WO2020107625A1 - Video classification method and apparatus, electronic device, and computer readable storage medium - Google Patents

Video classification method and apparatus, electronic device, and computer readable storage medium Download PDF

Info

Publication number
WO2020107625A1
WO2020107625A1 PCT/CN2018/125409 CN2018125409W WO2020107625A1 WO 2020107625 A1 WO2020107625 A1 WO 2020107625A1 CN 2018125409 W CN2018125409 W CN 2018125409W WO 2020107625 A1 WO2020107625 A1 WO 2020107625A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
type
picture
classification
computer
Prior art date
Application number
PCT/CN2018/125409
Other languages
French (fr)
Chinese (zh)
Inventor
刘德平
Original Assignee
北京微播视界科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京微播视界科技有限公司 filed Critical 北京微播视界科技有限公司
Publication of WO2020107625A1 publication Critical patent/WO2020107625A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass

Definitions

  • the present disclosure relates to video processing technology.
  • the present disclosure relates to a video classification method, device, electronic device, and computer-readable storage medium.
  • the present disclosure provides a video classification method, the method including:
  • the probability that the video belongs to each type is determined, and the type with a probability greater than or equal to the first threshold is determined as the type of the video.
  • the picture classification model is a pre-trained machine learning model.
  • the probability that the video belongs to each type is less than the first threshold, it is determined that the video type is an unrecognized type.
  • the method further includes: before determining the probability that the video belongs to each type, if the determined type of each type is greater than or equal to the second threshold, then determine the type of the video as an unrecognized type .
  • the method further includes: after determining that the type of the video is an unrecognized type, acquiring a custom type input by the user for the unrecognized type of video, and determining the custom type as the type of the video.
  • the method further includes: after determining the type of the video, storing the type of the video.
  • the present disclosure provides a video classification device, which includes:
  • Extraction module used to extract a predetermined number of frame pictures from the video
  • Frame picture type determination module used to determine the type of each frame picture through the picture classification model
  • the video type determining module is used to determine the probability that the video belongs to each type according to the determined types, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
  • the picture classification model is a pre-trained machine learning model.
  • the video type determination module is further configured to: if the probability that the video belongs to each type is less than the first threshold, determine the video type as an unrecognized type.
  • the video type determining module is further configured to: if the determined type of each type is greater than or equal to the second threshold, determine the type of the video as an unrecognized type.
  • the video type determination module is further configured to: obtain a user-defined type for a video input of an unrecognized type, and determine the user-defined type as the type of the video.
  • the video type determination module is further configured to store the type of video.
  • the present disclosure provides an electronic device including:
  • a processor and a memory stores at least one instruction, at least one program, code set, or instruction set, the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement as disclosed in the present disclosure
  • the present disclosure provides a computer-readable storage medium for storing computer instructions, programs, code sets or instruction sets, when the computer instructions, programs, code sets or instruction sets are in a computer
  • the computer When running on the computer, the computer is caused to execute the method as shown in the first aspect or any optional implementation manner of the first aspect of the present disclosure.
  • the intelligent classification of each video can be realized, which facilitates the user to quickly search according to the classified video, improves the efficiency of the user in selecting the video, and improves the user experience.
  • FIG. 1 is a schematic flowchart of a video classification method according to an embodiment of the present disclosure
  • FIG 2 is an example diagram of video classification display provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of a video classification device according to an embodiment of the present disclosure.
  • FIG. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • An embodiment of the present disclosure provides a music selection method when shooting a video. As shown in FIG. 1, the method includes:
  • Step S101 extract a predetermined number of frame pictures from the video
  • Step S102 Determine the type of each frame picture through the picture classification model
  • Step S103 According to the determined types, determine the probability that the video belongs to each type respectively, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
  • the intelligent classification of each video can be realized, which facilitates the user to quickly find the target video according to the classified video and perform subsequent sharing operations, improve the efficiency of the user in selecting the video, and improve the user experience.
  • the video classification method provided by the embodiment of the present disclosure is executed, so that when the user opens the folder or album, as shown in FIG. 2 , You can display the classified videos.
  • the user can directly click on the folder or album to view the video. It may also be that the user in the video sharing software (or website, platform, etc., the embodiment of the present disclosure uses software as an example for introduction, and the same parts will not be described in detail below).
  • the folder is opened indirectly in the video sharing software or Album to select videos.
  • a predetermined number of frame pictures are extracted from the video.
  • the frame pictures of the first few frames of the video are extracted, or the first few frames plus the middle frame can also be extracted.
  • Another example is extracting a frame picture of a fixed frame, or extracting a frame picture at a specific position according to the duration of a video.
  • a person skilled in the art can select an appropriate extraction method according to the actual situation, and can also set a predetermined number of extracted frame pictures according to requirements, for example, 5 frames, 10 frames, 20 frames, or more than 20 frames, etc. This embodiment of the disclosure does not limited.
  • step S102 the type to which each frame picture belongs is determined by the picture classification model.
  • the picture classification model is a pre-trained machine learning model.
  • the picture classification model may be trained in advance. Specifically, determine the type of each sample picture in the sample set, and iteratively train the picture classification model through each sample picture and its corresponding type. Subsequently, each frame picture extracted in step S101 is input to the trained picture classification model, and the type to which each frame picture belongs is output.
  • the picture classification model may be trained by the server side, and when the video classification method provided by the embodiment of the present disclosure is executed, the trained picture classification model is obtained from the server side, and then, each frame picture extracted in step S101 is input to the training Of the picture classification model, and output the type of each frame picture.
  • the picture classification model is trained by the server, and when the video classification method provided by the embodiment of the present disclosure is executed, each frame picture extracted in step S101 is sent to the server, and the picture classification model of the server determines the frame to which each picture belongs Type, to receive the type of each frame picture returned by the server, so as to execute step S103.
  • the image classification model provided by the iOS system may also be directly used to determine the type to which each frame picture belongs.
  • step S103 according to the determined types, the probability that the video belongs to each type is determined, and the type with a probability greater than or equal to the first threshold is determined as the type of the video.
  • the method for determining the probability that the video belongs to each type includes: determining the ratio (eg, percentage) of the number of frame pictures corresponding to each type to the number of frame pictures extracted from the video, as the probability that the video belongs to each type.
  • the number of frame pictures extracted from a video is five frames, where the first frame to the fourth frame are determined as the travel type through the picture classification model, and the fifth frame is determined as the dance type through the picture classification model, then the video
  • the probability of being a tourist type is 80%
  • the probability of being a dancing type is 20%.
  • the type whose probability is greater than or equal to the first threshold is determined as the type of video (hereinafter, this case is referred to as a recognized type).
  • the higher the first threshold the higher the accuracy of video classification.
  • those skilled in the art may set the first threshold according to the actual situation, and the embodiments of the present disclosure are not limited herein.
  • the first threshold is set to 80%, since the probability that the video belongs to the travel type is 80%, which is equal to the first threshold, it can be determined that the video type is the travel type.
  • classification can be achieved through the above process.
  • the classified videos can be displayed directly under each classification label.
  • the displayed classification label can be determined according to the identified types of each video.
  • the probability that the video belongs to the travel type is 80%, which is less than the first threshold, and the probability that the video belongs to the dance type is 20%, which is also less than the first threshold.
  • the probability that the video belongs to each type is less than the first threshold, it is determined that the type of the video is an unrecognized type. That is, in the above example, when the first threshold is set to 90%, the video can be classified as unrecognized.
  • each frame picture identified by the picture classification model in step S102 belongs to more types, it is generally difficult to determine that the probability that the video belongs to each type belongs to the first threshold.
  • the number of frame pictures extracted from a video is five frames, where the first frame and the fourth frame are determined as the travel type by the picture classification model, and the second frame and the third frame are determined as the game type by the picture classification model
  • the fifth frame is determined to be the dance type through the picture classification model.
  • the probability that the video belongs to the travel type is 40%
  • the probability to belong to the game type is 40%
  • the probability to belong to the dance type is 20%. Since the probability that the video belongs to each type is small, it is difficult to determine which type the video belongs to.
  • step S102 in order to improve the efficiency of video classification and reduce the amount of calculation, before step S102, if the determined type of each type is greater than or equal to the second threshold, the type of video is determined to be an unrecognized type.
  • step S103 After determining that the type of the video is an unrecognized type according to the type of the video type, step S103 can no longer be performed to improve the efficiency of video classification and reduce the amount of calculation.
  • the second threshold is set in combination with the predetermined number of frame pictures extracted from the video and the above first threshold, which is not limited in the embodiments of the present disclosure .
  • the videos determined to be of unrecognized type may be directly displayed under the unrecognized type classification label, wherein, for the video under the unrecognized type classification label, the embodiment of the present disclosure may provide a type-defined Features.
  • the video classification method provided by the embodiment of the present disclosure further includes: obtaining a user-defined type input for the unrecognized type of video, and determining the user-defined type as the video type .
  • users can take a custom way to classify.
  • the user can input a custom type for a video of an unrecognized type (for convenience, the video is referred to as a target video hereinafter).
  • a target video for convenience, the video is referred to as a target video hereinafter.
  • the first video type is determined Is the type of target video.
  • the target video may be moved to a category label corresponding to the first video type for display.
  • the target video can be displayed under the classification tag corresponding to the second video type.
  • the category tags corresponding to the unrecognized types may be deleted.
  • the type of video may also be stored.
  • each video is mapped and stored with the corresponding identified type; for each video of the unrecognized type, if a user-defined type has been obtained, each video and the corresponding self-defined type Define the type for mapping storage. For each video of an unrecognized type that is not customized by the user, map and store it with the unrecognized type.
  • the type of stored video when the folder or album is opened next time, only need to classify the newly added video, and directly read the stored type of the video that has been classified.
  • a video to be classified needs to be determined. Specifically, it is determined whether the type of video is already stored, and if the type of video is not stored, it is determined to be the video to be classified.
  • the stored type is determined as the type of the video, and it can be directly read and displayed. There is no need to perform the subsequent steps S101 to S103, which effectively reduces the calculation amount of the classification algorithm and improves the video classification. effectiveness.
  • intelligent classification of each video can be realized, which facilitates users to quickly search according to the classified videos, improves the user's efficiency in selecting videos, and improves the user experience.
  • the video classification apparatus 30 may include: an extraction module 301, a frame picture type determination module 302, and a video type determination module 303, where:
  • the extraction module 301 is used to extract a predetermined number of frame pictures from the video
  • the frame picture type determination module 302 is used to determine the type of each frame picture through the picture classification model
  • the video type determination module 303 is used to determine the probability that the video belongs to each type according to the determined types, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
  • the picture classification model is a pre-trained machine learning model.
  • the video type determination module 303 is further configured to: if the probability that the video belongs to each type is less than the first threshold, determine the type of the video as an unrecognized type.
  • the video type determining module 303 is further configured to: if the determined type of each type is greater than or equal to the second threshold, determine the type of the video as an unrecognized type.
  • the video type determination module 303 is further configured to: obtain a user-defined type for a video input of an unrecognized type, and determine the user-defined type as the type of the video.
  • the video type determination module 303 is further configured to store the type of video.
  • the video classification apparatus provided by the embodiments of the present disclosure may be specific hardware on the device or software or firmware installed on the device.
  • the implementation principles and the technical effects produced are the same as those in the foregoing method embodiments.
  • the device is implemented
  • the parts that are not mentioned in the example section please refer to the corresponding contents in the foregoing method embodiments, which will not be repeated here.
  • an embodiment of the present disclosure also provides an electronic device, the electronic device includes a memory and a processor, the memory stores at least one instruction, at least one program, code set or Instruction set, the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the method shown in any one of the above embodiments of the present disclosure.
  • an embodiment of the present disclosure also provides a computer-readable storage medium for storing computer instructions, programs, code sets, or instruction sets, When the computer instruction, program, code set, or instruction set runs on the computer, the computer is caused to execute the method shown in any of the above embodiments of the present disclosure.
  • FIG. 4 shows a schematic structural diagram of an electronic device 40 suitable for implementing embodiments of the present disclosure.
  • the electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals ( Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 4 is only an example, and should not bring any limitation to the functions and use scope of the embodiments of the present disclosure.
  • the electronic device 40 may include a processing device (for example, a central processing unit, a graphics processor, etc.) 401, which may be loaded into a random storage according to a program stored in a read only memory (ROM) 402 or from the storage device 408
  • the program in the memory (RAM) 403 is fetched to perform various appropriate actions and processes.
  • various programs and data necessary for the operation of the electronic device 40 are also stored.
  • the processing device 401, ROM 402, and RAM 403 are connected to each other via a bus 404.
  • An input/output (I/O) interface 405 is also connected to the bus 404.
  • the following devices can be connected to the I/O interface 405: including input devices 406 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speaker, vibration
  • input devices 406 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.
  • An output device 407 such as a storage device; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409.
  • the communication device 409 may allow the electronic device 40 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 4 shows an electronic device 40 having various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or provided instead.
  • the process described above with reference to the flowchart may be implemented as a computer software program.
  • embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 409, or from the storage device 408, or from the ROM 402.
  • the processing device 401 When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiments of the present disclosure are executed.
  • the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • the computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal that is propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: electric wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the computer-readable medium carries one or more programs.
  • the electronic device When the one or more programs are executed by the electronic device, the electronic device is caused to: extract a predetermined number of frame pictures from the video; determine each frame picture through the picture classification model The type to which it belongs; according to the determined types, determine the probability that the video belongs to each type respectively, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
  • the computer program code for performing the operations of the present disclosure can be written in one or more programming languages or a combination thereof.
  • the above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, as well as conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code may be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, through an Internet service provider Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider Internet connection for example, AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains one or more logic functions Executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks represented in succession may actually be executed in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented with dedicated hardware-based systems that perform specified functions or operations Or, it can be realized by a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Library & Information Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

A video classification method and apparatus, an electronic device, and a computer readable storage medium. The method comprises: extracting a predetermined number of frame pictures from a video (S101); determining a type to which each frame picture belongs by means of a picture classification model (S102); and according to the determined types, determining the probability that the video belongs to each type, and determining the type with the probability greater than or equal to a first threshold value to be the type of the video (S103). By means of the method, the smart classification of the type may be realized, it is convenient for a user to perform fast lookup according to the classified video, the efficiency of selecting the video by the user is improved, and the user experience is enhanced.

Description

视频分类方法、装置、电子设备及计算机可读存储介质Video classification method, device, electronic equipment and computer readable storage medium
相关申请的交叉引用Cross-reference of related applications
本公开要求于2018年11月27日在中国国家知识产权局提交的申请号为201811427554.4的中国专利申请的权益，其全部内容通过引用整体并入本文。This disclosure requires the rights and interests of the Chinese patent application with the application number 201811427554.4 filed at the State Intellectual Property Office of China on November 27, 2018, the entire contents of which are incorporated herein by reference.
技术领域Technical field
本公开涉及视频处理技术，具体而言，本公开涉及一种视频分类方法、装置、电子设备及计算机可读存储介质。The present disclosure relates to video processing technology. In particular, the present disclosure relates to a video classification method, device, electronic device, and computer-readable storage medium.
背景技术Background technique
随着网络技术的发展和智能移动终端的普及，人人可以随手拍摄视频来记录身边的新鲜事，大家也都乐于通过移动终端将拍摄的视频分享给更多人，例如从相册中选择一个视频上传至在线视频网站、短视频类应用程序或社交平台等。With the development of network technology and the popularization of smart mobile terminals, everyone can shoot videos to record new things around them. Everyone is also happy to share the captured videos to more people through the mobile terminal, such as selecting a video from an album Upload to online video websites, short video applications or social platforms, etc.
若相册中的视频过多，用户查找目标视频会比较困难，尤其是当用户需要上传多个同一类型的视频时，视频的查找工作就会花费用户大量的时间，影响了用户分享视频的体验。If there are too many videos in the album, it will be more difficult for the user to find the target video, especially when the user needs to upload multiple videos of the same type, the video search will take a lot of time for the user, which affects the user's experience of sharing the video.
发明内容Summary of the invention
第一方面，本公开提供了一种视频分类方法，该方法包括：In a first aspect, the present disclosure provides a video classification method, the method including:
在视频中提取预定数量的帧图片；Extract a predetermined number of frame pictures from the video;
通过图片分类模型确定各个帧图片所属的类型；Determine the type of each frame picture through the picture classification model;
根据确定出的各个类型，确定视频分别属于各个类型的概率，将概率大于或等于第一阈值的类型确定为视频的类型。According to the determined types, the probability that the video belongs to each type is determined, and the type with a probability greater than or equal to the first threshold is determined as the type of the video.
在一种可选的实现方式中，图片分类模型为预训练的机器学习模型。In an optional implementation, the picture classification model is a pre-trained machine learning model.
在一种可选的实现方式中，若视频分别属于各个类型的概率均小于第一阈值，则确定视频的类型为未识别类型。In an optional implementation manner, if the probability that the video belongs to each type is less than the first threshold, it is determined that the video type is an unrecognized type.
在一种可选的实现方式中，该方法还包括：在确定视频分别属于各个类型的概率之前，若确定出的各个类型的种类大于或等于第二阈值，则确定视频的类型为未识别类型。In an optional implementation, the method further includes: before determining the probability that the video belongs to each type, if the determined type of each type is greater than or equal to the second threshold, then determine the type of the video as an unrecognized type .
在一种可选的实现方式中，该方法还包括：在确定视频的类型为未识别类型之后，获取用户针对未识别类型的视频输入的自定义类型，将自定义类型确定为视频的类型。In an optional implementation manner, the method further includes: after determining that the type of the video is an unrecognized type, acquiring a custom type input by the user for the unrecognized type of video, and determining the custom type as the type of the video.
在一种可选的实现方式中，该方法还包括：确定视频的类型之后，存储视频的类型。In an optional implementation manner, the method further includes: after determining the type of the video, storing the type of the video.
第二方面，本公开提供了一种视频分类装置，该装置包括：In a second aspect, the present disclosure provides a video classification device, which includes:
提取模块，用于在视频中提取预定数量的帧图片；Extraction module, used to extract a predetermined number of frame pictures from the video;
帧图片类型确定模块，用于通过图片分类模型确定各个帧图片所属的类型；Frame picture type determination module, used to determine the type of each frame picture through the picture classification model;
视频类型确定模块，用于根据确定出的各个类型，确定视频分别属于各个类型的概率，将概率大于或等于第一阈值的类型确定为视频的类型。The video type determining module is used to determine the probability that the video belongs to each type according to the determined types, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
在一种可选的实现方式中，图片分类模型为预训练的机器学习模型。In an optional implementation, the picture classification model is a pre-trained machine learning model.
在一种可选的实现方式中，视频类型确定模块还被配置成：若视频分别属于各个类型的概率均小于第一阈值，则确定视频的类型为未识别类型。In an optional implementation manner, the video type determination module is further configured to: if the probability that the video belongs to each type is less than the first threshold, determine the video type as an unrecognized type.
在一种可选的实现方式中，视频类型确定模块还被配置成：若确定出的各个类型的种类大于或等于第二阈值，则确定视频的类型为未识别类型。In an optional implementation manner, the video type determining module is further configured to: if the determined type of each type is greater than or equal to the second threshold, determine the type of the video as an unrecognized type.
在一种可选的实现方式中，视频类型确定模块还被配置成：获取用户针对未识别类型的视频输入的自定义类型，将自定义类型确定为视频的类型。In an optional implementation manner, the video type determination module is further configured to: obtain a user-defined type for a video input of an unrecognized type, and determine the user-defined type as the type of the video.
在一种可选的实现方式中，视频类型确定模块还被配置成：存储视频的类型。In an optional implementation manner, the video type determination module is further configured to store the type of video.
第三方面，本公开提供了一种电子设备，该电子设备包括：In a third aspect, the present disclosure provides an electronic device including:
处理器和存储器，该存储器存储有至少一条指令、至少一段程序、代码集或指令集，该至少一条指令、至少一段程序、代码集或指令集由该处理器加载并执行以实现如本公开的第一方面或第一方面的任一可选的实现方式中所示的方法。A processor and a memory, the memory stores at least one instruction, at least one program, code set, or instruction set, the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement as disclosed in the present disclosure The method shown in the first aspect or any optional implementation manner of the first aspect.
第四方面，本公开提供了一种计算机可读存储介质，该计算机可读存储介质用于存储计算机指令、程序、代码集或指令集，当该计算机指令、程序、代码集或指令集在计算机上运行时，使得该计算机执行如本公开的第一方面或第一方面的任一可选的实现方式中所示的方法。According to a fourth aspect, the present disclosure provides a computer-readable storage medium for storing computer instructions, programs, code sets or instruction sets, when the computer instructions, programs, code sets or instruction sets are in a computer When running on the computer, the computer is caused to execute the method as shown in the first aspect or any optional implementation manner of the first aspect of the present disclosure.
根据本公开提供的技术方案，可以实现对各个视频的智能分类，便于用户根据分类后的视频进行快速查找，提高用户选择视频的效率，提升用户体验。According to the technical solution provided by the present disclosure, the intelligent classification of each video can be realized, which facilitates the user to quickly search according to the classified video, improves the efficiency of the user in selecting the video, and improves the user experience.
附图说明BRIEF DESCRIPTION
为了更清楚地说明本公开实施例中的技术方案，下面将对本公开实施例描述中所需要使用的附图作简单地介绍。In order to more clearly explain the technical solutions in the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments of the present disclosure will be briefly introduced below.
图1为本公开实施例提供的一种视频分类方法的流程示意图；FIG. 1 is a schematic flowchart of a video classification method according to an embodiment of the present disclosure;
图2为本公开实施例提供的视频分类显示的示例图；2 is an example diagram of video classification display provided by an embodiment of the present disclosure;
图3为本公开实施例提供的一种视频分类装置的结构示意图；3 is a schematic structural diagram of a video classification device according to an embodiment of the present disclosure;
图4为本公开实施例提供的一种电子设备的结构示意图。4 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
具体实施方式detailed description
下面详细描述本公开的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本公开，而不能解释为对本公开的限制。The embodiments of the present disclosure are described in detail below, and examples of the embodiments are shown in the drawings, in which the same or similar reference numerals indicate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary, and are only used to explain the present disclosure, and cannot be construed as limiting the present disclosure.
本技术领域技术人员可以理解，除非特意声明，这里使用的单数形式“一”、“一个”、“所述”和“该”也可包括复数形式。应该进一步理解的是，本公开的说明书中使用的措辞“包括”是指存在所述特征、整数、步骤、操作、元件和/或组件，但是并不排除存在或添加一个或多个其他特征、整 数、步骤、操作、元件、组件和/或它们的组。应该理解，当我们称元件被“连接”或“耦接”到另一元件时，它可以直接连接或耦接到其他元件，或者也可以存在中间元件。此外，这里使用的“连接”或“耦接”可以包括无线连接或无线耦接。这里使用的措辞“和/或”包括一个或更多个相关联的列出项的全部或任一单元和全部组合。Those skilled in the art can understand that unless specifically stated, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the word "comprising" used in the specification of the present disclosure refers to the presence of the described features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and/or their groups. It should be understood that when an element is referred to as being “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or intervening elements may also be present. In addition, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The expression "and/or" as used herein includes all or any unit and all combinations of one or more associated listed items.
为使本公开的目的、技术方案和优点更加清楚，下面将结合附图对本公开实施方式作进一步地详细描述。下面这几个具体的实施例可以相互结合，对于相同或相似的概念或过程可能在某些实施例中不再赘述。To make the objectives, technical solutions, and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below in conjunction with the accompanying drawings. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.
本公开实施例提供了一种拍摄视频时的音乐选取方法，如图1所示，该方法包括：An embodiment of the present disclosure provides a music selection method when shooting a video. As shown in FIG. 1, the method includes:
步骤S101：在视频中提取预定数量的帧图片；Step S101: extract a predetermined number of frame pictures from the video;
步骤S102：通过图片分类模型确定各个帧图片所属的类型；Step S102: Determine the type of each frame picture through the picture classification model;
步骤S103：根据确定出的各个类型，确定视频分别属于各个类型的概率，将概率大于或等于第一阈值的类型确定为视频的类型。Step S103: According to the determined types, determine the probability that the video belongs to each type respectively, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
基于本公开实施例提供的视频分类方法，能够实现各个视频的智能分类，便于用户根据分类后的视频快速查找目标视频并执行后续分享操作，提高用户选择视频的效率，提升用户体验。Based on the video classification method provided by the embodiments of the present disclosure, the intelligent classification of each video can be realized, which facilitates the user to quickly find the target video according to the classified video and perform subsequent sharing operations, improve the efficiency of the user in selecting the video, and improve the user experience.
可以理解，本公开实施例中，对于存储视频的文件夹或者相册中的每一个视频，均执行本公开实施例提供的视频分类方法，以使得用户打开文件夹或相册时，如图2所示，可以显示分类后的视频。It can be understood that in the embodiment of the present disclosure, for each video in the folder or album where the video is stored, the video classification method provided by the embodiment of the present disclosure is executed, so that when the user opens the folder or album, as shown in FIG. 2 , You can display the classified videos.
其中，打开文件夹或相册，可以是用户直接点击文件夹或相册来阅览视频。也可以是用户在视频分享软件(或者网站、平台等，本公开实施例以软件为例进行介绍，下文中相同的地方不再赘述)上传视频时，间接地在视频分享软件中打开文件夹或相册来选择视频。Among them, to open a folder or album, the user can directly click on the folder or album to view the video. It may also be that the user in the video sharing software (or website, platform, etc., the embodiment of the present disclosure uses software as an example for introduction, and the same parts will not be described in detail below). When uploading a video, the folder is opened indirectly in the video sharing software or Album to select videos.
具体而言，针对待分类的每一个视频，首先在步骤S101中，在视频中提取预定数量的帧图片。例如是提取视频前几帧的帧图片，或者也可以提取前几帧加上中间的帧等。又例如是提取固定帧的帧图片，或者是按照视频的时长提取特定位置的帧图片等。本领域技术人员可以根据实际情况选择合适的提取方式，也可以根据需求对提取帧图片的预定数量进行设置，例如5 帧、10帧、20帧或者20帧以上等，本公开实施例对此不作限定。Specifically, for each video to be classified, first in step S101, a predetermined number of frame pictures are extracted from the video. For example, the frame pictures of the first few frames of the video are extracted, or the first few frames plus the middle frame can also be extracted. Another example is extracting a frame picture of a fixed frame, or extracting a frame picture at a specific position according to the duration of a video. A person skilled in the art can select an appropriate extraction method according to the actual situation, and can also set a predetermined number of extracted frame pictures according to requirements, for example, 5 frames, 10 frames, 20 frames, or more than 20 frames, etc. This embodiment of the disclosure does not limited.
随后，在步骤S102中，通过图片分类模型确定各个帧图片所属的类型。Subsequently, in step S102, the type to which each frame picture belongs is determined by the picture classification model.
其中，图片分类模型为预训练的机器学习模型。Among them, the picture classification model is a pre-trained machine learning model.
本公开实施例中，可以预先训练该图片分类模型。具体而言，确定样本集中的各个样本图片所属的类型，通过各个样本图片及其分别对应的类型来迭代训练图片分类模型。随后，将步骤S101中提取的各个帧图片输入训练后的图片分类模型，输出各个帧图片所属的类型。In the embodiment of the present disclosure, the picture classification model may be trained in advance. Specifically, determine the type of each sample picture in the sample set, and iteratively train the picture classification model through each sample picture and its corresponding type. Subsequently, each frame picture extracted in step S101 is input to the trained picture classification model, and the type to which each frame picture belongs is output.
或者，该图片分类模型可以由服务器端进行训练，执行本公开实施例提供的视频分类方法时，从服务器端获取训练后的图片分类模型，随后，将步骤S101中提取的各个帧图片输入训练后的图片分类模型，输出各个帧图片所属的类型。Alternatively, the picture classification model may be trained by the server side, and when the video classification method provided by the embodiment of the present disclosure is executed, the trained picture classification model is obtained from the server side, and then, each frame picture extracted in step S101 is input to the training Of the picture classification model, and output the type of each frame picture.
或者，该图片分类模型由服务器端进行训练，执行本公开实施例提供的视频分类方法时，将步骤S101中提取的各个帧图片发送给服务器端，通过服务器端的图片分类模型确定各个帧图片所属的类型，接收服务器端返回的各个帧图片所属的类型，以便执行步骤S103。Alternatively, the picture classification model is trained by the server, and when the video classification method provided by the embodiment of the present disclosure is executed, each frame picture extracted in step S101 is sent to the server, and the picture classification model of the server determines the frame to which each picture belongs Type, to receive the type of each frame picture returned by the server, so as to execute step S103.
一种可行的实现方式中，若将本公开实施例提供的视频分类方法应用于iOS***中的软件或平台，也可直接采用iOS***提供的图片分类模型来确定各个帧图片所属的类型。In a feasible implementation manner, if the video classification method provided by the embodiments of the present disclosure is applied to software or platforms in the iOS system, the image classification model provided by the iOS system may also be directly used to determine the type to which each frame picture belongs.
随后，在步骤S103中，根据确定出的各个类型，确定视频分别属于各个类型的概率，将概率大于或等于第一阈值的类型确定为视频的类型。Subsequently, in step S103, according to the determined types, the probability that the video belongs to each type is determined, and the type with a probability greater than or equal to the first threshold is determined as the type of the video.
具体而言，确定视频分别属于各个类型的概率的方式包括：确定各个类型对应的帧图片的数量占视频中提取的帧图片数量的比例(例如百分比)，分别作为视频属于各个类型的概率。Specifically, the method for determining the probability that the video belongs to each type includes: determining the ratio (eg, percentage) of the number of frame pictures corresponding to each type to the number of frame pictures extracted from the video, as the probability that the video belongs to each type.
作为示例的，某视频中提取的帧图片的数量为五帧，其中，第一帧到第四帧通过图片分类模型确定为旅游类型，第五帧通过图片分类模型确定为跳舞类型，则该视频属于旅游类型的概率为80％，属于跳舞类型的概率为20％。As an example, the number of frame pictures extracted from a video is five frames, where the first frame to the fourth frame are determined as the travel type through the picture classification model, and the fifth frame is determined as the dance type through the picture classification model, then the video The probability of being a tourist type is 80%, and the probability of being a dancing type is 20%.
本公开实施例中，将概率大于或等于第一阈值的类型确定为视频的类 型(下文中，将这种情况称为已识别类型)。实际应用中，第一阈值越高，视频分类的准确性越高。但考虑到噪声的存在，为实现合理的分类效果，本领域技术人员可以根据实际情况对第一阈值进行设置，本公开实施例在此不做限定。In the embodiment of the present disclosure, the type whose probability is greater than or equal to the first threshold is determined as the type of video (hereinafter, this case is referred to as a recognized type). In practical applications, the higher the first threshold, the higher the accuracy of video classification. However, considering the existence of noise, in order to achieve a reasonable classification effect, those skilled in the art may set the first threshold according to the actual situation, and the embodiments of the present disclosure are not limited herein.
接上例，若将第一阈值设置为80％，由于上述视频属于旅游类型的概率为80％，等于第一阈值，则可确定该视频的类型为旅游类型。Continuing with the above example, if the first threshold is set to 80%, since the probability that the video belongs to the travel type is 80%, which is equal to the first threshold, it can be determined that the video type is the travel type.
依此类推，对于待分类的每一个视频，均可通过上述过程实现分类。本公开实施例中，如图2所示，在用户打开文件夹或相册时，可以直接在各分类标签下，分别显示分类后的视频。其中，显示的分类标签可以根据识别出的各个视频的类型来确定。By analogy, for each video to be classified, classification can be achieved through the above process. In the embodiment of the present disclosure, as shown in FIG. 2, when a user opens a folder or an album, the classified videos can be displayed directly under each classification label. Among them, the displayed classification label can be determined according to the identified types of each video.
再接上例，若将第一阈值设置为90％，那么视频属于旅游类型的概率为80％，小于第一阈值，而属于跳舞类型的概率为20％，也小于第一阈值。本公开实施例中，若视频分别属于各个类型的概率均小于第一阈值，则确定视频的类型为未识别类型。即上例中，在第一阈值设置为90％的情况下，该视频可以归为未识别类型。Continuing with the above example, if the first threshold is set to 90%, then the probability that the video belongs to the travel type is 80%, which is less than the first threshold, and the probability that the video belongs to the dance type is 20%, which is also less than the first threshold. In the embodiment of the present disclosure, if the probability that the video belongs to each type is less than the first threshold, it is determined that the type of the video is an unrecognized type. That is, in the above example, when the first threshold is set to 90%, the video can be classified as unrecognized.
实际应用中，若步骤S102中通过图片分类模型识别出的各个帧图片所属的类型较多，通常确定出的视频分别属于各个类型的概率很难超过第一阈值。作为示例地，某视频中提取的帧图片的数量为五帧，其中，第一帧和第四帧通过图片分类模型确定为旅游类型，第二帧和第三帧通过图片分类模型确定为游戏类型，第五帧通过图片分类模型确定为跳舞类型，那么，可以确定出该视频属于旅游类型的概率为40％，属于游戏类型的概率为40％，属于跳舞类型的概率为20％。由于视频属于各个类型的概率相差较小，难以确定视频属于哪种类型。In practical applications, if each frame picture identified by the picture classification model in step S102 belongs to more types, it is generally difficult to determine that the probability that the video belongs to each type belongs to the first threshold. As an example, the number of frame pictures extracted from a video is five frames, where the first frame and the fourth frame are determined as the travel type by the picture classification model, and the second frame and the third frame are determined as the game type by the picture classification model The fifth frame is determined to be the dance type through the picture classification model. Then, it can be determined that the probability that the video belongs to the travel type is 40%, the probability to belong to the game type is 40%, and the probability to belong to the dance type is 20%. Since the probability that the video belongs to each type is small, it is difficult to determine which type the video belongs to.
基于此，本公开实施例为提升视频分类效率，减少计算量，可以在步骤S102之前，若确定出的各个类型的种类大于或等于第二阈值，则确定视频的类型为未识别类型。Based on this, in the embodiment of the present disclosure, in order to improve the efficiency of video classification and reduce the amount of calculation, before step S102, if the determined type of each type is greater than or equal to the second threshold, the type of video is determined to be an unrecognized type.
通过视频类型的种类确定出视频的类型为未识别类型后，便可不再执行步骤S103，以提升视频分类效率，减少计算量。After determining that the type of the video is an unrecognized type according to the type of the video type, step S103 can no longer be performed to improve the efficiency of video classification and reduce the amount of calculation.
实际应用中，本领域技术人员可以根据实际情况对第二阈值进行设 置，例如结合视频中提取帧图片的预定数量和上述第一阈值对第二阈值进行设置，本公开实施例在此不做限定。In practical applications, a person skilled in the art can set the second threshold according to the actual situation, for example, the second threshold is set in combination with the predetermined number of frame pictures extracted from the video and the above first threshold, which is not limited in the embodiments of the present disclosure .
本公开实施例中，对于确定为未识别类型的视频，可以直接显示在未识别类型的分类标签下，其中，对于未识别类型的分类标签下的视频，本公开实施例可以提供类型自定义的功能。In the embodiment of the present disclosure, the videos determined to be of unrecognized type may be directly displayed under the unrecognized type classification label, wherein, for the video under the unrecognized type classification label, the embodiment of the present disclosure may provide a type-defined Features.
具体而言，在确定视频的类型为未识别类型之后，本公开实施例提供的视频分类方法还包括：获取用户针对未识别类型的视频输入的自定义类型，将自定义类型确定为视频的类型。Specifically, after determining that the type of the video is an unrecognized type, the video classification method provided by the embodiment of the present disclosure further includes: obtaining a user-defined type input for the unrecognized type of video, and determining the user-defined type as the video type .
也就是说，用户可以采取自定义的方式进行分类。具体而言，用户可以针对未识别类型的视频(为方便描述，下文将该视频称为目标视频)输入自定义类型。其中，若用户的自定义类型与上述已识别的任一视频类型(例如旅游类型等，为方便描述，下文将该任一视频类型称为第一视频类型)相同，则将第一视频类型确定为目标视频的类型。可以将该目标视频移动至第一视频类型对应的分类标签下进行显示。或者，若用户的自定义类型与已识别的视频类型均不相同，则新增一个视频类型(为方便描述，下文将该新增的自定义类型称为第二视频类型)及其对应的分类标签，便可在第二视频类型对应的分类标签下，显示目标视频。可选地，当未识别类型的视频均被用户自定义后，可以删除未识别类型对应的分类标签。In other words, users can take a custom way to classify. Specifically, the user can input a custom type for a video of an unrecognized type (for convenience, the video is referred to as a target video hereinafter). Wherein, if the user's user-defined type is the same as any of the above-identified video types (such as travel type, etc., for convenience of description, this video type will be referred to as the first video type below), the first video type is determined Is the type of target video. The target video may be moved to a category label corresponding to the first video type for display. Or, if the user’s custom type is different from the recognized video type, a new video type (for convenience of description, the new custom type will be referred to as the second video type below) and its corresponding classification are added Tag, the target video can be displayed under the classification tag corresponding to the second video type. Optionally, when the videos of unrecognized types are all customized by the user, the category tags corresponding to the unrecognized types may be deleted.
本公开实施例中，还可以在确定视频的类型之后，存储视频的类型。In the embodiment of the present disclosure, after determining the type of video, the type of video may also be stored.
具体而言，对于已识别类型的各个视频，将各个视频与对应的识别出的类型进行映射存储；对于未识别类型的各个视频，若已获取用户的自定义类型，将各个视频与对应的自定义类型进行映射存储。对于用户未自定义类型的未识别类型的各个视频，将其与未识别类型进行映射存储。Specifically, for each video of the identified type, each video is mapped and stored with the corresponding identified type; for each video of the unrecognized type, if a user-defined type has been obtained, each video and the corresponding self-defined type Define the type for mapping storage. For each video of an unrecognized type that is not customized by the user, map and store it with the unrecognized type.
对于本公开实施例，存储视频的类型，在下次打开文件夹或相册时，只需对新加入的视频进行分类，对已经分过类的视频直接读取存储的类型即可。For the embodiment of the present disclosure, the type of stored video, when the folder or album is opened next time, only need to classify the newly added video, and directly read the stored type of the video that has been classified.
那么，一种可行的实现方式中，在步骤S101之前，需要确定待分类的视频。具体而言，确定视频的类型是否已经存储，若视频的类型未存储，则确定是待分类的视频。Then, in a feasible implementation manner, before step S101, a video to be classified needs to be determined. Specifically, it is determined whether the type of video is already stored, and if the type of video is not stored, it is determined to be the video to be classified.
反之，若视频的类型已存储，则将存储的类型确定为视频的类型，直接读取并进行显示即可，不必再执行后续步骤S101～步骤S103，有效减少分类算法运算量，提升视频分类的效率。On the contrary, if the type of the video is already stored, the stored type is determined as the type of the video, and it can be directly read and displayed. There is no need to perform the subsequent steps S101 to S103, which effectively reduces the calculation amount of the classification algorithm and improves the video classification. effectiveness.
根据本公开实施例提供的视频分类方法，可以实现对各个视频的智能分类，便于用户根据分类后的视频进行快速查找，提高用户选择视频的效率，提升用户体验。According to the video classification method provided by the embodiment of the present disclosure, intelligent classification of each video can be realized, which facilitates users to quickly search according to the classified videos, improves the user's efficiency in selecting videos, and improves the user experience.
本公开实施例还提供了一种视频分类装置，如图3所示，该视频分类装置30可以包括：提取模块301、帧图片类型确定模块302以及视频类型确定模块303，其中：An embodiment of the present disclosure also provides a video classification apparatus. As shown in FIG. 3, the video classification apparatus 30 may include: an extraction module 301, a frame picture type determination module 302, and a video type determination module 303, where:
提取模块301用于在视频中提取预定数量的帧图片；The extraction module 301 is used to extract a predetermined number of frame pictures from the video;
帧图片类型确定模块302用于通过图片分类模型确定各个帧图片所属的类型；The frame picture type determination module 302 is used to determine the type of each frame picture through the picture classification model;
视频类型确定模块303用于根据确定出的各个类型，确定视频分别属于各个类型的概率，将概率大于或等于第一阈值的类型确定为视频的类型。The video type determination module 303 is used to determine the probability that the video belongs to each type according to the determined types, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
在一种可选的实现方式中，图片分类模型为预训练的机器学习模型。In an optional implementation, the picture classification model is a pre-trained machine learning model.
在一种可选的实现方式中，视频类型确定模块303还被配置成：若视频分别属于各个类型的概率均小于第一阈值，则确定视频的类型为未识别类型。In an optional implementation manner, the video type determination module 303 is further configured to: if the probability that the video belongs to each type is less than the first threshold, determine the type of the video as an unrecognized type.
在一种可选的实现方式中，视频类型确定模块303还被配置成：若确定出的各个类型的种类大于或等于第二阈值，则确定视频的类型为未识别类型。In an optional implementation manner, the video type determining module 303 is further configured to: if the determined type of each type is greater than or equal to the second threshold, determine the type of the video as an unrecognized type.
在一种可选的实现方式中，视频类型确定模块303还被配置成：获取用户针对未识别类型的视频输入的自定义类型，将自定义类型确定为视频的类型。In an optional implementation manner, the video type determination module 303 is further configured to: obtain a user-defined type for a video input of an unrecognized type, and determine the user-defined type as the type of the video.
在一种可选的实现方式中，视频类型确定模块303还被配置成：存储视频的类型。In an optional implementation manner, the video type determination module 303 is further configured to store the type of video.
本公开实施例所提供的视频分类装置，可以为设备上的特定硬件或者安装于设备上的软件或固件等，其实现原理及产生的技术效果和前述方法 实施例相同，为简要描述，设备实施例部分未提及之处，可参考前述方法实施例中相应内容，在此不再赘述。The video classification apparatus provided by the embodiments of the present disclosure may be specific hardware on the device or software or firmware installed on the device. The implementation principles and the technical effects produced are the same as those in the foregoing method embodiments. For brief description, the device is implemented For the parts that are not mentioned in the example section, please refer to the corresponding contents in the foregoing method embodiments, which will not be repeated here.
基于与本公开实施例中视频分类方法相同的原理，本公开实施例还提供了一种电子设备，该电子设备包括存储器和处理器，该存储器存储有至少一条指令、至少一段程序、代码集或指令集，该至少一条指令、至少一段程序、代码集或指令集由该处理器加载并执行以实现本公开上述任一实施例所示的方法。Based on the same principle as the video classification method in the embodiment of the present disclosure, an embodiment of the present disclosure also provides an electronic device, the electronic device includes a memory and a processor, the memory stores at least one instruction, at least one program, code set or Instruction set, the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the method shown in any one of the above embodiments of the present disclosure.
基于与本公开实施例中视频分类方法相同的原理，本公开实施例中还提供了一种计算机可读存储介质，该计算机可读存储介质用于存储计算机指令、程序、代码集或指令集，当该计算机指令、程序、代码集或指令集在计算机上运行时，使得该计算机执行本公开上述任一实施例所示的方法。Based on the same principle as the video classification method in the embodiment of the present disclosure, an embodiment of the present disclosure also provides a computer-readable storage medium for storing computer instructions, programs, code sets, or instruction sets, When the computer instruction, program, code set, or instruction set runs on the computer, the computer is caused to execute the method shown in any of the above embodiments of the present disclosure.
下面参考图4，其示出了适于用来实现本公开实施例的电子设备40的结构示意图。本公开实施例中的电子设备可以包括但不限于诸如移动电话机、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图4示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。The following refers to FIG. 4, which shows a schematic structural diagram of an electronic device 40 suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals ( Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG. 4 is only an example, and should not bring any limitation to the functions and use scope of the embodiments of the present disclosure.
如图4所示，电子设备40可以包括处理装置(例如中央处理器、图形处理器等)401，其可以根据存储在只读存储器(ROM)402中的程序或者从存储装置408加载到随机存取存储器(RAM)403中的程序而执行各种适当的动作和处理。在RAM 403中，还存储有电子设备40操作所需的各种程序和数据。处理装置401、ROM402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。As shown in FIG. 4, the electronic device 40 may include a processing device (for example, a central processing unit, a graphics processor, etc.) 401, which may be loaded into a random storage according to a program stored in a read only memory (ROM) 402 or from the storage device 408 The program in the memory (RAM) 403 is fetched to perform various appropriate actions and processes. In the RAM 403, various programs and data necessary for the operation of the electronic device 40 are also stored. The processing device 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to the bus 404.
通常，以下装置可以连接至I/O接口405：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置406；包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置407；包括例如磁带、硬盘等的存储装置408；以及通信装置409。通信装置409可以 允许电子设备40与其他设备进行无线或有线通信以交换数据。虽然图4示出了具有各种装置的电子设备40，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。Generally, the following devices can be connected to the I/O interface 405: including input devices 406 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speaker, vibration An output device 407 such as a storage device; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 40 to perform wireless or wired communication with other devices to exchange data. Although FIG. 4 shows an electronic device 40 having various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or provided instead.
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置409从网络上被下载和安装，或者从存储装置408被安装，或者从ROM 402被安装。在该计算机程序被处理装置401执行时，执行本公开实施例的方法中限定的上述功能。In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 409, or from the storage device 408, or from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiments of the present disclosure are executed.
需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。It should be noted that, the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In this disclosure, the computer-readable signal medium may include a data signal that is propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device . The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: electric wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独 存在，而未装配入该电子设备中。The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：在视频中提取预定数量的帧图片；通过图片分类模型确定各个帧图片所属的类型；根据确定出的各个类型，确定视频分别属于各个类型的概率，将概率大于或等于第一阈值的类型确定为视频的类型。The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device is caused to: extract a predetermined number of frame pictures from the video; determine each frame picture through the picture classification model The type to which it belongs; according to the determined types, determine the probability that the video belongs to each type respectively, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。The computer program code for performing the operations of the present disclosure can be written in one or more programming languages or a combination thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C++, as well as conventional Procedural programming language-such as "C" language or similar programming language. The program code may be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In situations involving remote computers, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, through an Internet service provider Internet connection).
附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。The flowcharts and block diagrams in the drawings illustrate the possible implementation architecture, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains one or more logic functions Executable instructions. It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks represented in succession may actually be executed in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts, can be implemented with dedicated hardware-based systems that perform specified functions or operations Or, it can be realized by a combination of dedicated hardware and computer instructions.
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的 情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。The above description is only the preferred embodiment of the present disclosure and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure in this disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover the above technical features or without departing from the above disclosed concepts. Other technical solutions formed by arbitrary combinations of equivalent features. For example, the above features and the technical features disclosed in this disclosure (but not limited to) having similar functions are replaced with each other to form a technical solution.
应该理解的是，虽然附图的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，其可以以其他的顺序执行。而且，附图的流程图中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，其执行顺序也不必然是依次进行，而是可以与其他步骤或者其他步骤的子步骤或者阶段的至少一部分轮流或者交替地执行。It should be understood that although the steps in the flowchart of the drawings are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a part of the steps in the flow chart of the drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the order of execution It is not necessarily performed sequentially, but may be executed in turn or alternately with at least a part of other steps or sub-steps or stages of other steps.
以上所述仅是本公开的部分实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本公开原理的前提下，还可以做出若干修改和润饰，这些修改和润饰也应视为在本公开的范围内。The above is only a part of the embodiments of the present disclosure. It should be pointed out that for those of ordinary skill in the art, without departing from the principles of the present disclosure, a number of modifications and retouches can also be made. These modifications and retouches also It should be considered within the scope of this disclosure.

Claims (10)

  1. 一种视频分类方法，包括：A video classification method, including:
    在视频中提取预定数量的帧图片；Extract a predetermined number of frame pictures from the video;
    通过图片分类模型确定各个帧图片所属的类型；Determine the type of each frame picture through the picture classification model;
    根据确定出的各个类型，确定所述视频分别属于所述各个类型的概率，将概率大于或等于第一阈值的类型确定为所述视频的类型。According to the determined types, determine the probabilities that the video belongs to the types respectively, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
  2. 根据权利要求1所述的视频分类方法，其中，所述图片分类模型为预训练的机器学习模型。The video classification method according to claim 1, wherein the picture classification model is a pre-trained machine learning model.
  3. 根据权利要求1所述的视频分类方法，其中，若所述视频分别属于所述各个类型的概率均小于第一阈值，则确定所述视频的类型为未识别类型。The video classification method according to claim 1, wherein if the probabilities that the videos belong to the respective types are less than a first threshold, the type of the video is determined to be an unrecognized type.
  4. 根据权利要求1所述的视频分类方法，还包括：在确定所述视频分别属于所述各个类型的概率之前，若确定出的各个类型的种类大于或等于第二阈值，则确定所述视频的类型为未识别类型。The video classification method according to claim 1, further comprising: before determining the probability that the video belongs to the respective types, if the determined type of each type is greater than or equal to the second threshold, determining the video's The type is unrecognized.
  5. 根据权利要求3或4所述的视频分类方法，还包括：在确定所述视频的类型为未识别类型之后，获取用户针对所述未识别类型的视频输入的自定义类型，将所述自定义类型确定为所述视频的类型。The video classification method according to claim 3 or 4, further comprising: after determining that the type of the video is an unrecognized type, acquiring a custom type input by the user for the video of the unrecognized type, and converting the custom The type is determined as the type of the video.
  6. 根据权利要求5所述的视频分类方法，还包括：在确定所述视频的类型之后，存储所述视频的类型。The video classification method according to claim 5, further comprising: after determining the type of the video, storing the type of the video.
  7. 一种视频分类装置，包括：A video classification device, including:
    提取模块，用于在视频中提取预定数量的帧图片；Extraction module, used to extract a predetermined number of frame pictures from the video;
    帧图片类型确定模块，用于通过图片分类模型确定各个帧图片所属的类型；Frame picture type determination module, used to determine the type of each frame picture through the picture classification model;
    视频类型确定模块，用于根据确定出的各个类型，确定所述视频分别属于所述各个类型的概率，将概率大于或等于第一阈值的类型确定为所述视频的类型。The video type determining module is configured to determine the probability that the video belongs to the respective types according to the determined types, and determine the type whose probability is greater than or equal to the first threshold as the type of the video.
  8. 根据权利要求7所述的视频分类装置，其中，所述视频类型确定模块还被配置成：若所述视频分别属于所述各个类型的概率均小于第一阈 值，则确定所述视频的类型为未识别类型。The video classification device according to claim 7, wherein the video type determination module is further configured to: if the probabilities that the videos belong to the respective types are less than a first threshold, determine the type of the video as Unrecognized type.
  9. 一种电子设备，包括：An electronic device, including:
    处理器和存储器，所述存储器存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现权利要求1-6中任一项所述的方法。A processor and a memory, the memory stores at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set is loaded by the processor and Performed to implement the method of any of claims 1-6.
  10. 一种计算机可读存储介质，用于存储计算机指令、程序、代码集或指令集，当所述计算机指令、程序、代码集或指令集在计算机上运行时，使得所述计算机执行权利要求1-6中任一项所述的方法。A computer-readable storage medium for storing computer instructions, programs, code sets or instruction sets, when the computer instructions, programs, code sets or instruction sets run on a computer, causing the computer to execute claims 1- The method according to any one of 6.
PCT/CN2018/125409 2018-11-27 2018-12-29 Video classification method and apparatus, electronic device, and computer readable storage medium WO2020107625A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811427554.4 2018-11-27
CN201811427554.4A CN109376268A (en) 2018-11-27 2018-11-27 Video classification methods, device, electronic equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
WO2020107625A1 true WO2020107625A1 (en) 2020-06-04

Family

ID=65383417

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/125409 WO2020107625A1 (en) 2018-11-27 2018-12-29 Video classification method and apparatus, electronic device, and computer readable storage medium

Country Status (2)

Country Link
CN (1) CN109376268A (en)
WO (1) WO2020107625A1 (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110046278B (en) * 2019-03-11 2021-10-15 北京奇艺世纪科技有限公司 Video classification method and device, terminal equipment and storage medium
CN109960745B (en) * 2019-03-20 2021-03-23 网易（杭州）网络有限公司 Video classification processing method and device, storage medium and electronic equipment
CN110298934A (en) * 2019-06-18 2019-10-01 重庆长安汽车股份有限公司 Driving video capture and sharing method
CN110377787B (en) * 2019-06-21 2022-03-25 北京奇艺世纪科技有限公司 Video classification method and device and computer readable storage medium
CN112084370A (en) * 2020-09-10 2020-12-15 维沃移动通信有限公司 Video processing method and device and electronic equipment
CN112668533A (en) * 2021-01-05 2021-04-16 株洲中车时代电气股份有限公司 Video visual angle classification method, device, equipment and storage medium
CN113033681A (en) * 2021-03-31 2021-06-25 北京有竹居网络技术有限公司 Video classification method and device, readable medium and electronic equipment
CN113836350B (en) * 2021-09-23 2024-02-27 深圳绿米联创科技有限公司 Video retrieval method, system, device, storage medium and electronic equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160342842A1 (en) * 2008-02-15 2016-11-24 Tivo Inc. Systems and methods for semantically classifying and normalizing shots in video
CN107180074A (en) * 2017-03-31 2017-09-19 北京奇艺世纪科技有限公司 A kind of video classification methods and device
CN107194419A (en) * 2017-05-10 2017-09-22 百度在线网络技术（北京）有限公司 Video classification methods and device, computer equipment and computer-readable recording medium
CN108334861A (en) * 2018-03-02 2018-07-27 北京未来媒体科技股份有限公司 A kind of video content recognition method and device based on machine learning
CN108615043A (en) * 2016-12-12 2018-10-02 中移（杭州）信息技术有限公司 A kind of video classification methods and system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7558809B2 (en) * 2006-01-06 2009-07-07 Mitsubishi Electric Research Laboratories, Inc. Task specific audio classification for identifying video highlights
CN102207966B (en) * 2011-06-01 2013-07-10 华南理工大学 Video content quick retrieving method based on object tag
CN105893930A (en) * 2015-12-29 2016-08-24 乐视云计算有限公司 Video feature identification method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160342842A1 (en) * 2008-02-15 2016-11-24 Tivo Inc. Systems and methods for semantically classifying and normalizing shots in video
CN108615043A (en) * 2016-12-12 2018-10-02 中移（杭州）信息技术有限公司 A kind of video classification methods and system
CN107180074A (en) * 2017-03-31 2017-09-19 北京奇艺世纪科技有限公司 A kind of video classification methods and device
CN107194419A (en) * 2017-05-10 2017-09-22 百度在线网络技术（北京）有限公司 Video classification methods and device, computer equipment and computer-readable recording medium
CN108334861A (en) * 2018-03-02 2018-07-27 北京未来媒体科技股份有限公司 A kind of video content recognition method and device based on machine learning

Also Published As

Publication number Publication date
CN109376268A (en) 2019-02-22

Similar Documents

Publication Publication Date Title
WO2020107625A1 (en) Video classification method and apparatus, electronic device, and computer readable storage medium
WO2022142014A1 (en) Multi-modal information fusion-based text classification method, and related device thereof
US10970334B2 (en) Navigating video scenes using cognitive insights
US20180054564A1 (en) Apparatus and method for providing user's emotional information in electronic device
WO2021008223A1 (en) Information determination method and apparatus, and electronic device
WO2020238320A1 (en) Method and device for generating emoticon
US20160306505A1 (en) Computer-implemented methods and systems for automatically creating and displaying instant presentations from selected visual content items
JP7394809B2 (en) Methods, devices, electronic devices, media and computer programs for processing video
WO2020107624A1 (en) Information pushing method and apparatus, electronic device and computer-readable storage medium
US10110933B2 (en) Video file processing
WO2023040697A1 (en) Information processing method and apparatus, device, readable storage medium and product
WO2023151589A1 (en) Video display method and apparatus, electronic device and storage medium
WO2024012251A1 (en) Semantic segmentation model training method and apparatus, and electronic device and storage medium
WO2023016349A1 (en) Text input method and apparatus, and electronic device and storage medium
CN110633423A (en) Target account identification method, device, equipment and storage medium
CN113919320A (en) Method, system and equipment for detecting early rumors of heteromorphic neural network
WO2020233144A1 (en) Method and device for providing comment input mode
WO2022156468A1 (en) Method and apparatus for processing model data, electronic device, and computer-readable medium
CN112182255A (en) Method and apparatus for storing media files and for retrieving media files
WO2021227953A1 (en) Image special effect configuration method, image recognition method, apparatuses, and electronic device
WO2022017299A1 (en) Text inspection method and apparatus, electronic device, and storage medium
CN111652675A (en) Display method and device and electronic equipment
CN113191257B (en) Order of strokes detection method and device and electronic equipment
CN113033682B (en) Video classification method, device, readable medium and electronic equipment
CN112843681B (en) Virtual scene control method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18941580

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 27/09/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18941580

Country of ref document: EP

Kind code of ref document: A1