A method, apparatus, storage medium, and electronic device for business execution

Abstract

This specification discloses a method, apparatus, storage medium, and electronic device for business execution. Among them, first, a target video is obtained, the frame rate of the target video is determined, and the frame rate difference between the frame rate of the target video and a preset target frame rate is determined. The target video and the frame rate difference are input into a preset image model, so that the image model determines the size relationship between the frame rate of the target video and the target frame rate according to the frame rate difference, and respectively determines different adjustment frames for adjusting the target video according to the size relationship, and adjusts the frame rate of the target video according to the adjustment frames to obtain an adjusted target video, and executes the business according to the adjusted target video.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and particularly to a method, apparatus, storage medium, and electronic device for business execution. Background Art

[0002] As one of the current mainstream carriers of information expression, video plays a great role in all walks of life. Essentially, a video is formed by a series of consecutive static images changing at high speed, and the number of static images that change per second in the video is the frame rate of the video.

[0003] In many actual businesses, it may be necessary to use videos with a specific frame rate to execute the business. For example, in businesses such as three-dimensional reconstruction and motion capture using videos, if the frame rate of the video is too high, it will lead to an increase in the processing cost of the video. Therefore, these businesses often need to use videos with a lower frame rate. In some operations and promotions, there may be a need to display videos to users. In this process, it is often necessary to use videos with a higher frame rate to improve the user's viewing experience.

[0004] However, the frame rate of the target video actually obtained in the business may not meet the requirements of the business. Therefore, it is necessary to adjust the frame rate of the obtained target video, remove some frames of the target video with too high a frame rate, or insert intermediate frames into the target video with too low a frame rate to obtain a target video that meets the business requirements.

[0005] However, the effects of existing methods for adjusting video frame rates are not satisfactory. For example, in existing frame removal methods, generally, frames in the video are evenly removed according to the total number of frames of the video. This method may result in the removal of high-quality frame images in the video, while low-quality blurred frames are retained, and the effect is poor in businesses with high requirements for video quality such as three-dimensional reconstruction and motion capture. In existing frame insertion methods, often the same frame as the previous frame is inserted into the video. This method of adjusting the video frame rate may cause problems such as video stuttering, which may affect the user's viewing experience in businesses where videos need to be displayed to users.

[0006] Therefore, how to adjust the frame rate of the video to better execute the business is an urgent problem to be solved. Summary of the Invention

[0007] This specification provides a method, apparatus, storage medium, and electronic device for business execution to partially solve the above problems existing in the prior art.

[0008] This specification adopts the following technical solutions:

[0009] This specification provides a method for business execution, including:

[0010] Obtain a target video;

[0011] Determine the frame rate of the target video, and determine the frame rate difference between the frame rate of the target video and a preset target frame rate;

[0012] Input the target video and the frame rate difference into a preset image model, so that the image model determines an adjustment frame for adjusting the target video according to the frame rate difference, and performs frame rate adjustment on the target video according to the adjustment frame to obtain an adjusted target video;

[0013] Execute a service according to the adjusted target video.

[0014] Optionally, the step of inputting the target video and the frame rate difference into a preset image model, so that the image model determines an adjustment frame for adjusting the target video according to the frame rate difference, and performs frame rate adjustment on the target video according to the adjustment frame to obtain an adjusted target video specifically includes:

[0015] Input the target video and the frame rate difference into a preset image model, so that when the image model determines that the frame rate of the target video is greater than the target frame rate according to the frame rate difference, identify blurred frames that do not meet a preset standard from the target video as adjustment frames for adjusting the target video, and remove the adjustment frames from the target video to obtain an adjusted target video.

[0016] Optionally, the step of identifying blurred frames that do not meet a preset standard from the target video specifically includes:

[0017] For each video frame included in the target video, determine whether the clarity at the image edge of the video frame is not lower than a preset clarity;

[0018] If it is determined that the clarity at the image edge of the video frame is lower than the preset clarity, determine the video frame as a blurred frame.

[0019] Optionally, the step of removing the adjustment frames from the target video to obtain an adjusted target video specifically includes:

[0020] Determine whether the number of the blurred frames is not less than the frame rate difference;

[0021] If it is determined that the number of the blurred frames is less than the frame rate difference, screen out the supplementary frames from other video frames in the target video except the blurred frames with the constraint that the sum of the number of the blurred frames and the number of the supplementary frames screened out from the target video is not less than the frame rate difference;

[0022] Remove the blurred frames and the supplementary frames from the target video to obtain an adjusted target video.

[0023] Optionally, the step of screening out the supplementary frames from other video frames in the target video except the blurred frames, with the constraint that the sum of the number of the blurred frames and the number of the supplementary frames screened out from the target video is not less than the frame rate difference, specifically includes:

[0024] Screen out initial supplementary frames from other video frames in the target video except the blurred frames, with the constraint that the sum of the number of the blurred frames and the number of the supplementary frames screened out from the target video is not less than the frame rate difference;

[0025] Remove the initial supplementary frames from the target video to obtain a video after removal;

[0026] Input the video after removal into the feature extraction layer of the image model to obtain video features of the video after removal, and input the video features into the generation layer of the image model to obtain a video generated based on the video features;

[0027] According to the generated video, determine whether the initial supplementary frames meet the preset conditions, and when it is determined that the initial supplementary frames do not meet the preset conditions, re-screen out initial supplementary frames from other video frames in the target video except the blurred frames with the constraint, and input the video after removal obtained by the re-screened initial supplementary frames into the feature extraction layer until initial supplementary frames that meet the preset conditions are obtained, and use the initial supplementary frames that meet the preset conditions as the determined supplementary frames.

[0028] Optionally, the step of determining whether the initial supplementary frames meet the preset conditions according to the generated video specifically includes:

[0029] For each initial supplementary frame, if it is determined that the generated video contains the initial supplementary frame, determine that the initial supplementary frame does not meet the preset conditions.

[0030] Optionally, the step of inputting the target video and the frame rate difference into a preset image model, so that the image model determines adjustment frames for adjusting the target video according to the frame rate difference, and performs frame rate adjustment on the target video according to the adjustment frames to obtain an adjusted target video, specifically includes:

[0031] Input the target video and the frame rate difference into a preset image model. When the image model determines that the frame rate of the target video is less than the target frame rate according to the frame rate difference, generate a number of intermediate frames according to the frame rate difference as adjustment frames for adjusting the target video, and insert the adjustment frames into the target video to obtain the adjusted target video.

[0032] This specification provides a device for business execution, including:

[0033] An acquisition module, configured to acquire a target video;

[0034] A determination module, configured to determine the frame rate of the target video and determine the frame rate difference between the frame rate of the target video and a preset target frame rate;

[0035] A processing module, configured to input the target video and the frame rate difference into a preset image model, so that the image model determines adjustment frames for adjusting the target video according to the frame rate difference, and perform frame rate adjustment on the target video according to the adjustment frames to obtain the adjusted target video;

[0036] An execution module, configured to execute a business according to the adjusted target video.

[0037] This specification provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above method for business execution is implemented.

[0038] This specification provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above method for business execution is implemented.

[0039] At least one of the above technical solutions adopted in this specification can achieve the following beneficial effects:

[0040] In the method for business execution provided in this specification, first, a target video is acquired, the frame rate of the target video is determined, and the frame rate difference between the frame rate of the target video and a preset target frame rate is determined. The target video and the frame rate difference are input into a preset image model. When the image model determines that the frame rate of the target video is greater than the target frame rate according to the frame rate difference, identify blurred frames that do not meet the preset standard from the target video as adjustment frames for adjusting the target video, and remove the adjustment frames from the target video to obtain the adjusted target video. Or when the image model determines that the frame rate of the target video is less than the target frame rate according to the frame rate difference, generate a number of intermediate frames according to the frame rate difference as adjustment frames for adjusting the target video, and insert the adjustment frames into the target video to obtain the adjusted target video. Finally, a business is executed according to the adjusted target video.

[0041] As can be seen from the above method, this specification determines whether the target video needs to have frames removed or frames inserted through a preset image model, and respectively determines the adjustment frames for adjusting the target video in different situations, which can meet the video frame rate adjustment requirements of various services. On this basis, the frame rate of the target video is adjusted according to the adjustment frames to obtain the adjusted target video, and the adjusted target video can better execute the service. Description of the Drawings

[0042] The drawings described herein are used to provide a further understanding of this specification and form a part of this specification. The schematic embodiments of this specification and their descriptions are used to explain this specification and do not constitute an improper limitation of this specification. In the drawings:

[0043] Figure 1 is a schematic flowchart of a method for executing a service provided in this specification;

[0044] Figure 2 is a detailed schematic diagram of frame rate adjustment provided in this specification;

[0045] Figure 3 is a schematic diagram of a device for executing a service provided in this specification;

[0046] Figure 4 is for Figure 1 schematic structural diagram of an electronic device. Detailed Embodiments

[0047] To make the purpose, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0048] With the rapid development of the Internet, video, as an excellent information expression carrier, has played a huge role in more and more industries.

[0049] However, different services may have different requirements for the frame rate of the video. For example, in services such as three-dimensional reconstruction and motion capture using video, if the frame rate of the video is too high, it will lead to an increase in the processing cost of the video. Therefore, these services often need to use videos with a lower frame rate. In some operations and promotion services, there may be a need to display videos to users. In this process, videos with a higher frame rate are often needed to improve the user's viewing experience.

[0050] When the frame rate of the target video actually obtained in the service does not meet the requirements of the service, it is often necessary to adjust the frame rate of the video.

[0051] However, the effects of existing methods for adjusting the video frame rate are not satisfactory. For example, in the existing method of removing frames, generally, frames in the video are evenly removed according to the total number of frames of the video. This method may cause high-quality frame images in the video to be removed, while low-quality blurred frames are retained, resulting in poor effects in services with high requirements for video quality such as 3D reconstruction and motion capture. In the existing method of inserting frames, often frames identical to the previous frame are inserted into the video. This method of adjusting the video frame rate may cause problems such as video stuttering, which may affect the viewing experience of users in services where videos need to be presented to users.

[0052] Based on this, this specification provides a method for business execution, which includes obtaining a target video, determining the frame rate of the target video, and determining the frame rate difference between the frame rate of the target video and a preset target frame rate. Then, input the target video and the frame rate difference into a preset image model, so that the image model determines adjustment frames for adjusting the target video according to the frame rate difference, and adjusts the frame rate of the target video according to the adjustment frames to obtain an adjusted target video. Finally, execute the service according to the adjusted target video.

[0053] The following will describe in detail the technical solutions provided by each embodiment of this specification with reference to the accompanying drawings.

[0054] Figure 1 FIG. is a schematic flowchart of a method for business execution provided in this specification, including the following steps:

[0055] S101: Obtain a target video.

[0056] In this specification, the execution entity for implementing the method for business execution can be a specified device such as a server, or a terminal device such as a desktop computer or a laptop computer, or a client installed in the terminal device. For the sake of convenience of description, this specification will only take the server as the execution entity as an example to describe a method for business execution provided in this specification.

[0057] The server can obtain the target video. Among them, the target video is the video required during the execution of the service, but the frame rate of the target video does not meet the video frame rate requirements of the service.

[0058] S102: Determine the frame rate of the target video, and determine the frame rate difference between the frame rate of the target video and a preset target frame rate.

[0059] The server can determine the frame rate of the target video obtained and determine the frame rate difference between the frame rate of the target video and the preset target frame rate. Among them, the preset target frame rate is the frame rate that meets the requirements of the business video frame rate, which can be determined according to actual needs. Specific values are not specifically limited here.

[0060] S103: Input the target video and the frame rate difference into a preset image model, so that the image model determines an adjustment frame for adjusting the target video according to the frame rate difference, and performs frame rate adjustment on the target video according to the adjustment frame to obtain an adjusted target video.

[0061] The server can input the target video and the frame rate difference into a preset image model, so that the image model determines an adjustment frame for adjusting the target video according to the frame rate difference, and performs frame rate adjustment on the target video according to the adjustment frame to obtain an adjusted target video.

[0062] Specifically, the image model can determine the size relationship between the frame rate of the target video and the target frame rate according to the frame rate difference. When it is determined that the frame rate of the target video is greater than the target frame rate, it can identify the blurred frames that do not meet the preset standard from the target video as the adjustment frames for adjusting the target video, and remove the adjustment frames from the target video to obtain an adjusted target video.

[0063] Among them, in the process of identifying the blurred frames that do not meet the preset standard from the target video, the image model can judge whether the clarity at the image edge of each video frame included in the target video is not lower than the preset clarity. If it is determined that the clarity at the image edge of the video frame is lower than the preset clarity, the video frame is determined as a blurred frame.

[0064] It should be noted that among all the video frames included in the target video, the number of blurred frames identified by the image model may be lower than the frame rate difference between the frame rate of the target video and the preset target frame rate. In this way, even if all the blurred frames included in the target video are removed, the frame rate of the target video after removal still cannot reach the target frame rate. Therefore, it is also necessary to judge whether the number of blurred frames is not less than the frame rate difference, and when the number of blurred frames is less than the frame rate difference, additional supplementary frames are determined in the target video for removal, so that the frame rate of the target video after removal reaches the target frame rate.

[0065] Specifically, the image model can judge whether the number of blurred frames included in the target video is not less than the frame rate difference. If it is determined that the number of blurred frames is less than the frame rate difference, the supplementary frames are screened out from the other video frames in the target video except the blurred frames with the constraint that the sum of the number of blurred frames and the number of supplementary frames screened out from the target video is not less than the frame rate difference.

[0066] Among them, in order to make the target video as smooth as possible after elimination, the supplementary frames selected from the target video cannot carry key information, and each supplementary frame cannot be concentrated in the same video segment. To achieve this goal, the image model can use the constraint that the sum of the number of blurred frames and the number of supplementary frames selected from the target video is not less than the frame rate difference. From the other video frames in the target video except the blurred frames, initial supplementary frames are selected and the initial supplementary frames are removed from the target video to obtain the video after elimination.

[0067] The server can input the video after elimination into the feature extraction layer in the image model to obtain the video features of the video after elimination, and input the video features into the generation layer in the image model to obtain the video generated based on the video features.

[0068] It should be noted that the above video after elimination is the target video after removing the initial supplementary frames. The above image model can extract the video features of the video after elimination and generate a video based on the video features. Among them, the feature extraction layer of the image model is equivalent to an encoder, and the generation layer is equivalent to a decoder. When the image model receives the input video after elimination, the feature extraction layer can extract the video features of the video after elimination and input the video features into the generation layer in the image model to generate a video. The image model is equivalent to restoring the video after elimination, and the generated video may contain the frame images that have been removed compared with the video after elimination.

[0069] That is to say, the above image model can restore the video after elimination to obtain a generated video closer to the target video. On this basis, if the generated video by the above model contains the removed initial supplementary frames, it means that the removed initial supplementary frames contain key information and cannot be used as the removed video frames. Correspondingly, if the generated video by the above model does not contain the removed initial supplementary frames, it means that the removed initial supplementary frames have little impact on the target video and can be used as the removed video frames.

[0070] Among them, the above image model can use existing deep learning models that can achieve the above effects and can be trained on a preset dataset to obtain an image model that can achieve the above effects. For example, the server can obtain a preset dataset, which contains training videos and training videos with some video frames removed. The training videos with some video frames removed are input into the image model to be trained, so that the image model to be trained restores the training videos with some video frames removed to generate new videos, and trains the image model to be trained with the goal of minimizing the deviation between the generated new videos and the training videos to obtain a trained image model. Among them, the training videos may not contain any redundant image frames, all the frame images contained in the training videos can be video frames containing key information, and the fluency of the training videos is relatively high.

[0071] On this basis, the image model can judge whether the initial supplementary frame meets the preset conditions according to the generated video, and when it is determined that the initial supplementary frame does not meet the preset conditions, re-screen the initial supplementary frame from other video frames in the target video except the blurred frame according to the constraint conditions, and input the removed video obtained by the re-screened initial supplementary frame into the feature extraction layer until an initial supplementary frame that meets the preset conditions is obtained, and use the initial supplementary frame that meets the preset conditions as the determined supplementary frame. Among them, for each initial supplementary frame, if it is determined that the generated video contains the initial supplementary frame, it is determined that the initial supplementary frame does not meet the preset conditions.

[0072] In this way, when the image model determines that the initial supplementary frame does not meet the preset conditions according to the generated video, it means that the initially determined initial supplementary frame will affect the fluency of the target video. That is to say, the initially determined initial supplementary frame contains key information and cannot be used as an image frame to be removed. Therefore, the image model can re-screen the initial supplementary frame from other video frames in the target video except the blurred frame according to the constraint conditions, and input the removed video obtained by the re-screened initial supplementary frame into the feature extraction layer until an initial supplementary frame that meets the preset conditions is obtained, and use the initial supplementary frame that meets the preset conditions as the determined supplementary frame. For the initial supplementary frame that meets the preset conditions, the initial supplementary frame does not contain key information and can be used as an image frame to be removed. In this way, the image model can directly use the initial supplementary frame that meets the preset conditions as the supplementary frame, and remove the blurred frame and the supplementary frame contained in the target video to obtain an adjusted target video.

[0073] After determining the blurred frames and supplementary frames in the target video, the image model can remove the blurred frames and supplementary frames from the target video to obtain an adjusted target video.

[0074] Further, when the image model determines that the frame rate of the target video is less than the target frame rate, the image model may generate a number of intermediate frames according to the frame rate difference as adjustment frames for adjusting the target video, and insert the adjustment frames into the target video to obtain the adjusted target video.

[0075] Specifically, the image model may determine the number of intermediate frames to be inserted into the target video according to the frame rate difference, and generate the corresponding number of intermediate frames according to the target video as adjustment frames for adjusting the target video, and insert the adjustment frames into the target video to obtain the adjusted target video. Among them, the image model may generate intermediate frames between any two consecutive image frames in the target video.

[0076] S104: Execute the service according to the adjusted target video.

[0077] The server may execute the service according to the adjusted target video.

[0078] For example, in a 3D reconstruction service, the frame rate of the target video actually obtained in the service is too high to meet the service requirements. Then the server may remove some image frames in the target video according to the method provided in this specification to execute the service according to the target video after removal. For another example, in a private domain operation service, it is necessary to upload the target video shown to users, and the frame rate of the actually obtained target video is too low, which may affect the user viewing experience. Then the server may perform frame interpolation on the target video according to the method provided in this specification to execute the service according to the target video after frame interpolation.

[0079] To describe the solution in this specification in more detail, this specification also provides a detailed schematic diagram of frame rate adjustment, as Figure 2 shown.

[0080] Figure 2 is a detailed schematic diagram of frame rate adjustment provided in this specification;

[0081] From Figure 2 it can be seen that when this specification performs frame rate adjustment, the server may obtain the target video, determine the frame rate difference between the frame rate of the target video and the preset target frame rate, and input the target video and the frame rate difference into the preset image model, so that the image model determines the frame rate adjustment operation required for the target video according to the frame rate difference. When the frame rate of the target video is greater than the target frame rate, determine the blurred frames and supplementary frames included in the target video and remove them in the target video. When the frame rate of the target video is less than the target frame rate, generate a number of intermediate frames according to the target video and insert the intermediate frames into the target video to finally obtain the adjusted target video.

[0082] As can be seen from the above method, this specification can determine that when the frame rate of the target video is greater than the target frame rate according to the frame rate difference between the frame rate of the target video and the preset target frame rate, identify the blurred frames that do not meet the preset standards from the target video as the adjustment frames for adjusting the target video, and remove the adjustment frames from the target video to obtain the adjusted target video. Or when it is determined according to the frame rate difference that the frame rate of the target video is less than the target frame rate, generate a number of intermediate frames according to the frame rate difference as the adjustment frames for adjusting the target video, and insert the adjustment frames into the target video to obtain the adjusted target video. Thus, the frame rate of the target video can be adjusted according to the video frame rate requirements of different services, and finally the target video with the frame rate meeting the service requirements can be obtained, which can better execute the service.

[0083] At the same time, during the process of removing frames, this specification will identify the blurred frames and supplementary frames in the target video, and preferentially remove the blurred frames and supplementary frames to ensure that the removed frame images will not affect the smoothness of the target video and that the removed frame images do not contain key information, which improves the quality of the adjusted target video to a certain extent.

[0084] The above is the method for implementing one or more services in this specification. Based on the same idea, this specification also provides the corresponding device for implementing services as Figure 3 shown.

[0085] Figure 3 The figure is a schematic diagram of a device for implementing services provided by this specification, including:

[0086] An acquisition module 301, configured to acquire a target video;

[0087] A determination module 302, configured to determine the frame rate of the target video and determine the frame rate difference between the frame rate of the target video and the preset target frame rate;

[0088] A processing module 303, configured to input the target video and the frame rate difference into a preset image model, so that the image model determines the adjustment frames for adjusting the target video according to the frame rate difference, and adjusts the frame rate of the target video according to the adjustment frames to obtain the adjusted target video;

[0089] An execution module 304, configured to execute services according to the adjusted target video.

[0090] Optionally, the processing module 303 is specifically configured to input the target video and the frame rate difference into a preset image model, so that when the image model determines that the frame rate of the target video is greater than the target frame rate according to the frame rate difference, identify the blurred frames that do not meet the preset criteria from the target video as adjustment frames for adjusting the target video, and remove the adjustment frames from the target video to obtain the adjusted target video.

[0091] Optionally, the processing module 303 is specifically configured to, for each video frame included in the target video, determine whether the clarity at the image edge of the video frame is not lower than a preset clarity; if it is determined that the clarity at the image edge of the video frame is lower than the preset clarity, determine the video frame as a blurred frame.

[0092] Optionally, the processing module 303 is specifically configured to determine whether the number of the blurred frames is not less than the frame rate difference; if it is determined that the number of the blurred frames is less than the frame rate difference, then, with the constraint that the sum of the number of the blurred frames and the number of supplementary frames selected from the target video is not less than the frame rate difference, select the supplementary frames from other video frames in the target video except the blurred frames; remove the blurred frames and the supplementary frames from the target video to obtain the adjusted target video.

[0093] Optionally, the processing module 303 is specifically configured to, with the constraint that the sum of the number of the blurred frames and the number of supplementary frames selected from the target video is not less than the frame rate difference, select initial supplementary frames from other video frames in the target video except the blurred frames;

[0094] Remove the initial supplementary frames from the target video to obtain the video after removal;

[0095] Input the video after removal into the feature extraction layer of the image model to obtain the video features of the video after removal, and input the video features into the generation layer of the image model to obtain the video generated based on the video features;

[0096] According to the generated video, determine whether the initial supplementary frames meet the preset conditions, and when it is determined that the initial supplementary frames do not meet the preset conditions, re-select the initial supplementary frames from other video frames in the target video except the blurred frames with the constraint condition, and input the video after removal obtained by the re-selected initial supplementary frames into the feature extraction layer until the initial supplementary frames that meet the preset conditions are obtained, and use the initial supplementary frames that meet the preset conditions as the determined supplementary frames;

[0097] Optionally, the processing module 303 is specifically configured to, for each initial supplementary frame, if it is determined that the generated video contains the initial supplementary frame, determine that the initial supplementary frame does not meet the preset condition.

[0098] Optionally, the processing module 303 is specifically configured to input the target video and the frame rate difference into a preset image model, so that when the image model determines that the frame rate of the target video is less than the target frame rate according to the frame rate difference, several intermediate frames are generated according to the frame rate difference as adjustment frames for adjusting the target video, and the adjustment frames are inserted into the target video to obtain an adjusted target video.

[0099] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above Figure 1 provided method for business execution.

[0100] This specification also provides a schematic structural diagram of an electronic device corresponding to Figure 1 as shown in the figure. As Figure 4 shown.

[0101] Figure 4 It is a schematic structural diagram of an electronic device provided in this specification and applied to Figure 1 ...

[0102] As shown in the figure, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, it may also include other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the above Figure 1 method for business execution.

[0103] Of course, in addition to the software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware. That is to say, the execution subject of the following processing flow is not limited to each logic unit, and can also be hardware or logic devices.

[0104] For an improvement in a technology, it can be clearly distinguished whether it is an improvement in hardware (for example, an improvement in the circuit structure of diodes, transistors, switches, etc.) or an improvement in software (an improvement in the method flow). However, with the development of technology, many improvements in method flows today can be regarded as direct improvements in hardware circuit structures. Almost all designers obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented with a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user programming the device. The designer can program by himself to "integrate" a digital system on a piece of PLD, without having to ask a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software, which is similar to the software compiler used in program development and writing. The original code before compilation also has to be written in a specific programming language, which is called a hardware description language (HDL), and there is not only one kind of HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones currently are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also be clear that only by slightly logically programming the method flow with the above-mentioned several hardware description languages and programming it into the integrated circuit, it is easy to obtain the hardware circuit that implements the logical method flow.

[0105] The controller can be implemented in any suitable manner. For example, the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program code (such as software or firmware) executable by the (micro)processor, logic gates, switches, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of the controller include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in the form of pure computer-readable program code, it is entirely possible to make the controller implement the same function in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be regarded as the structures within the hardware component. Or even, the devices for implementing various functions can be regarded as either software modules for implementing the method or the structures within the hardware component.

[0106] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0107] For the convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0108] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0109] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the specification. It should be understood that each flow and / or block in the flowchart and / or block diagram, and combinations of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0110] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0112] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0113] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory. The memory is an example of computer-readable media.

[0114] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0115] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0116] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0118] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiment.

[0119] The above description is only for the embodiments of this specification and is not intended to limit this specification. For those skilled in the art, various modifications and changes can be made to this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included within the scope of the claims of this specification.

Claims

1. A method for executing a service, characterized in that: include: Get the target video; Determining a frame rate of the target video, and determining a frame rate difference between the frame rate of the target video and a preset target frame rate; The target video and the frame rate difference are input into a preset image model. When the image model determines that the frame rate of the target video is greater than the target frame rate according to the frame rate difference, and the number of blurred frames in the target video is less than the frame number difference corresponding to the frame rate difference, the initial supplementary frame is screened out from other video frames in the target video except the blurred frame, with the sum of the number of blurred frames and the number of initial supplementary frames screened out from the target video being not less than the frame number difference as a constraint condition. The initial supplementary frame is a non-blurred frame, and the clarity at the image edge of the blurred frame is lower than the preset clarity. The initial supplementary frame is removed from the target video to obtain a video after removal. Input the removed video into the feature extraction layer in the image model to obtain the video features of the removed video, and input the video features into the generation layer in the image model to obtain a video generated based on the video features, wherein the feature extraction layer and the generation layer in the image model are used to restore the removed video; when the generated video does not contain any of the initial supplementary frames, the initial supplementary frame is used as a supplementary frame, and the supplementary frame and the blurred frame are removed from the target video to obtain an adjusted target video; The service is executed according to the adjusted target video.

2. The method according to claim 1, characterized in that Also includes the steps: In the case that the generated video contains the initial supplementary frame, the initial supplementary frame is re-screened from the other video frames in the target video except the blurred frame according to the constraint condition, and the eliminated video obtained by the re-screened initial supplementary frame is input into the feature extraction layer until the video generated by the re-screened initial supplementary frame does not contain the re-screened initial supplementary frame, and the re-screened initial supplementary frame is used as the determined supplementary frame.

3. The method according to claim 1, characterized in that When the image model determines that the frame rate of the target video is less than the target frame rate based on the frame rate difference, several intermediate frames are generated based on the frame rate difference as adjustment frames for adjusting the target video, and the adjustment frames are inserted into the target video to obtain the adjusted target video.

4. A device for executing a service, characterized in that: include: An acquisition module, used to acquire a target video; A determination module, used to determine the frame rate of the target video, and determine a frame rate difference between the frame rate of the target video and a preset target frame rate; A processing module, for inputting the target video and the frame rate difference into a preset image model, and when the image model determines that the frame rate of the target video is greater than the target frame rate according to the frame rate difference, and the number of blurred frames in the target video is less than the frame number difference corresponding to the frame rate difference, taking the sum of the number of blurred frames and the number of initial supplementary frames screened out from the target video as a constraint condition not less than the frame number difference, screen out initial supplementary frames from other video frames in the target video except the blurred frames, the initial supplementary frames being non-blurred frames, and the clarity at the image edge of the blurred frames being lower than the preset clarity; and removing the initial supplementary frames from the target video to obtain a video after removal; Input the removed video into the feature extraction layer in the image model to obtain the video features of the removed video, and input the video features into the generation layer in the image model to obtain a video generated based on the video features, wherein the feature extraction layer and the generation layer in the image model are used to restore the removed video; when the generated video does not contain any of the initial supplementary frames, the initial supplementary frame is used as a supplementary frame, and the supplementary frame and the blurred frame are removed from the target video to obtain an adjusted target video; An execution module is used to execute a service according to the adjusted target video.

5. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 3 is implemented.

Images