CN116074566B - Game video highlight recording method, device, equipment and storage medium - Google Patents
Game video highlight recording method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116074566B CN116074566B CN202310062849.0A CN202310062849A CN116074566B CN 116074566 B CN116074566 B CN 116074566B CN 202310062849 A CN202310062849 A CN 202310062849A CN 116074566 B CN116074566 B CN 116074566B
- Authority
- CN
- China
- Prior art keywords
- highlight
- frame
- video
- audio
- current
- 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 70
- 239000012634 fragment Substances 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000001228 spectrum Methods 0.000 claims abstract description 18
- 238000013145 classification model Methods 0.000 claims abstract description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 20
- 238000004891 communication Methods 0.000 claims description 18
- 230000001360 synchronised effect Effects 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000001131 transforming effect Effects 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 description 23
- 238000012552 review Methods 0.000 description 14
- 238000005070 sampling Methods 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000001052 transient effect Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013467 fragmentation Methods 0.000 description 2
- 238000006062 fragmentation reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4334—Recording operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4666—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms using neural networks, e.g. processing the feedback provided by the user
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4781—Games
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for recording a game video highlight, and relates to the technical field of video processing. The method comprises the steps of obtaining audio and video stream data generated in real time in a game process, obtaining a current image to be identified containing spectrum characteristic information through fast Fourier transform, frequency point amplitude coding and drawing processing based on a current audio frame in the audio and video stream data, inputting the image into a highlight frame classification model based on CNN and highlight audio frames to finish pretraining, obtaining a current classification result, and finally recording and storing at least one video frame in synchronization with the current audio frame when the highlight confidence in the classification result is greater than or equal to a preset threshold value to obtain a game video highlight frame fragment, so that highlight moment picture identification is indirectly carried out by replacing a plurality of video frames with one audio frame, and the purposes of greatly simplifying the process, improving the identification efficiency and reducing required computing resources can be achieved.
Description
Technical Field
The invention belongs to the technical field of video processing, and particularly relates to a method, a device, equipment and a storage medium for recording a game video highlight.
Background
With the rapid development of computer technology, players have a variety of demands for gaming experiences, among which, more prominently: the player wants to review and view the wonderful time pictures existing in the game, for example, pictures of opponents (such as two continuous breaks, three continuous breaks or five continuous breaks, etc.) are continuously and repeatedly defeated, which means that the game running platform needs to automatically identify the wonderful time pictures and record and save the wonderful time pictures in the game process so as to push the pictures to the player for review after the game is finished.
The existing highlight picture identification scheme mainly identifies whether a highlight picture is based on a video picture image, namely, a game video target highlight picture needs to be obtained in advance, then a game video current frame is used as an image to be identified in real time, hash values of the target highlight picture and the image to be identified are respectively obtained by using a perception hash algorithm, and finally the image to be identified is used as the highlight picture under the condition that the distance between the hash value of the target highlight picture and the hash value of the image to be identified is smaller than a preset threshold value. However, with the increase of the video frame rate (for example, up to 120 frames per second or more), the foregoing highlight picture recognition scheme has problems of complicated process and consumption of a large amount of computing resources, so how to provide a new scheme for highlight picture recognition that can be simplified to reduce the required computing resources is a subject of urgent study for those skilled in the art.
Disclosure of Invention
The invention aims to provide a game video highlight recording method, a device, computer equipment and a computer readable storage medium, which are used for solving the problems that the existing highlight picture identification scheme is complex in process and needs to consume a large amount of computing resources.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, a method for recording a video highlight of a game is provided, including:
acquiring audio and video stream data generated in real time in the game process;
performing fast Fourier transform processing on the current audio frame in the audio-video stream data to obtain a current frequency spectrum;
respectively encoding K magnitudes which are in the current frequency spectrum and correspond to K frequency points one by one into RGB three-channel color values to obtain current data to be identified, wherein K represents a natural number which is not less than 64, and the K frequency points are distributed at equal intervals in a human auditory frequency domain interval;
drawing to obtain a current image to be recognized, wherein the pixel matrix of the current image to be recognized is K, according to K RGB values of the current data to be recognized, and K is a natural number not smaller than the square root of K;
inputting the current image to be identified into a highlight frame classification model which is trained in advance based on a convolutional neural network CNN and a highlight audio frame to obtain a current classification result, wherein the highlight audio frame is an audio frame synchronous with a game video target highlight picture and is used for providing a positive sample for highlight frame classification training for the highlight frame classification model;
When the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, recording and storing at least one video frame which is in the audio-video stream data and is synchronous with the current audio frame to obtain a game video highlight picture segment, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result.
Based on the above summary, a new scheme for indirectly identifying a game highlight moment picture based on contemporaneous audio frames is provided, that is, after audio and video stream data generated in real time in a game process is obtained, based on the current audio frame in the audio and video stream data, a current image to be identified containing spectrum characteristic information is obtained through fast fourier transform, frequency point amplitude coding and drawing processing, then the image is input into a highlight frame classification model for completing pre-training based on a convolutional neural network CNN and a highlight audio frame, a current classification result is obtained, and finally at least one video frame which is in the audio and video stream data and is contemporaneous with the current audio frame is recorded and stored when the highlight confidence in the classification result is greater than or equal to a preset confidence threshold value, so that a game video highlight picture segment is obtained, and the purposes of greatly simplifying the process, improving the identification efficiency and reducing the required computing resources can be realized by indirectly carrying out highlight moment picture identification by using one audio frame instead of a plurality of video frames.
In one possible design, the encoding of K magnitudes, which are in one-to-one correspondence with the K frequency points, into RGB three-channel color values includes:
transforming the K amplitude values into values to be transformed under the same value unit and respectively within a section [0,16777215] by means of transforming the value units;
converting the value to be converted from decimal numbers to binary numbers;
0 is complemented on the binary digits from left to right to obtain 24-bit binary digits;
converting the first 8 digits in the 24 digits into decimal digits to obtain a red channel color value in the red, green and blue RGB three-channel color values;
converting the middle 8-bit binary digits in the 24-bit binary digits into decimal digits to obtain a green channel color value in the red, green and blue RGB three-channel color values;
and converting the last 8 binary digits in the 24-bit binary digits into decimal digits to obtain a blue channel color value in the red, green and blue RGB three-channel color values.
In one possible design, the CNN employs a Resnet50 network structure, a Mobile-net network structure, or a VGG16 network structure.
In one possible design, when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, recording and storing at least one video frame in the audio-video stream data and in synchronization with the current audio frame to obtain a game video highlight frame segment, including:
When the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, judging whether the audio frame number between the previous latest highlight frame and the current audio frame is equal to zero, wherein the highlight confidence refers to the confidence of classifying the current audio frame into the highlight frame in the current classification result, and the previous latest highlight frame refers to the audio frame which is positioned before the current audio frame in the audio-video stream data and corresponds to the highlight confidence which is greater than or equal to the preset confidence threshold;
if the audio frame number is equal to zero, recording and storing at least one video frame which is in the audio-video stream data and is synchronous with the current audio frame to obtain a game video highlight frame segment, otherwise, further judging whether the audio frame number is greater than or equal to a preset frame number threshold value;
if the audio frame number is greater than or equal to the preset frame number threshold, recording and storing at least one video frame in the audio-video stream data and in the same period as the current audio frame to obtain a game video highlight frame segment, otherwise recording and storing at least one video frame in the audio-video stream data and in the same period as the middle audio frame and the current audio frame to obtain a game video highlight frame segment, wherein the middle audio frame refers to at least one audio frame in the audio-video stream data, which is positioned between the last highlight frame and the current audio frame.
In one possible design, after obtaining the game video highlight clips, the method further comprises:
judging whether the previous latest game video highlight frame segment is continuous with the latest obtained game video highlight frame segment in time sequence;
if the time sequence is continuous, merging the two game video highlight frame fragments into one game video highlight frame fragment, otherwise, further judging whether the duration of the previous latest game video highlight frame fragment is smaller than or equal to a preset duration threshold value;
and if the duration is less than or equal to the preset duration threshold, deleting the stored latest previous game video highlight frame fragment.
In one possible design, the method further comprises:
summarizing all game video highlight frame fragments recorded in the game process at the end of the game to obtain at least one game video highlight frame fragment;
for each game video highlight segment in the at least one game video highlight segment, accumulating and calculating according to the following formula to obtain a corresponding highlight confidence sum:
wherein k represents a positive integer, GCT k A highlight confidence sum, N, representing a kth game video highlight clip in the at least one game video highlight clip k Representing the total number of frames of a plurality of audio frames taken contemporaneously with the kth game video highlight segment, n representing a positive integer, GC k,n Representing a highlight confidence level for an nth audio frame of the plurality of audio frames;
sequencing the at least one game video highlight frame segment according to the highlight confidence sum from high to low to obtain a game video highlight frame segment sequence;
pushing the first M game video highlight frame fragments in the game video highlight frame fragment sequence to a game player, wherein M represents a preset positive integer less than or equal to K, and K represents the total fragment number of the game video highlight frame fragment sequence.
In one possible design, after obtaining the game video highlight clips, the method further comprises:
randomly extracting a video frame from the game video highlight frame;
performing image processing on the video frame by adopting a perceptual hash algorithm to obtain image fingerprint information of the video frame;
judging whether the number of different data bits of the image fingerprint information of the video frame and the image fingerprint information of the game video target highlight is greater than or equal to a preset bit number threshold value;
If yes, deleting the recorded and saved game video highlight frame fragments.
In a second aspect, a game video highlight recording device is provided, which comprises a data acquisition module, a fourier transform processing module, a frequency point amplitude encoding module, an image drawing module to be identified, a highlight frame classification module and a video frame storage module;
the data acquisition module is used for acquiring audio and video stream data generated in real time in the game process;
the Fourier transform processing module is in communication connection with the data acquisition module and is used for carrying out fast Fourier transform processing on the current audio frame in the audio-video stream data to obtain a current frequency spectrum;
the frequency point amplitude coding module is in communication connection with the Fourier transform processing module and is used for respectively coding K amplitude values which are in the current frequency spectrum and correspond to K frequency points one by one into RGB three-channel color values to obtain current data to be identified which contain K RGB values, wherein K represents a natural number which is not less than 64, and the K frequency points are distributed at equal intervals in a human auditory frequency domain interval;
the image drawing module to be identified is in communication connection with the frequency point amplitude encoding module and is used for drawing the current image to be identified with a pixel matrix of K according to K RGB values of the current data to be identified, wherein K is a natural number not smaller than the square root of K;
The highlight frame classifying module is in communication connection with the image drawing module to be recognized and is used for inputting the current image to be recognized into a highlight frame classifying model which is trained in advance based on a convolutional neural network CNN and a highlight audio frame to obtain a current classifying result, wherein the highlight audio frame is an audio frame synchronous with a game video target highlight picture and is used for providing a positive sample for highlight frame classifying training for the highlight frame classifying model;
the video frame storage module is respectively in communication connection with the data acquisition module and the highlight frame classification module, and is used for recording and storing at least one video frame in the audio and video stream data and in the same period as the current audio frame when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold value to obtain a game video highlight frame fragment, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver in communication connection in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to receive and transmit a voice signal, and the processor is configured to read the computer program and perform the game video highlight recording method according to any of the first aspect or any of the possible designs of the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having instructions stored thereon which, when executed on a computer, perform the game video highlight recording method as described in the first aspect or any of the possible designs of the first aspect.
In a fifth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of recording a game video highlight as described in the first aspect or any of the possible designs of the first aspect.
The beneficial effect of above-mentioned scheme:
(1) The invention creatively provides a new scheme for indirectly identifying a game highlight moment picture based on a contemporaneous audio frame, namely, after audio and video stream data generated in real time in the game process are acquired, a current image to be identified containing spectrum characteristic information is obtained through fast Fourier transform, frequency point amplitude coding and drawing processing based on the current audio frame in the audio and video stream data, then the image is input into a highlight frame classification model which is trained based on a convolutional neural network CNN and a highlight audio frame to obtain a current classification result, and finally at least one video frame which is in the audio and video stream data and is contemporaneous with the current audio frame is recorded and stored when the highlight confidence in the classification result is greater than or equal to a preset confidence threshold value to obtain a game video highlight picture segment;
(2) Adjacent segments can be combined and isolated transient segments can be removed, so that the aim of avoiding excessively zero fragmentation of recorded video highlight segments of the game is fulfilled, and content with high review value is pushed to a player;
(3) The method can also calculate the review value of each segment for all the video highlight picture segments recorded in the game process when the game is finished, and push the content with the most review value to the game player based on the review value, so that the game experience of the player can be further improved, and the method is convenient for practical application and popularization.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart illustrating a method for recording a video highlight of a game according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a game video highlight recording apparatus according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the present application will be briefly described below with reference to the accompanying drawings and the description of the embodiments or the prior art, and it is obvious that the following description of the structure of the drawings is only some embodiments of the present application, and other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art. It should be noted that the description of these examples is for aiding in understanding the present application, but is not intended to limit the present application.
It should be understood that although the terms first and second, etc. may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, a first object may be referred to as a second object, and similarly a second object may be referred to as a first object, without departing from the scope of example embodiments of the application.
It should be understood that for the term "and/or" that may appear herein, it is merely one association relationship that describes an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: three cases of A alone, B alone or both A and B exist; as another example, A, B and/or C, can represent the presence of any one of A, B and C or any combination thereof; for the term "/and" that may appear herein, which is descriptive of another associative object relationship, it means that there may be two relationships, e.g., a/and B, it may be expressed that: the two cases of A and B exist independently or simultaneously; in addition, for the character "/" that may appear herein, it is generally indicated that the context associated object is an "or" relationship.
Examples:
as shown in fig. 1, the recording method of game video highlights provided in the first aspect of the present embodiment may be performed by, but not limited to, a computer device having a certain computing resource and capable of running a game program, for example, a platform server, a personal computer (Personal Computer, PC, a multipurpose computer with a size, price and performance suitable for personal use, a desktop computer, a notebook computer, a small notebook computer, a tablet computer, an ultrabook, etc. all belong to a personal computer), a smart phone, a personal digital assistant (Personal Digital Assistant, PDA) or an electronic device such as a wearable device. As shown in fig. 1, the game video highlight recording method may include, but is not limited to, the following steps S1 to S6.
S1, acquiring audio and video stream data generated in real time in the game process.
In the step S1, since the existing game program presents the game video picture and the game audio sound synchronized with the game video picture to the player in real time during the game in order to provide the player with the basic game immersion, the av stream data generated in real time during the game and used for presenting the foregoing game video picture and game audio sound can be acquired by the conventional art.
S2, performing fast Fourier transform processing on the current audio frame in the audio and video stream data to obtain a current frequency spectrum.
In the step S2, the current audio frame is the minimum unit data for displaying the current game audio sound, which may be, but not limited to, AAC (Advanced Audio Coding ) audio frame or MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert compression standard audio layer three) audio frame, the former contains 1024 sampling points, the latter contains 1152 sampling points, so the current audio frame can be obtained from the audio-video stream data in a conventional manner. Since the frame playing time length of the current audio frame is inversely related to the audio sampling rate (i.e. the higher the audio sampling rate, the shorter the frame playing time length), for example, when the audio sampling rate is 48kHz, the frame playing time length is 21.32 ms, and when the audio sampling rate is 20.05kHz, the frame playing time length is 46.43 ms, the audio sampling rate of the current audio frame is preferably lower, for example, 8kHz or 11.025kHz, in order to be able to replace more video frames for highlight picture recognition later. In addition, the fast fourier transform processing is a conventional signal processing method, and will not be described herein.
S3, respectively encoding K magnitudes which are in the current frequency spectrum and correspond to the K frequency points one by one into RGB three-channel color values, and obtaining current data to be identified which comprise K RGB values, wherein K represents a natural number which is not less than 64, and the K frequency points are distributed at equal intervals in a human auditory frequency domain interval.
In the step S3, since the current audio frame is used for displaying the current game audio sound to the player, the spectrum features of the highlight sound synchronous with the highlight picture such as the two-break, the three-break or the five-break are necessarily located in the human auditory frequency domain interval, and the K frequency points are preferably set to be distributed at equal intervals in the human auditory frequency domain interval; the human auditory frequency domain interval is generally 20 Hz-20 kHz, and if the frequency interval is set to be 10Hz by way of example, the K can be 1999, so that the design requirement of not less than 64 is met. In addition, specific coding modes may include, but are not limited to: transforming the K amplitude values into values to be transformed under the same value unit and respectively within a section [0,16777215] by means of transforming the value units; converting the value to be converted from decimal numbers to binary numbers; 0 is complemented on the binary digits from left to right to obtain 24-bit binary digits; converting the first 8 digits in the 24 digits into decimal digits to obtain a red channel color value in the red, green and blue RGB three-channel color values; converting the middle 8-bit binary digits in the 24-bit binary digits into decimal digits to obtain a green channel color value in the red, green and blue RGB three-channel color values; and converting the last 8 binary digits in the 24-bit binary digits into decimal digits to obtain a blue channel color value in the red, green and blue RGB three-channel color values.
And S4, drawing to obtain a current image to be identified with a pixel matrix of K according to the K RGB values of the current data to be identified, wherein K is a natural number not smaller than the square root of K.
In the step S4, the specific way of drawing the current image to be recognized may be, but is not limited to, thatThe RGB value is taken as the->Line and->RGB values of column pixels, wherein +.>For natural numbers between 1 and K, floor () represents a lower rounding function, and as for other pixels, the padding processing may be performed in a usual manner such as zero padding or average RGB padding, so that a rectangular image to be recognized may be obtained, for example for the case of 1999 magnitudes,an image to be identified with a pixel matrix of 45 x 45 can be obtained; for 396 magnitudes, an image to be identified with a pixel matrix of 20×20 can be obtained. In addition, considering that the size of the initially obtained image to be identified may be too small, the classification effect based on the convolutional neural network is not ideal, so after the current image to be identified is obtained, the method further comprises: and when K is smaller than a preset quantity threshold value, respectively amplifying the current images to be identified to obtain corresponding images to be identified with standard sizes. For example, an image with a size of 64 x 64 is enlarged.
S5, inputting the current image to be identified into a highlight frame classification model which completes pre-training based on a convolutional neural network CNN and a highlight audio frame to obtain a current classification result, wherein the highlight audio frame is an audio frame synchronous with a game video target highlight picture and is used for providing a positive sample for highlight frame classification training for the highlight frame classification model.
In the step S5, the convolutional neural network CNN (Convolutional Neural Networks) is an existing feedforward neural network (Feedforward Neural Networks) based on convolutional calculation and having a depth structure, including but not limited to an input layer, a convolutional layer, an active layer, a pooling layer, a full-connection layer, and an output layer, and can perform classification of image recognition by the output layer using a normalized index Softmax function; in particular, the CNN may, but is not limited to, employ a Resnet50 network structure, a Mobile-net network structure, or a VGG16 network structure, etc. The highlight audio frames need to be acquired in advance, for example, an audio frame that coincides with a game video object highlight such as a two-break, three-break, or five-break can be used as the highlight audio frame. Specific ways in which the highlight audio frames are used to provide positive samples for highlight frame classification training for the highlight frame classification model include, but are not limited to: performing the fast Fourier transform processing on the highlight audio frame to obtain a highlight frequency spectrum; then, respectively encoding K magnitudes which are in the highlight frequency spectrum and correspond to the K frequency points one by one into red, green and blue (RGB) three-channel color values to obtain positive sample data containing K RGB values; and finally, drawing to obtain a positive sample image with a pixel matrix of K according to the K RGB values of the positive sample data. Specific pre-training modes of the highlight frame classification model can include, but are not limited to: inputting a plurality of positive sample images obtained based on different wonderful audio frames into a classification model based on the CNN for training, and when the training set accuracy reaches a preset high value interval and the variation amplitude is smaller than a preset amplitude threshold value in the training process, adopting a self-adaptive gradient AdaGrad algorithm to adjust the learning rate, and then continuing training until the learning rate adjustment amplitude is smaller than the preset adjustment threshold value, stopping training to obtain a trained wonderful frame classification model; the adaptive gradient AdaGrad algorithm described above is an existing algorithm that utilizes the sum of the square root of the gradients of each iteration history to modify the learning rate. In addition, the negative sample images for performing highlight frame classification training can be provided for the highlight frame classification model by utilizing some non-highlight audio frames according to the positive sample providing mode, and are input into the classification model based on the CNN for training in the model training process so as to ensure the accuracy of the subsequent highlight frame classification; and the positive sample images and the negative sample images can also form a test sample set so as to carry out a highlight frame classification test on the highlight frame classification model after model training is completed by using the test sample set to verify whether the highlight frame classification can be accurately carried out.
S6, when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, recording and storing at least one video frame which is in the audio-video stream data and is synchronous with the current audio frame to obtain a game video highlight picture segment, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result.
In the step S6, the confidence level is conventional information output after classification and recognition, and the preset confidence threshold is used as a basis for determining whether to classify the current audio frame as a highlight frame, which may be exemplified by 50%. If the confidence level is greater than or equal to the preset confidence level threshold, the current audio frame may be classified as a highlight frame, and at least one video frame reflected in the audio-video stream data and contemporaneous with the current audio frame is a game video highlight frame, so that the at least one video frame needs to be recorded and saved as a game video highlight frame segment. Because the frame playing duration of the current audio frame is longer, for example 46.43 ms, if the video frame rate in the audio-video stream data is 120 frames per second, the frame number of the at least one video frame is about 6 frames, and then one audio frame can be used for replacing the about 6 video frames to indirectly perform highlight moment picture identification, so that the purposes of greatly simplifying the process, improving the identification efficiency and reducing the required computing resources are achieved.
In the step S6, considering that the frame playing duration of an audio frame is only several tens of milliseconds, and a game video highlight such as two-break, three-break or five-break may last for several seconds or more, in order to avoid missing recording of a video frame synchronous with a part of the audio frame due to the fact that the part of the audio frame is identified as a non-highlight frame in the several seconds or more, so as to ensure the integrity of the game video highlight, preferably, when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, at least one video frame in the audio-video stream data and synchronous with the current audio frame is recorded and saved, so as to obtain a game video highlight segment, including but not limited to the following steps S61-S63.
S61, judging whether the number of audio frames between a previous latest highlight frame and the current audio frame is equal to zero or not when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result, and the previous latest highlight frame is the audio frame which is positioned before the current audio frame in the audio-video stream data and corresponds to the highlight confidence which is greater than or equal to the preset confidence threshold.
In the step S61, the previous latest highlight frame is the historical audio frame that was most recently determined to be the highlight frame.
S62, if the audio frame number is equal to zero, recording and storing at least one video frame which is in the audio-video stream data and is synchronous with the current audio frame to obtain a game video highlight frame segment, otherwise, further judging whether the audio frame number is greater than or equal to a preset frame number threshold value.
In the step S62, the preset frame number threshold may be determined in advance according to the audio frame playing duration and the general maintenance duration of the game video object highlight, for example, when the audio frame playing duration is 46.43 ms, the preset frame number threshold may be set to 21 frames by way of example.
S63, if the audio frame number is larger than or equal to the preset frame number threshold, recording and storing at least one video frame in the audio-video stream data and in the same period as the current audio frame to obtain a game video highlight frame segment, otherwise, recording and storing at least one video frame in the audio-video stream data and in the same period as the middle audio frame and the current audio frame to obtain the game video highlight frame segment, wherein the middle audio frame refers to at least one audio frame in the audio-video stream data, which is positioned between the last highlight frame and the current audio frame.
In the step S63, the intermediate audio frame is the audio frame identified as the non-highlight frame in the video highlight frame maintaining time, so that the integrity of the video highlight frame can be ensured by recording and storing at least one video frame in the av stream data and at the same time as the intermediate audio frame and the current audio frame under a certain condition.
After said step S6, it is also considered that the audio frame is used to indirectly perform the highlight picture recognition instead of the contemporaneous plurality of video frames, and in order to ensure the accuracy of such indirect recognition result, it is necessary to perform a frame extraction check after obtaining said game video highlight picture segment, that is, preferably, after obtaining the game video highlight picture segment, said method further includes, but is not limited to, the following steps S71 to S74: s71, randomly extracting a video frame from the game video highlight frame; s72, performing image processing on the video frame by adopting a perceptual hash algorithm to obtain image fingerprint information of the video frame; s73, judging whether the number of different data bits of the image fingerprint information of the video frame and the image fingerprint information of the game video target highlight frame is larger than or equal to a preset bit number threshold value; and S74, if so, deleting the recorded and saved game video highlight frame fragments. The foregoing perceptual hash algorithm is an existing algorithm for generating fingerprint information for image data, and the principle thereof is not described herein again. Based on the foregoing steps S71 to S74, it may be checked in a frame extraction manner whether the video highlight frame segment is a video highlight time frame, if so, the video highlight frame segment is kept, otherwise (i.e. the difference between the image fingerprint information of the video frame and the image fingerprint information of the video target highlight frame is greater) the video highlight frame segment needs to be deleted. In addition, the preset bit number threshold may be exemplified by 10.
The method for recording the game video highlight picture described in the steps S1 to S6 provides a new scheme for indirectly identifying the game highlight picture based on the contemporaneous audio frames, namely, after audio and video stream data generated in real time in the game process are acquired, the current to-be-identified image containing spectral feature information is obtained through fast Fourier transform, frequency point amplitude coding and drawing processing based on the current audio frames in the audio and video stream data, then the image is input into a highlight frame classification model based on a convolutional neural network CNN and a highlight audio frame to finish pre-training, a current classification result is obtained, finally, when the highlight confidence in the classification result is larger than or equal to a preset confidence threshold value, at least one video frame which is synchronous with the current audio frame in the audio and video stream data is recorded and stored, so that a game video highlight picture fragment is obtained, and the purposes of greatly simplifying the process, improving the identification efficiency and reducing the required computing resources can be realized by indirectly carrying out highlight picture identification by using one audio frame instead of a plurality of video frames.
The present embodiment further provides a possible design of how to merge adjacent segments and reject isolated transient segments, based on the technical solution of the first aspect, i.e. after obtaining the video highlight segments, the method further includes, but is not limited to, the following steps S81-S83.
S81, judging whether the last game video highlight frame segment is continuous with the latest obtained game video highlight frame segment in time sequence.
In the step S81, whether the two segments are continuous in time series may be determined based on the human eye reaction time (i.e., typically 0.1 to 0.4 seconds), for example, if the last frame of the previous latest game video highlight segment and the first frame of the latest obtained game video highlight segment differ in time series by 0.4 seconds or more, the two segments may be considered to be discontinuous in time series, and cannot be combined into one segment, otherwise, the two segments are allowed to be combined into one segment.
S82, if the time sequence is continuous, combining the two game video highlight frame fragments into one game video highlight frame fragment, otherwise, further judging whether the duration of the previous latest game video highlight frame fragment is smaller than or equal to a preset duration threshold value.
In the step S82, since the previous latest game video highlight clip is not merged with the latest obtained game video highlight clip, it is a clip with a fixed duration, and it is necessary to determine whether it is an isolated transient clip based on the duration comparison result, if so, it needs to be deleted because the highlight clip is too short. Further, the preset duration threshold may be determined specifically based on the shortest duration of the highlight frame, for example, 1 second.
S83, if the duration is smaller than or equal to the preset duration threshold, deleting the stored latest game video highlight frame fragment.
Based on the possible design one, adjacent segments can be combined and isolated transient segments can be removed, so that the aim of avoiding excessively zero fragmentation of recorded video highlight segments of the game is fulfilled, and content with high review value is pushed to a player.
The embodiment further provides a second possible design how to push high-review value content to the player based on the first possible design, namely, the method further includes, but is not limited to, the following contents S91 to S94.
S91, summarizing all game video highlight frame fragments recorded in the game process when the game is finished, and obtaining at least one game video highlight frame fragment.
S92, accumulating and calculating corresponding highlight confidence sum according to the following formula aiming at each game video highlight frame segment in the at least one game video highlight frame segment:
wherein k represents a positive integer, GCT k A highlight confidence sum, N, representing a kth game video highlight clip in the at least one game video highlight clip k Representing the total number of frames of a plurality of audio frames taken contemporaneously with the kth game video highlight segment, n representing a positive integer, GC k,n Representing a confidence level of the highlight of the nth audio frame among the plurality of audio frames.
In the step S92, as known from the above formula, the confidence level of each segment is always positively correlated with the corresponding contemporaneous audio frame number and the confidence level of the contemporaneous audio frame, and thus can be used to reflect the review value of the corresponding segment: the longer the segment duration and the more highlights, the higher the review value.
S93, sequencing the at least one game video highlight frame segment according to the highlight confidence coefficient sum from high to low, and obtaining a game video highlight frame segment sequence.
S94, pushing the first M game video highlight frame fragments in the game video highlight frame fragment sequence to a game player, wherein M represents a preset positive integer less than or equal to K, and K represents the total fragment number of the game video highlight frame fragment sequence.
In the step S94, if the value of K is 100, the value of M is 10, i.e. the first 10 game video highlight clips with the highest review value are pushed to the game player.
Therefore, based on the second possible design, the review value of each segment can be calculated for all the video highlight segments recorded in the game process at the end of the game, and the content with the most review value is pushed to the game player based on the review value, so that the game experience of the player can be further improved.
As shown in fig. 2, a second aspect of the present embodiment provides a virtual device for implementing the game video highlight recording method of the first aspect, which may be designed into one or two, and includes a data acquisition module, a fourier transform processing module, a frequency point amplitude encoding module, an image drawing module to be identified, a highlight frame classification module, and a video frame storage module;
the data acquisition module is used for acquiring audio and video stream data generated in real time in the game process;
the Fourier transform processing module is in communication connection with the data acquisition module and is used for carrying out fast Fourier transform processing on the current audio frame in the audio-video stream data to obtain a current frequency spectrum;
the frequency point amplitude coding module is in communication connection with the Fourier transform processing module and is used for respectively coding K amplitude values which are in the current frequency spectrum and correspond to K frequency points one by one into RGB three-channel color values to obtain current data to be identified which contain K RGB values, wherein K represents a natural number which is not less than 64, and the K frequency points are distributed at equal intervals in a human auditory frequency domain interval;
The image drawing module to be identified is in communication connection with the frequency point amplitude encoding module and is used for drawing the current image to be identified with a pixel matrix of K according to K RGB values of the current data to be identified, wherein K is a natural number not smaller than the square root of K;
the highlight frame classifying module is in communication connection with the image drawing module to be recognized and is used for inputting the current image to be recognized into a highlight frame classifying model which is trained in advance based on a convolutional neural network CNN and a highlight audio frame to obtain a current classifying result, wherein the highlight audio frame is an audio frame synchronous with a game video target highlight picture and is used for providing a positive sample for highlight frame classifying training for the highlight frame classifying model;
the video frame storage module is respectively in communication connection with the data acquisition module and the highlight frame classification module, and is used for recording and storing at least one video frame in the audio and video stream data and in the same period as the current audio frame when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold value to obtain a game video highlight frame fragment, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result.
The working process, working details and technical effects of the foregoing apparatus provided in the second aspect of the present embodiment may be referred to in the first aspect, the first or second possible design of the game video highlight recording method, which are not described herein again.
As shown in fig. 3, a third aspect of the present embodiment provides an entity apparatus for implementing the game video highlight recording method according to the first aspect, the first or the second aspect, and the entity apparatus includes a memory, a processor, and a transceiver, which are sequentially connected in communication, where the memory is configured to store a computer program, the transceiver is configured to transmit and receive a voice signal, and the processor is configured to read the computer program, and perform the game video highlight recording method according to the first aspect, the first or the second aspect. By way of specific example, the Memory may include, but is not limited to, random-Access Memory (RAM), read-Only Memory (ROM), flash Memory (Flash Memory), first-in first-out Memory (First Input First Output, FIFO), and/or first-in last-out Memory (First Input Last Output, FILO), and the like.
The working process, working details and technical effects of the foregoing chip provided in the third aspect of the present embodiment may be referred to in the first aspect, the first or second possible design of the game video highlight recording method, and will not be described herein.
A fourth aspect of the present embodiment provides a computer readable storage medium storing instructions comprising the game video highlight recording method as described in the first aspect, possible to design one or possible to design two, i.e. having instructions stored thereon which, when executed on a computer, perform the game video highlight recording method as described in the first aspect, possible to design one or possible to design two. The computer readable storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, and/or a Memory Stick (Memory Stick), where the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
The working process, working details and technical effects of the computer readable storage medium provided in the fourth aspect of the present embodiment can be referred to as the game video highlight recording method in the first aspect, the first design possibility or the second design possibility, and will not be repeated here.
A fifth aspect of the present embodiment provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of recording a game video highlight as described in the first aspect, possibly designed one or possibly designed two. Wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus.
Finally, it should be noted that: the foregoing description is only of the preferred embodiments of the invention and is not intended to limit the scope of the invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for recording a video highlight of a game, comprising:
acquiring audio and video stream data generated in real time in the game process;
performing fast Fourier transform processing on the current audio frame in the audio-video stream data to obtain a current frequency spectrum;
respectively encoding K magnitudes which are in the current frequency spectrum and correspond to K frequency points one by one into RGB three-channel color values to obtain current data to be identified, wherein K represents a natural number which is not less than 64, and the K frequency points are distributed at equal intervals in a human auditory frequency domain interval;
drawing to obtain a current image to be recognized, wherein the pixel matrix of the current image to be recognized is K, according to K RGB values of the current data to be recognized, and K is a natural number not smaller than the square root of K;
inputting the current image to be identified into a highlight frame classification model which is trained in advance based on a convolutional neural network CNN and a highlight audio frame to obtain a current classification result, wherein the highlight audio frame is an audio frame synchronous with a game video target highlight picture and is used for providing a positive sample for highlight frame classification training for the highlight frame classification model;
When the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, recording and storing at least one video frame which is in the audio-video stream data and is synchronous with the current audio frame to obtain a game video highlight picture segment, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result.
2. The method of claim 1, wherein the encoding the K magnitudes corresponding to the K frequency points one to one into the RGB three-channel color values comprises:
transforming the K magnitudes into values of the same numerical unit and respectively in intervals by means of transforming the numerical units
A value to be converted in [0,16777215 ];
converting the value to be converted from decimal numbers to binary numbers;
0 is complemented on the binary digits from left to right to obtain 24-bit binary digits;
converting the first 8 digits in the 24 digits into decimal digits to obtain a red channel color value in the red, green and blue RGB three-channel color values;
converting the middle 8-bit binary digits in the 24-bit binary digits into decimal digits to obtain a green channel color value in the red, green and blue RGB three-channel color values;
And converting the last 8 binary digits in the 24-bit binary digits into decimal digits to obtain a blue channel color value in the red, green and blue RGB three-channel color values.
3. The game video highlight recording method according to claim 1, wherein the CNN adopts a network structure of Resnet50, a Mobile-net or a VGG 16.
4. The method for recording a video highlight of a game according to claim 1, wherein when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, recording and storing at least one video frame in the audio-video stream data and in synchronization with the current audio frame to obtain a video highlight segment of the game, comprising:
when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold, judging whether the audio frame number between the previous latest highlight frame and the current audio frame is equal to zero, wherein the highlight confidence refers to the confidence of classifying the current audio frame into the highlight frame in the current classification result, and the previous latest highlight frame refers to the audio frame which is positioned before the current audio frame in the audio-video stream data and corresponds to the highlight confidence which is greater than or equal to the preset confidence threshold;
If the audio frame number is equal to zero, recording and storing at least one video frame which is in the audio-video stream data and is synchronous with the current audio frame to obtain a game video highlight frame segment, otherwise, further judging whether the audio frame number is greater than or equal to a preset frame number threshold value;
if the audio frame number is greater than or equal to the preset frame number threshold, recording and storing at least one video frame in the audio-video stream data and in the same period as the current audio frame to obtain a game video highlight frame segment, otherwise recording and storing at least one video frame in the audio-video stream data and in the same period as the middle audio frame and the current audio frame to obtain a game video highlight frame segment, wherein the middle audio frame refers to at least one audio frame in the audio-video stream data, which is positioned between the last highlight frame and the current audio frame.
5. The method of claim 1, wherein after obtaining the video highlight clip, the method further comprises:
judging whether the previous latest game video highlight frame segment is continuous with the latest obtained game video highlight frame segment in time sequence;
If the time sequence is continuous, merging the two game video highlight frame fragments into one game video highlight frame fragment, otherwise, further judging whether the duration of the previous latest game video highlight frame fragment is smaller than or equal to a preset duration threshold value;
and if the duration is less than or equal to the preset duration threshold, deleting the stored latest previous game video highlight frame fragment.
6. The method of claim 5, further comprising:
summarizing all game video highlight frame fragments recorded in the game process at the end of the game to obtain at least one game video highlight frame fragment;
for each game video highlight segment in the at least one game video highlight segment, accumulating and calculating according to the following formula to obtain a corresponding highlight confidence sum:
wherein k represents a positive integer, GCT k A highlight confidence sum, N, representing a kth game video highlight clip in the at least one game video highlight clip k Representing the total number of frames of a plurality of audio frames taken contemporaneously with the kth game video highlight segment, n representing a positive integer, GC k,n Representing a highlight confidence level for an nth audio frame of the plurality of audio frames;
sequencing the at least one game video highlight frame segment according to the highlight confidence sum from high to low to obtain a game video highlight frame segment sequence;
pushing the first M game video highlight frame fragments in the game video highlight frame fragment sequence to a game player, wherein M represents a preset positive integer less than or equal to K, and K represents the total fragment number of the game video highlight frame fragment sequence.
7. The method of claim 1, wherein after obtaining the video highlight clip, the method further comprises:
randomly extracting a video frame from the game video highlight frame;
performing image processing on the video frame by adopting a perceptual hash algorithm to obtain image fingerprint information of the video frame;
judging whether the number of different data bits of the image fingerprint information of the video frame and the image fingerprint information of the game video target highlight is greater than or equal to a preset bit number threshold value;
if yes, deleting the recorded and saved game video highlight frame fragments.
8. The game video highlight image recording device is characterized by comprising a data acquisition module, a Fourier transform processing module, a frequency point amplitude encoding module, an image drawing module to be identified, a highlight frame classification module and a video frame storage module;
the data acquisition module is used for acquiring audio and video stream data generated in real time in the game process;
the Fourier transform processing module is in communication connection with the data acquisition module and is used for carrying out fast Fourier transform processing on the current audio frame in the audio-video stream data to obtain a current frequency spectrum;
the frequency point amplitude coding module is in communication connection with the Fourier transform processing module and is used for respectively coding K amplitude values which are in the current frequency spectrum and correspond to K frequency points one by one into RGB three-channel color values to obtain current data to be identified which contain K RGB values, wherein K represents a natural number which is not less than 64, and the K frequency points are distributed at equal intervals in a human auditory frequency domain interval;
the image drawing module to be identified is in communication connection with the frequency point amplitude encoding module and is used for drawing the current image to be identified with a pixel matrix of K according to K RGB values of the current data to be identified, wherein K is a natural number not smaller than the square root of K;
The highlight frame classifying module is in communication connection with the image drawing module to be recognized and is used for inputting the current image to be recognized into a highlight frame classifying model which is trained in advance based on a convolutional neural network CNN and a highlight audio frame to obtain a current classifying result, wherein the highlight audio frame is an audio frame synchronous with a game video target highlight picture and is used for providing a positive sample for highlight frame classifying training for the highlight frame classifying model;
the video frame storage module is respectively in communication connection with the data acquisition module and the highlight frame classification module, and is used for recording and storing at least one video frame in the audio and video stream data and in the same period as the current audio frame when the highlight confidence in the current classification result is greater than or equal to a preset confidence threshold value to obtain a game video highlight frame fragment, wherein the highlight confidence is the confidence of classifying the current audio frame into the highlight frame in the current classification result.
9. A computer device comprising a memory, a processor and a transceiver in communication connection in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive data, and the processor is configured to read the computer program and perform the game video highlight recording method according to any one of claims 1 to 7.
10. A computer readable storage medium having instructions stored thereon which, when executed on a computer, perform the method of recording a game video highlight according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310062849.0A CN116074566B (en) | 2023-01-13 | 2023-01-13 | Game video highlight recording method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310062849.0A CN116074566B (en) | 2023-01-13 | 2023-01-13 | Game video highlight recording method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116074566A CN116074566A (en) | 2023-05-05 |
| CN116074566B true CN116074566B (en) | 2023-10-20 |
Family
ID=86176462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310062849.0A Active CN116074566B (en) | 2023-01-13 | 2023-01-13 | Game video highlight recording method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116074566B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111625661A (en) * | 2020-05-14 | 2020-09-04 | 国家计算机网络与信息安全管理中心 | Audio and video segment classification method and device |
| CN112788200A (en) * | 2020-12-04 | 2021-05-11 | 光大科技有限公司 | Method and device for determining frequency spectrum information, storage medium and electronic device |
| WO2021163882A1 (en) * | 2020-02-18 | 2021-08-26 | 深圳市欢太科技有限公司 | Game screen recording method and apparatus, and computer-readable storage medium |
| CN113643728A (en) * | 2021-08-12 | 2021-11-12 | 荣耀终端有限公司 | Audio recording method, electronic device, medium, and program product |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10390082B2 (en) * | 2016-04-01 | 2019-08-20 | Oath Inc. | Computerized system and method for automatically detecting and rendering highlights from streaming videos |
-
2023
- 2023-01-13 CN CN202310062849.0A patent/CN116074566B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021163882A1 (en) * | 2020-02-18 | 2021-08-26 | 深圳市欢太科技有限公司 | Game screen recording method and apparatus, and computer-readable storage medium |
| CN111625661A (en) * | 2020-05-14 | 2020-09-04 | 国家计算机网络与信息安全管理中心 | Audio and video segment classification method and device |
| CN112788200A (en) * | 2020-12-04 | 2021-05-11 | 光大科技有限公司 | Method and device for determining frequency spectrum information, storage medium and electronic device |
| CN113643728A (en) * | 2021-08-12 | 2021-11-12 | 荣耀终端有限公司 | Audio recording method, electronic device, medium, and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116074566A (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113395578B (en) | Method, device, equipment and storage medium for extracting video theme text | |
| CN110347872B (en) | Video cover image extraction method and device, storage medium and electronic equipment | |
| CN111198958A (en) | Method, device and terminal for matching background music | |
| CN111062871A (en) | Image processing method and device, computer equipment and readable storage medium | |
| CN112559800B (en) | Method, apparatus, electronic device, medium and product for processing video | |
| CN113420556B (en) | Emotion recognition method, device, equipment and storage medium based on multi-mode signals | |
| CN111027419B (en) | Method, device, equipment and medium for detecting video irrelevant content | |
| CN108764114B (en) | Signal identification method and device, storage medium and terminal thereof | |
| EP4390725A1 (en) | Video retrieval method and apparatus, device, and storage medium | |
| WO2023173890A1 (en) | Real-time voice recognition method, model training method, apparatus, device, and storage medium | |
| CN115798459B (en) | Audio processing method and device, storage medium and electronic equipment | |
| CN112201253B (en) | Text marking method, text marking device, electronic equipment and computer readable storage medium | |
| CN111488813B (en) | Video emotion marking method and device, electronic equipment and storage medium | |
| CN110263218A (en) | Video presentation document creation method, device, equipment and medium | |
| CN108847251B (en) | Voice duplicate removal method, device, server and storage medium | |
| CN116074566B (en) | Game video highlight recording method, device, equipment and storage medium | |
| CN111986259B (en) | Training of pigment and text detection model, auditing method of video data and related device | |
| CN111858879B (en) | Question and answer method and system based on machine reading understanding, storage medium and computer equipment | |
| CN117079671A (en) | Audio processing method, device, computer equipment and storage medium | |
| CN116189678A (en) | Voice processing method and device and computer equipment | |
| CN107437414A (en) | Parallelization visitor's recognition methods based on embedded gpu system | |
| CN114706552A (en) | Voice control method, device and equipment based on interactive page and storage medium | |
| CN116631407A (en) | Voice playing method, device, equipment and medium based on LED display screen | |
| CN118570864A (en) | Method, device, equipment, medium and product for classifying biological information | |
| CN115966206A (en) | Intelligent picture generation method, device, equipment and medium for AI voice recognition |
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 |