CN111107395B - Video transcoding method, device, server and storage medium - Google Patents
Video transcoding method, device, server and storage medium Download PDFInfo
- Publication number
- CN111107395B CN111107395B CN201911410012.0A CN201911410012A CN111107395B CN 111107395 B CN111107395 B CN 111107395B CN 201911410012 A CN201911410012 A CN 201911410012A CN 111107395 B CN111107395 B CN 111107395B
- Authority
- CN
- China
- Prior art keywords
- transcoded
- transcoding
- video
- gear
- rate
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000013145 classification model Methods 0.000 claims description 24
- 230000004927 fusion Effects 0.000 claims description 11
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 8
- 239000002699 waste material Substances 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000007787 solid Substances 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
- H04N21/23—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
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
- H04N21/234363—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by altering the spatial resolution, e.g. for clients with a lower screen resolution
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses a method, a device, a server and a storage medium for video transcoding. Wherein, the method comprises the following steps: determining a transcoding factor selected when the video to be transcoded reaches a subjective quality index specified by a gear to be transcoded after being transcoded at different gear to be transcoded according to the picture coding characteristics of the video to be transcoded; and transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors. According to the technical scheme provided by the embodiment of the invention, the same subjective quality index is set for the video to be transcoded in the same code rate gear, the effect of transcoding the video to be transcoded according to the predicted transcoding factor is compared with the specified subjective quality index, the accuracy of the selected transcoding factor in different code rate gears is ensured, then the video to be transcoded is subjected to multi-code rate transcoding by adopting different code rate gears to be transcoded and the corresponding transcoding factors, the reasonable allocation of code rates is realized, and the unnecessary code rate waste is avoided.
Description
Technical Field
The embodiment of the invention relates to the field of video processing, in particular to a method, a device, a server and a storage medium for video transcoding.
Background
In a video transcoding system, in order to adapt to network bandwidths of different terminals at different times, corresponding terminal processing capabilities, and the like, multi-rate transcoding is often required to be performed on a received source video stream according to different rate gears and Constant Rate Factors (CRFs) preset at the rate gears, and the CRFs can enable the source video stream to achieve corresponding video playing quality after being transcoded at the rate gears, so that the video stream at the adaptive rate gears can be subsequently distributed to the different terminals.
At the moment, when transcoding is performed by adopting the corresponding preset CRF under different code rate gears, the video playing quality is mainly the objective playing quality of the video, and due to the influences of the contrast sensitivity, brightness nonlinearity, frequency sensitivity, masking effect and the like of human eyes on the video, the subjective playing quality of the video stream with different contents transcoded by adopting the same code rate gear by a user can have larger difference, for example, the user is sensitive to the distortion of a video picture under slow motion and is not easy to perceive the distortion of the video picture under severe motion, so that for any video, the corresponding preset fixed CRF is used for performing multi-code conversion under different code rate gears, and the subjective playing quality of each video watched by the user cannot be measured.
At present, firstly, the content of a source video stream is subjected to perception analysis, the video classification to which the source video stream belongs, such as movies, sports or cartoons, is judged, then CRFs preset for different code rate gears under the video classification are adapted to perform multi-code rate transcoding, and at the moment, corresponding CRFs are set under different video classifications to select corresponding CRFs according to different user bandwidths to issue videos, but the subjective playing quality of the video streams with different contents under the same video classification by users cannot be accurately measured.
Disclosure of Invention
The embodiment of the invention provides a video transcoding method, a video transcoding device, a server and a storage medium, which can ensure the consistency of subjective quality of videos to be transcoded under different code rate gears and improve the rationality of code rate distribution.
In a first aspect, an embodiment of the present invention provides a method for transcoding a video, where the method includes:
determining a transcoding factor adopted when the video to be transcoded reaches a subjective quality index specified by a gear to be transcoded after being transcoded at different gear to be transcoded according to the picture coding characteristics of the video to be transcoded;
and transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors.
In a second aspect, an embodiment of the present invention provides an apparatus for video transcoding, where the apparatus includes:
the transcoding factor determining module is used for determining a transcoding factor adopted when the video to be transcoded reaches a subjective quality index specified by a gear to be transcoded after being transcoded at different gear to be transcoded according to the picture coding characteristics of the video to be transcoded;
and the video transcoding module is used for transcoding the video to be transcoded by adopting different transcoding rate gears and corresponding transcoding factors.
In a third aspect, an embodiment of the present invention provides a server, where the server includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of video transcoding as described in any embodiment of the invention.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for transcoding video according to any embodiment of the present invention.
The method, the device, the server and the storage medium for video transcoding provided by the embodiment of the invention specify subjective quality indexes required to be reached after video transcoding in each gear of code rate to be transcoded in advance, so that the same subjective quality indexes are set in the same gear of code rate for the video to be transcoded, the subjective quality of the video to be transcoded in the same gear of code rate is ensured to be consistent, at the moment, in each gear of code rate to be transcoded, a plurality of transcoding factors are respectively matched and selected for transcoding the video to be transcoded, and the transcoding factor selected when the picture coding characteristics of the video to be transcoded reach the specified subjective quality indexes in the gear of code rate to be transcoded after transcoding under the matching of the corresponding transcoding factor is determined, so that the transcoding factor in each gear of code rate to be transcoded is determined, at the moment, the effect of transcoding any video to be transcoded according to the predicted transcoding factor is compared with the specified subjective quality indexes, the method has the advantages that the subjective playing quality of any video to be transcoded under different code rate gears is accurately measured, the accuracy of selected transcoding factors under different code rate gears is guaranteed, then multi-code rate transcoding is carried out on the video to be transcoded by adopting different code rate gears to be transcoded and corresponding transcoding factors, so that reasonable allocation of code rates is achieved, unnecessary code rate waste is avoided, and bandwidth resources are saved.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings:
fig. 1A is a flowchart of a video transcoding method according to an embodiment of the present invention;
fig. 1B is a schematic diagram of a video transcoding process according to an embodiment of the present invention;
fig. 2A is a flowchart of a video transcoding method according to a second embodiment of the present invention;
fig. 2B is a schematic diagram of a video transcoding process according to a second embodiment of the present invention;
fig. 3A is a flowchart of a video transcoding method according to a third embodiment of the present invention;
fig. 3B is a schematic diagram of a video transcoding process according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a video transcoding apparatus according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of a server according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
Example one
Fig. 1A is a flowchart of a video transcoding method according to an embodiment of the present invention, which can be applied to a situation of performing multi-rate transcoding on any video. The method for transcoding a video provided by this embodiment may be performed by the apparatus for transcoding a video provided by the embodiment of the present invention, where the apparatus may be implemented in a software and/or hardware manner, and is integrated in a server that executes the method, and the server may be a background server that stores different video data.
Specifically, referring to fig. 1A, the method may include the steps of:
s110, according to the picture coding characteristics of the video to be transcoded, determining a transcoding factor selected when the video to be transcoded reaches a subjective quality index specified by a gear of the video to be transcoded after being transcoded at different gears of the video to be transcoded.
Specifically, in order to avoid video playing jamming, when each user downloads a corresponding video from the server, the video at a code rate matched with the current network bandwidth needs to be selected, and since the network bandwidth of the user changes in real time in the video downloading process, the server performs multi-code rate transcoding on any source video according to preset multiple code rate gears so as to subsequently issue the source video at the adaptive code rate to the user in order to avoid the video playing jamming after the video is downloaded at each network bandwidth.
The video to be transcoded is a source video which needs to be transcoded with multiple code rates under any content type uploaded to a server by other users; the picture coding characteristics refer to basic parameters which are contained in a source video at a certain specific code rate level and can evaluate the objective coding quality of each video frame in the source video after being coded at the specific code rate level, such as Peak Signal to Noise Ratio (PSNR), coding rate, coding quantization parameters and the like of the coded video frames, and the picture coding characteristics are a characteristic set which can represent the space-time complexity of video pictures, at the moment, the specific code rate level corresponding to the picture coding characteristics can be the coding rate adopted when a user uploads the source video, and can also be the specific code rate adopted when a server receives the source video and carries out primary transcoding; the rate level to be transcoded is a plurality of transcoding rates which are preset for the source video and can be matched with the network bandwidth which changes in real time; the subjective quality index refers to subjective playing quality required by user viewing experience when a Video to be transcoded is transcoded at different transcoding rate levels and then played at a user terminal, and because the relation between the content of a source Video and subjective viewing experiences of different users can be better measured by using a Video multi-method Assessment Fusion (VMAF) algorithm, the subjective quality index in the embodiment can be expressed by using a VMAF score to measure the subjective playing quality after the source Video is transcoded.
Meanwhile, the code rate gear is the whole file size of the video to be transcoded in unit time, and the transcoding quality of the video with different contents cannot be guaranteed, so that the transcoding factor in the embodiment is used for controlling the transcoding quality of the video to be transcoded with different contents in different gear positions of the video to be transcoded. It should be noted that, as shown in fig. 1B, in this embodiment, multiple different transcoding factors are preset in each rate level to be transcoded, so that a transcoding factor adapted to a specified subjective quality index is subsequently screened out in each rate level to be transcoded, and then the source video is transcoded by using the transcoding factor in the rate level to be transcoded. The transcoding Factor in this embodiment may be a plurality of fixed Rate factors (CRFs) preset in each Rate level to be transcoded.
Optionally, after obtaining the video to be transcoded, the server first determines that the video to be transcoded is encoded in a specific bitrate level, and then can evaluate the picture coding characteristics of each picture quality of the encoded video to be transcoded, and as shown in fig. 1B, in each bitrate level to be transcoded, multiple transcoding of different transcoding factors in the same bitrate level to be transcoded can be performed on the video to be transcoded by using the bitrate level to be transcoded and different transcoding factors set in the bitrate level to be transcoded, and a feature transcoding effect corresponding to the picture coding characteristics of the video to be transcoded after transcoding under different transcoding factors in the bitrate level to be transcoded is searched, and whether the feature transcoding effect after transcoding by selecting different transcoding factors in the bitrate level to be transcoded reaches a subjective quality index specified by the bitrate level to be transcoded is judged, and the selected transcoding factor when the bitrate level to be transcoded reaches a specified subjective quality index is used as the transcoding effect to be transcoded The transcoding factor of the coded video is adapted under the rate level to be transcoded so as to carry out actual transcoding on the coded video to be transcoded subsequently; meanwhile, according to the steps, the transcoding factors of the video to be transcoded, which are adaptive to different transcoding rate gears, are determined, and the accuracy of the selected transcoding factors under different transcoding rate gears is guaranteed.
And S120, transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors.
Optionally, after the transcoding factors adapted to the video to be transcoded in different transcoding rate gears are determined, the video to be transcoded can be transcoded in each transcoding rate gear to be transcoded by respectively adopting the transcoding rate gear to be transcoded and the transcoding factor correspondingly adapted to the transcoding rate gear to be transcoded, so that multi-rate transcoding of the video to be transcoded is realized, thus reasonably allocating code rates, ensuring the subjective quality of the video to be transcoded in different transcoding rate gears to be consistent, avoiding unnecessary code rate waste and saving bandwidth resources.
The technical scheme provided by the embodiment is that a subjective quality index required to be reached after video transcoding is specified in advance in each gear of a code rate to be transcoded, so that the same subjective quality index is set in the same gear of the code rate to be transcoded, the subjective quality of the video to be transcoded in the same gear of the code rate is guaranteed to be consistent, at the moment, in each gear of the code rate to be transcoded, a plurality of transcoding factors are respectively matched and selected for transcoding the video to be transcoded, transcoding factors selected when the picture coding characteristics of the video to be transcoded reach the specified subjective quality index in the gear of the code rate to be transcoded after transcoding is carried out in the matching of the corresponding transcoding factors are determined, then the transcoding factors in each gear of the code rate to be transcoded are determined, at the moment, the transcoding effect of any video to be transcoded according to the predicted transcoding factors is compared with the specified subjective quality index, the method has the advantages that the subjective playing quality of any video to be transcoded under different code rate gears is accurately measured, the accuracy of selected transcoding factors under different code rate gears is guaranteed, then multi-code rate transcoding is carried out on the video to be transcoded by adopting different code rate gears to be transcoded and corresponding transcoding factors, so that reasonable allocation of code rates is achieved, unnecessary code rate waste is avoided, and bandwidth resources are saved.
Example two
Fig. 2A is a flowchart of a video transcoding method according to a second embodiment of the present invention, and fig. 2B is a schematic diagram of a video transcoding process according to the second embodiment of the present invention. The present embodiment is optimized based on the above embodiments, and the present embodiment mainly explains in detail a specific determination process of transcoding factors adapted to videos to be transcoded in different transcoding rate steps.
Optionally, as shown in fig. 2A, this embodiment may include the following steps:
s210, aiming at each code rate gear to be transcoded, fusing the picture coding characteristics of the video to be transcoded, the gear to be transcoded and a specified subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the gear to be transcoded.
Optionally, in this embodiment, since the adaptive transcoding factors under different to-be-transcoded rate gears are determined by pre-training corresponding neural network models, transcoding characteristics of the to-be-transcoded video under each to-be-transcoded rate gear need to be obtained first, at this time, for each to-be-transcoded rate gear, the embodiment may perform feature fusion on the picture coding characteristics of the to-be-transcoded video coded under a certain specific rate gear, the code rate value of the to-be-transcoded rate gear, and a pre-specified subjective quality index under the to-be-transcoded rate gear, so as to generate a comprehensive transcoding characteristic of the to-be-transcoded video under the to-be-transcoded rate gear; and according to the steps, generating comprehensive transcoding characteristics of the video to be transcoded in each code rate gear to be transcoded.
For example, as shown in fig. 2B, in this embodiment, the fusing the picture coding characteristics of the video to be transcoded, the gear of the rate to be transcoded and the specified subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the gear of the rate to be transcoded may specifically include: and carrying out dimension expansion on the picture coding characteristics of the video to be transcoded, the gear of the rate to be transcoded and the designated subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the gear of the rate to be transcoded.
Specifically, in order to ensure the prediction accuracy of the neural network model, the comprehensive transcoding characteristics of the video to be transcoded in different transcoding rate steps are required to include characteristics under multiple dimensions, so that a large number of dimension characteristics can be subjected to fusion analysis in the subsequent process; therefore, in the embodiment, the image coding feature of the video to be transcoded, the rate value of the rate to be transcoded and the specified subjective quality index under the rate to be transcoded are subjected to the fourth-order cross multiplication operation in sequence, and the image coding feature of the video to be transcoded, the rate to be transcoded and the specified subjective quality index are fused, so that the feature dimension of the fused comprehensive transcoding feature is further enlarged compared with the feature dimension which is directly merged, and therefore the comprehensive transcoding feature of the video to be transcoded after dimension expansion and fusion under the rate to be transcoded is obtained, and at this time, the comprehensive transcoding feature after dimension expansion and fusion contains a large amount of feature information under different dimensions.
S220, transcoding and judging comprehensive transcoding characteristics of the video to be transcoded in different transcoding rate gears through a pre-constructed transcoding classification model, and determining transcoding factors matched with the video to be transcoded in different transcoding rate gears.
Optionally, a large number of video samples are selected in advance, transcoding factor tags adapted to the video samples in different to-be-transcoded rate gears are set, and then the transcoding classification model in the embodiment is trained until the transcoding classification model can accurately judge the transcoding factors adapted to any video in the different to-be-transcoded rate gears; at this time, after the comprehensive transcoding characteristics of the video to be transcoded in different to-be-transcoded rate gears are determined, as shown in fig. 2B, the comprehensive transcoding characteristics in the different to-be-transcoded rate gears can be sequentially input into a pre-constructed transcoding classification model, and the transcoding classification model is used for performing corresponding transcoding judgment on the comprehensive transcoding characteristics in the different to-be-transcoded rate gears, so that transcoding factors adapted to the video to be transcoded in the different to-be-transcoded rate gears are determined.
In addition, when the transcoding classification model in this embodiment is trained, a large number of video samples are selected, subjective quality indexes of each video sample in different to-be-transcoded rate levels and transcoding factors selected when the subjective quality indexes are reached are determined, the transcoding factors are used as corresponding sample labels, four-order cross multiplication is performed on the picture coding characteristics of the video samples, the to-be-transcoded rate levels and the designated subjective quality indexes for each video sample, comprehensive transcoding characteristics after dimension expansion and fusion are obtained, then the comprehensive transcoding characteristics of the large number of video samples after dimension expansion and fusion are used as corresponding training sample sets, multi-classification training is performed on the training sample sets through the initially set transcoding classification model, and network parameters in the transcoding classification model are continuously updated until the training is completed.
For example, as shown in fig. 2B, in this embodiment, transcoding determination is performed on the comprehensive transcoding characteristics of the video to be transcoded in different to-be-transcoded rate steps through a pre-constructed transcoding classification model, and determining transcoding factors adapted to the video to be transcoded in different to-be-transcoded rate steps may specifically include: aiming at each code rate gear to be transcoded, inputting the comprehensive transcoding characteristics of the video to be transcoded under the code rate gear to be transcoded into a transcoding classification model to obtain classification scores of the video to be transcoded under different preset transcoding factors; and taking the preset transcoding factor with the highest classification score as the transcoding factor of the video to be transcoded, which is adaptive to the gear of the rate to be transcoded.
Specifically, multiple transcoding factors are preset in the transcoding classification model of this embodiment, the comprehensive transcoding characteristics of the video to be transcoded in each to-be-transcoded rate gear are respectively input into the transcoding classification model, the transcoding classification model analyzes the comprehensive transcoding characteristics in each to-be-transcoded rate gear to output the classification scores of the video to be transcoded in the transcoding classification model under different preset transcoding factors, and then the preset transcoding factor with the highest classification score in different to-be-transcoded rate gears is selected as the transcoding factor adapted to the video to be transcoded in the to-be-transcoded rate gear.
It should be noted that, in order to reduce the extra calculation amount in the transcoding classification model, the transcoding classification model in this embodiment may be composed of two or more layers of transcoding classification submodels; for example, a small neural network with three layers is adopted for implementation, the first layer can be a series connection of full connection and convolution, the second layer and the third layer are respectively a series connection of batch standardization, full connection and convolution, and finally, the classification score under each preset transcoding factor is output through a logistic regression layer.
And S230, transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors.
According to the technical scheme provided by the embodiment, the picture coding characteristics, the to-be-transcoded rate gears and the designated subjective quality indexes of the to-be-transcoded video are fused to obtain the comprehensive transcoding characteristics of the to-be-transcoded video in different to-be-transcoded rate gears, transcoding judgment is performed on the comprehensive transcoding characteristics in different to-be-transcoded rate gears through the pre-established transcoding classification model, the transcoding factors matched with the to-be-transcoded video in different to-be-transcoded rate gears are determined, the matching accuracy of the selected transcoding factors in different to-be-transcoded rate gears is guaranteed, reasonable allocation of code rates is achieved, the subjective quality of the to-be-transcoded video in different code rate gears is guaranteed to be consistent, unnecessary code rate waste is avoided, and bandwidth resources are saved.
EXAMPLE III
Fig. 3A is a flowchart of a video transcoding method according to a third embodiment of the present invention, and fig. 3B is a schematic diagram of a video transcoding process according to the third embodiment of the present invention. The present embodiment is optimized based on the above embodiments, and the present embodiment mainly explains the specific extraction process of the picture coding features and subjective quality indicators of the video to be transcoded in detail.
Optionally, as shown in fig. 3A, this embodiment may include the following steps:
s310, extracting the picture coding characteristics corresponding to the video to be transcoded in the lowest code rate gear of different code rate gears to be transcoded and the subjective quality indexes appointed by different code rate gears to be transcoded.
Optionally, in this embodiment, before obtaining the picture coding features of the video to be transcoded, the video to be transcoded is transcoded in a lowest code rate tap of different video to be transcoded, and corresponding picture basic features are extracted from the video transcoded in the lowest code rate tap and used as the picture editing features of the video to be transcoded in this embodiment, and video content included in the video to be transcoded is analyzed through a VMAF algorithm, so that a subjective quality index specified by the video to be transcoded in different video to determine an adapted transcoding factor in the future.
For example, as shown in fig. 3B, in this embodiment, extracting picture coding features corresponding to a video to be transcoded after being transcoded in a lowest bitrate level of different transcoding rate levels may specifically include: transcoding the video to be transcoded by adopting a lowest code rate gear and a fixed transcoding factor under the lowest code rate gear in different gear positions of the rate to be transcoded; extracting key information of the video to be transcoded at the lowest code rate gear, and obtaining a feature set of the video to be transcoded by a certain dimension expansion method according to the resolution and target quality of the video at different gears and the key information.
Specifically, a lowest code rate gear is selected from different to-be-transcoded rate gears, a corresponding fixed transcoding factor is set for the lowest code rate gear in advance in the embodiment, at this time, the lowest code rate gear and the corresponding fixed transcoding factor are adopted to transcode the to-be-transcoded video, key information capable of representing picture characteristic information is extracted from the transcoded video in the lowest code rate gear, and picture coding characteristics of the to-be-transcoded video are obtained by a certain dimension extension method according to the resolution and target quality of the video in different gears and the key information.
S320, according to the picture coding characteristics of the video to be transcoded, determining a transcoding factor selected when the video to be transcoded reaches the subjective quality index specified by the gear of the rate to be transcoded after being transcoded at different gear of the rate to be transcoded.
S330, transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors.
The technical scheme provided by the embodiment includes that the picture coding characteristics corresponding to a video to be transcoded in the lowest code rate gear of different gear positions of the rate to be transcoded are obtained, the accuracy of the picture coding characteristics is guaranteed, the transcoding factor selected when the picture coding characteristics of the video to be transcoded reach the designated subjective quality index in the gear position to be transcoded under the cooperation of the corresponding transcoding factor in the gear position to be transcoded is further determined, at the moment, the effect of transcoding any video to be transcoded according to the predicted transcoding factor is compared with the designated subjective quality index, the subjective playing quality of any video to be transcoded in different code rate gears is accurately measured, the accuracy of the selected transcoding factor in different code rate gears is guaranteed, then, the transcoding of the video to be transcoded is carried out at multiple code rates by adopting different gear positions to be transcoded and the corresponding transcoding factor, therefore, the reasonable allocation of the code rate is realized, the subjective quality consistency of the video to be transcoded under different code rate gears is ensured, the unnecessary code rate waste is avoided, and the bandwidth resource is saved.
Example four
Fig. 4 is a schematic structural diagram of an apparatus for video transcoding according to a fourth embodiment of the present invention, specifically, as shown in fig. 4, the apparatus may include:
the transcoding factor determining module 410 is configured to determine, according to picture coding characteristics of a video to be transcoded, a transcoding factor adopted when the video to be transcoded reaches a subjective quality index specified by a to-be-transcoded rate level after being transcoded at different to-be-transcoded rate levels;
and the video transcoding module 420 is configured to transcode the video to be transcoded by using different transcoding rate steps and corresponding transcoding factors.
The technical scheme provided by the embodiment is that a subjective quality index required to be reached after video transcoding is specified in advance in each gear of a code rate to be transcoded, so that the same subjective quality index is set in the same gear of the code rate to be transcoded, the subjective quality of the video to be transcoded in the same gear of the code rate is guaranteed to be consistent, at the moment, in each gear of the code rate to be transcoded, a plurality of transcoding factors are respectively matched and selected for transcoding the video to be transcoded, transcoding factors selected when the picture coding characteristics of the video to be transcoded reach the specified subjective quality index in the gear of the code rate to be transcoded after transcoding is carried out in the matching of the corresponding transcoding factors are determined, then the transcoding factors in each gear of the code rate to be transcoded are determined, at the moment, the transcoding effect of any video to be transcoded according to the predicted transcoding factors is compared with the specified subjective quality index, the method has the advantages that the subjective playing quality of any video to be transcoded under different code rate gears is accurately measured, the accuracy of selected transcoding factors under different code rate gears is guaranteed, then multi-code rate transcoding is carried out on the video to be transcoded by adopting different code rate gears to be transcoded and corresponding transcoding factors, so that reasonable allocation of code rates is achieved, the subjective quality of the video to be transcoded under different code rate gears is guaranteed to be consistent, unnecessary code rate waste is avoided, and bandwidth resources are saved.
Further, the transcoding factor determining module 410 may include:
the feature fusion unit is used for fusing the picture coding features of the video to be transcoded, the gear of the rate to be transcoded and a specified subjective quality index aiming at each gear of the code rate to be transcoded to obtain the comprehensive transcoding features of the video to be transcoded under the gear of the rate to be transcoded;
and the transcoding factor adapting unit is used for respectively carrying out transcoding judgment on the comprehensive transcoding characteristics of the video to be transcoded in different to-be-transcoded rate gears through a pre-constructed transcoding classification model and determining the transcoding factors adapted to the video to be transcoded in different to-be-transcoded rate gears.
Further, the feature fusion unit may be specifically configured to:
and performing dimension expansion fusion on the picture coding characteristics of the video to be transcoded, the gear of the rate to be transcoded and the specified subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the gear of the rate to be transcoded.
Further, the transcoding factor adapting unit may be specifically configured to:
aiming at each code rate gear to be transcoded, inputting the comprehensive transcoding characteristics of the video to be transcoded under the code rate gear to be transcoded into a transcoding classification model to obtain classification scores of the video to be transcoded under different preset transcoding factors;
and taking the preset transcoding factor with the highest classification score as the transcoding factor of the video to be transcoded, which is adaptive to the gear of the rate to be transcoded.
Further, the transcoding classification model may be composed of two or more transcoding classification submodels.
Further, the apparatus for transcoding video may further include:
and the transcoding parameter extraction module is used for extracting the picture coding characteristics corresponding to the video to be transcoded in the lowest code rate gear of different code rate gears to be transcoded and the subjective quality indexes specified by different code rate gears to be transcoded.
Further, the video transcoding apparatus may be specifically configured to:
transcoding the video to be transcoded by adopting a lowest code rate gear and a fixed transcoding factor under the lowest code rate gear in different gear positions of the rate to be transcoded;
and extracting key frames of the video to be transcoded at the lowest code rate gear, and combining picture coding parameters in the key frames to obtain picture coding characteristics of the video to be transcoded.
The video transcoding device provided by the embodiment can be applied to the video transcoding method provided by any of the above embodiments, and has corresponding functions and beneficial effects.
EXAMPLE five
Fig. 5 is a schematic structural diagram of a server according to a fifth embodiment of the present invention, and as shown in fig. 5, the server includes a processor 50, a storage device 51, and a communication device 52; the number of the processors 50 in the server may be one or more, and one processor 50 is taken as an example in fig. 5; the processor 50, the storage device 51 and the communication device 52 in the server may be connected by a bus or other means, and the bus connection is taken as an example in fig. 5.
The storage device 51, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the video transcoding method provided in the embodiments of the present invention. The processor 50 executes various functional applications of the server and data processing by running software programs, instructions and modules stored in the storage device 51, namely, implements the video transcoding method described above.
The storage device 51 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the storage 51 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage device 51 may further include memory located remotely from the processor 50, which may be connected to a server over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The communication means 62 may be used to enable a network connection or a mobile data connection between the server and the terminal.
The server provided by this embodiment can be used to execute the video transcoding method provided by any of the above embodiments, and has corresponding functions and advantages.
EXAMPLE six
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, can implement the method for transcoding a video in any of the above embodiments. The method specifically comprises the following steps:
determining a transcoding factor selected when the video to be transcoded reaches a subjective quality index specified by a gear to be transcoded after being transcoded at different gear to be transcoded according to the picture coding characteristics of the video to be transcoded;
and transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the method for transcoding a video provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the apparatus for transcoding video, the units and modules included in the apparatus are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A method of video transcoding, comprising:
extracting picture coding characteristics corresponding to a video to be transcoded in the lowest code rate gear of different code rate gears to be transcoded and subjective quality indexes specified by different code rate gears to be transcoded;
determining a transcoding factor selected when the video to be transcoded reaches a subjective quality index specified by a gear to be transcoded after being transcoded at different gear to be transcoded according to the picture coding characteristics of the video to be transcoded;
and transcoding the video to be transcoded by adopting different transcoding rate gears to be transcoded and corresponding transcoding factors.
2. The method according to claim 1, wherein determining a transcoding factor adopted when the video to be transcoded reaches a subjective quality index specified by a rate range to be transcoded after being transcoded at different rate ranges to be transcoded according to picture coding characteristics of the video to be transcoded comprises:
for each code rate gear to be transcoded, fusing the picture coding characteristics of the video to be transcoded, the gear to be transcoded and a specified subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the gear to be transcoded;
and respectively carrying out transcoding judgment on the comprehensive transcoding characteristics of the video to be transcoded in different transcoding rate gears through a pre-constructed transcoding classification model, and determining transcoding factors adapted to the video to be transcoded in different transcoding rate gears.
3. The method according to claim 2, wherein the step of fusing the picture coding characteristics of the video to be transcoded, the rate range to be transcoded and the specified subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the rate range to be transcoded comprises the steps of:
and performing dimension expansion fusion on the picture coding characteristics of the video to be transcoded, the gear of the rate to be transcoded and a specified subjective quality index to obtain the comprehensive transcoding characteristics of the video to be transcoded in the gear of the rate to be transcoded.
4. The method of claim 2, wherein the transcoding judgment of the comprehensive transcoding characteristics of the video to be transcoded in different transcoding rate steps is performed through a pre-constructed transcoding classification model, and the determination of the transcoding factors adapted to the video to be transcoded in different transcoding rate steps comprises:
aiming at each code rate gear to be transcoded, inputting the comprehensive transcoding characteristics of the video to be transcoded in the code rate gear to be transcoded into the transcoding classification model to obtain the classification scores of the video to be transcoded under different preset transcoding factors;
and taking the preset transcoding factor with the highest classification score as the transcoding factor of the video to be transcoded, which is adaptive to the gear of the rate to be transcoded.
5. The method of claim 2, wherein the transcoding classification model is comprised of two or more layers of transcoding classification submodels.
6. The method of claim 1, wherein extracting picture coding features corresponding to the video to be transcoded in a lowest code rate position of different code rate positions comprises:
transcoding the video to be transcoded by adopting a lowest code rate gear in different code rate gears to be transcoded and a fixed transcoding factor under the lowest code rate gear;
and extracting key frames of the video to be transcoded at the lowest code rate gear, and combining picture coding parameters in the key frames to obtain picture coding characteristics of the video to be transcoded.
7. An apparatus for video transcoding, comprising:
the transcoding parameter extraction module is used for extracting picture coding characteristics corresponding to a video to be transcoded in the lowest code rate gear of different code rate gears to be transcoded and subjective quality indexes specified by different code rate gears to be transcoded; the transcoding factor determining module is used for determining a transcoding factor adopted when the video to be transcoded reaches a subjective quality index specified by a gear to be transcoded after being transcoded at different gear to be transcoded according to the picture coding characteristics of the video to be transcoded;
and the video transcoding module is used for transcoding the video to be transcoded by adopting different transcoding rate gears and corresponding transcoding factors.
8. A server, characterized in that the server comprises:
one or more processors;
storage means for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method of video transcoding as recited in any of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of video transcoding as claimed in any one of claims 1 to 6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410012.0A CN111107395B (en) | 2019-12-31 | 2019-12-31 | Video transcoding method, device, server and storage medium |
| PCT/CN2020/137513 WO2021135983A1 (en) | 2019-12-31 | 2020-12-18 | Video transcoding method and apparatus, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911410012.0A CN111107395B (en) | 2019-12-31 | 2019-12-31 | Video transcoding method, device, server and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111107395A CN111107395A (en) | 2020-05-05 |
| CN111107395B true CN111107395B (en) | 2021-08-03 |
Family
ID=70424089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911410012.0A Active CN111107395B (en) | 2019-12-31 | 2019-12-31 | Video transcoding method, device, server and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111107395B (en) |
| WO (1) | WO2021135983A1 (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111107395B (en) * | 2019-12-31 | 2021-08-03 | 广州市百果园网络科技有限公司 | Video transcoding method, device, server and storage medium |
| CN111726656B (en) * | 2020-07-20 | 2022-07-26 | 有半岛(北京)信息科技有限公司 | Transcoding method, device, server and storage medium of live video |
| CN111901631B (en) * | 2020-07-30 | 2023-02-17 | 有半岛(北京)信息科技有限公司 | Transcoding method, device, server and storage medium for live video |
| CN111970565A (en) * | 2020-09-21 | 2020-11-20 | Oppo广东移动通信有限公司 | Video data processing method and device, electronic equipment and storage medium |
| CN115134639B (en) * | 2021-03-24 | 2023-12-19 | 北京字跳网络技术有限公司 | Video gear determining method, device, server, storage medium and system |
| CN113259730B (en) * | 2021-07-06 | 2021-12-14 | 北京达佳互联信息技术有限公司 | Code rate adjustment method and device for live broadcast |
| CN113891155B (en) * | 2021-09-29 | 2024-04-05 | 百果园技术(新加坡)有限公司 | Video playing gear determining method, video playing method and related devices |
| CN114025190B (en) * | 2021-11-03 | 2023-06-20 | 北京达佳互联信息技术有限公司 | Multi-code rate scheduling method and multi-code rate scheduling device |
| CN114040230B (en) * | 2021-11-08 | 2024-03-29 | 北京达佳互联信息技术有限公司 | Video code rate determining method and device, electronic equipment and storage medium thereof |
| CN114598927A (en) * | 2022-03-03 | 2022-06-07 | 京东科技信息技术有限公司 | Method and system for scheduling transcoding resources and scheduling device |
| CN114760506B (en) * | 2022-04-11 | 2024-02-09 | 北京字跳网络技术有限公司 | Video transcoding evaluation method, device, equipment and storage medium |
| CN115002520B (en) * | 2022-04-14 | 2024-04-02 | 百果园技术(新加坡)有限公司 | Video stream data processing method, device, equipment and storage medium |
| CN115379248B (en) * | 2022-07-14 | 2023-12-12 | 百果园技术(新加坡)有限公司 | Video source stream replacement method, system, equipment and storage medium |
| CN115379291B (en) * | 2022-07-19 | 2023-12-26 | 百果园技术(新加坡)有限公司 | Code table updating method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105187835A (en) * | 2014-05-30 | 2015-12-23 | 阿里巴巴集团控股有限公司 | Adaptive video transcode method and device based on contents |
| CN106713956A (en) * | 2016-11-16 | 2017-05-24 | 上海交通大学 | Rate control and version selection method and system for dynamic adaptive video streaming media |
| CN107820084A (en) * | 2016-09-13 | 2018-03-20 | 北京金山云网络技术有限公司 | A kind of video-aware coding method and device |
| CN109286825A (en) * | 2018-12-14 | 2019-01-29 | 北京百度网讯科技有限公司 | Method and apparatus for handling video |
| CN109729384A (en) * | 2018-12-18 | 2019-05-07 | 广州市百果园信息技术有限公司 | The selection method and device of video code conversion |
| CN110248189A (en) * | 2019-06-14 | 2019-09-17 | 北京字节跳动网络技术有限公司 | A kind of video quality prediction technique, device and electronic equipment |
| CN110418177A (en) * | 2019-04-19 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Method for video coding, device, equipment and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150172680A1 (en) * | 2013-12-16 | 2015-06-18 | Arris Enterprises, Inc. | Producing an Output Need Parameter for an Encoder |
| US10298969B2 (en) * | 2016-11-10 | 2019-05-21 | University Of Louisiana At Lafayette | Architecture and method for high performance on demand video transcoding |
| AU2017368324B2 (en) * | 2016-12-01 | 2022-08-25 | Brightcove, Inc. | Optimization of encoding profiles for media streaming |
| CN109391825A (en) * | 2017-08-03 | 2019-02-26 | 腾讯科技（深圳）有限公司 | A kind of video transcoding method and its device, server, readable storage medium storing program for executing |
| CN109660825B (en) * | 2017-10-10 | 2021-02-09 | 腾讯科技（深圳）有限公司 | Video transcoding method and device, computer equipment and storage medium |
| US10587669B2 (en) * | 2017-12-20 | 2020-03-10 | Facebook, Inc. | Visual quality metrics |
| CN108174290B (en) * | 2018-01-25 | 2019-05-24 | 北京百度网讯科技有限公司 | Method and apparatus for handling video |
| CN110248195B (en) * | 2019-07-17 | 2021-11-05 | 北京百度网讯科技有限公司 | Method and apparatus for outputting information |
| CN110493196A (en) * | 2019-07-24 | 2019-11-22 | 深圳市瑞讯云技术有限公司 | A kind of video code conversion unit and video code conversion component |
| CN111107395B (en) * | 2019-12-31 | 2021-08-03 | 广州市百果园网络科技有限公司 | Video transcoding method, device, server and storage medium |
-
2019
- 2019-12-31 CN CN201911410012.0A patent/CN111107395B/en active Active
-
2020
- 2020-12-18 WO PCT/CN2020/137513 patent/WO2021135983A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105187835A (en) * | 2014-05-30 | 2015-12-23 | 阿里巴巴集团控股有限公司 | Adaptive video transcode method and device based on contents |
| CN107820084A (en) * | 2016-09-13 | 2018-03-20 | 北京金山云网络技术有限公司 | A kind of video-aware coding method and device |
| CN106713956A (en) * | 2016-11-16 | 2017-05-24 | 上海交通大学 | Rate control and version selection method and system for dynamic adaptive video streaming media |
| CN109286825A (en) * | 2018-12-14 | 2019-01-29 | 北京百度网讯科技有限公司 | Method and apparatus for handling video |
| CN109729384A (en) * | 2018-12-18 | 2019-05-07 | 广州市百果园信息技术有限公司 | The selection method and device of video code conversion |
| CN110418177A (en) * | 2019-04-19 | 2019-11-05 | 腾讯科技（深圳）有限公司 | Method for video coding, device, equipment and storage medium |
| CN110248189A (en) * | 2019-06-14 | 2019-09-17 | 北京字节跳动网络技术有限公司 | A kind of video quality prediction technique, device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 《IPTV视频质量评估模型的研究》;张程祺;《中国优秀硕士学位论文全文数据库》;20190915;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021135983A1 (en) | 2021-07-08 |
| CN111107395A (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111107395B (en) | Video transcoding method, device, server and storage medium | |
| CN109286825B (en) | Method and apparatus for processing video | |
| US20220030244A1 (en) | Content adaptation for streaming | |
| CN111950653B (en) | Video processing method and device, storage medium and electronic equipment | |
| US20210160556A1 (en) | Method for enhancing resolution of streaming file | |
| CN109844736B (en) | Summarizing video content | |
| CN107222795B (en) | Multi-feature fusion video abstract generation method | |
| CN112954312B (en) | Non-reference video quality assessment method integrating space-time characteristics | |
| CN103414915B (en) | Quality evaluation method and device for uploaded videos of websites | |
| CN111669627B (en) | Method, device, server and storage medium for determining video code rate | |
| US11928793B2 (en) | Video quality assessment method and apparatus | |
| CN112637675B (en) | Video generation method, device, electronic equipment and storage medium | |
| CN114554211A (en) | Content adaptive video coding method, device, equipment and storage medium | |
| CN112383824A (en) | Video advertisement filtering method, device and storage medium | |
| CN111432206A (en) | Video definition processing method and device based on artificial intelligence and electronic equipment | |
| CN111726656A (en) | Transcoding method, device, server and storage medium for live video | |
| CN113452996B (en) | Video coding and decoding method and device | |
| CN114339362B (en) | Video bullet screen matching method, device, computer equipment and storage medium | |
| WO2024017106A1 (en) | Code table updating method, apparatus, and device, and storage medium | |
| CN111767428A (en) | Video recommendation method and device, electronic equipment and storage medium | |
| Micó-Enguídanos et al. | Per-title and per-segment CRF estimation using DNNs for quality-based video coding | |
| CN111901631B (en) | Transcoding method, device, server and storage medium for live video | |
| CN113382241A (en) | Video encoding method, video encoding device, electronic equipment and storage medium | |
| CN116743609B (en) | QoE evaluation method and device for video streaming media based on semantic communication | |
| WO2024109138A1 (en) | Video encoding method and apparatus 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220627 Address after: 31a, 15 / F, building 30, maple mall, bangrang Road, Brazil, Singapore Patentee after: Baiguoyuan Technology (Singapore) Co.,Ltd. Address before: Floor 4, 5, 6, 13, 14, 15, 16, Jisheng business center, 278 Xingtai Road, Shiqiao street, Panyu District, Guangzhou, Guangdong 510000 Patentee before: GUANGZHOU BAIGUOYUAN NETWORK TECHNOLOGY Co.,Ltd. |