Video playback system, method, device, electronic device and storage medium

Abstract

The disclosed embodiments relate to a video playback system, method, apparatus, electronic device, and storage medium. The system includes a terminal and a server, wherein the terminal is communicatively connected to the server, wherein: the terminal is configured to send a target playback request to the server; the server is configured to determine the target video to be played as instructed by the target playback request; obtain the start playback time and dialogue segment corresponding to the video segment of the target video; wherein the start playback time corresponding to the video segment is the time when the video segment starts playing in the target video; return the start playback time and the dialogue segment to the terminal; the terminal is further configured to present at least part of the text in the dialogue segment; and if a playback operation corresponding to the part of the text is detected, play the target video starting from the start playback time. This solution can improve the efficiency of generating video segments.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a video playback system, method, device, electronic device, and storage medium. Background Art

[0002] As society accelerates, short videos are becoming increasingly popular. Many short videos are remixes of classic clips from longer videos. In other words, a video can be thought of as a series of connected video clips. In existing technology, video segmentation is primarily done manually by video creators, who then write the corresponding presentation text (e.g., titles for the video clips).

[0003] However, the above method of dividing a video into video segments has a high creation cost and low efficiency. Summary of the Invention

[0004] In view of this, in order to solve some or all of the above technical problems, the embodiments of the present disclosure provide a video playback system, method, device, electronic device and storage medium.

[0005] In a first aspect, an embodiment of the present disclosure provides a video playback system, comprising a terminal and a server, wherein the terminal is communicatively connected to the server, wherein:

[0006] The terminal is configured to: send a target playback request to the server;

[0007] The server is configured to: determine the target video to be played as instructed by the target playback request; obtain a start playback time and a dialogue segment corresponding to a video segment of the target video; wherein the start playback time corresponding to the video segment is the time when the video segment starts playing in the target video; and return the start playback time and the dialogue segment to the terminal;

[0008] The terminal is further configured to: present at least part of the text in the dialogue segment; and if a playback operation corresponding to the part of the text is detected, play the target video starting from the start playback time.

[0009] Optionally, in the system of any embodiment of the present disclosure, the server is further configured to:

[0010] Dividing the video lines of the target video to obtain a first line segment set;

[0011] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0012] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0013] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0014] Optionally, in the system of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0015] The above server is specifically configured as follows:

[0016] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0017] Select the target number of results from the calculated results in descending order;

[0018] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0019] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0020] Determine the adjacent candidate segment as a new candidate segment;

[0021] From the calculated results that have not been selected, select the result with the largest value;

[0022] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0023] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0024] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0025] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0026] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0027] Optionally, in the system of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0028] The above server is also configured as follows:

[0029] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0030] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0031] Optionally, in the system of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0032] Optionally, in the system of any embodiment of the present disclosure, the server is specifically configured to:

[0033] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0034] The second precondition includes at least one of the following:

[0035] The number of views of the target video is greater than or equal to the preset view threshold;

[0036] The playback duration of the target video is greater than or equal to the preset playback duration.

[0037] Optionally, in the system of any embodiment of the present disclosure, the terminal is specifically configured to:

[0038] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0039] Optionally, in the system of any embodiment of the present disclosure, the terminal is specifically configured to:

[0040] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the corresponding dialogue clip; and

[0041] The terminal is further configured to:

[0042] If a click operation on the cover is detected, it is determined that a play operation corresponding to the partial text is detected.

[0043] In a second aspect, an embodiment of the present disclosure provides a video playback method, which is applied to a terminal and includes:

[0044] Sending a target playback request to a server, wherein the server is in communication with the terminal;

[0045] Receive the start playback time and the dialogue segment of the video segment of the target video indicated by the target playback request, which are returned by the server; wherein the start playback time of the video segment is the time when the video segment starts playing in the target video;

[0046] Presenting at least part of the text in the above dialogue fragment;

[0047] If a playback operation corresponding to the above-mentioned partial text is detected, the above-mentioned target video is played starting from the above-mentioned start playback time.

[0048] Optionally, in the method of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0049] Dividing the video lines of the target video to obtain a first line segment set;

[0050] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0051] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0052] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0053] Optionally, in the method of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0054] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0055] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0056] Select the target number of results from the calculated results in descending order;

[0057] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0058] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0059] Determine the adjacent candidate segment as a new candidate segment;

[0060] From the calculated results that have not been selected, select the result with the largest value;

[0061] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0062] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0063] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0064] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0065] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0066] Optionally, in the method of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0067] The above text is determined through the following steps:

[0068] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0069] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0070] Optionally, in the method of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0071] Optionally, in the method of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0072] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0073] The second precondition includes at least one of the following:

[0074] The number of views of the target video is greater than or equal to the preset view threshold;

[0075] The playback duration of the target video is greater than or equal to the preset playback duration.

[0076] Optionally, in the method of any embodiment of the present disclosure, presenting at least part of the text in the dialogue segment includes:

[0077] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0078] Optionally, in the method of any embodiment of the present disclosure, presenting at least part of the text in the dialogue segment as the title of the corresponding video segment includes:

[0079] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the dialogue clip; and

[0080] Before the above-mentioned if a playback operation corresponding to the above-mentioned part of the text is detected, the above-mentioned method further includes:

[0081] If a click operation on the cover is detected, it is determined that a play operation corresponding to the partial text is detected.

[0082] Optionally, in the method of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0083] In a third aspect, an embodiment of the present disclosure provides a video playback method, which is applied to a server and includes:

[0084] Receiving a target playback request sent by a terminal, wherein the terminal is in communication with the server;

[0085] Determine the target video to be played as instructed by the target playback request;

[0086] Obtaining the start playback time and dialogue segment corresponding to the video segment of the target video; wherein the start playback time corresponding to the video segment is: the time when the video segment starts playing in the target video;

[0087] The starting playback time and the dialogue segment are returned to the terminal so that the terminal presents at least part of the text in the dialogue segment, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time.

[0088] Optionally, in the method of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0089] Dividing the video lines of the target video to obtain a first line segment set;

[0090] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0091] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0092] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0093] Optionally, in the method of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0094] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0095] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0096] Select the target number of results from the calculated results in descending order;

[0097] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0098] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0099] Determine the adjacent candidate segment as a new candidate segment;

[0100] From the calculated results that have not been selected, select the result with the largest value;

[0101] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0102] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0103] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0104] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0105] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0106] Optionally, in the method of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0107] The above text is determined through the following steps:

[0108] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0109] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0110] Optionally, in the method of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0111] Optionally, in the method of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0112] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0113] The second precondition includes at least one of the following:

[0114] The number of views of the target video is greater than or equal to the preset view threshold;

[0115] The playback duration of the target video is greater than or equal to the preset playback duration.

[0116] Optionally, in the method of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0117] In a fourth aspect, an embodiment of the present disclosure provides a video playback device, which is provided in a terminal and includes:

[0118] a sending unit configured to send a target playback request to a server, wherein the server is in communication with the terminal;

[0119] The first receiving unit is configured to receive the start playback time and the dialogue segment of the video segment of the target video indicated by the target playback request, which are returned by the server; wherein the start playback time of the video segment is the time when the video segment starts playing in the target video;

[0120] a presenting unit configured to present at least part of the text in the dialogue segment;

[0121] The playback unit is configured to play the target video starting from the start playback time if a playback operation corresponding to the above-mentioned part of the text is detected.

[0122] Optionally, in the device of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0123] Dividing the video lines of the target video to obtain a first line segment set;

[0124] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0125] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0126] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0127] Optionally, in the device of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0128] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0129] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0130] Select the target number of results from the calculated results in descending order;

[0131] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0132] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0133] Determine the adjacent candidate segment as a new candidate segment;

[0134] From the calculated results that have not been selected, select the result with the largest value;

[0135] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0136] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0137] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0138] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0139] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0140] Optionally, in the apparatus of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0141] The above text is determined through the following steps:

[0142] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0143] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0144] Optionally, in the device of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0145] Optionally, in the device of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0146] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0147] The second precondition includes at least one of the following:

[0148] The number of views of the target video is greater than or equal to the preset view threshold;

[0149] The playback duration of the target video is greater than or equal to the preset playback duration.

[0150] Optionally, in the apparatus of any embodiment of the present disclosure, the presenting unit is further configured to:

[0151] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0152] Optionally, in the apparatus of any embodiment of the present disclosure, the presenting unit is further configured to:

[0153] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the dialogue clip; and

[0154] The above device also includes:

[0155] The first determining unit is configured to determine that a play operation corresponding to the above-mentioned part of the text is detected if a click operation on the above-mentioned cover is detected.

[0156] Optionally, in the device of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0157] In a fifth aspect, an embodiment of the present disclosure provides a video playback device, which is provided on a server and includes:

[0158] a second receiving unit configured to receive a target playback request sent by a terminal, wherein the terminal is communicatively connected to the server;

[0159] A second determining unit is configured to determine a target video to be played as instructed by the target playback request;

[0160] The acquisition unit is configured to acquire the start playback time and the dialogue segment corresponding to the video segment of the target video; wherein the start playback time corresponding to the video segment is: the time when the video segment starts to play in the target video;

[0161] The return unit is configured to return the above-mentioned starting playback time and the above-mentioned dialogue segment to the above-mentioned terminal, so that the above-mentioned terminal presents at least part of the text in the above-mentioned dialogue segment, and when a playback operation corresponding to the above-mentioned part of the text is detected, the above-mentioned target video is played from the above-mentioned starting playback time.

[0162] Optionally, in the device of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0163] Dividing the video lines of the target video to obtain a first line segment set;

[0164] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0165] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0166] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0167] Optionally, in the device of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0168] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0169] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0170] Select the target number of results from the calculated results in descending order;

[0171] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0172] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0173] Determine the adjacent candidate segment as a new candidate segment;

[0174] From the calculated results that have not been selected, select the result with the largest value;

[0175] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0176] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0177] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0178] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0179] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0180] Optionally, in the apparatus of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0181] The above text is determined through the following steps:

[0182] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0183] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0184] Optionally, in the device of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0185] Optionally, in the device of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0186] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0187] The second precondition includes at least one of the following:

[0188] The number of views of the target video is greater than or equal to the preset view threshold;

[0189] The playback duration of the target video is greater than or equal to the preset playback duration.

[0190] Optionally, in the device of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0191] In a sixth aspect, an embodiment of the present disclosure provides an electronic device, including:

[0192] memory for storing computer programs;

[0193] The processor is used to execute the computer program stored in the above-mentioned memory, and when the above-mentioned computer program is executed, the method of any embodiment of the video playback method of the second aspect or the third aspect of the present disclosure is implemented.

[0194] In a seventh aspect, an embodiment of the present disclosure provides a computer-readable storage medium, and when the computer program is executed by a processor, it implements the method of any embodiment of the video playback method of the second aspect or the third aspect mentioned above.

[0195] In an eighth aspect, an embodiment of the present disclosure provides a computer program comprising a computer-readable code, which, when executed on a device, enables a processor in the device to execute instructions for implementing each step of a method according to any embodiment of the video playback method of the second or third aspect described above.

[0196] The video playback system provided by the embodiment of the present disclosure includes a terminal and a server, wherein the terminal is communicatively connected to the server, wherein: the terminal is configured to: send a target playback request to the server; the server is configured to: determine the target video to be played indicated by the target playback request; obtain the starting playback time and the dialogue segment corresponding to the video segment of the target video; wherein the starting playback time corresponding to the video segment is: the time when the video segment starts to play in the target video; return the starting playback time and the dialogue segment to the terminal; the terminal is further configured to: present at least part of the text in the dialogue segment; if a playback operation corresponding to the part of the text is detected, then play the target video from the starting playback time. According to this solution, at least part of the text in the dialogue segment is presented by the terminal, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time returned by the server, thereby achieving the playback of the video segment and improving the efficiency of generating the video segment.

[0197] The video playback method applied to a terminal provided by the embodiment of the present disclosure obtains decrypted resource information, wherein, By this solution, by sending a target playback request to the server, wherein the server is in communication connection with the terminal, and then, receiving the starting playback time and the dialogue segment corresponding to the video segment of the target video indicated by the target playback request returned by the server; wherein, the starting playback time corresponding to the video segment is: the time when the video segment starts to play in the target video, and then, at least part of the text in the dialogue segment is presented, and then, if a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time. By this solution, at least part of the text in the dialogue segment is presented by the terminal, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time returned by the server, thereby realizing the playback of the video segment and improving the efficiency of generating the video segment.

[0198] The video playback method applied to the server provided by the embodiment of the present disclosure receives a target playback request sent by a terminal, wherein the terminal is in communication with the server, and then determines the target video indicated by the target playback request, and then obtains the starting playback time and the dialogue segment corresponding to the video segment of the target video; wherein the starting playback time corresponding to the video segment is: the time when the video segment starts to play in the target video, and then returns the starting playback time and the dialogue segment to the terminal, so that the terminal presents at least part of the text in the dialogue segment, and when a playback operation corresponding to the part of the text is detected, the target video starts to play from the starting playback time. According to this solution, at least part of the text in the dialogue segment is presented by the terminal, and when a playback operation corresponding to the part of the text is detected, the target video starts to play from the starting playback time returned by the server, thereby realizing the playback of the video segment and improving the efficiency of generating the video segment. BRIEF DESCRIPTION OF THE DRAWINGS

[0199] Figure 1 An interactive schematic diagram of a video playback system provided by an embodiment of the present disclosure;

[0200] Figure 2 An interactive schematic diagram of another video playback system provided by an embodiment of the present disclosure;

[0201] Figure 3 A schematic diagram of a flow chart of a video playback method applied to a terminal provided in an embodiment of the present disclosure;

[0202] Figure 4 A flowchart of a video playback method applied to a server provided by an embodiment of the present disclosure;

[0203] Figure 5 A schematic structural diagram of a video playback device provided in a terminal according to an embodiment of the present disclosure;

[0204] Figure 6 A schematic diagram of the structure of a video playback device provided on a server side according to an embodiment of the present disclosure;

[0205] Figure 7 A schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0206] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0207] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish objects such as different steps, devices or modules, and neither represent any specific technical meaning nor indicate the logical order between them.

[0208] It should also be understood that in this embodiment, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0209] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0210] In addition, the term "and / or" in this disclosure is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this disclosure generally indicates that the related objects are in an "or" relationship.

[0211] It should also be understood that the description of the various embodiments in this disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced with each other. For the sake of brevity, they will not be described one by one.

[0212] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0213] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the above-mentioned technologies, methods, and equipment should be considered part of the specification.

[0214] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0215] It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other. To facilitate understanding of the embodiments of the present disclosure, the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. Obviously, the embodiments described are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0216] Figure 1 This is a schematic diagram of an interaction of a video playback system provided by an embodiment of the present disclosure, such as Figure 1As shown, the system includes a terminal and a server. The terminal is in communication connection with the server.

[0217] The terminal is configured to: send a target playback request to the server;

[0218] The server is configured to: determine the target video to be played as instructed by the target playback request; obtain a start playback time and a dialogue segment corresponding to a video segment of the target video; wherein the start playback time corresponding to the video segment is the time when the video segment starts playing in the target video; and return the start playback time and the dialogue segment to the terminal;

[0219] The terminal is further configured to: present at least part of the text in the dialogue segment; and if a playback operation corresponding to the part of the text is detected, play the target video starting from the start playback time.

[0220] like Figure 1 As shown, in step 101, the terminal sends a target playback request to the server.

[0221] In this embodiment, the terminal may send a target playback request to the server.

[0222] The target playback request may be used to instruct the playback of a video (ie, the target video described later).

[0223] In step 102, the server determines the target video to be played as instructed by the target playback request.

[0224] In this embodiment, the server may determine the target video to be played as instructed by the target playback request.

[0225] Optionally, after receiving the target play request sent by the terminal, the server may send video data (eg, streaming media data) of the video indicated by the target play request to the terminal, so that the terminal plays the video indicated by the target play request.

[0226] In step 103, the server obtains the start playing time and the dialogue segment corresponding to the video segment of the target video.

[0227] In this embodiment, the server may obtain the start playing time and the dialogue segment corresponding to the video segment of the target video.

[0228] The start playback time corresponding to the video clip is: the time when the video clip starts to play in the above target video.

[0229] The video clips may be any one or more video clips in the target video. When the video clips are multiple video clips in the target video, the multiple video clips may be connected end to end.

[0230] The above-mentioned dialogue clips may be the dialogues contained in the video clips.

[0231] In step 104, the start playing time and the dialogue segment are returned to the terminal.

[0232] In this embodiment, the server may return the start playing time and the dialogue segment to the terminal.

[0233] In step 105, the terminal presents at least part of the text in the dialogue segment.

[0234] In this embodiment, the terminal may present at least part of the text in the dialogue segment.

[0235] The partial text may be any partial text in the dialogue segment. For example, the partial text may be any sentence in the dialogue segment.

[0236] Optionally, the terminal may also present all the text in the dialogue segment.

[0237] In addition, in some cases, if the number of characters of at least a portion of the text presented is greater than or equal to a preset character count threshold, the terminal may present the at least a portion of the text in a scrolling presentation manner.

[0238] In some cases, the terminal may set the transparency of the presented portion of text to reduce the impact of the presentation of the portion of text on other operations performed by the user (eg, viewing a target video).

[0239] In some optional implementations of this embodiment, the terminal may perform step 105 in the following manner: presenting at least part of the text in the dialogue segment as the title of the corresponding video segment.

[0240] It is understood that during the process of generating a video segment, it is usually necessary to determine a title for the generated video segment and present the title to the user so that they can understand the general content of the video segment. In the above optional implementation, at least part of the text in the dialogue segment can be used as the title of the corresponding video segment, which can further improve the efficiency of video segment generation.

[0241] In some optional implementations of this embodiment, or in some application scenarios of the above optional implementations, the terminal may perform step 105 in the following manner:

[0242] Renders the cover of the video clip.

[0243] The cover includes the title of the video clip, and the title includes at least part of the text in the corresponding dialogue clip.

[0244] In step 106, if a play operation corresponding to the partial text is detected, the terminal starts playing the target video from the start play time.

[0245] In this embodiment, if a play operation corresponding to the above-mentioned partial text is detected, the above-mentioned target video is played starting from the above-mentioned start play time.

[0246] The playback operation corresponding to the above part of the text may be a click operation on the above part of the text.

[0247] Here, before the terminal starts playing the target video from the start playback moment, the server may start sending the video clip described in step 103 to the terminal, or the server may also send the video clip described in step 103 to the terminal so that the terminal can play the target video from the start playback moment. The video clip may be sent before or after the playback operation is detected. In some cases, if the video clip is sent after the playback operation is detected, and the terminal is playing the target video before the playback operation corresponding to the partial text is detected, then the server may stop sending other video clips of the target video except the video clip described in step 103 to the terminal.

[0248] In some optional implementations of this embodiment, when the terminal executes step 105 by presenting the cover of the video clip, the terminal may also execute step 106 in the following manner: if a click operation on the cover is detected, it is determined that a playback operation corresponding to the partial text is detected.

[0249] It can be understood that in the above optional implementation method, the user can play the above video clip by clicking on the above cover.

[0250] In some cases, if the terminal detects that the video clip has been played during the playback of the target video, the terminal can continue playing the target video from the moment the video clip was terminated, or play other videos or video clips through user selection.

[0251] The video playback system provided by the embodiment of the present disclosure includes a terminal and a server, wherein the terminal is communicatively connected to the server, wherein: the terminal is configured to: send a target playback request to the server; the server is configured to: determine the target video to be played indicated by the target playback request; obtain the starting playback time and the dialogue segment corresponding to the video segment of the target video; wherein the starting playback time corresponding to the video segment is: the time when the video segment starts to play in the target video; return the starting playback time and the dialogue segment to the terminal; the terminal is further configured to: present at least part of the text in the dialogue segment; if a playback operation corresponding to the part of the text is detected, then play the target video from the starting playback time. According to this solution, at least part of the text in the dialogue segment is presented by the terminal, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time returned by the server, thereby achieving the playback of the video segment and improving the efficiency of generating the video segment.

[0252] Figure 2 This is another interactive diagram of a video playback system provided by an embodiment of the present disclosure, such as Figure 2 As shown, the system includes a terminal and a server. The terminal is in communication connection with the server.

[0253] The above-mentioned server is configured to: divide the video lines of the target video to obtain a first line segment set; determine the number of barrages and the number of drag-and-play times corresponding to the line segments in the above-mentioned first line segment set; generate a second line segment set based on the above-mentioned first line segment set, the above-mentioned number of barrages and the above-mentioned number of drag-and-play times, wherein the number of line segments in the above-mentioned second line segment set is less than the number of line segments in the above-mentioned first line segment set; determine the starting playback time corresponding to the video segment including the line segment in the above-mentioned second line segment set.

[0254] The terminal is configured to: send a target playback request to the server;

[0255] The server is configured to: determine the target video to be played as instructed by the target playback request; obtain a start playback time and a dialogue segment corresponding to a video segment of the target video; wherein the start playback time corresponding to the video segment is the time when the video segment starts playing in the target video; and return the start playback time and the dialogue segment to the terminal;

[0256] The terminal is further configured to: present at least part of the text in the dialogue segment; if a playback operation corresponding to the part of the text is detected, start playing from the start time.

[0257] like Figure 2As shown, in step 201, the server divides the video lines of the target video to obtain a first line segment set.

[0258] In this embodiment, the server may divide the video lines of the target video to obtain a first line segment set.

[0259] Among them, the video lines are the lines contained in the target video.

[0260] The first dialogue segment set is the result of dividing the video dialogues of the target video.

[0261] Each dialogue segment in the first dialogue segment set may contain one or more dialogue sentences, and each dialogue sentence may be a single sentence.

[0262] In step 202, the server determines the number of bullet comments and the number of drag-and-play times corresponding to the speech segments in the first speech segment set.

[0263] In this embodiment, the server may determine the number of bullet comments and the number of drag-and-play times corresponding to the speech segments in the first speech segment set.

[0264] The number of barrages corresponding to a dialogue segment may be the number of barrages sent for a video segment containing the dialogue segment.

[0265] The number of drag-and-drop playback times corresponding to the dialogue segment may be the number of times the video segment containing the dialogue segment is played in a drag-and-drop manner.

[0266] The above-mentioned number of bullet screens and number of drag and play times can be obtained via a terminal (including the above-mentioned terminal), and then sent by the terminal to the above-mentioned server and stored in the server or an electronic device connected to the server.

[0267] In step 203, the server generates a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times.

[0268] In this embodiment, the server may generate a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag-and-play times.

[0269] Among them, the number of speech segments in the above-mentioned second speech segment set is less than the number of speech segments in the above-mentioned first speech segment set.

[0270] As an example, the server may determine, in the first dialogue segment set, a set of dialogue segments whose number of barrages is greater than a first preset value and whose number of drag and play times is greater than a second preset value as the second dialogue segment set.

[0271] In some optional implementations of this embodiment, the first dialogue segment set is a dialogue segment sequence, and the number of dialogue segments in the second dialogue segment set is a target number.

[0272] The target number may be a predetermined value, or may be the product of the number of speech segments in the first speech segment set and a preset percentage.

[0273] On this basis, the server can also use the following method to determine the second dialogue segment set:

[0274] Step 1: Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each dialogue segment in the above dialogue segment sequence.

[0275] The weights of the number of bullet comments and the number of drag and play times can be two values ​​that can be set separately.

[0276] Step 2: Select the target number of results from the calculated results in descending order.

[0277] Step 3: Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set.

[0278] Since, in step 1, a result (i.e., the weighted summation result) is obtained for each speech segment in the speech segment sequence, there is a one-to-one correspondence between the speech segments in the speech segment sequence and the results. Based on this correspondence, the speech segments corresponding to the target number of results can be determined.

[0279] Step 4: If the candidate segment set includes adjacent candidate segments, perform the following determination steps (including sub-steps 1, 2, 3, and 4):

[0280] Sub-step 1: determine the adjacent candidate segment as a new candidate segment.

[0281] Sub-step 2: Select the result with the largest value from the calculated results that have not been selected.

[0282] Sub-step three: determine the dialogue segment corresponding to the selected result with the largest value as a new candidate segment.

[0283] Sub-step four: updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set.

[0284] Step 5: If the updated candidate segment set includes adjacent candidate segments, the above determination step is performed based on the updated candidate segment set.

[0285] Step 6: If the candidate segment set does not include adjacent candidate segments, the candidate segment set that does not include adjacent candidate segments is determined as the second dialogue segment set.

[0286] In the above optional implementation, the adjacent candidate segments are two adjacent dialogue segments in the above dialogue segment sequence.

[0287] It can be understood that in the above optional implementation, the generated second dialogue segment set does not include adjacent dialogue segments. Therefore, when the target video is divided into video segments, the divided video segments also do not include adjacent video segments.

[0288] In some optional implementations of this embodiment, the dialogue segment includes at least one dialogue sentence.

[0289] On this basis, the server can use the following method to determine the above part of the text:

[0290] First, obtain a set of preset lines.

[0291] Among them, the playback volume and / or comment volume of the dialogue sentences in the above-mentioned preset dialogue sentence set meets the first preset condition.

[0292] Afterwards, for each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0293] As an example, the speech sentence in the speech segment that is most similar to the speech sentence in the above-mentioned preset speech sentence set can be used as the above-mentioned partial text for presentation in the speech segment.

[0294] As another example, for each dialogue sentence included in the dialogue segment, the weighted sum of the similarities between the dialogue sentence and each dialogue sentence in the above-mentioned preset dialogue sentence set can be calculated, so that the dialogue sentence corresponding to the largest weighted sum result can be used as the above-mentioned partial text for presentation in the dialogue segment.

[0295] It can be understood that the above-mentioned preset dialogue sentence set can be used as a high-popularity dialogue library. In this way, by calculating the similarity between each dialogue segment in the second dialogue segment set and the dialogue sentence in the preset dialogue sentence set, the above-mentioned partial text can be determined, which can increase the probability of the user performing the playback operation, thereby increasing the playback volume of the video segment.

[0296] In some application scenarios where the above options are ready-made rooms or clocks, the above first preset condition includes: the weighted sum of the number of plays and the number of comments on the target line is greater than or equal to a preset value.

[0297] Optionally, the first preset condition may also include at least one of the following:

[0298] The first item is that the playback volume of the target line is greater than or equal to a preset first value.

[0299] The second item is that the number of comments on the target line is greater than or equal to a preset second value.

[0300] The third item is that the number of playbacks of the target line is greater than or equal to a preset third value, and the number of comments on the target line is greater than or equal to a preset fourth value.

[0301] In some optional implementations of this embodiment, if the target video meets the second preset condition, the server may generate a second set of dialogue segments based on the first set of dialogue segments, the number of barrages, and the number of drag and play times; if the target video does not meet the second preset condition, the server will not generate a second set of dialogue segments.

[0302] The second precondition includes at least one of the following:

[0303] The playback volume of the target video is greater than or equal to the preset playback volume threshold.

[0304] The playback duration of the target video is greater than or equal to the preset playback duration.

[0305] It is understood that in the above optional implementation, the timing of generating the second dialogue segment set can be determined based on the number of views and / or the duration of the target video. For videos that do not meet the second preset condition, there is no need to generate their video segments, which can save computing resources on the server side.

[0306] In step 204, the server determines the start playback time corresponding to the video segment including the speech segment in the second speech segment set.

[0307] In this embodiment, the server may determine the start playback time corresponding to the video segment including each dialogue segment in the second dialogue segment set.

[0308] The start playback time corresponding to the video clip is: the time when the video clip starts to play in the above target video.

[0309] In step 205, the terminal sends a target playback request to the server.

[0310] In this embodiment, the terminal may send a target playback request to the server.

[0311] In this embodiment, the execution method of step 205 can refer to the above-mentioned step 101 and will not be repeated here.

[0312] In step 206, the server determines the target video to be played as instructed by the target play request.

[0313] In this embodiment, the server may determine the target video to be played as instructed by the target playback request.

[0314] In this embodiment, the execution method of step 206 can refer to the above-mentioned step 102 and will not be repeated here.

[0315] In step 207, the start playing time and the dialogue segment corresponding to the video segment of the target video are obtained.

[0316] In this embodiment, the server may obtain the start playing time and the dialogue segment corresponding to the video segment of the target video.

[0317] The start playback time corresponding to the video clip is: the time when the video clip starts to play in the above target video.

[0318] The video clip described in step 207 may be a video clip containing any dialogue clip in the second dialogue clip set.

[0319] In this embodiment, the execution method of step 207 can refer to the above-mentioned step 103 and will not be repeated here.

[0320] In step 208, the server returns the start playing time and the dialogue segment to the terminal.

[0321] In this embodiment, the server may return the start playing time and the dialogue segment to the terminal.

[0322] In this embodiment, the execution method of step 208 can refer to the above-mentioned step 104 and will not be repeated here.

[0323] In step 209, the terminal presents at least part of the text in the dialogue segment.

[0324] In this embodiment, the terminal may present at least part of the text in the dialogue segment.

[0325] In this embodiment, the execution method of step 209 can refer to the above-mentioned step 105 and will not be repeated here.

[0326] In step 210, if a play operation corresponding to the partial text is detected, the terminal starts playing the target video from the start play time.

[0327] In this embodiment, if a play operation corresponding to the partial text is detected, the terminal may play the target video starting from the start play time.

[0328] In this embodiment, the execution method of step 210 can refer to the above-mentioned step 106 and will not be repeated here.

[0329] The video playback system provided by the embodiment of the present disclosure generates a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag-and-play times, and then plays video segments containing the dialogue segments in the second dialogue segment set. In this way, the number of barrages and the number of drag-and-play times can be used to assist in determining how to divide the target video into video segments, thereby increasing the user's interest in the played video segments and improving the completion rate of the video segments.

[0330] As an application scenario of this embodiment, this embodiment is exemplarily described below. However, it should be noted that the embodiments of the present disclosure may have the features described below, but the following description does not constitute a limitation on the scope of protection of the embodiments of the present disclosure.

[0331] In this application scenario, first, prepare some hot lines (that is, the above-mentioned preset line sentence set) in the video (that is, the target video mentioned above). Then, divide the video. The division rule is: each video clip contains a hot line, and all video clips connected end to end are equivalent to the original video. The title of the divided video clip is the hot lines contained in the video clip (that is, at least part of the above-mentioned text). When the user plays the video (that is, the target video), all the divided titles of the video can be listed in the player. When the user clicks on a title, the corresponding video clip starts playing.

[0332] Specifically, the following method can be used to divide the dialogue segments:

[0333] First, a database of highly popular lines (i.e., the aforementioned set of preset lines) is established. This database can be purchased commercially, manually extracted and annotated, or generated by artificial intelligence.

[0334] Afterwards, when the long video (i.e., the target video) is put online, it will not be divided first. After waiting for it to play for a period of time or the playback volume reaches a certain threshold, the long video will be divided into video segments. During the long video playback stage, the terminal records all the time offset points of the barrage launch and the time offset points of the user dragging and playing, and transmits the records to the server for storage. The server determines the number of barrages corresponding to the dialogue segment based on the time offset point of the barrage launch; and determines the number of drag-and-play times corresponding to the dialogue segment based on the time offset point of the user dragging and playing.

[0335] Then, the server can treat the continuous lines as a line segment (that is, the line segment in the first line segment set mentioned above) and calculate the popularity of each line segment in the long video. The calculation formula is:

[0336] Hot = λ × A + (1-λ) × B

[0337] Where λ is a predetermined weight value greater than 0 and less than 1. A represents the number of comments corresponding to the speech segment. B represents the number of drag and drop plays corresponding to the speech segment. Hot represents the popularity of the speech segment.

[0338] Then, the k (that is, the target number) most popular segments are selected from the obtained segments (that is, the first set of segments mentioned above). If two selected segments are adjacent, they are merged into one segment, and the most popular segment is selected from the unselected segments.

[0339] Thus, k segments of dialogue can be picked out (ie, the second set of dialogue segments mentioned above).

[0340] Next, for each of the k segments, the similarity of each line in the segment is compared with each line in the high-popularity lines database, and the line with the highest similarity is used as the title of the video clip containing the segment.

[0341] Specifically, in the above application scenario, the server can be responsible for generating video clips, while the terminal can be responsible for requesting data and controlling video playback. The server and terminal can be software or hardware, respectively.

[0342] On the server side, N popular lines of the target video (i.e., the preset lines set) can be prepared in advance. The lines are numbered as line1, line2, line3, etc. according to the time they appear in the target video. n After that, the target video is logically divided into N video clips, and the video clips are numbered as clip1, clip2, clip3...clip according to the start time of playback. n The division rule is: clip nMust contain line n , clip n The end time (ie clip n+1 The starting playback time of line n The end time and line n+1 The midpoint of the start playback time of the video clip is the time when the video clip starts playing in the target video. Then, the title of each video clip is recorded as the hottest line contained in the video clip, that is, the clip n The title record is line n The title and the start playing time of each video segment are combined into auxiliary information, and the auxiliary information is stored on the server together with the target video.

[0343] On the terminal side, you can request the target video and its corresponding auxiliary information from the server. After obtaining the auxiliary information, the terminal parses the auxiliary information to extract the start time and title of each video segment. The player then displays all video segment titles for the user to click. The player starts playing from the start time of the target video. If the user clicks on a video segment title at any time, the player jumps to the start time of that video segment and starts playing.

[0344] In the above application scenario, using highly popular lines to divide videos can make each video segment have a certain popularity, or even obtain classic video segments. Furthermore, in the above application scenario, using highly popular lines as titles to divide videos can increase the user's click-through rate on the video segments.

[0345] Figure 3 A flow chart of a video playback method applied to a terminal provided by an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the method specifically includes:

[0346] 301. Send a target playback request to the server.

[0347] In this embodiment, the terminal may send a target playback request to the server.

[0348] Wherein, the above-mentioned server is communicatively connected with the above-mentioned terminal.

[0349] 302. Receive the start playback time and dialogue segment corresponding to the video segment of the target video indicated by the target playback request and returned by the server.

[0350] In this embodiment, the terminal may receive the start playback time and the dialogue segment corresponding to the video segment of the target video indicated by the target playback request and returned by the server.

[0351] The start playback time corresponding to the video clip is: the time when the video clip starts to play in the above target video.

[0352] 303. Present at least part of the text in the above dialogue segment.

[0353] In this embodiment, the terminal may present at least part of the text in the dialogue segment.

[0354] 304. If a play operation corresponding to the partial text is detected, the target video is played starting from the start play time.

[0355] In this embodiment, if a play operation corresponding to the above part of the text is detected, the terminal can start playing the target video from the start play time.

[0356] The video playback method applied to a terminal provided by the embodiment of the present disclosure obtains decrypted resource information, wherein, By this solution, by sending a target playback request to the server, wherein the server is in communication connection with the terminal, and then, receiving the starting playback time and the dialogue segment corresponding to the video segment of the target video indicated by the target playback request returned by the server; wherein, the starting playback time corresponding to the video segment is: the time when the video segment starts to play in the target video, and then, at least part of the text in the dialogue segment is presented, and then, if a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time. By this solution, at least part of the text in the dialogue segment is presented by the terminal, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time returned by the server, thereby realizing the playback of the video segment and improving the efficiency of generating the video segment.

[0357] In some optional implementations of this embodiment, the start playback time is determined by the following steps:

[0358] Dividing the video lines of the target video to obtain a first line segment set;

[0359] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0360] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0361] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0362] In some optional implementations of this embodiment, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0363] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0364] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0365] Select the target number of results from the calculated results in descending order;

[0366] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0367] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0368] Determine the adjacent candidate segment as a new candidate segment;

[0369] From the calculated results that have not been selected, select the result with the largest value;

[0370] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0371] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0372] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0373] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0374] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0375] In some optional implementations of this embodiment, the dialogue segment includes at least one dialogue sentence; and

[0376] The above text is determined through the following steps:

[0377] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0378] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0379] In some optional implementations of this embodiment, the first preset condition includes: the weighted sum of the number of plays and the number of comments on the target line is greater than or equal to a preset value.

[0380] In some optional implementations of this embodiment, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0381] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0382] The second precondition includes at least one of the following:

[0383] The number of views of the target video is greater than or equal to the preset view threshold;

[0384] The playback duration of the target video is greater than or equal to the preset playback duration.

[0385] In some optional implementations of this embodiment, presenting at least part of the text in the dialogue segment includes:

[0386] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0387] In some optional implementations of this embodiment, presenting at least part of the text in the dialogue segment as the title of the corresponding video segment includes:

[0388] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the dialogue clip; and

[0389] Before the above-mentioned if a playback operation corresponding to the above-mentioned part of the text is detected, the above-mentioned method further includes:

[0390] If a click operation on the cover is detected, it is determined that a play operation corresponding to the partial text is detected.

[0391] In some optional implementations of this embodiment, the starting playback time corresponding to the video clip is: the middle time between the times when the two dialogue clips start playing in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the video clip before the video clip in the above-mentioned target video.

[0392] It should be noted that, in addition to the above contents, this embodiment may also include the above Figure 1 or Figure 2 The technical features described in Figure 1 or Figure 2 The technical effects described in will not be repeated here.

[0393] Figure 4 A flow chart of a video playback method applied to a server provided by an embodiment of the present disclosure is shown as follows: Figure 4 As shown, the method specifically includes:

[0394] 401. Receive a target playback request sent by a terminal.

[0395] In this embodiment, the server may receive a target playback request sent by the terminal.

[0396] Wherein, the above-mentioned terminal is communicatively connected with the above-mentioned server.

[0397] 402. Determine the target video to be played as instructed by the target play request.

[0398] In this embodiment, the server may determine the target video to be played as instructed by the target playback request.

[0399] The decryption resource consumption of the video data in the video data set is different, and the decryption resource consumption represents the amount of resources consumed in decrypting the video data.

[0400] 403. Obtain the start playback time and dialogue segment corresponding to the video segment of the target video.

[0401] In this embodiment, the server may obtain the start playing time and the dialogue segment corresponding to the video segment of the target video.

[0402] The start playback time corresponding to the video clip is: the time when the video clip starts to play in the above target video.

[0403] 404. Return the start playback time and the dialogue segment to the terminal, so that the terminal presents at least part of the text in the dialogue segment, and starts playing the target video from the start playback time when a playback operation corresponding to the part of the text is detected.

[0404] In this embodiment, the server may return the start playback time and the dialogue segment to the terminal, so that the terminal may present at least part of the text in the dialogue segment, and upon detecting a playback operation corresponding to the part of the text, start playing the target video from the start playback time.

[0405] The video playback method applied to the server provided by the embodiment of the present disclosure receives a target playback request sent by a terminal, wherein the terminal is in communication with the server, and then determines the target video indicated by the target playback request, and then obtains the starting playback time and the dialogue segment corresponding to the video segment of the target video; wherein the starting playback time corresponding to the video segment is: the time when the video segment starts to play in the target video, and then returns the starting playback time and the dialogue segment to the terminal, so that the terminal presents at least part of the text in the dialogue segment, and when a playback operation corresponding to the part of the text is detected, the target video starts to play from the starting playback time. According to this solution, at least part of the text in the dialogue segment is presented by the terminal, and when a playback operation corresponding to the part of the text is detected, the target video starts to play from the starting playback time returned by the server, thereby realizing the playback of the video segment and improving the efficiency of generating the video segment.

[0406] In some optional implementations of this embodiment, the start playback time is determined by the following steps:

[0407] Dividing the video lines of the target video to obtain a first line segment set;

[0408] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0409] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0410] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0411] In some optional implementations of this embodiment, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0412] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0413] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0414] Select the target number of results from the calculated results in descending order;

[0415] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0416] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0417] Determine the adjacent candidate segment as a new candidate segment;

[0418] From the calculated results that have not been selected, select the result with the largest value;

[0419] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0420] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0421] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0422] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0423] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0424] In some optional implementations of this embodiment, the dialogue segment includes at least one dialogue sentence; and

[0425] The above text is determined through the following steps:

[0426] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0427] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0428] In some optional implementations of this embodiment, the first preset condition includes: the weighted sum of the number of plays and the number of comments on the target line is greater than or equal to a preset value.

[0429] In some optional implementations of this embodiment, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0430] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0431] The second precondition includes at least one of the following:

[0432] The number of views of the target video is greater than or equal to the preset view threshold;

[0433] The playback duration of the target video is greater than or equal to the preset playback duration.

[0434] In some optional implementations of this embodiment, the starting playback time corresponding to the video clip is: the middle time between the times when the two dialogue clips start playing in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the video clip before the video clip in the above-mentioned target video.

[0435] It should be noted that, in addition to the above contents, this embodiment may also include the above Figure 1 or Figure 2 The technical features described in Figure 1 or Figure 2 The technical effects described in will not be repeated here.

[0436] Figure 5 A schematic diagram of the structure of a video playback device provided in a terminal according to an embodiment of the present disclosure specifically includes:

[0437] The sending unit 501 is configured to send a target playback request to a server, wherein the server is in communication with the terminal;

[0438] The first receiving unit 502 is configured to receive the start playback time and the dialogue segment of the video segment of the target video indicated by the target playback request, which are returned by the server. The start playback time of the video segment is the time when the video segment starts playing in the target video.

[0439] A presenting unit 503 is configured to present at least part of the text in the dialogue segment;

[0440] The playback unit 504 is configured to play the target video starting from the start playback time if a playback operation corresponding to the partial text is detected.

[0441] Optionally, in the device of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0442] Dividing the video lines of the target video to obtain a first line segment set;

[0443] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0444] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0445] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0446] Optionally, in the device of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0447] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0448] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0449] Select the target number of results from the calculated results in descending order;

[0450] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0451] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0452] Determine the adjacent candidate segment as a new candidate segment;

[0453] From the calculated results that have not been selected, select the result with the largest value;

[0454] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0455] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0456] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0457] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0458] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0459] Optionally, in the apparatus of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0460] The above text is determined through the following steps:

[0461] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0462] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0463] Optionally, in the device of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0464] Optionally, in the device of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0465] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0466] The second precondition includes at least one of the following:

[0467] The number of views of the target video is greater than or equal to the preset view threshold;

[0468] The playback duration of the target video is greater than or equal to the preset playback duration.

[0469] Optionally, in the apparatus of any embodiment of the present disclosure, the presenting unit 503 is further configured to:

[0470] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0471] Optionally, in the apparatus of any embodiment of the present disclosure, the presenting unit 503 is further configured to:

[0472] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the dialogue clip; and

[0473] The above device also includes:

[0474] The first determining unit (not shown in the figure) is configured to determine that a play operation corresponding to the above-mentioned part of the text is detected if a click operation on the above-mentioned cover is detected.

[0475] Optionally, in the device of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0476] The video playback device provided in this embodiment can be as follows Figure 5 The video playback device shown in , can execute the following Figure 3 All steps of the video playback method in the Figure 3 For technical effects of the video playback method shown, please refer to Figure 3 For the sake of brevity, the relevant description will not be repeated here.

[0477] Figure 6 A schematic diagram of the structure of a video playback device provided on a server side according to an embodiment of the present disclosure specifically includes:

[0478] The second receiving unit 601 is configured to receive a target playback request sent by a terminal, wherein the terminal is in communication with the server;

[0479] The second determining unit 602 is configured to determine the target video to be played as instructed by the target playback request;

[0480] The acquisition unit 603 is configured to acquire the start playing time and the dialogue segment corresponding to the video segment of the target video; wherein the start playing time corresponding to the video segment is: the time when the video segment starts playing in the target video;

[0481] The return unit 604 is configured to return the above-mentioned starting playback time and the above-mentioned dialogue segment to the above-mentioned terminal, so that the above-mentioned terminal presents at least part of the text in the above-mentioned dialogue segment, and when a playback operation corresponding to the above-mentioned part of the text is detected, the above-mentioned target video is played from the above-mentioned starting playback time.

[0482] Optionally, in the device of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0483] Dividing the video lines of the target video to obtain a first line segment set;

[0484] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0485] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0486] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0487] Optionally, in the device of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0488] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0489] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0490] Select the target number of results from the calculated results in descending order;

[0491] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0492] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0493] Determine the adjacent candidate segment as a new candidate segment;

[0494] From the calculated results that have not been selected, select the result with the largest value;

[0495] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0496] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0497] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0498] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0499] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0500] Optionally, in the apparatus of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0501] The above text is determined through the following steps:

[0502] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0503] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0504] Optionally, in the device of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0505] Optionally, in the device of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0506] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0507] The second precondition includes at least one of the following:

[0508] The number of views of the target video is greater than or equal to the preset view threshold;

[0509] The playback duration of the target video is greater than or equal to the preset playback duration.

[0510] Optionally, in the device of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0511] The video playback device provided in this embodiment can be as follows Figure 6 The video playback device shown in , can execute the following Figure 3 All steps of the video playback method in the Figure 4 For technical effects of the video playback method shown, please refer to Figure 4 For the sake of brevity, the relevant description will not be repeated here.

[0512] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure is shown. Figure 7 The electronic device 700 shown includes: at least one processor 701, a memory 702, at least one network interface 704 and another user interface 703. The various components in the electronic device 700 are coupled together via a bus system 705. It is understood that the bus system 705 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 705 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 705 is not shown in FIG. Figure 7 Various buses are labeled as bus system 705.

[0513] The user interface 703 may include a display, a keyboard, or a pointing device (eg, a mouse, a trackball, a touchpad, or a touch screen).

[0514] It is understood that the memory 702 in the embodiment of the present disclosure may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 702 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0515] In some embodiments, the memory 702 stores the following elements, executable units, or data structures, or a subset thereof, or an extended set thereof: an operating system 7021 and application programs 7022 .

[0516] The operating system 7021 includes various system programs, such as a framework layer, a core library layer, and a driver layer, for implementing various basic services and handling hardware-based tasks. Application programs 7022 include various application programs, such as a media player and a browser, for implementing various application services. Programs implementing the methods of the embodiments of the present disclosure may be included in application programs 7022.

[0517] In this embodiment, the processor 701 is configured to execute the method steps provided in each method embodiment by calling a program or instruction stored in the memory 702 , specifically, a program or instruction stored in the application 7022 .

[0518] As an example, this may include:

[0519] Sending a target playback request to a server, wherein the server is in communication with the terminal;

[0520] Receive the start playback time and the dialogue segment of the video segment of the target video indicated by the target playback request, which are returned by the server; wherein the start playback time of the video segment is the time when the video segment starts playing in the target video;

[0521] Presenting at least part of the text in the above dialogue fragment;

[0522] If a playback operation corresponding to the above-mentioned partial text is detected, the above-mentioned target video is played starting from the above-mentioned start playback time.

[0523] Optionally, in the method of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0524] Dividing the video lines of the target video to obtain a first line segment set;

[0525] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0526] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0527] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0528] Optionally, in the method of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0529] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0530] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0531] Select the target number of results from the calculated results in descending order;

[0532] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0533] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0534] Determine the adjacent candidate segment as a new candidate segment;

[0535] From the calculated results that have not been selected, select the result with the largest value;

[0536] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0537] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0538] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0539] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0540] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0541] Optionally, in the method of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0542] The above text is determined through the following steps:

[0543] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0544] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0545] Optionally, in the method of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0546] Optionally, in the method of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0547] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0548] The second precondition includes at least one of the following:

[0549] The number of views of the target video is greater than or equal to the preset view threshold;

[0550] The playback duration of the target video is greater than or equal to the preset playback duration.

[0551] Optionally, in the method of any embodiment of the present disclosure, presenting at least part of the text in the dialogue segment includes:

[0552] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0553] Optionally, in the method of any embodiment of the present disclosure, presenting at least part of the text in the dialogue segment as the title of the corresponding video segment includes:

[0554] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the dialogue clip; and

[0555] Before the above-mentioned if a playback operation corresponding to the above-mentioned part of the text is detected, the above-mentioned method further includes:

[0556] If a click operation on the cover is detected, it is determined that a play operation corresponding to the partial text is detected.

[0557] Optionally, in the method of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0558] Or, as another example, it may also include:

[0559] Receiving a target playback request sent by a terminal, wherein the terminal is in communication with the server;

[0560] Determine the target video to be played as instructed by the target playback request;

[0561] Obtaining the start playback time and dialogue segment corresponding to the video segment of the target video; wherein the start playback time corresponding to the video segment is: the time when the video segment starts playing in the target video;

[0562] The starting playback time and the dialogue segment are returned to the terminal so that the terminal presents at least part of the text in the dialogue segment, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time.

[0563] Optionally, in the method of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0564] Dividing the video lines of the target video to obtain a first line segment set;

[0565] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0566] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0567] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0568] Optionally, in the method of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0569] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0570] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0571] Select the target number of results from the calculated results in descending order;

[0572] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0573] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0574] Determine the adjacent candidate segment as a new candidate segment;

[0575] From the calculated results that have not been selected, select the result with the largest value;

[0576] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0577] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0578] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0579] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0580] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0581] Optionally, in the method of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0582] The above text is determined through the following steps:

[0583] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0584] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0585] Optionally, in the method of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0586] Optionally, in the method of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0587] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0588] The second precondition includes at least one of the following:

[0589] The number of views of the target video is greater than or equal to the preset view threshold;

[0590] The playback duration of the target video is greater than or equal to the preset playback duration.

[0591] Optionally, in the method of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0592] The methods disclosed in the above embodiments of the present disclosure can be applied to or implemented by processor 701. Processor 701 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in processor 701 or by software instructions. The above processor 701 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of the present disclosure can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software units in the decoding processor. The software units can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 702 , and the processor 701 reads the information in the memory 702 and completes the steps of the above method in combination with its hardware.

[0593] It is understood that the embodiments described herein may be implemented using hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit may be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, or other electronic units or combinations thereof for performing the above-mentioned functions of the present disclosure.

[0594] For software implementation, the techniques described above can be implemented by a unit that performs the functions described above. The software code can be stored in a memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0595] The electronic device provided in this embodiment may be Figure 7 The electronic device shown in FIG. 1 can perform the following operations: Figure 2 、 3 All steps of the streaming media playback method in the Figure 2 、 3 For technical effects of the streaming media playback method shown, please refer to Figure 2 、 3 For the sake of brevity, the relevant description will not be repeated here.

[0596] The present disclosure also provides a storage medium (computer-readable storage medium). The storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; and the memory may also include a combination of the aforementioned types of memory.

[0597] When one or more programs in the storage medium can be executed by one or more processors, the streaming media playback method executed on the electronic device side can be implemented.

[0598] The processor is used to execute the streaming media playback program stored in the memory to implement the following steps of the streaming media playback method executed on the electronic device side.

[0599] As an example, this may include:

[0600] Sending a target playback request to a server, wherein the server is in communication with the terminal;

[0601] Receive the start playback time and the dialogue segment of the video segment of the target video indicated by the target playback request, which are returned by the server; wherein the start playback time of the video segment is the time when the video segment starts playing in the target video;

[0602] Presenting at least part of the text in the above dialogue fragment;

[0603] If a playback operation corresponding to the above-mentioned partial text is detected, the above-mentioned target video is played starting from the above-mentioned start playback time.

[0604] Optionally, in the method of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0605] Dividing the video lines of the target video to obtain a first line segment set;

[0606] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0607] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0608] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0609] Optionally, in the method of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0610] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0611] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0612] Select the target number of results from the calculated results in descending order;

[0613] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0614] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0615] Determine the adjacent candidate segment as a new candidate segment;

[0616] From the calculated results that have not been selected, select the result with the largest value;

[0617] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0618] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0619] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0620] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0621] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0622] Optionally, in the method of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0623] The above text is determined through the following steps:

[0624] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0625] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0626] Optionally, in the method of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0627] Optionally, in the method of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0628] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0629] The second precondition includes at least one of the following:

[0630] The number of views of the target video is greater than or equal to the preset view threshold;

[0631] The playback duration of the target video is greater than or equal to the preset playback duration.

[0632] Optionally, in the method of any embodiment of the present disclosure, presenting at least part of the text in the dialogue segment includes:

[0633] At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

[0634] Optionally, in the method of any embodiment of the present disclosure, presenting at least part of the text in the dialogue segment as the title of the corresponding video segment includes:

[0635] Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the dialogue clip; and

[0636] Before the above-mentioned if a playback operation corresponding to the above-mentioned part of the text is detected, the above-mentioned method further includes:

[0637] If a click operation on the cover is detected, it is determined that a play operation corresponding to the partial text is detected.

[0638] Optionally, in the method of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0639] Or, as another example, it may also include:

[0640] Receiving a target playback request sent by a terminal, wherein the terminal is in communication with the server;

[0641] Determine the target video to be played as instructed by the target playback request;

[0642] Obtaining the start playback time and dialogue segment corresponding to the video segment of the target video; wherein the start playback time corresponding to the video segment is: the time when the video segment starts playing in the target video;

[0643] The starting playback time and the dialogue segment are returned to the terminal so that the terminal presents at least part of the text in the dialogue segment, and when a playback operation corresponding to the part of the text is detected, the target video is played from the starting playback time.

[0644] Optionally, in the method of any embodiment of the present disclosure, the start playback time is determined by the following steps:

[0645] Dividing the video lines of the target video to obtain a first line segment set;

[0646] Determine the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set;

[0647] Based on the first dialogue segment set, the number of barrages, and the number of drag and play times, a second dialogue segment set is generated, wherein the number of dialogue segments in the second dialogue segment set is less than the number of dialogue segments in the first dialogue segment set;

[0648] Determine the start playback time corresponding to the video segment including the dialogue segment in the second dialogue segment set.

[0649] Optionally, in the method of any embodiment of the present disclosure, the first speech segment set is a speech segment sequence, and the number of speech segments in the second speech segment set is a target number; and

[0650] The second dialogue segment set is generated based on the first dialogue segment set, the number of barrages, and the number of drag and play times, including:

[0651] Calculate the weighted sum of the number of bullet comments and the number of drag and play times corresponding to each line segment in the line segment sequence;

[0652] Select the target number of results from the calculated results in descending order;

[0653] Determine the set of dialogue segments corresponding to the target number of results as a candidate segment set;

[0654] If the candidate segment set includes adjacent candidate segments, the following determination steps are performed:

[0655] Determine the adjacent candidate segment as a new candidate segment;

[0656] From the calculated results that have not been selected, select the result with the largest value;

[0657] The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment;

[0658] Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set;

[0659] If the updated candidate segment set includes adjacent candidate segments, performing the above-mentioned determination step based on the updated candidate segment set;

[0660] If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as the second dialogue segment set;

[0661] The adjacent candidate segments are two adjacent dialogue segments in the above-mentioned dialogue segment sequence.

[0662] Optionally, in the method of any embodiment of the present disclosure, the dialogue segment includes at least one dialogue sentence; and

[0663] The above text is determined through the following steps:

[0664] Obtaining a set of preset dialogue sentences, wherein the playback volume and / or comment volume of the dialogue sentences in the set of preset dialogue sentences meet a first preset condition;

[0665] For each speech segment in the second speech segment set, the partial text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

[0666] Optionally, in the method of any embodiment of the present disclosure, the first preset condition includes: the weighted sum of the number of plays and the number of comments of the target line is greater than or equal to a preset value.

[0667] Optionally, in the method of any embodiment of the present disclosure, generating the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes:

[0668] If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times;

[0669] The second precondition includes at least one of the following:

[0670] The number of views of the target video is greater than or equal to the preset view threshold;

[0671] The playback duration of the target video is greater than or equal to the preset playback duration.

[0672] Optionally, in the method of any embodiment of the present disclosure, the starting playback moment corresponding to the video clip is: the middle moment between the starting playback moments of the two dialogue clips in the above-mentioned target video; wherein the above-mentioned two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the above-mentioned target video.

[0673] Professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0674] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0675] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present disclosure in detail. It should be understood that the above description is only a specific implementation method of the present disclosure and is not intended to limit the scope of protection of the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A video playback system, characterized in that: The system includes a terminal and a server, wherein the terminal is in communication with the server, wherein: The terminal is configured to: send a target play request to the server, wherein the target play request is used to instruct to play a target video; The server is configured to: determine the target video indicated by the target playback request; divide the video lines of the target video to obtain a first line segment set, wherein the first line segment set is a line segment sequence; determine the number of barrages and the number of drag-and-play times corresponding to the line segments in the first line segment set; calculate the weighted sum of the number of barrages and the number of drag-and-play times corresponding to each line segment in the line segment sequence; select a target number of results from the calculated results in descending order; determine the set of line segments corresponding to the target number of results as a candidate segment set; if the candidate segment set includes adjacent candidate segments, perform the following determination steps: determine the adjacent candidate segments as a new candidate segment, wherein adjacent candidate segments are two adjacent line segments in the line segment sequence; select the result with the largest value from the calculated results that have not been selected. the result; determining the speech segment corresponding to the selected result with the largest value as a new candidate segment; updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set; if the updated candidate segment set includes the adjacent candidate segments, performing the determination step based on the updated candidate segment set; if the candidate segment set does not include the adjacent candidate segments, determining the candidate segment set that does not include the adjacent candidate segments as a second speech segment set; wherein the number of speech segments in the second speech segment set is the target number, and the adjacent candidate segments are two adjacent speech segments in the speech segment sequence; determining the starting playback time corresponding to the video segment including the speech segment in the second speech segment set; wherein the starting playback time corresponding to the video segment is: the time when the video segment starts to be played in the target video; returning the starting playback time and the speech segments in the second speech segment set to the terminal; The terminal is further configured to: present at least part of the text in the dialogue segment; if a playback operation corresponding to the part of the text is detected, play the target video from the start playback moment; if during the playback of the target video, it is detected that the playback of the video segment is completed, continue playing the target video from the end playback moment of the video segment.

2. The system according to claim 1, wherein: The dialogue segment includes at least one dialogue sentence; and The server is further configured to: Obtaining a set of preset dialogue sentences, wherein the number of plays and / or the number of comments on the dialogue sentences in the set of preset dialogue sentences meet a first preset condition; For each speech segment in the second speech segment set, the portion of text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

3. The system according to claim 2, characterized in that The first preset condition includes: the weighted sum of the number of plays and the number of comments on the target line is greater than or equal to a preset value.

4. The system according to claim 1, wherein: The server is specifically configured as follows: If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times; The second preset condition includes at least one of the following: The target video has a playback volume greater than or equal to a preset playback volume threshold; The playback duration of the target video is greater than or equal to the preset playback duration.

5. The system according to any one of claims 1 to 4, characterized in that: The terminal is specifically configured to: At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

6. The system according to claim 5, characterized in that The terminal is specifically configured to: Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least part of the text in the corresponding dialogue clip; and The terminal is further configured to: If a click operation on the cover is detected, it is determined that a play operation corresponding to the portion of text is detected.

7. The system according to any one of claims 1 to 4, characterized in that: The starting playback time corresponding to the video clip is: the middle time between the starting playback times of the two dialogue clips in the target video; wherein, the two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the target video.

8. A video playback method, characterized in that: The method is applied to a terminal, and includes: Sending a target play request to a server, wherein the server is in communication with the terminal, and the target play request is used to instruct to play a target video; Receive the start playback time corresponding to the video segment of the target video indicated by the target playback request and the speech segment in the second speech segment set, which are returned by the server; wherein the start playback time corresponding to the video segment is: the time when the video segment starts to be played in the target video; presenting at least part of the text in the dialogue segment; If a play operation corresponding to the portion of text is detected, the target video is played starting from the start play time; if the completion of the video segment is detected during the play of the target video, the target video is continued from the end play time of the video segment; The start playback time is determined by the following steps: Dividing the video lines of the target video to obtain a first line segment set, wherein the first line segment set is a line segment sequence; Determining the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set; Calculating a weighted sum of the number of bullet comments and the number of drag and play times corresponding to each dialogue segment in the dialogue segment sequence; Select the target number of results from the calculated results in descending order; Determine a set of dialogue segments corresponding to the target number of results as a candidate segment set; If the candidate segment set includes adjacent candidate segments, the following determination steps are performed: Determining adjacent candidate segments as a new candidate segment, wherein the adjacent candidate segments are two adjacent dialogue segments in the dialogue segment sequence; From the calculated results that have not been selected, select the result with the largest value; The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment; Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set; If the updated candidate segment set includes adjacent candidate segments, performing the determining step based on the updated candidate segment set; If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as a second dialogue segment set; wherein the number of dialogue segments in the second dialogue segment set is the target number; Wherein, the adjacent candidate segments are two adjacent speech segments in the speech segment sequence, and the number of speech segments in the second speech segment set is less than the number of speech segments in the first speech segment set; Determine a start playback time corresponding to a video segment including a dialogue segment in the second dialogue segment set.

9. The method according to claim 8, characterized in that The dialogue segment includes at least one dialogue sentence; and The partial text is determined by the following steps: Obtaining a set of preset dialogue sentences, wherein the number of plays and / or the number of comments on the dialogue sentences in the set of preset dialogue sentences meet a first preset condition; For each speech segment in the second speech segment set, the portion of text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

10. The method according to claim 9, characterized in that The first preset condition includes: the weighted sum of the number of plays and the number of comments on the target line is greater than or equal to a preset value.

11. The method according to claim 8, characterized in that The generating of the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes: If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times; The second preset condition includes at least one of the following: The target video has a playback volume greater than or equal to a preset playback volume threshold; The playback duration of the target video is greater than or equal to the preset playback duration.

12. The method according to any one of claims 8 to 11, characterized in that: Presenting at least part of the text in the dialogue segment includes: At least part of the text in the dialogue segment is presented as the title of the corresponding video segment.

13. The method according to claim 12, characterized in that Presenting at least part of the text in the dialogue segment as the title of the corresponding video segment includes: Presenting a cover of the video clip, wherein the cover includes a title of the video clip, and the title includes at least a portion of text in the dialogue clip; and Before detecting the playback operation corresponding to the portion of text, the method further includes: If a click operation on the cover is detected, it is determined that a play operation corresponding to the portion of text is detected.

14. The method according to any one of claims 8 to 11, characterized in that: The starting playback time corresponding to the video clip is: the middle time between the starting playback times of the two dialogue clips in the target video; wherein, the two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the target video.

15. A video playback method, characterized in that: The method is applied to the server, and includes: Receiving a target playback request sent by a terminal, wherein the terminal is communicatively connected to the server; Determine the target video to be played as instructed by the target playback request; Obtaining the start playback time and dialogue segment corresponding to the video segment of the target video; wherein the start playback time corresponding to the video segment is: the time when the video segment starts to play in the target video; Returning the start playback time and the dialogue segment to the terminal so that the terminal presents at least a portion of the text in the dialogue segment, and upon detecting a playback operation corresponding to the portion of the text, starting playback of the target video from the start playback time, wherein if, during playback of the target video, it is detected that playback of the video segment is complete, continuing playback of the target video from the playback end time of the video segment; The start playback time is determined by the following steps: Dividing the video lines of the target video to obtain a first line segment set, wherein the first line segment set is a line segment sequence; Determining the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set; Calculating a weighted sum of the number of bullet comments and the number of drag and play times corresponding to each dialogue segment in the dialogue segment sequence; Select the target number of results from the calculated results in descending order; Determine a set of dialogue segments corresponding to the target number of results as a candidate segment set; If the candidate segment set includes adjacent candidate segments, the following determination steps are performed: Determining adjacent candidate segments as a new candidate segment, wherein the adjacent candidate segments are two adjacent dialogue segments in the dialogue segment sequence; From the calculated results that have not been selected, select the result with the largest value; The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment; Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set; If the updated candidate segment set includes adjacent candidate segments, performing the determining step based on the updated candidate segment set; If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as a second dialogue segment set; wherein the number of dialogue segments in the second dialogue segment set is the target number; Wherein, the adjacent candidate segments are two adjacent speech segments in the speech segment sequence, and the number of speech segments in the second speech segment set is less than the number of speech segments in the first speech segment set; Determine a start playback time corresponding to a video segment including a dialogue segment in the second dialogue segment set.

16. The method according to claim 15, characterized in that The dialogue segment includes at least one dialogue sentence; and The partial text is determined by the following steps: Obtaining a set of preset dialogue sentences, wherein the number of plays and / or the number of comments on the dialogue sentences in the set of preset dialogue sentences meet a first preset condition; For each speech segment in the second speech segment set, the portion of text for presentation in the speech segment is determined based on the similarity between the speech sentences included in the speech segment and the speech sentences in the preset speech sentence set.

17. The method according to claim 16, characterized in that The first preset condition includes: the weighted sum of the number of plays and the number of comments on the target line is greater than or equal to a preset value.

18. The method according to claim 15, characterized in that The generating of the second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times includes: If the target video meets the second preset condition, generating a second dialogue segment set based on the first dialogue segment set, the number of barrages, and the number of drag and play times; The second preset condition includes at least one of the following: The target video has a playback volume greater than or equal to a preset playback volume threshold; The playback duration of the target video is greater than or equal to the preset playback duration.

19. The method according to any one of claims 15 to 18, characterized in that The starting playback time corresponding to the video clip is: the middle time between the starting playback times of the two dialogue clips in the target video; wherein, the two dialogue clips include: the dialogue clip included in the video clip, and the dialogue clip included in the previous video clip of the video clip in the target video.

20. A video playback device, characterized in that: The device is provided at a terminal, and includes: a sending unit configured to send a target play request to a server, wherein the server is in communication with the terminal, and the target play request is used to instruct to play a target video; The first receiving unit is configured to receive the start playback time corresponding to the video segment of the target video indicated by the target playback request and the speech segment in the second speech segment set, which are returned by the server; wherein the start playback time corresponding to the video segment is: the time when the video segment starts to be played in the target video; a presenting unit configured to present at least part of the text in the dialogue segment; The playback unit is configured to, if a playback operation corresponding to the portion of text is detected, play the target video from the start playback time; if, during the playback of the target video, it is detected that the playback of the video segment is completed, continue to play the target video from the end playback time of the video segment; The start playback time is determined by the following steps: Dividing the video lines of the target video to obtain a first line segment set, wherein the first line segment set is a line segment sequence; Determining the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set; Calculating a weighted sum of the number of bullet comments and the number of drag and play times corresponding to each dialogue segment in the dialogue segment sequence; Select the target number of results from the calculated results in descending order; Determine a set of dialogue segments corresponding to the target number of results as a candidate segment set; If the candidate segment set includes adjacent candidate segments, the following determination steps are performed: Determining adjacent candidate segments as a new candidate segment, wherein the adjacent candidate segments are two adjacent dialogue segments in the dialogue segment sequence; From the calculated results that have not been selected, select the result with the largest value; The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment; Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set; If the updated candidate segment set includes adjacent candidate segments, performing the determining step based on the updated candidate segment set; If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as a second dialogue segment set; wherein the number of dialogue segments in the second dialogue segment set is the target number; Wherein, the adjacent candidate segments are two adjacent speech segments in the speech segment sequence, and the number of speech segments in the second speech segment set is less than the number of speech segments in the first speech segment set; Determine a start playback time corresponding to a video segment including a dialogue segment in the second dialogue segment set.

21. A video playback device, characterized in that: The device is provided at the server end and includes: a second receiving unit configured to receive a target playback request sent by a terminal, wherein the terminal is communicatively connected to the server; a second determining unit, configured to determine a target video to be played as instructed by the target playback request; An acquisition unit is configured to acquire a start playback time and a line segment corresponding to a video segment of the target video; wherein the start playback time corresponding to the video segment is: a time when the video segment starts to play in the target video; a returning unit configured to return the start playback time and the speech segment to the terminal so that the terminal presents at least a portion of the text in the speech segment, and to start playing the target video from the start playback time when a playback operation corresponding to the portion of the text is detected, wherein if it is detected that the video segment is completed during playback of the target video, the target video is continued to be played from the end playback time of the video segment; The start playback time is determined by the following steps: Dividing the video lines of the target video to obtain a first line segment set, wherein the first line segment set is a line segment sequence; Determining the number of bullet comments and the number of drag-and-play times corresponding to the dialogue segments in the first dialogue segment set; Calculating a weighted sum of the number of bullet comments and the number of drag and play times corresponding to each dialogue segment in the dialogue segment sequence; Select the target number of results from the calculated results in descending order; Determine a set of dialogue segments corresponding to the target number of results as a candidate segment set; If the candidate segment set includes adjacent candidate segments, the following determination steps are performed: Determining adjacent candidate segments as a new candidate segment, wherein the adjacent candidate segments are two adjacent dialogue segments in the dialogue segment sequence; From the calculated results that have not been selected, select the result with the largest value; The dialogue segment corresponding to the selected result with the largest value is determined as a new candidate segment; Updating the adjacent candidate segments to the two determined new candidate segments to update the candidate segment set; If the updated candidate segment set includes adjacent candidate segments, performing the determining step based on the updated candidate segment set; If the candidate segment set does not include adjacent candidate segments, determining the candidate segment set that does not include adjacent candidate segments as a second dialogue segment set; wherein the number of dialogue segments in the second dialogue segment set is the target number; Wherein, the adjacent candidate segments are two adjacent speech segments in the speech segment sequence, and the number of speech segments in the second speech segment set is less than the number of speech segments in the first speech segment set; Determine a start playback time corresponding to a video segment including a dialogue segment in the second dialogue segment set.

22. An electronic device, characterized in that: include: memory for storing computer programs; A processor is configured to execute a computer program stored in the memory, and when the computer program is executed, implements the method described in any one of claims 8 to 19.

23. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 8 to 19 is implemented.

Images