtitles including only one line of subtitles; the double-line output mode is a display mode of the target subtitles including two lines of subtitles.

[0114] In the embodiment of the present application, the word-by-word output mode is a subtitle, and all intermediate results transcribed by the "audio transcription device" are displayed on the video client. Word-by-word is an incremental subtitle display format;

[0115] For example, if the sentence "diversified subtitles" is a subtitle, the order of word-by-word output is as follows:

[0116] 1) More

[0117] 2) Diversity

[0118] 3) Diversification

[0119] 4) Diversified characters

[0120] 5) Diversified subtitles

[0121] The sentence-by-sentence output mode is a sentence-by-sentence subtitle, that is, the final result is directly output. If the length of a subtitle exceeds one sentence, it is displayed in a sentence-by-sentence manner according to the length rule;

[0122] The single-line output mode is to output to the front end each time, only one line of subtitle data is included;

[0123] The double-line output mode is to output to the front end each time, including data of two lines of subtitles.

[0124] In addition, the present application supports the combination of several modes of the above-mentioned subtitles, realizes the diversification of subtitle generation and display methods, can cover all subtitle display forms, fills the shortcomings of subtitle output methods, can be applied to various live subtitle scenarios, and solves the problem of single display form of existing video subtitles.

[0125] In the embodiments of the present application, a variety of different subtitle output and display modes are provided. When playing the same target video, according to different requirements for subtitle accuracy, a subtitle output mode with a different time delay from the main viewing angle can be selected, that is, a phonetic character synchronous output mode or a non-phonetic character synchronous output mode; it is also possible to select subtitles with different display forms when the speech speed requirements of the video playback content are different, that is, a word-by-word output mode or a sentence-by-sentence output mode, and / or a single-line output mode or a double-line output mode, to achieve diversified generation and display methods of subtitles, cover all subtitle display forms, fill the gaps in subtitle output methods, adapt to a variety of video scenes, and enhance user experience.

[0126] In the embodiment of the present application, optionally, adjusting and displaying the target subtitles of the target live video according to the display mode of the target subtitles includes:

[0127] Preprocessing the initial subtitles by filtering sensitive words in the subtitles according to the display mode of the target subtitles to obtain preprocessed subtitles;

[0128] Performing standardization processing on the pre-processed subtitles to remove subtitle interference factors, so as to obtain standardized subtitles;

[0129] Intelligent sentence segmentation is performed on the standardized subtitles to obtain target subtitles for the target live video.

[0130] In the present application embodiment, Figure 3 As shown, the transcription result IstResult returned by the audio transcription device is processed into an array of SubtitleResult;

[0131] Combination Figure 3 The specific processing flow is as follows:

[0132] (1) The subtitle generation module receives the subtitle recognition result IstResult input from the audio transcription device;

[0133] (2) IstResult is sent to the subtitle sequence generator of the subtitle preprocessing module, and IstResult.SegId and IstResult.Index are numbered, including:

[0134] Set the global SegId to GLOBAL_SEG_ID, with an initial value of 1;

[0135] Set the global Index to GLOBAL_SEG_INDEX, with an initial value of 1;

[0136] Each time a new IstResult is accepted, set:

[0137] IstResult.SegId=GLOBAL_SEG_ID;

[0138] IstResult.Index=GLOBAL_SEG_INDEX;

[0139] Determine IstResult.Type. If IstResult.Type is progressive, then:

[0140] The GLOBAL_SEG_INDEX value increases by 1;

[0141] If IstResult.Type is sentence, then:

[0142] The GLOBAL_SEG_ID value increases by 1;

[0143] The GLOBAL_SEG_INDEX value is reset to 1;

[0144] Through the above mechanism, each IstResult is numbered to ensure that the SegId of the intermediate result and the final result of the same subtitle remain consistent, and the Index increases;

[0145] (3) In the subtitle preprocessing module, IstResult is sent to the sensitive word filter to perform sensitive word filtering and replacement operations to ensure the security of subtitle content. The specific process is as follows:

[0146] IstResult.List <istword>Send to sensitive word filter;

[0147] List <istword>Traverse and process each IstWord;

[0148] The sensitive word filter determines IstWord.Word. If a sensitive word exists in IstWord.Word, the start and end subscripts of the sensitive word in IstWord.Word are output;

[0149] SenceWord(BgIndex,EdIndex), if there are multiple sensitive words, multiple SenceWord will be output;

[0150] Process sensitive words in IstWord.Word, and replace the words between SenceWord.BgIndex and SenceWord.EdIndex in IstWord.Word with *;

[0151] Finally, the sensitive word processor will fill the replaced IstWord back into IstResult.List <istword>.

[0152] After the preprocessing module, IstResult will be sent to the "transcription result standardization processing module", in which IstResult will be further standardized.

[0153] (4) IstResult.List <istword>Send it to the modal particle filter. Through this step, invalid modal particles in the subtitles are filtered out to reduce the risk of mis-transmission caused by ambient sound and noise in the live video.

[0154] List <istword>Traverse, replace the modal particles in IstWord.Word with the empty character "", and fill them back into IstWord.Word;

[0155] Determine the length of IstWord.Word. If IstWord.Word.Lengt is 0, then select <istword>Remove this IstWord from the list;

[0156] List <istword>Backfill to IstResult.List <istword>;

[0157] (5) IstResult.List <istword>Send to the punctuation filter; by filtering the punctuation, the jump of the upper and lower sentences can be relatively stable, and the subtitle splitting will not be unstable due to the wrong sentence segmentation of the audio transcriber;

[0158] List <istword>Conduct traversal;

[0159] If IstWord.WType is p, it means the current word is a punctuation mark, then remove this IstWord from the List <istword>Remove;

[0160] If IstWord.WType is not p, filter the punctuation in IstWord.Word. If it contains . ! ? , .! ? , "", replace it with a null character "";

[0161] Determine the value of IstWord.Word. If it is null, remove this IstWord from the List <istword>Removed;

[0162] The filtered List <istword>Backfill to IstResult.List <istword>;

[0163] (6) IstResult.List <istword>The subtitles are sent to a small word filter for processing invalid subtitles. The small word filter filters the final results during the game, which have a long time since the last subtitle return and a shorter length this time. According to statistics, in general, in live video broadcasts, the proportion of such subtitles as invalid subtitles is as high as >95%, and can be filtered.

[0164] For example: Assuming that the current IstResut is CurIstResult and the last IstResult is LastIstResult, then:

[0165]

[0166] Note: Tgap is the time difference threshold, which can be adjusted dynamically; SMALL_SENTENCE_LENGTH is the maximum length of the small word rule.

[0167] (7) Send IstResult to the word segmentation timestamp distributor. The purpose of the word segmentation timestamp distributor is to split an IstWord.Word with an excessive length into multiple IstWords that meet the length requirements. In this way, the granularity of the video application client display is finer, and the subtitles will not appear to be a large piece of content suddenly. The specific implementation is as follows.

[0168] Prerequisites:

[0169] (IstResult.List <istresult>[i]).Word.lengh>SINGLE_WORD_MAX_LENGTH;

[0170] SINGLE_WORD_MAX_LENGTH is the maximum length threshold of a single IstWord.Word, which can be adjusted dynamically;

[0171] Determine the time difference taken by a single word:

[0172] TForPerWord=(IstWord.Wed–IstWord.Wbg) / IstWord.Word.Length(microseconds)

[0173] Convert IstResult.Word to a single character array:

[0174] WordArray=IstResult.Word.toCharArray();

[0175] Traverse WordArray, starting with WordArray[i], and

[0176] WordArray[i+SINGLE_WORD_MAX_LENGTH-1] is used to complete the character concatenation and obtain the new IstWordi.Word.

[0177] IstWordi.Wbg=i*TForPerWord;

[0178] IstWordi.Wed=(i+IstWordi.Word.Length)*TForPerWord;

[0179] According to the above rules, an IstWord is split into multiple IstWordi, recorded as List <istwordi>, use List <istwordi>Replace IstWord and fill it back into IstResult;

[0180] After IstResult passes through the "transcription result standardization processing module", a relatively pure word segmentation array with safe content and removed jump interference factors is obtained. Next, the word segmentation array can be sent to the "double-line intelligent sentence processing module" to generate a subtitle data structure that can be output to the video application client.

[0181] (8) Send IstResult to Figure 4 The short sentence merging processor shown in the figure aims to reduce the number of subtitles that are too short and are directly displayed as a single line on the video application client. The short sentence merging mechanism is introduced to split the subtitles into short sentences and display them merged. This reduces the frequency of displaying short subtitles below a certain threshold or short subtitles generated by long subtitles after sentence splitting rules as a single line of subtitles, allowing short subtitles to stay longer on the front end of the video application, avoiding excessive switching of subtitles and causing visual fatigue to the audience.

[0182] Assume that the minimum length of subtitle display of the video application client set in the system is SUBTITLE_MIN_LEN, and the maximum length is SUBTITLE_MAX_LEN.

[0183] The short sentence merging processor includes Figure 4 Modules:

[0184] Short sentence cache trigger, IstResult will eventually be split into multiple clauses that meet the length of the video application front-end display. The length of the last clause may be less than the minimum subtitle length SUBTITLE_MIN_LEN displayed by the video application front-end. In this case, the short sentence cache trigger will trigger the short sentence cache, and the word group corresponding to this clause;

[0185] ShortSentenceList <istword>Will be stored in the cache;

[0186] The short sentence cache getter returns the short sentence phrases that need to be merged according to certain rules.

[0187] In this step, the short sentences to be merged are obtained through the short sentence cache getter, and the ShortSentenceList <istword>Add to IstResult.List <istresult>The beginning of .

[0188] (9) Send IstResult to the sentence generator. This step is to specifically split a sentence of subtitles and generate a subtitle data array List <subtitleresult>.

[0189] Iterate over IstResult.List <istword>, assuming a subtitle SubtitleResult, in IstResult.List <istword>The corresponding starting subscript is sx and the ending subscript is sy, then:

[0190] SubtitleResult.StartTime=IstResult.List <istword>[sx].Wbg;

[0191] SubtitleResult.EndTime=IstResult.List <istword>[sy].Wed;

[0192] SubtitleResult.OriginText=Contact(IstResult.List <istword>,sx,sy);

[0193] The Contact method concatenates IstWord.Word and generates a subtitle string.

[0194] SubtitleResult.Type is determined by the value of IstResult.Type. When IstResult.Type is sentence, SubtitleResult.Type is F; when IstResult.Type is progressive, SubtitleResult.Type is M.

[0195] Among them, SubtitleResult.OrigiText.Length<=SUBTITLE_MAX_LEN.

[0196] (10) List <subtitleresult>Send to the double-line subtitle mounter. Regardless of single-line or double-line mode, double-line subtitles are generated first and processed uniformly.

[0197] Record the following information about the last subtitle sent to the video application client:

[0198] SubtitleResultLast, SegIdLast, this SubtitleResult is in List <subtitleresult>Based on this condition, the rules for mounting double-line subtitles are as follows:

[0199] List <subtitleresult>In the case where the first subtitle data is mounted to LastSubtitleResult,

[0200] (List <subtitleresult>[0].StartTime - SubtitleResultLast.EndTime) <= CLEAN_SCREEN_MIN_TIME, that is, it meets the mounting condition, and LastSubtitleResult = genFromSubtitleResult(SubtitleResultLast) can be based on;

[0201] The specific logic of genFromSubtitleResult is as follows:

[0202] LastSubtitleResult.StartTime = SubtitleResultLast.StartTime

[0203] LastSubtitleResult.EndTime = SubtitleResultLast.EndTime

[0204] LastSubtitleResult.OriginText = SubtitleResultLast.OriginText

[0205] LastSubtitleResult.Type = SubtitleResultLast.Type

[0206] Mounting operation: List <subtitleresult>[0].Last=LastSubtitleResult

[0207] List <subtitleresult>The non-first subtitle in the mount, that is, when the index m>0,

[0208] Then there is List <subtitleresult>[m].Last=

[0209] genFromSubtitleResult(List <subtitleresult>[m-1])

[0210] (11) Mount the List with double-line subtitle data <subtitleresult>Send to the sentence splitting and merging processor.

[0211] As mentioned in (8) above, the short sentence merging processor includes a short sentence cache trigger. In this step, List <subtitleresult>In the example, assuming that the last index is EndIndex, if List <subtitleresult>[EndIndex].OriginText.Length <

[0212] SUBTITLE_MIN_LEN, then the List <subtitleresult>[EndIndex].OriginText corresponding word group IstResult.List <istword>(sx,sy) is cached as short sentence cache data

[0213] List <subtitleresult>The timestamp is sent to the sentence timestamp reset module to reset the timestamp of each subtitle sentence to ensure that the timestamps of multiple subtitle sentences in a subtitle are continuous.

[0214] like Figure 5 As shown, the start timestamp of SubtitleResult0 corresponds to IstWord1.Wbg1, and the end time is IstWord4.Wed4; the start timestamp of SubtitleResult1 is IstWord5.Wbg5, and the end timestamp is IstWord8.Wed8;

[0215] If IstWord4.Wed4!=IstWord5.Wbg5, then for the subtitle sentences SubtitleResult0 and SubtitleResult1, their subtitle timestamps are not continuous. We expect that for different sentences of the same subtitle, the timestamps are continuous, so as to ensure the display effect at the video application front end.

[0216] The subtitle timestamp reset rule is simple.

[0217] SubtitleResult1.StartTime=SubtitleResult0.EndTime, and so on.

[0218] (13) List <subtitleresult>Send it to the standard subtitle generator. In this step, specific intervention will be made for the line mode. The above steps take double-line subtitles as an example. When the mode of this live video subtitle task is single-line mode, we need to set all SubtitleResult.Last to empty; at the same time, if SubtitleResult.Type is F, it will be intervened to M.

[0219] (14) Output standard subtitles to the video application front end;

[0220] (15) Determine the alignment relationship between subtitles and videos;

[0221] Specifically: After caching the video, Figure 6 As shown, it is assumed that the video module cached by the live stream at that time is ts_n;

[0222] SubtitleResult.StartTime and SubtitleResult.EndTime are timestamps relative to the start PTS of the live video stream, assuming that SubtitleResult falls in the video buffer block ts_n;

[0223] Then find the corresponding video start and end pts in ts_n according to SubtitleResult.StartTime and SubtitleResult.EndTime: pts_n1, pts_n2;

[0224] Through video encoding technology, subtitles are inserted into the subtitle track of the video clip (pts_n1, pts_n2) of ts_n; for the specific video live subtitle diversified display user interface, please refer to Figure 7 For vertical display and Figure 8 For horizontal display.

[0225] In the embodiment of the present application, a subtitle backend screen clearing mechanism solution is also introduced, through which the display and disappearance time of subtitles on the video application client are controlled.

[0226] The video application client and the device of this solution agree that when the video application receives a SubtitleResult of type M, the client only changes the content display without considering the disappearance time of the subtitles on the front end; after the video application receives a subtitle of type F, the front-end application subtitles will be cleared.

[0227] The specific screen clearing mechanism implementation process is as follows:

[0228] After the preprocessing module completes the processing, the video live broadcast diversified subtitle output display device records IstResult.SegId, IstResult.Index, and IstResult.StartTime as a data structure - SubtitleRecord, and the combination of SubtitleRecord is recorded as List <subtitlerecord>;

[0229] When you get List <subtitleresult>Finally, the last index of the subtitle array is recorded as EndIndex, and the List <subtitleresult>[EndIndex].EndTime makes the following determination:

[0230] Iterating over a List <subtitlerecord>, assuming the current traversal index is i

[0231] (0<=i<(List <subtitlerecord>).Length);

[0232] if

[0233] List <subtitlerecord>[i].StartTime <List <subtitleresult>[EndIndex].EndTime, then i is removed from the List <subtitlerecord>Remove, indicating that the data corresponding to i has lost its comparison value, and the end time of the current subtitle is after the subtitle corresponding to i;

[0234] if

[0235] List <subtitlerecord>[i].StartTime>=List <subtitleresult>[EndIndex].EndTime, and

[0236] List <subtitlerecord>[i].StartTime-List <subtitleresult>[EndIndex].EndTime

[0237] >CLEAN_SCREEN_MIN_TIME, the scheduled task is triggered, and the task execution time point is the current server physical time T+CLEAN_SCREEN_MIN_TIME. At T+CLEAN_SCREEN_MIN_TIME, a subtitle of type F will be generated and sent to the video application front end, and the video application will clear the screen. By introducing the back-end clearing mechanism, that is, the subtitles are output to the front end, if the front end does not receive the clearing signal, the subtitles will be displayed or the content will be updated, and the clearing or removal of the subtitle display control will not be triggered. The timing of subtitle clearing is completely controlled by the back end, which improves the subtitle experience and enables the back end to control the residence time of subtitles on the video client. This solves the problem of subtitle flashing caused by displaying subtitles according to the actual duration in the industry, and improves the user's visual sensory effect.

[0238] In the embodiment of the present application, optionally, when the selected display mode of the target subtitle is a balanced subtitle output mode or a high-precision subtitle output mode;

[0239] After preprocessing the initial subtitles to filter sensitive words in the target subtitle display mode to obtain the preprocessed subtitles, the method further includes:

[0240] Performing subtitle correction detection on the preprocessed subtitles to obtain corrected subtitles.

[0241] In the embodiment of the present application, when the selected display mode of the target subtitle is the balanced subtitle output mode or the high-precision subtitle output mode, the target subtitle can be sent to the external subtitle correction module after the subtitle preprocessing module completes the processing. If the external subtitle correction module corrects the subtitle within the specified waiting time period ModifyWaitTime, the corrected subtitle content will be used in the subtitle;

[0242] The external subtitle correction module is as follows Fig. 9 As shown, IstResult.Sentence is modified;

[0243] If the sensitive word detection is passed, IstResult.SentenceOfModify will be assigned the modified content;

[0244] Send IstResult to the word segmentation generator and perform word segmentation on IstResult.SentenceModify. The specific process is as follows:

[0245] The IstResult is sent to the word segmentation timestamp distributor. The purpose of the word segmentation timestamp distributor is to split an IstWord.Word with an excessive length into multiple IstWords that meet the length requirements. In this way, the granularity of the video application client display is finer, and the subtitles will not appear to be a large piece of content suddenly. The specific implementation is as follows.

[0246] Prerequisites:

[0247] (IstResult.List <istresult>[i]).Word.lengh>SINGLE_WORD_MAX_LENGTH;

[0248] SINGLE_WORD_MAX_LENGTH is the maximum length threshold of a single IstWord.Word, which can be adjusted dynamically;

[0249] Determine the time difference taken by a single word:

[0250] TForPerWord=(IstWord.Wed–IstWord.Wbg) / IstWord.Word.Length(microseconds)

[0251] Convert IstResult.Word to a single character array:

[0252] WordArray=IstResult.Word.toCharArray();

[0253] Traverse WordArray, starting with WordArray[i], and

[0254] WordArray[i+SINGLE_WORD_MAX_LENGTH-1] is used to complete the character concatenation and obtain the new IstWordi.Word.

[0255] IstWordi.Wbg=i*TForPerWord;

[0256] IstWordi.Wed=(i+IstWordi.Word.Length)*TForPerWord;

[0257] According to the above rules, an IstWord is split into multiple IstWordi, recorded as List <istwordi>, use List <istwordi>Replace IstWord and fill it back into IstResult;

[0258] After IstResult passes through the "transcription result standardization processing module", a relatively pure word segmentation array with safe content and removed jump interference factors is obtained. Next, the word segmentation array can be sent to the "double-line intelligent sentence processing module" to generate a subtitle data structure that can be output to the video application client.

[0259] After the word segmentation process is completed, the new word segmentation array is backfilled into IstResult.List <istword>;

[0260] Then send IstResult to the "transcription result standardization processing module" for subsequent processing.

[0261] In an embodiment of the present application, in a balanced subtitle output mode or a high-precision subtitle output mode, it supports sending subtitles to a real-time subtitle correction system for manual correction, thereby improving the accuracy of subtitles and making it possible to produce subtitles for live video broadcasts in multiple languages, such as Mandarin, Cantonese, Minnan, Sichuanese and other dialects, thereby achieving diversification of subtitle languages; and the balanced subtitle output mode or the high-precision subtitle output mode supports hot plugging of various "audio transcription devices", thereby bringing greater convenience to business operations and effectively improving the accuracy of subtitles.

[0262] In the embodiment of the present application, specifically, the process of diversified output display of target subtitles for the target live video is shown in Table 5:

[0263] For example, take the subtitle text "Asian Games bring joy and brilliance together. The 19th Asian Games came to a successful conclusion in Hangzhou on the evening of the 8th" as an example to describe the subtitle output order.

[0264] In the embodiment of the present application, only the double-line, word-by-word output process is taken as an example, and the single-line, sentence-by-sentence output is a simplified version of the double-line, word-by-word mode, which will not be repeated.

[0265] Table 5

[0266]

[0267]

[0268]

[0269]

[0270] Please refer to Fig.10 , the embodiment of the present application provides a video subtitle display device, including:

[0271] An acquisition module 101 is used to acquire a target live video and a target subtitle of the target live video;

[0272] The first processing module 102 is used to select a display mode of a target subtitle that meets the current playback requirement of the target live video according to the current playback requirement of the user;

[0273] The second processing module 103 is used to adjust and display the target subtitles of the target live video according to the display mode of the target subtitles.

[0274] In the embodiment of the present application, optionally, the current playback requirement includes: a subtitle accuracy requirement of the currently played content;

[0275] The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes:

[0276] Selecting a sound-and-character synchronous output mode or a non-sound-and-character synchronous output mode according to the subtitle accuracy requirement of the current playing content of the target live video;

[0277] Among them, in the non-audio-text synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the audio-text synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream.

[0278] In the embodiment of the present application, optionally, the non-sound word synchronous output mode includes: an extremely fast subtitle output mode;

[0279] The audio-text synchronous output mode includes any one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the live video source stream increases successively.

[0280] In the embodiment of the present application, optionally, the current playback requirement includes: a speech speed requirement of the currently played content;

[0281] The first processing module 102 includes:

[0282] A first processing submodule is used to select a word-by-word output mode or a sentence-by-sentence output mode, and a single-line output mode or a double-line output mode according to the speech speed requirement of the current playback content of the target live video;

[0283] The word-by-word output mode displays all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode displays the final result of the target subtitle transcription;

[0284] The single-line output mode is a display mode of the target subtitles including only one line of subtitles; the double-line output mode is a display mode of the target subtitles including two lines of subtitles.

[0285] In the embodiment of the present application, optionally, the second processing module 103 includes:

[0286] A preprocessing module, used for preprocessing the initial subtitles by filtering sensitive words in the subtitles according to the display mode of the target subtitles, to obtain preprocessed subtitles;

[0287] A standardization processing module, used for performing standardization processing on the pre-processed subtitles to remove subtitle interference factors, so as to obtain standardized subtitles;

[0288] The intelligent sentence processing module is used to perform intelligent sentence processing on the standardized subtitles to obtain target subtitles for the target live video.

[0289] In the embodiment of the present application, optionally, when the selected display mode of the target subtitle is a balanced subtitle output mode or a high-precision subtitle output mode;

[0290] Also includes:

[0291] The subtitle correction module is used to perform subtitle correction detection on the pre-processed subtitles to obtain corrected subtitles.

[0292] The video subtitle display device provided in the embodiment of the present application can achieve Figure 1 The various processes implemented by the method embodiment and achieving the same technical effect are not described here to avoid repetition.

[0293] The present application embodiment provides an electronic device 110, see Fig.11 As shown, Fig.11 This is a principle block diagram of an electronic device 110 according to an embodiment of the present application, including a processor 111, a memory 112, and a program or instruction stored in the memory 112 and executable on the processor 111. When the program or instruction is executed by the processor, the steps in any video subtitle display method of the present application are implemented.

[0294] An embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of an embodiment of a method for displaying video subtitles as described above is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0295] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiment shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0296] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0297] It should be noted that, in this article, the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0298] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0299] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a service classification device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0300] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.< / istword> < / istwordi> < / istwordi> < / istresult> < / subtitleresult> < / subtitlerecord> < / subtitleresult> < / subtitlerecord> < / subtitlerecord> < / subtitleresult> < / subtitlerecord> < / subtitlerecord> < / subtitlerecord> < / subtitleresult> < / subtitleresult> < / subtitlerecord> < / subtitleresult> < / subtitleresult> < / istword> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / subtitleresult> < / istword> < / istword> < / istword> < / istword> < / istword> < / subtitleresult> < / istresult> < / istword> < / istword> < / istwordi> < / istwordi> < / istresult> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword> < / istword>

Claims

1. A method for displaying video subtitles, characterized in that: include: Obtain a target live video and target subtitles for the target live video; According to the current playback requirement of the user for the target live video, a display mode of the target subtitles that meets the current playback requirement is selected; The target subtitles of the target live video are adjusted and displayed according to the display mode of the target subtitles.

2. The method for displaying video subtitles according to claim 1, characterized in that: The current playback requirements include: requirements for the accuracy of subtitles of the currently played content; The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes: Selecting a sound-and-character synchronous output mode or a non-sound-and-character synchronous output mode according to the subtitle accuracy requirement of the current playing content of the target live video; Among them, in the non-audio-text synchronous output mode, there is no time difference between the display mode of the target subtitles and the live video source stream; in the audio-text synchronous output mode, there is a time difference between the display mode of the target subtitles and the live video source stream.

3. The method for displaying video subtitles according to claim 2, characterized in that: The non-sound word synchronous output mode includes: an extremely fast subtitle output mode; The audio-text synchronous output mode includes any one of the following: a low-latency subtitle output mode, a balanced subtitle output mode, and a high-precision subtitle output mode, wherein the time difference between the low-latency subtitle output mode, the balanced subtitle output mode, and the high-precision subtitle output mode and the live video source stream increases successively.

4. The method for displaying video subtitles according to claim 1, characterized in that: The current playback requirements include: the speech speed requirements of the currently played content; The step of obtaining the current playback requirement of the target live video by the user and selecting a display mode of the target subtitles that meets the current playback requirement includes: According to the speech speed requirement of the current playback content of the target live video, select a word-by-word output mode or a sentence-by-sentence output mode, and a single-line output mode or a double-line output mode; The word-by-word output mode displays all intermediate results of the target subtitle transcription; the sentence-by-sentence output mode displays the final result of the target subtitle transcription; The single-line output mode is a display mode of the target subtitles including only one line of subtitles; the double-line output mode is a display mode of the target subtitles including two lines of subtitles.

5. The method for displaying video subtitles according to claim 3, characterized in that: The adjusting and displaying the target subtitles of the target live video according to the display mode of the target subtitles includes: Preprocessing the initial subtitles by filtering sensitive words in the subtitles according to the display mode of the target subtitles to obtain preprocessed subtitles; Performing standardization processing on the pre-processed subtitles to remove subtitle interference factors, so as to obtain standardized subtitles; Intelligent sentence segmentation is performed on the standardized subtitles to obtain target subtitles for the target live video.

6. The method for displaying video subtitles according to claim 5, characterized in that: When the selected target subtitle display mode is balanced subtitle output mode or high-precision subtitle output mode; After preprocessing the initial subtitles to filter sensitive words in the target subtitle display mode to obtain the preprocessed subtitles, the method further includes: Performing subtitle correction detection on the preprocessed subtitles to obtain corrected subtitles.

7. A video subtitle display device, characterized in that: include: An acquisition module, used to acquire a target live video and target subtitles of the target live video; A first processing module, configured to select a display mode of a target subtitle that meets the current playback requirement of the target live video according to the current playback requirement of the user; The second processing module is used to adjust and display the target subtitles of the target live video according to the display mode of the target subtitles.

8. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps in the method for displaying video subtitles as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by the processor, the steps in the method for displaying video subtitles according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps in the method for displaying video subtitles as described in any one of claims 1 to 6.

Images