Virtual tool testing method and apparatus

Abstract

Embodiments of the present disclosure provide a virtual tool testing method and device, the method comprising: obtaining a virtual tool to be tested, and extracting tool features of the virtual tool to be tested according to attribute information of the virtual tool; obtaining model information of full-quantity models, and extracting model features of each model according to the model information of the full-quantity models; inputting the tool features and the model features of each model into a pre-trained scoring model respectively, and outputting performance test parameters of each model corresponding to the virtual tool to be tested; and outputting a result of whether the virtual tool to be tested passes the test according to the performance test parameters of each model corresponding to the virtual tool to be tested. The test process of the embodiments of the present disclosure can cover full-quantity models, has high test coverage, and the test result is more accurate.

Description

Technical Field

[0001] This disclosure relates to the field of computer and software technology, and in particular to a virtual tool testing method and device. Background Technology

[0002] When a user needs to create a video using a video application (such as a short video application), the backend can send corresponding virtual tools (such as virtual props, virtual gameplay, etc.) to the user's terminal based on the user's request. The user can then use these virtual tools to create videos on their terminal. These virtual tools are created by creators using creation software according to certain rules. Creators typically use packaging tools to package the virtual tools into a virtual toolkit for use on the user's terminal. Before being deployed, the created virtual tools need to undergo performance testing to determine whether they run smoothly or experience lag on the user's terminal.

[0003] Currently, traditional virtual tool testing methods can only test real devices of a few common models. The testing effect on all models cannot be determined, which leads to problems such as incomplete test coverage and low test accuracy of virtual tools. Summary of the Invention

[0004] This disclosure provides a virtual tool testing method and device to overcome the problems of traditional virtual tool testing methods, which can only test real devices of a few common models and cannot determine the testing effect for all models, resulting in incomplete test coverage and low test accuracy.

[0005] In a first aspect, embodiments of this disclosure provide a virtual tool testing method, including:

[0006] Obtain the virtual tool to be tested, and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video;

[0007] Obtain the model information of all models, and extract the model features of each model based on the model information of all models;

[0008] The tool features and the model features of each device are respectively input into the pre-trained scoring model, and the performance test parameters of each device corresponding to the virtual tool to be tested are output.

[0009] Based on the performance test parameters of each machine model corresponding to the virtual tool under test, output the result of whether the virtual tool under test passes the test.

[0010] Secondly, embodiments of this disclosure provide a virtual tool testing apparatus, comprising:

[0011] The tool feature processing module is used to acquire the virtual tool to be tested and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video;

[0012] The model feature processing module is used to obtain model information of all models and extract model features of each model based on the model information of all models.

[0013] The model processing module is used to input the tool features and the model features of each model into a pre-trained scoring model, and output the performance test parameters of each model corresponding to the virtual tool to be tested.

[0014] The test result processing module is used to output the result of whether the virtual tool under test passes the test based on the performance test parameters of each model corresponding to the virtual tool under test.

[0015] Thirdly, embodiments of this disclosure provide an electronic device, including: a processor and a memory;

[0016] The memory stores computer-executed instructions;

[0017] The processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the virtual tool testing method as described in the first aspect and various possible designs of the first aspect.

[0018] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the virtual tool testing method described in the first aspect and various possible designs of the first aspect.

[0019] Fifthly, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the virtual tool testing method described in the first aspect and various possible designs of the first aspect.

[0020] The virtual tool testing method and equipment provided in this embodiment extract the model features of each model based on the model information of all models. By inputting the tool features of the virtual tool to be tested and the model features of each model into a pre-trained scoring model, the performance test parameters of each model corresponding to the virtual tool to be tested are output. Based on the performance test parameters of each model corresponding to the virtual tool to be tested, it is determined whether the virtual tool to be tested passes the model test. The testing process of this embodiment can cover all models, with high test coverage and high test accuracy. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic diagram of a scenario for testing virtual tools provided in this embodiment of the disclosure;

[0023] Figure 2 Flowchart of the virtual tool testing method provided in the embodiments of this disclosure Figure 1 ;

[0024] Figure 3 Flowchart of the virtual tool testing method provided in the embodiments of this disclosure Figure 2 ;

[0025] Figure 4 A structural block diagram of the virtual tool testing apparatus provided in the embodiments of this disclosure;

[0026] Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0028] Currently, most virtual tools (including virtual props and virtual gameplay) require creators to set stickers, computer vision (CV) effects, and other related features. Many of these effects require calling algorithm libraries for tasks such as face detection, eyebrow detection, or image generation when running on a user's device. During this process, when the virtual tool runs on the user's device, calling numerous algorithm models or using a large number of layers after completing related detections can significantly impact the user's device performance, even causing lag on some low-end devices. Therefore, before these virtual tools are released, their creators need to undergo performance testing to ensure they can run stably on most user devices. The traditional method for testing virtual tools involves loading the virtual tool on a real test device, calculating metrics such as frame rate, CPU usage, and memory usage, and then determining if these metrics fall within a certain threshold range. If they do, the virtual tool passes the performance test; otherwise, it fails. However, traditional virtual tool testing methods can only test real devices of a few common models, and the testing effect on all models cannot be determined, which leads to incomplete testing coverage of virtual tools.

[0029] To address the aforementioned technical problems, this disclosure provides the following technical solution: Obtaining the tool features of the virtual tool to be tested; obtaining the model features of all device models based on the model information of all device models; inputting the tool features and each model feature into a pre-trained scoring model to output performance test parameters for each device model corresponding to the virtual tool to be tested; determining whether the virtual tool to be tested passes the model test based on the performance test parameters for each device model corresponding to the virtual tool to be tested. Since the model features of each device model are extracted based on the model information of all device models, the testing process can cover all device models, resulting in high test coverage and more accurate test results.

[0030] refer to Figure 1 , Figure 1 This is a schematic diagram illustrating a scenario for testing the virtual tool provided in an embodiment of this disclosure. Figure 1As shown, the system includes a user terminal 101 and a server 102. The user terminal 101 can be any type of terminal device; the terminal devices involved in this disclosure can be wireless 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 connectivity, or other processing devices connected to a wireless modem. The wireless terminal can communicate with one or more core network devices via a Radio Access Network (RAN). The wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device, which exchanges voice and / or data with the RAN. For example, the 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 similar devices. A wireless terminal can 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, user device, or user equipment, without limitation. Optionally, the aforementioned user terminal can also be a mobile phone, smart wearable device, tablet computer, or other terminal device.

[0031] Server 102 can be a single server or a cluster of multiple servers. The server can communicate with the terminal via a network and can provide various communication data to the user terminal 101, including the distribution of virtual tools for video production.

[0032] refer to Figure 2 , Figure 2 Flowchart of the virtual tool testing method provided in the embodiments of this disclosure Figure 1 The method of this embodiment can be applied to, for example, Figure 1 The user terminal or server shown herein does not impose any limitations on this method of testing the virtual tool, which includes:

[0033] S201: Obtain the virtual tool to be tested, and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video.

[0034] In this embodiment, the virtual tool to be tested can be a virtual toolkit, such as a prop pack.

[0035] Specifically, extracting tool features of the virtual tool under test based on the attribute information of the virtual tool may include: parsing the virtual toolkit of the virtual tool under test to obtain the attribute information corresponding to the virtual tool under test, and extracting key parameters or key fields based on the attribute information to obtain tool features. Here, the attribute information of the virtual tool may include, but is not limited to: the size of the virtual toolkit, the size of the rendered image, and the computer vision (CV) algorithm used.

[0036] For example, virtual tools are virtual props that users can use to add effects to their original videos, thereby obtaining a target video with certain effects.

[0037] S202: Obtain the model information of all models, and extract the model features of each model based on the model information of all models.

[0038] In this embodiment, web crawler and other technologies can be used to collect model information for all available mobile phone models on the market. This model information includes various parameter details of the model.

[0039] Specifically, the model features of each model are extracted based on the model information of all models. This may include extracting the model name, processor parameters, memory size, and image processor parameters from various parameter information of all models as model features.

[0040] S203: Input the tool features and the model features of each model into the pre-trained scoring model, and output the performance test parameters of each model corresponding to the virtual tool to be tested.

[0041] In this embodiment, the pre-trained scoring model can be a deepFM model, an XGBoost model, a logistic regression model, etc.

[0042] Specifically, the tool features and device features corresponding to any of the virtual tools and device models are input into any one of the deepFM model, XGBoost model, and logistic regression model, and the performance test parameters of the virtual tools and device models are output. The above steps are repeated until the performance test parameters of the virtual tools to be tested and all device models are obtained.

[0043] In this embodiment, the performance test parameters can be the expected frame rate of the virtual tool under test running on any model, the score of the virtual tool, the average frame rate, or the weighted average frame rate, etc.

[0044] S204: Based on the performance test parameters of each machine model corresponding to the virtual tool to be tested, output the result of whether the virtual tool to be tested passes the virtual tool test.

[0045] Specifically, if the performance test parameters of each device model corresponding to the virtual tool under test are within the preset parameter threshold range, then the first result of the virtual tool under test passing the test is output. If the performance test parameters of each device model corresponding to the virtual tool under test exceed the preset parameter threshold range, then a real device evaluation is performed on the virtual tool under test. If the real device evaluation passes, the first result of the virtual tool under test passing the test is output; if the real device evaluation fails, the second result of the virtual tool under test failing the test is output.

[0046] In this embodiment, the preset parameter threshold range can be set as needed.

[0047] In one embodiment of this disclosure, after outputting the first result of the virtual tool under test passing the test, the method may further include determining that the virtual tool under test has passed the test and sending the virtual tool under test to the user terminal so that the user can use it on the user terminal.

[0048] In one embodiment of this disclosure, after outputting a second result indicating that the virtual tool under test failed the test, the method may further include sending a notification that the virtual tool under test failed the test to the terminal of the virtual tool creator, so that the virtual tool creator can modify the virtual tool under test.

[0049] As described above, the device features of each device are extracted based on the device information of all device models. The tool features of the virtual tool to be tested and the features of each device model are input into a pre-trained scoring model to output the performance test parameters of each device model corresponding to the virtual tool to be tested. Based on the performance test parameters of each device model corresponding to the virtual tool to be tested, it is determined whether the virtual tool to be tested passes the device model test. The testing process of this embodiment can cover all device models, with high test coverage and high test accuracy.

[0050] refer to Figure 3 , Figure 3 Flowchart of the virtual tool testing method provided in the embodiments of this disclosure Figure 2 Based on the above embodiments, step S203 specifically includes:

[0051] S301: Input the tool features and the model features of any model into the first sub-model of the pre-trained scoring model to rank the features by importance.

[0052] The pre-trained scoring model can be a combination of the XGBoost model and the deepFM model, and the first sub-model can be the XGBoost model.

[0053] In this embodiment, the tool features and the model features of any device are input into the XGBoost model. The XGBoost model traverses each feature of the tool features and the model features of any device according to a decision tree to determine the feature split number of each feature, and determines the importance index of each feature based on the feature split number. Specifically, the larger the feature split number, the higher the feature importance index, and the higher the importance of the feature.

[0054] For example, the computer vision (CV) algorithms used in virtual tools, the processor parameters of the device, the memory size of the device, and the image processor parameters of the device are complex features with a large number of feature splits, making them features with high importance. Features such as the size of the virtual toolkit, the size of the rendered image, and the name of the device are simple features with a small number of feature splits, making them features with low importance.

[0055] S302: Filter based on the sorted tool features and model features to obtain the target features.

[0056] In this embodiment, a preset number of tool features and machine model features ranked first in terms of feature importance can be identified as target features.

[0057] The preset number of items can be 5 or 10.

[0058] S303: Input the target features into the second sub-model of the pre-trained scoring model to obtain the performance test parameters of any model corresponding to the virtual tool to be tested.

[0059] Specifically, the step of inputting the target features into the second sub-model of the pre-trained scoring model to obtain the performance test parameters of any device model corresponding to the virtual tool under test includes: performing feature transformation processing on the target features to obtain sparse features corresponding to the virtual tool under test and any device model; performing sparse encoding on the sparse features to obtain dense embedding features; inputting the dense embedding features into the first module of the second sub-model to extract low-order features from the dense embedding features; inputting the dense embedding features into the second module of the second sub-model to extract high-order features from the dense embedding features; and inputting the low-order features and high-order features from the dense embedding features into the output module of the second sub-model to output the performance test parameters of any device model corresponding to the virtual tool under test.

[0060] In this embodiment, sparse features are sparsely encoded to obtain dense embedding features, thereby reducing the dimensionality of the feature space and lowering the computational cost. Specifically, one-hot sparse encoding is used to process the sparse features and transform them into dense embedding features.

[0061] In one embodiment of this disclosure, the second sub-model is a deepFM model. The step of inputting the dense embedding features into a first module of the second sub-model to extract low-order features, and inputting the dense embedding features into a second module of the second sub-model to extract high-order features, includes: inputting the dense embedding features into the FM layer of the deepFM model to extract low-order features, and inputting the dense embedding features into the hidden layer of the deepFM model to extract high-order features. The low-order and high-order features in the dense embedding features are then fused to obtain a fused feature, which is input into the output module of the second sub-model, so that the output module of the second sub-model outputs performance test parameters for any model corresponding to the virtual machine tool under test based on the fused feature.

[0062] The deepFM model uses the L2 loss function during training.

[0063] As can be seen from the above description, by sparsely encoding sparse features and densely embedding them, the dimensionality of the feature space can be reduced, thus reducing the computational load. At the same time, by densely embedding low-order and high-order features separately and fusing the high-order and low-order features, the output module can output the prediction result based on the fused features, resulting in a more accurate prediction result.

[0064] In one embodiment of this disclosure, in step S204 of the above embodiment, a real device evaluation is performed on the virtual tool to be tested. If the real device evaluation passes, a first result indicating that the virtual tool to be tested has passed the test is output; if the real device evaluation fails, a second result indicating that the virtual tool to be tested has failed the test is output, including:

[0065] Based on the performance test parameters of each device model corresponding to the virtual tool under test, a fallback device model that exceeds the preset parameter threshold range is determined; the virtual tool under test is then sent to the real device corresponding to the fallback device model for execution, and the performance test parameters of the virtual tool under test running on the real device corresponding to the fallback device model are obtained; if the performance test parameters of the real device running are within the preset parameter threshold range, a first result indicating that the virtual tool under test has passed the test is output; if the performance test parameters of the real device running exceed the preset parameter threshold range, a second result indicating that the virtual tool under test has failed the test is output.

[0066] In this embodiment, virtual tools whose performance test parameters exceed the preset parameter threshold range are considered low-confidence virtual tools. For virtual tools with low confidence, their corresponding backup device is determined. The backup device is then used to further confirm whether the virtual tool under test passes the test, which improves accuracy and reduces the cost of using real devices.

[0067] Corresponding to the virtual tool testing method in the above embodiments, Figure 4 This is a structural block diagram of a virtual tool testing apparatus provided for embodiments of this disclosure. For ease of explanation, only the parts relevant to embodiments of this disclosure are shown. (Refer to...) Figure 4 The device includes: a tool feature processing module 401, a machine feature processing module 402, a model processing module 403, and a test result processing module 404.

[0068] The tool feature processing module 401 is used to acquire the virtual tool to be tested and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video;

[0069] The model feature processing module 402 is used to obtain model information of all models and extract model features of each model based on the model information of all models.

[0070] The model processing module 403 is used to input the tool features and the model features of each model into the pre-trained scoring model, and output the performance test parameters of each model corresponding to the virtual tool to be tested.

[0071] The test result processing module 404 is used to output the result of whether the virtual tool under test passes the virtual tool test based on the performance test parameters of each model corresponding to the virtual tool under test.

[0072] As described above, the device features of each device are extracted based on the device information of all device models. The tool features of the virtual tool to be tested and the features of each device model are input into a pre-trained scoring model to output the performance test parameters of each device model corresponding to the virtual tool to be tested. Based on the performance test parameters of each device model corresponding to the virtual tool to be tested, it is determined whether the virtual tool to be tested passes the device model test. The testing process of this embodiment can cover all device models, with high test coverage and high test accuracy.

[0073] According to one or more embodiments of this disclosure, the model processing module 403 specifically includes:

[0074] The first sub-model processing unit 4031 is used to input tool features and model features of any model into the first sub-model of the pre-trained scoring model for feature importance ranking; and to filter the ranked tool features and model features to obtain target features.

[0075] The second sub-model processing unit 4032 is used to input the target features into the second sub-model of the pre-trained scoring model to obtain the performance test parameters of any model corresponding to the virtual tool to be tested.

[0076] According to one or more embodiments of this disclosure, the second sub-model processing unit 4032 is specifically configured to perform feature transformation processing on the target feature to obtain sparse features corresponding to the virtual tool and any of the device models; perform sparse encoding on the sparse features to obtain dense embedding features; input the dense embedding features into the first module of the second sub-model to extract low-order features from the dense embedding features; input the dense embedding features into the second module of the second sub-model to extract high-order features from the dense embedding features; and input the low-order features and high-order features from the dense embedding features into the output module of the second sub-model to output the performance test parameters of any of the device models corresponding to the virtual tool to be tested.

[0077] According to one or more embodiments of this disclosure, the test result processing module 404 specifically includes: a first test result processing unit 4041, configured to output a first result indicating that the virtual tool under test has passed the test if the performance test parameters of each device model corresponding to the virtual tool under test are within a preset parameter threshold range; and a second test result processing unit 4042, configured to perform a real device evaluation on the virtual tool under test if the performance test parameters of each device model corresponding to the virtual tool under test exceed the preset parameter threshold range; if the real device evaluation passes, outputting a first result indicating that the virtual tool under test has passed the test; and if the real device evaluation fails, outputting a second result indicating that the virtual tool under test has failed the test.

[0078] According to one or more embodiments of this disclosure, the second test result processing unit 4042 is specifically configured to: determine the fallback model that exceeds the preset parameter threshold range based on the performance test parameters of each model corresponding to the virtual tool to be tested; send the virtual tool to be tested to the real machine corresponding to the fallback model for operation, and obtain the performance test parameters of the virtual tool to be tested running on the real machine corresponding to the fallback model; if the performance test parameters of the real machine running are within the preset parameter threshold range, output a first result that the virtual tool to be tested has passed the test; if the performance test parameters of the real machine running exceed the preset parameter threshold range, output a second result that the virtual tool to be tested has failed the test.

[0079] The apparatus provided in this embodiment can be used to execute the technical solutions of the above method embodiments. Its implementation principle and technical effects are similar, and will not be described again here.

[0080] To implement the above embodiments, this disclosure also provides an electronic device.

[0081] refer to Figure 5 The diagram illustrates a structural schematic of an electronic device 500 suitable for implementing embodiments of the present disclosure. The electronic device 500 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants (PDAs), portable Android devices (PADs), portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0082] like Figure 5 As shown, the electronic device 500 may include a processing unit (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. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0083] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, 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 alternatively.

[0084] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0085] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0086] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0087] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0088] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone 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 remote computers, the remote computer can 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 can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0090] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0091] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0092] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0093] In a first aspect, according to one or more embodiments of this disclosure, a virtual tool testing method is provided, comprising:

[0094] Obtain the virtual tool to be tested, and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video;

[0095] Obtain the model information of all models, and extract the model features of each model based on the model information of all models;

[0096] The tool features and the model features of each device are respectively input into the pre-trained scoring model, and the performance test parameters of each device corresponding to the virtual tool to be tested are output.

[0097] Based on the performance test parameters of each machine model corresponding to the virtual tool under test, output the result of whether the virtual tool under test passes the test.

[0098] According to one or more embodiments of this disclosure, the step of inputting the tool features and the model features of each device type into a pre-trained scoring model to output performance test parameters for each device type corresponding to the virtual tool to be tested includes: inputting the tool features and the model features of any device type into a first sub-model of the pre-trained scoring model to sort the features by importance; filtering based on the sorted tool features and model features to obtain target features; and inputting the target features into a second sub-model of the pre-trained scoring model to obtain performance test parameters for any device type corresponding to the virtual tool to be tested.

[0099] According to one or more embodiments of this disclosure, the step of inputting the target features into a second sub-model of the pre-trained scoring model to obtain performance test parameters for any device model corresponding to the virtual tool to be tested includes: performing feature transformation processing on the target features to obtain sparse features corresponding to the virtual tool and the device model; performing sparse encoding on the sparse features to obtain dense embedding features; inputting the dense embedding features into a first module of the second sub-model to extract low-order features from the dense embedding features; inputting the dense embedding features into a second module of the second sub-model to extract high-order features from the dense embedding features; and inputting the low-order features and high-order features from the dense embedding features into an output module of the second sub-model to output performance test parameters for any device model corresponding to the virtual tool to be tested.

[0100] According to one or more embodiments of this disclosure, the step of outputting the result of whether the virtual tool under test passes the test based on the performance test parameters of each device model corresponding to the virtual tool under test includes: if the performance test parameters of each device model corresponding to the virtual tool under test are within a preset parameter threshold range, then outputting a first result that the virtual tool under test has passed the test; if the performance test parameters of each device model corresponding to the virtual tool under test exceed the preset parameter threshold range, then performing a real device evaluation on the virtual tool under test; if the real device evaluation passes, then outputting a first result that the virtual tool under test has passed the test; if the real device evaluation fails, then outputting a second result that the virtual tool under test has failed the test.

[0101] According to one or more embodiments of this disclosure, the step of performing a real-device evaluation on the virtual tool under test, and outputting a first result indicating that the virtual tool under test has passed the test if the real-device evaluation passes, and a second result indicating that the virtual tool under test has failed the test if the real-device evaluation fails, includes: determining a fallback device model that exceeds the preset parameter threshold range based on the performance test parameters of each device model corresponding to the virtual tool under test; running the virtual tool under test on the real device corresponding to the fallback device model, and obtaining the performance test parameters of the virtual tool under test running on the real device corresponding to the fallback device model; outputting a first result indicating that the virtual tool under test has passed the test if the performance test parameters of the real device running are within the preset parameter threshold range; and outputting a second result indicating that the virtual tool under test has failed the test if the performance test parameters of the real device running exceed the preset parameter threshold range.

[0102] Secondly, according to one or more embodiments of this disclosure, a virtual tool testing apparatus is provided, comprising:

[0103] The tool feature processing module is used to acquire the virtual tool to be tested and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video;

[0104] The model feature processing module is used to obtain model information of all models and extract model features of each model based on the model information of all models.

[0105] The model processing module is used to input the tool features and the model features of each model into a pre-trained scoring model, and output the performance test parameters of each model corresponding to the virtual tool to be tested.

[0106] The test result processing module is used to output the result of whether the virtual tool under test passes the test based on the performance test parameters of each model corresponding to the virtual tool under test.

[0107] According to one or more embodiments of this disclosure, the model processing module specifically includes: a first sub-model processing unit, used to input tool features and model features of any device type into a first sub-model of a pre-trained scoring model for feature importance ranking; and to filter based on the ranked tool features and model features to obtain target features; and a second sub-model processing unit, used to input the target features into a second sub-model of the pre-trained scoring model to obtain performance test parameters of any device type corresponding to the virtual tool to be tested.

[0108] According to one or more embodiments of this disclosure, the second sub-model processing unit is specifically configured to perform feature transformation processing on the target feature to obtain sparse features corresponding to the virtual tool and any of the device models; perform sparse encoding on the sparse features to obtain dense embedding features; input the dense embedding features into a first module of the second sub-model to extract low-order features from the dense embedding features; input the dense embedding features into a second module of the second sub-model to extract high-order features from the dense embedding features; and input the low-order features and high-order features from the dense embedding features into an output module of the second sub-model to output performance test parameters for any of the device models corresponding to the virtual tool to be tested.

[0109] According to one or more embodiments of this disclosure, the test result processing module specifically includes: a first test result processing unit, configured to output a first result indicating that the virtual tool under test has passed the test if the performance test parameters of each device model corresponding to the virtual tool under test are within a preset parameter threshold range; and a second test result processing unit, configured to perform a real device evaluation on the virtual tool under test if the performance test parameters of each device model corresponding to the virtual tool under test exceed the preset parameter threshold range; if the real device evaluation passes, outputting a first result indicating that the virtual tool under test has passed the test; and if the real device evaluation fails, outputting a second result indicating that the virtual tool under test has failed the test.

[0110] According to one or more embodiments of this disclosure, the second test result processing unit is specifically configured to: determine the fallback device model that exceeds the preset parameter threshold range based on the performance test parameters of each device model corresponding to the virtual tool under test; send the virtual tool under test to the real device corresponding to the fallback device model for operation, and obtain the performance test parameters of the virtual tool under test running on the real device corresponding to the fallback device model; if the performance test parameters of the real device running are within the preset parameter threshold range, output a first result indicating that the virtual tool under test has passed the test; if the performance test parameters of the real device running exceed the preset parameter threshold range, output a second result indicating that the virtual tool under test has failed the test.

[0111] Thirdly, according to one or more embodiments of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory;

[0112] The memory stores computer-executed instructions;

[0113] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the virtual tool testing method as described in the first aspect and various possible designs of the first aspect.

[0114] Fourthly, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, and when a processor executes the computer-executable instructions, the virtual tool testing method described in the first aspect and various possible designs of the first aspect is implemented.

[0115] Fifthly, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the virtual tool testing method as described in the first aspect and various possible designs of the first aspect.

[0116] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0117] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0118] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A virtual tool testing method, characterized in that, include: Obtain the virtual tool to be tested, and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video; Obtain the model information of all models, and extract the model features of each model based on the model information of all models; The tool features and the model features of any model are input into the first sub-model of the pre-trained scoring model for feature importance ranking; The target features are obtained by filtering based on the sorted tool features and device features; the target features are a predetermined number of tool features and device features that are ranked first in terms of feature importance. The target features are input into the second sub-model of the pre-trained scoring model to obtain the performance test parameters of any model corresponding to the virtual tool to be tested; Based on the performance test parameters of each machine model corresponding to the virtual tool under test, output the result of whether the virtual tool under test passes the test.

2. The method according to claim 1, characterized in that, The step of inputting the target features into the second sub-model of the pre-trained scoring model to obtain the performance test parameters for any device model corresponding to the virtual tool to be tested includes: The target features are transformed to obtain sparse features corresponding to the virtual tool to be tested and any of the device models. The sparse features are sparsely encoded to obtain dense embedding features; The dense embedding features are input into the first module of the second sub-model to extract low-order features from the dense embedding features, and the dense embedding features are input into the second module of the second sub-model to extract high-order features from the dense embedding features; The low-order features and high-order features in the densely embedded features are input into the output module of the second sub-model to output the performance test parameters of any model corresponding to the virtual tool to be tested.

3. The method according to any one of claims 1 to 2, characterized in that, The step of outputting the result of whether the virtual tool under test passes the test based on the performance test parameters of each machine model corresponding to the virtual tool under test includes: If the performance test parameters of each model corresponding to the virtual tool under test are within the preset parameter threshold range, then the first result of the virtual tool under test passing the test will be output. If the performance test parameters of each device model corresponding to the virtual tool under test exceed the preset parameter threshold range, then a real device evaluation is performed on the virtual tool under test. If the real device evaluation passes, the first result of the virtual tool under test passing the test is output. If the real device evaluation fails, the second result of the virtual tool under test failing the test is output.

4. The method according to claim 3, characterized in that, The process involves performing a real-device evaluation on the virtual tool under test. If the real-device evaluation passes, a first result indicating that the virtual tool under test has passed the test is output. If the real-device evaluation fails, a second result indicating that the virtual tool under test has failed the test is output, including: Based on the performance test parameters of each model corresponding to the virtual tool to be tested, determine the fallback model that exceeds the preset parameter threshold range; The virtual tool to be tested is sent to the real device corresponding to the backup device model for running, and the performance test parameters of the virtual tool to be tested running on the real device corresponding to the backup device model are obtained. If the performance test parameters of the real device are within the preset parameter threshold range, the first result of the virtual tool under test being passed is output; if the performance test parameters of the real device are outside the preset parameter threshold range, the second result of the virtual tool under test being failed is output.

5. A virtual tool testing device, characterized in that, include: The tool feature processing module is used to acquire the virtual tool to be tested and extract the tool features of the virtual tool to be tested based on the attribute information of the virtual tool, wherein the virtual tool is used to add video editing effects to the original video to obtain the target video; The model feature processing module is used to obtain model information of all models and extract model features of each model based on the model information of all models. The model processing module is used to input the tool features and the model features of any model into the first sub-model of the pre-trained scoring model for feature importance ranking; The target features are obtained by filtering based on the sorted tool features and device features; the target features are a predetermined number of tool features and device features that are ranked first in terms of feature importance. The target features are input into the second sub-model of the pre-trained scoring model to obtain the performance test parameters of each model corresponding to the virtual tool to be tested; The test result processing module is used to output the result of whether the virtual tool under test passes the test based on the performance test parameters of each model corresponding to the virtual tool under test.

6. An electronic device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the virtual tool testing method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the virtual tool testing method as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for testing virtual tools as described in any one of claims 1 to 4.

Images