WO2021197023A1 - Procédé et appareil de filtrage de ressources multimédia, dispositif électronique et support de stockage informatique - Google Patents

Procédé et appareil de filtrage de ressources multimédia, dispositif électronique et support de stockage informatique Download PDF

Info

Publication number
WO2021197023A1
WO2021197023A1 PCT/CN2021/080321 CN2021080321W WO2021197023A1 WO 2021197023 A1 WO2021197023 A1 WO 2021197023A1 CN 2021080321 W CN2021080321 W CN 2021080321W WO 2021197023 A1 WO2021197023 A1 WO 2021197023A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature
screening
screened
multimedia
video
Prior art date
Application number
PCT/CN2021/080321
Other languages
English (en)
Chinese (zh)
Inventor
党方园
张明亮
蔡斯杰
张瑞晶
李谊羽
张琪
王逊志
Original Assignee
北京字节跳动网络技术有限公司
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 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Publication of WO2021197023A1 publication Critical patent/WO2021197023A1/fr

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
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/483—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Definitions

  • the present disclosure relates to the technical field of multimedia resource processing. Specifically, the present disclosure relates to a multimedia resource screening method, device, electronic equipment, and computer storage medium.
  • video can quickly spread information on the network.
  • As an information carrier video has a strong information carrying capacity. Whether the information carried by the video meets the basic requirements of network transmission needs to be reviewed.
  • a method for screening multimedia resources includes:
  • the multimedia resources to be screened are screened according to preset screening rules to obtain screening results.
  • a multimedia resource screening device which includes:
  • the multimedia resource acquisition module is used to acquire multimedia resources to be screened
  • the characteristic content determining module is used to determine the characteristic content of the multimedia resource to be screened
  • the characteristic label determining module is configured to match the corresponding characteristic label according to the characteristic content
  • the screening module is used to screen the multimedia resources to be screened based on the feature tags and according to preset screening rules to obtain screening results.
  • an electronic device in a third aspect, includes:
  • One or more processors are One or more processors;
  • One or more application programs wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute according to The above-mentioned multimedia resource screening method
  • a computer storage medium stores at least one instruction, at least one program, a code set, or an instruction set, the at least one instruction, the at least one program, the code set, or the The instruction set is loaded and executed by the processor to implement the multimedia resource screening method as described above.
  • the present disclosure can at least achieve the following technical effects: by determining the feature tag of the video to be reviewed, and according to the feature tag, the multimedia resources to be screened are screened according to preset rules, and the screening result is obtained without manual confirmation of the screening result, and no manual labor Fatigue, high screening efficiency, and the screening of multimedia resources will not be mixed with human factors, and the screening results of multimedia resources are accurate.
  • FIG. 1 is a schematic flowchart of a method for screening multimedia resources according to an embodiment of the present disclosure
  • FIG. 2 is a schematic flowchart of a method for determining a feature label according to an embodiment of the present disclosure
  • FIG. 3 is a schematic flowchart of a method for determining a feature label of an image according to an embodiment of the present disclosure
  • FIG. 4 is a schematic flowchart of a method for determining feature labels with text according to an embodiment of the present disclosure
  • FIG. 5 is a schematic flowchart of a method for obtaining screening according to an embodiment of the disclosure.
  • FIG. 6 is a schematic flowchart of a method for determining the level of a screening result provided by an embodiment of the present disclosure
  • FIG. 7 is a schematic structural diagram of a multimedia resource screening device provided by an embodiment of the present disclosure.
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the disclosure.
  • An embodiment of the present disclosure provides a method for screening multimedia resources. As shown in FIG. 1, the method includes:
  • step S101 a multimedia resource to be screened is obtained.
  • the videos to be audited refer to videos that need to be audited.
  • the method of obtaining can be to receive videos uploaded by users or It is to read locally stored videos or receive videos transmitted by other computers.
  • the specific acquisition method is not limited in the present disclosure.
  • the type of video may be various common video formats such as MP4, AVI, MOV, and ASF, and the specific video format is not limited in the present disclosure.
  • step S102 the characteristic content of the multimedia resource to be screened is determined.
  • the feature content can be only the content of the multimedia resource feature.
  • video review is taken as an example for illustration, such as some video clips, some subtitles, or titles of the video to be reviewed .
  • step S103 the corresponding feature tag is matched according to the feature content.
  • the feature tag can be manually determined or automatically determined based on the video feature of the video to be reviewed, such as the title or subtitle in the video feature frequency.
  • the keywords in the, or the video content the feature tag represents the feature corresponding to the video.
  • the feature tag of the video to be reviewed needs to be determined.
  • the determination of the feature tag can be manually determined. For example, after manually watching the video, associate the video to be reviewed. Enter a feature tag for the video.
  • the determination of the feature tag may also be determined by the feature of the video, such as the keyword in the video title or subtitle, the content of the video, and so on.
  • determining the feature tags according to the title of the video to be reviewed includes: obtaining the title of the video to be reviewed, identifying the text in the title, and identifying keywords in the title through keyword recognition technology, such as children smoking, fighting, etc., you can add " Keywords such as “child smoking” and “fighting” are used as the feature tags of the video to be reviewed; determining the feature tags of the video to be reviewed through the video content includes identifying the content of the video to be reviewed through video recognition technology, and determining the content of the video to be reviewed. Feature tag. If the video content of the video to be reviewed is car racing, the feature tag of the video to be reviewed is determined to be "racing racing".
  • step S104 based on the feature tag, the multimedia resources to be screened are screened according to preset screening rules to obtain screening results.
  • the preset rules refer to pre-set rules for reviewing videos to be reviewed, and the review rules refer to dividing different videos into different Rules for video categories.
  • video review is taken as an example.
  • the video to be reviewed is reviewed according to the preset review rules based on the feature tag, and the review result is obtained.
  • the determined feature label is "child smoking”
  • the preset review rule is that a child smoking video is a violation video
  • the video to be reviewed is determined to be a violation video
  • the review result of the video to be reviewed is Violating video.
  • the determined feature tag is "singer singing”
  • the preset rule is that a singer singing video belongs to a qualified video
  • the review result of the video to be reviewed is a qualified video.
  • the embodiment of the present disclosure determines the feature tag of the video to be reviewed, and screens the multimedia resources to be screened according to preset rules according to the feature tag, and obtains the screening result. There is no need to manually confirm the screening result, and there is no artificial fatigue, and the screening efficiency is high. And the selection of multimedia resources will not be mixed with human factors, and the results of the selection of multimedia resources are accurate.
  • the matching of the corresponding feature tag according to the feature content includes:
  • step S201 at least one key frame image in the multimedia resource to be filtered is extracted, and image feature information in the at least one key frame image is determined through image recognition processing.
  • a key frame image refers to a certain frame or a few frames of images that can display key information in the video.
  • the method of extracting the key frame image may be The video image is recognized frame by frame through image recognition technology. When the key information is identified, one or more frames of the image containing the key information are used as the key frame image.
  • video review is taken as an example.
  • image recognition technology When extracting key frame images through image recognition technology, at least one key frame image, or more than one, is extracted, and the key frame image is identified Image feature information in.
  • a video has 3000 frames of images, and image recognition technology is used to identify the 3000 frames of images.
  • the key information is recognized, the key frame images are determined.
  • the frame image is used as a key frame image, and the image feature information in the key frame image is identified as a child smoking.
  • multiple image feature information can be identified.
  • step S202 a feature tag corresponding to the image feature information is matched according to a preset matching rule, and the feature tag is determined as the feature tag of the multimedia resource to be screened.
  • the feature tag is a preset tag used to indicate the feature of the video to be reviewed, and it can be a wide range of tags, such as illegal video, normal Videos, etc., can also be labels with a small range that are used to indicate specific content, such as children smoking, singers singing, etc.
  • video review is taken as an example.
  • the image feature information of the key frame image in the video to be reviewed is determined, the image feature information corresponding to the image feature information is matched through a preset matching rule.
  • Feature label Specifically, when the image feature information is identified as "child smoking”, the matching corresponding feature tag can be "child smoking”, the feature tag can also be "violating video", and the scope of the specific feature tag is not limited in the present disclosure.
  • the embodiments of the present disclosure extract key frame images in the video to be reviewed, identify image feature information in the key frame images, and match corresponding feature tags to ensure the accuracy of identification of the feature tags of the video to be reviewed.
  • the embodiment of the present disclosure provides a possible implementation manner.
  • the matching of corresponding feature tags according to the feature content includes:
  • the video review is taken as an example. After the video to be reviewed is obtained, the content of the video to be reviewed is displayed, the feature tag input by the user according to the content is received, and the feature The tag serves as the feature tag of the video to be reviewed.
  • the matching of corresponding feature tags according to the feature content includes:
  • step S301 at least one key frame image in the multimedia resource to be filtered is extracted, and the at least one key frame image is displayed.
  • video review is taken as an example.
  • at least one key frame image in the video to be reviewed at least one key frame image is displayed for review by reviewers.
  • at least one of the key frame images is selected for display for review by the reviewer. Specifically, if the video to be reviewed contains the information of a child smoking, when determining the key frame image, the image containing the child smoking is listed as the key frame image.
  • the key frame can be randomly selected from the above key frame image. Choose at least one of the images, or use the same image recognition technology, choose the clearest one or more images as the key frame image displayed for review by the reviewer.
  • step S302 a feature tag input by the user according to the at least one key frame image is received, and the feature tag is determined as the feature tag of the multimedia resource to be screened.
  • the video review is taken as an example.
  • the feature tag input by the user according to the key frame image displayed in the previous step is received, and the feature tag is used as the feature tag of the video to be reviewed.
  • the displayed key frame image contains information about the child smoking
  • the user can input the feature tag of "child smoking” or directly input the feature tag of "illegal video” according to the feature information, and
  • the feature tag is directly used as the feature tag of the video to be reviewed.
  • the embodiment of the present disclosure selects a key frame image for display, and receives a feature tag input by the reviewer according to the key frame, and uses the feature tag as the feature tag of the video to be reviewed, so that the review of the video is quick and accurate.
  • the matching of corresponding feature tags according to the feature content includes:
  • step 401 keywords corresponding to the multimedia resources to be filtered are obtained.
  • the video review is taken as an example.
  • the keywords are words that can only be the characteristics of the video to be reviewed, such as sensitive words required by various video platforms and laws, and general words that can express the content of the video. Wait.
  • the video review is taken as an example.
  • the keywords of the video to be reviewed are first obtained.
  • the title of the video to be reviewed can be obtained Keywords in the subtitles of the video with review, or keywords in the voice of the video to be reviewed, further, the title in the video to be reviewed and the keywords in the subtitles can be recognized through text recognition.
  • the recognition technology recognizes keywords in the voice in the video to be reviewed, and text recognition and voice recognition can be reasonably applied by those skilled in the art, so this disclosure will not elaborate.
  • step S402 feature tags are matched according to the keywords, and the feature tags are determined as the feature tags of the multimedia resources to be screened.
  • the video review is taken as an example.
  • the keywords of the video to be reviewed are obtained according to the previous step, the feature tags of the video to be reviewed are matched according to the keywords. Specifically, if the keyword of the obtained video with review is "child smoking", then according to the key, according to the preset rules, the corresponding feature tag is matched with "child smoking” or "illegal video".
  • the preset rules It may be a feature tag library preset by the component, and matching is performed in the feature tag library according to keywords, wherein the correspondence between keywords and feature tags is also preset.
  • the multimedia resource screening realizes automatic review, the multimedia resource screening efficiency is fast, and the review result is accurate.
  • obtaining keywords corresponding to the multimedia resource to be screened includes: obtaining keywords in the title of the video resource; And/or obtain the keywords of the subtitles in the video resource; and/or obtain the keywords of the voice in the video resource.
  • the video review is taken as an example.
  • There are many methods for obtaining the keywords of the video to be reviewed including obtaining the keywords in the title of the video to be reviewed, such as the title of the video to be reviewed.
  • the keywords that can be obtained can include XX, singing, and song.
  • the keywords in the subtitles of the video to be reviewed if there is the following line of subtitles in the video to be reviewed, "This young lady dances so well", then keywords such as young lady, dance, etc. can be obtained in the subtitles.
  • the keywords in the voice in the video to be reviewed are obtained. If the following voice "Oh, why is this kid still smoking" exists in the video to be reviewed, the keywords child, smoking, etc. can be identified through voice recognition.
  • the above three identification methods can also be combined to perform identification together.
  • keywords are recognized by recognizing characters in titles, subtitles, or voices, and keywords can be recognized by combining three methods, and the recognition results are more accurate.
  • the multimedia resources to be screened are screened according to preset screening rules based on the feature tags to obtain screening results, including:
  • the screening result corresponding to the characteristic tag is determined based on the screening rule of the audit queue.
  • video review is taken as an example for description.
  • the screening queue is review-to-customer, and the review queue refers to the queue of videos that need to be reviewed. Videos in the same review queue belong to the same type of video.
  • the review queue is preset and can be divided according to the video type, content, duration, etc. The specific division form is not limited in this disclosure.
  • the video review is taken as an example.
  • the video to be reviewed is added to the review queue corresponding to the feature tag. Specifically, when it is determined that the feature tag of the video to be reviewed is "child smoking", the video to be reviewed is included in the violating video queue.
  • video review is still taken as an example for description.
  • the review is conducted according to the review rules of the review queue, and the review result is obtained. Specifically, if a video to be reviewed is included in the violating video queue, according to the review rules of the queue, the review result of the video to be reviewed is a violating video, illegal, and prohibited from playing.
  • the videos to be reviewed with the same or similar feature tags are listed in the same review queue, and the review videos are reviewed according to the review rules of the review queue, and the review results are obtained.
  • the review speed is fast and the results are accurate.
  • the multimedia resources to be screened are screened according to preset screening rules to obtain screening results, including:
  • step S601 the feature content corresponding to the feature tag in the multimedia to be screened is determined according to the feature tag
  • video review is taken as an example for description.
  • the feature tag of the video to be reviewed is determined, the feature content corresponding to the feature tag is extracted. Specifically, when it is determined that the feature tag of the video to be reviewed is "illegal video”, the illegal content in the video is extracted, such as "child smoking", and the content of the child's smoking is taken as the feature content.
  • step S602 according to the feature label and the feature content, the corresponding screening result and the level of the screening result are determined according to a preset screening rule.
  • the video review is taken as an example.
  • the review results of the videos to be reviewed can be divided into multiple levels.
  • the feature is that the review results of the illegal videos can be based on the review results.
  • the review result of the video to be reviewed is an illegal video
  • the degree of violation can be judged according to preset rules.
  • Obtain the level of illegality Specifically, it can be determined that the degree of illegality of the audited video is relatively serious, and the account of the video publisher is suspended for one week.
  • the grade determination and punishment measures in the specific embodiments can be set by those skilled in the art, and the present disclosure does not limit it.
  • the embodiments of the present disclosure perform level judgment on the review result of the video to be reviewed, and can give different review results to the video publisher according to the review result level, and has a wide range of applications.
  • the embodiment of the present disclosure determines the feature tag of the video to be reviewed, and screens the multimedia resources to be screened according to preset rules according to the feature tag, and obtains the screening result. There is no need to manually confirm the screening result, and there is no artificial fatigue, and the screening efficiency is high. And the selection of multimedia resources will not be mixed with human factors, and the results of the selection of multimedia resources are accurate.
  • the multimedia resource screening device 70 may include:
  • the multimedia resource acquisition module 710 is used to acquire multimedia resources to be screened
  • the characteristic content determining module 720 is configured to determine the characteristic content of the multimedia resource to be screened
  • the characteristic label determining module 730 is configured to match the corresponding characteristic label according to the characteristic content
  • the screening module 740 is configured to screen the multimedia resources to be screened based on the feature tags and according to preset screening rules to obtain screening results.
  • the multimedia resource screening device of this embodiment can execute the multimedia resource screening method shown in the above-mentioned embodiments of the present disclosure, and its implementation principles are similar, and will not be repeated here.
  • the embodiment of the present disclosure determines the feature tag of the video to be reviewed, and screens the multimedia resources to be screened according to preset rules according to the feature tag, and obtains the screening result. There is no need to manually confirm the screening result, and there is no artificial fatigue, and the screening efficiency is high. And the selection of multimedia resources will not be mixed with human factors, and the results of the selection of multimedia resources are accurate.
  • Terminal 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 (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device includes a memory and a processor.
  • the processor here may be referred to as the processing device 801 below, and the memory may include a read-only memory (ROM) 802, a random access memory (RAM) 803, and a storage device 808 below.
  • ROM read-only memory
  • RAM random access memory
  • storage device 808 At least one item of, as follows:
  • the electronic device 800 may include a processing device (such as a central processing unit, a graphics processor, etc.) 801, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 802 or from a storage device 808
  • the program in the memory (RAM) 803 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 800 are also stored.
  • the processing device 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804.
  • An input/output (I/O) interface 805 is also connected to the bus 804.
  • the following devices can be connected to the I/O interface 805: including input devices 806 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 807 such as a device; a storage device 808 such as a magnetic tape, a hard disk, etc.; and a communication device 809.
  • the communication device 809 may allow the electronic device 800 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 6 shows an electronic device 800 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may be implemented alternatively or provided with more or fewer devices.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 809, or installed from the storage device 808, or installed from the ROM 802.
  • the processing device 801 the above-mentioned functions defined in the method of the embodiment 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 a combination of any of the above.
  • 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 removable 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 above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein.
  • 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 the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the client and server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communication e.g., communication network
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.
  • 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 aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device: obtains the multimedia resource to be screened; determines the characteristic content of the multimedia resource to be screened; The characteristic content matches the corresponding characteristic label; based on the characteristic label, the multimedia resources to be screened are screened according to a preset screening rule to obtain a screening result.
  • the computer readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device: obtains the video to be reviewed; determines the feature tag of the video to be reviewed; based on the feature tag , According to the preset review rules, the videos to be reviewed are reviewed, and the review results are obtained.
  • the computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include but are not limited to object-oriented programming languages such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can 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 it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions can also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the modules or units involved in the embodiments described in the present disclosure can be implemented in software or hardware. Wherein, the name of the module or unit does not constitute a limitation on the unit itself under certain circumstances.
  • the first obtaining unit can also be described as "a unit for obtaining at least two Internet Protocol addresses.”
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on Chip
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing.
  • machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read only memory
  • magnetic storage device or any suitable combination of the foregoing.
  • a method for screening multimedia resources includes:
  • the multimedia resources to be screened are screened according to preset screening rules to obtain screening results.
  • the matching corresponding feature tags according to the feature content includes:
  • the feature tag corresponding to the image feature information is matched according to a preset matching rule, and the feature tag is determined as the feature tag of the multimedia resource to be screened.
  • the matching corresponding feature tags according to the feature content includes:
  • the matching corresponding feature tags according to the feature content includes:
  • the matching corresponding feature tags according to the feature content includes:
  • the feature tag is matched according to the keyword, and the feature tag is determined as the feature tag of the multimedia resource to be screened.
  • acquiring keywords corresponding to the multimedia resource to be screened includes:
  • the screening of the multimedia resources to be screened based on the feature tags according to preset screening rules to obtain screening results includes:
  • the screening result corresponding to the characteristic tag is determined based on the screening rule of the audit queue.
  • filtering the multimedia resources to be screened based on the feature tags according to preset screening rules to obtain screening results includes:
  • the corresponding review result and the level of the review result are determined according to preset screening rules.
  • a multimedia resource screening device which includes:
  • the multimedia resource acquisition module is used to acquire multimedia resources to be screened
  • the characteristic content determining module is used to determine the characteristic content of the multimedia resource to be screened
  • the characteristic label determining module is configured to match the corresponding characteristic label according to the characteristic content
  • the screening module is used to screen the multimedia resources to be screened based on the feature tags and according to preset screening rules to obtain screening results.
  • the matching corresponding feature tags according to the feature content includes:
  • the feature tag corresponding to the image feature information is matched according to a preset matching rule, and the feature tag is determined as the feature tag of the multimedia resource to be screened.
  • the matching corresponding feature tags according to the feature content includes:
  • the matching corresponding feature tags according to the feature content includes:
  • the matching corresponding feature tags according to the feature content includes:
  • the feature tag is matched according to the keyword, and the feature tag is determined as the feature tag of the multimedia resource to be screened.
  • acquiring keywords corresponding to the multimedia resources to be screened includes:
  • the screening of the multimedia resources to be screened according to the preset screening rules based on the feature tags to obtain screening results includes:
  • the screening result corresponding to the characteristic tag is determined based on the screening rule of the audit queue.
  • screening the multimedia resources to be screened according to preset screening rules to obtain screening results includes:
  • the corresponding screening result and the level of the screening result are determined according to a preset screening rule.
  • an electronic device including:
  • One or more processors are One or more processors;
  • One or more application programs where one or more application programs are stored in a memory and configured to be executed by one or more processors, and one or more programs are configured to execute the foregoing multimedia resource screening method.
  • a computer storage medium stores at least one instruction, at least one program, code set or instruction set, at least one instruction, at least one program, code set Or the instruction set is loaded and executed by the processor to realize the above multimedia resource screening method.

Landscapes

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

Abstract

L'invention concerne un procédé et un appareil de filtrage de ressources multimédia, un dispositif électronique et un support de stockage informatique. Ledit procédé consiste : à acquérir des ressources multimédia à filtrer (S101) ; à déterminer un contenu de caractéristique desdites ressources multimédia (S102) ; à trouver une étiquette de caractéristique correspondante appariée, en fonction du contenu de caractéristique (S103) ; et sur la base de l'étiquette de caractéristique, à filtrer lesdites ressources multimédia selon une règle de filtrage prédéfinie, de façon à obtenir un résultat de filtrage (S104). Le procédé détermine une étiquette de caractéristique de ressources multimédia à filtrer, et selon l'étiquette de caractéristique, filtre lesdites ressources multimédia selon une règle prédéfinie pour obtenir un résultat de filtrage. Le filtrage non manuel ne provoque pas de fatigue manuelle, l'efficacité de filtrage est élevée, et le filtrage de vidéos n'est pas affecté par des facteurs artificiels, de sorte que le résultat de filtrage de ressources multimédia est précis.
PCT/CN2021/080321 2020-04-02 2021-03-11 Procédé et appareil de filtrage de ressources multimédia, dispositif électronique et support de stockage informatique WO2021197023A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010256830 2020-04-02
CN202010256830.6 2020-04-02

Publications (1)

Publication Number Publication Date
WO2021197023A1 true WO2021197023A1 (fr) 2021-10-07

Family

ID=77927800

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/080321 WO2021197023A1 (fr) 2020-04-02 2021-03-11 Procédé et appareil de filtrage de ressources multimédia, dispositif électronique et support de stockage informatique

Country Status (1)

Country Link
WO (1) WO2021197023A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113992939A (zh) * 2021-10-28 2022-01-28 上海游效信息科技有限公司 一种基于视频传播链的监测方法及系统
CN114637896A (zh) * 2022-05-23 2022-06-17 杭州闪马智擎科技有限公司 数据的审核方法和装置、存储介质及电子装置
CN114827732A (zh) * 2022-04-25 2022-07-29 康键信息技术（深圳）有限公司 一种多通道内容审核方法、平台及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070214112A1 (en) * 2006-03-13 2007-09-13 Adobe Systems Incorporated Augmenting the contents of an electronic document with data retrieved from a search
CN103914559A (zh) * 2014-04-14 2014-07-09 小米科技有限责任公司 筛选网络用户的方法及装置
CN108512886A (zh) * 2017-10-26 2018-09-07 平安科技（深圳）有限公司 客户迁徙方法、系统、计算机设备及存储介质
CN109543714A (zh) * 2018-10-16 2019-03-29 北京达佳互联信息技术有限公司 数据特征的获取方法、装置、电子设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070214112A1 (en) * 2006-03-13 2007-09-13 Adobe Systems Incorporated Augmenting the contents of an electronic document with data retrieved from a search
CN103914559A (zh) * 2014-04-14 2014-07-09 小米科技有限责任公司 筛选网络用户的方法及装置
CN108512886A (zh) * 2017-10-26 2018-09-07 平安科技（深圳）有限公司 客户迁徙方法、系统、计算机设备及存储介质
CN109543714A (zh) * 2018-10-16 2019-03-29 北京达佳互联信息技术有限公司 数据特征的获取方法、装置、电子设备及存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113992939A (zh) * 2021-10-28 2022-01-28 上海游效信息科技有限公司 一种基于视频传播链的监测方法及系统
CN114827732A (zh) * 2022-04-25 2022-07-29 康键信息技术（深圳）有限公司 一种多通道内容审核方法、平台及存储介质
CN114637896A (zh) * 2022-05-23 2022-06-17 杭州闪马智擎科技有限公司 数据的审核方法和装置、存储介质及电子装置
CN114637896B (zh) * 2022-05-23 2022-09-09 杭州闪马智擎科技有限公司 数据的审核方法和装置、存储介质及电子装置

Similar Documents

Publication Publication Date Title
WO2021197023A1 (fr) Procédé et appareil de filtrage de ressources multimédia, dispositif électronique et support de stockage informatique
WO2021004221A1 (fr) Procédé et appareil de traitement d'affichage pour effets spéciaux, et dispositif électronique
WO2021196903A1 (fr) Procédé et dispositif de traitement vidéo, support lisible et dispositif électronique
WO2021008223A1 (fr) Procédé et appareil de détermination d'informations, et dispositif électronique associé
WO2021093737A1 (fr) Procédé et appareil de génération de vidéo, dispositif électronique, et support lisible par ordinateur
WO2020233166A1 (fr) Procédé de fourniture et d'affichage de données de commentaire, appareil, dispositif électronique et support d'informations
WO2021135626A1 (fr) Procédé et appareil de sélection d'éléments de menu, support lisible et dispositif électronique
JP6971292B2 (ja) 段落と映像を整列させるための方法、装置、サーバー、コンピュータ可読記憶媒体およびコンピュータプログラム
WO2021068634A1 (fr) Procédé et appareil de saut vers une page, dispositif électronique et support d'informations lisible par ordinateur
WO2022042389A1 (fr) Procédé et appareil d'affichage de résultat de recherche, support lisible et dispositif électronique
WO2022053004A1 (fr) Procédé et appareil de traitement de courrier, et dispositif électronique, et support lisible par ordinateur
WO2021082649A1 (fr) Procédé et appareil de mise à jour de liste, support lisible et dispositif électronique
WO2022037419A1 (fr) Procédé et appareil de reconnaissance de contenu audio, ainsi que dispositif et support lisible par ordinateur
WO2023051294A1 (fr) Procédé et appareil de traitement de support, dispositif et support
WO2020042376A1 (fr) Procédé et appareil permettant d'émettre des informations
US20220394333A1 (en) Video processing method and apparatus, storage medium, and electronic device
WO2022095942A1 (fr) Procédé et appareil d'affichage d'informations, dispositif électronique et support d'enregistrement lisible par ordinateur
WO2023016349A1 (fr) Procédé et appareil de saisie de texte, dispositif électronique et support de stockage
WO2024008184A1 (fr) Procédé et appareil d'affichage d'informations, dispositif électronique et support lisible par ordinateur
US11818491B2 (en) Image special effect configuration method, image recognition method, apparatus and electronic device
WO2023088006A1 (fr) Procédé et appareil d'interaction de jeu en nuage, support lisible et dispositif électronique
WO2020224294A1 (fr) Procédé, système et appareil de traitement d'informations
WO2021218680A1 (fr) Procédé et appareil de traitement d'informations d'interaction, dispositif électronique et support de stockage
WO2023124944A1 (fr) Procédé et appareil d'appel vidéo, dispositif électronique et support de stockage
WO2023000782A1 (fr) Procédé et appareil d'acquisition d'un point d'accès sans fil vidéo, support lisible, et dispositif électronique

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: 21778937

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21778937

Country of ref document: EP

Kind code of ref document: A1

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 030723)

122 Ep: pct application non-entry in european phase

Ref document number: 21778937

Country of ref document: EP

Kind code of ref document: A1