Video material generation method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a video material generation method and device, electronic equipment and storage medium, and relates to the technical field of video processing. The specific implementation scheme is: performing video quality filtering processing on all original videos collected by users in a video library to obtain a plurality of original videos; grouping the plurality of original videos based on a theme and a picture size to obtain a plurality of video groups; and generating a plurality of video materials corresponding to each video group based on a preset video material generation strategy and each video group. The present disclosure can effectively improve the quality of video materials and further improve the quality of video generation.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer technology, in particular to the technical field of video processing, and more particularly to a video material generation method and device, an electronic device, and a storage medium. BACKGROUND

[0002] At present, user videos on a platform can be videos directly published by users or videos automatically generated based on video materials published by users.

[0003] For the way of directly publishing videos by users, the users need to spend a lot of time and effort to shoot video materials, generate videos based on the video materials, and publish the videos on the video platform. This way, the users have a lot of work, which affects the efficiency of the users in creating videos and leads to a decline in the video increment speed of the platform. For the way of automatically generating videos based on video materials published by users, the users upload the shot video materials, and the platform automatically generates videos based on the uploaded video materials and publishes the videos. Compared with the former way, this way can improve the efficiency of the users in publishing videos and has been favored by more and more users. SUMMARY

[0004] The present disclosure provides a video material generation method and device, an electronic device, and a storage medium.

[0005] According to an aspect of the present disclosure, a video material generation method is provided, which includes:

[0006] performing video quality filtering processing on all original videos collected by users in a video library to obtain a plurality of original videos;

[0007] grouping the plurality of original videos based on themes and picture sizes to obtain a plurality of video groups;

[0008] generating a plurality of video materials corresponding to each of the video groups based on a preset video material generation strategy and each of the video groups.

[0009] According to another aspect of the present disclosure, a video material generation device is provided, which includes:

[0010] a video quality filtering module configured to perform video quality filtering processing on all original videos collected by users in a video library to obtain a plurality of original videos;

[0011] a grouping module configured to group the plurality of original videos based on themes and picture sizes to obtain a plurality of video groups;

[0012] a video material generation module configured to generate a plurality of video materials corresponding to each of the video groups based on a preset video material generation strategy and each of the video groups.

[0013] According to still another aspect of the present disclosure, an electronic device is provided, comprising:

[0014] at least one processor; and

[0015] a memory connected with the at least one processor in communication; wherein

[0016] the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method of the aspects and any possible implementation thereof as described above.

[0017] According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of the aspects and any possible implementation thereof as described above is provided.

[0018] According to still another aspect of the present disclosure, a computer program product comprising a computer program which, when executed by a processor, implements the method of the aspects and any possible implementation thereof as described above is provided.

[0019] According to the technology of the present disclosure, the quality of video material can be effectively improved, and the quality of video generation is further improved.

[0020] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0021] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0022] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure;

[0023] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram according to the third embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram according to the fourth embodiment of the present disclosure;

[0026] Figure 5 is a block diagram of an electronic device for implementing the method of the embodiments of the present disclosure. DETAILED DESCRIPTION

[0027] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are included to provide a thorough understanding of embodiments of the present disclosure and are not intended to be inclusive of all embodiments. Accordingly, those of ordinary skill in the art will recognize that various changes in the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. As well, explanations of any well-known functions or constructions are omitted for clarity and conciseness.

[0028] It is apparent that the described embodiments are only part of the embodiments of the present disclosure, but not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of protection of the present disclosure.

[0029] It should be noted that the terminal device involved in the embodiments of the present disclosure can include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and the like. The display device can include, but is not limited to, a personal computer, a television, and the like.

[0030] In addition, the term "and / or" in the embodiments of the present disclosure is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects before and after it.

[0031] The quality of the generated video depends largely on the quality of the video material provided by the user. In the current technology, the video material is completely manually captured by the user, and no quality detection is performed on it. Therefore, the quality of the video material cannot be effectively ensured, and the quality of the generated video is low.

[0032] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; as Figure 1 shown, the embodiment provides a video material generation method, which is applied to a video platform and can specifically include the following steps:

[0033] S101, performing video quality filtering processing on all original videos collected by users in a video library to obtain a plurality of original videos;

[0034] The video material of the embodiment refers to the source material for generating a video published to a platform. The video material in the prior art is the original video collected by a user. Since the video platform in the prior art does not perform any quality detection on the original video of the user, the quality of the video material is low, and thus the quality of the video directly generated based on the video material is also low. Based on this, the technical scheme of the embodiment is to provide a generation scheme of the video material, so as to provide the quality of the generated video material, and thus when a video is generated based on the video material, the quality of the generated video can be improved.

[0035] In the embodiment, the video library is a video library of a user. For example, a user who wants to use the automatic video generation service can register with the video platform and purchase the corresponding service. When using, the video platform configures certain resources for the user. The user uploads the original video shot by the user to the video library under the name of the user. After the above processing, the video library under the name of the user can include multiple original videos collected by the user.

[0036] In addition, it should be noted that in the embodiment, when the user uploads the original video shot by the user to the video library, the user needs to identify the theme of the original video. Because the video material generated by combining original videos of different themes will be more conspicuous and have poorer continuity. Therefore, in order to improve the quality of the generated video material, in the embodiment, the user needs to identify the theme of the original video when uploading the original video.

[0037] In the embodiment, in order to improve the quality of the generated video material, all original videos in the video library need to be filtered for quality, and the original videos with poor quality are removed, which can improve the quality of the generated video material.

[0038] S102, grouping the multiple original videos based on the theme and the picture size, to obtain multiple video groups;

[0039] For all original videos in the video library, grouping can be performed based on the theme and the picture size. For example, through the grouping, the theme and the picture size in the same video group are consistent, which is more conducive to generating high-quality video material.

[0040] S103, generating a plurality of video materials corresponding to each video group based on the preset video material generation strategy and each video group.

[0041] The video material generation strategy of the embodiment is used to control the generation of the video material. Specifically, in each video group, a plurality of video materials are generated based on the original videos in the video group by using the preset video material generation strategy. Finally, for each video group, a plurality of video materials can be obtained.

[0042] The video material generation method of the embodiment can effectively filter out low-quality original videos by performing video quality filtering processing on all original videos collected by users in the video library, effectively guarantee the quality of the multiple original videos used to generate the video material, and further improve the quality of the generated video material. Moreover, in the embodiment, multiple original videos are grouped based on themes and picture sizes to obtain multiple video groups, and based on a preset video material generation strategy and each video group, a plurality of video materials corresponding to each video group are generated, which can effectively guarantee that the plurality of video materials of the same video group are of the same theme and the same picture size, effectively guarantee the quality of the video materials corresponding to the same video group, and further effectively improve the quality of the video generated based on the video material of each video group.

[0043] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure; as Figure 2 indicated, the video material generation method of the embodiment can effectively guarantee that the plurality of video materials of the same video group are of the same theme and the same picture size, effectively guarantee the quality of the video materials corresponding to the same video group, and further effectively improve the quality of the video generated based on the video material of each video group. Figure 1 The technical solutions of the present disclosure are further introduced in more detail based on the technical solutions of the above Figure 2 indicated, the video material generation method of the embodiment can effectively guarantee that the plurality of video materials of the same video group are of the same theme and the same picture size, effectively guarantee the quality of the video materials corresponding to the same video group, and further effectively improve the quality of the video generated based on the video material of each video group.

[0044] S201, obtaining themes of each original video in the video library;

[0045] S202, extracting core words of the original videos based on the themes of the original videos;

[0046] For example, in the embodiment, a pre-trained core word extraction model can be used to implement the core word extraction model, which is trained using multiple training themes and training core words labeled for each training theme. Each training theme can be the theme of a video. For example, the core word extraction module can be a named entity recognition (Named Entity Recognition; NER) model. Alternatively, other core word extraction rules such as templates can be used to extract core words from themes.

[0047] In addition, it should be noted that there are some original videos whose theme descriptions are not standardized, etc., which cannot extract core words.

[0048] S203, detecting whether there is an original video in the video library that cannot extract core words; if there is, performing step S204; if there is not, performing step S205;

[0049] S204, deleting the original video in the video library that cannot extract core words; performing step S205;

[0050] The steps S201-S205 can be a preprocessing process of the video library. After the preprocessing, some original videos that cannot extract core words can be deleted to ensure the quality of the original videos of the generated video materials, and thus the quality of the generated video materials can be improved.

[0051] S205, obtaining a quality score of each original video in the video library;

[0052] S206, performing video quality filtering processing on each original video in the video library based on a preset quality score threshold and the quality score of each original video, to obtain a plurality of original videos meeting the requirements.

[0053] For example, in a specific implementation, at least one of the watermark recognition score, the marketing number recognition score, the definition recognition score, and the courseware recognition score of each original video in the video library can be obtained. Specifically, the score of each category can be implemented by using a neural network model of the corresponding category, and the scores of the categories can be a value between 0 and 1.

[0054] For example, for each original video, a watermark recognition model can be used to identify the watermark recognition score of the original video. A marketing number recognition model can be used to identify the marketing number recognition score of the original video. A definition recognition model can be used to identify the definition recognition score of the original video. A courseware recognition model can be used to identify the courseware recognition score of the original video.

[0055] In order to ensure the originality and video quality of the generated video, the original video of the generated video material must also be an original video. For example, the higher the watermark recognition score, the higher the probability that the video does not contain a watermark. The higher the marketing number recognition score, the higher the probability that the video is not a marketing number. The higher the definition recognition score, the higher the definition of the video. The higher the courseware recognition score, the higher the probability that the video is not a courseware. At this time, the higher the score of each category, the higher the quality of the video.

[0056] Then, based on at least one of the watermark recognition score, the marketing number recognition score, the definition recognition score, and the courseware recognition score of each original video, and a preset weight ratio, a quality score of the corresponding original video is obtained. That is, at least one of the watermark recognition score, the marketing number recognition score, the definition recognition score, and the courseware recognition score of each original video is multiplied by the weight of the corresponding category and then added to obtain the quality score of the original video.

[0057] In the embodiment, the preset quality score threshold can be configured based on experience. It is determined whether the quality score of each original video is greater than or equal to the quality score threshold. If not, the original video is filtered out, otherwise, the original video is retained. After the above video quality filtering processing is performed on all original videos in the video library, a plurality of original videos meeting the requirements are obtained.

[0058] Alternatively, in the embodiment, the lower the score of each category, the higher the quality of the video. At this time, when performing video quality filtering, it is determined whether the quality score of each original video is less than or equal to the quality score threshold. If not, the original video is filtered out, otherwise, the original video is retained. The remaining implementation principles are the same and will not be described here. In addition, in actual applications, other quality parameters can also be configured, and the implementation manners are the same and will not be described here.

[0059] Steps S205-S206 are an implementation of step S201 of the embodiment shown in Figure 1 In actual applications, other ways can also be used to perform video quality filtering on all original videos in the video library, for example, video quality filtering can be directly performed based on certain quality parameters in the video. In summary, no matter which video quality filtering way is used, the quality of the original videos left can be effectively improved, and the quality of the video materials generated based on the original videos can be improved, and the quality of the video generated based on the video materials can be further improved.

[0060] S207, grouping the plurality of original videos according to the core word and the picture size, so that the core word and the picture size in the same video group are the same, and a plurality of video groups are obtained;

[0061] It is considered that when generating a video, if the same video includes video materials of different themes, it will be very conspicuous and the user experience will be very poor, which will affect the stickiness of users in the video platform. If the picture sizes of the videos included in the same video are inconsistent, the quality of the video will be distorted, which will cause the problem of the decrease of the video clarity. Therefore, in order to improve the quality of the generated video, the quality of the video materials for generating the video must be ensured first. In the embodiment, the original videos with the same core word and picture size are divided into the same video group, so as to ensure the quality of the video materials generated based on each video group.

[0062] In addition, it is considered that the theme of each original video can be long, and the core word is extracted based on the theme of the video. Therefore, the plurality of original videos can be grouped according to the core word and the picture size, which can effectively improve the grouping efficiency.

[0063] S208, performing grouping quality filtering processing on the plurality of video groups based on a preset grouping screening strategy;

[0064] In actual applications, a plurality of video groups can be obtained according to the grouping manner described above. For example, one original video, two original videos or a plurality of original videos can be included in different video groups. In this embodiment, during the quality filtering of the grouping, a video group in which the number of original videos is less than a preset number threshold and / or the total duration of the included videos is less than a first preset duration threshold can be filtered out.

[0065] Specifically, in this embodiment, in order to generate more and better video materials based on each video group, the number of original videos included in the video group must be greater than a certain preset number threshold. For example, if only one original video is included in the video group, more video materials cannot be generated based on the one original video. Therefore, in order to improve the quality of the generated video materials, the video group can be filtered out at this time. In addition, if the original videos included in a certain video group are all relatively short and the total duration does not reach the first preset duration threshold, the video group can be filtered out at this time. The first preset duration threshold can be set with reference to the historical click volume of the videos of the video platform. For example, through statistics and analysis, the duration of the videos of the video platform with a historical click volume greater than a preset click volume threshold is concentrated above 40s, and the first preset duration threshold can be set to 40s at this time. The preset click volume threshold can be a relatively reasonable click volume value set based on experience.

[0066] Through the above grouping quality filtering, the video groups with poor quality can be filtered out to ensure the quality of the video materials generated subsequently.

[0067] S209, combining the plurality of original videos in each video group according to a preset restrictive combination strategy to generate a plurality of video materials corresponding to the video groups;

[0068] For example, in this embodiment, a backtracking algorithm with restrictions can be used to combine the plurality of original videos in each video group according to a preset restrictive combination strategy to generate a plurality of video materials corresponding to the video groups. The preset restrictive combination strategy can include one, two or more restrictive strategies.

[0069] For example, the plurality of original videos in each video group can be combined as one video material according to at least one combination strategy that the duration of the combined video segment needs to reach a second preset duration threshold, the original videos included in the combined video segment are not repeated, and the combined video segments are not repeated, to obtain a plurality of video materials. The second preset duration threshold can be set with reference to the setting method of the first preset duration threshold and with reference to the historical click volume of the videos of the video platform.

[0070] In the combination of generating the video material, any number of any original videos can be combined to obtain a video clip as the video material. In the specific combination, a traversal manner can be adopted to obtain more video materials. For example, in a video group, the more the number of original videos, the more the combinations between different original videos, and the more the expanded video materials. Therefore, the scheme can effectively expand the quantity of the video materials, and further can generate a higher quality video based on more high-quality video materials.

[0071] Optionally, in the embodiment, in each video group, when generating the video material, the original video with a time length greater than the second preset time length threshold in the video group can also be reserved as a video material. Of course, all original videos can also be reserved as the video material. Or other strategies can also be adopted to reserve part of the original videos as the video material. In actual application, the more the video materials in the video group, the more abundant the materials for generating the video, and the higher the quality of the generated video.

[0072] S210, generating a video based on the video materials of each video group.

[0073] In the embodiment, when generating the video, the video material theme of the same video group is consistent, and the picture size is consistent. The video generation model can automatically generate a high-quality video based on all the video materials in the same video group. Compared with the prior art, the number of video materials is more and the quality is higher when generating the video, and thus the quality of the generated video can be effectively improved.

[0074] The video material generation method of the embodiment can effectively improve the quality of the generated video material by deleting the original video in the video library that cannot extract the core word, filtering the video quality of the original video in the video library, and filtering the grouping quality of the video group. By adopting the preset restrictive combination strategy, the number of original videos in each video group is combined to generate a number of video materials corresponding to the video group, which can effectively expand the quantity of the video material. Under the premise of ensuring that the quality of the video material is high and the quantity is sufficient, when generating a video based on the video materials of each video group, the quality of the video can be effectively improved.

[0075] Figure 3 is a schematic diagram according to the third embodiment of the disclosure; as Figure 3 shown, the video material generation device 300 of the embodiment includes:

[0076] The video quality filtering module 301 is configured to perform video quality filtering processing on all original videos collected by the user in the video library to obtain a plurality of original videos.

[0077] The grouping module 302 is configured to group the plurality of original videos based on the theme and the picture size, to obtain a plurality of video groups.

[0078] The video material generation module 303 is configured to generate a plurality of video materials corresponding to each of the video groups based on a preset video material generation strategy and each of the video groups.

[0079] The video material generation apparatus 300 of the embodiment generates video materials by using the above modules, and has the same implementation principle and technical effects as the related method embodiments, and details can be referred to the related method embodiments, which will not be repeated here.

[0080] Figure 4 is a schematic diagram according to the fourth embodiment of the disclosure; as Figure 4 shown, the video material generation apparatus 400 of the embodiment includes the same function modules as shown in the above Figure 3 : video quality filtering module 401, grouping module 402 and video material generation module 403.

[0081] As Figure 4 shown, the video material generation apparatus 400 of the embodiment further includes:

[0082] The grouping quality filtering module 404 is configured to perform grouping quality filtering processing on the plurality of video groups based on a preset grouping filtering strategy.

[0083] In an embodiment of the disclosure, the grouping quality filtering module 404 is configured to:

[0084] filter out the video groups in the plurality of video groups, wherein the number of original videos in the video groups is less than a preset number threshold, and / or the total video duration included in the video groups is less than a first preset duration threshold.

[0085] In an embodiment of the disclosure, the video quality filtering module 401 is configured to:

[0086] obtain a quality score of each of the original videos in the video library;

[0087] perform video quality filtering processing on each of the original videos in the video library based on a preset quality score threshold and the quality score of each of the original videos, to obtain the plurality of original videos meeting the requirements.

[0088] In an embodiment of the disclosure, the video quality filtering module 401 is configured to:

[0089] obtain at least one of a watermark identification score, a marketing number identification score, a definition identification score and a courseware identification score of each of the original videos in the video library;

[0090] Based on at least one of the watermark identification score, the marketing number identification score, the definition identification score and the courseware identification score of each of the original videos, and a preset weight ratio, a quality score of the corresponding original video is obtained.

[0091] As shown in the figure, in one embodiment of the present disclosure, the video material generation device 400 further comprises: Figure 4 A theme acquisition module 405 is configured to acquire the theme of each of the original videos in the video library.

[0092] An extraction module 406 is configured to extract the core word of each of the original videos based on the theme of each of the original videos.

[0093] A deletion module 407 is configured to delete the original video in the video library which does not extract the core word.

[0094] In one embodiment of the present disclosure, the grouping module 402 is configured to:

[0095] Group the plurality of original videos according to the core word and the picture size, so that the core word and the picture size in the same video group are the same, and obtain the plurality of video groups.

[0096] In one embodiment of the present disclosure, the video material generation module 403 is configured to:

[0097] Use a preset restrictive combination strategy to combine the plurality of original videos in each of the video groups, and generate the plurality of video materials corresponding to the video groups.

[0098] In one embodiment of the present disclosure, the video material generation module 403 is configured to:

[0099] In each of the video groups, combine the plurality of original videos in the video group as one of the video materials according to at least one of the combination strategies that the length of the combined video segment needs to reach a second preset length threshold, the original videos included in the combined video segment are not repeated, and the combined video segments are not repeated, and obtain the plurality of video materials.

[0100] As shown in the figure, in one embodiment of the present disclosure, the video material generation device 400 further comprises:

[0101] Figure 4 A video generation module 408 is configured to generate a video based on the plurality of video materials of each of the video groups.

[0102]

[0103] ​​The video material generation apparatus 400 of the embodiment generates video material by using the above modules, and the implementation principle and technical effects of generating video material are the same as those of the above method embodiments. For details, refer to the description of the above method embodiments, which will not be repeated here.

[0104] In the technical solution of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0105] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0106] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the present disclosure described and / or claimed in this document.

[0107] As shown in Figure 5 The electronic device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded into a random access memory (RAM) 503 from a storage unit 508. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0108] Various components in the electronic device 500 are connected to the I / O interface 505, including an input unit 506 such as a keyboard, a mouse, etc., an output unit 507 such as various types of displays, a speaker, etc., a storage unit 508 such as a magnetic disk, an optical disk, etc., and a communication unit 509 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0109] The computing unit 501 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs various methods and processes described above, such as the above-described methods of the present disclosure. For example, in some embodiments, the above-described methods of the present disclosure can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded onto the RAM 503 and executed by the computing unit 501, one or more steps of the above-described methods of the present disclosure described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the above-described methods of the present disclosure by any other appropriate means, such as by means of firmware.

[0110] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0111] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0112] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0114] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0115] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0116] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, which is not limited herein.

[0117] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating video clips, comprising: performing video quality filtering on all original videos collected by users in a video library to obtain a plurality of original videos; a quality score of each of the original videos is determined based on at least one of a watermark identification score, a marketing number identification score, a definition identification score, and a courseware identification score of the original video; grouping the plurality of original videos based on a theme and a picture size to obtain a plurality of video groups; all original videos in each of the video groups have a consistent picture size and include core words extracted based on the theme; combining any number of original videos in each of the video groups in a traversal manner based on a preset restrictive combination strategy to generate a plurality of video clips corresponding to the video group; a same video group supports a plurality of combinations and can generate the plurality of video clips; the preset restrictive combination strategy includes at least one of a combination strategy that a time length of a combined video segment needs to reach a second preset time length threshold, a combination strategy that original videos included in a combined video segment are not repeated, and a combination strategy that combined video segments are not repeated.

2. The method of claim 1, wherein, After grouping the plurality of original videos based on a theme and a picture size to obtain a plurality of video groups, before generating a plurality of video clips corresponding to each of the video groups based on a preset video clip generation strategy and each of the video groups, the method further comprises: performing grouping quality filtering on the plurality of video groups based on a preset grouping screening strategy.

3. The method of claim 2, wherein, Performing grouping quality filtering on the plurality of video groups based on a preset grouping screening strategy comprises: filtering out the video groups in which the number of original videos is less than a preset number threshold and / or the total time length of videos included is less than a first preset time length threshold.

4. The method of claim 1 or 2, wherein, Performing video quality filtering on all original videos collected by users in a video library to obtain a plurality of original videos comprises: obtaining a quality score of each of the original videos in the video library; performing video quality filtering on each of the original videos in the video library based on a preset quality score threshold and the quality score of each of the original videos to obtain the plurality of original videos that meet the requirements.

5. The method of claim 4, wherein, Obtaining a quality score of each of the original videos in the video library comprises: obtaining at least one of a watermark identification score, a marketing number identification score, a definition identification score, and a courseware identification score of each of the original videos in the video library; obtaining the quality score of the corresponding original video based on at least one of the watermark identification score, the marketing number identification score, the definition identification score, and the courseware identification score of each of the original videos and a preset weight ratio.

6. The method of claim 1, wherein, Before performing video quality filtering on all original videos collected by users in a video library to obtain a plurality of original videos, the method further comprises: obtaining a theme of each of the original videos in the video library; extracting core words of the original videos based on the theme of each of the original videos; deleting the original videos in the video library for which the core words are not extracted.

7. The method of claim 6, wherein, grouping the plurality of original videos based on a theme and a picture size, to obtain a plurality of video groups, including: grouping the plurality of original videos according to the core word and the picture size, so that the core word and the picture size in a same video group are all the same, to obtain the plurality of video groups.

8. The method of claim 1, wherein, combining a plurality of original videos in each video group according to a preset restrictive combination strategy, to generate a plurality of video clips corresponding to the video group, including: combining a plurality of original videos in each video group as a video clip according to at least one combination strategy that the length of the combined video clip needs to reach a second preset length threshold, the original videos included in the combined video clip are not repeated, and the combined video clips are not repeated, to obtain the plurality of video clips.

9. The method of any one of claims 1-8, wherein, After generating a plurality of video clips corresponding to each video group based on a preset video clip generation strategy and each video group, the method further includes: generating a video based on the plurality of video clips of each video group.

10. A device for generating a video clip, including: a video quality filtering module configured to perform video quality filtering processing on all original videos collected by users in a video library, to obtain a plurality of original videos; a quality score of each original video is determined based on at least one of a watermark identification score, a marketing number identification score, a definition identification score, and a courseware identification score of the original video; a grouping module configured to group the plurality of original videos based on a theme and a picture size, to obtain a plurality of video groups; all original videos in each video group have consistent picture sizes, and all include a core word extracted based on the theme; a video clip generation module configured to: combine any number of original videos in each video group in a traversal manner based on a preset restrictive combination strategy, to generate a plurality of video clips corresponding to the video group; a same video group supports a plurality of combinations, and can generate the plurality of video clips; the preset restrictive combination strategy includes at least one combination strategy that the length of the combined video clip needs to reach a second preset length threshold, the original videos included in the combined video clip are not repeated, and the combined video clips are not repeated.

11. The apparatus of claim 10, wherein, The device further includes: a grouping quality filtering module configured to perform grouping quality filtering processing on the plurality of video groups based on a preset grouping screening strategy.

12. The apparatus of claim 11, wherein, The grouping quality filtering module is configured to: filter out the video groups in which the number of original videos is less than a preset number threshold, and / or the total video length included is less than a first preset length threshold.

13. The apparatus of claim 10 or 11, wherein, The video quality filtering module is configured to: obtain a quality score of each original video in the video library; perform video quality filtering processing on each original video in the video library based on a preset quality score threshold and the quality score of each original video, to obtain the plurality of original videos that meet the requirements.

14. The apparatus of claim 13, wherein, The video quality filtering module is configured to: At least one of a watermark identification score, a marketing account identification score, a definition identification score, and a courseware identification score of each of the original videos in the video library is acquired. At least one of a watermark identification score, a marketing account identification score, a definition identification score, and a courseware identification score of each of the original videos in the video library is acquired.

15. The apparatus of claim 10, wherein, The device further includes: A theme acquisition module is configured to acquire a theme of each of the original videos in the video library. An extraction module is configured to extract a core word of the original video based on the theme of each of the original videos. A deletion module is configured to delete the original video in the video library that does not extract the core word.

16. The apparatus of claim 15, wherein, The grouping module is configured to: Group the plurality of original videos according to the core word and the picture size, so that the core word and the picture size in the same video group are the same, and obtain the plurality of video groups.

17. The apparatus of claim 10, wherein, The video material generation module is configured to: Combine a plurality of original videos in each video group as a video material according to at least one combination strategy that the length of the combined video segment needs to reach a second preset length threshold, the original videos included in the combined video segment are not repeated, and the combined video segments are not repeated, to obtain the plurality of video materials.

18. The apparatus of any one of claims 10-17, wherein, The device further includes: A video generation module is configured to generate a video based on the plurality of video materials of each video group.

19. An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-9.

21. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-9.

Images