CN110704679A - Video classification method and device and electronic equipment - Google Patents
Video classification method and device and electronic equipment Download PDFInfo
- Publication number
- CN110704679A CN110704679A CN201910921207.5A CN201910921207A CN110704679A CN 110704679 A CN110704679 A CN 110704679A CN 201910921207 A CN201910921207 A CN 201910921207A CN 110704679 A CN110704679 A CN 110704679A
- Authority
- CN
- China
- Prior art keywords
- video
- value
- feature
- target video
- classification
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the disclosure provides a video classification method, a video classification device and electronic equipment, which belong to the technical field of data processing, and the method comprises the following steps: based on the heat values of different videos of a video platform, acquiring a target video with the heat value exceeding a preset value and a recommended value generated by the video platform for the target video; performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value; performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video; and combining the first characteristic value and the second characteristic value to form a third characteristic value which is used as the input characteristic of the classified fully-connected layer to further judge the classification of the target video. Through the scheme disclosed by the invention, the accuracy of video classification can be improved.
Description
Technical Field
The present disclosure relates to the field of data processing technologies, and in particular, to a video classification method and apparatus, and an electronic device.
Background
With the continuous development of the technology, the video content is increasing. In the process of operating the video content, the videos are often required to be classified. Traditional manual work is categorised not only consuming time, extravagant manpower moreover, and efficiency is not high.
The traditional video classification technology based on visual information relates to the content of three aspects of feature extraction, video modeling and classification technology. In the feature extraction step, a researcher usually autonomously selects global or local features of a video frame to represent a video, such as features of HSV, LBP, and the like.
As a specific application scene, a video played in a video platform often has more interaction with a user, and the user can interact with the video in the playing platform in a click mode or a video comment mode. During the interaction, the video in the video platform generates different heat values. In the process of video classification, how to improve the accuracy of video classification with a higher heat value is a technical problem to be solved.
Disclosure of Invention
In view of the above, embodiments of the present disclosure provide a video classification method, an apparatus, and an electronic device, which at least partially solve the problems in the prior art.
In a first aspect, an embodiment of the present disclosure provides a video classification method, including:
based on the heat values of different videos of a video platform, acquiring a target video with the heat value exceeding a preset value and a recommended value generated by the video platform for the target video;
performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value;
performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video;
and combining the first characteristic value and the second characteristic value to form a third characteristic value which is used as the input characteristic of the classified fully-connected layer to further judge the classification of the target video.
According to a specific implementation manner of the embodiment of the present disclosure, the obtaining, based on the heat values of different videos by the video platform, a target video with a heat value exceeding a preset value and a recommended value generated by the video platform for the target video includes:
acquiring click quantity values of the video platform for all videos in a preset time period;
searching videos with click quantity values exceeding a preset value to form a video set related to the heat value;
determining the target video according to a preset rule in the video set;
and determining a recommendation value generated by the video platform for the target video based on the video identification of the target video.
According to a specific implementation manner of the embodiment of the present disclosure, the determining the target video according to a preset rule in the video set includes:
searching a video with the video attribute as the video recommended for the first time in the video set;
and determining the video with the highest click rate in the videos with the searched video attributes as the first recommended video as the target video.
According to a specific implementation manner of the embodiment of the present disclosure, before performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value, the method further includes:
obtaining the size requirement of the classification network on an input matrix;
quantizing the recommendation value into a characteristic value matrix matched with the input matrix size of the classification network;
and setting the characteristic value matrix as a recommendation value after quantization processing.
According to a specific implementation manner of the embodiment of the present disclosure, the performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value includes:
performing feature calculation on the quantized recommended value by using the convolution layer and the pooling layer of the classification network to obtain a first feature matrix;
and taking the first feature matrix as a first feature value related to the recommended value.
According to a specific implementation manner of the embodiment of the present disclosure, the performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video includes:
setting a video separation layer in the classification network;
extracting a plurality of video frames from the target video based on the video separation layer;
performing feature computation on the target video based on the plurality of video frames.
According to a specific implementation manner of the embodiment of the present disclosure, the performing feature calculation on the target video based on the plurality of video frames includes:
converting the plurality of video frames into a plurality of image matrices;
sequentially utilizing the convolution layer and the pooling layer in the classification network to perform characteristic calculation on the plurality of image matrixes;
and taking the feature matrix input to the classification network full-connection layer as a second feature value of the target video.
According to a specific implementation manner of the embodiment of the present disclosure, the step of further determining the classification of the target video by using a third feature value formed by combining the first feature value and the second feature value as an input feature of the classified fully-connected layer includes:
carrying out mean value processing on the feature matrixes representing the first feature value and the second feature value to obtain a feature matrix representing a third feature;
and determining the classification of the target video by using the feature matrix representing the third feature and a full connection layer of the classification network.
In a second aspect, an embodiment of the present disclosure provides a video classification apparatus, including:
the acquisition module is used for acquiring a target video with the heat value exceeding a preset value and a recommended value generated by the video platform for the target video based on the heat values of different videos of the video platform;
the first calculation module is used for performing feature calculation on the quantized recommended value by utilizing a preset classification network to obtain a first feature value related to the recommended value;
the second calculation module is used for performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video;
and the execution module is used for combining the first characteristic value and the second characteristic value to form a third characteristic value which is used as the input characteristic of the classified full-link layer to further judge the classification of the target video.
In a third aspect, an embodiment of the present disclosure further provides an electronic device, where the electronic device includes:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of video classification of any of the preceding first aspects or any implementation manner of the first aspect.
In a fourth aspect, the disclosed embodiments also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the video classification method in the first aspect or any implementation manner of the first aspect.
In a fifth aspect, the present disclosure also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, cause the computer to perform the video classification method in the foregoing first aspect or any implementation manner of the first aspect.
The video classification scheme in the embodiment of the disclosure comprises the steps of obtaining a target video with a heat value exceeding a preset value and a recommended value generated by a video platform for the target video based on the heat values of the video platform for different videos; performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value; performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video; and combining the first characteristic value and the second characteristic value to form a third characteristic value which is used as the input characteristic of the classified fully-connected layer to further judge the classification of the target video. Through the scheme disclosed by the invention, the accuracy of target video classification can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic view of a video classification process provided in an embodiment of the present disclosure;
fig. 2 is a schematic view of another video classification flow provided by the embodiment of the present disclosure;
fig. 3 is a schematic view of another video classification flow provided by the embodiment of the present disclosure;
fig. 4 is a schematic view of another video classification flow provided by the embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a video classification apparatus according to an embodiment of the disclosure;
fig. 6 is a schematic diagram of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the disclosure, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present disclosure, and the drawings only show the components related to the present disclosure rather than the number, shape and size of the components in actual implementation, and the type, amount and ratio of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.
In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.
The embodiment of the disclosure provides a video classification method. The video classification method provided by the embodiment can be executed by a computing device, which can be implemented as software or as a combination of software and hardware, and can be integrally arranged in a server, a terminal device and the like.
Referring to fig. 1, a video classification method provided by the embodiment of the present disclosure includes the following steps:
s101, acquiring a target video with a heat value exceeding a preset value and a recommended value generated by a video platform for the target video based on the heat values of the video platform for different videos.
The video platform (for example, soul, love art, etc.) is a platform that can show video content to users, and in addition, users can upload videos obtained by themselves on the video platform through accounts registered by themselves, and in this way, the video platform usually includes massive video resources.
Videos on the video platform have different classifications, and a user can establish interaction with the videos in modes of clicking, video commenting and the like in the process of viewing the videos on the video platform. The user forms the popularity value of a certain video according to interaction numerical values such as the click quantity and the video comment quantity of the certain video within a certain time. The popularity value of a video indicates the user's preference for that video.
For videos with higher heat values, the video platform will generally recommend the video to more users in order to more quickly propagate to users that are not watching the video. In the process of recommending the video to the user, the video platform usually sets video classification information for the recommended video, and whether the video classification information is set accurately or not directly determines the range of the target user to be pushed and the pushing effect. For example, pushing an action type movie to a user who likes to watch the action type movie results in a good pushing effect, and otherwise, the effect is poor.
Therefore, once the popularity value video appears on the video platform, the target video can be screened through a preset value, and the recommendation value generated by the video platform for the target video can be acquired while the target video is acquired. The recommendation value of the video platform for the target video may be different due to different recommendation value formats set by different video platforms, and optionally, the recommendation value may include content such as a video identifier, a video heat value, a video name, a video brief introduction, and the like.
And S102, performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value.
After the recommendation value is obtained, the features of the target video may be calculated based on the recommendation value, so as to further extract the relevant features of the target video.
In order to conveniently extract the features, a classification network can be constructed, and the features of the recommended values can be extracted through the classification network.
The classification network may be a neural network architecture arranged based on a convolutional neural network. For example, the classification network may include a convolutional layer, a pooling layer, a sampling layer, and a fully-connected layer.
The convolutional layers mainly comprise the size of convolutional kernels and the number of input feature graphs, each convolutional layer can comprise a plurality of feature graphs with the same size, the feature values of the same layer adopt a weight sharing mode, and the sizes of the convolutional kernels in each layer are consistent. The convolution layer performs convolution calculation on the input image and extracts the layout characteristics of the input image.
The back of the feature extraction layer of the convolutional layer can be connected with the sampling layer, the sampling layer is used for solving the local average value of the input image and carrying out secondary feature extraction, and the sampling layer is connected with the convolutional layer, so that the neural network model can be guaranteed to have better robustness for the input image.
In order to accelerate the training speed of the classification network, a pooling layer is arranged behind the convolutional layer, the output result of the convolutional layer is processed by the pooling layer in a maximum pooling mode, and invariance characteristics of an input image can be better extracted.
In addition, an embedding layer can be arranged in the classification network, the embedding layer carries out vectorization operation on the content in the recommended value to obtain a recommended value vector matrix, and feature calculation is carried out on the recommended value based on the recommended value feature vector matrix. The embedding layer may be disposed before the convolutional layer, the pooling layer, and the sampling layer.
When the classification network is used for feature calculation, the convolution layer, the pooling layer and the full-connection layer in the classification network can be used for feature calculation of the recommended value vector matrix in sequence, and finally the feature matrix obtained by calculation of the full-connection layer is used as the first feature value of the recommended value.
S103, performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video.
The target video comprises a plurality of video frames, therefore, a video separation layer can be arranged in the classification network, the video separation layer can be used for extracting the plurality of video frames from the target video, and finally, feature calculation can be carried out on the target video based on the plurality of video frames.
In the process of performing feature calculation on the target video, the plurality of video frames may be converted into a plurality of image matrices, feature calculation is performed on the plurality of image matrices by using the convolutional layer and the pooling layer in the classification network in sequence, and finally, the feature matrix input to the full connection layer of the classification network is used as the second feature of the target video.
And S104, a third characteristic value formed by combining the first characteristic value and the second characteristic value is used as the input characteristic of the classified full-link layer to further judge the classification of the target video.
After the first characteristic value and the second characteristic value are obtained, the first characteristic value and the second characteristic value can be used as input characteristics of a classification network full-link layer together, the classification probability of the target video is calculated through the classification network full-link layer, and the final classification of the target video is determined based on the calculated final probability value.
By the scheme, the classification of the target video can be judged based on the recommendation value information of the target video, so that the accuracy of the classification of the target video is improved.
Referring to fig. 2, according to a specific implementation manner of the embodiment of the present disclosure, the acquiring, based on the heat values of the video platforms for different videos, a target video with a heat value exceeding a preset value and a recommended value generated by the video platform for the target video includes:
s201, obtaining click rate values of the video platform for all videos in a preset time period.
The click rate of the video can be used as an index of the heat value, and the click rate value of the video platform for all videos in a preset time period (for example, one week or one month) can be obtained.
S202, searching for videos with click quantity values exceeding a preset value, and forming a video set related to the heat value.
By setting a preset value, videos related to the heat value can be screened, and then a video set related to the heat value is obtained, wherein the video set can comprise one or more videos.
S203, determining the target video according to a preset rule in the video set.
The videos in the video set can be used as a basis for selecting the target video, and for this reason, the screening rules for the target video can be further set, so that the target video is determined according to the rules set in advance.
For example, in the video set, a video with a video attribute as first recommended may be searched, and a video with a highest click rate in the searched videos with the video attribute as first recommended may be determined as a target video.
S204, based on the video identification of the target video, determining a recommendation value generated by the video platform for the target video.
The video platform sets a video Identifier (ID) for each target video, and the video identifier can be used for searching a recommended value corresponding to the target video in the video platform.
Referring to fig. 3, according to a specific implementation manner of the embodiment of the present disclosure, before performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value, the method further includes:
s301, obtaining the size requirement of the classification network on the input matrix.
By querying the specification of the classification network, the matrix size (e.g., 128 × 128) of the classification network for the data that needs to be input can be obtained, and thus the size requirement of the input matrix can be determined.
S302, quantizing the recommendation value into a characteristic value matrix matched with the input matrix size of the classification network.
Through a data conversion mode, the content corresponding to the recommended value can be converted according to the size requirement of the input matrix, and therefore the recommended value is quantized into a characteristic value matrix matched with the input matrix of the classification network.
And S303, setting the characteristic value matrix as a recommendation value after quantization processing.
According to a specific implementation manner of the embodiment of the present disclosure, in the process of performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value, feature calculation may be performed on the quantized recommended value by using a convolution layer and a pooling layer of the classification network to obtain a first feature matrix, and the first feature matrix is used as the first feature value related to the recommended value.
Referring to fig. 4, according to a specific implementation manner of the embodiment of the present disclosure, in the process of performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video, the method may include the following steps:
s401, setting a video separation layer in the classification network.
The video separation layer can identify a plurality of video frames existing in the target video, and the video frames can be extracted from the target video based on the identification result of the plurality of video frames.
S402, extracting a plurality of video frames from the target video based on the video separation layer.
A rapid frame extraction mode can be adopted, typical frames are extracted from adjacent video frames by judging whether the change between the adjacent video frames in the target video is larger than a preset value, and finally the extracted typical frames are combined together to form a plurality of video frames.
And S403, performing feature calculation on the target video based on the plurality of video frames.
Specifically, a plurality of video frames may be converted into a plurality of image matrices, feature calculation may be performed on the plurality of image matrices by sequentially using a convolution layer and a pooling layer in the classification network, and finally, a feature matrix input to a full connection layer of the classification network may be used as a second feature value of the target video.
According to a specific implementation manner of the embodiment of the present disclosure, the step of further determining the classification of the target video by using a third feature value formed by combining the first feature value and the second feature value as an input feature of the classified fully-connected layer includes: carrying out mean value processing on the feature matrixes representing the first feature value and the second feature value to obtain a feature matrix representing a third feature; and determining the classification of the target video by using the feature matrix representing the third feature and a full connection layer of the classification network.
Corresponding to the above method embodiment, referring to fig. 5, the disclosed embodiment further provides a video classification apparatus 50, including:
an obtaining module 501, configured to obtain, based on heat values of different videos by a video platform, a target video with a heat value exceeding a preset value and a recommended value generated by the video platform for the target video.
The video platform (for example, soul, love art, etc.) is a platform that can show video content to users, and in addition, users can upload videos obtained by themselves on the video platform through accounts registered by themselves, and in this way, the video platform usually includes massive video resources.
Videos on the video platform have different classifications, and a user can establish interaction with the videos in modes of clicking, video commenting and the like in the process of viewing the videos on the video platform. The user forms the popularity value of a certain video according to interaction numerical values such as the click quantity and the video comment quantity of the certain video within a certain time. The popularity value of a video indicates the user's preference for that video.
For videos with higher heat values, the video platform will generally recommend the video to more users in order to more quickly propagate to users that are not watching the video. In the process of recommending the video to the user, the video platform usually sets video classification information for the recommended video, and whether the video classification information is set accurately or not directly determines the range of the target user to be pushed and the pushing effect. For example, pushing an action type movie to a user who likes to watch the action type movie results in a good pushing effect, and otherwise, the effect is poor.
Therefore, once the popularity value video appears on the video platform, the target video can be screened through a preset value, and the recommendation value generated by the video platform for the target video can be acquired while the target video is acquired. The recommendation value of the video platform for the target video may be different due to different recommendation value formats set by different video platforms, and optionally, the recommendation value may include content such as a video identifier, a video heat value, a video name, a video brief introduction, and the like.
A first calculating module 502, configured to perform feature calculation on the quantized recommended value by using a preset classification network, so as to obtain a first feature value related to the recommended value.
After the recommendation value is obtained, the features of the target video may be calculated based on the recommendation value, so as to further extract the relevant features of the target video.
In order to conveniently extract the features, a classification network can be constructed, and the features of the recommended values can be extracted through the classification network.
The classification network may be a neural network architecture arranged based on a convolutional neural network. For example, the classification network may include a convolutional layer, a pooling layer, a sampling layer, and a fully-connected layer.
The convolutional layers mainly comprise the size of convolutional kernels and the number of input feature graphs, each convolutional layer can comprise a plurality of feature graphs with the same size, the feature values of the same layer adopt a weight sharing mode, and the sizes of the convolutional kernels in each layer are consistent. The convolution layer performs convolution calculation on the input image and extracts the layout characteristics of the input image.
The back of the feature extraction layer of the convolutional layer can be connected with the sampling layer, the sampling layer is used for solving the local average value of the input image and carrying out secondary feature extraction, and the sampling layer is connected with the convolutional layer, so that the neural network model can be guaranteed to have better robustness for the input image.
In order to accelerate the training speed of the classification network, a pooling layer is arranged behind the convolutional layer, the output result of the convolutional layer is processed by the pooling layer in a maximum pooling mode, and invariance characteristics of an input image can be better extracted.
In addition, an embedding layer can be arranged in the classification network, the embedding layer carries out vectorization operation on the content in the recommended value to obtain a recommended value vector matrix, and feature calculation is carried out on the recommended value based on the recommended value feature vector matrix. The embedding layer may be disposed before the convolutional layer, the pooling layer, and the sampling layer.
When the classification network is used for feature calculation, the convolution layer, the pooling layer and the full-connection layer in the classification network can be used for feature calculation of the recommended value vector matrix in sequence, and finally the feature matrix obtained by calculation of the full-connection layer is used as the first feature value of the recommended value.
A second calculating module 503, configured to perform feature calculation on the target video by using the classification network, so as to obtain a second feature value related to the target video.
The target video comprises a plurality of video frames, therefore, a video separation layer can be arranged in the classification network, the video separation layer can be used for extracting the plurality of video frames from the target video, and finally, feature calculation can be carried out on the target video based on the plurality of video frames.
In the process of performing feature calculation on the target video, the plurality of video frames may be converted into a plurality of image matrices, feature calculation is performed on the plurality of image matrices by using the convolutional layer and the pooling layer in the classification network in sequence, and finally, the feature matrix input to the full connection layer of the classification network is used as the second feature of the target video.
An executing module 504, configured to combine the first feature value and the second feature value to form a third feature value, which is used as an input feature of the classified fully-connected layer, to further determine the classification of the target video.
After the first characteristic value and the second characteristic value are obtained, the first characteristic value and the second characteristic value can be used as input characteristics of a classification network full-link layer together, the classification probability of the target video is calculated through the classification network full-link layer, and the final classification of the target video is determined based on the calculated final probability value.
By the scheme, the classification of the target video can be judged based on the recommendation value information of the target video, so that the accuracy of the classification of the target video is improved.
The apparatus shown in fig. 5 may correspondingly execute the content in the above method embodiment, and details of the part not described in detail in this embodiment refer to the content described in the above method embodiment, which is not described again here.
Referring to fig. 6, an embodiment of the present disclosure also provides an electronic device 60, including:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the video classification method of the preceding method embodiment.
The disclosed embodiments also provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the foregoing method embodiments.
The disclosed embodiments also provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the video classification method in the aforementioned method embodiments.
Referring now to FIG. 6, a schematic diagram of an electronic device 60 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may 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., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, the electronic device 60 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 60 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 60 to communicate with other devices wirelessly or by wire to exchange data. While the figures illustrate an electronic device 60 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring at least two internet protocol addresses; sending a node evaluation request comprising the at least two internet protocol addresses to node evaluation equipment, wherein the node evaluation equipment selects the internet protocol addresses from the at least two internet protocol addresses and returns the internet protocol addresses; receiving an internet protocol address returned by the node evaluation equipment; wherein the obtained internet protocol address indicates an edge node in the content distribution network.
Alternatively, the computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: receiving a node evaluation request comprising at least two internet protocol addresses; selecting an internet protocol address from the at least two internet protocol addresses; returning the selected internet protocol address; wherein the received internet protocol address indicates an edge node in the content distribution network.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".
It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof.
The above description is only for the specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present disclosure should be covered within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (11)
1. A method of video classification, comprising:
based on the heat values of different videos of a video platform, acquiring a target video with the heat value exceeding a preset value and a recommended value generated by the video platform for the target video;
performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value;
performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video;
and combining the first characteristic value and the second characteristic value to form a third characteristic value which is used as the input characteristic of the classified fully-connected layer to further judge the classification of the target video.
2. The method according to claim 1, wherein the obtaining, based on the heat values of the video platform for different videos, a target video with a heat value exceeding a preset value and a recommendation value generated by the video platform for the target video comprises:
acquiring click quantity values of the video platform for all videos in a preset time period;
searching videos with click quantity values exceeding a preset value to form a video set related to the heat value;
determining the target video according to a preset rule in the video set;
and determining a recommendation value generated by the video platform for the target video based on the video identification of the target video.
3. The method according to claim 2, wherein the determining the target video according to a preset rule in the video set comprises:
searching a video with the video attribute as the video recommended for the first time in the video set;
and determining the video with the highest click rate in the videos with the searched video attributes as the first recommended video as the target video.
4. The method according to claim 1, wherein before the performing the feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value, the method further comprises:
obtaining the size requirement of the classification network on an input matrix;
quantizing the recommendation value into a characteristic value matrix matched with the input matrix size of the classification network;
and setting the characteristic value matrix as a recommendation value after quantization processing.
5. The method according to claim 1, wherein the performing feature calculation on the quantized recommended value by using a preset classification network to obtain a first feature value related to the recommended value comprises:
performing feature calculation on the quantized recommended value by using the convolution layer and the pooling layer of the classification network to obtain a first feature matrix;
and taking the first feature matrix as a first feature value related to the recommended value.
6. The method of claim 1, wherein the performing the feature calculation on the target video by using the classification network to obtain a second feature value related to the target video comprises:
setting a video separation layer in the classification network;
extracting a plurality of video frames from the target video based on the video separation layer;
performing feature computation on the target video based on the plurality of video frames.
7. The method of claim 6, wherein said performing feature calculations on the target video based on the plurality of video frames comprises:
converting the plurality of video frames into a plurality of image matrices;
sequentially utilizing the convolution layer and the pooling layer in the classification network to perform characteristic calculation on the plurality of image matrixes;
and taking the feature matrix input to the classification network full-connection layer as a second feature value of the target video.
8. The method according to claim 1, wherein the step of determining the classification of the target video further by using a third feature value formed by combining the first feature value and the second feature value as an input feature of the classified fully-connected layer comprises:
carrying out mean value processing on the feature matrixes representing the first feature value and the second feature value to obtain a feature matrix representing a third feature;
and determining the classification of the target video by using the feature matrix representing the third feature and a full connection layer of the classification network.
9. A video classification apparatus, comprising:
the acquisition module is used for acquiring a target video with the heat value exceeding a preset value and a recommended value generated by the video platform for the target video based on the heat values of different videos of the video platform;
the first calculation module is used for performing feature calculation on the quantized recommended value by utilizing a preset classification network to obtain a first feature value related to the recommended value;
the second calculation module is used for performing feature calculation on the target video by using the classification network to obtain a second feature value related to the target video;
and the execution module is used for combining the first characteristic value and the second characteristic value to form a third characteristic value which is used as the input characteristic of the classified full-link layer to further judge the classification of the target video.
10. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the video classification method of any of the preceding claims 1-8.
11. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the video classification method of any of the preceding claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921207.5A CN110704679B (en) | 2019-09-27 | 2019-09-27 | Video classification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910921207.5A CN110704679B (en) | 2019-09-27 | 2019-09-27 | Video classification method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110704679A true CN110704679A (en) | 2020-01-17 |
| CN110704679B CN110704679B (en) | 2023-10-13 |
Family
ID=69197697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910921207.5A Active CN110704679B (en) | 2019-09-27 | 2019-09-27 | Video classification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110704679B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836327A (en) * | 2021-09-26 | 2021-12-24 | 杭州网易云音乐科技有限公司 | Recommendation method, medium, device and computing equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190007816A (en) * | 2017-07-13 | 2019-01-23 | 삼성전자주식회사 | Electronic device for classifying video and operating method thereof |
| CN109902634A (en) * | 2019-03-04 | 2019-06-18 | 上海七牛信息技术有限公司 | A kind of video classification methods neural network based and system |
| CN110162669A (en) * | 2019-04-04 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Visual classification processing method, device, computer equipment and storage medium |
| CN110278447A (en) * | 2019-06-26 | 2019-09-24 | 北京字节跳动网络技术有限公司 | Video pushing method, device and electronic equipment based on continuous feature |
-
2019
- 2019-09-27 CN CN201910921207.5A patent/CN110704679B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190007816A (en) * | 2017-07-13 | 2019-01-23 | 삼성전자주식회사 | Electronic device for classifying video and operating method thereof |
| CN109902634A (en) * | 2019-03-04 | 2019-06-18 | 上海七牛信息技术有限公司 | A kind of video classification methods neural network based and system |
| CN110162669A (en) * | 2019-04-04 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Visual classification processing method, device, computer equipment and storage medium |
| CN110278447A (en) * | 2019-06-26 | 2019-09-24 | 北京字节跳动网络技术有限公司 | Video pushing method, device and electronic equipment based on continuous feature |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836327A (en) * | 2021-09-26 | 2021-12-24 | 杭州网易云音乐科技有限公司 | Recommendation method, medium, device and computing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110704679B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111476309B (en) | Image processing method, model training method, device, equipment and readable medium | |
| CN110321958B (en) | Training method of neural network model and video similarity determination method | |
| CN110189246B (en) | Image stylization generation method and device and electronic equipment | |
| CN110399848A (en) | Video cover generation method, device and electronic equipment | |
| CN110278447B (en) | Video pushing method and device based on continuous features and electronic equipment | |
| CN110210532B (en) | Background color generation method and device and electronic equipment | |
| CN110674349B (en) | Video POI (Point of interest) identification method and device and electronic equipment | |
| CN113642673B (en) | Image generation method, device, equipment and storage medium | |
| CN109862100B (en) | Method and device for pushing information | |
| CN111738316B (en) | Zero sample learning image classification method and device and electronic equipment | |
| CN113204555B (en) | Data table processing method, device, electronic equipment and storage medium | |
| CN110555861B (en) | Optical flow calculation method and device and electronic equipment | |
| CN110211017B (en) | Image processing method and device and electronic equipment | |
| CN109359727B (en) | Method, device and equipment for determining structure of neural network and readable medium | |
| CN110069997B (en) | Scene classification method and device and electronic equipment | |
| CN110704679B (en) | Video classification method and device and electronic equipment | |
| CN110378936B (en) | Optical flow calculation method and device and electronic equipment | |
| CN111414921B (en) | Sample image processing method, device, electronic equipment and computer storage medium | |
| CN112561779B (en) | Image stylization processing method, device, equipment and storage medium | |
| CN109977925B (en) | Expression determination method and device and electronic equipment | |
| CN110197459B (en) | Image stylization generation method and device and electronic equipment | |
| CN111832354A (en) | Target object age identification method and device and electronic equipment | |
| CN110781066A (en) | User behavior analysis method, device, equipment and storage medium | |
| CN114625876B (en) | Method for generating author characteristic model, method and device for processing author information | |
| CN112492399A (en) | Information display method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |