Method, device, equipment and medium for generating video ringback tone

Abstract

The present application discloses a method, device, equipment and storage medium for generating a video ring back tone, which receives a video ring back tone generation request and a material image of a target user, determines a target video ring back tone template set from an original video ring back tone template set; extracts material elements corresponding to each material image through an image recognition algorithm; for a video ring back tone template, selects a first number of material images as insertion images, and determines a plurality of image insertion sorting solutions corresponding to the video ring back tone template through a permutation and combination method; determines the matching degree of each image insertion sorting solution corresponding to the video ring back tone template according to the material elements and the recommended elements, and records the first image insertion sorting solution corresponding to each video ring back tone template; determines a second image insertion sorting solution according to the first image insertion sorting solution, and generates a target video ring back tone. The method can improve the production efficiency and generation quality of video ring back tone. The present application can be widely used in the field of video ring back tone technology.

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 a 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, more and more customers are starting to use video ringback tone services, which have gradually become one of the important means for customers to display a good corporate image and spread valuable information. With the prosperous development of video ringback tone services, how to make a ringback tone that suits them has become the focus of customers.

[0003] In the related technology, the platform generally provides users with the function of making video ringback rings by themselves. However, the method of making video ringback rings is generally too complicated, and it is difficult for first-time users to independently make video ringback rings that meet their needs. Some platforms provide video ringback ring templates, and users can make video ringback rings based on templates, which improves the production efficiency to a certain extent and lowers the technical threshold. However, in actual applications, it is found that due to the large differences in the needs of different users, as the platform is constantly updated, the number of video ringback ring templates is rapidly increasing, and it is difficult for users to quickly find video ringback ring templates that suit their needs, resulting in difficulty in use, low production efficiency of video ringback rings, average generation quality, and poor experience.

[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 embodiments of the present application is to provide a method, apparatus, device and storage medium for generating a 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 video ringback tone, the method comprising:

[0009] Receive a video ringback tone generation request from a target user and a number of material images uploaded by the target user, and determine a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a number of video ringback tone templates, each of which has image requirement information corresponding to it, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each of the inserted images;

[0010] Extracting material elements corresponding to each of the material images by using an image recognition algorithm;

[0011] For each of the video ring back tone templates, selecting the first number of the material images as insertion images, and determining multiple image insertion sorting solutions corresponding to the video ring back tone template by permutation and combination; wherein the image insertion sorting solution is used to indicate the sorting order of the material images inserted as insertion images into the video ring back tone template;

[0012] Determine the matching degree of each of the image insertion sorting solutions corresponding to the video ring back tone template according to the material element and the recommendation element, and record the first image insertion sorting solution corresponding to each of the video ring back tone templates; wherein the first image insertion sorting solution is the image insertion sorting solution with the greatest matching degree corresponding to each of the video ring back tone templates;

[0013] Determine a second image insertion sorting solution according to the first image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution;

[0014] A target video ring back tone is generated according to the video ring back tone template and the material image corresponding to the second image insertion sorting solution and the sorting order indicated by the second image insertion sorting solution.

[0015] In addition, the method for generating a video ringback tone according to the above embodiment of the present application may also have the following additional technical features:

[0016] Further, in one embodiment of the present application, determining a target video RBT template set corresponding to the video RBT generation request from the original video RBT template set includes:

[0017] Parse the video ringback tone generation request to determine the industry information corresponding to the target video ringback tone generated by the video ringback tone generation request;

[0018] Determining an industry video ringback tone template set from the original video ringback tone template set according to the industry information;

[0019] Counting a second number of the material images;

[0020] The target video ringback tone template set is obtained by removing corresponding video ringback tone templates whose first number is greater than the second number from the industry video ringback tone template set.

[0021] Furthermore, in one embodiment of the present application, extracting the material elements corresponding to each of the material images by using an image recognition algorithm includes:

[0022] Inputting the material image into a trained image element recognition model;

[0023] The material image is processed by the image element recognition model to obtain a first element recognition result; wherein the first element recognition result is used to identify a recognition result of a material element corresponding to the material image.

[0024] Furthermore, in one embodiment of the present application, the image element recognition model is trained by the following steps:

[0025] Acquire a number of sample images and element labels corresponding to the sample images; wherein the element labels are used to identify the real results of the material elements corresponding to the sample images;

[0026] Inputting the sample image into the image element recognition model to be trained;

[0027] Processing the sample image through the image element recognition model to obtain a second element recognition result; wherein the second element recognition result is used to identify the recognition result of the material element corresponding to the sample image;

[0028] Determining a training loss value according to the second element recognition result and the element label;

[0029] According to the loss value, the parameters of the image element recognition model are updated to obtain a trained image element recognition model.

[0030] Furthermore, in one embodiment of the present application, after the step of acquiring a plurality of sample images, the method further includes:

[0031] Preprocessing the sample image;

[0032] The preprocessing includes at least one of image scaling, image cropping, normalization, noise processing, image flipping, and contrast enhancement.

[0033] Further, in an embodiment of the present application, determining the matching degree of each image insertion sorting solution corresponding to the video ringback tone template according to the material element and the recommendation element includes:

[0034] determining, according to the sorting order indicated by the image insertion sorting solution, a correspondence between each of the material elements and the recommended elements, and determining the material elements and the recommended elements having the correspondence as element pairs;

[0035] For each element pair, comparing whether the material element and the recommended element therein match;

[0036] Counting the proportion of element pairs matching the material element and the recommended element in all the element pairs, and determining the matching degree of the image insertion sorting solution according to the proportion;

[0037] The ratio is positively correlated with the matching degree.

[0038] Further, in one embodiment of the present application, the step of receiving a video ringback tone generation request from a target user includes:

[0039] The video ringback tone generation request is received according to the interactive operation of the target user.

[0040] On the other hand, an embodiment of the present application provides a device for generating a video ringback tone, the device comprising:

[0041] A receiving unit, configured to receive a video ringback tone generation request from a target user and a plurality of material images uploaded by the target user, and determine a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a plurality of video ringback tone templates, each of the video ringback tone templates corresponds to image requirement information, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each of the inserted images;

[0042] An extraction unit, used for extracting material elements corresponding to each of the material images through an image recognition algorithm;

[0043] A selection unit, configured to select the first number of the material images as insertion images for each of the video ring back tone templates, and determine a plurality of image insertion sorting solutions corresponding to the video ring back tone template by permutation and combination; wherein the image insertion sorting solution is used to indicate a sorting order in which the material images are inserted as insertion images into the video ring back tone template;

[0044] A recording unit, used to determine the matching degree of each image insertion sorting solution corresponding to the video ring back tone template according to the material element and the recommended element, and record the first image insertion sorting solution corresponding to each video ring back tone template; wherein the first image insertion sorting solution is the image insertion sorting solution with the greatest matching degree corresponding to each video ring back tone template;

[0045] A comparison unit, configured to determine a second image insertion sorting solution according to the first image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution;

[0046] A generating unit is used to generate a target video ring back tone according to the video ring back tone template corresponding to the second image insertion sorting solution, the material image and the sorting order indicated by the second image insertion sorting solution.

[0047] On the other hand, an embodiment of the present application provides an electronic device, including:

[0048] at least one processor;

[0049] at least one memory for storing at least one program;

[0050] 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 a video color ring back tone.

[0051] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned method for generating a video ringback tone.

[0052] 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:

[0053] The video ringback tone generation method, device, equipment and storage medium disclosed in the embodiments of the present application receive a video ringback tone generation request of a target user and a number of material images uploaded by the target user, and determine a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a number of video ringback tone templates, each of which corresponds to image requirement information, and the image requirement information is used to indicate the first number of inserted images required to use the video ringback tone template and the recommended elements corresponding to each inserted image; the material elements corresponding to each of the material images are extracted through an image recognition algorithm; for each of the video ringback tone templates, the first number of the material images are selected as inserted images, and the video ringback tone template is determined by permutations and combinations. Corresponding multiple image insertion sorting solutions; wherein the image insertion sorting solution is used to indicate the sorting order of the material image inserted as an inserted image into the video ring back tone template; according to the material element and the recommended element, determine the matching degree of each image insertion sorting solution corresponding to the video ring back tone template, and record the first image insertion sorting solution corresponding to each video ring back tone template; wherein the first image insertion sorting solution is the image insertion sorting solution with the largest matching degree corresponding to each video ring back tone template; according to the first image insertion sorting solution, determine the second image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution; according to the video ring back tone template, the material image corresponding to the second image insertion sorting solution and the sorting order indicated by the second image insertion sorting solution, generate the target video ring back tone. This method can help users quickly find the video ring back tone template that suits their needs. Users only need to upload the material image they want to use to automatically generate the video ring back tone. It is easy to use, has high production efficiency, and can improve the generation quality of the video ring back tone, thereby helping to improve the user experience of using the video ring back tone service. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] 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.

[0055] Figure 1 A schematic diagram of an implementation environment of a method for generating a video ringback tone provided in an embodiment of the present application;

[0056] Figure 2 A schematic diagram of a flow chart of a method for generating a video ringback tone provided in an embodiment of the present application;

[0057] Figure 3 A schematic diagram of the structure of a device for generating a video ringback tone provided in an embodiment of the present application;

[0058] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] 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.

[0060] 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.

[0061] 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.

[0062] First, some nouns involved in this application are analyzed:

[0063] 1) Artificial intelligence is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0064] 2) Machine learning is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning usually includes artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and learning by teaching.

[0065] 3) Deep learning, a branch of machine learning, is a machine learning method based on artificial neural networks. Compared with traditional machine learning methods, deep learning learns the feature representation of data through a multi-level neural network model, thereby achieving the learning and modeling of complex patterns and relationships. Deep learning has a wide range of applications in various fields, including computer vision, natural language processing, speech recognition, recommendation systems, etc. In the field of computer vision, deep learning can be used for tasks such as image classification, object detection, and image generation; in the field of natural language processing, deep learning can be used for tasks such as text classification, machine translation, and sentiment analysis.

[0066] 4) Image recognition, an AI technology that aims to enable computers to recognize and understand objects, scenes, and features in digital images. By using deep learning and neural network algorithms, image recognition can analyze and classify images to identify what is contained in the image. This technology has a wide range of applications in many fields, such as medical image analysis, security monitoring, self-driving cars, image search, and social media.

[0067] At present, with the development of information technology, more and more applications are being developed to provide services for users. For example, more and more customers are starting to use video ringback tone services, which have gradually become one of the important means for customers to display a good corporate image and spread valuable information. With the prosperous development of video ringback tone services, how to make a ringback tone that suits them has become the focus of customers.

[0068] In the related technology, the platform generally provides users with the function of making video ringback rings by themselves. However, the method of making video ringback rings is generally too complicated, and it is difficult for first-time users to independently make video ringback rings that meet their needs. Some platforms provide video ringback ring templates, and users can make video ringback rings based on templates, which improves the production efficiency to a certain extent and lowers the technical threshold. However, in actual applications, it is found that due to the large differences in the needs of different users, as the platform is constantly updated, the number of video ringback ring templates is rapidly increasing, and it is difficult for users to quickly find video ringback ring templates that suit their needs, resulting in difficulty in use, low production efficiency of video ringback rings, average generation quality, and poor experience.

[0069] In view of this, a method for generating a video ringback tone is provided in an embodiment of the present application, which receives a video ringback tone generation request of a target user and a number of material images uploaded by the target user, and determines a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a number of video ringback tone templates, each of the video ringback tone templates corresponds to image requirement information, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each inserted image; the material elements corresponding to each of the material images are extracted by an image recognition algorithm; for each of the video ringback tone templates, the first number of the material images are selected as inserted images, and the corresponding image of the video ringback tone template is determined by permutations and combinations. A plurality of image insertion sorting solutions; wherein the image insertion sorting solution is used to indicate the sorting order of the material image inserted as an inserted image into the video ring back tone template; according to the material element and the recommended element, the matching degree of each image insertion sorting solution corresponding to the video ring back tone template is determined, and the first image insertion sorting solution corresponding to each video ring back tone template is recorded; wherein the first image insertion sorting solution is the image insertion sorting solution with the largest matching degree corresponding to each video ring back tone template; according to the first image insertion sorting solution, a second image insertion sorting solution is determined; wherein the second image insertion sorting solution is the largest first image insertion sorting solution; according to the video ring back tone template, the material image corresponding to the second image insertion sorting solution and the sorting order indicated by the second image insertion sorting solution, a target video ring back tone is generated. The method can help users quickly find a video ring back tone template that suits their needs. Users only need to upload the material image they want to use to automatically generate a video ring back tone. It is easy to use, has high production efficiency, and can improve the generation quality of video ring back tone, thereby helping to improve the user experience of using the video ring back tone service.

[0070] Please refer to Figure 1 , Figure 1The schematic diagram of the implementation environment of a method for generating a video ring back 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.

[0071] Specifically, the method for generating a 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.

[0072] 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.

[0073] 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.

[0074] 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 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.

[0075] Next, in combination with the introduction of the aforementioned implementation environment, a method for generating a video ringback tone provided in an embodiment of the present application is introduced and illustrated.

[0076] Please refer to Figure 2 , Figure 2 : is a schematic diagram of a method for generating a video ringback tone provided in an embodiment of the present application. The method for generating a video ringback tone includes but is not limited to:

[0077] Step 210: receiving a video ringback tone generation request from a target user and a plurality of material images uploaded by the target user, and determining a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a plurality of video ringback tone templates, each of the video ringback tone templates corresponds to image requirement information, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each of the inserted images;

[0078] Step 220: extracting material elements corresponding to each of the material images through an image recognition algorithm;

[0079] Step 230: For each of the video ring back tone templates, select the first number of the material images as insertion images, and determine multiple image insertion sorting solutions corresponding to the video ring back tone template by permutation and combination; wherein the image insertion sorting solution is used to indicate the sorting order of the material images inserted as insertion images into the video ring back tone template;

[0080] Step 240: Determine the matching degree of each of the image insertion sorting solutions corresponding to the video ring back tone template according to the material element and the recommendation element, and record the first image insertion sorting solution corresponding to each of the video ring back tone templates; wherein the first image insertion sorting solution is the image insertion sorting solution with the greatest matching degree corresponding to each of the video ring back tone templates;

[0081] Step 250: Determine a second image insertion sorting solution according to the first image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution;

[0082] Step 260: Generate a target video ringback tone according to the video ringback tone template and the material image corresponding to the second image insertion sorting solution and the sorting order indicated by the second image insertion sorting solution.

[0083] In an embodiment of the present application, a method for generating a video ringback tone is provided, which can help users quickly find a video ringback tone template that suits their needs. Users only need to upload the material images they want to use to automatically generate the video ringback tone. The method is easy to use and has high production efficiency. It can also improve the generation quality of the video ringback tone, thereby helping to improve the user experience of the video ringback tone service.

[0084] Specifically, in the embodiment of the present application, when generating a video ringback tone, the user who needs to perform the video ringback tone generation service is recorded as the target user, and the video ringback tone generation request of the target user and several material images uploaded by the target user can be received. Specifically, in the embodiment of the present application, there is no restriction on the specific triggering method of the video ringback tone generation request. It can be triggered by the interactive operation of the target user. For example, the target user can perform the interactive operation of the touch screen on the terminal device to initiate the video ringback tone generation request, or initiate the video ringback tone generation request through voice interaction. Based on these interactive operations of the target user, the video ringback tone generation request can be received. At the same time, in the embodiment of the present application, several material images uploaded by the target user are also obtained. The number of material images can be one or more (generally multiple). The material images here can be inserted into the specified video ringback tone template later, so as to generate the video ringback tone. The main task in the present application is to help the target user find a suitable video ringback tone template.

[0085] After obtaining the target user's video ringback tone generation request and material image, in the embodiment of the present application, the video ringback tone template set corresponding to the video ringback tone generation request can be determined from the original video ringback tone template set, and recorded as the target video ringback tone template set. The target video ringback tone template set may include multiple video ringback tone templates, and these video ringback tone templates correspond to image requirement information, which is used to indicate the number of inserted images that need to be provided when using the video ringback tone template and the recommended elements corresponding to each inserted image.

[0086] It is understandable that there are often multiple images in a video ringback tone. When a user makes a video ringback tone, the video ringback tone template can provide a frame-type content, and the image therein is generally provided by the user. In the embodiment of the present application, for each video ringback tone template, it corresponds to the number of inserted images that need to be inserted, and the number is recorded as the first number. In addition, different video ringback tone templates may be applicable to different business scenarios. Therefore, each applicable inserted image also corresponds to a recommended element. The recommended element is used to indicate what kind of element needs to be included in the inserted image, such as whether it needs to include people, animals or certain products. When the user uses the video ringback tone template, he sees the image requirement information and can collect the corresponding material image according to the image requirement information, thereby inserting it into the video ringback tone template to generate the video ringback tone. In the embodiment of the present application, the target video ringback tone template set includes multiple video ringback tone templates, each video ringback tone template corresponds to the image requirement information, the first number of inserted images required by different video ringback tone templates may be different, and the recommended elements corresponding to each inserted image may also be different.

[0087] It should be pointed out that since a video ringback tone template generally requires multiple inserted images, and each inserted image corresponds to its own recommended element, the inserted images required in the video ringback tone template can be sorted accordingly. When using the video ringback tone template, the inserted material images need to correspond to the position order of the recommended elements corresponding to each inserted image in the sort.

[0088] In an embodiment of the present application, for the acquired material images, an image recognition algorithm can be used to extract the material elements therein. Specifically, the material element is the most representative element category in the image, for example, it can be a category of people, animals or products, etc., and the present application does not limit this. For each video ringtone template, a first number of material images can be selected from the material images uploaded by the target user as inserted images, and the multiple image insertion sorting solutions corresponding to the video ringtone template can be determined by permutations and combinations. For example, for example, the number of material images uploaded by the target user is m, and the material elements corresponding to the material images are represented as P, then the set of material elements corresponding to the material images can be represented as P = (P1, P2, ...P m ), where m is a positive integer. For a video ring back tone template, the first number of inserted images to be provided is recorded as n, and the recommended elements corresponding to the inserted images are expressed as V. Then the set of recommended elements required by the video ring back tone template can be expressed as V = (V1, V2, ... V n ), where n is a positive integer. In the embodiment of the present application, n images can be selected from m material images (the default value is m≥n), and the number that can be selected is C(m,n). After selecting n material images, since the positions where each material image can be inserted are diverse, there are many different sorting combinations, and the number here can be expressed as D(n,n). Therefore, for a video ringtone template with a first number of n, the number of image insertion sorting solutions can be expressed as Z=C(m,n)×D(n,n). Each image insertion sorting solution here corresponds to a sorting order in which n material images are inserted into the video ringtone template as inserted images.

[0089] In the embodiment of the present application, after obtaining the image insertion sorting solution, the matching degree of each image insertion sorting solution corresponding to the video ring back tone template can be determined according to the material element and the recommended element. The matching degree here can be used to characterize the matching degree of the image insertion sorting solution and the insertion image that needs to be provided corresponding to the video ring back tone template. The higher the matching degree, the more suitable the insertion order of the material image given by the image insertion sorting solution is for the video ring back tone template. According to the obtained matching degree, the first image insertion sorting solution corresponding to the video ring back tone template can be determined, which is the image insertion sorting solution with the largest matching degree corresponding to the video ring back tone template. In the embodiment of the present application, since there are multiple video ring back tone templates, each video ring back tone template corresponds to a first image insertion sorting solution, and different first image insertion sorting solutions have different matching degrees. Therefore, the largest first image insertion sorting solution can be determined according to the size of the first image insertion sorting solution, and it is recorded as the second image insertion sorting solution. It can be understood that the matching degree corresponding to the second image insertion sorting solution is the largest among all the image insertion sorting solutions, the video ringback tone template corresponding to it is the most suitable, and the selection and insertion order of the given material images are also the most suitable. Therefore, the target video ringback tone can be generated according to the video ringback tone template corresponding to the second image insertion sorting solution, the material image and the sorting order indicated by the second image insertion sorting solution.

[0090] It can be understood that the method for generating video ringback tone in the embodiment of the present application can help users quickly find video ringback tone templates that suit their needs. Users only need to upload the material images they want to use to automatically generate video ringback tone. It is easy to use and has high production efficiency. It can also improve the generation quality of video ringback tone, thereby helping to improve the user experience of using the video ringback tone service.

[0091] Of course, in the embodiment of the present application, the generated target video ringback tone can be sent to the target user, and the target user can decide whether to use the target video ringback tone. If satisfied, the target user can select related ringtone content to synthesize the audio content of the target video ringback tone. If dissatisfied, the target user can also use a self-made method to generate a video ringback tone. The present application does not impose any restrictions on this.

[0092] In some embodiments, determining a target video RBT template set corresponding to the video RBT generation request from the original video RBT template set includes:

[0093] Parse the video ringback tone generation request to determine the industry information corresponding to the target video ringback tone generated by the video ringback tone generation request;

[0094] Determining an industry video ringback tone template set from the original video ringback tone template set according to the industry information;

[0095] Counting a second number of the material images;

[0096] The target video ringback tone template set is obtained by removing corresponding video ringback tone templates whose first number is greater than the second number from the industry video ringback tone template set.

[0097] In an embodiment of the present application, the video ringback ring templates can be divided according to different industries in advance. When determining the target video ringback ring template set, the video ringback ring generation request can be parsed to first determine the industry information corresponding to the target video ringback ring that the target user wants to generate. Then, based on the industry information, the industry video ringback ring template set can be determined from the original video ringback ring template set. Next, it can be understood that some video ringback ring templates may require more inserted images. If the target user uploads insufficient material images, these video ringback ring templates cannot be used normally. Therefore, the second number of material images can be counted, and based on the second number, the industry video ringback ring template set can be further deleted, and the video ringback ring templates whose first number is greater than the second number are removed to obtain the target video ringback ring template set.

[0098] In some embodiments, extracting the material elements corresponding to each of the material images by using an image recognition algorithm includes:

[0099] Inputting the material image into a trained image element recognition model;

[0100] The material image is processed by the image element recognition model to obtain a first element recognition result; wherein the first element recognition result is used to identify a recognition result of a material element corresponding to the material image.

[0101] In an embodiment of the present application, an image element recognition model can be used when extracting material elements corresponding to a material image. The image element recognition model can be used to extract element categories of the most important content in the material image. Specifically, the material image can be input into a trained image element recognition model and processed by the image element recognition model to obtain an element recognition result, which is recorded as the first element recognition result, and can be used to identify the recognition result of the material element corresponding to the material image.

[0102] It should be noted that when using the image element recognition model, it is necessary to train it first to improve the effect of its application. Specifically, when training it, several sample images and element labels corresponding to the sample images can be obtained, and the element labels can be used to identify the real results of the material elements corresponding to the sample images. Then, the sample images are input into the image element recognition model for prediction, and the corresponding element recognition results are obtained, which are recorded as the second element recognition results.

[0103] After obtaining the second element recognition result, the loss value in the training process can be determined based on the second element recognition result and the element label. It can be understood that the closer the element label and the second element recognition result are, the smaller the loss value is, and the better the prediction effect of the image element recognition model is, indicating that the performance is closer to expectations; the closer the element label and the second element recognition result are, the worse the prediction effect of the image element recognition model is, and the larger the loss value is, indicating that the performance is further from the expected effect.

[0104] For an artificial intelligence model, the accuracy of its prediction can be measured by a loss function, which is defined on a single (group) of training data and is used to measure the prediction error of a training data. During actual training, a training data set (sample image data set) has a lot of training data, such as the sample image data set in the embodiment of the present application includes several sample images. Therefore, a cost function is generally used to measure the overall error of the training data set. The cost function is defined on the entire training data set and is used to calculate the average value of the prediction error of all training data, which can better measure the prediction effect of the model. In the embodiment of the present application, when determining the loss value of the training, the loss values ​​corresponding to all sample images participating in the training in the current round can be calculated first, and then the average value is calculated to obtain the loss value corresponding to the current round, thereby updating the parameters of the image element recognition model. There are many types of commonly used loss functions, such as 0-1 loss function, square loss function, absolute loss function, logarithmic loss function, cross entropy loss function, etc., which can all be used as loss functions of machine learning models, which will not be described one by one here. In the embodiment of the present application, any one of the loss functions can be selected to determine the loss value of training, that is, the loss value between the second element recognition result and the element label.

[0105] In the embodiment of the present application, the parameter update of the image element recognition model can be performed in a cyclic iteration manner. That is, after updating the parameters of a round of image element recognition model, the image element recognition model with updated parameters is continued to be used for prediction to determine a new loss value, and then the parameters of the image element recognition model are updated again. This cycle is repeated until the pre-set training end condition is met, and the training can be considered completed, and a trained image element recognition model is obtained.

[0106] In some embodiments, the sample image may also be preprocessed, and the preprocessing type may include at least one of the following:

[0107] Image scaling: reduce or enlarge the size of the image to adapt it to the input size requirements of the model. Image cropping: crop the image to remove irrelevant parts or adjust the size of the area of ​​interest. Normalization: scale the pixel values ​​of the image to a specific range to better train the model. Noise processing: remove noise from the image and improve image quality. Image rotation and flipping: change the angle or direction of the image to increase the diversity of the data and enhance the generalization ability of the model. Enhance contrast: increase the contrast between image pixels to make the image clearer. Of course, the preprocessing operations that can be applied in the embodiments of the present application are not limited to this.

[0108] In some embodiments, determining the matching degree of each image insertion sorting solution corresponding to the video ring back tone template according to the material element and the recommendation element includes:

[0109] determining, according to the sorting order indicated by the image insertion sorting solution, a correspondence between each of the material elements and the recommended elements, and determining the material elements and the recommended elements having the correspondence as element pairs;

[0110] For each element pair, comparing whether the material element and the recommended element therein match;

[0111] Counting the proportion of element pairs matching the material element and the recommended element in all the element pairs, and determining the matching degree of the image insertion sorting solution according to the proportion;

[0112] The ratio is positively correlated with the matching degree.

[0113] In the embodiment of the present application, when determining the matching degree of the image insertion sorting solution, the corresponding relationship between the material element and the recommended element can be determined according to the sorting order indicated by the image insertion sorting solution, and they are recorded as an element pair. For example, (P1, V1) can represent an element pair. For each element pair, it is possible to compare whether the material element and the recommended element match. The matching here can be whether the two are consistent, or the similarity between the two can be calculated, and whether their similarity is higher than a preset threshold. If they are consistent or the similarity is higher than a preset threshold, it is considered that the two match. Then, the proportion of element pairs matching the material element and the recommended element in all element pairs of the image insertion sorting solution can be counted, and the matching degree of the image insertion sorting solution is determined according to the numerical value of the proportion. The two can be positively correlated, that is, the higher the proportion, the greater the matching degree of the image insertion sorting solution. In the embodiment of the present application, there is no restriction on the functional relationship between the two. For example, in some embodiments, the numerical value of the proportion can be directly determined as the matching degree of the image insertion sorting solution.

[0114] Exemplarily, in the embodiment of the present application, the following formula may be used to determine the matching degree of the image insertion sorting solution:

[0115]

[0116] In the formula, X represents the matching degree, and the function f(P, V) is a containment function. If V = P or V contains P, the value is 1, otherwise the value is 0. For example, for f(P1, V1), if the material element P1 is consistent with the recommended element V1, or the content of the recommended element V1 includes the material element P1, then the value of f(P1, V1) is 1, otherwise it is 0.

[0117] Reference Figure 3 In an embodiment of the present application, a device for generating a video ringback tone is also provided, including:

[0118] The receiving unit 310 is used to receive a video ringback tone generation request from a target user and a plurality of material images uploaded by the target user, and determine a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a plurality of video ringback tone templates, each of which has image requirement information corresponding to it, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each of the inserted images;

[0119] An extraction unit 320 is used to extract material elements corresponding to each of the material images through an image recognition algorithm;

[0120] The selection unit 330 is used to select the first number of the material images as insertion images for each of the video ring back tone templates, and determine a plurality of image insertion sorting solutions corresponding to the video ring back tone template by permutation and combination; wherein the image insertion sorting solution is used to indicate the sorting order of the material images as insertion images inserted into the video ring back tone template;

[0121] The recording unit 340 is used to determine the matching degree of each image insertion sorting solution corresponding to the video ring back tone template according to the material element and the recommended element, and record the first image insertion sorting solution corresponding to each video ring back tone template; wherein the first image insertion sorting solution is the image insertion sorting solution with the greatest matching degree corresponding to each video ring back tone template;

[0122] A comparison unit 350 is used to determine a second image insertion sorting solution according to the first image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution;

[0123] The generating unit 360 is configured to generate a target video ring back tone according to the video ring back tone template corresponding to the second image insertion sorting solution, the material image, and the sorting order indicated by the second image insertion sorting solution.

[0124] 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.

[0125] Reference Figure 4 , an embodiment of the present application provides an electronic device, including:

[0126] at least one processor 410;

[0127] At least one memory 420, used to store at least one program;

[0128] When at least one program is executed by at least one processor 410, at least one processor 410 implements the above-mentioned method for generating a video ringback tone.

[0129] 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.

[0130] The embodiment of the present application further provides a computer-readable storage medium, in which a program executable by the processor 410 is stored. When the program executable by the processor 410 is executed by the processor 410, it is used to execute the above-mentioned method for generating a video ringback tone.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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 video ring back tone, characterized in that: The method comprises: Receive a video ringback tone generation request from a target user and a number of material images uploaded by the target user, and determine a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a number of video ringback tone templates, each of which has image requirement information corresponding to it, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each of the inserted images; Extracting material elements corresponding to each of the material images by using an image recognition algorithm; For each of the video ring back tone templates, selecting the first number of the material images as insertion images, and determining multiple image insertion sorting solutions corresponding to the video ring back tone template by permutation and combination; wherein the image insertion sorting solution is used to indicate the sorting order of the material images inserted as insertion images into the video ring back tone template; Determine the matching degree of each of the image insertion sorting solutions corresponding to the video ring back tone template according to the material element and the recommendation element, and record the first image insertion sorting solution corresponding to each of the video ring back tone templates; wherein the first image insertion sorting solution is the image insertion sorting solution with the greatest matching degree corresponding to each of the video ring back tone templates; Determine a second image insertion sorting solution according to the first image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution; generating a target video ringback tone according to the video ringback tone template and the material image corresponding to the second image insertion sorting solution and the sorting order indicated by the second image insertion sorting solution; The determining, according to the material element and the recommendation element, the matching degree of each image insertion sorting solution corresponding to the video ringback tone template comprises: determining, according to the sorting order indicated by the image insertion sorting solution, a correspondence between each of the material elements and the recommended elements, and determining the material elements and the recommended elements having the correspondence as element pairs; For each element pair, comparing whether the material element and the recommended element therein match; Counting the proportion of element pairs matching the material element and the recommended element in all the element pairs, and determining the matching degree of the image insertion sorting solution according to the proportion; The ratio is positively correlated with the matching degree.

2. The method for generating a video ringback tone according to claim 1, characterized in that: The step of determining a target video RBT template set corresponding to the video RBT generation request from the original video RBT template set includes: Parse the video ringback tone generation request to determine the industry information corresponding to the target video ringback tone generated by the video ringback tone generation request; Determining an industry video ringback tone template set from the original video ringback tone template set according to the industry information; Counting a second number of the material images; The target video ringback tone template set is obtained by removing corresponding video ringback tone templates whose first number is greater than the second number from the industry video ringback tone template set.

3. The method for generating a video ringback tone according to claim 1, characterized in that: The extracting the material elements corresponding to each of the material images by using an image recognition algorithm includes: Inputting the material image into a trained image element recognition model; The material image is processed by the image element recognition model to obtain a first element recognition result; wherein the first element recognition result is used to identify a recognition result of a material element corresponding to the material image.

4. The method for generating a video ring back tone according to claim 3, characterized in that: The image element recognition model is trained by the following steps: Acquire a number of sample images and element labels corresponding to the sample images; wherein the element labels are used to identify the real results of the material elements corresponding to the sample images; Inputting the sample image into the image element recognition model to be trained; Processing the sample image through the image element recognition model to obtain a second element recognition result; wherein the second element recognition result is used to identify the recognition result of the material element corresponding to the sample image; Determining a training loss value according to the second element recognition result and the element label; According to the loss value, the parameters of the image element recognition model are updated to obtain a trained image element recognition model.

5. The method for generating a video ring back tone according to claim 4, characterized in that: After the step of acquiring a plurality of sample images, the method further comprises: Before inputting the sample image into the image element recognition model to be trained, preprocessing the sample image; The preprocessing includes at least one of image scaling, image cropping, normalization, noise processing, image flipping, and contrast enhancement.

6. A method for generating a video ringback tone according to any one of claims 1 to 5, characterized in that: The receiving a video ringback tone generation request from a target user includes: The video ringback tone generation request is received according to the interactive operation of the target user.

7. A device for generating a video ring back tone, characterized in that: The device comprises: A receiving unit, configured to receive a video ringback tone generation request from a target user and a plurality of material images uploaded by the target user, and determine a target video ringback tone template set corresponding to the video ringback tone generation request from an original video ringback tone template set; wherein the target video ringback tone template set includes a plurality of video ringback tone templates, each of the video ringback tone templates corresponds to image requirement information, and the image requirement information is used to indicate a first number of inserted images that need to be provided when using the video ringback tone template and a recommended element corresponding to each of the inserted images; An extraction unit, used for extracting material elements corresponding to each of the material images through an image recognition algorithm; A selection unit, configured to select the first number of the material images as insertion images for each of the video ring back tone templates, and determine a plurality of image insertion sorting solutions corresponding to the video ring back tone template by permutation and combination; wherein the image insertion sorting solution is used to indicate a sorting order in which the material images are inserted as insertion images into the video ring back tone template; A recording unit, used to determine the matching degree of each image insertion sorting solution corresponding to the video ring back tone template according to the material element and the recommended element, and record the first image insertion sorting solution corresponding to each video ring back tone template; wherein the first image insertion sorting solution is the image insertion sorting solution with the greatest matching degree corresponding to each video ring back tone template; A comparison unit, configured to determine a second image insertion sorting solution according to the first image insertion sorting solution; wherein the second image insertion sorting solution is the largest first image insertion sorting solution; A generating unit, configured to generate a target video ringback tone according to the video ringback tone template corresponding to the second image insertion sorting solution, the material image, and the sorting order indicated by the second image insertion sorting solution; The determining, according to the material element and the recommendation element, the matching degree of each image insertion sorting solution corresponding to the video ringback tone template comprises: determining, according to the sorting order indicated by the image insertion sorting solution, a correspondence between each of the material elements and the recommended elements, and determining the material elements and the recommended elements having the correspondence as element pairs; For each element pair, comparing whether the material element and the recommended element therein match; Counting the proportion of element pairs matching the material element and the recommended element in all the element pairs, and determining the matching degree of the image insertion sorting solution according to the proportion; The ratio is positively correlated with the matching degree.

8. 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 video ringback tone as described in any one of claims 1-6.

9. 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 video ringback tone as described in any one of claims 1 to 6 when executed by the processor.

Images