CN114531557B - Digital television signal acquisition method and device based on mixed data packet - Google Patents

Digital television signal acquisition method and device based on mixed data packet Download PDF

Info

Publication number
CN114531557B
CN114531557B CN202210084917.9A CN202210084917A CN114531557B CN 114531557 B CN114531557 B CN 114531557B CN 202210084917 A CN202210084917 A CN 202210084917A CN 114531557 B CN114531557 B CN 114531557B
Authority
CN
China
Prior art keywords
data
digital
program
packet
preset
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
Application number
CN202210084917.9A
Other languages
Chinese (zh)
Other versions
CN114531557A (en
Inventor
谢定容
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Justek Technology Co ltd
Original Assignee
Shenzhen Justek Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Justek Technology Co ltd filed Critical Shenzhen Justek Technology Co ltd
Priority to CN202210084917.9A priority Critical patent/CN114531557B/en
Publication of CN114531557A publication Critical patent/CN114531557A/en
Application granted granted Critical
Publication of CN114531557B publication Critical patent/CN114531557B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/44Receiver circuitry for the reception of television signals according to analogue transmission standards
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/04Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Television Signal Processing For Recording (AREA)
  • Television Systems (AREA)

Abstract

The application discloses a digital television signal acquisition method based on a mixed data packet, which is used for carrying out continuous image acquisition processing to obtain digital video data; obtaining first digital audio data; combining the first digital program data with a specified time sequence; obtaining a second digital audio data; performing timing adjustment to form second digital program data; cutting off the first data segments and the second data segments respectively to obtain a plurality of first data segments and a plurality of second data segments; performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; recording as default program data; if a program signal acquisition request from a digital television playing end is received, default program data are sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point, so that the problem of scenario blank possibly occurring when a user watches the digital television program is solved, and the overall playing effect is improved.

Description

Digital television signal acquisition method and device based on mixed data packet
Technical Field
The present disclosure relates to the field of computers, and in particular, to a method and apparatus for acquiring digital television signals based on hybrid data packets.
Background
In the conventional digital television signal acquisition scheme, only a digital acquisition device is used to acquire audio and video digital signals of program scenes (of course, the program scenes include characters, and actually shot shots including the characters). Therefore, the conventional digital television signal acquisition scheme (i.e., digital television program signal data acquisition) can only generate one digital program data to play corresponding audio and video at the digital television playing end. However, when the user watches the digital television program, the line of sight may leave the screen of the playing end of the digital television, so that a scenario blank will appear, and the digital television signal acquired by the traditional method cannot solve the problem, thereby causing objective degradation of the playing effect.
Disclosure of Invention
The application provides a digital television signal acquisition method based on a mixed data packet, which comprises the following steps:
s1, adopting a preset digital camera to perform continuous image acquisition processing on a preset program scene so as to obtain digital video data;
S2, adopting a preset first digital audio collector to carry out audio collection processing on the program scene so as to obtain first digital audio data corresponding to the digital video data;
s3, combining the digital video data and the first digital audio data into first digital program data with a specified time sequence;
s4, adopting a preset second digital audio collector to carry out audio collection processing on the broadcaster so as to obtain second digital audio data; wherein the second digital audio data is used for performing voice description on the program scene;
s5, performing time sequence adjustment on the second digital audio data to form second digital data with the designated time sequence;
s6, cutting off the first digital program data and the second digital program data according to a preset cutting-off method, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; wherein the first data segments and the second data segments are in one-to-one correspondence in time;
s7, performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2;
S8, marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data, and judging whether a program signal acquisition request from a digital television playing end is received or not;
and S9, if a program signal acquisition request from the digital television playing end is received, transmitting the default program data, and requiring the digital television playing end to only play the first data segment or the second data segment in the mixed data packet at any time point.
Further, after the step S8 of marking the first mixed data packet, the second mixed data packet, the … and the nth mixed data packet as default program data and determining whether a program signal acquisition request from the digital television playing end is received, the method includes:
s81, if a program signal acquisition request from a digital television playing end is received, inputting the plurality of first data segments into a preset first importance degree prediction model for processing so as to obtain a first importance degree sequence output by the first importance degree prediction model; the first importance degree sequence is composed of n first importance degree values, the n first importance degree values respectively correspond to n first data segments, and the first importance degree prediction model is trained based on a neural network model;
S82, inputting the plurality of second data segments into a preset second importance prediction model for processing to obtain a second importance sequence output by the second importance prediction model; the second importance degree sequence is composed of n second importance degree values, the n second importance degree values respectively correspond to n second data segments, and the second importance degree prediction model is trained based on a neural network model;
s83, selecting a designated first data segment from the plurality of first data segments according to a rule that the importance value is larger than a preset importance threshold, and selecting an important second data segment from the plurality of second data segments;
s84, acquiring a specified second data segment corresponding to the specified first data segment according to the corresponding relation between the first data segment and the second data segment;
s85, generating standby program data, sending the standby program data, and requiring a digital television playing end to only play one first data segment or one second data segment at any time point; wherein the spare program data is constituted by the plurality of first data pieces, the important second data pieces, and the specified second data pieces.
Further, if a request for acquiring a program signal from a digital television playing end is received, the step S81 of inputting the plurality of first data segments into a preset first importance prediction model for processing to obtain a first importance sequence output by the first importance prediction model includes:
s801, if a program signal acquisition request from a digital television broadcasting terminal is received, judging whether the received program signal acquisition request requests a comprehensive program signal or a brief program signal;
s802, if the received program signal acquisition request is a request brief program signal, inputting the plurality of first data segments into a preset first importance degree prediction model for processing so as to obtain a first importance degree sequence output by the first importance degree prediction model.
Further, if a program signal acquisition request from a digital television playing end is received, the step S81 of inputting the plurality of first data segments into a preset first importance prediction model for processing to obtain a first importance sequence output by the first importance prediction model includes:
s71, acquiring a plurality of sample data collected in advance; wherein the sample data is composed of sample video data and sample audio data corresponding to the sample video data;
S72, respectively carrying out manual segmentation and labeling treatment on the plurality of sample data to obtain a plurality of sample data segment sequences; wherein, all sample data segments in each sample data segment sequence are marked with importance degrees;
s73, dividing the plurality of sample data segment sequences into a plurality of training data segment sequences and a plurality of verification data segment sequences according to a preset proportion;
s74, sequentially inputting the training data segment sequences into a preset neural network model for training to obtain a preliminary prediction model; in the training process, a back propagation algorithm is adopted to update parameters in each layer of network;
s75, verifying the preliminary prediction model by adopting the plurality of verification data segment sequences to obtain a verification result, and judging whether the verification result passes the verification;
and S76, if the verification result is that the verification is passed, the preliminary prediction model is recorded as a first importance degree prediction model.
Further, the program scenario has a plurality of program scenes, and the step S6 of performing cutting processing on the first digital program data and the second digital program data according to a preset cutting method, so as to obtain a plurality of first data segments and a plurality of second data segments correspondingly includes:
S601, recording video clips in the same long lens as a first data segment, so as to obtain a plurality of first data segments corresponding to all the long lenses; the long shot refers to a video clip for continuously shooting the same scene without switching the shot, and the continuous shooting time of the long shot is larger than a preset time threshold;
s602, sequentially cutting off video clips except long shots according to a preset time length to obtain a plurality of first data segments;
s603, cutting the second digital data into a plurality of second data segments corresponding to all the first data segments according to the specified time sequence and all the first data segments obtained through cutting.
The application provides a digital television signal acquisition device based on mixed data packet, including:
the digital video data acquisition unit is used for adopting a preset digital camera to perform continuous image acquisition processing on a preset program scene so as to obtain digital video data;
the first digital audio data acquisition unit is used for carrying out audio acquisition processing on the program scene by adopting a preset first digital audio acquisition device so as to obtain first digital audio data corresponding to the digital video data;
A first digital program data combining unit configured to combine the digital video data and the first digital audio data into first digital program data having a specified timing;
the second digital audio data acquisition unit is used for carrying out audio acquisition processing on the broadcaster by adopting a preset second digital audio acquisition device so as to obtain second digital audio data; wherein the second digital audio data is used for performing voice description on the program scene;
a second digital data acquisition unit configured to perform timing adjustment on the second digital audio data to form second digital data having the specified timing;
a digital program data cutting unit, configured to perform cutting processing on the first digital program data and the second digital program data according to a preset cutting method, so as to obtain a plurality of first data segments and a plurality of second data segments correspondingly; wherein the first data segments and the second data segments are in one-to-one correspondence in time;
a hybrid data packet generation unit, configured to perform hybrid data packet generation processing to generate a first hybrid data packet, a second hybrid data packet, …, and an nth hybrid data packet; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2;
A default program data marking unit, configured to mark the first hybrid data packet, the second hybrid data packet, …, and the nth hybrid data packet as default program data, and determine whether a program signal acquisition request from a digital television playing end is received;
the default program data sending unit is used for sending the default program data if a program signal acquisition request from the digital television playing end is received, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point.
The present application provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the methods described above when the computer program is executed by the processor.
The present application provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the above.
The digital television signal acquisition method, the device, the computer equipment and the storage medium based on the mixed data packet perform continuous image acquisition processing on a preset program scene to obtain digital video data; obtaining first digital audio data corresponding to the digital video data; combining the first digital program data with a specified time sequence; obtaining a second digital audio data; performing timing adjustment to form second digital program data having the specified timing; cutting off respectively, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data; if a program signal acquisition request from the digital television playing end is received, the default program data is sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point, so that the problem of scenario blank possibly occurring when a user watches the digital television program is solved, and the overall playing effect is improved.
The problem of the plot blank that the user probably appears when watching the digital television program is solved, the overall playing effect is improved, and the problem that the plot blank appears when the viewer is found by the applicant is generally caused by the conditions of eye closure and the like, namely, the vision in five senses leaves the digital television, but the hearing in five senses still receives external sound signals independently. Therefore, by constructing two sets of digital program data with the same time sequence, even if the viewer leaves the digital television, the viewer can still fill the blank plot which can occur in the traditional scheme through the other set of digital program data, so that the overall playing effect is improved. Of course, only the principle of the application will be described, and the specific implementation will be described in detail with reference to the following steps.
Drawings
Fig. 1 is a flow chart of a digital television signal acquisition method based on a hybrid data packet according to an embodiment of the present application;
fig. 2 is a schematic block diagram of a digital television signal acquisition device based on a hybrid data packet according to an embodiment of the present application;
fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present application provides a digital television signal acquisition method based on a hybrid data packet, including the following steps:
s1, adopting a preset digital camera to perform continuous image acquisition processing on a preset program scene so as to obtain digital video data;
s2, adopting a preset first digital audio collector to carry out audio collection processing on the program scene so as to obtain first digital audio data corresponding to the digital video data;
s3, combining the digital video data and the first digital audio data into first digital program data with a specified time sequence;
s4, adopting a preset second digital audio collector to carry out audio collection processing on the broadcaster so as to obtain second digital audio data; wherein the second digital audio data is used for performing voice description on the program scene;
S5, performing time sequence adjustment on the second digital audio data to form second digital data with the designated time sequence;
s6, cutting off the first digital program data and the second digital program data according to a preset cutting-off method, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; wherein the first data segments and the second data segments are in one-to-one correspondence in time;
s7, performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2;
s8, marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data, and judging whether a program signal acquisition request from a digital television playing end is received or not;
and S9, if a program signal acquisition request from the digital television playing end is received, transmitting the default program data, and requiring the digital television playing end to only play the first data segment or the second data segment in the mixed data packet at any time point.
As described in the above steps S1-S3, a preset digital camera is adopted to perform continuous image acquisition processing on a preset program scene so as to obtain digital video data; adopting a preset first digital audio collector to perform audio collection processing on the program scene so as to obtain first digital audio data corresponding to the digital video data; the digital video data and the first digital audio data are combined into first digital program data having a specified timing.
The digital video data is the data source of the common digital television playing end playing pictures, and the first digital audio data is the data source of the common digital television playing end playing sounds. Therefore, in the application, the digital video data and the first digital audio data acquired by the digital video camera and the first digital audio collector are the same as the digital signal acquisition process in the common scheme, and the obtained data are the same. However, this process needs to be described herein, and the digital audio data therein is numbered as the first digital audio data, because although the present application obtains the digital video data and the first digital audio data as in the common scheme, the digital video data and the first digital audio data are not directly transmitted to the digital television playing end, and the number of the first digital audio data is used to distinguish from the subsequent second digital audio data. Wherein the first digital audio data is a representation of a digital signal of a content such as a speech dialogue.
And combining the digital video data and the first digital audio data into first digital program data with a specified time sequence, wherein the first digital program data cannot be directly transmitted to a digital television playing end, and if the first digital program data is directly transmitted to the digital television playing end, the application aims to solve the problem of scenario blank possibly occurring when a user watches a digital television program, and the purpose of improving the overall playing effect cannot be achieved. The appointed time sequence is a time axis of the playing program, is embodied in a visual interface and is a progress bar when the program is played, and the appointed time sequence is also an indication that the digital video data and the first digital audio data are correspondingly matched in time. The digital audio collector is, for example, a high-definition radio, a directional radio, etc.
As described in the above steps S4-S6, a preset second digital audio collector is adopted to perform audio collection processing on the broadcaster so as to obtain a second digital audio; wherein the second digital audio data is used for performing voice description on the program scene; performing timing adjustment on the second digital audio data to form second digital data having the specified timing; cutting off the first digital program data and the second digital program data according to a preset cutting-off method, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; wherein the first data segments and the second data segments are in one-to-one correspondence in time.
The second digital audio, although also acquired by the digital audio collector, is essentially different from the first digital audio data, i.e. the first digital audio data mainly reflects speech, and the second digital audio data is used for speech description of the program scene, i.e. the second digital audio data is acquired by a broadcaster describing the program scene (i.e. the episodes of the digital television program) in language, and is a deduction of the digital television program in another form, which of course discards video, so that the user can learn about the episodes of the digital television program only in an audio manner.
The second digital audio data is time-sequentially adjusted to form second digital program data having the specified time sequence, with the object of enabling the second digital program data to correspond in time to the first digital program data. For example, for a shot, the first digital program data is presented at a first point in time, and the second digital program data should likewise be presented at the first point in time with speech describing the episode of the a shot; whereas for a shot B of a preset length of time after a shot, the first digital program data occurs at a second point in time (the second point in time is later than the first point in time by the preset length of time), the second digital program data should also occur at the second point in time with speech describing the scenario of the shot B. This is the specific meaning of the specified timing.
And then data cutting processing is carried out, so that partial continuous data (which is embodied as continuous shots in video and continuous voices in audio) with tight plot association is divided into the same data segment, namely, the plot association degree between different cut data segments is lower. The specific data cutting method is a process of selecting cutting points, and the cutting points can be automatically cut off by a computer or manually and automatically cut off. And because the severing is only required once (meaning one pass on the time axis) here, a manual severing process may be employed. Since the first digital program data and the second digital program data have the specified time sequence, the plurality of first data segments and the plurality of second data segments obtained by cutting are in one-to-one correspondence in time, which indicates that the two digital program data are cut at the same cutting point. The data cutting process is performed so that two digital program data can be replaced when necessary. Because, if the viewer switches to the second digital program data directly as soon as he closes his eyes to deduct the digital television program by means of the speech description scenario, if he closes his eyes, it is just a speech set, it is likely that a sentence will be directly broken, but the use of the current speech description scenario directly does not improve the implementation of the scheme of the present application. Therefore, a data cut-off process is necessary.
Performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet as described in the above steps S7 to S9; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2; marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data, and judging whether a program signal acquisition request from a digital television playing end is received or not; if a program signal acquisition request from the digital television playing end is received, the default program data is sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point.
The ellipses in this application are omitted, which is a common manner in the mathematical field, for example, the first hybrid packet, the second hybrid packet, …, and the nth hybrid packet, wherein the third hybrid packet to the nth-1 hybrid packet are omitted. Each hybrid packet is made up of a first data segment and a corresponding second data segment. In this way, when the digital television signal data is transmitted, two groups of mutually related digital television signals can be transmitted together, so that the digital television playing end can select one data segment in the mixed data packet for playing according to the requirement. Namely, the first mixed data packet, the second mixed data packet, … and the nth mixed data packet are recorded as default program data, and whether a program signal acquisition request from a digital television playing end is received is judged; if a program signal acquisition request from the digital television playing end is received, the default program data is sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point. Since only one data segment can be played at the same time point, the situation that the data of the repeated plot is repeatedly played does not occur. In addition, with this playback mode, although switching between two sets of digital signal data occurs, the scenario process before and after switching does not change.
Of course, the purpose of the application can be achieved by adopting a complete mixed data packet for transmission at this time, but the situation of increasing the data transmission amount occurs, because only one group of digital television program data needs to be transmitted compared with the traditional scheme, and two groups of digital television program data need to be transmitted in the application. On the other hand, the present application can still control the data transmission amount (reduce the partial data transmission amount) on the basis of the purpose of the present application, and the specific implementation process and the following description will be given.
From the viewpoint of a viewer, the viewer can open eyes to watch a screen when watching a digital television program, and enjoys visual and auditory enjoyment, wherein the first digital program data is played, namely the first data segment in the mixed data packet is played. When the eyes are tired, the eyes can be closed, and only the hearing sense is used for sensing the evolution of the story line, and at the moment, the second digital data are played, namely the second data segment in the mixed data packet is played.
In one embodiment, after the step S8 of marking the first mixed data packet, the second mixed data packet, …, and the nth mixed data packet as default program data and determining whether a program signal acquisition request from a digital television playing end is received, the method includes:
S81, if a program signal acquisition request from a digital television playing end is received, inputting the plurality of first data segments into a preset first importance degree prediction model for processing so as to obtain a first importance degree sequence output by the first importance degree prediction model; the first importance degree sequence is composed of n first importance degree values, the n first importance degree values respectively correspond to n first data segments, and the first importance degree prediction model is trained based on a neural network model;
s82, inputting the plurality of second data segments into a preset second importance prediction model for processing to obtain a second importance sequence output by the second importance prediction model; the second importance degree sequence is composed of n second importance degree values, the n second importance degree values respectively correspond to n second data segments, and the second importance degree prediction model is trained based on a neural network model;
s83, selecting a designated first data segment from the plurality of first data segments according to a rule that the importance value is larger than a preset importance threshold, and selecting an important second data segment from the plurality of second data segments;
S84, acquiring a specified second data segment corresponding to the specified first data segment according to the corresponding relation between the first data segment and the second data segment;
s85, generating standby program data, sending the standby program data, and requiring a digital television playing end to only play one first data segment or one second data segment at any time point; wherein the spare program data is constituted by the plurality of first data pieces, the important second data pieces, and the specified second data pieces.
Thereby realizing the purposes of improving the playing effect and controlling the data transmission quantity. Wherein the control data transmission amount is realized by: since there are only all the first data segments and part of the second data segments in the spare program data, there are fewer parts of the second data segments than the aforementioned hybrid data packets. Instead of sending all the second data pieces, since the digital television program is after all mainly a television program, the video data is more important, and thus all the first data pieces (corresponding to video) are sent all the time, and the part of the second data pieces where the viewer can occur that the episode neglect is most likely to be played, which is the important second data piece, and thus the important second data piece needs to be sent. In addition, it should be noted that designating the second data segment is also necessary because designating the second data segment corresponds to designating the first data segment, and the importance of designating the first data segment is high, so that if the viewer accidentally ignores the scenario designating the first data segment, for example, the eyes are closed when the designated first data segment is played, the scenario supplementation can be realized by way of playing the designated second data segment.
The first importance degree prediction model is trained based on a neural network model, and the second importance degree prediction model is also trained based on a neural network model, and the neural network model can be any feasible model, such as a residual network model, a deep convolution neural network model, an countermeasure network model, a long-term and short-term memory network model, and the like. The reason why the first digital program data (i.e. the plurality of first data segments) can be predicted to be important is that the important first data segments are either long, or frequent in speech dialogue, or have high quality special effects, so these will be represented in the image sequence or audio of the video (i.e. can be represented in the first digital program data), whereas the neural network model is suitable for finding these necessarily existing potential laws, which of course requires a large amount of sample data to train. Similarly, for the important second data segment, the duration is longer, and the intonation and the speaking speed adopted by the broadcaster are different, so that the important second data segment is also reflected in the second digital data, and the important second data segment is also suitable for finding the importance degree by adopting the neural network model. The two importance prediction models are classification or prediction models in nature.
Further, if a request for acquiring a program signal from a digital television playing end is received, the step S81 of inputting the plurality of first data segments into a preset first importance prediction model for processing to obtain a first importance sequence output by the first importance prediction model includes:
s801, if a program signal acquisition request from a digital television broadcasting terminal is received, judging whether the received program signal acquisition request requests a comprehensive program signal or a brief program signal;
s802, if the received program signal acquisition request is a request brief program signal, inputting the plurality of first data segments into a preset first importance degree prediction model for processing so as to obtain a first importance degree sequence output by the first importance degree prediction model.
Thus, different program signals are sent according to different requirements of the digital television playing end. Specifically, if the digital television playing end sends a complete data request (which is default, so the mixed data packet is defined as default data), default program data is sent; if the request of the abbreviated program signal is sent by the digital television playing end, the standby program data with smaller data quantity is sent again.
Further, if a program signal acquisition request from a digital television playing end is received, the step S81 of inputting the plurality of first data segments into a preset first importance prediction model for processing to obtain a first importance sequence output by the first importance prediction model includes:
s71, acquiring a plurality of sample data collected in advance; wherein the sample data is composed of sample video data and sample audio data corresponding to the sample video data;
s72, respectively carrying out manual segmentation and labeling treatment on the plurality of sample data to obtain a plurality of sample data segment sequences; wherein, all sample data segments in each sample data segment sequence are marked with importance degrees;
s73, dividing the plurality of sample data segment sequences into a plurality of training data segment sequences and a plurality of verification data segment sequences according to a preset proportion;
s74, sequentially inputting the training data segment sequences into a preset neural network model for training to obtain a preliminary prediction model; in the training process, a back propagation algorithm is adopted to update parameters in each layer of network;
s75, verifying the preliminary prediction model by adopting the plurality of verification data segment sequences to obtain a verification result, and judging whether the verification result passes the verification;
And S76, if the verification result is that the verification is passed, the preliminary prediction model is recorded as a first importance degree prediction model.
Thereby obtaining a first importance prediction model capable of performing importance prediction work. The first importance prediction model is trained by adopting a supervised learning training mode, so that sample data is required to be manually segmented and labeled. The sample data may be ordinary digital television data, and in order to further expand the number of sample data, analog digital television data may be converted into digital television data by analog-to-digital conversion, and then added into the sample data. Because the number of digital television data and analog television data is sufficient, the problem of sample data starvation that may occur during certain model training processes does not occur in this application because any one program data may be used as one sample data. In the training and verification process, sample data from the same source are adopted, and the model obtained through training can pass verification, so that the reliability of the first importance degree prediction model can be ensured, and the reliability of a prediction result output by the first importance degree prediction model in formal use can be ensured.
In one embodiment, the program scenario has a plurality of pieces, and the step S6 of performing cutting processing on the first digital program data and the second digital program data according to a preset cutting method, so as to obtain a plurality of first data segments and a plurality of second data segments correspondingly includes:
s601, recording video clips in the same long lens as a first data segment, so as to obtain a plurality of first data segments corresponding to all the long lenses; the long shot refers to a video clip for continuously shooting the same scene without switching the shot, and the continuous shooting time of the long shot is larger than a preset time threshold;
s602, sequentially cutting off video clips except long shots according to a preset time length to obtain a plurality of first data segments;
s603, cutting the second digital data into a plurality of second data segments corresponding to all the first data segments according to the specified time sequence and all the first data segments obtained through cutting.
Thereby, a cut-off process is realized to obtain a plurality of first data pieces and a plurality of second data pieces. The cutting process may be performed manually or by a computer. The method and the device can adopt a high-speed cutting-off mode to achieve efficient data segment acquisition. Specifically, since the long shot is a special means in the video, it is generally considered that the video segment corresponding to the long shot is not separable or is more suitable as a whole, and thus, the long shot is directly split, so that a plurality of first data segments can be obtained. For other first data segments, since the first data segments are relatively less integrated, sequential cutting processing according to a preset time length is adopted to obtain a plurality of first data segments. Although this approach may result in some miscut, the implementation speed is fast, and the degree of miscut is limited due to the precondition of the first data segment corresponding to the long shot video segment. The second data segments are in one-to-one correspondence with the first data segments in time, so that according to the first data segments obtained by cutting, cutting processing can be directly performed to obtain a plurality of second data segments.
According to the digital television signal acquisition method based on the mixed data packet, continuous image acquisition processing is carried out on a preset program scene so as to obtain digital video data; obtaining first digital audio data corresponding to the digital video data; combining the first digital program data with a specified time sequence; obtaining a second digital audio data; performing timing adjustment to form second digital program data having the specified timing; cutting off respectively, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data; if a program signal acquisition request from the digital television playing end is received, the default program data is sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point, so that the problem of scenario blank possibly occurring when a user watches the digital television program is solved, and the overall playing effect is improved.
As shown in fig. 2, an embodiment of the present application provides a digital television signal acquisition device based on a hybrid data packet, including:
the digital video data acquisition unit 10 is configured to perform continuous image acquisition processing on a preset program scene by using a preset digital camera so as to obtain digital video data;
a first digital audio data acquisition unit 20, configured to perform audio acquisition processing on the program scene by using a preset first digital audio collector, so as to obtain first digital audio data corresponding to the digital video data;
a first digital program data combining unit 30 for combining the digital video data and the first digital audio data into first digital program data having a specified timing;
a second digital audio acquisition unit 40, configured to perform audio acquisition processing on the broadcaster by using a preset second digital audio acquisition unit, so as to obtain second digital audio data; wherein the second digital audio data is used for performing voice description on the program scene;
a second digital data acquisition unit 50 for performing timing adjustment on the second digital audio data to form second digital data having the specified timing;
A digital program data cutting unit 60, configured to perform cutting processing on the first digital program data and the second digital program data according to a preset cutting method, so as to obtain a plurality of first data segments and a plurality of second data segments correspondingly; wherein the first data segments and the second data segments are in one-to-one correspondence in time;
a hybrid packet generation unit 70, configured to perform hybrid packet generation processing to generate a first hybrid packet, a second hybrid packet, …, and an nth hybrid packet; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2;
a default program data marking unit 80, configured to mark the first hybrid data packet, the second hybrid data packet, …, and the nth hybrid data packet as default program data, and determine whether a program signal acquisition request from a digital television playing end is received;
and the default program data sending unit 90 is configured to send the default program data if a program signal acquisition request from the digital television playing end is received, and request the digital television playing end to only play the first data segment or the second data segment in the mixed data packet at any time point.
The operations performed by the units are respectively corresponding to the steps of the digital television signal acquisition method based on the hybrid data packet in the foregoing embodiment one by one, and are not described herein again.
The digital television signal acquisition device based on the mixed data packet performs continuous image acquisition processing on a preset program scene to obtain digital video data; obtaining first digital audio data corresponding to the digital video data; combining the first digital program data with a specified time sequence; obtaining a second digital audio data; performing timing adjustment to form second digital program data having the specified timing; cutting off respectively, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data; if a program signal acquisition request from the digital television playing end is received, the default program data is sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point, so that the problem of scenario blank possibly occurring when a user watches the digital television program is solved, and the overall playing effect is improved.
Referring to fig. 3, in an embodiment of the present invention, there is further provided a computer device, which may be a server, and the internal structure of which may be as shown in the drawing. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data used by the digital television signal acquisition method based on the mixed data packet. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a digital television signal acquisition method based on hybrid data packets.
The above processor executes the above digital television signal acquisition method based on the hybrid data packet, where the steps included in the method are respectively corresponding to the steps of executing the digital television signal acquisition method based on the hybrid data packet in the foregoing embodiment one by one, and are not described herein again.
It will be appreciated by persons skilled in the art that the structures shown in the drawings are only block diagrams of some of the structures that may be associated with the aspects of the present application and are not intended to limit the scope of the computer apparatus to which the aspects of the present application may be applied.
The computer equipment performs continuous image acquisition processing on a preset program scene to obtain digital video data; obtaining first digital audio data corresponding to the digital video data; combining the first digital program data with a specified time sequence; obtaining a second digital audio data; performing timing adjustment to form second digital program data having the specified timing; cutting off respectively, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data; if a program signal acquisition request from the digital television playing end is received, the default program data is sent, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point, so that the problem of scenario blank possibly occurring when a user watches the digital television program is solved, and the overall playing effect is improved.
An embodiment of the present application further provides a computer readable storage medium, on which a computer program is stored, where the computer program when executed by a processor implements a digital television signal acquisition method based on hybrid data packets, and the steps included in the method are respectively corresponding to the steps of executing the digital television signal acquisition method based on hybrid data packets in the foregoing embodiment one to one, which is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.

Claims (8)

1. The digital television signal acquisition method based on the mixed data packet is characterized by comprising the following steps of:
s1, adopting a preset digital camera to perform continuous image acquisition processing on a preset program scene so as to obtain digital video data;
s2, adopting a preset first digital audio collector to carry out audio collection processing on the program scene so as to obtain first digital audio data corresponding to the digital video data;
s3, combining the digital video data and the first digital audio data into first digital program data with a specified time sequence;
s4, adopting a preset second digital audio collector to carry out audio collection processing on the broadcaster so as to obtain second digital audio data; wherein the second digital audio data is used for performing voice description on the program scene;
s5, performing time sequence adjustment on the second digital audio data to form second digital data with the designated time sequence;
s6, cutting off the first digital program data and the second digital program data according to a preset cutting-off method, so as to correspondingly obtain a plurality of first data segments and a plurality of second data segments; wherein the first data segments and the second data segments are in one-to-one correspondence in time;
S7, performing mixed data packet generation processing to generate a first mixed data packet, a second mixed data packet, … and an nth mixed data packet; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2;
s8, marking the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data, and judging whether a program signal acquisition request from a digital television playing end is received or not;
and S9, if a program signal acquisition request from the digital television playing end is received, transmitting the default program data, and requiring the digital television playing end to only play the first data segment or the second data segment in the mixed data packet at any time point.
2. The method for acquiring digital television signals based on mixed data packets according to claim 1, wherein after the step S8 of recording the first mixed data packet, the second mixed data packet, … and the nth mixed data packet as default program data and determining whether a program signal acquisition request from a digital television playing end is received, the method comprises:
S81, if a program signal acquisition request from a digital television playing end is received, inputting the plurality of first data segments into a preset first importance degree prediction model for processing so as to obtain a first importance degree sequence output by the first importance degree prediction model; the first importance degree sequence is composed of n first importance degree values, the n first importance degree values respectively correspond to n first data segments, and the first importance degree prediction model is trained based on a neural network model;
s82, inputting the plurality of second data segments into a preset second importance prediction model for processing to obtain a second importance sequence output by the second importance prediction model; the second importance degree sequence is composed of n second importance degree values, the n second importance degree values respectively correspond to n second data segments, and the second importance degree prediction model is trained based on a neural network model;
s83, selecting a designated first data segment from the plurality of first data segments according to a rule that the importance value is larger than a preset importance threshold, and selecting an important second data segment from the plurality of second data segments;
S84, acquiring a specified second data segment corresponding to the specified first data segment according to the corresponding relation between the first data segment and the second data segment;
s85, generating standby program data, sending the standby program data, and requiring a digital television playing end to only play one first data segment or one second data segment at any time point; wherein the spare program data is constituted by the plurality of first data pieces, the important second data pieces, and the specified second data pieces.
3. The method for acquiring digital television signals based on mixed data packets according to claim 2, wherein the step S81 of inputting the plurality of first data segments into a preset first importance prediction model for processing if a program signal acquisition request from a digital television playing end is received, so as to obtain a first importance sequence output by the first importance prediction model comprises:
s801, if a program signal acquisition request from a digital television broadcasting terminal is received, judging whether the received program signal acquisition request requests a comprehensive program signal or a brief program signal;
s802, if the received program signal acquisition request is a request brief program signal, inputting the plurality of first data segments into a preset first importance degree prediction model for processing so as to obtain a first importance degree sequence output by the first importance degree prediction model.
4. The method for acquiring digital television signals based on mixed data packets according to claim 2, wherein, before step S81 of inputting the plurality of first data segments into a preset first importance prediction model for processing to obtain a first importance sequence output by the first importance prediction model, the method is characterized in that the method comprises:
s71, acquiring a plurality of sample data collected in advance; wherein the sample data is composed of sample video data and sample audio data corresponding to the sample video data;
s72, respectively carrying out manual segmentation and labeling treatment on the plurality of sample data to obtain a plurality of sample data segment sequences; wherein, all sample data segments in each sample data segment sequence are marked with importance degrees;
s73, dividing the plurality of sample data segment sequences into a plurality of training data segment sequences and a plurality of verification data segment sequences according to a preset proportion;
s74, sequentially inputting the training data segment sequences into a preset neural network model for training to obtain a preliminary prediction model; in the training process, a back propagation algorithm is adopted to update parameters in each layer of network;
S75, verifying the preliminary prediction model by adopting the plurality of verification data segment sequences to obtain a verification result, and judging whether the verification result passes the verification;
and S76, if the verification result is that the verification is passed, the preliminary prediction model is recorded as a first importance degree prediction model.
5. The method for acquiring digital television signals based on mixed data packets according to claim 1, wherein the program scenes have a plurality of, and the step S6 of cutting off the first digital program data and the second digital program data according to a preset cutting-off method, respectively, so as to obtain a plurality of first data segments and a plurality of second data segments correspondingly, includes:
s601, recording video clips in the same long lens as a first data segment, so as to obtain a plurality of first data segments corresponding to all the long lenses; the long shot refers to a video clip for continuously shooting the same scene without switching the shot, and the continuous shooting time of the long shot is larger than a preset time threshold;
s602, sequentially cutting off video clips except long shots according to a preset time length to obtain a plurality of first data segments;
S603, cutting the second digital data into a plurality of second data segments corresponding to all the first data segments according to the specified time sequence and all the first data segments obtained through cutting.
6. A digital television signal acquisition device based on a hybrid data packet, comprising:
the digital video data acquisition unit is used for adopting a preset digital camera to perform continuous image acquisition processing on a preset program scene so as to obtain digital video data;
the first digital audio data acquisition unit is used for carrying out audio acquisition processing on the program scene by adopting a preset first digital audio acquisition device so as to obtain first digital audio data corresponding to the digital video data;
a first digital program data combining unit configured to combine the digital video data and the first digital audio data into first digital program data having a specified timing;
the second digital audio data acquisition unit is used for carrying out audio acquisition processing on the broadcaster by adopting a preset second digital audio acquisition device so as to obtain second digital audio data; wherein the second digital audio data is used for performing voice description on the program scene;
A second digital data acquisition unit configured to perform timing adjustment on the second digital audio data to form second digital data having the specified timing;
a digital program data cutting unit, configured to perform cutting processing on the first digital program data and the second digital program data according to a preset cutting method, so as to obtain a plurality of first data segments and a plurality of second data segments correspondingly; wherein the first data segments and the second data segments are in one-to-one correspondence in time;
a hybrid data packet generation unit, configured to perform hybrid data packet generation processing to generate a first hybrid data packet, a second hybrid data packet, …, and an nth hybrid data packet; wherein the first hybrid packet is formed by a first data segment and a first second data segment, the second hybrid packet is formed by a second first data segment and a second data segment, …, and the nth hybrid packet is formed by an nth first data segment and an nth second data segment; n is an integer greater than 2;
a default program data marking unit, configured to mark the first hybrid data packet, the second hybrid data packet, …, and the nth hybrid data packet as default program data, and determine whether a program signal acquisition request from a digital television playing end is received;
The default program data sending unit is used for sending the default program data if a program signal acquisition request from the digital television playing end is received, and the digital television playing end is required to only play the first data segment or the second data segment in the mixed data packet at any time point.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
CN202210084917.9A 2022-01-25 2022-01-25 Digital television signal acquisition method and device based on mixed data packet Active CN114531557B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210084917.9A CN114531557B (en) 2022-01-25 2022-01-25 Digital television signal acquisition method and device based on mixed data packet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210084917.9A CN114531557B (en) 2022-01-25 2022-01-25 Digital television signal acquisition method and device based on mixed data packet

Publications (2)

Publication Number Publication Date
CN114531557A CN114531557A (en) 2022-05-24
CN114531557B true CN114531557B (en) 2024-03-29

Family

ID=81621437

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210084917.9A Active CN114531557B (en) 2022-01-25 2022-01-25 Digital television signal acquisition method and device based on mixed data packet

Country Status (1)

Country Link
CN (1) CN114531557B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1695137A (en) * 2002-10-11 2005-11-09 松下电器产业株式会社 A method and apparatus for delivering programme-associated data to generate relevant visual displays for audio contents
CN1842147A (en) * 2005-04-01 2006-10-04 晶发科技股份有限公司 Device and method for carrying out audio modification using program content information
WO2009127805A1 (en) * 2008-04-18 2009-10-22 De Montfort University Metadata enriched digital media
CN113630650A (en) * 2021-10-12 2021-11-09 深圳佳力拓科技有限公司 Digital television playing method and device based on audio and video switching and computer equipment

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8359399B2 (en) * 2008-10-16 2013-01-22 Echostar Technologies L.L.C. Method and device for delivering supplemental content associated with audio/visual content to a user
US10142585B2 (en) * 2015-04-28 2018-11-27 Rovi Guides, Inc. Methods and systems for synching supplemental audio content to video content
BR112022026060A2 (en) * 2020-06-22 2023-01-17 Audiomob Ltd ADD AUDIO CONTENT TO DIGITAL WORKS

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1695137A (en) * 2002-10-11 2005-11-09 松下电器产业株式会社 A method and apparatus for delivering programme-associated data to generate relevant visual displays for audio contents
CN1842147A (en) * 2005-04-01 2006-10-04 晶发科技股份有限公司 Device and method for carrying out audio modification using program content information
WO2009127805A1 (en) * 2008-04-18 2009-10-22 De Montfort University Metadata enriched digital media
CN113630650A (en) * 2021-10-12 2021-11-09 深圳佳力拓科技有限公司 Digital television playing method and device based on audio and video switching and computer equipment

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Rule-Embedded Network for Audio-Visual Voice Activity Detection in Live Musical Video Streams;Yuanbo Hou et al.;《ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)》;第4165-4169页 *
基于深度强化学习的视频自动描述研究;董文普;《中国优秀硕士学位论文全文库(信息科技辑)》(第8期);全文 *
数字视频在线语音讲解系统;李卫红;《价值工程》(第8期);第117-118页 *

Also Published As

Publication number Publication date
CN114531557A (en) 2022-05-24

Similar Documents

Publication Publication Date Title
CN107633719B (en) Anthropomorphic image artificial intelligence teaching system and method based on multi-language human-computer interaction
CN110971964A (en) Intelligent comment generation and playing method, device, equipment and storage medium
CN108259971A (en) Subtitle adding method, device, server and storage medium
CN106796496A (en) Display device and its operating method
US11533542B2 (en) Apparatus, systems and methods for provision of contextual content
CN108920128B (en) Operation method and system of presentation
CN110166651A (en) A kind of director method, device, terminal device and storage medium
CN111263227A (en) Multimedia playing method, device and storage medium
CN108766071A (en) A kind of method, apparatus, storage medium and the relevant device of content push and broadcasting
CN113052085A (en) Video clipping method, video clipping device, electronic equipment and storage medium
CN110769279B (en) Video processing method and device
CN109326154A (en) A method of human-computer interaction teaching is carried out by speech recognition engine
CN114531557B (en) Digital television signal acquisition method and device based on mixed data packet
CN110996021A (en) Director switching method, electronic device and computer readable storage medium
CN113703579A (en) Data processing method and device, electronic equipment and storage medium
CN110808075A (en) Intelligent recording and broadcasting method
CN109714603A (en) The method and device of multichannel audio-video frequency live streaming
CN110493609B (en) Live broadcast method, terminal and computer readable storage medium
CN106534964A (en) Speed adjusting method and device
CN113808593A (en) Voice interaction system, related method, device and equipment
CN114727119A (en) Live broadcast and microphone connection control method and device and storage medium
CN110853428A (en) Recording and broadcasting control method and system based on Internet of things
CN106973282B (en) Panoramic video immersion enhancement method and system
CN110111640A (en) It practises handwriting learning method, calligraphy practising pen and terminal device
CN115050083B (en) Mouth shape correcting model, training of model and application method of model

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