Method, system and equipment for generating personalized video polyphonic ringtone and medium

Abstract

The invention discloses a personalized video polyphonic ringtone generation method and device, equipment and a storage medium. The personalized video polyphonic ringtone generation method comprises the steps of obtaining a user-defined pattern and text description information uploaded by a user; acquiring historical behavior data of the user, and generating an initial video polyphonic ringtone corresponding to the user according to the historical behavior data; generating a basic watermark in the initial video polyphonic ringtone according to the custom pattern and the text description information through a Stable Diffusion technology; and adjusting the basic watermark according to the text description information through the ControlNet to obtain a target video polyphonic ringtone, and feeding back the target video polyphonic ringtone to the user. The method can improve the generation efficiency of the video polyphonic ringtone and reduce the cost; moreover, according to the method, the watermark specified by the user can be added into the video polyphonic ringtone, and the watermark can be well fused with the video content, so that the copyright protection of the personalized video polyphonic ringtone is realized, and the risk of being stolen is reduced. The method can be widely applied to the technical field of video polyphonic ringtones.

Description

Technical Field

[0001] The present application relates to the technical field of video ringback tone, and in particular to a method, device, equipment and storage medium for generating personalized video ringback tone. Background Art

[0002] At present, with the development of information technology, more and more applications are being developed to provide services for users. For example, video ringback tone is a value-added service based on the communication network. When a user makes a voice call, it provides a short video to the called party, replacing the traditional audio ringback tone. When the caller calls the called party, he can see the personalized video content pre-set by the called party while waiting for the call to be answered, such as personal short videos, corporate promotions, holiday greetings, etc.

[0003] In the related technologies, the existing video ringback tone content is relatively fixed, and the operator often sets the basic template in advance, and generates it by users providing some materials. This implementation method is difficult to meet the personalized needs of users. Although some technical solutions provide the function of users editing video ringback tone by themselves, it takes a lot of time and effort to produce, and the cost is high. Since the video ringback tone may be displayed anywhere, it is easy for others to easily obtain the content of the video ringback tone, and there is a risk of theft.

[0004] In summary, the problems existing in related technologies need to be solved urgently. Summary of the invention

[0005] The purpose of this application is to solve one of the technical problems existing in the related art to at least a certain extent.

[0006] To this end, an object of the embodiments of the present application is to provide a method, apparatus, device and storage medium for generating personalized video ringback tone.

[0007] In order to achieve the above technical objectives, the technical solutions adopted by the embodiments of the present application include:

[0008] On the one hand, an embodiment of the present application provides a method for generating a personalized video ringback tone, the method comprising:

[0009] Obtaining a custom pattern and text description information uploaded by a user; wherein the text description information is used to indicate that a corresponding watermark is added to the video ringback tone according to the custom pattern and to indicate a display effect of the watermark;

[0010] Acquire historical behavior data of the user, and generate an initial video ringback tone corresponding to the user according to the historical behavior data;

[0011] Generate a basic watermark in the initial video ring back tone according to the custom pattern and the text description information by using the Stable Diffusion technology;

[0012] Through ControlNet, the basic watermark is adjusted according to the text description information to obtain a target video ringback tone, and the target video ringback tone is fed back to the user.

[0013] In addition, the method for generating a personalized video ringback tone according to the above embodiment of the present application may also have the following additional technical features:

[0014] Furthermore, in one embodiment of the present application, obtaining the historical behavior data of the user includes:

[0015] Obtaining identity information of the user;

[0016] According to the identity information, a historical behavior database is searched and queried to obtain the historical behavior data of the user.

[0017] Furthermore, in one embodiment of the present application, the historical behavior data includes the user's video browsing data, interaction data, and playback habit information.

[0018] Furthermore, in one embodiment of the present application, the method further includes:

[0019] By using EbSynth technology, the basic watermark is dynamically migrated between multiple frames in the initial video ringback tone;

[0020] Alternatively, a key frame in the initial video ring back tone is identified, and the position of the basic watermark is adjusted in the key frame by using the EbSynth technology.

[0021] Furthermore, in one embodiment of the present application, the method further includes:

[0022] Conducting content review on the custom pattern;

[0023] When it is determined that the custom pattern passes the content review, the custom pattern is preprocessed; wherein the preprocessing operation includes at least one of a denoising operation, a cropping operation, or a normalization operation.

[0024] Furthermore, in one embodiment of the present application, the text description information is used to indicate at least one of the position, size, transparency, dynamic effect, and display time of the watermark.

[0025] On the other hand, an embodiment of the present application provides a device for generating a personalized video ringback tone, the device comprising:

[0026] An acquisition unit, used to acquire the custom pattern and text description information uploaded by the user; wherein the text description information is used to indicate that a corresponding watermark is added to the video ringback tone according to the custom pattern and to indicate the display effect of the watermark;

[0027] A generating unit, configured to obtain historical behavior data of the user, and generate an initial video ringback tone corresponding to the user according to the historical behavior data;

[0028] A processing unit, configured to generate a basic watermark in the initial video ring back tone according to the custom pattern and the text description information by using a Stable Diffusion technology;

[0029] The adjustment unit is used to adjust the basic watermark according to the text description information through ControlNet to obtain a target video ring back tone, and feed the target video ring back tone to the user.

[0030] Furthermore, in one embodiment of the present application, the text description information is used to indicate at least one of the position, size, transparency, dynamic effect, and display time of the watermark.

[0031] On the other hand, an embodiment of the present application provides an electronic device, including:

[0032] at least one processor;

[0033] at least one memory for storing at least one program;

[0034] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method for generating personalized video ringback tone.

[0035] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for generating personalized video ringback tone.

[0036] The advantages and benefits of the present application will be partially given in the following description, and partially become apparent from the following description, or be understood through the practice of the present application:

[0037] The method, device, equipment and storage medium for generating personalized video ringback tone disclosed in the embodiment of the present application obtain the custom pattern and text description information uploaded by the user; wherein the text description information is used to indicate the addition of the corresponding watermark in the video ringback tone according to the custom pattern and the display effect of the watermark; obtain the historical behavior data of the user, and generate the initial video ringback tone corresponding to the user according to the historical behavior data; generate a basic watermark in the initial video ringback tone according to the custom pattern and the text description information through the Stable Diffusion technology; adjust the basic watermark according to the text description information through ControlNet to obtain the target video ringback tone, and feed the target video ringback tone back to the user. This method can realize the automatic generation of personalized video ringback tone, improve the generation efficiency of video ringback tone, and reduce the cost; moreover, this method can add the user-specified watermark in the video ringback tone, and the watermark can be better integrated with the video content, which is conducive to the copyright protection of personalized video ringback tone and reduces the risk of theft. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present application. For technical personnel in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A schematic diagram of an implementation environment of a method for generating a personalized video ringback tone provided in an embodiment of the present application;

[0040] Figure 2 A flowchart of a method for generating a personalized video ringback tone provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of the application process of a method for generating a personalized video ringback tone provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of the structure of a device for generating a personalized video ringback tone provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0045] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0047] 1) Video ringback tone: refers to a video played instead of the traditional audio ringback tone during a mobile phone call, usually a short video content selected by the ringback tone user.

[0048] 2) Stable Diffusion: A deep learning technique based on a diffusion model that is specifically designed to generate high-quality images. It is a generative model that gradually extracts and optimizes images from noise to ultimately generate realistic images that match the input conditions (such as text or other image features).

[0049] 3) EbSynth: A style transfer tool based on keyframe interpolation, commonly used in video processing.

[0050] 4) ControlNet: A deep learning technique for stable image generation, specifically designed to enhance the control capabilities of existing generative models (such as Stable Diffusion).

[0051] At present, with the development of information technology, more and more applications are being developed to provide services for users. For example, video ringback tone is a value-added service based on the communication network. When a user makes a voice call, it provides a short video to the called party, replacing the traditional audio ringback tone. When the caller calls the called party, he can see the personalized video content pre-set by the called party while waiting for the call to be answered, such as personal short videos, corporate promotions, holiday greetings, etc.

[0052] In the related technologies, the existing video ringback tone content is relatively fixed, and the operator often sets the basic template in advance, and generates it by users providing some materials. This implementation method is difficult to meet the personalized needs of users. Although some technical solutions provide the function of users editing video ringback tone by themselves, it takes a lot of time and effort to produce, and the cost is high. Since the video ringback tone may be displayed anywhere, it is easy for others to easily obtain the content of the video ringback tone, and there is a risk of theft.

[0053] In view of this, a method for generating a personalized video ringback tone is provided in an embodiment of the present application, wherein the user-uploaded custom pattern and text description information are obtained; wherein the text description information is used to indicate the addition of a corresponding watermark in the video ringback tone according to the custom pattern and the display effect of the watermark; the user's historical behavior data is obtained, and the initial video ringback tone corresponding to the user is generated according to the historical behavior data; a basic watermark is generated in the initial video ringback tone according to the custom pattern and the text description information through the Stable Diffusion technology; the basic watermark is adjusted according to the text description information through ControlNet to obtain a target video ringback tone, and the target video ringback tone is fed back to the user. This method can realize the automated generation of personalized video ringback tones, improve the generation efficiency of video ringback tones, and reduce costs; moreover, this method can add a user-specified watermark in the video ringback tone, and the watermark can be better integrated with the video content, which is conducive to the copyright protection of personalized video ringback tones and reduces the risk of theft.

[0054] Please refer to Figure 1 , Figure 1 The schematic diagram of the implementation environment of a method for generating a personalized video ringback tone provided in an embodiment of the present application is shown. In the implementation environment, the main hardware and software entities involved include a terminal device 110 and a backend server 120. The terminal device 110 and the backend server 120 are connected in communication.

[0055] Specifically, the method for generating personalized video ringback tone provided in the embodiment of the present application can be executed alone on the terminal device 110 side, or can be executed alone on the background server 120 side, or can be executed based on data interaction between the terminal device 110 and the background server 120.

[0056] The terminal device 110 of the above embodiment may include a mobile phone, a computer, a smart wearable device, a PDA device, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc., but is not limited thereto. The backend server 120 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0057] The terminal device 110 and the backend server 120 may establish a communication connection via a wireless network or a wired network. The wireless network or wired network uses standard communication technology and / or protocols, and the network may be set to the Internet or any other network, such as but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network or any combination of a virtual private network.

[0058] Of course, it is understandable that Figure 1 The implementation environment in the embodiment of the present application is only some optional application scenarios of the method for generating personalized video ringback tone provided in the embodiment of the present application, and the actual application is not fixed. Figure 1 The hardware and software environment shown.

[0059] Next, in combination with the introduction of the aforementioned implementation environment, a method for generating a personalized video ringback tone provided in an embodiment of the present application is introduced and illustrated.

[0060] Please refer to Figure 2 , Figure 2 : is a schematic diagram of a method for generating a personalized video ringback tone provided in an embodiment of the present application. The method for generating a personalized video ringback tone includes but is not limited to:

[0061] Step 210: Obtain the custom pattern and text description information uploaded by the user; wherein the text description information is used to indicate that a corresponding watermark is added to the video ringback tone according to the custom pattern and to indicate the display effect of the watermark;

[0062] Step 220: Obtain the historical behavior data of the user, and generate an initial video ringback tone corresponding to the user according to the historical behavior data;

[0063] Step 230: Generate a basic watermark in the initial video ring back tone according to the custom pattern and the text description information by using the Stable Diffusion technology;

[0064] Step 240: Through ControlNet, the basic watermark is adjusted according to the text description information to obtain a target video ringback tone, and the target video ringback tone is fed back to the user.

[0065] In an embodiment of the present application, a method for generating a personalized video ringback tone is provided. The method can realize the automated generation of personalized video ringback tone, improve the generation efficiency of the video ringback tone, and reduce the cost. Moreover, the method can add a user-specified watermark to the video ringback tone. The watermark can be better integrated with the video content, which is conducive to realizing the copyright protection of the personalized video ringback tone and reducing the risk of theft.

[0066] Specifically, in the embodiment of the present application, when generating a personalized video ringback tone, the user can upload a custom pattern and text description information according to their needs. In the embodiment of the present application, the custom pattern is an image uploaded by the user, and the user can generate a corresponding watermark in the video ringback tone based on the custom pattern. The custom pattern here can be a photo, an icon, a logo, a work of art, etc. The user can flexibly select or create a unique pattern as a custom pattern to upload according to his or her preferences and needs, and the present application does not limit this.

[0067] In the embodiment of the present application, the text description information can be used to indicate that a watermark is added to the video ringtone according to a custom pattern and to indicate the display effect of the watermark. Exemplarily, the text description information can be used to indicate at least one of the position, size, transparency, dynamic effect, and display time of the watermark. Among them, the watermark position means that the user can specify the specific position of the watermark in the video through the text description information, such as requiring the generated watermark to be in the upper left corner, upper right corner, or centered of the video ringtone; the size means that the user can indicate the size ratio of the watermark in the integrated screen through the text description information, such as small (10%), medium (20%), large (30%), etc.; the user can also set the transparency of the watermark through the text description information to make the watermark more naturally integrated into the video; the dynamic effect can be used to adjust the display of the watermark, such as the watermark can be static, rotating, or faded in and out; the display time can be used to set the time period in which the watermark appears during the playback of the entire video ringtone, which can be a part of the time, such as the first 5 seconds, the last 10 seconds, or it can be displayed from the beginning to the end, and the present application does not limit this.

[0068] In an embodiment of the present application, the user's historical behavior data can be obtained, and the initial video ringback tone corresponding to the user can be generated based on the historical behavior data. Here, the historical behavior data may include the user's video browsing data, interaction data, and playback habit information, but is not limited to this. Specifically, in some embodiments, the viewing behavior such as the type, duration, and frequency of the video content watched by the user on the platform, as well as the user's interactive behaviors such as likes, comments, and sharing, can be obtained, and the keywords and categories searched by the user, the channels or creators followed or subscribed to by the user can be obtained. Based on this information, the user can be feature extracted and analyzed to better understand the user's preferences and behavior patterns. Then, a user portrait can be constructed based on the user's basic information and historical behavior data, and a corresponding video ringback tone can be generated based on the user's characteristics and behavior patterns. In an embodiment of the present application, it is recorded as the initial video ringback tone.

[0069] After obtaining the initial video ringback tone, the Stable Diffusion technology can be used to generate a basic watermark in the initial video ringback tone according to the custom pattern and text description information. Stable Diffusion is a generative AI technology based on a diffusion model. The core idea is to degenerate the image into random noise by gradually adding noise, and then learn how to gradually restore a clear image from the noise. It supports text-to-image generation, and the image generation process can be guided by inputting text description information. The model will adjust the generated image content according to the prompt to make it conform to the description. Exemplarily, for example, the user's text description information can be "Generate a watermark based on a custom pattern, displayed in the lower right corner of the ringback tone video, and the color is a soft gradient blue." Using the custom pattern and text description information as input, the Stable Diffusion model can generate a high-quality watermark image and embed it into the initial video ringback tone. In the embodiment of the present application, the watermark generated by the Stable Diffusion model in the initial video ringback tone is used as the basic watermark.

[0070] After obtaining the basic watermark, ControlNet can be used to adjust the basic watermark according to the text description information. ControlNet is a neural network architecture for conditional image generation, which allows users to guide the image generation process according to specific conditions (such as edges, depth maps, semantic segmentation, etc.). In the embodiment of the present application, the use of ControlNet allows the generated image to be controlled according to additional conditions (such as sketches, edge detection, posture estimation, etc.), and the style or position of the watermark can be adjusted to meet specific requirements, such as clear edge lines of the QR code or precise alignment of the watermark with the background content. After adjustment through ControlNet, the target video ringtone can be obtained and then fed back to the user.

[0071] It can be understood that the method for generating personalized video ringback tone provided in the embodiment of the present application obtains the custom pattern and text description information uploaded by the user; wherein the text description information is used to indicate the addition of a corresponding watermark in the video ringback tone according to the custom pattern and the display effect of the watermark; obtains the historical behavior data of the user, and generates the initial video ringback tone corresponding to the user according to the historical behavior data; generates a basic watermark in the initial video ringback tone according to the custom pattern and the text description information through the Stable Diffusion technology; adjusts the basic watermark according to the text description information through ControlNet to obtain the target video ringback tone, and feeds the target video ringback tone back to the user. This method can realize the automated generation of personalized video ringback tone, improve the generation efficiency of video ringback tone, and reduce the cost; moreover, this method can add a user-specified watermark in the video ringback tone, and the watermark can be better integrated with the video content, which is conducive to the copyright protection of personalized video ringback tone and reduces the risk of theft.

[0072] Specifically, in some embodiments, obtaining the historical behavior data of the user includes:

[0073] Obtaining identity information of the user;

[0074] According to the identity information, a historical behavior database is searched and queried to obtain the historical behavior data of the user.

[0075] In an embodiment of the present application, when obtaining a user's historical behavior data, the user's identity information may be obtained first, for example, the basic information provided by the user when registering on the platform (such as user name, email, mobile phone number, etc.). Based on the user's identity information, a search query may be performed in a pre-established historical behavior database to obtain the user's historical behavior data. Exemplarily, in some embodiments, a precise query based on the user ID may be performed, that is, all historical behavior records may be directly searched based on the user ID; in some embodiments, a fuzzy match may be performed based on partial information (such as part of a user name), which is not limited in the present application.

[0076] In some embodiments, the method further comprises:

[0077] By using EbSynth technology, the basic watermark is dynamically migrated between multiple frames in the initial video ringback tone;

[0078] Alternatively, a key frame in the initial video ring back tone is identified, and the position of the basic watermark is adjusted in the key frame by using the EbSynth technology.

[0079] In an embodiment of the present application, the basic watermark can be adjusted using EbSynth technology. EbSynth is an image and video-based style transfer and editing tool that uses deep learning technology to achieve stylized processing of images or videos. Specifically, in an embodiment of the present application, using EbSynth technology, dynamic texture migration can be achieved in multiple frames of a video ringback tone based on the basic watermark, ensuring that the basic watermark moves, scales, or fades with changes in the video content. In some embodiments, EbSynth can also be used to adjust the watermark position according to key frames to maintain visual consistency in different scene switches. For example, the user requires the watermark to fade in and out between different scenes or to follow a specific object in a dynamic video.

[0080] In some embodiments, the method further comprises:

[0081] Conducting content review on the custom pattern;

[0082] When it is determined that the custom pattern passes the content review, the custom pattern is preprocessed; wherein the preprocessing operation includes at least one of a denoising operation, a cropping operation, or a normalization operation.

[0083] In the embodiment of the present application, the video ringback tone is generated by the system based on the user's historical behavior data, and there is relatively no risk in terms of content. However, for the custom pattern, it is uploaded by the user himself, and there may be some sensitive information that needs to be avoided. Therefore, in the embodiment of the present application, the content of the custom pattern can be reviewed separately to detect whether it contains content that is not suitable for display. If so, the generation task can be terminated and the user can be prompted to re-upload the custom pattern. If not, it can be determined that the custom pattern has passed the content review, and it can be pre-processed accordingly. For example, denoising, cropping or normalization operations can be performed, and this application does not limit this.

[0084] The technical solution in the embodiment of this application, combined with the intelligent generation of Stable Diffusion, the dynamic synchronization of EbSynth and the precise control of ControlNet, not only achieves highly customized visual effects, but also ensures the natural integration and stable display of watermarks in dynamic videos. Whether it is used for brand promotion, personality display, or copyright protection, this solution can meet the diverse needs of users and provide a flexible and efficient solution.

[0085] Please refer to Figure 3 , Figure 3A schematic diagram of the application process of a method for generating a personalized video ringback tone provided in an embodiment of the present application is shown. In the embodiment of the present application, a user can generate a personalized video ringback tone through a third-party application, and the third-party application can call other AI services to realize the processing of personalized video ringback tone, and the present application does not impose any restrictions on this.

[0086] Some specific application examples of this application are given below:

[0087] 1. Accurately control the dynamic performance of brand logo:

[0088] Users upload brand logos and hope that the watermarks will interact with the characters in the video scene. Stable Diffusion is used to generate a logo that matches the style. ControlNet controls the shape and position of the watermark to ensure that the logo always follows the movement of the characters in the video, and EbSynth achieves dynamic synchronization.

[0089] 2. Dynamic QR code and precise positioning:

[0090] Users require that the QR code in the ring tone video gradually appears at a specific location and can be scanned. StableDiffusion generates the QR code, ControlNet controls the precise positioning of the QR code in the picture to ensure seamless integration with scene elements, and EbSynth dynamically adjusts the QR code display process.

[0091] 3. Personalized copyright protection of invisible signature:

[0092] The user inputs a personalized signature or logo as an invisible watermark, which is embedded into the video texture through Stable Diffusion. ControlNet ensures that the signature remains consistent in complex scenes, and EbSynth is responsible for the dynamic migration and transition of the watermark. Invisible watermarks are difficult to detect in videos and can be extracted and verified through specific algorithms.

[0093] It is understandable that the technical solution in the embodiment of the present application realizes the innovation of personalized customization, dynamic visual effects, and invisible copyright protection in video ringback tone. It combines advanced AI generation technology and animation synchronization function, which not only improves the expressiveness and flexibility of watermarks, but also greatly enriches the creative expression of users.

[0094] Reference Figure 4 In an embodiment of the present application, a device for generating a personalized video ringback tone is also provided, including:

[0095] The acquisition unit 410 is used to acquire the custom pattern and text description information uploaded by the user; wherein the text description information is used to indicate that a corresponding watermark is added to the video ringback tone according to the custom pattern and indicates the display effect of the watermark;

[0096] A generating unit 420 is used to obtain the historical behavior data of the user, and generate an initial video ring back tone corresponding to the user according to the historical behavior data;

[0097] The processing unit 430 is used to generate a basic watermark in the initial video ring back tone according to the custom pattern and the text description information by using the Stable Diffusion technology;

[0098] The adjustment unit 440 is used to adjust the basic watermark according to the text description information through ControlNet to obtain a target video ringback tone, and feed the target video ringback tone back to the user.

[0099] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0100] Reference Figure 5 , an embodiment of the present application provides an electronic device, including:

[0101] at least one processor 510;

[0102] At least one memory 520, used to store at least one program;

[0103] When at least one program is executed by at least one processor 510, at least one processor 510 implements the above-mentioned method for generating personalized video ringback tone.

[0104] Similarly, the contents of the above method embodiments are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0105] The embodiment of the present application further provides a computer-readable storage medium, in which a program executable by the processor 510 is stored. When the program executable by the processor 510 is executed by the processor 510, it is used to execute the above-mentioned method for generating personalized video ringback tone.

[0106] Similarly, the contents of the above method embodiments are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0107] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the application is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0108] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present application. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional techniques of the engineer. Therefore, those skilled in the art can implement the present application set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the attached claims and their equivalents.

[0109] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0111] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or processing in another suitable manner as necessary, and then stored in a computer memory.

[0112] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] In the above description of this specification, the description with reference to the terms "one embodiment / example", "another embodiment / example" or "certain embodiments / examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0114] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0115] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Technical personnel familiar with the field can make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for generating a personalized video ringback tone, characterized in that: The method comprises: Obtaining a custom pattern and text description information uploaded by a user; wherein the text description information is used to indicate that a corresponding watermark is added to the video ringback tone according to the custom pattern and to indicate a display effect of the watermark; Acquire historical behavior data of the user, and generate an initial video ringback tone corresponding to the user according to the historical behavior data; Generate a basic watermark in the initial video ring back tone according to the custom pattern and the text description information by using the Stable Diffusion technology; Through ControlNet, the basic watermark is adjusted according to the text description information to obtain a target video ringback tone, and the target video ringback tone is fed back to the user.

2. The method for generating a personalized video ringback tone according to claim 1, characterized in that: The obtaining of the historical behavior data of the user includes: Obtaining identity information of the user; According to the identity information, a historical behavior database is searched and queried to obtain the historical behavior data of the user.

3. The method for generating a personalized video ringback tone according to claim 2, characterized in that: The historical behavior data includes the user's video browsing data, interaction data and playback habit information.

4. The method for generating a personalized video ringback tone according to claim 1, characterized in that: The method further comprises: By using EbSynth technology, the basic watermark is dynamically migrated between multiple frames in the initial video ringback tone; Alternatively, a key frame in the initial video ring back tone is identified, and the position of the basic watermark is adjusted in the key frame by using the EbSynth technology.

5. The method for generating a personalized video ringback tone according to claim 1, characterized in that: The method further comprises: Conducting content review on the custom pattern; When it is determined that the custom pattern passes the content review, the custom pattern is preprocessed; wherein the preprocessing operation includes at least one of a denoising operation, a cropping operation, or a normalization operation.

6. The method for generating a personalized video ringback tone according to claim 1, characterized in that: The text description information is used to indicate at least one of the position, size, transparency, dynamic effect, and display time of the watermark.

7. A device for generating personalized video ringback tone, characterized in that: The device comprises: An acquisition unit, used to acquire the custom pattern and text description information uploaded by the user; wherein the text description information is used to indicate that a corresponding watermark is added to the video ringback tone according to the custom pattern and to indicate the display effect of the watermark; A generating unit, configured to obtain historical behavior data of the user, and generate an initial video ringback tone corresponding to the user according to the historical behavior data; A processing unit, configured to generate a basic watermark in the initial video ring back tone according to the custom pattern and the text description information by using a Stable Diffusion technology; The adjustment unit is used to adjust the basic watermark according to the text description information through ControlNet to obtain a target video ring back tone, and feed the target video ring back tone to the user.

8. The device for generating a personalized video ringback tone according to claim 7, characterized in that: The text description information is used to indicate at least one of the position, size, transparency, dynamic effect, and display time of the watermark.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a method for generating a personalized video ringback tone as described in any one of claims 1-6.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to implement a method for generating a personalized video ringback tone as described in any one of claims 1 to 6 when executed by the processor.

Images