CN109005382A - A kind of video acquisition management method and server - Google Patents
A kind of video acquisition management method and server Download PDFInfo
- Publication number
- CN109005382A CN109005382A CN201810684525.XA CN201810684525A CN109005382A CN 109005382 A CN109005382 A CN 109005382A CN 201810684525 A CN201810684525 A CN 201810684525A CN 109005382 A CN109005382 A CN 109005382A
- Authority
- CN
- China
- Prior art keywords
- video
- breakdown maintenance
- maintenance
- breakdown
- content
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of video acquisition management method and servers.Wherein, method includes: acquisition breakdown maintenance video；The acquisition request for the breakdown maintenance video of receiving terminal apparatus；The acquisition request is responded, sends the breakdown maintenance video to the terminal device；Receive the feedback for the breakdown maintenance video of the terminal device.Also disclose corresponding server.The application acquires high-quality and fining breakdown maintenance video by first directionality, video maintenance video is pushed to user further according to the acquisition request of user, finally user is received again to the feedback of the breakdown maintenance video of push, to provide a kind of efficient video acquisition management method for breakdown maintenance video, it allows users to utilize high-quality and fining breakdown maintenance video, it quickly suits the remedy to the case to the failure of automobile, therefore effectively raises the efficiency of accident treatment.
Description
Technical field
This application involves Internet technical field more particularly to a kind of video acquisition management method and servers.
Background technique
With economic development, the automobile on road is more and more.Although automobile greatly facilitates our life,
We bring many puzzlements, because automobile is a loss product, not can avoid loss and aging during use, therefore
Needing the meticulous maintenance of car owner can just be used for a long time.
Even if be timely maintenance and regularly vehicle failure check, service life long automobile is also inevitably in road
On break down and accident, cause automobile to be difficult to be further continued for travelling.When especially on a highway, around fault car
Vehicle is numerous and travel speed also quickly, farther out along with accident spot generally distance maintenance website, so that fault car
A possibility that residence time is longer, and second accident occurs is bigger.
The case where breaking down suddenly in face of automobile, most of car owner only has original place waiting rescue, but there are also dynamic
Hand ability strong car owner can independently be repaired in search vehicle failure and corresponding method for maintaining on the net.But online pass
Mix very much in the resource of auto repair method, quality is difficult to ensure, and the auto repair since rudimentary knowledge for being mostly
Study course.Therefore car owner in a short time at all can not therefrom quick obtaining need resource, delay rescue time instead so that
The treatment effeciency of accident is low.
Summary of the invention
The embodiment of the present application provides a kind of video acquisition management method and server, can effectively improve the effect of accident treatment
Rate.
In a first aspect, the embodiment of the present application provides a kind of video acquisition management method, this method comprises:
Acquire breakdown maintenance video；The acquisition request for the breakdown maintenance video of receiving terminal apparatus；Response institute
Acquisition request is stated, sends the breakdown maintenance video to the terminal device；Receive the terminal device is directed to the failure
Repair the feedback of video.
With reference to first aspect, in the first implementation of first aspect, the acquisition breakdown maintenance video includes:
Receive target video；The similar video for being higher than preset value with the target video similarity is searched in video library；
The similar video if it does not exist then acquires the target video as breakdown maintenance video.
With reference to first aspect, described to connect after the acquisition breakdown maintenance video in second of realization of first aspect
Before the acquisition request for receiving terminal device, further includes:
Identify the content in the breakdown maintenance video；According to breakdown maintenance video described in the content optimization.
Second of realization with reference to first aspect, in the third realization of first aspect, the identification failure dimension
Repair the content in video, comprising:
Using the content in breakdown maintenance video described in deep learning Network Recognition, the content includes maintenance step, dimension
Repair tool and/or auto parts.
The third realization with reference to first aspect, it is described excellent according to the content in the 4th kind of realization of first aspect
Change the breakdown maintenance video, comprising:
Audio-frequency information and/or caption information are obtained according to the maintenance step；By the audio-frequency information and/or the subtitle
Information is in conjunction with the breakdown maintenance video.
The third realization with reference to first aspect, it is described excellent according to the content in the 5th kind of realization of first aspect
Change the breakdown maintenance video, comprising:
Obtain the fuzzy frame in the breakdown maintenance video；Obtain the maintenance tool and/or automobile zero in the fuzzy frame
The corresponding standard picture of part；The maintenance tool and/or auto parts in the fuzzy frame are replaced using the standard picture.
It realizes to any one implementation of the 5th kind of realization of first aspect, the with reference to first aspect second
During the 6th kind of one side is realized, the breakdown maintenance video according to the content optimization includes:
Label is added to the breakdown maintenance video according to the content.
Second aspect, the embodiment of the present application provide a kind of server, which includes for executing above-mentioned first party
The unit of the method in face, the server include:
Acquisition unit, for acquiring breakdown maintenance video；
Receiving unit, the acquisition request for the breakdown maintenance video for receiving terminal apparatus；It is also used to receive
The feedback for the breakdown maintenance video of the terminal device；
Response unit sends the breakdown maintenance video to the terminal device for responding the acquisition request.
In conjunction with second aspect, in the first implementation of second aspect:
The receiving unit is also used to receive target video；
Searching unit, for searching the similar video for being higher than preset value with the target video similarity in video library；
The acquisition unit then acquires the target video as breakdown maintenance for the similar video if it does not exist
Video.
In conjunction with second aspect, in second of realization of second aspect, the server further include:
Recognition unit, for identification content in the breakdown maintenance video；
Optimize unit, is used for the breakdown maintenance video according to the content optimization.
In conjunction with second of realization of second aspect, in the third realization of second aspect:
The recognition unit, it is described interior for utilizing the content in breakdown maintenance video described in deep learning Network Recognition
Hold includes maintenance step, maintenance tool and/or auto parts.
In conjunction with the third realization of second aspect, in the 4th kind of realization of second aspect:
The optimization unit, for obtaining audio-frequency information and/or caption information according to the maintenance step；It is also used to institute
Audio-frequency information and/or the caption information are stated in conjunction with the breakdown maintenance video.
In conjunction with the third realization of second aspect, in the 5th kind of realization of second aspect:
Acquiring unit, for obtaining the fuzzy frame in the breakdown maintenance video；It is also used to obtain in the fuzzy frame
Maintenance tool and/or the corresponding standard picture of auto parts；
The optimization unit is also used to replace the maintenance tool and/or vapour in the fuzzy frame using the standard picture
Vehicle part.
In conjunction with any one implementation of second of the 5th kind of realization to second aspect of second aspect, in second party
During the 6th kind of face is realized:
The optimization unit, for adding label to the breakdown maintenance video according to the content.
The third aspect, the embodiment of the present application provide another server, including processor, communication interface and memory,
The processor, communication interface and memory are connected with each other, wherein the communication interface with other electronic equipments for being handed over
Data are changed, the memory is used to store the computer program for supporting server to execute the above method, the computer program packet
Program instruction is included, the processor is configured for calling described program instruction, to execute any reality in above-mentioned first aspect
Existing method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, the computer storage medium
It is stored with computer program, the computer program includes program instruction, and described program instruction is when being executed by processor, to hold
The method of any realization in the above-mentioned first aspect of row.
The application acquires high-quality and fining breakdown maintenance video by first directionality, and the acquisition further according to user is asked
It asks to user and pushes video maintenance video, finally receive user again to the feedback of the breakdown maintenance video of push, to be directed to
Breakdown maintenance video provides a kind of efficient video acquisition management method, allows users to utilize high-quality and fining event
Barrier maintenance video, quickly suits the remedy to the case to the failure of automobile, therefore the effective efficiency for improving accident treatment.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described.
Fig. 1 is a kind of schematic flow diagram of video acquisition management method provided by the embodiments of the present application；
Fig. 2 is the schematic flow diagram of another video acquisition management method provided by the embodiments of the present application；
Fig. 3 is a kind of schematic block diagram of server provided by the embodiments of the present application；
Fig. 4 is a kind of structural diagram of server provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application is described.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determination " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
Server described in the embodiment of the present application is the equipment for having powerful computing function, also due to can for it is multiple its
His server or terminal device provide calculating service simultaneously, therefore server is also equipped with the service of undertaking and ensures the energy of service
Power.Server includes but is not limited to such as computer.In processing capacity, stability, reliability, safety, scalability, can manage
Rationality etc. has outstanding performance.In the specific implementation, server is with powerful image processing function, huge memory and strong
The equipment of big transmittability.
Automobile inevitably will appear failure during use, but the failure that most people automobile can not occur is tieed up
It repairs, is primarily due to lack the maintenance direction of service experience and profession.However this problem becomes with the development of internet
Different, people learn the tool that this is powerful using internet gradually to be searched for accordingly, such as inquiry automobile
Method for maintaining etc., but mix very much about the resource of auto repair method causes the quality of video to be difficult to ensure on the net, Er Qie great
The auto repair study course since rudimentary knowledge for being all, car owner in a short time at all can not therefrom quick obtaining need money
Source wastes more times when automobile breaks down instead, so that the treatment effeciency of accident is low.
To solve the above-mentioned problems, the embodiment of the present application provides a kind of video acquisition management method, and server, which obtains, to be come
From different terminal equipment for instructing the video of breakdown maintenance, then in order to carry out control to the quality in the video, comform
Acquire the high-quality video of needs in the video more got, and push the event to user further according to the acquisition request of user
Barrier maintenance video, then receive the feedback of user again, to provide a kind of for the breakdown maintenance video for instructing auto repair
Video acquisition management method, thus for instructing the breakdown maintenance video of auto repair to provide a kind of efficient video acquisition pipe
Reason method allows users to quickly suit the remedy to the case to the failure of automobile using the breakdown maintenance video of precision, therefore effectively
The efficiency for improving accident treatment optionally can also collect the content after breakdown maintenance video also according to video again
Video is further optimized, is with higher readable and clearer video by Video Quality Metric.
In order to more fully understand the embodiment of the present application, will be situated between below to the method for application the embodiment of the present application
It continues, the embodiment of the present application can be applied in the scene of video acquisition processing.
Server adaper is first acquired video.Specifically, server receives the view uploaded from different terminal equipment
Frequently, which is for instructing user to carry out vehicle failure maintenance.Then in order to carry out control to the quality in the video, then
The video of high quality is targetedly therefrom acquired as breakdown maintenance video, specifically, the video that can be will acquire and service
The video that device has acquired is matched, and is regarded as plagiarizing if being matched to the high video of similarity and not be acquired.There are also one
The method of the quality of kind control video is, using the content in deep learning Network Recognition video, to contain if recognizing in video
It is accused of also not acquiring for content against the form of the statute, such as drugs, gambling, uncultivated behavior speech and weapon etc..
Other than the quality of control video when acquiring video, server can also be adopted according to the classification of video
Collect video, i.e. server classifies to collected video according to the classification of the video recognized, wherein classification can be
Automobile model or maintenance gimmick etc..Then the subsequent content to collected video carry out it is detailed identification and extraction
When, it is identified using different deep learning Network Recognitions according to the difference of video generic.It needs to illustrate
It is that the deep neural network of function subdivision has more powerful image processing function, the video processing for the classification being directed to it
Ability is greater than the neural convolutional network of non-function subdivision, therefore can preferably identify the content in different classes of video.
Server also needs to optimize video after collecting video, it is intended to improve the clarity of video and readable
Property.Specifically, being recognized after server by utilizing deep learning network is to the identification of collected video progress content using this
Content video is optimized, the content recognized includes maintenance step, maintenance tool and/or auto parts, such as is identified
The maintenance step of the content arrived is " to open front cover for vehicle；Find turning machine；Check that the rubber limit in turning machine groove is blocky
State；Replace new rubber limited block, or adjustment rubber limited block position；Check whether vehicle steering wheel becomes a full member ", it recognizes
The maintenance tool of content is " rice word screwdriver ", and the auto parts of the content recognized are " rubber limited block ".
In order to improve the readability of video, server adds label to breakdown maintenance video according to the content of video, so that
User is not switched on video can know the approximate contents of video according to the label of video.Likewise, the content based on video is given
Screen labels but also video is based on its label by systematization, it is easier to it is accurately searched by user, it is specifically, general to be
In the search information searching video inputted according to user, what can only be contained according to the title and video of video artificially sets system
The most matched video of information is searched and searched for the label set, and based on the content of video to breakdown maintenance in for the application
Video adds for label, and label is richer, and common people may can not find very proper keyword when search,
But more can take into account some expression in relation to video content, such label also more meets the thinking mode of people, passes through
Machine learning identifies that the content of video also can be more comprehensive than the content manually added, careful and accurate, therefore user is just
Can use vernacular language it is easier search corresponding video, also correspond to the readability for improving video.
For example, if the interior of the video that server recognizes has " rubber limited block ", " rice word screwdriver " " is opened
Front cover for vehicle " and " carrying out safety to automobile to inspect " etc., then can stamp " rubber limited block ", " rice word screwdriver " to video
And/or labels such as " inspecting safely ".
In order to further improve the readability of video, server obtains sound according to the maintenance step in the content recognized
Frequency information and/or caption information, then by audio-frequency information and/or caption information in conjunction with breakdown maintenance video.
For example, it is " to open front cover for vehicle that server, which recognizes the maintenance step of the content of video,；Find turning machine；
Check the rubber limit bulk state in turning machine groove；Replace new rubber limited block, or adjustment rubber limited block position；It looks into
See whether vehicle steering wheel becomes a full member ", then audio can be generated according to the maintenance step with server, or generate subtitling format
Subtitle, then subtitle and audio & video are synthesized again, audio and subtitle can play explanation to video, then using
Family can better understand and grasp the method for maintaining in video by the audio or subtitle when watching the video, from
And improve the treatment effeciency of accident.
In order to improve the clarity of video, server identifies and obtains the fuzzy frame in video, then identifies that this is fuzzy again
Maintenance tool and/or auto parts in frame, then by the fuzzy frame maintenance tool and/or auto parts be substituted for it is corresponding
Standard picture, the standard picture are obtained in the perhaps cloud device being locally stored in server or are set from other terminals
The maintenance tool template and/or auto parts template of standby middle acquisition.
For example, in one section of video in screen contain multiple fuzzy frames, then in order to enable watch video user
It is enough clearly to see maintenance tool or auto parts crucial in screen, it can be from the maintenance in being locally stored of server
Tool palette and/or auto parts template come corresponding maintenance tool or auto parts in fuzzy frame, due to maintenance tool mould
Plate and auto parts template are the images more visible relative to script fuzzy frame image quality, therefore after above-mentioned replacement operation, can
To improve the clarity of video.
Then breakdown maintenance video is being collected, and according to the content of breakdown maintenance video to the content of breakdown maintenance video
It carries out after further optimizing, the acquisition request that reception user utilizes terminal device to send, which includes search event
The key message of barrier maintenance video, the key message include crucial words or sentence etc., and then server is receiving user
Acquisition request after corresponding breakdown maintenance video can be found according to key message therein, and push the event to user
Barrier maintenance video, then user repairs automobile under the guidance for the auto repair method that the breakdown maintenance video includes,
To which user can quickly suit the remedy to the case to the failure of automobile using the breakdown maintenance video of precision, then user can be with
It scores the breakdown maintenance video got, then server can be according to the breakdown maintenance video for receiving user feedback
Scoring breakdown maintenance video is ranked up, then from now on to preferential in the corresponding breakdown maintenance video of identical key message
Select breakdown maintenance video push in the top to user.Corresponding breakdown maintenance video is wherein searched according to key message
Method includes accurate inquiry or fuzzy query etc., and the embodiment of the present application does not limit this.
The application can with directionality acquisition it is high-quality and fining breakdown maintenance video, further according to user request to
Family pushes video maintenance video, and user can be using the breakdown maintenance video of precision, under quickly suiting the medicine to the illness to the failure of automobile
Medicine, in addition to this, the application can also carry out into one breakdown maintenance video according to the content of collected breakdown maintenance video
The optimization of step, the breakdown maintenance video then optimized can preferably instruct user to carry out auto repair, in addition, server is also
User be can receive to the feedback of the breakdown maintenance video of push, then server can be according to the feedback adjustment of user for view
The comprehensive score of frequency quality, and the producer etc. of award video, so that it is more high-quality to attract more video production persons to upload
Breakdown maintenance video, and according to scoring video in the top is pushed to user, to provide a kind of view of higher efficiency
Frequency acquisition management method.As a whole, video acquisition management method provided by the present application can help user to obtain in a short time
It takes and understands breakdown maintenance video, car owner can be removed from order to search and understand breakdown maintenance video and waste the plenty of time, because
This improves the treatment effeciency of accident.
Referring to Fig. 1, Fig. 1 is the schematic flow diagram of a video acquisition management method disclosed in the embodiment of the present application, such as scheme
Shown method can include:
101: acquisition breakdown maintenance video.
In the embodiment of the present application, breakdown maintenance video is the video for instructing the audient of viewing to carry out auto repair,
And above-mentioned acquisition fault video refers to that server judges the quality of the target video received, determines whether it is
The video for the high quality for needing to acquire, if could acquire as breakdown maintenance video, then acquisition breakdown maintenance video it
Before, server needs to receive target video, wherein target video is the video that any terminal device is uploaded to server.
It should be noted that the measurement standard of high quality includes whether as original video, if contain violation content, if
Clearly, whether the user of uploaded videos is certification user (by the user of Professional Certification or real-name authentication) etc..
For example, judge whether target video is original video, specifically, after server receives target video
Preliminary identification is carried out to target video, and the similar view for being higher than preset value to the target video similarity is searched in video library
Frequently, similar video if it does not exist then acquires above-mentioned target video as failure then illustrating that above-mentioned target video is original video
Video is repaired, similar video, does not acquire above-mentioned target video then if it exists.
It should be noted that the above-mentioned content to video carry out preliminary knowledge method for distinguishing be using server to video into
Row image procossing includes that image recognition technology neural network based, the image based on wavelet moment are known including image processing techniques
Other technology and the image recognition technology based on fractal characteristic etc..
Also it should be noted that, when acquiring breakdown maintenance video, one in above-mentioned measurement standard can be used simultaneously
A or multiple, the application limits not to this.
Optionally, breakdown maintenance video is acquired according to classification when acquiring breakdown maintenance video.
In the embodiment of the present application, when can also be acquired to breakdown maintenance video, to the content of breakdown maintenance video
Preliminary identification is carried out, several major class are divided into according to its content, which can be the type of vehicle and the component that need to be repaired
It can be the model of automobile Deng, wherein the type of vehicle, the size (patronage or pay load etc.) of automobile, automobile
Purposes (carrying, cargo transport, fire-fighting or operation etc.), automobile power device type (internal combustion engine, electronic, jet-propelled, steam engine or
Person's solar energy etc.) and the road conditions (highway use, cross-country, mine, airport or building site) of running car etc..
102: the acquisition request for above-mentioned breakdown maintenance video of receiving terminal apparatus.
In the embodiment of the present application, after collecting breakdown maintenance video, which can be added to
In the video library of special storage breakdown maintenance video, then if asked when receiving the acquisition request of terminal device according to acquisition
Key message in asking searches most matched breakdown maintenance video, wherein acquisition request includes Terminal Equipment Identifier and crucial letter
Breath etc., and key message includes keyword, keyword and/or key sentence etc., it is also necessary to explanation, it is above-mentioned to be asked according to acquisition
Seeking the method for searching breakdown maintenance video includes precisely inquiry and fuzzy query etc., and the embodiment of the present application does not limit this.
Further, the content in above-mentioned breakdown maintenance video is identified.
In the present embodiment, the content of above-mentioned collected breakdown maintenance video is further identified, the identification
Method be image procossing to be carried out to video using server, including image processing techniques includes that image neural network based is known
Other technology, the image recognition technology based on wavelet moment and image recognition technology based on fractal characteristic etc., wherein what is recognized is interior
Hold includes maintenance step, maintenance tool and/or auto parts.
For example, maintenance step is " to open front cover for vehicle；Find turning machine；Check the rubber limit in turning machine groove
Position bulk state；Replace new rubber limited block, or adjustment rubber limited block position；Check whether vehicle steering wheel becomes a full member ", know
The maintenance tool for the content being clipped to is " rice word screwdriver ", and the auto parts of the content recognized are " rubber limited block ".
Optionally, the content in the above-mentioned breakdown maintenance video of deep learning Network Recognition is utilized.
It should be noted that deep learning network is the model that one kind can simulate that human brain carries out study analysis.It can use
In image procossing, principle is then to form more abstract high-rise expression attribute classification or feature by combining low-level feature,
It to find that the distributed nature of data indicates, therefore is a kind of based on the method for carrying out representative learning to data.Due to depth
Practising network constantly can be learnt and be updated according to the input data, therefore can be effectively iterated using big data
Upgrading reaches the traditional inaccessiable image processing efficiency of image recognition institute and accuracy.
It should be noted that deep learning network used in the embodiment of the present application can be newly-established by server
The framework of deep learning network, or the framework of existing deep learning network is obtained, then it is carried out using training sample
Training is to obtain, so that deep learning network after training is mature image processing model, it can be to breakdown maintenance video
In content identified well, wherein existing deep learning network for example has TensorFlow and Caffe etc..
Optionally, if acquiring above-mentioned breakdown maintenance video according to classification when acquiring breakdown maintenance video, difference is utilized
The different classes of breakdown maintenance video of deep learning Network Recognition in content.
In the optional way mentioned in the previous step, if when acquiring breakdown maintenance video according to classification acquisition failure dimension
Video is repaired, then then when the subsequent content to collected video carries out detailed identification and extracts, according to video institute
The difference for belonging to classification identifies it using different deep learning Network Recognitions.It should be noted that the depth of function subdivision
Spending neural network has more powerful image processing function, and it is thin that the ability of the video processing for the classification being directed to it is greater than non-function
The neural convolutional network divided, can preferably identify the content in different classes of video.
Further, it after identifying the content in above-mentioned breakdown maintenance video, is tieed up according to the above-mentioned failure of content optimization
Repair video.
In the embodiment of the present application, above-mentioned breakdown maintenance video is optimized according to above content, so that video becomes apparent from,
With more readability.Next several optimal ways will be enumerated, wherein content includes that content includes maintenance step, maintenance tool
And/or auto parts.
Optionally, label is added to above-mentioned breakdown maintenance video according to above content.
In the embodiment of the present application, can according in the content of breakdown maintenance video maintenance step, maintenance tool and/or
Auto parts add label to breakdown maintenance video, to increase the readable of breakdown maintenance video and be easier to be searched.
For example, if the interior of the video that server recognizes has " rubber limited block ", " rice word screwdriver " " is opened
Front cover for vehicle " and " carrying out safety to automobile to inspect " etc., then can stamp " rubber limited block ", " rice word screwdriver " to video
And/or labels such as " inspecting safely ".
Optionally, audio-frequency information and/or caption information are obtained according to maintenance step；By audio-frequency information and/or caption information
In conjunction with above-mentioned breakdown maintenance video.
In the embodiment of the present application, corresponding audio letter can be obtained by the maintenance step in the above-mentioned content recognized
Breath or caption information, then can obtain an existing content solution for audio-frequency information and subtitle in conjunction with breakdown maintenance video
The more perfect instructional video of subtitle is said and has, then user can be with by the audio or subtitle when watching the video
The method for maintaining in video is better understood and grasped, the readability of video is further improved.
For example, it is " to open front cover for vehicle that server, which recognizes the maintenance step of the content of video,；Find turning machine；
Check the rubber limit bulk state in turning machine groove；Replace new rubber limited block, or adjustment rubber limited block position；It looks into
See whether vehicle steering wheel becomes a full member ", then audio can be generated according to the maintenance step with server, or generate subtitling format
Subtitle, then subtitle and audio & video are synthesized again.
Optionally, the fuzzy frame in above-mentioned breakdown maintenance video is obtained；Identify the maintenance tool and/or automobile in fuzzy frame
Part；Obtain the maintenance tool and/or the corresponding standard picture of auto parts in fuzzy frame；Fuzzy frame is replaced using standard picture
In maintenance tool and/or auto parts.
Server identifies and obtains the fuzzy frame in video in the embodiment of the present application, is then identified in the fuzzy frame again
Maintenance tool and/or auto parts, then by the fuzzy frame maintenance tool and/or auto parts be substituted for corresponding standard drawing
Picture, the standard picture are obtained in the perhaps cloud device being locally stored in server or are obtained from other terminal devices
The maintenance tool template and/or auto parts template taken, by the way that the key message in fuzzy frame to be apparent to increase
The clarity and readability of video.
For example, in one section of video in screen contain multiple fuzzy frames, then in order to enable watch video user
It is enough clearly to see maintenance tool or auto parts crucial in screen, it can be from the maintenance in being locally stored of server
Tool palette and/or auto parts template come corresponding maintenance tool or auto parts in fuzzy frame, due to maintenance tool mould
Plate and auto parts template are the images more visible relative to script fuzzy frame image quality, therefore after above-mentioned replacement operation, can
To improve the clarity of video.
103: responding above-mentioned acquisition request, send above-mentioned breakdown maintenance video to above-mentioned terminal device.
In the embodiment of the present application, if server has received the acquisition request of terminal device, in can be based on essence
The querying methods such as quasi- inquiry or fuzzy query, find most matched breakdown maintenance video according to above-mentioned acquisition request, then
If above-mentioned breakdown maintenance video is exactly most matched breakdown maintenance video, above-mentioned acquisition request is responded, i.e., to above-mentioned terminal
Equipment sends the breakdown maintenance video.
104: receiving the feedback for above-mentioned breakdown maintenance video of above-mentioned terminal device.
In the embodiment of the present application, server can not only acquire and push breakdown maintenance video to other terminal devices,
It can feed back including scoring, evaluation, label, collection and turn with the feedback for breakdown maintenance video of receiving terminal apparatus
Hair etc., the embodiment of the present application does not limit this.
Further, server is according to the TOP SCORES of the above-mentioned breakdown maintenance video of above-mentioned feedback adjustment.
In the embodiment of the present application, server can be commented for the totality of above-mentioned different feedback adjustment breakdown maintenance video
Point, wherein the different corresponding different scoring adjustable strategies of feedback, for example, every forwarding or collection are primary, on TOP SCORES
0.2 point is adjusted, and if feedback includes scoring, in conjunction with the corresponding history scoring record of the breakdown maintenance video, calculate together
New TOP SCORES etc. to new average mark as the breakdown maintenance video.
Further, server is according to the corresponding label of the above-mentioned breakdown maintenance video of above-mentioned feedback adjustment.
In the embodiment of the present application, if above-mentioned feedback includes label, server can be above-mentioned according to the feedback adjustment
The label of breakdown maintenance video.
Further, server is according to the producer's of the feedback adjustment of the above-mentioned breakdown maintenance video breakdown maintenance video
Account information.
In the embodiment of the present application, server is after the feedback for obtaining above-mentioned breakdown maintenance video, according to the feedback meter
Calculation obtains the new TOP SCORES of the breakdown maintenance video, is then obtained according to the height in section of scoring belonging to the TOP SCORES
Corresponding amount of money award is obtained, then server is rewarded with the amount of money award, specifically to the producer for making the breakdown maintenance video
, account of the amount of money award to producer of transferring accounts from the account of the above-mentioned user for obtaining the breakdown maintenance video, Huo Zhecong
Amount of money award is transferred accounts to the account of producer in some tissue, group or the destiny account of company, and the embodiment of the present application is to this
Without limitation.
The embodiment of the present application can be with the breakdown maintenance video that the acquisition of directionality is high-quality and refines, further according to asking for user
It asks to user and pushes video maintenance video, user can be quick to the failure of automobile using the breakdown maintenance video of fining
It suits the remedy to the case, in addition to this, server can also receive user to the feedback of the breakdown maintenance video of push, and then server can
To be directed to the comprehensive score of video quality, and the producer etc. of award video according to the feedback adjustment of user, to attract more
More video production person uploads more good breakdown maintenance videos, and by breakdown maintenance video according to scoring ranking, to
User preferentially pushes video in the top when push, to provide a kind of video acquisition management method of higher efficiency.
As a whole, video acquisition management method provided by the present application can provide a user high-quality and fining breakdown maintenance view
Frequently, it is then able to that user is helped to obtain and understand breakdown maintenance video in a short time, saves car owner to search and understand event
The plenty of time for hindering maintenance video and wasting, therefore improve the treatment effeciency of accident.
Referring to Fig. 2, Fig. 2 is the schematic flow diagram of another kind video acquisition management method disclosed in the embodiment of the present application,
Method as shown in the figure can include:
201: acquisition breakdown maintenance video.
In the embodiment of the present application, breakdown maintenance video is the video for instructing the audient of viewing to carry out auto repair,
And above-mentioned acquisition fault video refers to that server judges the quality of the target video received, determines whether it is
The video for the high quality for needing to acquire, if could acquire as breakdown maintenance video, then acquisition breakdown maintenance video it
Before, server needs to receive target video, wherein target video is the video that any terminal device is uploaded to server.
It should be noted that the measurement standard of high quality includes whether as original video, if contain violation content, if
Clearly, whether the user of uploaded videos is certification user (by the user of Professional Certification or real-name authentication) etc..
For example, judge whether target video is original video, specifically, after server receives target video
Preliminary identification is carried out to target video, and the similar view for being higher than preset value to the target video similarity is searched in video library
Frequently, similar video if it does not exist then acquires above-mentioned target video as failure then illustrating that above-mentioned target video is original video
Video is repaired, similar video, does not acquire above-mentioned target video then if it exists.
It should be noted that the above-mentioned content to video carry out preliminary knowledge method for distinguishing be using server to video into
Row image procossing includes that image recognition technology neural network based, the image based on wavelet moment are known including image processing techniques
Other technology and the image recognition technology based on fractal characteristic etc..
Also it should be noted that, when acquiring breakdown maintenance video, one in above-mentioned measurement standard can be used simultaneously
A or multiple, the application limits not to this.
Optionally, breakdown maintenance video is acquired according to classification when acquiring breakdown maintenance video.
In the embodiment of the present application, when can also be acquired to breakdown maintenance video, to the content of breakdown maintenance video
Preliminary identification is carried out, several major class are divided into according to its content, which can be the type of vehicle and the component that need to be repaired
It can be the model of automobile Deng, wherein the type of vehicle, the size (patronage or pay load etc.) of automobile, automobile
Purposes (carrying, cargo transport, fire-fighting or operation etc.), automobile power device type (internal combustion engine, electronic, jet-propelled, steam engine or
Person's solar energy etc.) and the road conditions (highway use, cross-country, mine, airport or building site) of running car etc..
202: identifying the content in above-mentioned breakdown maintenance video.
In the present embodiment, the content of above-mentioned collected breakdown maintenance video is further identified, the identification
Method be image procossing to be carried out to video using server, including image processing techniques includes that image neural network based is known
Other technology, the image recognition technology based on wavelet moment and image recognition technology based on fractal characteristic etc., wherein what is recognized is interior
Hold includes maintenance step, maintenance tool and/or auto parts.
For example, maintenance step is " to open front cover for vehicle；Find turning machine；Check the rubber limit in turning machine groove
Position bulk state；Replace new rubber limited block, or adjustment rubber limited block position；Check whether vehicle steering wheel becomes a full member ", know
The maintenance tool for the content being clipped to is " rice word screwdriver ", and the auto parts of the content recognized are " rubber limited block ".
Optionally, the content in the above-mentioned breakdown maintenance video of deep learning Network Recognition is utilized.
It should be noted that deep learning network is the model that one kind can simulate that human brain carries out study analysis.It can use
In image procossing, principle is then to form more abstract high-rise expression attribute classification or feature by combining low-level feature,
It to find that the distributed nature of data indicates, therefore is a kind of based on the method for carrying out representative learning to data.Due to depth
Practising network constantly can be learnt and be updated according to the input data, therefore can be effectively iterated using big data
Upgrading reaches the traditional inaccessiable image processing efficiency of image recognition institute and accuracy.
It should be noted that deep learning network used in the embodiment of the present application can be newly-established by server
The framework of deep learning network, or the framework of existing deep learning network is obtained, then it is carried out using training sample
Training is to obtain, so that deep learning network after training is mature image processing model, it can be to breakdown maintenance video
In content identified well, wherein existing deep learning network for example has TensorFlow and Caffe etc..
Optionally, if acquiring above-mentioned breakdown maintenance video according to classification when acquiring breakdown maintenance video, difference is utilized
The different classes of breakdown maintenance video of deep learning Network Recognition in content.
In the optional way mentioned in the previous step, if when acquiring breakdown maintenance video according to classification acquisition failure dimension
Video is repaired, then then when the subsequent content to collected video carries out detailed identification and extracts, according to video institute
The difference for belonging to classification identifies it using different deep learning Network Recognitions.It should be noted that the depth of function subdivision
Spending neural network has more powerful image processing function, and it is thin that the ability of the video processing for the classification being directed to it is greater than non-function
The neural convolutional network divided, can preferably identify the content in different classes of video.
203: above-mentioned breakdown maintenance video is optimized according to above content.
In the embodiment of the present application, above-mentioned breakdown maintenance video is optimized according to above content, so that video becomes apparent from,
With more readability.Next several optimal ways will be enumerated, wherein content includes maintenance step, maintenance tool and/or automobile
Part.
Optionally, label is added to above-mentioned breakdown maintenance video according to above content.
In the embodiment of the present application, can according in the content of breakdown maintenance video maintenance step, maintenance tool and/or
Auto parts add label to breakdown maintenance video, to increase the readable of breakdown maintenance video and be easier to be searched.
For example, if the interior of the video that server recognizes has " rubber limited block ", " rice word screwdriver " " is opened
Front cover for vehicle " and " carrying out safety to automobile to inspect " etc., then can stamp " rubber limited block ", " rice word screwdriver " to video
And/or labels such as " inspecting safely ".
Optionally, audio-frequency information and/or caption information are obtained according to maintenance step；By audio-frequency information and/or caption information
In conjunction with above-mentioned breakdown maintenance video.
In the embodiment of the present application, corresponding audio letter can be obtained by the maintenance step in the above-mentioned content recognized
Breath or caption information, then can obtain an existing content solution for audio-frequency information and subtitle in conjunction with breakdown maintenance video
The more perfect instructional video of subtitle is said and has, then user can be with by the audio or subtitle when watching the video
The method for maintaining in video is better understood and grasped, the readability of video is further improved.
For example, it is " to open front cover for vehicle that server, which recognizes the maintenance step of the content of video,；Find turning machine；
Check the rubber limit bulk state in turning machine groove；Replace new rubber limited block, or adjustment rubber limited block position；It looks into
See whether vehicle steering wheel becomes a full member ", then audio can be generated according to the maintenance step with server, or generate subtitling format
Subtitle, then subtitle and audio & video are synthesized again.
Optionally, the fuzzy frame in above-mentioned breakdown maintenance video is obtained；Identify the maintenance tool and/or automobile in fuzzy frame
Part；Obtain the maintenance tool and/or the corresponding standard picture of auto parts in fuzzy frame；Fuzzy frame is replaced using standard picture
In maintenance tool and/or auto parts.
Server identifies and obtains the fuzzy frame in video in the embodiment of the present application, is then identified in the fuzzy frame again
Maintenance tool and/or auto parts, then by the fuzzy frame maintenance tool and/or auto parts be substituted for corresponding standard drawing
Picture, the standard picture are obtained in the perhaps cloud device being locally stored in server or are obtained from other terminal devices
The maintenance tool template and/or auto parts template taken, by the way that the key message in fuzzy frame to be apparent to increase
The clarity and readability of video.
For example, in one section of video in screen contain multiple fuzzy frames, then in order to enable watch video user
It is enough clearly to see maintenance tool or auto parts crucial in screen, it can be from the maintenance in being locally stored of server
Tool palette and/or auto parts template come corresponding maintenance tool or auto parts in fuzzy frame, due to maintenance tool mould
Plate and auto parts template are the images more visible relative to script fuzzy frame image quality, therefore after above-mentioned replacement operation, can
To improve the clarity of video.
204: the acquisition request for above-mentioned breakdown maintenance video of receiving terminal apparatus.
In the embodiment of the present application, after collecting breakdown maintenance video, which can be added to
In the video library of special storage breakdown maintenance video, then if asked when receiving the acquisition request of terminal device according to acquisition
Key message in asking is matched with the label of breakdown maintenance video, instructs user to solve user with most probable to find
Described breakdown maintenance video, wherein acquisition request includes Terminal Equipment Identifier and key message etc., and key message includes
Keyword, keyword and/or key sentence etc., it is also necessary to explanation, it is above-mentioned that breakdown maintenance video is searched according to acquisition request
Method includes precisely inquiry and fuzzy query etc., and the embodiment of the present application does not limit this.
205: responding above-mentioned acquisition request, send above-mentioned breakdown maintenance video to above-mentioned terminal device.
In the embodiment of the present application, if server has received the acquisition request of terminal device, in can be based on essence
The querying methods such as quasi- inquiry or fuzzy query, find most matched breakdown maintenance video according to above-mentioned acquisition request, then
If above-mentioned breakdown maintenance video is exactly most matched breakdown maintenance video, above-mentioned acquisition request is responded, i.e., to above-mentioned terminal
Equipment sends the breakdown maintenance video.
206: receiving the feedback for above-mentioned breakdown maintenance video of above-mentioned terminal device.
In the embodiment of the present application, server can not only acquire and push breakdown maintenance video to other terminal devices,
It can feed back including scoring, evaluation, label, collection and turn with the feedback for breakdown maintenance video of receiving terminal apparatus
Hair etc., the embodiment of the present application does not limit this.
Further, server is according to the TOP SCORES of the above-mentioned breakdown maintenance video of above-mentioned feedback adjustment.
In the embodiment of the present application, server can be commented for the totality of above-mentioned different feedback adjustment breakdown maintenance video
Point, wherein the different corresponding different scoring adjustable strategies of feedback, for example, every forwarding or collection are primary, on TOP SCORES
0.2 point is adjusted, and if feedback includes scoring, in conjunction with the corresponding history scoring record of the breakdown maintenance video, calculate together
New TOP SCORES etc. to new average mark as the breakdown maintenance video.
Further, server is according to the corresponding label of the above-mentioned breakdown maintenance video of above-mentioned feedback adjustment.
In the embodiment of the present application, if above-mentioned feedback includes label, server can be above-mentioned according to the feedback adjustment
The label of breakdown maintenance video.
Further, server is according to the producer's of the feedback adjustment of the above-mentioned breakdown maintenance video breakdown maintenance video
Account information.
In the embodiment of the present application, server is after the feedback for obtaining above-mentioned breakdown maintenance video, according to the feedback meter
Calculation obtains the new TOP SCORES of the breakdown maintenance video, is then obtained according to the height in section of scoring belonging to the TOP SCORES
Corresponding amount of money award is obtained, then server is rewarded with the amount of money award, specifically to the producer for making the breakdown maintenance video
, account of the amount of money award to producer of transferring accounts from the account of the above-mentioned user for obtaining the breakdown maintenance video, Huo Zhecong
Amount of money award is transferred accounts to the account of producer in some tissue, group or the destiny account of company, and the embodiment of the present application is to this
Without limitation.
The embodiment of the present application is opposite with for a upper inventive embodiments, in addition to acquiring breakdown maintenance video, pushes to user
Breakdown maintenance video and reception user are directed to except the feedback of the breakdown maintenance video, can also be according to breakdown maintenance video
Content further optimizes breakdown maintenance video, so that the content of breakdown maintenance video is easier to by the understanding of user simultaneously
User is preferably instructed to carry out auto repair, in addition to this it is possible to be acquired according to classification to breakdown maintenance video, then
Different classes of breakdown maintenance video is identified using different deep learning networks, therefore since the embodiment of the present application is adopted
Deep learning network constantly can be learnt and be updated according to the input data, can effectively using big data into
Row iteration upgrading reaches the traditional inaccessiable image processing efficiency of image recognition technology institute and accuracy.And why
Different classes of breakdown maintenance video is identified using different deep learning networks, is the depth because of function subdivision
Neural network has more powerful image processing function, and the processing capacity of the video for the classification being directed to it is segmented greater than non-function
Neural convolutional network, can preferably identify the content in different classes of video.Therefore the embodiment of the present application can be more accurately
It identifies the content of breakdown maintenance video, and can preferably optimize breakdown maintenance video using the more accurate content, to be promoted
The readability and clarity of breakdown maintenance video are searched but also video is based on label by systematization to more shorten user
With the time for understanding breakdown maintenance video, the treatment effeciency of accident is further increased.
The embodiment of the present application also provides a kind of server, which is used to execute the unit of any one of aforementioned method.Tool
Body, it is a kind of schematic block diagram of server provided by the embodiments of the present application referring to Fig. 3.The server of the present embodiment includes: to adopt
Collect unit 310, receiving unit 320 and response unit 330, specific:
Acquisition unit 310, for acquiring breakdown maintenance video；
Receiving unit 320, the acquisition request for above-mentioned breakdown maintenance video for receiving terminal apparatus；It is also used to connect
Receive the feedback for above-mentioned breakdown maintenance video of above-mentioned terminal device；
Response unit 330 sends above-mentioned breakdown maintenance video to above-mentioned terminal device for responding above-mentioned acquisition request.
Further, above-mentioned receiving unit 320, is also used to receive target video.
Correspondingly, above-mentioned server further includes searching unit 340, for searching and above-mentioned target video phase in video library
It is higher than the similar video of preset value like degree；Above-mentioned acquisition unit 310 then acquires above-mentioned for above-mentioned similar video if it does not exist
Target video is as breakdown maintenance video.
Further, above-mentioned server further includes recognition unit 350, interior in above-mentioned breakdown maintenance video for identification
Hold；Optimize unit 360, for optimizing above-mentioned breakdown maintenance video according to above content.
Specifically, above-mentioned recognition unit 350, for utilizing in the above-mentioned breakdown maintenance video of deep learning Network Recognition
Hold, content includes maintenance step, maintenance tool and/or auto parts.
Specifically, above-mentioned optimization unit 360, for obtaining audio-frequency information and/or caption information according to above-mentioned maintenance step；
It is also used to above-mentioned audio-frequency information and/or above-mentioned caption information in conjunction with above-mentioned breakdown maintenance video.
Further, above-mentioned server further includes acquiring unit 370, fuzzy in above-mentioned breakdown maintenance video for obtaining
Frame；The corresponding standard picture of maintenance tool and/or auto parts for being also used to obtain in above-mentioned fuzzy frame；
Correspondingly, above-mentioned optimization unit 360, is also used to replace the maintenance mans in above-mentioned fuzzy frame using above-mentioned standard image
Tool and/or auto parts.
Optionally, above-mentioned optimization unit 360, for adding label to above-mentioned breakdown maintenance video according to above content.
In the embodiment of the present application, the acquisition unit in server can failure high-quality with the acquisition of directionality and fining
Video is repaired, then receiving unit receives the acquisition request of user, is then responding to unit and pushes according to the acquisition request to user
The video repairs video, allows users to quickly suit the remedy to the case to the failure of automobile using the breakdown maintenance video of precision.
In addition to this, server can also receive user to the feedback of the breakdown maintenance video of push by receiving unit, then service
Device can be directed to the comprehensive score of video quality, and the producer etc. of award video according to the feedback adjustment of user, to inhale
Draw more video production persons and upload more good breakdown maintenance videos, and is pushed to user according to scoring in the top
Video, to provide a kind of video acquisition management method of higher efficiency.As a whole, video acquisition management provided by the present application
Method can provide a user it is high-quality and fining breakdown maintenance video, be then able to help user obtains in a short time with
Understand breakdown maintenance video, car owner can be removed from order to search and understand breakdown maintenance video and waste the plenty of time, therefore mentioned
The high treatment effeciency of accident.
Referring to FIG. 4, the embodiment of the present application provides another server, including one or more processor
410, communication interface 420 and memory 430, processor 410, communication interface 420 and memory 430 are mutual by bus 440
Connection, wherein memory 430 is for storing computer program, and computer program includes program instruction, and processor 410 is configured
It is instructed for caller, specific to execute the method such as above-mentioned inventive embodiments:
Communication interface 420 is used to execute the function of acquisition unit 310, for acquiring breakdown maintenance video；It is also used to execute
The function of receiving unit 320 is also used to receive for the acquisition request for above-mentioned breakdown maintenance video of receiving terminal apparatus
The feedback for above-mentioned breakdown maintenance video of above-mentioned terminal device；It is also used to execute the function of response unit 330, for responding
Above-mentioned acquisition request sends above-mentioned breakdown maintenance video to above-mentioned terminal device.
Processor 410, for executing the function of searching unit 340, for being searched and above-mentioned target video in video library
Similarity is higher than the similar video of preset value；It is also used to execute the function of recognition unit 350, for identification above-mentioned breakdown maintenance view
Content in frequency；It is also used to execute the function of optimization unit 360, for optimizing above-mentioned breakdown maintenance video according to above content.
Specifically, above-mentioned processor 410, for utilizing in the above-mentioned breakdown maintenance video of deep learning Network Recognition
Hold, content includes maintenance step, maintenance tool and/or auto parts；For according to above-mentioned maintenance step obtain audio-frequency information and/
Or caption information；It is also used to above-mentioned audio-frequency information and/or above-mentioned caption information in conjunction with above-mentioned breakdown maintenance video.
Further, above-mentioned communication interface 420, is also used to receive target video；It is also used to above-mentioned similar view if it does not exist
Frequently, then above-mentioned target video is acquired as breakdown maintenance video.
Further, above-mentioned processor 410 is also used to execute the function of acquiring unit 370, for obtaining above-mentioned failure dimension
Repair the fuzzy frame in video；The corresponding standard picture of maintenance tool and/or auto parts for being also used to obtain in above-mentioned fuzzy frame；
It is also used to replace the maintenance tool and/or auto parts in above-mentioned fuzzy frame using above-mentioned standard image；It is also used to according to above-mentioned
Content adds label to above-mentioned breakdown maintenance video.
It should be appreciated that in the embodiment of the present application, alleged processor 410 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at
Reason device is also possible to any conventional processor etc..
The memory 430 may include read-only memory and random access memory, and to processor 410 provide instruction and
Data.The a part of of memory 430 can also include nonvolatile RAM.For example, memory 430 can also be deposited
Store up the information of device type.
In the specific implementation, processor 410, communication interface 420 described in the embodiment of the present application and memory 430 can
Execute reality described in the first embodiment and second embodiment of the method for video acquisition management provided by the embodiments of the present application
Existing mode, also can be performed the implementation of terminal device described in the embodiment of the present application, details are not described herein.
The embodiment of the present application also provides a kind of computer readable storage mediums, which is characterized in that computer storage medium
It is stored with computer program, computer program includes program instruction, and program instruction is executed by processor, to execute such as above-mentioned hair
The method of bright embodiment.
Computer readable storage medium can be the internal storage unit of the server of aforementioned any embodiment, such as service
The hard disk or memory of device.Computer readable storage medium is also possible to the External memory equipment of server, such as matches on server
Standby plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD)
Card, flash card (Flash Card) etc..Further, computer readable storage medium can also have been deposited both the inside including server
Storage unit also includes External memory equipment.Computer readable storage medium is for storing needed for computer program and server
Other programs and data.Computer readable storage medium can be also used for temporarily storing the number that has exported or will export
According to.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond scope of the present application.
It is apparent to those skilled in the art that for convenience of description and succinctly, the clothes of foregoing description
The specific work process of business device and unit, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed server and method can pass through
Other modes are realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, only
For a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine
Or it is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of device or unit
It connects, is also possible to electricity, mechanical or other form connections.
Unit may or may not be physically separated as illustrated by the separation member, shown as a unit
Component may or may not be physical unit, it can and it is in one place, or may be distributed over multiple networks
On unit.It can select some or all of unit therein according to the actual needs to realize the mesh of the embodiment of the present application scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, is also possible to two or more units and is integrated in one unit.It is above-mentioned integrated
Unit both can take the form of hardware realization, can also realize in the form of software functional units.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer readable storage medium.Based on this understanding, the technical solution of the application substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
The all or part of (can be personal computer, server or the network equipment etc.) execution each embodiment method of the application
Step.And storage medium above-mentioned include: USB flash disk, it is mobile hard disk, read-only memory (ROM, Read-Only Memory), random
Access various Jie that can store program code such as memory (RAM, Random Access Memory), magnetic or disk
Matter.
Claims (10)
1. a kind of video acquisition management method, which is characterized in that the described method includes:
Acquire breakdown maintenance video；
The acquisition request for the breakdown maintenance video of receiving terminal apparatus；
The acquisition request is responded, sends the breakdown maintenance video to the terminal device；
Receive the feedback for the breakdown maintenance video of the terminal device.
2. the method according to claim 1, wherein the acquisition breakdown maintenance video includes:
Receive target video；
The similar video for being higher than preset value with the target video similarity is searched in video library；
The similar video if it does not exist then acquires the target video as the breakdown maintenance video.
3. the method according to claim 1, wherein the reception is eventually after the acquisition breakdown maintenance video
Before the acquisition request of end equipment, further includes:
Identify the content in the breakdown maintenance video；
According to breakdown maintenance video described in the content optimization.
4. according to the method described in claim 3, it is characterized in that, the content identified in the breakdown maintenance video, packet
It includes:
Using the content in breakdown maintenance video described in deep learning Network Recognition, the content includes maintenance step, maintenance mans
Tool and/or auto parts.
5. according to the method described in claim 4, it is characterized in that, the breakdown maintenance according to the content optimization regards
Frequently, comprising:
Audio-frequency information and/or caption information are obtained according to the maintenance step；
By the audio-frequency information and/or the caption information in conjunction with the breakdown maintenance video.
6. according to the method described in claim 4, it is characterized in that, the breakdown maintenance according to the content optimization regards
Frequently, comprising:
Obtain the fuzzy frame in the breakdown maintenance video；
Obtain the maintenance tool and/or the corresponding standard picture of auto parts in the fuzzy frame；
The maintenance tool and/or auto parts in the fuzzy frame are replaced using the standard picture.
7. according to method described in claim 3~6 any one, which is characterized in that described according to the content optimization
Breakdown maintenance video includes:
Label is added to the breakdown maintenance video according to the content.
8. a kind of server characterized by comprising
Acquisition unit, for acquiring breakdown maintenance video；
Receiving unit, the acquisition request for the breakdown maintenance video for receiving terminal apparatus；It is also used to receive described
The feedback for the breakdown maintenance video of terminal device；
Response unit sends the breakdown maintenance video to the terminal device for responding the acquisition request.
9. a kind of server, which is characterized in that including maintaining apparatus, communication interface and memory, the processor, communication interface
It is connected with each other with memory by bus, wherein for storing computer program, the computer program includes the memory
Program instruction, the processor is configured for calling described program instruction, to execute as described in claim any one of 1-7
Method.
10. a kind of computer readable storage medium, which is characterized in that the computer storage medium is stored with computer program,
The computer program includes program instruction, and described program instruction is executed by processor, to execute as claim 1-7 is any
Method described in.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810684525.XA CN109005382A (en) | 2018-06-27 | 2018-06-27 | A kind of video acquisition management method and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810684525.XA CN109005382A (en) | 2018-06-27 | 2018-06-27 | A kind of video acquisition management method and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109005382A true CN109005382A (en) | 2018-12-14 |
Family
ID=64601376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810684525.XA Pending CN109005382A (en) | 2018-06-27 | 2018-06-27 | A kind of video acquisition management method and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109005382A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109871963A (en) * | 2019-01-08 | 2019-06-11 | 西藏纳旺网络技术有限公司 | Operation troubles restoring method, device, electronic equipment and storage medium |
| CN109982134A (en) * | 2019-02-27 | 2019-07-05 | 深圳市轱辘汽车维修技术有限公司 | A kind of video teaching method based on diagnostic device, diagnostic device and system |
| CN110688570A (en) * | 2019-09-19 | 2020-01-14 | 上海车仁堂信息科技有限公司 | DIY automobile self-maintenance method, device and system based on artificial intelligence technology |
| CN110751750A (en) * | 2019-09-20 | 2020-02-04 | 深圳市轱辘汽车维修技术有限公司 | Data processing method and device |
| CN110996124A (en) * | 2019-12-20 | 2020-04-10 | 北京百度网讯科技有限公司 | Original video determination method and related equipment |
| CN111091246A (en) * | 2019-12-23 | 2020-05-01 | 华自科技股份有限公司 | Path planning method and device, computer equipment and storage medium |
| CN112182364A (en) * | 2020-09-11 | 2021-01-05 | 上海仙塔智能科技有限公司 | Vehicle scheme sharing method, server and computer storage medium |
| CN113596378A (en) * | 2021-07-13 | 2021-11-02 | 安庆市电匠院网络科技有限公司 | Remote one-key calling type household appliance maintenance service system |
| EP4250193A1 (en) * | 2022-03-25 | 2023-09-27 | Koninklijke Philips N.V. | Ghost mode glasses for use in servicing medical devices and servicing workflows using same |
| WO2023180050A1 (en) * | 2022-03-25 | 2023-09-28 | Koninklijke Philips N.V. | Ghost mode glasses for use in servicing medical devices and servicing workflows using same |
| WO2024072797A1 (en) * | 2022-09-29 | 2024-04-04 | Nvidia Corporation | Improved frame selection for streaming applications |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110150327A1 (en) * | 2009-12-18 | 2011-06-23 | Electronics And Telecommunications Research Institute | Method and apparatus for masking privacy area of image |
| CN105426854A (en) * | 2015-11-24 | 2016-03-23 | 大连楼兰科技股份有限公司 | Vehicle identification number and part code-based vehicle part identification and display method as well as intelligent glasses for realizing method |
| CN105488232A (en) * | 2016-01-26 | 2016-04-13 | 程志勇 | Graphical display method for breakdown maintenance of electronic equipment |
| CN105718547A (en) * | 2016-01-18 | 2016-06-29 | 传成文化传媒（上海）有限公司 | Tour guide method and system based on scenic spot label |
| CN106708949A (en) * | 2016-11-25 | 2017-05-24 | 成都三零凯天通信实业有限公司 | Identification method of harmful content of video |
| CN107690673A (en) * | 2017-08-24 | 2018-02-13 | 深圳前海达闼云端智能科技有限公司 | Image processing method and device and server |
-
2018
- 2018-06-27 CN CN201810684525.XA patent/CN109005382A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110150327A1 (en) * | 2009-12-18 | 2011-06-23 | Electronics And Telecommunications Research Institute | Method and apparatus for masking privacy area of image |
| CN105426854A (en) * | 2015-11-24 | 2016-03-23 | 大连楼兰科技股份有限公司 | Vehicle identification number and part code-based vehicle part identification and display method as well as intelligent glasses for realizing method |
| CN105718547A (en) * | 2016-01-18 | 2016-06-29 | 传成文化传媒（上海）有限公司 | Tour guide method and system based on scenic spot label |
| CN105488232A (en) * | 2016-01-26 | 2016-04-13 | 程志勇 | Graphical display method for breakdown maintenance of electronic equipment |
| CN106708949A (en) * | 2016-11-25 | 2017-05-24 | 成都三零凯天通信实业有限公司 | Identification method of harmful content of video |
| CN107690673A (en) * | 2017-08-24 | 2018-02-13 | 深圳前海达闼云端智能科技有限公司 | Image processing method and device and server |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109871963A (en) * | 2019-01-08 | 2019-06-11 | 西藏纳旺网络技术有限公司 | Operation troubles restoring method, device, electronic equipment and storage medium |
| CN109982134B (en) * | 2019-02-27 | 2022-05-10 | 深圳市轱辘车联数据技术有限公司 | Video teaching method based on diagnosis equipment, diagnosis equipment and system |
| CN109982134A (en) * | 2019-02-27 | 2019-07-05 | 深圳市轱辘汽车维修技术有限公司 | A kind of video teaching method based on diagnostic device, diagnostic device and system |
| CN110688570A (en) * | 2019-09-19 | 2020-01-14 | 上海车仁堂信息科技有限公司 | DIY automobile self-maintenance method, device and system based on artificial intelligence technology |
| CN110751750A (en) * | 2019-09-20 | 2020-02-04 | 深圳市轱辘汽车维修技术有限公司 | Data processing method and device |
| CN110751750B (en) * | 2019-09-20 | 2022-06-17 | 深圳市轱辘车联数据技术有限公司 | Data processing method and device |
| CN110996124B (en) * | 2019-12-20 | 2022-02-08 | 北京百度网讯科技有限公司 | Original video determination method and related equipment |
| CN110996124A (en) * | 2019-12-20 | 2020-04-10 | 北京百度网讯科技有限公司 | Original video determination method and related equipment |
| CN111091246A (en) * | 2019-12-23 | 2020-05-01 | 华自科技股份有限公司 | Path planning method and device, computer equipment and storage medium |
| CN111091246B (en) * | 2019-12-23 | 2023-09-12 | 华自科技股份有限公司 | Path planning method, path planning device, computer equipment and storage medium |
| CN112182364A (en) * | 2020-09-11 | 2021-01-05 | 上海仙塔智能科技有限公司 | Vehicle scheme sharing method, server and computer storage medium |
| CN113596378A (en) * | 2021-07-13 | 2021-11-02 | 安庆市电匠院网络科技有限公司 | Remote one-key calling type household appliance maintenance service system |
| EP4250193A1 (en) * | 2022-03-25 | 2023-09-27 | Koninklijke Philips N.V. | Ghost mode glasses for use in servicing medical devices and servicing workflows using same |
| WO2023180050A1 (en) * | 2022-03-25 | 2023-09-28 | Koninklijke Philips N.V. | Ghost mode glasses for use in servicing medical devices and servicing workflows using same |
| WO2024072797A1 (en) * | 2022-09-29 | 2024-04-04 | Nvidia Corporation | Improved frame selection for streaming applications |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109005382A (en) | A kind of video acquisition management method and server | |
| CN110147726B (en) | Service quality inspection method and device, storage medium and electronic device | |
| CN104503998B (en) | For the kind identification method and device of user query sentence | |
| CN108984650B (en) | Computer-readable recording medium and computer device | |
| CN107357787B (en) | Semantic interaction method and device and electronic equipment | |
| CN107562918A (en) | A kind of mathematical problem knowledge point discovery and batch label acquisition method | |
| CN110795532A (en) | Voice information processing method and device, intelligent terminal and storage medium | |
| CN106383875A (en) | Artificial intelligence-based man-machine interaction method and device | |
| CN110489527A (en) | Banking intelligent consulting based on interactive voice and handle method and system | |
| CN110875039B (en) | Speech recognition method and device | |
| WO2020055128A2 (en) | Method and system for providing voice guidance based public transportation route guidance service | |
| CN104462064A (en) | Method and system for prompting content input in information communication of mobile terminals | |
| CN110019617B (en) | Method and device for determining address identifier, storage medium and electronic device | |
| CN104731873A (en) | Evaluation information generation method and device | |
| CN112765974A (en) | Service assisting method, electronic device and readable storage medium | |
| CN109359299A (en) | A kind of internet of things equipment ability ontology based on commodity data is from construction method | |
| CN112148874A (en) | Intention identification method and system capable of automatically adding potential intention of user | |
| CN107291774A (en) | Error sample recognition methods and device | |
| CN110222139A (en) | Road solid data De-weight method, calculates equipment and medium at device | |
| CN113837907A (en) | Man-machine interaction system and method for English teaching | |
| CN116467607B (en) | Information matching method and storage medium | |
| CN114528851B (en) | Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium | |
| CN111198978A (en) | Information processing method and device, storage medium and intelligent terminal | |
| CN112749556B (en) | Multi-language model training method and device, storage medium and electronic equipment | |
| CN116303951A (en) | Dialogue processing method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Bantian street, Longgang District of Shenzhen City, Guangdong province 518000 yuan and five Avenue sign technology plant No. 1 building 4 floor Applicant after: SHENZHEN GOLO CHELIAN DATA TECHNOLOGY Co.,Ltd. Address before: Bantian street Shenzhen city Guangdong province 518000 yuan and five Avenue sign technology plant No. 1 building 4 floor Applicant before: GOLO IOV DATA TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181214 |
|
| RJ01 | Rejection of invention patent application after publication |