WO2022022075A1 - 视频及直播处理方法、直播系统、电子设备、终端、介质 - Google Patents

视频及直播处理方法、直播系统、电子设备、终端、介质 Download PDF

Info

Publication number
WO2022022075A1
WO2022022075A1 PCT/CN2021/098901 CN2021098901W WO2022022075A1 WO 2022022075 A1 WO2022022075 A1 WO 2022022075A1 CN 2021098901 W CN2021098901 W CN 2021098901W WO 2022022075 A1 WO2022022075 A1 WO 2022022075A1
Authority
WO
WIPO (PCT)
Prior art keywords
video
information
processing method
live broadcast
consultation information
Prior art date
Application number
PCT/CN2021/098901
Other languages
English (en)
French (fr)
Inventor
周丽佳
王志东
孙秀茹
郭萌
唐浩
Original Assignee
京东方科技集团股份有限公司
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 京东方科技集团股份有限公司 filed Critical 京东方科技集团股份有限公司
Priority to US17/765,041 priority Critical patent/US11956510B2/en
Publication of WO2022022075A1 publication Critical patent/WO2022022075A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/233—Processing of audio elementary streams
    • 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
    • G06F16/71—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/57—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for processing of video signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/47815—Electronic shopping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L2015/088—Word spotting

Definitions

  • the present disclosure relates to the field of video processing, and in particular, to a video processing method, a live broadcast processing method, an electronic device, a live broadcast system, a terminal, and a computer-readable storage medium.
  • the anchor In the process of live broadcast, in addition to displaying products in a personal way, the anchor also needs to maintain close interaction with consumers, so as to increase consumers' desire to buy. When there are too many people online in the live broadcast room, it is difficult for the anchor to answer every consumer's question, which may lead to consumers who have not been resolved to withdraw from the live broadcast room.
  • the purpose of the present disclosure is to provide a video processing method, a live broadcast processing method, an electronic device, a terminal, and a computer-readable storage medium.
  • a video processing method comprising:
  • determining the target short video corresponding to the consultation information according to the consultation information includes:
  • a short video whose feature information matches the keyword is used as the target short video.
  • the step of extracting the keywords of the consultation information includes:
  • the target video sent to the terminal sending the consultation information of the same category is the same.
  • the video processing method before the step of determining a target short video corresponding to the consultation information according to the consultation information, the video processing method further includes:
  • a short video is extracted from the already broadcasted video stream and the short video is stored.
  • extracting a short video from an already broadcasted video stream and storing the short video according to the preset feature information includes:
  • the time period corresponding to each feature in the video stream is stored as a corresponding short video.
  • the video processing method further includes:
  • the time period corresponding to the word in the video stream is used as the target short video.
  • the video processing method further includes:
  • the step of generating prompt information includes:
  • the consultation information is displayed on the screen of the device performing the live broadcast.
  • a live broadcast processing method comprising:
  • the live broadcast program is returned.
  • the live broadcast processing method further includes:
  • the live broadcast program In response to the short video playback information, the live broadcast program is controlled to enter a background running state.
  • an electronic device comprising:
  • a first storage module on which a first executable program is stored
  • one or more first processors capable of invoking the first executable program to cause the one or more first processors to implement the method described in accordance with the first aspect of the present disclosure Provided video processing methods.
  • a live broadcast system includes:
  • an image capture device the image capture device is used to capture video information
  • the electronic device provided by the third aspect of the present disclosure.
  • a terminal comprising:
  • a second storage module on which a second executable program is stored
  • one or more second processors capable of invoking the second executable program to cause the one or more second processors to implement what is described in accordance with the second aspect of the present disclosure Provided live processing methods.
  • a computer-readable storage medium is provided on which an executable program is stored, and when the executable program is invoked, the video processing provided according to the first aspect of the present disclosure can be implemented The method or the live broadcast processing method provided according to the second aspect of the present disclosure.
  • FIG. 1 is a schematic flowchart of an embodiment of a video processing method provided by the present disclosure
  • FIG. 2 is a schematic flowchart of a second embodiment of the video processing method provided by the present disclosure
  • FIG. 3 is a flowchart of an embodiment of step S111
  • step S105 is a flowchart of an embodiment of step S105
  • FIG. 5 is a flowchart of an embodiment of the live broadcast processing method provided by the present disclosure.
  • FIG. 6 is a flowchart of another embodiment of the live broadcast processing method provided by the present disclosure.
  • FIG. 7 is a work flow diagram of the live broadcast system provided by the present disclosure.
  • the video processing method includes:
  • step S110 a target short video corresponding to the consultation information is determined according to the consultation information
  • step S120 the target short video is pushed to the terminal sending the consultation information.
  • the video processing method provided by the present disclosure is executed by the electronic device on the host side. It should be noted that the consultation information is input by the consumer through his own terminal and transmitted to the electronic device on the host side through the communication network.
  • the target short video corresponds to the consultation information may mean that the content in the short video can answer the questions involved in the consultation information.
  • the consultation information may be information about consultation discounts
  • the target short video may be a short video introducing commodity discounts.
  • the target short video corresponding to the consultation information is pushed to the terminal to respond to the consumer's consultation, so as to avoid the problem that the anchor cannot answer all the consultation information one by one due to too much consultation information.
  • the interactivity during live broadcast improves the live broadcast experience of consumers.
  • the short video there is no special limitation on how to obtain the short video.
  • the video stream generated by the live broadcast can be stored, and a plurality of short videos can be intercepted from the stored video stream.
  • the host will repeatedly introduce product information and discount information during the live broadcast. Intercepting short videos from the video stream generated by the live broadcast can reduce the workload of the host and staff, and reduce labor costs.
  • the video processing method may further include:
  • step S100 the video stream generated during the live broadcast is stored.
  • the target short video is intercepted from the video stream.
  • step S110 may include:
  • step S111 the keywords of the consultation information are extracted
  • step S112 the extracted keywords are matched with the stored feature information of multiple short videos
  • step S113 the short video whose feature information matches the keyword is used as the target short video.
  • the consultation information input by the consumer contains many useless modal particles, and the "keywords" involved in step S111 are useful information in the consultation information.
  • a plurality of the short videos are "stored", which means that before extracting the keywords of the consultation information, a plurality of short videos have been stored in the electronic device on the host side.
  • the feature information can be used to mark the short videos.
  • the feature information of a short video involving product discounts is "discount”, therefore, the video can be marked with "discount”.
  • the feature information related to the product parameters is the feature parameters of the product.
  • the corresponding characteristic parameter is "color number”
  • the product can be marked with a specific color number.
  • the same short video may correspond to multiple different feature information.
  • the same short video includes discount information of a lipstick of a certain color number, and the same short video can be marked by using the lipstick number and the discount information as feature information.
  • the consultation information input by the consumer may be, "How much is the discount?"
  • the key word is "discount”, and the rest are modal particles.
  • step S112 the extracted "discount” can be matched with the feature information of multiple short videos, and in step S113, the short video whose feature information includes “discount” is used as the target short video and pushed to consumers user's terminal.
  • the consultation information input by the consumer may be, "How much is the discount of 105?", where the keyword is "105+ discount", and the rest are modal particles.
  • the extracted "105” and “discount” can be matched with multiple short video features, and in step S113, the short video whose feature information includes both "105" and “discount” can be used as the target Short videos, pushed to consumers' terminals.
  • each model of product has corresponding discount information
  • the discount information of different models of products may also be different.
  • a model 105 item has a different discount than a model 106 discount.
  • the consultation information sent by consumers usually includes both the model and the discount.
  • the product model and the question should also be included.
  • step S111 may include:
  • step S111a classify all the received consultation information
  • step S111b keywords of various types of consultation information are extracted.
  • step S120 the target videos sent to the terminals sending consultation information of the same category are the same.
  • the consultation information sent by consumers is mostly text. After receiving the consultation information of each consumer, the information whose text content overlaps 80% is classified into the same category.
  • the present disclosure does not specifically limit the threshold of the coincidence degree, and the threshold may be 80% or 90%, as long as it is taken from 70% to 99%. The higher the threshold is, the more refined the classification is, and the more targeted the questions raised by consumers can be answered.
  • the classification of the consultation information may include inquiring about discounts, making a reward, inquiring about commodity information, and the like.
  • the target short video is intercepted from a video stream generated during live broadcast.
  • the video processing method further includes:
  • step S105 a short video is extracted from the already broadcasted video stream according to the preset feature information.
  • a script can be provided to the anchor before the live broadcast, and the anchor is required to say the required information at a certain time period.
  • the product features and discount information are introduced every 20 minutes, and after the video stream generated by the live broadcast is stored, a short video is intercepted at a predetermined time, and the short video is marked with the feature information.
  • problems with high consultation frequency for example, the frequency can be set to 10 times per minute
  • problems with high consultation frequency can be determined according to big data and previous live broadcast records, and set according to the problems with high consultation frequency the "feature information".
  • the short video can be intercepted and stored.
  • consumers send out consultation information they can directly use the keywords in the consultation information to match.
  • step S105 may include:
  • step S105a voice recognition is performed on the video stream
  • step S105b according to the speech recognition result and the preset feature information are compared, and the corresponding part of each feature information in the video stream will be determined;
  • step S105c the part corresponding to each feature in the video stream is stored as a corresponding short video.
  • step S105b may be specifically executed as "determine the start time and end time of the corresponding part of each feature information in the video stream". The part between the start time and the end time is intercepted in the video stream, and then the part corresponding to each feature in the video stream can be obtained.
  • the video processing method may further include:
  • step S130 voice recognition is performed on the broadcasted video stream
  • step S140 compare with the extracted keyword according to the speech recognition result
  • step S150 when there is a word matching the keyword in the speech recognition result, the part corresponding to the word in the video stream is used as the target short video;
  • step S160 the part corresponding to the word in the video stream is marked with the word as feature information, and the marked short video is stored.
  • step S150 may be specifically executed as "determine the corresponding start time and end time of the word in the video stream, and use the part between the start time and the end time as the target short video”.
  • step S160 may be specifically executed as "marking the short video corresponding to the word between the corresponding start time and end time in the video stream by using the word as feature information, and storing the marked short video”.
  • step S160 is equivalent to supplementing the material library.
  • the processing method may further include:
  • step S170 when there is no word matching the keyword in the speech recognition result, prompt information is generated.
  • step S110 to S160 the probability of performing step S170 can be reduced, and the workload of the host can be reduced, so that the host can better introduce products.
  • the function of the prompt information is to remind the host or other staff to answer the consultation information.
  • the specific form of the prompt information is not particularly limited.
  • the steps of generating prompt information may include:
  • the consultation information is displayed on the screen of the device performing the live broadcast.
  • consultation information that cannot be automatically matched to the target video is displayed on the screen of the device performing the live broadcast.
  • all consultation information is displayed on the screen of the device performing the live broadcast.
  • the consultation information that cannot be automatically matched to the target video is different in color or font from the consultation information that can be automatically matched to the target video. Identify the corresponding consultation information in a timely manner.
  • other identification information can also be added to the consultation information that cannot be automatically matched to the target video, so that the host can identify and answer in time.
  • the video processing method provided by the present disclosure may also include:
  • the initial video collected by the image collection device is processed to obtain a live video stream.
  • the processing performed on the initial video may include at least one of filtering, beautifying, image enhancement, audio noise reduction, etc. on the initial video, so as to improve the broadcasting effect of the live video stream.
  • the video stream is pushed to each client.
  • the live broadcast processing method may include:
  • step S210 sending consultation information through a live broadcast program
  • step S220 in response to the short video playback information corresponding to the consultation information, play the corresponding target short video;
  • step S230 in response to the live broadcast return information, the live broadcast program is returned.
  • the live broadcast processing method provided by the present disclosure is executed by a user terminal.
  • the live broadcast return information may be the end information after the short video is played, or may be the end information generated when the consumer closes the short video through the terminal.
  • the live broadcast processing method further includes:
  • step S240 in response to the short video playback information, the live broadcast program is controlled to enter a background running state.
  • an electronic device comprising:
  • a first storage module on which a first executable program is stored
  • one or more first processors capable of invoking the first executable program to cause the one or more first processors to implement the method described in accordance with the first aspect of the present disclosure Provided video processing methods.
  • the electronic device is arranged on the host side and is used for processing the video stream generated by the live broadcast.
  • the target short video corresponding to the consultation information is pushed to the terminal to respond to the consumer's consultation, so as to avoid the problem that the anchor cannot answer all the consultation information one by one due to too much consultation information. , which enhances the interactivity of consumers during live broadcast and improves the live broadcast experience of consumers.
  • the electronic device may also include one or more I/O first interfaces, connected between the first processor and the first storage module, configured to implement information between the first processor and the first storage module interact.
  • the first processor is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the first storage module is a device with data storage capabilities, including but not limited to random access memory (RAM, more Specifically, such as SDRAM, DDR, etc.), read only memory (ROM), charged erasable programmable read only memory (EEPROM), flash memory (FLASH).
  • RAM random access memory
  • ROM read only memory
  • EEPROM charged erasable programmable read only memory
  • FLASH flash memory
  • the first I/O interface is connected between the first processor and the first storage module, and can realize information exchange between the first processor and the first storage module, including but not limited to a data bus (Bus) and the like.
  • a data bus Bus
  • the first processor, the first storage module and the first I/O interface are connected to each other through a bus, and further connected to other components of the display terminal.
  • a live broadcast system includes:
  • an image capture device the image capture device is used to capture video information
  • the image capture device can be externally connected to the electronic device, and the video information collected by the electronic device is the initial video stream used for live broadcast. It is also video material processed by electronic equipment.
  • the image acquisition device may be a professional video camera or a camera.
  • the image capture device may be integrated on the electronic device.
  • the electronic device may further include a display panel for displaying live video streams and consumer consultation information.
  • the image capture device includes a main camera device and an auxiliary camera device, the main camera device is used to capture the front video image of the anchor, and the auxiliary camera device is used to capture the video images of other directions in the live broadcast process in an all-round way.
  • the image capture device includes a main camera device and an auxiliary camera device, the main camera device is used to capture the front video image of the anchor, and the auxiliary camera device is used to capture the video images of other directions in the live broadcast process in an all-round way.
  • mobile video robots can also be used.
  • the mobile video robot moves on its own without disturbing the host to achieve all-round video image acquisition. ;
  • the present disclosure preferably adopts the method of mobile video robot.
  • the mobile video robot can move according to the road set in advance to complete the 360° all-round video image acquisition; If the live broadcaster has a large moving range (such as clothing live broadcast), the moving method of the video mobile robot can take the anchor as the reference center, and automatically perform a circular reciprocating movement, thereby realizing 360° all-round video image acquisition.
  • the live broadcaster has a large moving range (such as clothing live broadcast)
  • the moving method of the video mobile robot can take the anchor as the reference center, and automatically perform a circular reciprocating movement, thereby realizing 360° all-round video image acquisition.
  • the following will briefly introduce the live broadcast process of the live broadcast system provided by the present disclosure with reference to FIG. 7 .
  • the whole live broadcast process is as follows:
  • the image acquisition device performs image acquisition on the live broadcast process of the host to obtain an initial video stream
  • the electronic device performs filtering, beautification, image enhancement, audio noise reduction, etc. on the initial video stream to obtain a live video stream;
  • the live video stream is stored
  • the electronic device classifies the received consultation information
  • the target short video does not exist in the stored short video, use the keyword to match the voice information identified in the video stream;
  • the consultation information is pushed to the display device of the host.
  • a terminal comprising:
  • a second storage module on which a second executable program is stored
  • the terminal is a terminal used by consumers.
  • the terminal can send watching live broadcast, send consultation information, and play a target short video corresponding to the consultation information.
  • the terminal may also include one or more I/O second interfaces, connected between the second processor and the second storage module, and configured to implement information interaction between the second processor and the second storage module .
  • the second processor is a device with data processing capability, including but not limited to a central processing unit (CPU), etc.
  • the first storage module is a device with data storage capability, including but not limited to random access memory (RAM, more Specifically, such as SDRAM, DDR, etc.), read only memory (ROM), charged erasable programmable read only memory (EEPROM), flash memory (FLASH).
  • RAM random access memory
  • ROM read only memory
  • EEPROM charged erasable programmable read only memory
  • FLASH flash memory
  • the second I/O interface is connected between the second processor and the second storage module, and can realize information exchange between the second processor and the second storage module, including but not limited to a data bus (Bus) and the like.
  • a data bus Bus
  • the second processor, the second storage module, and the second I/O interface are connected to each other through a bus, and further connected to other components of the display terminal.
  • a computer-readable storage medium is provided on which an executable program is stored, and when the executable program is invoked, the video processing provided according to the first aspect of the present disclosure can be implemented The method or the live broadcast processing method provided according to the second aspect of the present disclosure.
  • Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media).
  • computer storage media includes both volatile and nonvolatile implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules or other data flexible, removable and non-removable media.
  • Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices, or may Any other medium used to store desired information and that can be accessed by a computer.
  • communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and can include any information delivery media, as is well known to those of ordinary skill in the art .

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

本公开提供一种视频处理方法，包括：根据咨询信息确定与所述咨询信息对应的目标短视频；将所述目标短视频推送至发送所述咨询信息的终端。本公开还提供一种直播处理方法、一种电子设备、一种直播系统、一种终端、一种计算机可读存储介质。所述视频处理方法能够提高直播过程中的用户体验。

Description

视频及直播处理方法、直播系统、电子设备、终端、介质
本申请要求享有2020年7月30日提交的、申请号为202010753323.3、发明名称为“视频及直播处理方法、直播系统、电子设备、终端、介质”的中国发明专利申请的优先权。
技术领域
本公开涉及视频处理领域，具体地，涉及一种视频处理方法、一种直播处理方法、一种电子设备、一种直播系统、一种终端、一种计算机可读存储介质。
背景技术
随着计算机、视频处理、通信技术的发展，信息技术也影响到人们的日常生活。例如，人们日常中的购物已经从实体店购物发展为电商平台购物，又由电商平台购物发展为直播平台带货购物。与传统的图文广告相比，直播带货不仅保障强互动性和实时反馈性，还缩短了消费者的决策时间，提升购物效率。
直播过程中，主播除了采用具有个人特色的方式展示商品之外，还需要与消费者保持亲密互动，借此来提升消费者的购买欲。在直播间在线人数过多时，主播难以回答每一位消费者的问题，这样有可能导致问题没有得到解决的消费者退出直播间。
因此，如何回答每一位消费者的提问成为本领域亟待解决的技术问题。
发明内容
本公开的目的在于提供一种视频处理方法、一种直播处理方法、一种电子设备、一种终端、一种计算机可读存储介质。
作为本公开的第一个方面，提供一种视频处理方法，包括：
根据咨询信息确定与所述咨询信息对应的目标短视频；
将所述目标短视频推送至发送所述咨询信息的终端。
可选地，根据咨询信息确定与所述咨询信息对应的目标短视频包括：
提取所述咨询信息的关键词；
将提取到的关键词与已存储的多个短视频的特征信息进行匹配；
将特征信息与所述关键词匹配的短视频作为所述目标短视频。
可选地，提取所述咨询信息的关键词的步骤包括：
对接收到的所有咨询信息进行分类；
提取各类咨询信息的关键词；
其中，在将所述目标短视频推送至发送所述咨询信息的终端的步骤中，向发送类别相同的咨询信息的终端发送的目标视频相同。
可选地，在根据咨询信息确定与所述咨询信息对应的目标短视频的步骤之前，所述视频处理方法还包括：
根据预设的所述特征信息从已经播出的视频流中提取短视频并存储所述短视频。
可选地，根据预设的所述特征信息从已经播出的视频流中提取短视频并存储所述短视频包括：
对视频流进行语音识别；
根据语音识别结果与预设的所述特征信息进行对比，并将确定各个特征信息在所述视频流中对应的时间段；
将各个特征在所述视频流中对应的时间段存储为相应的短视频。
可选地，当已存储的多个短视频的特征信息均不能够与提取到的关键词匹配时，所述视频处理方法还包括：
对已播出的视频流进行语音识别；
根据语音识别结果与提取到的所述关键词进行对比；
当所述语音识别结果中存在与所述关键词匹配的词语时，将该词语在所述视频流中对应的时间段作为所述目标短视频。
可选地，所述视频处理方法还包括：
当所述语音识别结果中不存在与所述关键词匹配的词语时，生成提示信息。
可选地，生成提示信息的步骤包括：
在进行直播的设备的屏幕上显示所述咨询信息。
作为本公开的第二个方面，提供一种直播处理方法，包括：
通过直播程序发送咨询信息；
响应于与所述咨询信息对应的短视频播放信息，播放相应的目标短视频；
响应于直播返回信息，返回直播程序。
可选地，所述直播处理方法还包括：
响应于短视频播放信息，控制所述直播程序进入后台运行状态。
作为本公开的第三个方面，提供一种电子设备，所述电子设备包括：
第一存储模块，其上存储有第一可执行程序；
一个或多个第一处理器，所述一个或多个第一处理器能够调用所述第一可执行程序，以使得所述一个或多个第一处理器实现根据本公开第一个方面所提供的视频处理方法。
作为本公开的第四个方面，提供一种直播系统，所述直播系统包括：
图像采集装置，所述图像采集装置用于采集视频信息；
本公开第三个方面所提供的电子设备。
作为本公开的第五个方面，提供一种终端，包括：
第二存储模块，其上存储有第二可执行程序；
一个或多个第二处理器，所述一个或多个第二处理器能够调用所述第二可执行程序，以使得所述一个或多个第二处理器实现根据本公开第二个方面所提供的直播处理方法。
作为本公开的第六个方面，提供一种计算机可读存储介质，其上存储有可执行程序，当所述可执行程序被调用时，能够实现根据本公开第一个方面所提供的视频处理方法或者根据本公开第二个方面所提供的直播处理方法。
附图说明
附图是用来提供对本发明的进一步理解，并且构成说明书的一部分，与下面的具体实施方式一起用于解释本发明，但并不构成对本发明的限制。在 附图中：
图1是本公开所提供的视频处理方法的一种实施方式的流程示意图；
图2是本公开所提供的视频处理方法的第二种实施方式的流程示意图；
图3是步骤S111的一种实施方式的流程图；
图4是步骤S105的一种实施方式的流程图；
图5是本公开所提供的直播处理方法的一种实施方式的流程图；
图6是本公开所提供的直播处理方法的另一种实施方式的流程图；
图7是本公开所提供给的直播系统的工作流程图。
具体实施方式
以下结合附图对本发明的具体实施方式进行详细说明。应当理解的是，此处所描述的具体实施方式仅用于说明和解释本发明，并不用于限制本发明。
作为本公开的一个方面，提供一种视频处理方法，如图1所示，所述视频处理方法包括：
在步骤S110中，根据咨询信息确定与所述咨询信息对应的目标短视频；
在步骤S120中，将所述目标短视频推送至发送所述咨询信息的终端。
本公开所提供的视频处理方法由主播侧的电子设备所执行，需要指出的是，所述咨询信息为消费者通过自己的终端输入、并通过通信网络传输至主播侧的电子设备。
“所述目标短视频与所述咨询信息对应”可以是指，短视频中的内容可以回复所述咨询信息中所涉及的问题。
例如，所述咨询信息可以为咨询折扣的信息，所述目标短视频可以为介绍商品折扣的短视频。
在本公开中，通过向终端推送与咨询信息相对应的目标短视频来回应消费者的咨询，从而可以避免主播因咨询信息过多、无法对所有咨询信息一一解答的问题，增强了消费者在直播时的互动性，提高了消费者的直播体验。
在本公开中对如何获得所述短视频并不做特殊的限定，例如，可以在直播开始时，对直播产生的视频流进行存储，并在存储的视频流中截取多段短 视频，也可以是主播预先录制好的对商品进行讲解的短视频。
通常，主播在进行直播时会反复介绍商品信息、以及折扣信息，从直播产生的视频流中截取短视频可以减小主播以及工作人员的工作量，并降低人工成本。相应地，如图2所示，在步骤S110之前，所述视频处理方法还可以包括：
在步骤S100中，存储直播时产生的视频流。
相应地，所述目标短视频截取自所述视频流。
在本公开中，对如何执行步骤S110步骤特殊的限定，作为一种可选实施方式，如图2所示，步骤S110可以包括：
在步骤S111中，提取所述咨询信息的关键词；
在步骤S112中，将提取到的关键词与已存储的多个短视频的特征信息进行匹配；
在步骤S113中，将特征信息与所述关键词匹配的短视频作为所述目标短视频。
通常，消费者输入的咨询信息中包含很多无用的语气词，在步骤S111中所涉及到的“关键词”则是咨询信息中的有用信息。
如上文中所示，多个所述短视频是“已存储的”，意思是，在提取咨询信息的关键词之前，已经在主播侧的电子设备中存储了多个短视频。在存储短视频时，可以利用特征信息对短视频进行标记。例如，涉及商品折扣的短视频的特征信息为“折扣”，因此，可以利用“折扣”对该视频进行标记。涉及商品参数的特征信息为该商品的特征参数。例如，当商品为口红时，相应的特征参数为“色号”，可以利用具体的色号来对商品进行标记。需要指出的是，同一段短视频可以对应多个不同的特征信息。例如，同一段短视频中包括了某一色号口红的打折信息，可以利用口红色号以及打折信息作为特征信息来标记同一段短视频。
例如，消费者输入的咨询信息可能是，“折扣是多少啊？”其中的关键词为“折扣”，其余均为语气词。
在步骤S112中，可以将提取到的“折扣”去与多个短视频的特征信息进 行匹配，并在步骤S113中将特征信息包括“折扣”的短视频作为所述目标短视频，推送给消费者的终端。
又例如，消费者输入的咨询信息可能是，“105的折扣是多少啊？”，其中关键词为“105+折扣”，其余均为语气词。在步骤S112中，可以将提取到的“105”、“折扣”与多个短视频特征进行匹配，并在步骤S113中将特征信息同时包括“105”和“折扣”的短视频作为所述目标短视频，推送给消费者的终端。
需要指出的是，关键词长度越长、则匹配精度越高。例如，在一场直播中推销多种型号的商品时，每种型号的商品都有相应的折扣信息，并且，不同型号的商品折扣信息也可能不同。例如，型号105的商品的折扣与型号106的折扣不同。消费者提问时，问题也是自己关注的型号的折扣信息。因此，消费者发出的咨询信息中通常是同时包括型号和折扣的。在从咨询信息中提取关键词时，也要包括商品型号、以及问题(该问题可以为，折扣)。
在观看直播时，消费者关注的信息基本类似。例如，大部分消费者关注的信息多为折扣信息、商品型号、购买方式等几大类。为了快速地对消费者的咨询作出反馈，可选地，如图3所示，步骤S111可以包括：
在步骤S111a中，对接收到的所有咨询信息进行分类；
在步骤S111b中，提取各类咨询信息的关键词。
相应地，在步骤S120中，向发送类别相同的咨询信息的终端发送的目标视频相同。
在本公开中，对如何执行步骤S111a不做特殊的限定。例如，消费者发送的咨询信息多为文字。在接收到各个消费者的咨询信息后，将文字内容重合度达到80％的信息归为同一类。当然，本公开并不对重合度的阈值做特殊的限定，所述阈值可以是80％，也可以是90％，只要取自70％至99％即可。所述阈值越高、则分类越精细，越能够针对性地回答消费者提出的问题。
通过对咨询信息进行分类，可以提高向各个消费者推送目标短视频的效率，有利于实时解决消费者的问题，提高消费者的互动体验，并提高商品售出的概率。
可选地，咨询信息的分类可以包括询问折扣、进行打赏、询问商品信息等。
如上文中所述，所述目标短视频截取自直播时产生的视频流。相应地，在根据咨询信息确定与所述咨询信息对应的目标短视频的步骤之前，如图2所示，所述视频处理方法还包括：
在步骤S105中，根据预设的所述特征信息从已经播出的视频流中提取短视频。
在本公开中，对如何执行步骤S105不做特殊的限定。例如，可以在直播开始前给主播提供台本，要求主播在某些特定的时间段说出所需要的信息。例如，在直播开始的前五分钟介绍商品参数、以及折扣信息。每隔20分钟介绍一次商品特征以及折扣信息等，然后在存储了直播产生的视频流之后，在约定好的时间截取短视频、然后利用所述特征信息标记所述短视频即可。
在本公开中，对如何预设所述特征信息不做特殊的限定。作为一种可选实施方式，可以根据大数据、以及以往的直播记录来确定咨询频率高(例如，可以将该频率设定为每分钟10次)的问题，并根据咨询频率高的问题设定所述“特征信息”。当直播视频流中出现上述“特征信息”即可截取短视频，并存储所述短视频。在消费者发出咨询信息时，直接利用咨询信息中的关键字进行匹配即可。
众所周知的是，很多主播个人特色明显，设置台本会对主播造成限制。因此，很多主播在直播时并没有台本。相应地，如图4所示，步骤S105可以包括：
在步骤S105a中，对视频流进行语音识别；
在步骤S105b中，根据语音识别结果与预设的所述特征信息进行对比，并将确定各个特征信息在所述视频流中对应的部分；
在步骤S105c中，将各个特征在所述视频流中对应的部分存储为相应的短视频。
作为一种可选实施方式，步骤S105b可以被具体执行为“确定各个特征信息在所述视频流中对应的部分的开始时间和结束时间”。在所述视频流中 截取所述开始时间、和所述结束时间之间的部分，即可获得与各个特征在视频流中对应的部分。
上文中所述的预先存储的短视频中存在目标视频的情况。当预先存储的短视频中不存在与关键词匹配的目标视频时，如图2所示，所述视频处理方法还可以包括：
在步骤S130中，对已播出的视频流进行语音识别；
在步骤S140中，根据语音识别结果与提取到的所述关键词进行对比；
在步骤S150中，当所述语音识别结果中存在与所述关键词匹配的词语时，将该词语在所述视频流中对应的部分作为所述目标短视频；
在步骤S160中，以所述词语作为特征信息标记所述词语在所述视频流中对应的部分，并存储标记后的短视频。
在本公开中，步骤S150可以被具体执行为“确定该词语在所述视频流中对应的开始时间和结束时间，并将开始时间和结束时间之间的部分作为所述目标短视频”。步骤S160可以被具体执行为“以所述词语作为特征信息标记所述词语在所述视频流中对应的开始时间和结束时间之间对应的短视频，并存储标记后的短视频”。
如果将已存储的短视频作为素材的话，步骤S160相当于对素材库进行补充。
当然，如果经历过步骤S130至步骤S140后，仍然无法得到所述目标短视频时，则需要主播直接进行解答。
相应地，如图2所示，所述处理方法还可以包括：
在步骤S170中，当所述语音识别结果中不存在与所述关键词匹配的词语时，生成提示信息。
通过步骤S110至步骤S160可以降低执行步骤S170的几率，减少主播的工作量，以利于主播更好地介绍商品。
所述提示信息的作用在于提醒主播或者其他工作人员对所述咨询信息进行解答。在本公开中，对提示信息的具体形式不做特殊的限定。例如，生成提示信息的步骤可以包括：
在进行直播的设备的屏幕上显示所述咨询信息。
作为一种可选实施方式，进行直播的设备的屏幕上只显示无法自动匹配到目标视频的咨询信息。
作为另一种可选实施方式，进行直播的设备的屏幕上显示所有咨询信息，但是，无法自动匹配到目标视频的咨询信息与可以自动匹配到目标视频的咨询信息颜色不同或者字体不同，以便主播及时识别出相应的咨询信息。当然，也可以在无法自动匹配到目标视频的咨询信息上添加其他标识信息，以便于主播及时识别并解答。
本公开所提供的视频处理方法除了包括对咨询信息进行处理之外，还可以包括：
对图像采集装置采集到的初始视频进行处理，以获得直播视频流。
对初始视频进行的处理可以包括对初始视频进行过滤、美颜、图像增强、音频降噪等处理中的至少一者，以提高直播视频流的播出效果。
获得所述直播视频流后，将所述视频流推送至各个客户端。
作为本公开的第二个方面，提供一种直播处理方法，如图5所示，所述直播处理方法可以包括：
在步骤S210中，通过直播程序发送咨询信息；
在步骤S220中，响应于与所述咨询信息对应的短视频播放信息，播放相应的目标短视频；
在步骤S230中，响应于直播返回信息，返回直播程序。
本公开所提供的直播处理方法由用户终端所执行。在播放短视频时，可以将直播程序设置为后台运行，也可以直接退出直播程序。
在本公开中，对直播返回信息的具体类型不做特殊的限定。例如，所述直播返回信息可以是短视频播放完毕后的的结束信息，也可以是消费者通过终端关闭短视频时产生的结束信息。
停止播放目标短视频后，即刻返回直播程序，以便于消费者继续观看直播。
为了便于消费者可以快速地重返直播间，可选地，如图6所示，所述直 播处理方法还包括：
在步骤S240中，响应于短视频播放信息，控制所述直播程序进入后台运行状态。
作为本公开的第三个方面，提供一种电子设备，所述电子设备包括：
第一存储模块，其上存储有第一可执行程序；
一个或多个第一处理器，所述一个或多个第一处理器能够调用所述第一可执行程序，以使得所述一个或多个第一处理器实现根据本公开第一个方面所提供的视频处理方法。
所述电子设备设置在主播侧，用于对直播产生的视频流进行处理。如上文中所述，在本公开中，通过向终端推送与咨询信息相对应的目标短视频来回应消费者的咨询，从而可以避免主播因咨询信息过多、无法对所有咨询信息一一解答的问题，增强了消费者在直播时的互动性，提高了消费者的直播体验。
所述电子设备还可以包括一个或多个I/O第一接口，连接在所述第一处理器与第一存储模块之间，配置为实现所述第一处理器与第一存储模块的信息交互。
第一处理器为具有数据处理能力的器件，其包括但不限于中央处理器(CPU)等；第一存储模块为具有数据存储能力的器件，其包括但不限于随机存取存储器(RAM，更具体如SDRAM、DDR等)、只读存储器(ROM)、带电可擦可编程只读存储器(EEPROM)、闪存(FLASH)。
第一I/O接口连接在第一处理器与第一存储模块间，能实现第一处理器与第一存储模块的信息交互，其包括但不限于数据总线(Bus)等。
在一些实施例中，第一处理器、第一存储模块和第一I/O接口通过总线相互连接，进而与显示终端的其它组件连接。
作为本公开的第四个方面，提供一种直播系统，所述直播系统包括：
图像采集装置，所述图像采集装置用于采集视频信息；
本公开所提供的上述电子设备。
在本公开中，所述图像采集装置可以外接于所述电子设备，所述电子设 备所采集到的视频信息即为用于直播的初始视频流。也是电子设备进行处理的视频素材。
在本公开中，图像采集装置可以是专业的摄像机，也可以是摄像头。当所述图像采集为摄像头时，所述图像采集装置可以集成在所述电子设备上。相应地，所述电子设备还可以包括显示面板，用于显示直播视频流、以及消费者的咨询信息。
作为一种可选实施方式，图像采集装置包括主摄像装置和辅助摄像装置，主摄像装置用于采集主播正面视频图像，辅助摄像装置用于全方位采集直播过程中的其他方位的视屏图像，可以采用多角度分布多个摄像头实现360°全方位视频图像采集，也可以采用移动视频机器人的方式，在主播直播过程中，移动视频机器人在不干扰主播的情况下自行移动实现全方位的视频图像采集；本公开优选采用移动视频机器人的方式，若主播的直播方式以坐为主，移动范围不大，移动视频机器人可按照提前设定的路劲移动完成360°全方位视频图像采集；若主播的直播方过程中有较大移动范围(比如服装直播)，则视频移动机器人的移动方式可以主播为参考中心，自动进行循环往复环绕式移动，进而实现360°全方位视频图像采集。
下面结合图7对本公开所提供的直播系统的进行直播的过程进行简单介绍。整个直播流程如下：
图像采集装置对主播的直播过程进行图像采集，获得初始视频流；
电子设备对初始视频流进行过滤、美颜、图像增强、音频降噪等处理，获得直播视频流；
将直播视频流推送给用户终端；
将直播视频流推送给用户终端的同时，对直播视频流进行存储；
根据预先设定的特征信息对直播视频流进行分割和截取，形成多个短视频；
消费者通过用户终端上安装的直播程序发出咨询信息；
电子设备对接收到的咨询信息进行分类；
对分类后获得的各类咨询信息分别提取关键词；
利用所述关键词与已存储的短视频的特征信息进行匹配(判断关键词与特征信息的相似性)；
将与特征信息与关键词匹配的信息作为目标短视频推送给相应的终端；
若已存储的短视频中不存在目标短视频，则利用关键词与视频流中识别的语音信息进行匹配；
当视频流的语音信息中存在与所述关键词相匹配的部分时，将该部分对应的视频流部分存储为目标短视频，并推送给用户终端；
当视频流的的语音信息中不存在与所述关键词相匹配的部分，将咨询信息推送至主播端的显示装置。
作为本公开的第五个方面，提供一种终端，包括：
第二存储模块，其上存储有第二可执行程序；
一个或多个第二处理器，所述一个或多个第二处理器能够调用所述第二可执行程序，以使得所述一个或多个第二处理器实现本公开第二个方面所提供的直播处理方法。
在本公开中，所述终端为消费者所使用的终端。通过所述终端可以发送观看直播、发送咨询信息、以及播放与所述咨询信息对应的目标短视频。
所述终端还可以包括一个或多个I/O第二接口，连接在所述第二处理器与第二存储模块之间，配置为实现所述第二处理器与第二存储模块的信息交互。
第二处理器为具有数据处理能力的器件，其包括但不限于中央处理器(CPU)等；第一存储模块为具有数据存储能力的器件，其包括但不限于随机存取存储器(RAM，更具体如SDRAM、DDR等)、只读存储器(ROM)、带电可擦可编程只读存储器(EEPROM)、闪存(FLASH)。
第二I/O接口连接在第二处理器与第二存储模块间，能实现第二处理器与第二存储模块的信息交互，其包括但不限于数据总线(Bus)等。
在一些实施例中，第二处理器、第二存储模块和第二I/O接口通过总线相互连接，进而与显示终端的其它组件连接。
作为本公开的第六个方面，提供一种计算机可读存储介质，其上存储有可执行程序，当所述可执行程序被调用时，能够实现根据本公开第一个方面 所提供的视频处理方法或者根据本公开第二个方面所提供的直播处理方法。
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。在硬件实施方式中，在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其它数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其它存储器技术、CD-ROM、数字多功能盘(DVD)或其它光盘存储、磁盒、磁带、磁盘存储或其它磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其它的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其它传输机制之类的调制数据信号中的其它数据，并且可包括任何信息递送介质。
可以理解的是，以上实施方式仅仅是为了说明本公开的原理而采用的示例性实施方式，然而本公开并不局限于此。对于本领域内的普通技术人员而言，在不脱离本公开的精神和实质的情况下，可以做出各种变型和改进，这些变型和改进也视为本公开的保护范围。

Claims (14)

  1. 一种视频处理方法，包括：
    根据咨询信息确定与所述咨询信息对应的目标短视频；
    将所述目标短视频推送至发送所述咨询信息的终端。
  2. 根据权利要求1所述的视频处理方法，其中，根据咨询信息确定与所述咨询信息对应的目标短视频包括：
    提取所述咨询信息的关键词；
    将提取到的关键词与已存储的多个短视频的特征信息进行匹配；
    将特征信息与所述关键词匹配的短视频作为所述目标短视频。
  3. 根据权利要求2所述的视频处理方法，其中，提取所述咨询信息的关键词的步骤包括：
    对接收到的所有咨询信息进行分类；
    提取各类咨询信息的关键词；
    其中，在将所述目标短视频推送至发送所述咨询信息的终端的步骤中，向发送类别相同的咨询信息的终端发送的目标视频相同。
  4. 根据权利要求2所述的视频处理方法，其中，在根据咨询信息确定与所述咨询信息对应的目标短视频的步骤之前，所述视频处理方法还包括：
    根据预设的所述特征信息从已经播出的视频流中提取短视频并存储所述短视频。
  5. 根据权利要求4所述的视频处理方法，其中，根据预设的所述特征信息从已经播出的视频流中提取短视频并存储所述短视频包括：
    对视频流进行语音识别；
    根据语音识别结果与预设的所述特征信息进行对比，并将确定各个特征 信息在所述视频流中对应的部分；
    将各个特征在所述视频流中对应的部分存储为相应的短视频。
  6. 根据权利要求2至5中任意一项所述的视频处理方法，其中，当已存储的多个短视频的特征信息均不能够与提取到的关键词匹配时，所述视频处理方法还包括：
    对已播出的视频流进行语音识别；
    根据语音识别结果与提取到的所述关键词进行对比；
    当所述语音识别结果中存在与所述关键词匹配的词语时，将该词语在所述视频流中对应的部分作为所述目标短视频；
    以所述词语作为特征信息标记所述词语在所述视频流中对应的部分，并存储标记后的短视频。
  7. 根据权利要求6所述的视频处理方法，其中，所述视频处理方法还包括：
    当所述语音识别结果中不存在与所述关键词匹配的词语时，生成提示信息。
  8. 根据权利要求7所述的视频处理方法，其中，生成提示信息的步骤包括：
    在进行直播的设备的屏幕上显示所述咨询信息。
  9. 一种直播处理方法，包括：
    通过直播程序发送咨询信息；
    响应于与所述咨询信息对应的短视频播放信息，播放相应的目标短视频；
    响应于直播返回信息，返回直播程序。
  10. 根据权利要求9所述的直播处理方法，其中，所述直播处理方法还 包括：
    响应于短视频播放信息，控制所述直播程序进入后台运行状态。
  11. 一种电子设备，所述电子设备包括：
    第一存储模块，其上存储有第一可执行程序；
    一个或多个第一处理器，所述一个或多个第一处理器能够调用所述第一可执行程序，以使得所述一个或多个第一处理器实现根据权利要求1至8中任意一项所述的视频处理方法。
  12. 一种直播系统，所述直播系统包括：
    图像采集装置，所述图像采集装置用于采集视频信息；
    权利要求11所述的电子设备。
  13. 一种终端，包括：
    第二存储模块，其上存储有第二可执行程序；
    一个或多个第二处理器，所述一个或多个第二处理器能够调用所述第二可执行程序，以使得所述一个或多个第二处理器实现根据权利要求9或10所述的直播处理方法。
  14. 一种计算机可读存储介质，其上存储有可执行程序，当所述可执行程序被调用时，能够实现根据权利要求1至8中任意一项所述的视频处理方法或者根据权利要求9或10所述的直播处理方法。
PCT/CN2021/098901 2020-07-30 2021-06-08 视频及直播处理方法、直播系统、电子设备、终端、介质 WO2022022075A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/765,041 US11956510B2 (en) 2020-07-30 2021-06-08 Video processing method, live streaming processing method, live streaming system, electronic device, terminal, and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010753323.3 2020-07-30
CN202010753323.3A CN114095738A (zh) 2020-07-30 2020-07-30 视频及直播处理方法、直播系统、电子设备、终端、介质

Publications (1)

Publication Number Publication Date
WO2022022075A1 true WO2022022075A1 (zh) 2022-02-03

Family

ID=80037466

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/098901 WO2022022075A1 (zh) 2020-07-30 2021-06-08 视频及直播处理方法、直播系统、电子设备、终端、介质

Country Status (3)

Country Link
US (1) US11956510B2 (zh)
CN (1) CN114095738A (zh)
WO (1) WO2022022075A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114866818B (zh) * 2022-06-17 2024-04-26 深圳壹账通智能科技有限公司 视频推荐方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170125060A1 (en) * 2015-10-28 2017-05-04 Xiaomi Inc. Video playing method and device
CN106878819A (zh) * 2017-01-20 2017-06-20 合网络技术（北京）有限公司 一种网络直播中信息交互的方法、系统及装置
CN108280155A (zh) * 2018-01-11 2018-07-13 百度在线网络技术（北京）有限公司 基于短视频的问题检索反馈方法、装置及其设备
CN108419138A (zh) * 2018-02-05 2018-08-17 平安科技（深圳）有限公司 直播互动装置、方法及计算机可读存储介质
CN110929094A (zh) * 2019-11-20 2020-03-27 北京香侬慧语科技有限责任公司 一种视频标题处理方法和装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8209713B1 (en) * 2008-07-11 2012-06-26 The Directv Group, Inc. Television advertisement monitoring system
CN109429075A (zh) * 2017-08-25 2019-03-05 阿里巴巴集团控股有限公司 一种直播内容处理方法、装置和系统
CN110582025B (zh) * 2018-06-08 2022-04-01 北京百度网讯科技有限公司 用于处理视频的方法和装置
CN109640112B (zh) * 2019-01-15 2021-11-23 广州虎牙信息科技有限公司 视频处理方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170125060A1 (en) * 2015-10-28 2017-05-04 Xiaomi Inc. Video playing method and device
CN106878819A (zh) * 2017-01-20 2017-06-20 合网络技术（北京）有限公司 一种网络直播中信息交互的方法、系统及装置
CN108280155A (zh) * 2018-01-11 2018-07-13 百度在线网络技术（北京）有限公司 基于短视频的问题检索反馈方法、装置及其设备
CN108419138A (zh) * 2018-02-05 2018-08-17 平安科技（深圳）有限公司 直播互动装置、方法及计算机可读存储介质
CN110929094A (zh) * 2019-11-20 2020-03-27 北京香侬慧语科技有限责任公司 一种视频标题处理方法和装置

Also Published As

Publication number Publication date
US11956510B2 (en) 2024-04-09
CN114095738A (zh) 2022-02-25
US20220345783A1 (en) 2022-10-27

Similar Documents

Publication Publication Date Title
CN108259936B (zh) 基于直播技术的问答方法、服务器及存储介质
US20220360825A1 (en) Livestreaming processing method and apparatus, electronic device, and computer-readable storage medium
CN111754267B (zh) 基于区块链的数据处理方法及系统
US10939165B2 (en) Facilitating television based interaction with social networking tools
CN111178970B (zh) 广告投放的方法及装置、电子设备和计算机可读存储介质
CN111935554A (zh) 直播信息的处理方法、装置、设备及计算机可读存储介质
CN109947984A (zh) 一种针对儿童的内容推送方法及推送装置
US20230368248A1 (en) Method and system for analyzing live broadcast video content with a machine learning model implementing deep neural networks to quantify screen time of displayed brands to the viewer
US20190155864A1 (en) Method and apparatus for recommending business object, electronic device, and storage medium
US20150112814A1 (en) System and method for an integrated content publishing system
CN113315979A (zh) 数据处理方法、装置、电子设备和存储介质
CN113347498A (zh) 一种视频播放方法、装置及计算机可读存储介质
CN112804582A (zh) 弹幕处理方法、装置、电子设备及存储介质
CN107659545B (zh) 一种媒体信息处理方法及媒体信息处理系统、电子设备
WO2022022075A1 (zh) 视频及直播处理方法、直播系统、电子设备、终端、介质
CN110888997A (zh) 内容评价方法、系统和电子设备
CN111277898A (zh) 一种内容推送方法及装置
KR102460595B1 (ko) 게임 방송에서의 실시간 채팅 서비스 제공 방법 및 장치
CN113301362B (zh) 视频元素展示方法及装置
CN113077295B (zh) 基于用户终端的广告分级投放方法、用户终端和存储介质
CN117354548A (zh) 一种评论展示方法、装置、电子设备、计算机可读介质
CN110415015A (zh) 产品认可度分析方法、装置、终端及计算机可读存储介质
US20240146979A1 (en) System, method and computer-readable medium for live streaming recommendation
CN111369312A (zh) 商品信息的推荐方法、装置、计算设备及计算机存储介质
CN117217831B (zh) 广告投放方法及装置、存储介质及电子设备

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: 21851240

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: 21851240

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 10-08-2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21851240

Country of ref document: EP

Kind code of ref document: A1