Virtual tool distribution processing method and device

Abstract

An embodiment of the present disclosure provides a method and device for processing the distribution of a virtual tool, the method comprising: obtaining tool dimension features corresponding to the virtual tool and model dimension features corresponding to the user model, inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated willingness index of the user to use the virtual tool and the user model to publish content, determining whether to distribute the virtual tool to the user terminal corresponding to the user model based on the estimated willingness index, obtaining the estimated willingness index for content publishing through the feature input model of the virtual tool and the user model, and then distributing the virtual tool based on the estimated willingness index for content publishing, so that the virtual tool distributed to the user is a virtual tool that the user is interested in, thereby improving the user's willingness to publish content and enhancing the user's creative enthusiasm.

Description

Technical Field

[0001] The present disclosure relates to the field of computer and software technology, and more particularly to a method and device for processing the distribution of virtual tools. Background Art

[0002] When users use video applications, especially short video applications, and need to make videos, the background server can send corresponding virtual tools (such as virtual props, virtual gameplay) to the user device. Users can use the virtual tools to make videos on the user device and publish them in the video application.

[0003] At present, the commonly used virtual tool distribution scheme may not distribute virtual tools that users want to use or are interested in, which in turn reduces users' willingness to make videos and affects their enthusiasm for creation and publication. Summary of the Invention

[0004] The embodiments of the present disclosure provide a method and device for processing the distribution of virtual tools to overcome the problem in the prior art that the virtual tools distributed to the user end are not the virtual tools that the user wants to use or is interested in, resulting in a decrease in the user's willingness to make videos, which in turn affects the user's submission rate.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for issuing a virtual tool, including:

[0006] Obtaining tool dimension features of a virtual tool, wherein the tool dimension features include a statistically analyzed historical user willingness index for using the virtual tool to publish content and tool attribute features of the virtual tool, wherein the virtual tool is used to add a video editing effect to an original video to obtain a target video;

[0007] Acquiring model dimension features of the user model, wherein the model dimension features include statistical historical user willingness indicators of using the user model to publish content and model attribute features of the user model;

[0008] Inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated user willingness index for using the virtual tool and the user model to publish content;

[0009] Determine whether to send the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

[0010] In a second aspect, an embodiment of the present disclosure provides a virtual tool delivery processing device, including:

[0011] Performing feature conversion processing on the tool dimension feature and the machine model dimension feature respectively to obtain sparse features of the tool dimension feature and sparse features of the machine model dimension feature;

[0012] Inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model;

[0013] Inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is an XGBoost model;

[0014] The first estimated willingness index and the second estimated willingness index are weighted averaged to obtain the final estimated willingness index.

[0015] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0016] The memory stores computer-executable instructions;

[0017] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the virtual tool delivery processing method described in the first aspect and various possible designs of the first aspect.

[0018] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the virtual tool issuance processing method described in the first aspect and various possible designs of the first aspect is implemented.

[0019] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the virtual tool distribution processing method described in the first aspect and various possible designs of the first aspect.

[0020] The present embodiment provides a method and device for processing the distribution of virtual tools. This method obtains tool dimension features corresponding to the virtual tool and model dimension features corresponding to the user model, inputs the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model, obtains an estimated willingness index of the user to use the virtual tool and the user model to publish content, determines whether to distribute the virtual tool to the user terminal corresponding to the user model based on the estimated willingness index, and distributes the virtual tool based on the estimated willingness index for content publishing obtained by inputting the features of the virtual tool and the user model into the model. This ensures that the virtual tool distributed to the user is a virtual tool that the user is interested in, thereby improving the user's willingness to publish content and enhancing the user's creative enthusiasm. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0022] Figure 1 A schematic diagram of a scenario for processing the delivery of a virtual tool according to an embodiment of the present disclosure;

[0023] Figure 2 Schematic diagram of the process of issuing virtual tools provided in the embodiment of the present disclosure Figure 1 ;

[0024] Figure 3 Schematic diagram of the process of issuing virtual tools provided in the embodiment of the present disclosure Figure 2 ;

[0025] Figure 4 A structural block diagram of a virtual tool delivery processing device provided in an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0028] With the improvement of terminal device hardware performance and the continuous advancement of computer technology and artificial intelligence technology, more and more applications (Application, App for short) are running on terminal devices. At present, video apps have become an important platform for people's daily entertainment or obtaining various content information. In the process of using video apps, users will have the need to make videos. At this time, the background will send corresponding virtual tools (virtual props, virtual gameplay, virtual special effects, etc.) to the user's device, and the user can use the virtual tools to make videos on the user's device. When the background sends the virtual tools to the user's device, it is based on the test results of the representative model of the offline test, and sends the virtual tools with a higher video frame rate output by the model to the user. However, this method may cause the virtual tools sent to be not the virtual tools that the user wants to use or is interested in, which in turn reduces the user's willingness to make videos and affects the user's submission rate.

[0029] In order to solve the above technical problems, the present disclosure provides the following technical solutions: based on the tool dimension features corresponding to the obtained virtual tools and the model dimension features corresponding to the user models, a pre-trained prediction model is input for prediction to obtain an estimated willingness index of the user to use the virtual tools and the user models to publish content, and according to the estimated willingness index, it is determined whether to send the virtual tools to the corresponding users, so that the virtual tools sent to the users are the virtual tools that the users are interested in, thereby improving the users' willingness to publish content and enhancing the users' creative enthusiasm.

[0030] refer to Figure 1 , Figure 1 Schematic diagram of the scenario of virtual tool delivery processing provided by the embodiment of the present disclosure. Figure 1As shown, it includes a user terminal 101 and a server 102. The user terminal 101 can be any form of terminal device. The terminal devices involved in this disclosure can be either wireless terminals or wired terminals. A wireless terminal can be a device that provides voice and / or other service data connectivity to a user, a handheld device with wireless connection capabilities, or other processing devices connected to a wireless modem. A wireless terminal can communicate with one or more core network devices via a radio access network (RAN). A wireless terminal can be a mobile terminal, such as a mobile phone (also known as a "cellular" phone) and a computer with a mobile terminal. For example, it can be a portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile device that exchanges voice and / or data with the radio access network. For another example, a wireless terminal can also be a Personal Communication Service (PCS) phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), or other devices. A wireless terminal may also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, access terminal, user terminal, user agent, or user device or user equipment, without limitation herein. Optionally, the user terminal may also be a mobile phone, smart wearable device, tablet computer, or other terminal device.

[0031] The server 102 may be a single server or a cluster of multiple servers. The server may communicate with the terminal via a network. The server may provide various communication data to the user terminal 101, including issuing virtual tools for producing videos.

[0032] refer to Figure 2 , Figure 2 Schematic diagram of the process of issuing virtual tools provided in the embodiment of the present disclosure Figure 1 The method of this embodiment can be applied in Figure 1 In the server shown, to which this disclosure does not impose any limitation, the virtual tool delivery processing method includes:

[0033] S201: Obtain tool dimension features of a virtual tool, wherein the tool dimension features include statistical historical user willingness indicators for using the virtual tool to publish content, and tool attribute features of the virtual tool, wherein the virtual tool is used to add video editing effects to an original video to obtain a target video.

[0034] Specifically, by receiving a large number of behavior logs reported by users, the willingness index of the virtual tool to publish content can be obtained from the behavior logs.

[0035] The willingness indicators for virtual tools to publish content may include: the average number of contributions per person to the virtual tool, the contribution penetration rate of the virtual tool, etc. The contribution penetration rate of a virtual tool refers to the percentage of users who have contributed content to the total number of users who have been issued the virtual tool, as measured within a certain period of time.

[0036] Specifically, the tool attribute characteristics corresponding to the virtual tool can be obtained by parsing the virtual toolkit.

[0037] The tool attribute features corresponding to the virtual tool may include: the size of the virtual tool package, the size of the virtual tool rendering image, and the computer vision (CV) algorithm used by the virtual tool.

[0038] For example, the virtual tool is a virtual prop, and the user can use the virtual prop to add special effects processed by the virtual prop to the original video shot by the user, thereby obtaining a target video with certain special effects.

[0039] S202: Acquire model dimension features of the user model, wherein the model dimension features include statistical historical user willingness indicators for using the user model to publish content and model attribute features of the user model.

[0040] Here, the user model's willingness to publish content indicator can also be obtained from the behavior log. The user model's willingness to publish content indicator may include: the model's corresponding virtual tool submission rate, the model's number of submissions, etc. The model's corresponding virtual tool submission rate refers to the percentage of the model's total number of submissions using the virtual tool.

[0041] The model attribute characteristics corresponding to the user model may include: model name, model processor parameters, model memory size, model image processor parameters, etc. Here, the model attribute characteristics can be obtained through the configuration parameters of the user model, or through the running test of the user model.

[0042] S203: Inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated willingness index of the user to use the virtual tool and the user model to publish content.

[0043] Specifically, feature conversion processing is performed on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features; the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model are input into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model; the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model are input into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is an XGBoost model; the first estimated willingness index and the second estimated willingness index are weighted averaged to obtain the final estimated willingness index.

[0044] Among them, feature conversion processing is performed on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features, which specifically includes: normalizing the tool dimension features and the model dimension features; hot encoding the normalized tool dimension features and the normalized model dimension features to obtain sparse features corresponding to the virtual tool and the user model.

[0045] In this embodiment, feature engineering conversion is performed on the feature data in the tool dimension features and the model dimension features, and the feature data is normalized; then, a one-hot encoding operation is performed on the normalized feature data to obtain sparse features corresponding to the virtual tool and the user model.

[0046] In this embodiment, the pre-trained first prediction model and the pre-trained second prediction model are different types of models. In an optional embodiment of the present disclosure, the pre-trained first prediction model is a linear regression training model, and the pre-trained second prediction model is a neural network training model.

[0047] In this embodiment, the weights in calculating the weighted average of the first estimated willingness index and the second estimated willingness index can be adjusted according to actual needs.

[0048] In one embodiment of the present disclosure, the weight of the first estimated willingness index is 0.3, and the weight of the second estimated willingness index is 0.7.

[0049] In one embodiment of the present disclosure, the second prediction model is an XGBoost model. Optionally, the XGBoost model is trained using a regression model. The first prediction model is an output module of a deepFM model, in which sigmoid is removed as an output and trained using a regression method, and its loss function is changed from a logloss function to an mse function.

[0050] S204: Determine whether to deliver the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

[0051] Specifically, if the estimated willingness index meets the preset conditions, the virtual tool is sent to the user terminal corresponding to the user model.

[0052] From the above description, it can be seen that by obtaining the tool dimension features corresponding to the virtual tool and the model dimension features corresponding to the user model, the tool dimension features of the virtual tool and the model dimension features of the user model are input into the pre-trained prediction model to obtain the estimated willingness index of the user to use the virtual tool and the user model to publish content, and according to the estimated willingness index, it is determined whether to send the virtual tool to the user terminal corresponding to the user model. The estimated willingness index for content publishing is obtained by inputting the features of the virtual tool and the user model into the model, and then the virtual tool is sent according to the estimated willingness index for content publishing. This can ensure that the virtual tool sent to the user is a virtual tool that the user is interested in, thereby improving the user's willingness to publish content and enhancing the user's creative enthusiasm.

[0053] refer to Figure 3 , Figure 3 Schematic diagram of the process of issuing virtual tools provided in the embodiment of the present disclosure Figure 2 Based on the above embodiment, in the above embodiment, the step of inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model specifically includes:

[0054] S301: sparsely encode the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model to obtain dense embedded features.

[0055] In this embodiment, sparse features are sparsely encoded to obtain densely embedded features, so as to reduce the dimension of the feature space and reduce the amount of calculation.

[0056] Specifically, one-hot sparse coding is used to process sparse features and convert them into dense embedded features (denseembedding).

[0057] S302: Input the dense embedded features into the first module of the first prediction model to extract low-order features from the dense embedded features, and input the dense embedded features into the second module of the first prediction model to extract high-order features from the dense embedded features.

[0058] In one embodiment of the present disclosure, the first prediction model is a deepFM model; inputting the dense embedded features into the first module of the first prediction model to extract low-order features in the dense embedded features, and inputting the dense embedded features into the second module of the first prediction model to extract high-order features in the dense embedded features, includes: inputting the dense embedded features into the FM layer of the deepFM model to extract low-order features in the dense embedded features, and inputting the dense embedded features into the hidden layer of the deepFM model to extract high-order features in the dense embedded features.

[0059] S303: Inputting the low-order features in the densely embedded features and the high-order features in the densely embedded features into the output module of the first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model.

[0060] In this embodiment, the low-order features and high-order features in the densely embedded features are fused into fused features and input into the output module of the first prediction model, so that the output module of the first prediction model outputs a prediction result based on the fused features, which is the first estimated willingness indicator.

[0061] Here, the first estimated willingness indicator may be the number of submissions or the submission rate.

[0062] From the above description, it can be seen that by sparsely encoding sparse features and densely embedding features to reduce the dimension of the feature space, the amount of calculation is reduced; at the same time, by densely embedding low-order features and high-order features in the features respectively, and fusing the high-order features and low-order features, the output module outputs the prediction results based on the fused features, and the obtained prediction results are more accurate.

[0063] In one embodiment of the present disclosure, in step S204, the process of determining whether to deliver the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index may include two implementation methods, as follows:

[0064] In a first manner, if the estimated willingness index exceeds a preset index threshold, the virtual tool is delivered to the user terminal corresponding to the user model.

[0065] The preset indicator threshold value can be set as needed. For example, the preset indicator threshold value is 80%.

[0066] From the above description, it can be seen that a virtual tool that exceeds the preset indicator threshold is sent to the user. The speed of sending the virtual tool is fast, so that the user can obtain the virtual tool in time.

[0067] The second way is to sort the estimated willingness index of each virtual tool from high to low, and send a preset number of virtual tools ranked at the top to the user terminal corresponding to the user model.

[0068] The preset number of virtual tools may be 5 or 10, and the specific value may be determined according to requirements.

[0069] From the above description, it can be seen that multiple virtual tools with higher estimated willingness indicators are sent to the user terminal corresponding to the user model, so that the user can select virtual tools according to needs, expand the user's selection range, and further improve the user's submission rate.

[0070] Corresponding to the virtual tool delivery processing method in the above embodiment, Figure 4 This is a structural block diagram of a virtual tool delivery processing device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 4 The device includes: a first acquisition module 401, a second acquisition module 402, a prediction module 403 and a sending module 404.

[0071] The first acquisition module 401 is configured to acquire tool-dimensional features of a virtual tool, wherein the tool-dimensional features include a historical statistical indicator of users' willingness to use the virtual tool to publish content and tool attribute features of the virtual tool, wherein the virtual tool is used to add video editing effects to an original video to obtain a target video.

[0072] The second acquisition module 402 is configured to acquire model dimension features of the user's model, wherein the model dimension features include historical user willingness indicators of using the user's model for content publishing and model attribute features of the user's model;

[0073] Prediction module 403, configured to input the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated user willingness index for using the virtual tool and the user model to publish content;

[0074] The sending module 404 is used to determine whether to send the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

[0075] According to one or more embodiments of the present disclosure, the prediction module 403 is specifically used to perform feature conversion processing on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features; input the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model; input the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is an XGBoost model; and perform weighted averaging on the first estimated willingness index and the second estimated willingness index to obtain the final estimated willingness index.

[0076] According to one or more embodiments of the present disclosure, the prediction module 403 is specifically used to normalize the tool dimension features and the model dimension features; perform hot encoding on the normalized tool dimension features and the normalized model dimension features to obtain sparse features corresponding to the virtual tool and the user model.

[0077] According to one or more embodiments of the present disclosure, the prediction module 403 is specifically configured to perform sparse coding on the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model to obtain densely embedded features;

[0078] Inputting the dense embedded features into a first module of the first prediction model to extract low-order features from the dense embedded features, and inputting the dense embedded features into a second module of the first prediction model to extract high-order features from the dense embedded features;

[0079] The low-order features in the densely embedded features and the high-order features in the densely embedded features are input into an output module of the first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model.

[0080] According to one or more embodiments of the present disclosure, the sending module 404 is specifically used to send the virtual tool to the user terminal corresponding to the user model if the estimated willingness index exceeds a preset index threshold; or, to sort the estimated willingness index of each virtual tool from high to low, and send a preset number of virtual tools that are ranked first to the user terminal corresponding to the user model.

[0081] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0082] In order to implement the above embodiment, the embodiment of the present disclosure further provides an electronic device.

[0083] refer to Figure 5 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. The electronic device 500 may be a terminal device or a server. The terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0084] like Figure 5 As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0085] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0086] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0087] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0088] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0089] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0090] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0092] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0093] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0094] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] In a first aspect, according to one or more embodiments of the present disclosure, a method for issuing a virtual tool is provided, comprising:

[0096] Obtaining tool dimension features of a virtual tool, wherein the tool dimension features include a statistically analyzed historical user willingness index for using the virtual tool to publish content and tool attribute features of the virtual tool, wherein the virtual tool is used to add a video editing effect to an original video to obtain a target video;

[0097] Acquiring model dimension features of the user model, wherein the model dimension features include statistical historical user willingness indicators of using the user model to publish content and model attribute features of the user model;

[0098] Inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated user willingness index for using the virtual tool and the user model to publish content;

[0099] Determine whether to send the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

[0100] According to one or more embodiments of the present disclosure, the step of inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated willingness index corresponding to the virtual tool and the user model includes: performing feature conversion processing on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features; inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model; inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is an XGBoost model; and performing weighted averaging on the first estimated willingness index and the second estimated willingness index to obtain the final estimated willingness index.

[0101] According to one or more embodiments of the present disclosure, the feature conversion processing is performed on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features, including: normalizing the tool dimension features and the model dimension features; and hot encoding the normalized tool dimension features and the normalized model dimension features to obtain sparse features corresponding to the virtual tool and the user model.

[0102] According to one or more embodiments of the present disclosure, the step of inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model includes: sparsely encoding the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model to obtain dense embedded features; inputting the dense embedded features into a first module of the first prediction model to extract low-order features from the dense embedded features, and inputting the dense embedded features into a second module of the first prediction model to extract high-order features from the dense embedded features; and inputting the low-order features in the dense embedded features and the high-order features in the dense embedded features into an output module of the first prediction model to output the first estimated willingness index corresponding to the virtual tool and the user model.

[0103] According to one or more embodiments of the present disclosure, determining whether to send the virtual tool to the user terminal corresponding to the user model based on the estimated willingness index includes: if the estimated willingness index exceeds a preset index threshold, sending the virtual tool to the user terminal corresponding to the user model; or, sorting the estimated willingness index of each virtual tool from high to low, and sending a preset number of virtual tools that are ranked first to the user terminal corresponding to the user model.

[0104] In a second aspect, according to one or more embodiments of the present disclosure, a virtual tool delivery processing device is provided, comprising:

[0105] a first acquisition module, configured to acquire tool-dimensional features of a virtual tool, wherein the tool-dimensional features include a statistically analyzed historical user willingness index for using the virtual tool to publish content and tool attribute features of the virtual tool, wherein the virtual tool is used to add video editing effects to an original video to obtain a target video;

[0106] A second acquisition module is configured to acquire model dimension features of a user model, wherein the model dimension features include statistical historical user willingness indicators of using the user model for content publishing and model attribute features of the user model;

[0107] a prediction module, configured to input the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated user willingness index for using the virtual tool and the user model to publish content;

[0108] A sending module is used to determine whether to send the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

[0109] According to one or more embodiments of the present disclosure, the prediction module is specifically used to perform feature conversion processing on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features; the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model are input into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model; the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model are input into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is an XGBoost model; and the first estimated willingness index and the second estimated willingness index are weighted averaged to obtain the final estimated willingness index.

[0110] According to one or more embodiments of the present disclosure, the prediction module is specifically used to normalize the tool dimension features and the model dimension features; perform hot encoding on the normalized tool dimension features and the normalized model dimension features to obtain sparse features corresponding to the virtual tool and the user model.

[0111] According to one or more embodiments of the present disclosure, the prediction module is specifically configured to perform sparse coding on the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model to obtain densely embedded features;

[0112] Inputting the dense embedded features into a first module of the first prediction model to extract low-order features from the dense embedded features, and inputting the dense embedded features into a second module of the first prediction model to extract high-order features from the dense embedded features;

[0113] The low-order features in the densely embedded features and the high-order features in the densely embedded features are input into an output module of the first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model.

[0114] According to one or more embodiments of the present disclosure, the sending module is specifically used to send the virtual tool to the user terminal corresponding to the user model if the estimated willingness index exceeds a preset index threshold; or, to sort the estimated willingness index of each virtual tool from high to low, and send a preset number of virtual tools in the front of the sort to the user terminal corresponding to the user model.

[0115] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0116] The memory stores computer-executable instructions;

[0117] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the virtual tool delivery processing method described in the first aspect and various possible designs of the first aspect.

[0118] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the virtual tool issuance processing method described in the first aspect and various possible designs of the first aspect is implemented.

[0119] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the virtual tool distribution processing method described in the first aspect and various possible designs of the first aspect.

[0120] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0121] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0122] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for issuing a virtual tool, characterized in that: include: Obtaining tool dimension features of a virtual tool, wherein the tool dimension features include a statistically analyzed historical user willingness index for using the virtual tool to publish content and tool attribute features of the virtual tool, wherein the virtual tool is used to add a video editing effect to an original video to obtain a target video; Obtaining model dimension features of the user model, wherein the model dimension features include historical user willingness indicators for using the user model to publish content and model attribute features of the user model; wherein the user model willingness indicators for publishing content include: a virtual tool contribution rate corresponding to the model and a number of contributions to the model; Inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated user willingness index for using the virtual tool and the user model to publish content; Determine whether to send the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

2. The method according to claim 1, characterized in that Inputting the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated willingness index corresponding to the virtual tool and the user model includes: Performing feature conversion processing on the tool dimension feature and the machine model dimension feature respectively to obtain sparse features of the tool dimension feature and sparse features of the machine model dimension feature; Inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model; Inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained second prediction model is an XGBoost model; The first estimated willingness index and the second estimated willingness index are weighted averaged to obtain the final estimated willingness index.

3. The method according to claim 2, characterized in that The performing feature conversion processing on the tool dimension feature and the machine model dimension feature respectively to obtain sparse features of the tool dimension feature and sparse features of the machine model dimension feature includes: Normalizing the tool dimension features and the machine model dimension features; Hot encoding is performed on the normalized tool dimension features and the normalized machine model dimension features to obtain sparse features corresponding to the virtual tool and the user machine model.

4. The method according to claim 2, characterized in that Inputting the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model includes: sparsely encoding the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model to obtain dense embedded features; Inputting the dense embedded features into a first module of the first prediction model to extract low-order features from the dense embedded features, and inputting the dense embedded features into a second module of the first prediction model to extract high-order features from the dense embedded features; The low-order features in the densely embedded features and the high-order features in the densely embedded features are input into an output module of the first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model.

5. The method according to any one of claims 1 to 4, characterized in that The determining, based on the estimated willingness index, whether to deliver the virtual tool to the user terminal corresponding to the user model includes: If the estimated willingness index exceeds a preset index threshold, the virtual tool is sent to the user terminal corresponding to the user model; or, The estimated willingness indexes of the virtual tools are sorted from high to low, and a preset number of virtual tools ranked at the top are sent to the user terminals corresponding to the user models.

6. A virtual tool distribution processing device, characterized in that: include: a first acquisition module, configured to acquire tool-dimensional features of a virtual tool, wherein the tool-dimensional features include a statistically analyzed historical user willingness index for using the virtual tool to publish content and tool attribute features of the virtual tool, wherein the virtual tool is used to add video editing effects to an original video to obtain a target video; A second acquisition module is configured to acquire model-dimensional features of a user's model, wherein the model-dimensional features include historical user willingness indicators for using the user's model to publish content, and model attribute features of the user's model; wherein the user's willingness indicators for publishing content include: a virtual tool contribution rate corresponding to the model, and a number of contributions to the model; A prediction module, configured to input the tool dimension features of the virtual tool and the model dimension features of the user model into a pre-trained prediction model to obtain an estimated user willingness index for using the virtual tool and the user model to publish content; A sending module is used to determine whether to send the virtual tool to the user terminal corresponding to the user model according to the estimated willingness index.

7. The device according to claim 6, characterized in that The prediction module is specifically used to perform feature conversion processing on the tool dimension features and the model dimension features respectively to obtain sparse features of the tool dimension features and sparse features of the model dimension features; input the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained first prediction model to output a first estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained first prediction model is a deepFM model; input the sparse features of the tool dimension features of the virtual tool and the sparse features of the model dimension features of the user model into a pre-trained second prediction model to output a second estimated willingness index corresponding to the virtual tool and the user model, wherein the pre-trained second prediction model is an XGBoost model; and perform weighted averaging on the first estimated willingness index and the second estimated willingness index to obtain the final estimated willingness index.

8. An electronic device, characterized in that: include: processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the virtual tool delivery processing method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the virtual tool delivery processing method according to any one of claims 1 to 5 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the virtual tool distribution processing method according to any one of claims 1 to 5 is implemented.

Images