Video playing method and device, equipment and medium

Abstract

The embodiment of the invention relates to a video playing method and device, equipment and a medium, and the method comprises the steps: obtaining target user information and a target video in response to a video playing operation; a voice changing video matched with the target user information is generated based on the target video, and the target video and the voice changing video are the same in video frame and different in audio frequency; and playing the voice-changing video. According to the technical scheme, the user information and the target video can be obtained based on the video playing operation, then the voice-changing video with the changed audio corresponding to the target user information can be generated on the basis of the target video, and then the voice-changing video is played, so that the voice-changing videos with different audios can be displayed for different users for the same video, and the user experience is improved. Different users can experience personalized videos, the video playing effect is greatly improved, and then the video playing completion rate and the user experience effect are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of video processing technology, and in particular to a video playback method, device, equipment and medium. Background Art

[0002] With the development of video playback technology, content recommendation or introduction through video has become an important recommendation method. The timing of video appearance, content quality, audio copy, and audio timbre are important factors in video playback effect. In related technologies, for the same content recommendation video, all users see the same content and audio, the video playback method is single, and the playback effect is poor, resulting in poor user experience. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a video playback method, device, equipment and medium.

[0004] The present disclosure provides a video playback method, the method comprising:

[0005] In response to a video playback operation, obtaining target user information and a target video;

[0006] Generate a voice-changed video matching the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio;

[0007] Play the voice changing video.

[0008] The present disclosure also provides a video playback device, the device comprising:

[0009] A request module, used to obtain target user information and target video in response to a video playback operation;

[0010] A video module, used for generating a voice-changed video matching the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio;

[0011] A playing module is used to play the voice changing video.

[0012] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the video playback method provided by the embodiment of the present disclosure.

[0013] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the video playback method provided by the embodiment of the present disclosure.

[0014] The technical solution provided by the disclosed embodiment has the following advantages over the prior art: the video playback solution provided by the disclosed embodiment obtains target user information and target video in response to the video playback operation; generates a voice-changing video matching the target user information based on the target video, wherein the target video and the voice-changing video have the same video frame but different audio; and plays the voice-changing video. With the above technical solution, user information and target video can be obtained based on the video playback operation, and then a voice-changing video with audio changes corresponding to the target user information can be generated based on the target video, and then the voice-changing video can be played, so that different users can be shown voice-changing videos with different audios for the same video, and different users can experience personalized videos, which greatly improves the video playback effect, and thus improves the video completion rate and user experience effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0016] Figure 1 A flowchart of a video playback method provided by an embodiment of the present disclosure;

[0017] Figure 2 A flowchart of another video playback method provided by an embodiment of the present disclosure;

[0018] Figure 3 A flowchart of another video playback method provided by an embodiment of the present disclosure;

[0019] Figure 4 A schematic diagram of a process for determining a first target timbre provided by an embodiment of the present disclosure;

[0020] Figure 5 A schematic diagram of a video playback process provided by an embodiment of the present disclosure;

[0021] Figure 6 A schematic diagram of the structure of a video playback device provided in an embodiment of the present disclosure;

[0022] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0024] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0025] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0026] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0027] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0028] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0029] In order to solve the problem of a single video playback mode in the related art, an embodiment of the present disclosure provides a video playback method, which is introduced below in conjunction with a specific embodiment.

[0030] Figure 1 The flowchart of a video playback method provided by an embodiment of the present disclosure is shown in FIG. 1 , which can be executed by a video playback device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0031] Step 101: In response to a video playback operation, obtain target user information and a target video.

[0032] Among them, the video playback operation can be a trigger operation of the user to start playing the target video, which can include a display operation of the associated page of the target video or a gesture control operation such as clicking, long pressing, double clicking, etc. on the associated control in the associated page. For example, for a short video application, the video playback operation can be a swipe up operation on the previous video. The target video can be the video that is about to be played corresponding to the video playback operation, and can be a video that introduces or recommends an object. The target video can stimulate the user's interest in the introduced object and prompt the user to obtain the object. The object can be an object that is highlighted in the target video, for example, the object can include headphones, lipstick, etc., without limitation. The target user information can be the relevant information corresponding to the user currently performing the video playback operation. The target user information can reflect some personalized characteristics of the user, for example, the target user information can include gender, etc. The target user information is notified to the user in an appropriate manner and obtains the user's authorization.

[0033] The video playback method of the embodiment of the present disclosure can be executed by a client or a server, without limitation. The client can be a client with strong computing power and supports complex algorithms.

[0034] Specifically, after receiving the video playback operation of the current user, the video playback device may obtain target user information and a target video corresponding to the video playback operation, and the target video may be an original video generated by a partner.

[0035] Step 102: Generate a voice-changed video that matches the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio.

[0036] The voice-changed video may be a personalized video that best matches the current user and is obtained by personalizing the audio of the target video. The voice-changed video has the same video frame as the target video but different audio, that is, the video picture is the same but the sound is different.

[0037] Specifically, after obtaining the target user information and the target video, the video playback device can personalize the audio of the target video according to the target user information to obtain a voice-changed video. The personalization process can specifically obtain a matching video as the voice-changed video from multiple videos with changed audio that are pre-generated by the server according to the target video according to the target user information, or select matching texts and timbres from multiple texts and multiple timbres that are pre-generated by the server according to the target video according to the target user information to generate a new audio, and replace the audio in the target video with the new audio to obtain the voice-changed video.

[0038] The personalized processing here can be the optimization processing of the text and timbre of the audio by the server based on various models. The model can be a neural network-based model. These models can understand and generate high-quality text, voice, image and other content through learning and training of large-scale data.

[0039] Step 103: Play the voice-changing video.

[0040] After the video playback device generates a voice-changed video matching the target user information based on the target video, it can play the voice-changed video, so that different users can watch different voice-changed videos for the same target video.

[0041] For example, for the same video introducing headphones, when male users see the video, they hear a voice with a female voice, while when female users see the video, they hear a voice with a male voice. Different users hear different voices for the same video, which increases its appeal to users.

[0042] The video playback solution provided by the disclosed embodiment obtains target user information and target video in response to a video playback operation; generates a voice-changed video matching the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio; and plays the voice-changed video. Using the above technical solution, user information and target video can be obtained based on the video playback operation, and then a voice-changed video with audio changes corresponding to the target user information can be generated based on the target video, and then the voice-changed video is played, so that different users can be shown voice-changed videos with different audio for the same video, so that different users can experience personalized videos, which greatly improves the video playback effect, and thus improves the video completion rate and user experience effect.

[0043] For example, Figure 2 A flowchart of another video playback method provided by an embodiment of the present disclosure is shown in FIG. Figure 2 As shown, in a feasible implementation manner, generating a voice-changing video matching the target user information based on the target video may include the following steps:

[0044] Step 201: Generate multiple first videos according to a target video.

[0045] Among them, the first video can be a video obtained by performing multiple personalized processing on the audio of the target video. Each first video is the same as the video frame of the target video, and the text and timbre of the audio are different. The text of the audio can be the text obtained by recognizing the audio through speech recognition technology. The timbre can be the characteristics of the sound in the audio, which enables different sound sources to be distinguished under the same pitch and loudness, such as different timbres of different musical instruments.

[0046] In some embodiments, generating multiple first videos based on a target video may include: extracting multiple corresponding first target timbres from a timbre library based on the gender of a character in the target video; generating multiple first prompt words based on the original text of the target video and a preset prompt word template, and generating multiple first texts based on the multiple first prompt words; generating multiple first videos based on the video frame of the target video, the first target timbre and the multiple first texts.

[0047] The timbre library may include multiple timbres associated with different genders of characters. One gender of a character may be associated with multiple timbres. The multiple associated timbres may be selected timbres that are more attractive to users and arouse their interest. The gender of a character may include male, female, and unrecognizable. For example, the multiple timbres associated with a male gender may include female timbres. The original text may be the text obtained by performing voice recognition on the target video. The first target timbre may be a timbre that matches the gender of the character in the target video. The number of first target timbres may include multiple ones.

[0048] The preset prompt word template can be a template that specifies the information and specific format included in the prompt word (Prompt). The prompt word template can include placeholders to reserve space for subsequent insertion of relevant specific information, and the prompt word is generated by the prompt word template. In the embodiment of the present disclosure, the preset prompt word template can include relevant information of the target video, multiple user information and original text. The prompt word can be accurately converted into a form that the model can effectively understand and process to generate appropriate context information, which can enhance the accuracy of the interpretation of the user's intention, thereby generating a more accurate and more practical answer. The prompt word, as an interactive guidance mechanism, is of great significance for defining the task boundary of the model and optimizing its execution strategy. The first prompt word can be a prompt word used to polish and optimize the original text of the target video according to the preset direction that is closer to the relevant information of the target video and various different user information. Since the users who watch the target video can include multiple, the number of the first prompt words can be multiple, which is specifically determined according to the actual situation.

[0049] For example, when the target video is a recommended video, the first prompt word may be "Now you are an {author_type} anchor, your name is {author_name}, and you are now required to post a video to introduce the advantages of the product and guide users to place an order. The type of this product is {category}, and the target audience is usually {audience}. The word count is controlled within the range of {min} words to {max} words; the example script you refer to is: {script_example}, and the short video script you want to polish is: {script}", where the short video script is the original text of the target video.

[0050] The first text may be a text generated after optimizing the original text. The first text may include multiple first texts. Different types of user information may correspond to different first texts. The first text not only amplifies the effect of the target video but also better matches different types of users.

[0051] Specifically, when the video playback device is set on the client, the target video can be sent to the server, and the server generates multiple first videos based on the target video. Specifically, the target video can extract video frames to determine the corresponding character's gender. For example, multiple video frames can be extracted according to the frame extraction frequency, such as extracting one video frame every 1 second, and face detection can be performed on the multiple video frames. When the number of times the face is detected reaches a threshold, the corresponding character's gender can be determined based on the video frame. After that, multiple associated timbres can be extracted from the timbre library according to the character's gender, and a preset number of timbres from the multiple timbres can be determined as multiple first target timbres, or a preset number of timbres ranked top from the multiple timbres can be extracted according to a preset timbre strategy. The timbre of the target video is determined as a plurality of first target timbres, and the preset number can be set according to the actual situation. The preset timbre strategy can be, for example, sorting according to the interactive data such as the playback volume of the video and / or audio corresponding to the timbre, which is only an example and not a limitation. Afterwards, the original text of the target video can be extracted, and a plurality of first prompt words can be generated according to the original text and the preset prompt word template. The plurality of first prompt words are input into the text optimization model to generate a plurality of first texts. The text optimization model can be a model for generating high-quality texts. Video synthesis is performed based on the video frame of the target video, the plurality of first target timbres and the plurality of first texts to generate a plurality of first videos. The number of the first target timbres can be the same as the number of the first texts.

[0052] For example, Figure 4 A schematic diagram of a process for determining a first target timbre provided in an embodiment of the present disclosure is shown in FIG. Figure 4 As shown in the figure, the process of determining the above-mentioned first target timbre may include: extracting frames from the target video to identify the face, identifying the gender of the person through a model, the gender of the person may include male, female and unrecognizable, extracting multiple timbres from the timbre library according to the identified gender of the person, and extracting multiple first target timbres from the multiple timbres.

[0053] Step 202: Input the target user information and the multiple first videos into a video matching model to obtain multiple matching degrees of the multiple first videos.

[0054] The video matching model may be a model for determining the degree of matching between certain information and multiple videos, and the video matching model may be a deep learning model, and the specific type is not limited. The matching degree may indicate the degree of matching between the target user information and a first video in multiple dimensions.

[0055] Specifically, after generating multiple first videos, the video playback device may input the target user information and the multiple first videos into a video matching model to calculate the matching degree, and output multiple matching degrees between the target user information and the multiple first videos respectively.

[0056] Step 203: Determine the first video corresponding to the highest matching degree among the multiple matching degrees as the voice-changing video.

[0057] The highest matching degree may be the matching degree with the highest value among the multiple matching degrees. After determining the matching degrees between the target user information and the multiple first videos, the video playback device may extract the first video with the highest matching degree as the voice-changed video. If the server executes at this time, the voice-changed video may be returned to the client.

[0058] In the above scheme, by deriving multiple first videos in advance according to the target video in the server, when the user requests to play the target video, the first video with the highest matching degree can be sent as the final voice-changing video to be played according to the current user information. Since the server completes most of the calculation process, the efficiency of video playback is guaranteed.

[0059] For example, Figure 3 A flowchart of another video playback method provided by the embodiment of the present disclosure is shown as follows: Figure 3 As shown, in another feasible implementation manner, generating a voice-changing video matching the target user information based on the target video may include the following steps:

[0060] Step 301: Acquire multiple second texts corresponding to a target video that are optimized for the original text, and determine a third text among the multiple second texts according to target user information.

[0061] The original text may be a text obtained by performing speech recognition on the target video. The second text may be a text generated after optimizing the original text, which may be obtained by pre-optimizing the original text by the server. The specific optimization method may be to generate prompt words using the original text and a preset prompt word template and input them into a text optimization model. The second text may be the same as the first text, and the number of second texts may include multiple. The third text may be a second text that matches the current user and is determined from multiple optimized second texts according to the target user information of the current user.

[0062] Specifically, the video playback device can obtain multiple second texts optimized by the server for the original text of the target video, and match the target user information with each second text to determine multiple matching degrees, and determine the second text with the highest matching degree as the third text. The method of matching the target user information with the second text here, for example, can be to input the target user information and multiple second texts into a matching model, and output multiple matching degrees, which is only an example.

[0063] In some embodiments, determining a third text among multiple second texts according to target user information may include: determining a target category according to the target user information; and determining a second text among the multiple second texts corresponding to the target category as the third text.

[0064] Among them, the target category can be a user category determined according to the target user information, and the user category can be a category divided according to multiple user information. The user category can include multiple categories, for example, it can be divided into 3 user categories according to gender: "male; female; unrecognizable".

[0065] Specifically, when the video playback device determines the third text among multiple second texts based on the target user information, it can also first determine the user category to which the target user belongs as the target category based on the target user information. For example, the user category to which the current user belongs can be determined as the target category based on the gender in the target user information; then, the corresponding second text can be extracted from a mapping relationship library between user categories and second texts based on the target category to determine it as the third text. The mapping relationship library may include a mapping relationship between each user category and the second text that best matches the multiple second texts, and the user categories include multiple ones.

[0066] In the above scheme, a more matching text can be determined based on the user information of the current user to replace the original text, so that the subsequent video is more attractive to the user from the perspective of the text.

[0067] Step 302: Obtain a second target timbre corresponding to the target video.

[0068] The second target timbre may be the timbre that best matches the target video or the timbre that best matches the current user. For example, the second target timbre may be the timbre that ranks first among multiple timbres that match the gender of the character in the target video, or the timbre preset by the current user.

[0069] In some embodiments, obtaining a second target timbre corresponding to the target video includes: extracting a corresponding second target timbre from a timbre library according to the target video; or obtaining an input user timbre and determining it as the second target timbre.

[0070] The video playback device can obtain the first ranked timbre among multiple timbres associated with the gender of the character after the server recognizes the gender of the character in the target video, and extract the changed timbre from the timbre library to determine it as the second target timbre. The process of determining the timbre associated with the gender of the character in the target video is described in the above embodiment and will not be repeated here. Alternatively, the video playback device can display a timbre setting page, and in response to the user timbre input by the current user on the timbre setting page, the user timbre can be determined as the second target timbre. The user timbre can be the timbre set by the current user or the timbre that the user is interested in.

[0071] Step 303: Generate target audio based on the second target timbre and the third text, and replace the original audio in the target video with the target audio to obtain a voice-changed video.

[0072] The original audio may be the original unprocessed audio in the target video, and the target audio may be the audio obtained by optimizing both the text and the timbre of the original audio.

[0073] After obtaining the second target timbre and the third text, the video playback device can generate a target audio based on the second target timbre and the third text. Specifically, the third text can be converted into speech audio of the second target timbre using Text-To-Speech (TTS) technology to obtain the target timbre; then the original audio in the target video can be deleted and replaced with the target audio, and video synthesis can be performed to obtain a voice-changed video.

[0074] For example, Figure 5 A schematic diagram of a video playback process provided by an embodiment of the present disclosure, such as Figure 5 As shown, the figure shows the video playback process when the video playback device is set on the client, which specifically includes: the user initiates a request; obtains the target video and target user information; selects the optimized text according to the target user information, that is, the above-mentioned step 301; generates the target audio according to the timbre set by the user and the optimized text, that is, the generation of the target audio in the above-mentioned step 303, and the timbre set by the user is the second target timbre; uses the target audio to replace the original audio in the target video to obtain a voice-changed video; and plays the voice-changed video.

[0075] In the above scheme, for the target video requested by the user to be played, a voice-changed video matching the current user can be generated in real time on the client for playback, so that different users can experience personalized videos, greatly improving the video playback effect.

[0076] The video playback solution provided by the embodiment of the present disclosure can personalize the audio of the video requested to be played according to the characteristics of the current user, so that different users can see personalized videos with different texts and tones, thereby increasing the user's interest in the video, improving the completion rate and conversion rate of the video playback, and thus improving the user experience.

[0077] Figure 6 The structure diagram of a video playback device provided by an embodiment of the present disclosure is shown in FIG. 1 , which can be implemented by software and / or hardware and can generally be integrated into an electronic device. Figure 6 As shown, the package includes:

[0078] The request module 601 is used to obtain target user information and target video in response to a video playback operation;

[0079] A video module 602 is used to generate a voice-changed video matching the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio;

[0080] The playing module 603 is used to play the voice changing video.

[0081] Optionally, the video module 602 includes:

[0082] A generating unit, configured to generate a plurality of first videos according to the target video;

[0083] A matching unit, configured to input the target user information and the multiple first videos into a video matching model to obtain multiple matching degrees of the multiple first videos;

[0084] A determination unit is used to determine the first video corresponding to the highest matching degree among the multiple matching degrees as the voice-changing video.

[0085] Optionally, the generating unit is used for:

[0086] Extracting a plurality of corresponding first target timbres from a timbre library according to the gender of the person in the target video;

[0087] Generate a plurality of first prompt words based on the original text of the target video and a preset prompt word template, and generate a plurality of first texts based on the plurality of first prompt words;

[0088] A plurality of first videos are generated based on the video frame of the target video, the plurality of first target timbres and the plurality of first texts.

[0089] Optionally, each of the first videos has the same video frame as the target video, but has different audio text and timbre.

[0090] Optionally, the video module 602 includes:

[0091] A text unit, used to obtain a plurality of second texts corresponding to the target video that are optimized for the original text, and determine a third text among the plurality of second texts according to the target user information;

[0092] A timbre unit, used to obtain a second target timbre corresponding to the target video;

[0093] A replacement unit is used to generate a target audio based on the second target timbre and the third text, and replace the original audio in the target video with the target audio to obtain the voice-changed video.

[0094] Optionally, the text unit is used to:

[0095] Determine a target category according to the target user information;

[0096] A second text corresponding to the target category among the plurality of second texts is determined as a third text.

[0097] Optionally, the timbre unit is used for:

[0098] Extracting a corresponding second target timbre from a timbre library according to the target video;

[0099] Alternatively, the input user timbre is obtained and determined as the second target timbre.

[0100] The video playback device provided in the embodiments of the present disclosure can execute the video playback method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0101] The embodiments of the present disclosure also provide a computer program product, including a computer program / instruction, which implements the video playback method provided by any embodiment of the present disclosure when executed by a processor.

[0102] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0103] The following specific reference Figure 7 , which shows a schematic diagram of the structure of an electronic device 700 suitable for implementing the embodiment of the present disclosure. The electronic device 700 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 7The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0104] like Figure 7 As shown, the electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0105] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 700 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0106] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the video playback method of the embodiment of the present disclosure are executed.

[0107] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0108] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0109] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0110] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains target user information and target video in response to a video playback operation; generates a voice-changed video matching the target user information based on the target video, wherein the target video has the same video frame as the voice-changed video but different audio; and plays the voice-changed video.

[0111] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0112] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0114] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0115] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0117] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

[0118] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0119] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A video playback method, characterized in that: include: In response to a video playback operation, obtaining target user information and a target video; Generate a voice-changed video matching the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio; Play the voice changing video.

2. The method according to claim 1, characterized in that Generating a voice-changed video matching the target user information based on the target video includes: Generate multiple first videos according to the target video; Inputting the target user information and the multiple first videos into a video matching model to obtain multiple matching degrees of the multiple first videos; The first video corresponding to the highest matching degree among the multiple matching degrees is determined as the voice-changing video.

3. The method according to claim 2, characterized in that Generating a plurality of first videos according to the target video includes: Extracting a plurality of corresponding first target timbres from a timbre library according to the gender of the person in the target video; Generate a plurality of first prompt words based on the original text of the target video and a preset prompt word template, and generate a plurality of first texts based on the plurality of first prompt words; A plurality of first videos are generated based on the video frame of the target video, the plurality of first target timbres and the plurality of first texts.

4. The method according to claim 2, characterized in that: Each of the first videos has the same video frame as the target video, but has different text and timbre of audio.

5. The method according to claim 1, characterized in that Generating a voice-changed video matching the target user information based on the target video includes: Acquire multiple second texts corresponding to the target video that are optimized for the original text, and determine a third text among the multiple second texts according to the target user information; Obtaining a second target timbre corresponding to the target video; A target audio is generated based on the second target timbre and the third text, and the original audio in the target video is replaced with the target audio to obtain the voice-changed video.

6. The method according to claim 5, characterized in that Determining a third text among the plurality of second texts according to the target user information includes: Determine a target category according to the target user information; A second text corresponding to the target category among the plurality of second texts is determined as a third text.

7. The method according to claim 5, characterized in that Obtaining a second target timbre corresponding to the target video includes: Extracting a corresponding second target timbre from a timbre library according to the target video; Alternatively, the input user timbre is obtained and determined as the second target timbre.

8. A video playback device, characterized in that: include: A request module, used to obtain target user information and target video in response to a video playback operation; A video module, used for generating a voice-changed video matching the target user information based on the target video, wherein the target video and the voice-changed video have the same video frame but different audio; A playing module is used to play the voice changing video.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the video playback method described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the video playback method described in any one of claims 1 to 7.

Images