CN112423036B - Video data processing method, video data processing device, computer equipment and storage medium - Google Patents
Video data processing method, video data processing device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112423036B CN112423036B CN202011053033.4A CN202011053033A CN112423036B CN 112423036 B CN112423036 B CN 112423036B CN 202011053033 A CN202011053033 A CN 202011053033A CN 112423036 B CN112423036 B CN 112423036B
- Authority
- CN
- China
- Prior art keywords
- video
- target
- order service
- content
- service video
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 title claims abstract description 71
- 238000003672 processing method Methods 0.000 title abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000001514 detection method Methods 0.000 claims description 74
- 238000004590 computer program Methods 0.000 claims description 25
- 238000012550 audit Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims 2
- 238000012552 review Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 8
- 230000005611 electricity Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000009434 installation Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005086 pumping Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011900 installation process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
-
- 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
- H04N21/23406—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving management of server-side video buffer
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application relates to a video data processing method, a video data processing device, a computer device and a storage medium. The method comprises the following steps: acquiring a current order service video corresponding to current order data; editing the current order service video to obtain a target order service video; inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model; and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video. By adopting the method, the actual order service site corresponding to the order data can be restored through the order service video.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a video data processing method and apparatus, a computer device, and a storage medium.
Background
At present, after a user purchases articles, some articles need to be installed at home by special installers, for example, when the user purchases a television, the user needs to install the television at home by special installers, and when the installer provides installation service at home, in order to prove service quality, user satisfaction and the like, a form of taking a field service photo is usually adopted when an order is sold for a single ring, and a service installation process is embodied by the field service photo. However, in this way, the on-site service photos as the static content carriers can only show part of the service results, and cannot show the operation process, so that the service quality is difficult to evaluate, and the real situation of the service site cannot be restored.
Disclosure of Invention
Based on this, it is necessary to provide a video data processing method, an apparatus, a computer device and a storage medium capable of restoring an actual order service site corresponding to order data through an order service video in order to solve the above technical problems.
A method of video data processing, the method comprising:
acquiring a current order service video corresponding to current order data;
editing the current order service video to obtain a target order service video;
inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model;
and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
In one embodiment, the obtaining of the current order service video corresponding to the current order data includes: acquiring at least one operation link corresponding to the current order data; acquiring video shooting instructions corresponding to all the operation links, and determining corresponding target objects from the video shooting objects corresponding to all the operation links according to the video shooting instructions; acquiring corresponding target object shooting guide according to the target object of each operation link; and shooting adjustment is carried out according to the shooting guide of the target object of each operation link to obtain an operation service video corresponding to each operation link, and a current order service video is obtained according to the operation service video corresponding to each operation link.
In one embodiment, the clipping processing is performed on the current order service video to obtain a target order service video, and the clipping processing includes: acquiring a target effective video identification model; inputting the current order service video into a target effective video identification model, carrying out effectiveness detection on a service video frame corresponding to the current order service video through the target effective video identification model, extracting a key service video frame from the service video frame, and obtaining the target order service video according to an effectiveness detection result and the key service video frame; and outputting the target order service video through the target effective video identification model.
In one embodiment, the target video content auditing model comprises a target video content validity auditing submodel and a target video content standardization auditing submodel, the target order service video is input into the target video content auditing model, and the target order service video is processed through the target video content auditing model to obtain a target order service content result output by the target video content auditing model, and the method comprises the following steps: the target order service video is used as the input of a target video content validity checking submodel, video content validity processing is carried out on the target order service video through the target video content validity checking submodel, and a video content checking result corresponding to the target order service video is output; when the video content checking result is that the video content checking is passed, performing video image quality detection on the target order service video to obtain a video quality detection result; and inputting the video quality detection result and the target order service video into a target video content normative auditing submodel, performing video content normative processing on the target order service video according to the video quality detection result through the target video content normative auditing submodel, and outputting a target order service content result corresponding to the target order service video.
In one embodiment, the video data processing method further includes stopping processing the current order service video when the video content audit result is that the video content audit is not passed; acquiring a next order service video corresponding to the next order data; and taking the next order service video as the current order service video, and performing clipping processing on the current order service video in the entering step to obtain a target order service video and obtain a corresponding target order service content result.
In one embodiment, performing video image quality detection on a target order service video to obtain a video quality detection result includes: and detecting the attractiveness and the definition of the video of the target order service video, and detecting whether the target order service video has blurs, defocusing, noise points, sawteeth and mosaics to obtain a video quality detection result.
In one embodiment, the sending the target order service video to the target terminal according to the target order service content result includes: and when the target order service content result is that the target order service content is approved, generating a corresponding target order service video link according to the target order service video, and sending the target order service video link to the target terminal.
A video data processing apparatus, the apparatus comprising:
the order service video acquisition module is used for acquiring a current order service video corresponding to the current order data;
the order service video clipping module is used for clipping the current order service video to obtain a target order service video;
the target video content auditing model processing module is used for inputting the target order service video into the target video content auditing model and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model;
and the order service video sending module is used for sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a current order service video corresponding to current order data;
editing the current order service video to obtain a target order service video;
inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model;
and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a current order service video corresponding to current order data;
editing the current order service video to obtain a target order service video;
inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model;
and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video.
The video data processing method, the video data processing device, the computer equipment and the storage medium acquire the current order service video corresponding to the current order data; editing the current order service video to obtain a target order service video; inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model; and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video. Therefore, after the target terminal receives the target order service video, the actual order service site corresponding to the current order data can be restored by playing the target order service video, compared with the method that a static content carrier such as a site service photo can only show part of service results and cannot show the working process, the service quality is difficult to evaluate, the working process can be shown by the target order service video, and the dynamic content carrier such as a video can restore the service site and ensure the quality of the order service site.
Drawings
FIG. 1 is a diagram of an exemplary video data processing system;
FIG. 2 is a flow diagram illustrating a method for video data processing according to one embodiment;
FIG. 3 is a flowchart illustrating the current order service video acquisition step in one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating the current step of servicing a video clip in one embodiment;
FIG. 5 is a flowchart illustrating the content result generation step of the target order service in one embodiment;
FIG. 6 is a flow diagram illustrating a method for video data processing according to one embodiment;
FIG. 7 is a block diagram showing a configuration of a video data processing apparatus according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
The video data processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by multiple servers.
Specifically, the server 104 obtains a current order service video corresponding to the current order data, clips the current order service video to obtain a target order service video, inputs the target order service video into a target video content auditing model, processes the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model, and sends the target order service video to the target terminal 102 according to the target order service content result, so that the target terminal 102 restores an actual order service site corresponding to the current order data according to the target order service video.
In one embodiment, as shown in fig. 2, a video data processing method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
The current order data refers to order data currently implementing order service, and when a user purchases a certain commodity, the user generates corresponding order data, where the order data includes, but is not limited to, an order identifier, a commodity name, a commodity amount, and the like. And the current order service video is a service video corresponding to the current order data, after the user purchases a commodity, if the commodity needs installation service by related operators, the related operators need to shoot a video of an installation service site, and the video of the installation service site can be determined as the current order service video.
Specifically, when relevant operators go to the door to provide after-sale service, current order data are obtained from terminals of the operators, order service is completed according to the current order data, in the order service completion process, videos of order service sites need to be shot, and the shot videos of the order service sites can be determined to be the current order service videos.
In another embodiment, in the video shooting process, related operators do not know the shooting standards very much, non-professionals lack shooting skills, and consumers urge to execute the remaining operation links as soon as possible, so the video imaging effect is often fuzzy and rough, the real object placement position and the shooting process in the scene do not meet the business standards, and the service standards, therefore, if the current order data includes at least one operation link, each operation link corresponding to the current order data is obtained, when each operation link carries out operation, the operation process needs to be shot, the video shooting instruction corresponding to each operation link is obtained, the corresponding target object is determined from the video shooting objects corresponding to each operation link according to the video shooting instruction, then the corresponding target object shooting instruction is obtained according to the target object of each operation link, shooting adjustment is carried out according to the target object shooting instruction of each operation link, the operation service video corresponding to each operation link is obtained, and the current order service video is obtained according to the operation service video corresponding to each operation link.
And step 204, clipping the current order service video to obtain a target order service video.
The editing process is used for performing effectiveness and key video frame processing on each video frame corresponding to the current order service video, the editing process can directly perform effectiveness detection on each video frame of the current order service video and extract key video frames so as to obtain a target order service video, and can also perform editing processing on the current order service video through a target effective video identification model, specifically, the current order service video is used as the input of the target effective video identification model, the effectiveness detection is performed on each video frame corresponding to the current order service video through the target effective video identification model and extract key video frames from each video frame, and the target order service video is obtained according to the effectiveness detection result and the key video frames.
In another embodiment, after video shooting is performed in multiple operation links, sales slip videos corresponding to the operation links are generated, transition among the operation links is hard, continuous watching experience is poor, if manual merging or clipping is easy to consume a large amount of human resources, a consumer cannot conveniently play videos in a service process, and in order to solve the problem, the automatic merging and artificial intelligent clipping of the multiple sales slip videos are achieved based on the video merging and artificial intelligent clipping technology so as to improve the video watching experience of the consumer. Each sales order video shot by related operators during field operation is automatically combined into a single editing video after sales order sales, intelligent processing models such as intelligent identification, effective shot detection, key frame extraction and automatic synthesis editing are generated on the basis of intelligent visual identification, understanding and editing technology and by the aid of the types, models and detailed characteristics of common real objects of after-sales service scenes, and the brilliant gathering video is automatically edited and output through comprehensive application of a target effective video identification model, so that the target order service video is obtained.
And step 206, inputting the target order service video into the target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model.
The target video content auditing model is a model used for auditing the video content corresponding to the target order service video, and the target video content auditing model is trained through a large number of training samples and can be trained through the existing model training mode, which is not repeated herein. Specifically, a trained target video content auditing model is obtained, the target order service video is used as the input of the target video content auditing model, the video content of the target order service video is processed through the target video content auditing model, and a corresponding target order service content result is output.
In another embodiment, since the video needs to be subjected to illegal review before being put on shelf to ensure compliance with legal regulations, the possibility of video leakage and transmission is brought by manual review of the video, negative effects and illegal risks are brought to companies, the review efficiency is low, the review cost is high, and in order to solve the problem, the illegal video such as pornography, riot, administration and the like is accurately identified by a massive large data sample library and a machine learning algorithm, and the illegal video artificial intelligent review technology is adopted to meet the legal regulations. Specifically, the target video content auditing model comprises a target video content validity auditing submodel and a target video content normative auditing submodel, the video content validity of the target order service video can be audited through the target video content validity auditing submodel, the target order service video is used as the input of the target video content validity auditing submodel to obtain a video content auditing result corresponding to the target order service video, and when the video content auditing result is passed, the video image quality detection can be performed on the target order service video to obtain a video quality detection result.
Further, since normative review is required before the video is put on shelf and a synchronous manufacturer to ensure compliance with the after-sale service standard and the manufacturer settlement standard, the requirement of manual review on the professional of the reviewer for the video is high, the risk of revealing the privacy of the user exists, the review efficiency is low, the review cost is high, and the requirement of monitoring the service site in real time by the consumer and timely settling the service cost by the service provider is difficult to meet.
And 208, sending the target order service video to the target terminal according to the target order service content result, so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
Specifically, after a target order service content result is obtained, a target order service video can be sent to a target terminal according to the target order service content result, the target order service content result includes but is not limited to that the target order service content is approved and that the target order service content is not approved, when the target order service content result is that the target order service content is approved, the target order service video is sent to the target terminal, and after the target terminal receives the target order service video, an actual order service site corresponding to current order data can be restored by playing the target order service video.
In one embodiment, the sending the target order service video to the target terminal according to the target order service content result includes: and when the target order service content result is that the target order service content is approved, generating a corresponding target order service video link according to the target order service video, and sending the target order service video link to the target terminal.
The method includes the steps that when the result of the target order service content is that the target order service content is approved, a target order service video can be shared to a target terminal user in a link mode and pushed to the target terminal through the video link, and specifically, when the result of the target order service content is that the target order service content is approved, a corresponding target order service video link is generated according to the target order service video, and the target order service video link is sent to the target terminal. The target terminal receives the target order service video link and then clicks the target order service video link to obtain the target order service video.
In the video data processing method, a current order service video corresponding to current order data is obtained; editing the current order service video to obtain a target order service video; inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model; and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video. Therefore, after the target terminal receives the target order service video, the actual order service site corresponding to the current order data can be restored by playing the target order service video, compared with the method that a static content carrier such as a site service photo can only show part of service results and cannot show the working process, the service quality is difficult to evaluate, the working process can be shown by the target order service video, and the dynamic content carrier such as a video can restore the service site and ensure the quality of the order service site.
In one embodiment, as shown in fig. 3, acquiring a current order service video corresponding to current order data includes:
And 304, acquiring video shooting instructions corresponding to all the operation links, and determining corresponding target objects from the video shooting objects corresponding to all the operation links according to the video shooting instructions.
In the video shooting process, related operators do not know the shooting standard very much, non-professionals lack shooting skills, and consumers urge to execute the rest operation links as soon as possible, so the video imaging effect is often fuzzy and rough, the real object placing position and the shooting flow in the scene do not meet the business standard, and the service is standard.
The method comprises the steps that current order data correspond to at least one operation link, and the current order data comprise a plurality of commodities requiring order service, the order service corresponding to one commodity is one operation link, when the order service corresponding to each commodity is realized, the site of the corresponding operation link needs to be shot, video shooting instructions corresponding to each operation link are obtained, after the video shooting instructions corresponding to each operation link are obtained, video shooting objects corresponding to each link appear on a shooting interface, and corresponding target objects can be determined from the video shooting objects. The target object can be determined according to business requirements, product requirements or application scenes, for example, safety guarantee nodes such as standard electricity measurement, vacuum pumping, wall plugging holes and water testing in an order service scene (namely, each operation link) can determine common electric appliances, furniture, walls, windows, electricity measuring instruments, vacuum pumps, pressure gauges and other real objects in the order service scene as the target object.
And step 306, acquiring corresponding target object shooting guidance according to the target object of each operation link.
And 308, performing shooting adjustment according to the shooting guide of the target object of each operation link to obtain an operation service video corresponding to each operation link, and obtaining a current order service video according to the operation service video corresponding to each operation link.
The target object shooting guide is used for guiding the target object to shoot, corresponding target object shooting instructions exist in all the target objects, and the association relationship between the target objects and the target object shooting guide can be established in advance. After the target object is determined, the target object guide can be obtained according to the target object, the target object guide can be displayed in a voice or text mode, relevant operators can adjust shooting of the current operation link according to the target object shooting guide, accordingly, operation service videos corresponding to all operation links are obtained, and then current order service videos can be obtained according to the operation videos corresponding to all operation links. In the video shooting process, related operators do not know the shooting standard well, non-professionals lack shooting skills, and consumers urge to execute the rest operation links as soon as possible, so that the video imaging effect is fuzzy and rough, the real object placing position and the shooting flow in a scene do not accord with the business standard, the service is standard, and shooting adjustment can be carried out through the shooting guide of a target object, so that the problem is solved. For example, safety guarantee nodes such as standard electricity measurement, vacuum pumping, wall plugging, water testing and the like in an order service scene (namely, each operation link) can determine common electric appliances, furniture, walls, windows, electricity measuring instruments, vacuum pumps, pressure gauges and the like in the order service scene as target objects, and guide operating personnel to execute a standard shooting process in real time through images, characters and voice in the shooting process according to an after-sale standard service process combined with specific real object identification in the order scene, so that the after-sale service standard is met. For another example, at the safety guarantee node for electricity measurement, the entity and the lighting state of the electricity meter are tracked and recognized in real time through a 3D object, characters below the lamp position of the electricity meter are recognized through OCR (optical character recognition), the correct moving direction and distance of the current position and the standard position of the electricity meter are drawn through an AR (augmented reality) auxiliary shooting system in a shooting view frame, and the lighting state recognized by the 3D object and the lamp position name recognized by OCR are combined to guide an engineer to adjust the shooting focus and the focal length.
In one embodiment, as shown in fig. 4, the process of clipping the current order service video to obtain the target order service video includes:
And 406, outputting a target order service video through the target effective video identification model.
After the videos are shot in the multiple operation links, the generated order selling videos corresponding to the operation links are hard to transition from one another, the continuous watching experience is poor, if the order selling videos are manually combined or edited, a large amount of human resources are easily consumed, a consumer cannot conveniently play the videos in the service process, in order to solve the problem, the current order service video can be edited, invalid video frames in the current order service video are eliminated, and the quality of the current order service video is guaranteed. The editing process of the current order service video may be performed through a target effective video recognition model, specifically, a trained target effective video recognition model is obtained, where the target effective video recognition model is used to recognize effectiveness of each service video frame in the current order service video and extract a key video frame from each service video frame. The target effective video recognition model can be obtained by training a large number of training samples in advance, and the training of the target effective video recognition model can be obtained by training in the existing training mode. Specifically, a current order service video is input into a target effective video identification model, effectiveness detection is carried out on a service video frame corresponding to the current order service video through the target effective video identification model, a key service video frame is extracted from the service video frame, the target order service video is obtained according to an effectiveness detection result and the key service video frame, and then the target order service video is output. The validity detection includes valid shot detection, invalid shot screening, and the like.
In an embodiment, as shown in fig. 5, the target video content auditing model includes a target video content validity auditing submodel and a target video content normative auditing submodel, the target order service video is input into the target video content auditing model, and the target order service video is processed by the target video content auditing model to obtain a target order service content result output by the target video content auditing model, which includes:
And step 504, when the video content auditing result is that the video content auditing is passed, performing video image quality detection on the target order service video to obtain a video quality detection result.
The method comprises the steps that a video is subjected to illegal review before being put on shelf to ensure that the video conforms to laws and regulations, the possibility of video leakage and transmission is brought by manual review of the video, negative effects and illegal risks are brought to companies, the review efficiency is low, the review cost is high, and in order to solve the problem, the machine learning algorithm is advanced through a large-amount large data sample library, and illegal videos such as pornography, riots, administration and the like are accurately identified by adopting an illegal video artificial intelligent review technology to conform to the legal regulations. Specifically, the target video content auditing model comprises a target video content validity auditing submodel and a target video content normative auditing submodel, the video content validity of the target order service video can be audited through the target video content validity auditing submodel, the target order service video is used as the input of the target video content validity auditing submodel to obtain a video content auditing result corresponding to the target order service video, and when the video content auditing result is passed, the video image quality detection can be performed on the target order service video to obtain a video quality detection result.
Further, since normative review is required before the video is put on shelf and a synchronous manufacturer to ensure compliance with the after-sale service standard and the manufacturer settlement standard, the requirement of manual review on the professional of the reviewer for the video is high, the risk of revealing the privacy of the user exists, the review efficiency is low, the review cost is high, and the requirement of monitoring the service site in real time by the consumer and timely settling the service cost by the service provider is difficult to meet.
In one embodiment, performing video image quality detection on a target order service video to obtain a video quality detection result, includes: and detecting the attractiveness and the definition of the video of the target order service video, and detecting whether the target order service video has blurs, defocusing, noise points, sawteeth and mosaics to obtain a video quality detection result.
In order to ensure the accuracy of the target order service content result, before the video quality detection result and the target order service video are input into the target video content normative auditing submodel, video image quality detection can be performed on the target order service video, the image quality is detected firstly when the conditions of image color, composition and blurring, defocusing, noise, sawtooth, mosaic and the like are detected through image aesthetic degree and definition identification, specifically, the video aesthetic degree and the video definition detection can be performed on the target order service video, and whether the blurring, the defocusing, the noise, the sawtooth and the mosaic exist in the target order service video is detected, so that the video quality detection result is obtained.
The video aesthetic measure and the video definition of the target order service video may be specifically detected by using an existing video aesthetic measure and video definition detection algorithm, if it is not detected that blur, defocus, noise, jaggy and mosaic exist in the target order service video, it is indicated that the video quality detection result is that no problem exists in the video quality, the video quality detection result and the target order service video may be input into a target video content normative sub-audit model, and if it is detected that blur, defocus, noise, jaggy and mosaic exist in the target order service video, it is indicated that the video quality detection result is that the video quality exists in a problem, and video image processing may be performed on the target order service video, for example, video frames in which blur exists in the target order service video are clearly processed, or video frames in which mosaic exists in the target order service video are clearly processed, and the like.
In one embodiment, as shown in fig. 6, the video data processing method further includes:
And 606, taking the next order service video as the current order service video, and performing clipping processing on the current order service video to obtain a target order service video and obtain a corresponding target order service content result.
If the video content auditing result is that the video content auditing is not passed, the video content validity problem of the current order service video is shown, the video cannot be put on shelf, and the processing of the current order service video is stopped. The current order service video may be discarded for processing. Further, a next order service video corresponding to the next order data is obtained, the next order service video is used as a current order service video, the current order service video is clipped in the step, a target order service video is obtained, and a corresponding target order service content result is obtained. By the method, the legality of the video content can be ensured, only the legal video can continue to be processed, and otherwise, the legal video can be discarded and the like.
In a specific embodiment, a video processing method is provided, which specifically includes the following steps:
1. and acquiring a current order service video corresponding to the current order data.
1-1, acquiring at least one operation link corresponding to the current order data.
And 1-2, acquiring video shooting instructions corresponding to all the operation links, and determining corresponding target objects from the video shooting objects corresponding to all the operation links according to the video shooting instructions.
And 1-3, acquiring corresponding target object shooting guide according to the target object of each operation link.
And 1-4, shooting and adjusting according to the shooting guide of the target object of each operation link to obtain an operation service video corresponding to each operation link, and obtaining a current order service video according to the operation service video corresponding to each operation link.
2. And editing the current order service video to obtain a target order service video.
And 2-1, acquiring a target effective video recognition model.
2-2, inputting the current order service video into a target effective video identification model, carrying out effectiveness detection on a service video frame corresponding to the current order service video through the target effective video identification model, extracting a key service video frame from the service video frame, and obtaining the target order service video according to an effectiveness detection result and the key service video frame.
And 2-3, outputting the target order service video through the target effective video identification model.
3. And inputting the target order service video into the target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model.
And 3-1, enabling the target video content auditing model to comprise a target video content validity auditing submodel and a target video content standardization auditing submodel, taking the target order service video as the input of the target video content validity auditing submodel, carrying out video content validity processing on the target order service video through the target video content validity auditing submodel, and outputting a video content auditing result corresponding to the target order service video.
And 3-2, when the video content auditing result is that the video content auditing is passed, performing video image quality detection on the target order service video to obtain a video quality detection result.
And 3-2-1, detecting the video attractiveness and the video definition of the target order service video, and detecting whether the target order service video is fuzzy, out-of-focus, noisy, sawtooth and mosaic to obtain a video quality detection result.
And 3-3, inputting the video quality detection result and the target order service video into a target video content normative auditing submodel, performing video content normative processing on the target order service video according to the video quality detection result through the target video content normative auditing submodel, and outputting a target order service content result corresponding to the target order service video.
And 3-4, stopping processing the current order service video when the video content auditing result is that the video content auditing is not passed.
And 3-5, acquiring a next order service video corresponding to the next order data.
And 3-6, taking the next order service video as the current order service video, and performing clipping processing on the current order service video in the entering step to obtain a target order service video and obtain a corresponding target order service content result.
4. And sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video.
And 4-1, when the target order service content result is that the target order service content is approved, generating a corresponding target order service video link according to the target order service video, and sending the target order service video link to the target terminal.
It should be understood that, although the steps in the above-described flowcharts are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a portion of the steps in the above-described flowcharts may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or the stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a video data processing apparatus 700 comprising: an order service video acquisition module 702, an order service video clipping module 704, a target video content auditing model processing module 706, and an order service video transmission module 708, wherein:
an order service video obtaining module 702, configured to obtain a current order service video corresponding to current order data.
And the order service video clipping module 704 is configured to clip the current order service video to obtain a target order service video.
And the target video content auditing model processing module 706 is configured to input the target order service video into the target video content auditing model, and process the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model.
The order service video sending module 708 is configured to send the target order service video to the target terminal according to the target order service content result, so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
In an embodiment, the order service video obtaining module 702 is further configured to obtain at least one operation link corresponding to current order data, obtain a video shooting instruction corresponding to each operation link, determine a corresponding target object from video shooting objects corresponding to each operation link according to the video shooting instruction, obtain a corresponding target object shooting guide according to the target object of each operation link, perform shooting adjustment according to the target object shooting guide of each operation link, obtain an operation service video corresponding to each operation link, and obtain a current order service video according to the operation service video corresponding to each operation link.
In an embodiment, the order service video clipping module 704 is further configured to obtain a target valid video identification model, input the current order service video into the target valid video identification model, perform validity detection on a service video frame corresponding to the current order service video through the target valid video identification model, extract a key service video frame from the service video frame, obtain the target order service video according to the validity detection result and the key service video frame, and output the target order service video through the target valid video identification model.
In one embodiment, the target video content auditing model includes a target video content validity auditing submodel and a target video content normative auditing submodel, and the target video content auditing model processing module 706 is further configured to use the target order service video as an input of the target video content validity auditing submodel, perform video content validity processing on the target order service video through the target video content validity auditing submodel, output a video content auditing result corresponding to the target order service video, perform video image quality detection on the target order service video when the video content auditing result is that the video content auditing passes, obtain a video quality detection result, input the video quality detection result and the target order service video into the target video content normative auditing submodel, perform video content normative processing on the target order service video according to the video quality detection result through the target video content normative auditing submodel, and output a target order service content result corresponding to the target order service video.
In an embodiment, the video data processing apparatus 700 is further configured to, when the video content audit result indicates that the video content audit is not passed, suspend processing the current order service video, obtain a next order service video corresponding to the next order data, use the next order service video as the current order service video, and perform an editing process on the current order service video to obtain a target order service video, so as to obtain a corresponding target order service content result.
In an embodiment, the target video content auditing model processing module 706 is further configured to perform video aesthetics and video definition detection on the target order service video, and detect whether the target order service video is blurred, out-of-focus, noisy, jagged, and mosaic, so as to obtain a video quality detection result.
In an embodiment, the order service video sending module 708 is further configured to generate a corresponding target order service video link according to the target order service video when the result of the target order service content is that the target order service content is approved, and send the target order service video link to the target terminal.
For specific limitations of the video data processing apparatus, reference may be made to the above limitations of the video data processing method, which are not described herein again. The respective modules in the video data processing apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing the target video content auditing model. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a video data processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring a current order service video corresponding to current order data; editing the current order service video to obtain a target order service video; inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model; and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring at least one operation link corresponding to current order data; acquiring video shooting instructions corresponding to all the operation links, and determining corresponding target objects from the video shooting objects corresponding to all the operation links according to the video shooting instructions; acquiring corresponding target object shooting guide according to the target object of each operation link; and performing shooting adjustment according to the target object shooting guide of each operation link to obtain operation service videos corresponding to each operation link, and obtaining current order service videos according to the operation service videos corresponding to each operation link.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring a target effective video identification model; inputting a current order service video into a target effective video identification model, carrying out effectiveness detection on a service video frame corresponding to the current order service video through the target effective video identification model, extracting a key service video frame from the service video frame, and obtaining a target order service video according to an effectiveness detection result and the key service video frame; and outputting the target order service video through the target effective video identification model.
In one embodiment, the target video content auditing model includes a target video content validity auditing submodel and a target video content normative auditing submodel, and the processor, when executing the computer program, further implements the following steps: the target order service video is used as the input of a target video content validity checking sub-model, video content validity processing is carried out on the target order service video through the target video content validity checking sub-model, and a video content checking result corresponding to the target order service video is output; when the video content auditing result is that the video content auditing is passed, performing video image quality detection on the target order service video to obtain a video quality detection result; and inputting the video quality detection result and the target order service video into a target video content normative auditing submodel, performing video content normative processing on the target order service video according to the video quality detection result through the target video content normative auditing submodel, and outputting a target order service content result corresponding to the target order service video.
In one embodiment, the processor when executing the computer program further performs the steps of: when the video content auditing result is that the video content auditing is not passed, stopping processing the current order service video; acquiring a next order service video corresponding to the next order data; and taking the next order service video as the current order service video, and performing clipping processing on the current order service video in the entering step to obtain a target order service video and obtain a corresponding target order service content result.
In one embodiment, the processor when executing the computer program further performs the steps of: and detecting the attractiveness and the definition of the video of the target order service video, and detecting whether the target order service video has blurs, defocusing, noise points, sawteeth and mosaics to obtain a video quality detection result.
In one embodiment, the processor when executing the computer program further performs the steps of: and when the target order service content result is that the target order service content is approved, generating a corresponding target order service video link according to the target order service video, and sending the target order service video link to the target terminal.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a current order service video corresponding to current order data; editing the current order service video to obtain a target order service video; inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model; and sending the target order service video to the target terminal according to the target order service content result so that the target terminal restores the actual order service site corresponding to the current order data according to the target order service video.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring at least one operation link corresponding to current order data; acquiring video shooting instructions corresponding to all operation links, and determining corresponding target objects from the video shooting objects corresponding to all the operation links according to the video shooting instructions; acquiring corresponding target object shooting guide according to the target object of each operation link; and shooting adjustment is carried out according to the shooting guide of the target object of each operation link to obtain an operation service video corresponding to each operation link, and a current order service video is obtained according to the operation service video corresponding to each operation link.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a target effective video identification model; inputting the current order service video into a target effective video identification model, carrying out effectiveness detection on a service video frame corresponding to the current order service video through the target effective video identification model, extracting a key service video frame from the service video frame, and obtaining the target order service video according to an effectiveness detection result and the key service video frame; and outputting the target order service video through the target effective video identification model.
In one embodiment, the target video content auditing model includes a target video content validity auditing submodel and a target video content normative auditing submodel, and the processor, when executing the computer program, further implements the following steps: the target order service video is used as the input of a target video content validity checking sub-model, video content validity processing is carried out on the target order service video through the target video content validity checking sub-model, and a video content checking result corresponding to the target order service video is output; when the video content checking result is that the video content checking is passed, performing video image quality detection on the target order service video to obtain a video quality detection result; and inputting the video quality detection result and the target order service video into a target video content normative auditing submodel, performing video content normative processing on the target order service video according to the video quality detection result through the target video content normative auditing submodel, and outputting a target order service content result corresponding to the target order service video.
In one embodiment, the processor when executing the computer program further performs the steps of: when the video content auditing result is that the video content auditing is not passed, stopping processing the current order service video; acquiring a next order service video corresponding to the next order data; and taking the next order service video as the current order service video, and performing clipping processing on the current order service video in the entering step to obtain a target order service video and obtain a corresponding target order service content result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and detecting the attractiveness and the definition of the video of the target order service video, and detecting whether the target order service video has blurs, defocusing, noise points, sawteeth and mosaics to obtain a video quality detection result.
In one embodiment, the processor when executing the computer program further performs the steps of: and when the target order service content result is that the target order service content is approved, generating a corresponding target order service video link according to the target order service video, and sending the target order service video link to the target terminal.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (9)
1. A method of video data processing, the method comprising:
acquiring at least one operation link corresponding to current order data;
acquiring a video shooting instruction corresponding to each operation link, and determining a corresponding target object from video shooting objects corresponding to each operation link according to the video shooting instruction;
acquiring corresponding target object shooting guide according to the target object of each operation link;
shooting adjustment is carried out according to the shooting guide of the target object of each operation link, so that an operation service video corresponding to each operation link is obtained, and a current order service video is obtained according to the operation service video corresponding to each operation link;
editing the current order service video to obtain a target order service video;
inputting the target order service video into a target video content auditing model, and processing the target order service video through the target video content auditing model to obtain a target order service content result output by the target video content auditing model;
and sending the target order service video to a target terminal according to the target order service content result so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
2. The method of claim 1, wherein said clipping the current order service video to obtain a target order service video comprises:
acquiring a target effective video identification model;
inputting the current order service video into the target effective video identification model, carrying out effectiveness detection on a service video frame corresponding to the current order service video through the target effective video identification model, extracting a key service video frame from the service video frame, and obtaining the target order service video according to an effectiveness detection result and the key service video frame;
and outputting the target order service video through the target effective video identification model.
3. The method of claim 1, wherein the target video content audit model comprises a target video content validity audit submodel and a target video content normative audit submodel, the inputting the target order service video into the target video content audit model, processing the target order service video through the target video content audit model to obtain the target order service content result output by the target video content audit model comprises:
the target order service video is used as the input of the target video content validity checking submodel, video content validity processing is carried out on the target order service video through the target video content validity checking submodel, and a video content checking result corresponding to the target order service video is output;
when the video content auditing result is that the video content auditing is passed, performing video image quality detection on the target order service video to obtain a video quality detection result;
and inputting the video quality detection result and the target order service video into a target video content normative auditing submodel, performing video content normative processing on the target order service video according to the video quality detection result through the target video content normative auditing submodel, and outputting a target order service content result corresponding to the target order service video.
4. The method of claim 3, further comprising:
when the video content auditing result is that the video content auditing is not passed, stopping processing the current order service video;
acquiring a next order service video corresponding to the next order data;
and taking the next order service video as the current order service video, and performing clipping processing on the current order service video to obtain a target order service video and obtain a corresponding target order service content result.
5. The method according to claim 3, wherein the performing video image quality inspection on the target order service video to obtain a video quality inspection result comprises:
and detecting the attractiveness and the definition of the video of the target order service video, and detecting whether the target order service video is fuzzy, out-of-focus, noisy, sawtooth and mosaic to obtain a video quality detection result.
6. The method according to claim 1, wherein the sending the target order service video to a target terminal according to the target order service content result comprises:
and when the target order service content result is that the target order service content is approved, generating a corresponding target order service video link according to the target order service video, and sending the target order service video link to a target terminal.
7. A video data processing apparatus, characterized in that the apparatus comprises:
the order service video acquisition module is used for acquiring at least one operation link corresponding to current order data, acquiring a video shooting instruction corresponding to each operation link, determining a corresponding target object from video shooting objects corresponding to each operation link according to the video shooting instruction, acquiring corresponding target object shooting guide according to the target object of each operation link, carrying out shooting adjustment according to the target object shooting guide of each operation link to obtain an operation service video corresponding to each operation link, and acquiring a current order service video according to the operation service video corresponding to each operation link;
the order service video clipping module is used for clipping the current order service video to obtain a target order service video;
the target video content auditing model processing module is used for inputting the target order service video into a target video content auditing model, processing the target order service video through the target video content auditing model and obtaining a target order service content result output by the target video content auditing model;
and the order service video sending module is used for sending the target order service video to a target terminal according to the target order service content result so that the target terminal restores an actual order service site corresponding to the current order data according to the target order service video.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 6 are implemented when the computer program is executed by the processor.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011053033.4A CN112423036B (en) | 2020-09-29 | 2020-09-29 | Video data processing method, video data processing device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011053033.4A CN112423036B (en) | 2020-09-29 | 2020-09-29 | Video data processing method, video data processing device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112423036A CN112423036A (en) | 2021-02-26 |
| CN112423036B true CN112423036B (en) | 2023-04-14 |
Family
ID=74854819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011053033.4A Active CN112423036B (en) | 2020-09-29 | 2020-09-29 | Video data processing method, video data processing device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112423036B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523343A (en) * | 2018-10-16 | 2019-03-26 | 深圳希智电子有限公司 | Purchase data processing method, device, computer equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107566907B (en) * | 2017-09-20 | 2019-08-30 | Oppo广东移动通信有限公司 | Video clipping method, device, storage medium and terminal |
| CN108255922A (en) * | 2017-11-06 | 2018-07-06 | 优视科技有限公司 | Video frequency identifying method, equipment, client terminal device, electronic equipment and server |
| CN111698554B (en) * | 2020-06-19 | 2022-06-07 | 广州方硅信息技术有限公司 | Live video album generating method, device, equipment and storage medium |
-
2020
- 2020-09-29 CN CN202011053033.4A patent/CN112423036B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523343A (en) * | 2018-10-16 | 2019-03-26 | 深圳希智电子有限公司 | Purchase data processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112423036A (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200167612A1 (en) | Image processing method and apparatus | |
| US11004234B2 (en) | Method and apparatus for annotating point cloud data | |
| CN108027830B (en) | System and method for automatic content verification | |
| CN108197618B (en) | Method and device for generating human face detection model | |
| CN110751149B (en) | Target object labeling method, device, computer equipment and storage medium | |
| CN108337505B (en) | Information acquisition method and device | |
| CN111242097A (en) | Face recognition method and device, computer readable medium and electronic equipment | |
| EP3598386A1 (en) | Method and apparatus for processing image | |
| CN107622504B (en) | Method and device for processing pictures | |
| CN105956469A (en) | Method and device for identifying file security | |
| US20080091365A1 (en) | Image verification with tiered tolerance | |
| EP3561776A1 (en) | Method and apparatus for processing a 3d scene | |
| CN115170932A (en) | Store terminal identification method, device and system and computer readable storage medium | |
| CN109996063A (en) | Video image flower screen detection method, device, computer equipment and storage medium | |
| CN114419712A (en) | Feature extraction method for protecting personal data privacy, model training method and hardware | |
| US10299117B2 (en) | Method for authenticating a mobile device and establishing a direct mirroring connection between the authenticated mobile device and a target screen device | |
| CN110633773B (en) | Two-dimensional code generation method and device for terminal equipment | |
| CN112423036B (en) | Video data processing method, video data processing device, computer equipment and storage medium | |
| CN105590241B (en) | Self-adaptive electronic bill implementation method and system | |
| CN111292333A (en) | Method and apparatus for segmenting an image | |
| CN107590065B (en) | Algorithm model detection method, device, equipment and system | |
| CN112418789A (en) | Claims evaluation processing method and device, nonvolatile storage medium and electronic equipment | |
| CN106412567A (en) | Method and system for determining video definition | |
| CN112784246A (en) | Method, device and equipment for verifying slider verification code and storage medium | |
| CN113379582A (en) | Information adding method, information extracting device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |