CN113613069A - Video generation method and electronic equipment - Google Patents
Video generation method and electronic equipment Download PDFInfo
- Publication number
- CN113613069A CN113613069A CN202110954700.4A CN202110954700A CN113613069A CN 113613069 A CN113613069 A CN 113613069A CN 202110954700 A CN202110954700 A CN 202110954700A CN 113613069 A CN113613069 A CN 113613069A
- Authority
- CN
- China
- Prior art keywords
- video
- question
- content
- answer
- target
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000000694 effects Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 20
- 230000004044 response Effects 0.000 claims description 12
- 230000003542 behavioural effect Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 abstract description 15
- 238000004519 manufacturing process Methods 0.000 description 15
- 230000009471 action Effects 0.000 description 13
- 230000006399 behavior Effects 0.000 description 9
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—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
-
- 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
- H04N21/44016—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 splicing one content stream with another content stream, e.g. for substituting a video clip
-
- 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
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application discloses a video generation method and electronic equipment, wherein the method comprises the following steps: acquiring question and answer information aiming at the playing content of the first video; generating a corresponding virtual target based on the acquired first characteristic of the first target in the first video; and generating a second video based on the question and answer information, the virtual target and the playing content of the first video so as to solve the question and answer information by utilizing the second video. The video generation method can timely answer the questions of the user in the process of playing the video, and the answering process is specifically implemented through the virtual target with the first characteristic, so that the user feels that the first target specially answers the questions for the user, the video which is recorded and played originally has a live broadcast effect, and the user satisfaction is improved.
Description
Technical Field
The present disclosure relates to the field of image processing, and in particular, to a video generation method and an electronic device.
Background
At present, in order to assist students in learning, a teacher needs to record a teaching video (recorded broadcast video) for the students to broadcast in some cases, so that the students can learn through the teaching video. However, the current teaching video is always played from beginning to end, and the teacher can not respond according to the reaction of the students as in the live video. For example, a teacher in a teaching video cannot answer the student's question. The student and the teaching video are split, and the student is not beneficial to learning.
Disclosure of Invention
The embodiment of the application aims to provide a video generation method and electronic equipment.
The embodiment of the application adopts the following technical scheme: a video generation method, comprising:
acquiring question and answer information aiming at the playing content of the first video;
generating a corresponding virtual target based on the acquired first characteristic of the first target in the first video;
and generating a second video based on the question and answer information, the virtual target and the playing content of the first video so as to solve the question and answer information by utilizing the second video.
Optionally, the generating a second video based on the question and answer information, the virtual target, and the playing content of the first video includes:
associating the virtual target with solution content for solving the question-answer information;
and merging the content of the virtual target and the playing content of the first video to generate the second video.
Optionally, the generating a second video based on the question and answer information, the virtual target, and the playing content of the first video further includes:
associating the virtual target with solution content for solving the question-answer information;
and replacing at least part of the content of the first target displayed in the first video with the content of the virtual target to generate the second video.
Optionally, the replacing the content of at least part of the first target displayed in the first video with the content of the virtual target includes:
segmenting the first video into a video background and the first target;
and merging the content of the virtual target and the video background based on the mutual position relation between the first target and the video background.
Optionally, the method further comprises:
under the condition that question answering information sent out aiming at the playing content of the first video is obtained, the playing of the first video is paused, and corresponding pause position information is generated;
and after the virtual target in the second video is used for completing answering to the question answering information, playing the second video based on the pause position information.
Optionally, the first feature includes at least one of: appearance, behavioral action or speech of the first target; correspondingly, the generating a corresponding virtual target based on the acquired first feature of the first target in the first video includes: the virtual target is generated based on the appearance, behavioral actions and/or speech of the first target.
Optionally, the method further comprises:
based on the first characteristic, the virtual target is moved in the second video according to a first moving track, and answering of the question answering information is implemented, so that the live broadcasting effect of the second video is improved.
Optionally, the method further includes generating solution content corresponding to the question-answer information, where the solution content includes:
generating answer content corresponding to the question and answer information based on historical data related to the question and answer information; alternatively, the first and second electrodes may be,
taking the question-answering information as the input of a response model, and performing semantic analysis on the content of the question-answering information through the response model; and generating the solution content based on the result of the semantic analysis.
Optionally, the method further comprises:
generating prompt information under the condition that the current question answering information cannot be answered;
sending the question and answer information which can not be answered to a server so as to obtain answer content corresponding to the question and answer information through the server;
and answering the question and answer information based on the acquired answer content at a preset time point in the second video.
An embodiment of the present application further provides an electronic device, including:
an acquisition module configured to: acquiring question and answer information aiming at the playing content of the first video;
a processing module configured to: generating a corresponding virtual target based on the acquired first characteristic of the first target in the first video;
and generating a second video based on the question and answer information, the virtual target and the playing content of the first video so as to solve the question and answer information by utilizing the second video.
The video generation method can timely answer the questions of the user in the process of playing the video, and the answering process is specifically implemented through the virtual target with the first characteristic, so that the user feels that the first target specially answers the questions for the user, the video which is recorded and played originally has a live broadcast effect, and the user satisfaction is improved.
Drawings
Fig. 1 is a flowchart of a video generation method according to an embodiment of the present application;
FIG. 2 is a flowchart of one embodiment of step S30 of FIG. 1 according to an embodiment of the present application;
FIG. 3 is a flowchart of an embodiment of step S340 in FIG. 2 according to an embodiment of the present application;
fig. 4 is a flowchart of a specific embodiment of a video generation method according to an embodiment of the present application;
FIG. 5 is a diagram illustrating an exemplary network teaching scenario according to an embodiment of the present application;
fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.
Description of the reference numerals
1-a first target; 2-video background; 3-virtual target
Detailed Description
Various aspects and features of the present application are described herein with reference to the drawings.
It will be understood that various modifications may be made to the embodiments of the present application. Accordingly, the foregoing description should not be construed as limiting, but merely as exemplifications of embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the application.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with a general description of the application given above and the detailed description of the embodiments given below, serve to explain the principles of the application.
These and other characteristics of the present application will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the attached drawings.
It should also be understood that, although the present application has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of application, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the application, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the application of unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the application.
The video generation method can be applied to electronic equipment, and can be used in a scene of network teaching or a scene of video production.
The method comprises the following steps: and acquiring question and answer information aiming at the playing content of the first video. The question-answer information may be information generated based on a question posed by the user for the playback content, so that the user desires to be able to obtain a corresponding answer. The question-answering information may be configured in the form of voice, text, and/or image. The electronic device may generate a corresponding virtual object 3 based on the acquired first feature of the first object 1 in the first video. The first object 1 has an association relationship with the first video, for example, in a scene of network teaching, the first object 1 may be an image of a teacher explaining the first video content, for example, the teacher explains the teaching content on a blackboard in the first video. Of course, the first object 1 may also be other content related to the first video, such as other related information. The first feature is a feature of the first object 1, such as an action behavior feature, a feature and/or a voice feature of the first object 1. And a virtual object 3 associated with the first object 1 can be generated based on the first feature, the feature of the virtual object 3 being the same as or similar to the first feature of the first object 1, e.g. the virtual object 3 may be a virtual image of a teacher. So that the question-answering information can be solved by the virtual object 3 instead of the first object 1. For the purpose of solution, the electronic device may generate the second video to solve the question and answer information using the second video based on the question and answer information, the virtual target 3, and the playing content of the first video. Specifically, the electronic device may associate the virtual object 3 with the answer content of the question-answer information, and combine the virtual video with the playing content of the first video, for example, combine the image of the virtual teacher with the content of the first video except for the first object 1, thereby obtaining the second video. The questions of the students can be answered through the playing of the second video, so that the originally recorded and played first video is converted into the second video with a live broadcast effect, and the user satisfaction is improved.
The video generation method of the present application is described in detail below with reference to the accompanying drawings, as shown in fig. 1 and with reference to fig. 5, the method includes the following steps:
s10, the question answering information of the playing content of the first video is acquired.
The first video may be a plurality of types of videos, for example, the type of the first video may be a teaching video, a communication video, a friend-making video, and the like. When watching the playing content of the first video, the user can ask his or her question for the playing content, including asking questions in the form of voice, text and/or image, etc., to form corresponding question and answer information, so that the electronic device is expected to answer the question and answer information.
The electronic device may obtain the question and answer information in various ways, for example, the question and answer information may be obtained through an input device, or the question and answer information may be obtained through a network or the like. In one embodiment, the electronic device can analyze and process the question and answer information immediately after acquiring the question and answer information. The method comprises the step of obtaining corresponding answer content according to the question and answer information.
And S20, generating a corresponding virtual target 3 based on the acquired first feature of the first target 1 in the first video.
The first feature of the first object 1 can characterize aspects of the first object 1. In the case where the first object 1 is a character, such as a teacher, the first feature may be an action behavior feature, a feature and/or a voice feature of the teacher. In the case where the first object 1 is a specific object, such as an application (e.g., an image creation tool), the first feature may be the appearance of the application, an action of generating a specific image or text, or the like.
The specific way for the electronic device to acquire the first characteristic may be to acquire the first characteristic when the first target 1 works, and perform digital processing on the acquired first characteristic or acquire the acquired first characteristic in a digital manner. In one embodiment, the first feature may be invoked directly to generate a virtual target 3 corresponding to the first target 1. In another embodiment, the first feature may be stored for subsequent invocation.
The generated virtual target 3 has the characteristic of the first feature, and the answer content corresponding to the question-answer information can be output through the virtual target 3. Since the virtual target 3 has the first feature, the virtual target 3 can perform output of the solution content with the action behavior of the first target 1. In the network teaching scenario, the first object 1 may be an image of a teacher, and the corresponding virtual object 3 may restore the action behavior characteristics, appearance characteristics and/or voice characteristics of the teacher to form a virtual character in the form of a teacher's model, and answer the question and answer information provided by the students.
S30, generating a second video based on the question and answer information, the virtual target 3 and the playing content of the first video, so as to solve the question and answer information by using the second video.
Specifically, after the electronic device acquires the question and answer information, the electronic device may acquire the answer content corresponding to the question and answer information, and the specific acquisition manner may be that the answer content is acquired in a preset database through an association relationship between the question and answer information and the answer content.
The generated virtual target 3 may be associated with the solution content so that the solution content may be output through the virtual target 3. In the scenario of web-based education described above, the virtual teacher may answer the student's question. The virtual teacher is associated with the answer content corresponding to the question-answer information, and then the virtual target 3 is combined with the playing content of the first video, for example, the virtual teacher is combined with the background of the first video to generate a second video. In the second video, the virtual teacher (virtual target 3) can answer the question and answer information provided by the student through voice and action, so that the student feels that the teacher answers the question of the student himself, and a live broadcast effect is formed.
And in a scenario where an application (e.g., an image production tool) is utilized to present or teach the production of an image to a user. The first object 1 may be an application and the virtual object 3 may be an object generated based on the appearance of the application and the characteristics of the image production action. The virtual target 3 may also be associated with the answer content corresponding to the question-answer information, for example, a virtual image production tool is combined with the playing background of the first video to generate a second video, in which the virtual image production tool can solve the question of the user in an image manner.
The video generation method can timely answer the questions of the user in the process of playing the video, and the answering process is specifically implemented through the virtual target 3 with the first characteristic, so that the user feels that the first target 1 specially answers the questions for the user, the video which is recorded and played originally has the live broadcast effect, and the user satisfaction is improved.
In an embodiment of the present application, the generating a second video based on the question and answer information, the virtual target 3, and the playing content of the first video, as shown in fig. 2, includes:
s310, associating the virtual target 3 with the solution content for solving the question-answer information.
The question-answering information has corresponding answering content, and the answering content can comprise image, text and/or audio expression modes.
The answering content can be pre-constructed according to the question and answer information, for example, the answering content can be prepared in advance for more common question and answer information and stored. The answering content can also be generated instantly, namely the corresponding answering content is generated instantly according to the specific content of the question and answer information formed by the current user asking the play content.
In this embodiment, the virtual target 3 is associated with the solution content, for example, an association relationship between the two is established, so that the associated solution content can be output through the virtual target 3. For example, the virtual target 3 is a virtual teacher, and after the virtual teacher is associated with the answer content corresponding to the student question and answer information, the virtual teacher may call the answer content at the same time and output the answer content by the behavior and sound of the virtual teacher.
S320, merging the content of the virtual target 3 and the playing content of the first video to generate the second video.
The playing content of the first video may be other content except the first target 1 in the first video, for example, teaching content in the background of the first video; the content of the specific target in the first video can also be content, such as corresponding image, text and the like on a blackboard in the first video.
The content of the virtual object 3 may be data capable of representing the virtual object 3, and the content of the virtual object 3 and the content of the first video are combined together. The virtual object 3 is thus added to the first video, forming a second video.
In one embodiment, the first target 1 does not appear in all or part of the first video, but only has the playing content, and at this time, the content of the virtual target 3 may be merged with the playing content of the first video, so that the generated second video has the virtual target 3 similar to the first target 1 to answer the question and answer information of the user.
With reference to fig. 5, for example, in the network teaching scene, the first video is a teaching video, the playing content of the first video is teaching content, and no teacher (first goal 1) may appear in all or part of the first video, but the student asks questions about the teaching content at this time, so as to form question and answer information. And generating a virtual teacher (virtual teacher) according to the first characteristic of the teacher, combining the virtual teacher with the teaching content in the teaching video, and generating a second video, so that the question and answer information of the students is answered by the virtual teacher in the second video. The students can feel that the teaching video is to independently answer the questions of the students in the live broadcasting process, the experience of the students in the teaching process is improved, and the satisfaction degree is increased.
In an embodiment of the present application, the generating a second video based on the question and answer information, the virtual target 3, and the playing content of the first video further includes:
s330, associating the virtual target 3 with the solution content for solving the question-answer information.
The question-answering information has corresponding answering content, and the answering content can comprise image, text and/or audio expression modes.
The answering content can be pre-constructed according to the question and answer information, for example, the answering content can be prepared in advance for more common question and answer information and stored. The answering content can also be generated instantly, namely the corresponding answering content is generated instantly according to the specific content of the question and answer information formed by the current user asking the play content.
The virtual target 3 is associated with the solution content, for example, an association relationship between the two is established, so that the associated solution content can be output through the virtual target 3. In different application scenarios, the virtual target 3 is associated with the solution content in different forms.
S340, replacing at least part of the content of the first target 1 displayed in the first video with the content of the virtual target 3, and generating the second video.
Specifically, the first video may have a first object 1, for example, in a scene of network teaching, the first video is a teaching video, the first object 1 is a teacher in the first video, and the first video also has other teaching contents. The teacher may teach the student a lesson through the teaching content in the first video.
The first object 1 appears in the whole or a part of the first video, and in the case of solving the question-answer information, the content of the first object 1 in the first video may be replaced with the content of the virtual object 3, and a second video may be generated so that the solved content is output through the virtual object 3 in the second video.
With the above specific embodiment, in the process of playing the first video, the student provides question and answer information for the played teaching content. According to the first characteristic of the teacher, a virtual teacher can be generated, and the content corresponding to the virtual teacher replaces the content of the original teacher in the first video, so that at least part of the content in the second video is formed with the content of the virtual teacher, and the virtual teacher solves the student questions to give solved content.
In an embodiment of the present application, the replacing at least part of the content of the first target 1 displayed in the first video with the content of the virtual target 3, as shown in fig. 3 and in conjunction with fig. 5, includes:
s3410, the first video is divided into a video background 2 and the first object 1.
Specifically, the first video has a video background 2 (background image) and a first object 1. For example, in a web-based tutoring scenario, the first object 1 may be a teacher in a first video, and the video background 2 may be a specific tutorial. As another example, in a scenario where an application (e.g., an image production tool) is utilized to present or teach image production to a user. The first object 1 may be the image production tool and the interpretation associated with the image production tool may be the video background 2.
In this embodiment, the first video is divided into the video background 2 and the first object 1. It may be convenient to process the first object 1 and/or the video background 2 by replacing the first object 1 with a virtual object 3 as mentioned above or by combining the virtual object 3 with the video background 2.
S3420, merging the content of the virtual object 3 and the video background 2 based on the mutual position relationship between the first object 1 and the video background 2.
The first object 1 and the video background 2 have a mutual position relationship, for example, the first object 1 is at the lower right of the video background 2, or at the middle position of the video background 2. When the content of the virtual object 3 is merged with the video background 2, the merging operation may be performed based on the mutual position relationship. So that the merged virtual object 3 is still located at the lower right of the video background 2 or at an intermediate position of the video background 2. This will make the user unaware that the first object 1 has been replaced, enabling "seamless replacement", further increasing the live effect of the second video.
In one embodiment of the present application, as shown in fig. 4, the method further comprises the steps of:
and S40, when the question and answer information sent out aiming at the playing content of the first video is acquired, pausing the playing of the first video and generating corresponding pause position information.
Specifically, the playing of the first video is paused under the condition that the question and answer information is acquired. So that the play content does not continue to increase. And the generated pause location information may be location information of the time point of the pause in the entire first video.
And by combining a specific network teaching scene, the students propose questions and answers when the first video is played, and corresponding question and answer information is generated. At the moment, the first video pauses the playing of the first video, so that a corresponding virtual teacher is generated, a second video is further generated, the question and answer information is answered by the virtual teacher in the second video, and meanwhile, the pause position information is generated according to the pause time point.
S50, after the virtual target 3 in the second video is used to complete the answering of the question answering information, playing the second video based on the pause position information.
Further, with reference to the above embodiment, after the virtual teacher in the second video answers the questions of the student, the teaching work needs to be continued. And playing the second video based on the pause position information, namely based on the pause time point, so that the second video is played continuously.
In one embodiment of the application, the first feature comprises at least one of: appearance, behavioral action or voice of the first target 1; correspondingly, the generating a corresponding virtual target 3 based on the acquired first feature of the first target 1 in the first video includes: the virtual target 3 is generated based on the appearance, behavioral actions and/or speech of the first target 1.
Specifically, in the scenario of web-based tutoring, the first object 1 may be a teacher tutoring in the first video, and the first feature of the teacher may include at least one of the following: appearance, behavioral action or speech of the first object 1. The virtual target 3 generated by this first feature is also one having at least one of the following features: appearance, behavioral action or speech of the first object 1. This makes the virtual object 3 appear to the student watching the video to be still a teacher and not to be a human change. When the virtual teacher answers the questions of the students, the virtual teacher can answer the questions based on the appearance, behavior and/or voice of the original teacher, and therefore the sense of reality of the video is increased.
In one embodiment of the present application, the method further comprises the steps of:
based on the first characteristic, the virtual target 3 is moved in the second video according to a first moving track, and answers to the question answering information are implemented, so that the live effect of the second video is increased.
By combining with a specific use scene for explanation, a teacher may move in the first video during the teaching course, so that the teaching vividness can be increased. In this example, the generated virtual teacher may also move according to the movement habits of the original teacher, including the movement habits in the field displayed in the first video.
The first movement trajectory may then be a trajectory of movements made by the teacher in the scene of the first video display. If the virtual teacher in the second video moves according to the first moving track according to the walking gesture of the teacher, the virtual teacher can answer the question and answer information in the moving process. Therefore, when the student watches the second video, the student can think that the virtual teacher vividly answers the question, the reality sense is increased, and the live broadcast effect of the second video is further increased.
In an embodiment of the present application, the method further includes generating solution content corresponding to the question-answer information, where the solution content includes:
generating answer content corresponding to the question and answer information based on historical data related to the question and answer information; alternatively, the first and second electrodes may be,
taking the question-answering information as the input of a response model, and performing semantic analysis on the content of the question-answering information through the response model; and generating the solution content based on the result of the semantic analysis.
Specifically, the answer content may be generated in advance based on the question-answer information, or may be generated directly. For a specific generation process, on the one hand, the question answering information can be generated according to historical data related to the question answering information. Question-and-answer information may be information that many different students ask the same or similar questions. For the question-answer information, there are already formed answer contents. The answer contents may be stored as a part of the history data, and if the same question and answer information is subsequently presented again by the student, that is, the same question and answer information is generated, the corresponding answer contents may be called based on the history data, that is, the answer contents corresponding to the same question and answer information are generated.
On the other hand, the current question-answering information may be subjected to semantic analysis to perform an immediate answer. The question-answering information can be specifically used as input of a response model, the response model can be a model constructed based on semantic analysis, and after training, semantic analysis can be performed on input data, so that the actual meaning of the input data is obtained. After the question and answer information is input into the response model, the response model carries out semantic analysis on the content of the question and answer information to obtain the meaning of the question and answer information, and then the electronic equipment generates answer content based on the result of the semantic analysis. Therefore, the question and answer information can be answered instantly, new questions of students can be answered, and the real and effective effect of answering the questions is improved.
In one embodiment of the present application, the method further comprises:
generating prompt information under the condition that the current question answering information cannot be answered;
sending the question and answer information which can not be answered to a server so as to obtain answer content corresponding to the question and answer information through the server;
and answering the question and answer information based on the acquired answer content at a preset time point in the second video.
In combination with the specific embodiment, in the network teaching process, students may present various questions, and for a few questions, accurate solution contents may not be provided according to the original solution scheme. At this time, the electronic device may generate a prompt message to prompt the user that the solution content, which will be given at a later preset point in time, cannot be given for a while.
The electronic equipment sends the question and answer information to the server, and the server can answer the question and answer information because of strong processing capacity and information storage capacity of the server. The solution content may then be transmitted to the electronic device.
After receiving the answering content, the electronic device can answer the question of the student at a preset time point in the second video, namely, the received answering content is used for answering the question and answer information, so that the student can be satisfied with the answer.
The present embodiment also provides an electronic device, as shown in fig. 6, including:
an acquisition module configured to: and acquiring question and answer information aiming at the playing content of the first video.
Specifically, the first video may be multiple types of videos, for example, the type of the first video may be a teaching video, a communication video, a friend-making video, or the like. When watching the playing content of the first video, the user can ask his or her question for the playing content, including asking questions in the form of voice, text and/or image, etc., to form corresponding question and answer information, so that the electronic device is expected to answer the question and answer information.
The obtaining module may obtain the question and answer information in various ways, for example, the question and answer information may be obtained through an input device, or the question and answer information may be obtained through a network or the like. In one embodiment, the electronic device may analyze and process the question and answer information immediately after the obtaining module obtains the question and answer information. The method comprises the step of obtaining corresponding answer content according to the question and answer information.
A processing module configured to: generating a corresponding virtual target 3 based on the acquired first feature of the first target 1 in the first video;
and generating a second video based on the question and answer information, the virtual target 3 and the playing content of the first video so as to solve the question and answer information by using the second video.
The first feature of the first object 1 can characterize aspects of the first object 1. In the case where the first object 1 is a character, such as a teacher, the first feature may be an action behavior feature, a feature and/or a voice feature of the teacher. In the case where the first object 1 is a specific object, such as an application (e.g., an image creation tool), the first feature may be the appearance of the application, an action of generating a specific image or text, or the like.
The specific way for the electronic device to acquire the first characteristic may be to acquire the first characteristic when the first target 1 works, and perform digital processing on the acquired first characteristic or acquire the acquired first characteristic in a digital manner. In one embodiment, the first feature may be invoked directly by the processing module to generate a virtual target 3 corresponding to the first target 1. In another embodiment, the processing module may store the first feature for subsequent invocation.
The virtual target 3 generated by the processing module has the characteristic of the first characteristic, and the answering content corresponding to the question answering information can be output through the virtual target 3. Since the virtual target 3 has the first feature, the virtual target 3 can perform output of the solution content with the action behavior of the first target 1. In the network teaching scenario, the first object 1 may be an image of a teacher, and the corresponding virtual object 3 may restore the action behavior characteristics, appearance characteristics and/or voice characteristics of the teacher to form a virtual character in the form of a teacher's model, and answer the question and answer information provided by the students.
The obtaining module may obtain the answer content corresponding to the question and answer information after obtaining the question and answer information, and the specific obtaining manner may be that the answer content is obtained in a preset database through an association relationship between the question and answer information and the answer content.
The virtual target 3 generated by the processing module may be associated with the solution content so that the solution content may be output through the virtual target 3. In the scenario of web-based education described above, the virtual teacher may answer the student's question. The processing module associates the virtual teacher with the answer content corresponding to the question-answer information, and then combines the virtual target 3 with the playing content of the first video, for example, combines the virtual teacher with the background of the first video to generate a second video. In the second video, the virtual teacher (virtual target 3) can answer the question and answer information provided by the student through voice and action, so that the student feels that the teacher answers the question of the student himself, and a live broadcast effect is formed.
And in a scenario where an application (e.g., an image production tool) is utilized to present or teach the production of an image to a user. The first object 1 may be an application and the virtual object 3 may be an object generated based on the appearance of the application and the characteristics of the image production action. The processing module may also associate the virtual target 3 with the answer content corresponding to the question-answer information, for example, combine a virtual image production tool with the playing background of the first video to generate a second video, in which the virtual image production tool can solve the question of the user in an image manner.
In one embodiment of the present application, the processing module is further configured to:
associating the virtual target 3 with the contents of the solution for solving the question-answer information;
and combining the content of the virtual target 3 with the playing content of the first video to generate the second video.
In one embodiment of the present application, the processing module is further configured to:
associating the virtual target 3 with the contents of the solution for solving the question-answer information;
and replacing at least part of the content of the first target 1 displayed in the first video with the content of the virtual target 3 to generate the second video.
In one embodiment of the present application, the processing module is further configured to:
segmenting the first video into a video background 2 and the first target 1;
and merging the content of the virtual target 3 and the video background 2 based on the mutual position relation between the first target 1 and the video background 2.
In one embodiment of the present application, the processing module is further configured to:
under the condition that question answering information sent out aiming at the playing content of the first video is obtained, the playing of the first video is paused, and corresponding pause position information is generated;
and after the virtual target 3 in the second video is used for completing the answering of the question answering information, playing the second video based on the pause position information.
In one embodiment of the application, the first feature comprises at least one of: appearance, behavioral action or voice of the first target 1; accordingly, the processing module is further configured to: the virtual target 3 is generated based on the appearance, behavioral actions and/or speech of the first target 1.
In one embodiment of the present application, the processing module is further configured to:
based on the first characteristic, the virtual target 3 is moved in the second video according to a first moving track, and answers to the question answering information are implemented, so that the live effect of the second video is increased.
In one embodiment of the present application, the electronic device further comprises a generation module configured to: generating answer content corresponding to the question-answer information, wherein the answer content comprises:
generating answer content corresponding to the question and answer information based on historical data related to the question and answer information; alternatively, the first and second electrodes may be,
taking the question-answering information as the input of a response model, and performing semantic analysis on the content of the question-answering information through the response model; and generating the solution content based on the result of the semantic analysis.
In one embodiment of the present application, the processing module is further configured to:
generating prompt information under the condition that the current question answering information cannot be answered;
sending the question and answer information which can not be answered to a server so as to obtain answer content corresponding to the question and answer information through the server;
and answering the question and answer information based on the acquired answer content at a preset time point in the second video.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A video generation method, comprising:
acquiring question and answer information aiming at the playing content of the first video;
generating a corresponding virtual target based on the acquired first characteristic of the first target in the first video;
and generating a second video based on the question and answer information, the virtual target and the playing content of the first video so as to solve the question and answer information by utilizing the second video.
2. The method of claim 1, wherein generating a second video based on the question-answering information, a virtual target, and the playing content of the first video comprises:
associating the virtual target with solution content for solving the question-answer information;
and merging the content of the virtual target and the playing content of the first video to generate the second video.
3. The method of claim 1, wherein generating a second video based on the question-answering information, a virtual target, and the playing content of the first video, further comprises:
associating the virtual target with solution content for solving the question-answer information;
and replacing at least part of the content of the first target displayed in the first video with the content of the virtual target to generate the second video.
4. The method of claim 3, the replacing the content of at least a portion of the first target displayed in the first video with the content of the virtual target, comprising:
segmenting the first video into a video background and the first target;
and merging the content of the virtual target and the video background based on the mutual position relation between the first target and the video background.
5. The method of claim 1, further comprising:
under the condition that question answering information sent out aiming at the playing content of the first video is obtained, the playing of the first video is paused, and corresponding pause position information is generated;
and after the virtual target in the second video is used for completing answering to the question answering information, playing the second video based on the pause position information.
6. The method of claim 1, the first characteristic comprising at least one of: appearance, behavioral action or speech of the first target; correspondingly, the generating a corresponding virtual target based on the acquired first feature of the first target in the first video includes: the virtual target is generated based on the appearance, behavioral actions and/or speech of the first target.
7. The method of claim 1, further comprising:
based on the first characteristic, the virtual target is moved in the second video according to a first moving track, and answering of the question answering information is implemented, so that the live broadcasting effect of the second video is improved.
8. The method according to claim 1, further comprising generating answer content corresponding to the question-answer information, wherein the answer content comprises:
generating answer content corresponding to the question and answer information based on historical data related to the question and answer information; alternatively, the first and second electrodes may be,
taking the question-answering information as the input of a response model, and performing semantic analysis on the content of the question-answering information through the response model; and generating the solution content based on the result of the semantic analysis.
9. The method of claim 1, further comprising:
generating prompt information under the condition that the current question answering information cannot be answered;
sending the question and answer information which can not be answered to a server so as to obtain answer content corresponding to the question and answer information through the server;
and answering the question and answer information based on the acquired answer content at a preset time point in the second video.
10. An electronic device, comprising:
an acquisition module configured to: acquiring question and answer information aiming at the playing content of the first video;
a processing module configured to: generating a corresponding virtual target based on the acquired first characteristic of the first target in the first video;
and generating a second video based on the question and answer information, the virtual target and the playing content of the first video so as to solve the question and answer information by utilizing the second video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110954700.4A CN113613069A (en) | 2021-08-19 | 2021-08-19 | Video generation method and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110954700.4A CN113613069A (en) | 2021-08-19 | 2021-08-19 | Video generation method and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113613069A true CN113613069A (en) | 2021-11-05 |
Family
ID=78341330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110954700.4A Pending CN113613069A (en) | 2021-08-19 | 2021-08-19 | Video generation method and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113613069A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071530A (en) * | 2006-05-12 | 2007-11-14 | 姜雪亭 | Computer classroom-simulating method |
| CN111290568A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Interaction method and device and computer equipment |
| CN112071138A (en) * | 2020-09-05 | 2020-12-11 | 胡振刚 | Companion processing method and device, and electronic device |
| CN113067953A (en) * | 2021-03-22 | 2021-07-02 | 平安科技（深圳）有限公司 | Customer service method, system, device, server and storage medium |
| CN113257061A (en) * | 2021-04-01 | 2021-08-13 | 作业帮教育科技（北京）有限公司 | Virtual teaching method, device, electronic equipment and computer readable medium |
-
2021
- 2021-08-19 CN CN202110954700.4A patent/CN113613069A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101071530A (en) * | 2006-05-12 | 2007-11-14 | 姜雪亭 | Computer classroom-simulating method |
| CN111290568A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Interaction method and device and computer equipment |
| CN112071138A (en) * | 2020-09-05 | 2020-12-11 | 胡振刚 | Companion processing method and device, and electronic device |
| CN113067953A (en) * | 2021-03-22 | 2021-07-02 | 平安科技（深圳）有限公司 | Customer service method, system, device, server and storage medium |
| CN113257061A (en) * | 2021-04-01 | 2021-08-13 | 作业帮教育科技（北京）有限公司 | Virtual teaching method, device, electronic equipment and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107633719B (en) | Anthropomorphic image artificial intelligence teaching system and method based on multi-language human-computer interaction | |
| CN109101879B (en) | Posture interaction system for VR virtual classroom teaching and implementation method | |
| US11848003B2 (en) | System for communication skills training using juxtaposition of recorded takes | |
| US10127831B2 (en) | Systems and methods for computerized interactive skill training | |
| Barreira et al. | MOW: Augmented Reality game to learn words in different languages: Case study: Learning English names of animals in elementary school | |
| CN107967830A (en) | Online teaching interaction method, device, equipment and storage medium | |
| CN111541947A (en) | Teaching video processing method, device and system | |
| Guo | The use of video recordings as an effective tool to improve presentation skills | |
| CN111445738B (en) | Online motion action tutoring method and system | |
| CN112887790A (en) | Method for fast interacting and playing video | |
| RomERo-Hall et al. | Using physiological measures to assess the effects of animated pedagogical Agents on multimedia instruction | |
| KR100994434B1 (en) | Bidirectional video player and service system | |
| CN113613069A (en) | Video generation method and electronic equipment | |
| CN111080497A (en) | Online programming learning client and server | |
| Nishchyk et al. | How elderly people experience videos in MOOCs | |
| Patel et al. | Virtual expert guided serious role-playing game for learning communication with autistic people | |
| Ramaha et al. | AN INTELLIGENT TUTORING SYSTEM TO MAINTAIN THE STUDENTS’MOTIVATION | |
| CN110853428A (en) | Recording and broadcasting control method and system based on Internet of things | |
| US20240119923A1 (en) | System for Communication Skills Training | |
| Cui et al. | E-Learning Tool to Enhance Technological Pedagogical Content Knowledge | |
| Ma et al. | Virtual tools for training: The spectrum of apps and virtual aids for learning gastrointestinal endoscopy | |
| Tiarsiwi et al. | An Investigation of Motivational Strategies Used by English Teachers in Teaching Efl in Secondary Islamic Schools in Tangerang | |
| Gandolfi et al. | Does digital immersion matter? An analysis of the role of 360 videos within digital experiences for teacher training | |
| Fadhla | EFL Students' Perceptions on stimulated-reflection (VSR) video as a learning strategy to increase speaking performance in Indonesia public university | |
| Starr | Comparing Various Staff Training Modalities Within Applied Behavior Analysis |
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 |