CN115734045B - Video playing method, device, equipment and storage medium - Google Patents
Video playing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115734045B CN115734045B CN202211425128.3A CN202211425128A CN115734045B CN 115734045 B CN115734045 B CN 115734045B CN 202211425128 A CN202211425128 A CN 202211425128A CN 115734045 B CN115734045 B CN 115734045B
- Authority
- CN
- China
- Prior art keywords
- picture
- video
- time stamp
- track
- frame
- 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 68
- 238000000605 extraction Methods 0.000 claims abstract description 30
- 230000007613 environmental effect Effects 0.000 claims description 24
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 239000012634 fragment Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to a video playing method, a video playing device, video playing equipment and a storage medium. Acquiring a video clip to be confirmed; taking one frame of picture in the video segment to be confirmed as a picture to be tested for feature extraction; determining the characteristics of the picture to be detected by utilizing the characteristic extraction; the features include at least one of scene placement, dressing features, actor information; and according to the characteristics, searching the picture to be detected to determine a target video and displaying the target video.
Description
Technical Field
The present application relates to the field of video playing technologies, and in particular, to a video playing method, device, equipment and storage medium.
Background
With rapid development of technology, video playing platforms are increasing. People also increasingly rely on the use of video playback platforms over networks to learn news, interesting trivia in life, or to watch interesting television shows, movies, etc. via video playback platforms.
As these video playback platforms become more diverse, so too does the user's selectivity. Accordingly, the problem arises that the user gets fragments more and more fragmented. For example, many users browse a segment of interest on a video playback platform, but because the segment is too fragmented, the corresponding video asset cannot be obtained. This results in a user being unable to view the corresponding video asset, thereby greatly affecting the user's experience.
Disclosure of Invention
The application provides a video playing method, a video playing device, video playing equipment and a storage medium.
In a first aspect, the present application provides a video playing method, the method comprising:
Acquiring a video clip to be confirmed;
taking one frame of picture in the video segment to be confirmed as a picture to be tested for feature extraction;
determining the characteristics of the picture to be detected by utilizing the characteristic extraction; the features include at least one of scene placement, dressing features, actor information;
and according to the characteristics, searching the picture to be detected to determine a target video and displaying the target video.
According to the method, after the video segment to be confirmed is obtained, feature extraction is carried out, and after the features are confirmed, the target video is obtained by searching the features. After browsing the related interested videos, the user can obtain the target video and the corresponding playing source in time by the method provided by the application. The key problem that the user cannot find the target video is solved, and the experience of the user is improved.
Optionally, the feature extraction of taking a frame of picture in the video clip to be confirmed as a picture to be tested includes:
determining the number of feature types in each frame of picture of the video clip to be confirmed by using a preset feature type;
Sequencing the number of the feature types in each frame of picture, and determining the picture frame with the largest feature number;
and taking the picture frame with the largest feature quantity as a picture to be detected to extract features.
By means of the method, the number of the feature types of the video clips to be confirmed is summarized, the number of the feature types of the video clips to be confirmed is ordered, and a frame of picture with the largest feature types is obtained. The search range can be reduced, and the workload can be reduced. The accuracy of the search can also be improved by searching one frame of picture with the most characteristic types.
Optionally, the searching the picture to be detected according to the feature to determine the target video and displaying includes:
determining the character image in the characteristics according to the characteristics;
Determining information corresponding to actors of the character image according to the character image;
Determining the participations of the actors of the character image according to the information;
And comparing the picture to be detected with the reference work to determine a target video and displaying the target video.
By means of the method, the extracted character image features are analyzed, and actor information of the role player is determined. And obtain the actor's participation from the corresponding actor information. And comparing the video segment to be confirmed with the reference, and confirming and displaying the target video. This approach can correspond to the corresponding actor at the fastest speed, improving the retrieval speed and accuracy of the retrieval.
Optionally, the searching the picture to be detected according to the feature to determine the target video and displaying includes:
according to the characteristics, searching the picture to be detected to obtain the target video;
acquiring the authority of the target video;
and sequencing and displaying the target videos by using the preset priority and the authority.
By means of the method, when the target video is retrieved for display, the playing authorities of different playing sources can be obtained, and the playing sources are ordered according to the playing authorities, so that a user can obtain the best playing source according to the ordering result, and more convenient service is provided for the user. And the experience of the user is improved.
Optionally, the method further comprises:
Acquiring a network bandwidth at the current moment;
matching the image quality grade corresponding to the network bandwidth by utilizing the network bandwidth range corresponding to the preset image quality grade;
according to the matching result, adjusting the image quality at the current moment;
And playing the target video by utilizing the image quality.
The method provided by the embodiment can enable the video to be smoothly played by acquiring the network bandwidth at the current moment and performing corresponding image quality grade matching and adjustment. The network bandwidth can be obtained in real time in the playing process, when the network bandwidth is changed, corresponding image quality grade matching is timely carried out, the image quality is adjusted, smooth playing of the video is ensured, and the video playing is prevented from being blocked due to poor network bandwidth data, so that the experience of a user is prevented from being influenced.
Optionally, the method further comprises:
Acquiring environmental noise at the current moment;
comparing the environmental noise with a preset noise threshold value, and determining a level corresponding to the environmental noise;
and according to the level, determining a volume adjusting range corresponding to the current moment and taking the minimum value in the volume adjusting range as the playing volume.
The embodiment provides a volume adjustment mode, when environmental noise changes at the current moment, the environmental noise is timely acquired and matched with a preset noise threshold value, a corresponding volume adjustable range is determined, and the minimum volume value of the volume adjustable range is used as an adjustment target to adjust the volume. The method can avoid the problem that the user cannot hear the video playing sound due to sudden noise in the watching process, and the hearing of the user cannot be impacted by adjusting the minimum volume of the volume adjustable range, so that the user has better volume adjustment experience.
Optionally, the method further comprises:
Acquiring a time stamp corresponding to a sound track, a time stamp corresponding to a picture track and a time stamp corresponding to a subtitle track of the target video;
judging whether the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are consistent;
and if the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are inconsistent, judging that the track corresponding to the inconsistent time stamp exists, and calibrating according to a preset time stamp calibration rule.
According to the method and the device, the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are obtained, and when the situation that the sound track is inconsistent is compared and confirmed, the time stamp corresponding to the inconsistent track is calibrated according to the preset time stamp calibration rule, so that the problem of asynchronous sound and picture can be solved in the shortest time. Thereby improving the experience of the user.
In a second aspect, the present application provides a video playing device, including:
The segment acquisition module is used for acquiring the video segment to be confirmed;
the feature extraction module is used for extracting features by taking a frame of picture in the video segment to be confirmed as a picture to be detected;
the feature determining module is used for determining the features of the picture to be detected by utilizing the feature extraction; the features include at least one of scene placement, dressing features, actor information;
and the fragment retrieval and display module is used for retrieving and displaying the target video for the picture to be detected according to the characteristics.
Optionally, the feature extraction module is specifically configured to:
determining the number of feature types in each frame of picture of the video clip to be confirmed by using a preset feature type;
Sequencing the number of the feature types in each frame of picture, and determining the picture frame with the largest feature number;
and taking the picture frame with the largest feature quantity as a picture to be detected to extract features.
Optionally, the fragment retrieval display module is specifically configured to:
determining the character image in the characteristics according to the characteristics;
Determining information corresponding to actors of the character image according to the character image;
Determining the participations of the actors of the character image according to the information;
And comparing the picture to be detected with the reference work to determine a target video and displaying the target video.
Optionally, the fragment retrieval display module is specifically further configured to:
according to the characteristics, searching the picture to be detected to obtain the target video;
acquiring the authority of the target video;
and sequencing and displaying the target videos by using the preset priority and the authority.
Optionally, the device further includes an image quality adjustment module, configured to:
Acquiring a network bandwidth at the current moment;
matching the image quality grade corresponding to the network bandwidth by utilizing the network bandwidth range corresponding to the preset image quality grade;
according to the matching result, adjusting the image quality at the current moment;
And playing the target video by utilizing the image quality.
Optionally, the apparatus further includes a volume adjustment module configured to:
Acquiring environmental noise at the current moment;
comparing the environmental noise with a preset noise threshold value, and determining a level corresponding to the environmental noise;
and according to the level, determining a volume adjusting range corresponding to the current moment and taking the minimum value in the volume adjusting range as the playing volume.
Optionally, the apparatus further comprises a calibration module for:
Acquiring a time stamp corresponding to a sound track, a time stamp corresponding to a picture track and a time stamp corresponding to a subtitle track of the target video;
judging whether the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are consistent;
and if the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are inconsistent, judging that the track corresponding to the inconsistent time stamp exists, and calibrating according to a preset time stamp calibration rule.
In a third aspect, the present application provides a video playback device comprising: a memory and a processor, the memory having stored thereon a computer program capable of being loaded by the processor and performing the method of the first aspect.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program capable of being loaded by a processor and performing the method of the first aspect.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;
Fig. 2 is a flowchart of a video playing method according to an embodiment of the present application;
Fig. 3 is a schematic structural diagram of a video playing device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a video playing device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
Embodiments of the application are described in further detail below with reference to the drawings.
As video playback platforms become more diverse, so too does the user's selectivity. Accordingly, the problem arises that the user gets fragments more and more fragmented. For example, many users browse a segment of interest on a video playback platform, but because the segment is too fragmented, the corresponding video asset cannot be obtained. This results in a user being unable to view the corresponding video asset, thereby greatly affecting the user's experience.
Based on the above, the application provides a video playing method, a device, equipment and a storage medium.
And extracting the characteristics of a frame of picture in the video segment to be confirmed as a picture to be confirmed by acquiring the video segment to be confirmed, searching according to the corresponding characteristics, determining a target video of the video segment to be confirmed and displaying. By the method, when a user browses the video clips of interest, the target video can be timely, efficiently and accurately searched and watched by the method provided by the application. Solve the fragment fragmentation problem and improve the experience of users.
Fig. 1 is a schematic view of an application scenario provided by the present application. The server acquires fragments to be confirmed of other video playing platforms provided by the user equipment. After the acquisition is successful, one frame of picture is selected as the picture to be detected for feature extraction. And carrying out related retrieval according to the feature extraction result to obtain a target video, and displaying the target video in user equipment. Reference may be made to the following examples for specific implementation.
Fig. 2 is a flowchart of a video playing method according to an embodiment of the present application, where the method of the present embodiment may be applied to a server in the above scenario. As shown in fig. 2, the method includes:
s201, obtaining a video clip to be confirmed.
The video clip to be confirmed is the video clip of interest transmitted by the user, and can also be the screenshot corresponding to the video clip of interest transmitted by the user.
S202, taking a frame of picture in the video segment to be confirmed as a picture to be detected for feature extraction.
The determination of a frame of picture can be one frame with the most characteristic types, or can be one frame with representative meaning, such as the existence of task images, scene information and the like.
Specifically, feature extraction can be performed on the picture to be detected by setting a deep learning model, and key features of the picture are confirmed.
S203, determining the characteristics of the picture to be detected by utilizing the characteristic extraction; the features include at least one of scene placement, dressing features, actor information.
After the feature extraction in step S202, the features existing in the picture to be measured are determined. Such as scene type: ancient costume scenes, modern scenes; dressing characteristics: ancient dressing and modern dressing; actor information: gender, name, age, participants, activities, near conditions, etc.
S204, searching the picture to be detected according to the characteristics to determine a target video and displaying the target video.
Specifically, after determining the features in the picture to be detected in step S203, the features may be matched by using the deep learning model. And the target video can be obtained and displayed by retrieving the database content.
A deep learning model is constructed, and the deep learning model is trained by means of a large amount of data, so that the deep learning model has the capability of classifying picture features. The data is feature data in each frame of picture in different dramas, such as image information of people, background features, makeup, and the like. And transmitting the segment to be confirmed obtained in the step S201 to a trained deep learning model, and realizing the step S201-S204 by automatically identifying the deep learning model, confirming the characteristics of a picture to be tested in the video segment to be confirmed, and further searching and displaying the target video.
According to the method, after the video segment to be confirmed is obtained, feature extraction is carried out, and after the features are confirmed, the target video is obtained by searching the features. After browsing the related interested videos, the user can obtain the target video and the corresponding playing source in time by the method provided by the application. The key problem that the user cannot find the target video is solved, and the experience of the user is improved.
In some embodiments, the picture under test may be determined by determining the number of feature types. And if one frame of picture with the most characteristic types is taken as the picture to be detected, carrying out characteristic extraction. Specifically, the method comprises the following steps: determining the number of feature types in each frame of picture of the video clip to be confirmed by using the preset feature types; sequencing the number of the feature types in each frame of picture, and determining the picture frame with the largest feature number; and taking the picture frame with the largest feature quantity as a picture to be detected to extract the features.
The preset feature types may be adjusted accordingly, including scene type, make-up type, dressing type, etc. Scene types such as modern dramas are mostly tall buildings, ancient costume dramas are mostly courtyard pavilions, and the swordsman dramas are mostly dreamy arrangements; hair types such as long hair, curly hair, and various styling, which are typical of modern dramas; ancient costume are popular models with historic characteristics; the pattern of the natural gas is mainly the natural gas. By way of example only, those skilled in the art will recognize that adjustments to the preset feature types may be made by reviewing the material or browsing the corresponding episodes.
Specifically, after the video clip to be confirmed is obtained through the steps, each frame of the video clip to be confirmed is subjected to feature type statistics, the feature type number of each frame of the video clip to be confirmed is confirmed, and the video clip is sequenced to obtain a frame of the video clip with the largest feature type number. And carrying out detailed feature extraction and recognition on the frame of picture with the largest number of feature types.
In some implementations, a priority of feature types may be set, such as a character image priority over a make-up hair style; make-up styling priority over scene type, etc. After the sorting, a plurality of frame pictures with the feature types in parallel number can exist, and then the frame pictures with the feature types in the same number are subjected to priority sorting. If more than half of the feature types in a certain frame of picture have higher priority than other frames of pictures, the frame of picture can be determined as a picture to be detected for feature extraction.
By means of the method, the number of the feature types of the video clips to be confirmed is summarized, the number of the feature types of the video clips to be confirmed is ordered, and a frame of picture with the largest feature types is obtained. The search range can be reduced, and the workload can be reduced. The accuracy of the search can also be improved by searching one frame of picture with the most characteristic types.
In some embodiments, the target video to which the video segment to be confirmed belongs may be determined by determining the character image in the feature. Specifically, the method comprises the following steps: determining character images in the features according to the features; determining information corresponding to actors of the character image according to the character image; determining the participation of actors of the character image according to the information; and comparing the picture to be detected with the reference work to determine a target video and displaying the target video.
The character image mainly includes facial features of a character. Actor information of a player of a person is determined by acquiring facial features of the person. Actor information may include personal basic information of the actor (such as gender, height, age, constellation, etc.), participants, recent events, etc.
Specifically, after the corresponding features are extracted through the steps, character image analysis is performed, actor information of the role player is determined, corresponding participants are called to be compared with the video segments to be confirmed, and then target videos of the video segments to be confirmed are confirmed and displayed.
By means of the method, the extracted character image features are analyzed, and actor information of the role player is determined. And obtain the actor's participation from the corresponding actor information. And comparing the video segment to be confirmed with the reference, and confirming and displaying the target video. This approach can correspond to the corresponding actor at the fastest speed, improving the retrieval speed and accuracy of the retrieval.
In some embodiments, the target videos may be ordered by rights type so that the user can intuitively view the playable source. Specifically, the method comprises the following steps: according to the characteristics, searching the picture to be detected to obtain a target video; acquiring the authority of a target video; and sequencing and displaying the target videos by using preset priority and authority.
Rights in this embodiment may represent play rights, such as whether play requires a member, whether play requires payment. The preset priority is also set according to the authority, for example, the priority of the unnecessary member is higher than the priority of the necessary member, and the priority of the necessary member is higher than the priority of the necessary payment. The target videos of the different video playing platforms are ordered according to the sequence. So that the user can find the most suitable playing platform at the first time.
In some implementations, the priority of the click rate may also be set, and the target videos are ranked according to the click rates of the target videos on different video playing platforms from high to low. The higher the click-through, the higher the entitlement, and the higher the rank. The user can judge which video playing platform has better experience according to the condition, and can correspondingly select which video playing platform.
By means of the method, when the target video is retrieved for display, the playing authorities of different playing sources can be obtained, and the playing sources are ordered according to the playing authorities, so that a user can obtain the best playing source according to the ordering result, and more convenient service is provided for the user. And the experience of the user is improved.
In some embodiments, the network bandwidth at the current time may be acquired, and the image quality level may be determined according to the network bandwidth, so as to adjust the image quality at the current time. Specifically, the method further comprises the following steps: acquiring a network bandwidth at the current moment; matching the image quality grade corresponding to the network bandwidth by utilizing the network bandwidth range corresponding to the preset image quality grade; according to the matching result, adjusting the image quality at the current moment; and playing the target video by using the image quality.
Network bandwidth is mainly the bandwidth in a network, which means the amount of information, i.e. the data transmission rate, that flows from one end to the other within a defined time. The network condition of the current environment can be obtained by obtaining the information of the network bandwidth in the playing process.
The preset image quality level is set according to the fluency of video playing under different network bandwidth states. The network bandwidth range can be understood as the network bandwidth within the set range, so that the video playing under the current image quality can be smooth.
In some implementations, setting the network bandwidth range corresponding to the image quality may be performed by building a deep learning model. In addition, a person skilled in the art may set the network bandwidth range corresponding to the preset image quality level according to experience. And constructing a deep learning model, and training the deep learning model by means of a large amount of image quality data to enable the deep learning model to have the capability of matching network bandwidth with corresponding image quality grades. The image quality data is image quality capable of smoothly playing video under different network bandwidth states. And inputting the network bandwidth at the current moment into a trained deep learning model, and confirming the image quality grade corresponding to the network bandwidth at the current moment through automatic identification of the deep learning model.
Specifically, the network bandwidth at the current moment is obtained, and the obtained network bandwidth is compared with the network bandwidth range corresponding to the preset image quality level. The video playing at the current moment can be smooth by determining the network bandwidth range to which the network bandwidth at the current moment belongs and judging the image quality grade corresponding to the network bandwidth range based on the network bandwidth range. And according to the matching result, taking the determined image quality grade as the image quality of the current moment and adjusting to play the target video.
The method provided by the embodiment can enable the video to be smoothly played by acquiring the network bandwidth at the current moment and performing corresponding image quality grade matching and adjustment. The network bandwidth can be obtained in real time in the playing process, when the network bandwidth is changed, corresponding image quality grade matching is timely carried out, the image quality is adjusted, smooth playing of the video is ensured, and the video playing is prevented from being blocked due to poor network bandwidth data, so that the experience of a user is prevented from being influenced.
In some embodiments, ambient noise may be acquired and the play volume of the video adjusted. Specifically, the method further comprises the following steps: acquiring environmental noise at the current moment; comparing the environmental noise with a preset noise threshold value, and determining the corresponding level of the environmental noise; and determining a volume adjusting range corresponding to the current moment according to the level, and taking the minimum value in the volume adjusting range as the playing volume.
Ambient noise refers to everything around that can create sounds that interfere with the surrounding living environment. Such as talking sounds from person to person, pet calls, etc.
The preset noise threshold value can also be set correspondingly through the deep learning model in the embodiment, a new deep learning model is constructed, a large amount of noise data is input to train the deep learning model, and the proper volume range can be determined when different noises are acquired. So that different noise thresholds correspond to different volume ranges.
Specifically, after the environmental noise at the current moment is obtained, the environmental noise at the current moment is compared with a preset noise threshold value, and the volume adjusting range to which the environmental noise at the current moment belongs is determined. And playing the minimum value in the volume adjusting range as the playing volume.
In some implementations, the user can set whether to automatically adjust the volume according to the environment based on preferences. For example, during the playing process, the environment is noisier and noisier, and the volume at the current moment cannot enable the user to clearly hear the content played by the video. At this time, it is determined whether the user sets the automatic volume adjustment. If the user is judged to have set the automatic volume adjustment, when the environmental noise at the current moment is obtained to exceed the original matched preset noise threshold value, re-matching is carried out, and the volume adjustment is carried out according to the steps; if the current user is judged not to set the automatic volume adjustment, when the environmental noise at the current moment is obtained to exceed the original matched preset noise threshold value, voice reminding can be carried out, for example, a voice assistant carries out voice broadcasting to remind the user whether to carry out the volume adjustment.
The embodiment provides a volume adjustment mode, when environmental noise changes at the current moment, the environmental noise is timely acquired and matched with a preset noise threshold value, a corresponding volume adjustable range is determined, and the minimum volume value of the volume adjustable range is used as an adjustment target to adjust the volume. The method can avoid the problem that the user cannot hear the video playing sound due to sudden noise in the watching process, and the hearing of the user cannot be impacted by adjusting the minimum volume of the volume adjustable range, so that the user has better volume adjustment experience.
In some embodiments, when the audio and video are out of sync, the corresponding adjustment can be made by calibrating the time stamps of the different tracks. Specifically, the method further comprises the following steps: acquiring a time stamp corresponding to a sound track, a time stamp corresponding to a picture track and a time stamp corresponding to a subtitle track of a target video; judging whether the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are consistent; if the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are inconsistent, judging the track corresponding to the inconsistent time stamp, and calibrating according to a preset time stamp calibration rule.
The time stamp is mainly for verifying the time of data generation. For example, in this embodiment, it is possible to verify by a time stamp at which time the sound track generates the corresponding sound data. During video playing, three tracks of sound, picture and subtitle are usually existed, so the time stamp corresponding to the three tracks is used for proving the time when the corresponding data of sound, picture and subtitle appear.
The preset timestamp calibration rules may be referenced to the corresponding timestamps of the frame tracks in some implementations. If there is an inconsistency in the time stamp corresponding to the sound track, the time stamp corresponding to the picture track, and the time stamp corresponding to the subtitle track, the adjustment is uniformly performed based on the time stamp corresponding to the picture track, regardless of whether the time stamps corresponding to the sound track and the subtitle track are identical. If the time stamp corresponding to the sound track or the caption track is faster than the time stamp corresponding to the picture track, the time stamp of the corresponding faster track is adjusted to be paused, and the sound track or the caption track is played after the time stamps corresponding to the picture track are consistent. Or the time stamp of the corresponding faster track is adjusted to reduce the speed of the track, and the normal playing speed is restored after the time stamp corresponding to the picture track is consistent. If the time stamp corresponding to the sound track or the subtitle track is slower than the time stamp corresponding to the picture track, the time stamp of the corresponding slower track is adjusted to speed up the playing until the time stamp corresponding to the picture track is consistent and then returns to normal.
In some implementations, if there are two tracks with identical time stamps, the relationship between the time stamps corresponding to the tracks with inconsistent conditions and the time stamps corresponding to the other tracks can be determined. If the time stamp corresponding to the track with the inconsistent condition is faster than the time stamps corresponding to other tracks, the time stamp of the corresponding faster track is adjusted to be paused by the mode, and the playing of the sound track or the subtitle track is performed after the time stamp corresponding to the picture track is consistent. Or the time stamp of the corresponding faster track is adjusted to reduce the speed of the track, and the normal playing speed is restored after the time stamp corresponding to the picture track is consistent. If the time stamp corresponding to the sound track or the subtitle track is slower than the time stamp corresponding to the picture track, the time stamp of the corresponding slower track is adjusted to speed up the playing until the time stamp corresponding to the picture track is consistent and then returns to normal.
Specifically, the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are obtained first, and whether the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are consistent is judged. If the time stamp of the corresponding track is inconsistent, carrying out secondary determination, determining the speed of the time stamp of the corresponding track which is inconsistent compared with the time stamp of the normal track, and then carrying out corresponding adjustment and calibration on the time stamp by using the method.
According to the method and the device, the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are obtained, and when the situation that the sound track is inconsistent is compared and confirmed, the time stamp corresponding to the inconsistent track is calibrated according to the preset time stamp calibration rule, so that the problem of asynchronous sound and picture can be solved in the shortest time. Thereby improving the experience of the user.
In some embodiments, the comments may be extracted by the user's comments, and the target video may be retrieved and displayed. Specifically, the method further comprises the following steps: acquiring user comments under the video clips to be confirmed; extracting keywords in the user comments for preliminary retrieval; matching the video segment to be confirmed with the video obtained by preliminary retrieval; and determining the target video according to the matching result and displaying the target video.
The method provided by the embodiment can set an information acquisition link on the short video platform, and if the user browses the interested video clips to be confirmed on the short video platform, the user clicks the information acquisition link to acquire comments of each user under the relevant video clips to be confirmed. And comparing the content in the comments of each user with the names of the episodes in the database. And acquiring keywords with correct scenario names and performing related retrieval. And matching the video segment to be confirmed with the scenario corresponding to the retrieved keyword, and displaying the scenario with the highest matching degree as the target video.
Specifically, the video optimization methods, such as image quality adjustment, volume adjustment, and time stamp calibration, related to the above embodiments are all applicable in this embodiment, and will not be described in detail herein.
By means of the method provided by the embodiment, if a user browses the interested video to be confirmed on the short video platform, the user can directly acquire links through the information provided by the embodiment, acquire the scenario keywords and perform related retrieval. And matching the video segment to be confirmed with the scenario corresponding to the retrieved keyword, and displaying the scenario with the highest matching degree as the target video. The method can enable the user to directly search the video clips to be confirmed without downloading the video, reduces the occupation of the memory of the equipment, improves the use convenience of the user, and further improves the satisfaction of the user.
Fig. 3 is a schematic structural diagram of a data transmission device according to an embodiment of the present application, and as shown in fig. 3, a video playing device 300 of the present embodiment includes: a segment acquisition module 301, a feature extraction module 302, a feature determination module 303, and a segment retrieval presentation module 304.
A segment acquisition module 301, configured to acquire a video segment to be confirmed;
The feature extraction module 302 is configured to perform feature extraction by using a frame of picture in the video segment to be confirmed as a picture to be detected;
A feature determining module 303, configured to determine features of the to-be-detected picture by using the feature extraction; the features include at least one of scene placement, dressing features, actor information;
And the segment retrieval and display module 304 is configured to retrieve and determine a target video from the to-be-detected picture according to the feature and display the target video.
Optionally, the feature extraction module 302 is specifically configured to:
determining the number of feature types in each frame of picture of the video clip to be confirmed by using a preset feature type;
Sequencing the number of the feature types in each frame of picture, and determining the picture frame with the largest feature number;
and taking the picture frame with the largest feature quantity as a picture to be detected to extract features.
Optionally, the segment search display module 304 is specifically configured to:
determining the character image in the characteristics according to the characteristics;
Determining information corresponding to actors of the character image according to the character image;
Determining the participations of the actors of the character image according to the information;
And comparing the picture to be detected with the reference work to determine a target video and displaying the target video.
Optionally, the segment search presentation module 304 is specifically further configured to:
according to the characteristics, searching the picture to be detected to obtain the target video;
acquiring the authority of the target video;
and sequencing and displaying the target videos by using the preset priority and the authority.
Optionally, the apparatus further includes an image quality adjustment module 305, configured to:
Acquiring a network bandwidth at the current moment;
matching the image quality grade corresponding to the network bandwidth by utilizing the network bandwidth range corresponding to the preset image quality grade;
according to the matching result, adjusting the image quality at the current moment;
And playing the target video by utilizing the image quality.
Optionally, the apparatus further includes a volume adjustment module 306 for:
Acquiring environmental noise at the current moment;
comparing the environmental noise with a preset noise threshold value, and determining a level corresponding to the environmental noise;
and according to the level, determining a volume adjusting range corresponding to the current moment and taking the minimum value in the volume adjusting range as the playing volume.
Optionally, the apparatus further comprises a calibration module 307 for:
Acquiring a time stamp corresponding to a sound track, a time stamp corresponding to a picture track and a time stamp corresponding to a subtitle track of the target video;
judging whether the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are consistent;
and if the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are inconsistent, judging that the track corresponding to the inconsistent time stamp exists, and calibrating according to a preset time stamp calibration rule.
The apparatus of this embodiment may be used to perform the method of any of the foregoing embodiments, and its implementation principle and technical effects are similar, and will not be described herein again.
Fig. 4 is a schematic structural diagram of a video playing device according to an embodiment of the present application, as shown in fig. 4, a video playing device 400 according to this embodiment may include: a memory 401 and a processor 402.
The memory 401 has stored thereon a computer program that can be loaded by the processor 402 and that performs the methods of the above-described embodiments.
Wherein the processor 402 is coupled to the memory 401, e.g. via a bus.
Optionally, the video playback device 400 may also include a transceiver. It should be noted that, in practical applications, the transceiver is not limited to one, and the structure of the video playing device 400 is not limited to the embodiment of the present application.
The Processor 402 may be a CPU (Central Processing Unit ), general purpose Processor, DSP (DIGITAL SIGNAL Processor, data signal Processor), ASIC (Application SPECIFIC INTEGRATED Circuit), FPGA (Field Programmable GATE ARRAY ) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 402 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
A bus may include a path that communicates information between the components. The bus may be a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
Memory 401 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 401 is used for storing application program codes for executing the inventive arrangements and is controlled to be executed by the processor 402. The processor 402 is configured to execute the application code stored in the memory 401 to implement what is shown in the foregoing method embodiment.
Among other things, video playback devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. But may also be a server or the like. The video playback device shown in fig. 4 is only an example, and should not be construed as limiting the functionality and scope of use of the embodiments of the present application.
The video playing device of the present embodiment may be used to execute the method of any of the foregoing embodiments, and its implementation principle and technical effects are similar, and will not be described herein.
The present application also provides a computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the method in the above embodiments.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
Claims (9)
1. A video playing method, comprising:
Acquiring a video clip to be confirmed;
taking one frame of picture in the video segment to be confirmed as a picture to be tested for feature extraction;
determining the characteristics of the picture to be detected by utilizing the characteristic extraction; the features include at least one of scene placement, dressing features, actor information;
According to the characteristics, searching the picture to be detected to determine a target video and displaying the target video;
the feature extraction by taking a frame of picture in the video segment to be confirmed as a picture to be detected comprises the following steps:
determining the number of feature types in each frame of picture of the video clip to be confirmed by using a preset feature type; the characteristic types comprise scene types, makeup types and dressing types;
Sequencing the number of the characteristic types in each frame of picture, and determining the picture frame with the largest number of the characteristic types;
And taking the picture frame with the largest number of the feature types as a picture to be detected to extract the features.
2. The method according to claim 1, wherein retrieving the frame to be tested to determine a target video and displaying the target video according to the characteristics comprises:
determining the character image in the characteristics according to the characteristics;
Determining information corresponding to actors of the character image according to the character image;
Determining the participations of the actors of the character image according to the information;
And comparing the picture to be detected with the reference work to determine a target video and displaying the target video.
3. The method according to claim 1, wherein retrieving the frame to be tested to determine a target video and displaying the target video according to the characteristics comprises:
according to the characteristics, searching the picture to be detected to obtain the target video;
acquiring the authority of the target video;
and sequencing and displaying the target videos by using the preset priority and the authority.
4. The method as recited in claim 1, further comprising:
Acquiring a network bandwidth at the current moment;
matching the image quality grade corresponding to the network bandwidth by utilizing the network bandwidth range corresponding to the preset image quality grade;
according to the matching result, adjusting the image quality at the current moment;
And playing the target video by utilizing the image quality.
5. The method as recited in claim 1, further comprising:
Acquiring environmental noise at the current moment;
comparing the environmental noise with a preset noise threshold value, and determining a level corresponding to the environmental noise;
and according to the level, determining a volume adjusting range corresponding to the current moment and taking the minimum value in the volume adjusting range as the playing volume.
6. The method as recited in claim 1, further comprising:
Acquiring a time stamp corresponding to a sound track, a time stamp corresponding to a picture track and a time stamp corresponding to a subtitle track of the target video;
judging whether the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are consistent;
and if the time stamp corresponding to the sound track, the time stamp corresponding to the picture track and the time stamp corresponding to the subtitle track are inconsistent, judging that the track corresponding to the inconsistent time stamp exists, and calibrating according to a preset time stamp calibration rule.
7. A video playback device, comprising:
The segment acquisition module is used for acquiring the video segment to be confirmed;
the feature extraction module is used for extracting features by taking a frame of picture in the video segment to be confirmed as a picture to be detected;
the feature determining module is used for determining the features of the picture to be detected by utilizing the feature extraction; the features include at least one of scene placement, dressing features, actor information;
the fragment retrieval display module is used for retrieving and displaying the to-be-detected picture to determine a target video according to the characteristics;
The feature extraction module is specifically configured to: determining the number of feature types in each frame of picture of the video clip to be confirmed by using a preset feature type; the characteristic types comprise scene types, makeup types and dressing types; sequencing the number of the characteristic types in each frame of picture, and determining the picture frame with the largest number of the characteristic types; and taking the picture frame with the largest number of the feature types as a picture to be detected to extract the features.
8. A video playback device, comprising: a memory and a processor;
The memory is used for storing program instructions;
The processor being adapted to invoke and execute program instructions in the memory to perform the method of any of claims 1-6.
9. A computer-readable storage medium, wherein the computer-readable storage medium has a computer program stored therein; the computer program, when executed by a processor, implements the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211425128.3A CN115734045B (en) | 2022-11-15 | 2022-11-15 | Video playing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211425128.3A CN115734045B (en) | 2022-11-15 | 2022-11-15 | Video playing method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115734045A CN115734045A (en) | 2023-03-03 |
| CN115734045B true CN115734045B (en) | 2024-07-12 |
Family
ID=85295682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211425128.3A Active CN115734045B (en) | 2022-11-15 | 2022-11-15 | Video playing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115734045B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110913241A (en) * | 2019-11-01 | 2020-03-24 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2851397B1 (en) * | 2003-02-14 | 2005-05-13 | Canon Europa Nv | METHOD AND DEVICE FOR ANALYZING VIDEO SEQUENCES IN A COMMUNICATION NETWORK |
| CN101604325B (en) * | 2009-07-17 | 2012-06-20 | 北京邮电大学 | Method for classifying sports video based on key frame of main scene lens |
| CN103475935A (en) * | 2013-09-06 | 2013-12-25 | 北京锐安科技有限公司 | Method and device for retrieving video segments |
| CN110019938A (en) * | 2017-11-29 | 2019-07-16 | 深圳Tcl新技术有限公司 | Video Information Retrieval Techniquess method, apparatus and storage medium based on RGB classification |
| CN109640062A (en) * | 2018-12-19 | 2019-04-16 | 深圳市东明炬创电子有限公司 | A kind of ultra high-definition video is without compression long distance transmitter |
| CN110570841A (en) * | 2019-09-12 | 2019-12-13 | 腾讯科技（深圳）有限公司 | Multimedia playing interface processing method, device, client and medium |
| CN111581433B (en) * | 2020-05-18 | 2023-10-10 | Oppo广东移动通信有限公司 | Video processing method, device, electronic equipment and computer readable medium |
| CN114741553B (en) * | 2022-03-31 | 2023-03-24 | 慧之安信息技术股份有限公司 | Image feature-based picture searching method |
-
2022
- 2022-11-15 CN CN202211425128.3A patent/CN115734045B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110913241A (en) * | 2019-11-01 | 2020-03-24 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115734045A (en) | 2023-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20150082330A1 (en) | Real-time channel program recommendation on a display device | |
| WO2017161776A1 (en) | Bullet comment pushing method and device | |
| US20180068690A1 (en) | Data processing apparatus, data processing method | |
| US20150365725A1 (en) | Extract partition segments of personalized video channel | |
| US20170169040A1 (en) | Method and electronic device for recommending video | |
| US8453179B2 (en) | Linking real time media context to related applications and services | |
| CN110663079A (en) | Method and system for correcting input generated using automatic speech recognition based on speech | |
| DE102016125806B4 (en) | Methods, systems and media for identifying and presenting multilingual media content items to users | |
| CN112653902B (en) | Speaker recognition method and device and electronic equipment | |
| JP2011217209A (en) | Electronic apparatus, content recommendation method, and program | |
| CN111966909B (en) | Video recommendation method, device, electronic equipment and computer readable storage medium | |
| CN108322791B (en) | Voice evaluation method and device | |
| CN111279709A (en) | Providing video recommendations | |
| US20190342428A1 (en) | Content evaluator | |
| WO2022161328A1 (en) | Video processing method and apparatus, storage medium, and device | |
| CN112507163A (en) | Duration prediction model training method, recommendation method, device, equipment and medium | |
| CN106936830B (en) | Multimedia data playing method and device | |
| CN114845149A (en) | Editing method of video clip, video recommendation method, device, equipment and medium | |
| CN115734045B (en) | Video playing method, device, equipment and storage medium | |
| CN112055258A (en) | Time delay testing method and device for loading live broadcast picture and electronic equipment | |
| CN114430491A (en) | Live broadcast-based data processing method and device | |
| CN111741333B (en) | Live broadcast data acquisition method and device, computer equipment and storage medium | |
| CN110942070A (en) | Content display method and device, electronic equipment and computer readable storage medium | |
| CN117156184B (en) | Intelligent video playing method, device, equipment and storage medium | |
| US10536729B2 (en) | Methods, systems, and media for transforming fingerprints to detect unauthorized media content items |
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 |