Disclosure of Invention
In view of the above problems, the present application provides a method and related apparatus for analyzing and editing emotions of viewers, so as to achieve the purposes of real-time emotion analysis and intelligent editing. The specific scheme is as follows:
a first aspect of the present application provides a method of audience emotion analysis clipping, the method comprising:
Acquiring a first video of a spectator area and a second video of a stage area in the recording process of target content, and simultaneously determining a target spectator to be clipped and a sub-mirror period thereof by carrying out emotion analysis on spectators in the first video;
And synchronously editing the first video and the second video according to the sub-mirror period of the target audience.
In a possible implementation, the determining, by performing emotion analysis on the audience in the first video, the target audience to be clipped and the sub-mirror period thereof includes:
analyzing and obtaining first emotion data of the first video, wherein the first emotion data comprises facial features and emotion scores of audiences at different times;
Clustering facial features corresponding to emotion scores meeting first emotion requirements in the first emotion data to obtain second emotion data of candidate audiences, wherein the second emotion data comprises the emotion scores meeting the first emotion requirements and corresponding time;
Determining a mirror separation period of the candidate audience according to the emotion score and time in the second emotion data;
And determining target audiences to be clipped in the candidate audiences, and obtaining the sub-mirror period of the target audiences.
In one possible implementation, the audience area includes a plurality of audience segments, each audience segment being deployed with a respective first machine location, the stage area being deployed with a respective second machine location;
The obtaining the first video of the audience area and the second video of the stage area in the recording process of the target content comprises the following steps:
Acquiring sub-videos of the affiliated audience partitions through the first machine, wherein a plurality of sub-videos corresponding to the plurality of audience partitions form the first video;
and acquiring the second video through the second phone position.
In one possible implementation, the analyzing obtains first mood data of the first video, including:
Extracting video frames at a specified time in the first video;
And carrying out face detection and emotion analysis on the video frames to obtain corresponding emotion analysis results, wherein the emotion analysis results comprise facial features and emotion scores of audiences in the appointed time.
In one possible implementation, the determining the sub-mirror period of the candidate audience according to the emotion score and time in the second emotion data includes:
Expanding and intersection merging are carried out on the time in the second emotion data, and an initial sub-mirror period is obtained;
Determining a first comprehensive emotion score of the initial sub-mirror period according to the emotion score corresponding to the initial sub-mirror period in the second emotion data;
And determining a recommendation index of the initial sub-mirror period based on the first comprehensive emotion score, and selecting a target sub-mirror period with the highest recommendation index from the initial sub-mirror periods.
In one possible implementation, the first emotion data further includes facial positions of the audience at different times;
the step of synchronously editing the first video and the second video according to the sub-mirror period of the target audience comprises the following steps:
determining a face position of the target audience within a sub-mirror period of the target audience, and editing a first sub-mirror video of the target audience from the first video according to the determined face position;
Determining a sub-mirror period in the second video corresponding to the sub-mirror period of the target audience by aligning the first video with the second video;
And editing a second sub-mirror video from the second video according to the determined sub-mirror period, and establishing a corresponding relation between the second sub-mirror video and the first sub-mirror video.
In one possible implementation, the method further comprises:
and calculating a second comprehensive emotion score of the target content according to the emotion scores meeting the second emotion requirements in the first emotion data.
A second aspect of the present application provides a spectator emotion analysis clipping apparatus, the apparatus comprising:
the video acquisition and analysis module is used for acquiring a first video of a spectator area and a second video of a stage area in the recording process of target content, and determining a target spectator to be clipped and a sub-mirror period thereof by carrying out emotion analysis on spectators in the first video;
and the sub-mirror clipping module is used for synchronously clipping the first video and the second video according to the sub-mirror period of the target audience.
A third aspect of the application provides a computer program product comprising computer readable instructions which, when run on an electronic device, cause the electronic device to implement the audience emotion analysis clipping method of the first aspect or any implementation of the first aspect.
A third aspect of the application provides an electronic device comprising at least one processor and a memory coupled to the processor, wherein:
The memory is used for storing a computer program;
The processor is configured to execute the computer program to enable the electronic device to implement the audience emotion analysis clipping method of the first aspect or any implementation manner of the first aspect.
A fourth aspect of the present application provides a computer storage medium carrying one or more computer programs which, when executed by an electronic device, enable the electronic device to implement the audience emotion analysis editing method of the first aspect or any implementation of the first aspect.
By means of the technical scheme, the audience emotion analysis editing method and related device comprise the steps of obtaining a first video of an audience area and a second video of a stage area in the recording process of target content, determining target audience to be edited and a sub-mirror period of the target audience through emotion analysis of the audience in the first video, and synchronously editing the first video and the second video according to the sub-mirror period of the target audience. The application can collect video pictures of audience areas and stage areas in real time in the program recording process, and determines target audience to be clipped and a mirror splitting period by carrying out emotion analysis on the audience, thereby synchronously clipping the audience pictures and the stage pictures and realizing seamless connection of instant capturing and highlight presentation.
Detailed Description
Embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. The terminology used in the description of the embodiments of the application herein is for the purpose of describing particular embodiments of the application only and is not intended to be limiting of the application.
Embodiments of the present application are described below with reference to the accompanying drawings. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.
The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and are merely illustrative of the manner in which embodiments of the application have been described in connection with the description of the objects having the same attributes. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to solve the problems that the prior art cannot meet the requirements of a program producer on real-time analysis and accurate editing of the emotion of a live audience, the program effect is quantized based on the emotion of the audience and the live interactivity is lacking, the embodiment of the application provides a editing method for analyzing the emotion of the audience. The audience emotion analysis editing method according to the embodiment of the present application is described in detail below with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for editing a mood analysis of a viewer according to an embodiment of the present application. As shown in fig. 1, a method for editing a mood analysis of a viewer according to an embodiment of the present application may include steps S101 to S102, which are described in detail below, respectively.
S101, acquiring a first video of an audience area and a second video of a stage area in the recording process of target content, and simultaneously determining a target audience to be clipped and a sub-mirror period thereof by carrying out emotion analysis on the audience in the first video.
In the embodiment of the application, the target content is the recorded content of the designated program, and the video (i.e. the first video) of the audience area and the video (i.e. the second video) of the stage area in the recording process of the target content can be respectively acquired by respectively arranging the machine positions of the audience area and the stage area and determining to start recording when receiving the start signal of the target content. Meanwhile, for the first video, determining target audience and corresponding sub-mirror time periods thereof according with emotion requirements through emotion analysis on audiences appearing in the first video.
In one possible implementation, multiple machine-oriented auditoriums may be used, with the captured image covering the audience area, ensuring that all viewers are captured. In contrast, in the audience emotion analysis editing method provided by the embodiment of the application, the audience area comprises a plurality of audience partitions, each audience partition is provided with a corresponding first machine position, and the stage area is provided with a corresponding second machine position. Accordingly, the step of "acquiring the first video of the audience area and the second video of the stage area during the recording of the target content" in step S101 may include the following steps:
The method comprises the steps of obtaining sub-videos of a affiliated audience partition through a first machine position, forming a first video by a plurality of sub-videos corresponding to the plurality of audience partitions, and obtaining a second video through a second machine position.
In the embodiment of the application, the audience area can be divided into a plurality of audience partitions, each audience partition is provided with a corresponding machine position (namely a first machine position), the first machine position can be a single camera, videos (namely sub videos) of the audience partition can be shot through the first machine position, and a plurality of sub videos corresponding to all the audience partitions are taken as the first video. In addition, a corresponding position (namely a second position) is arranged in the stage area, the second position can be a single camera, and a second video corresponding to the stage area can be shot through the second position.
For the first station or the second station, an SDI (SERIAL DIGITAL INTERFACE ) line may be used to connect the camera with a separate encoder (such as eradek VidiU Pro, NEWTEK TRICASTER MINI, etc.) supporting the SDI interface, where the encoder converts the video collected by the camera into an RTMP (Real-TIME MESSAGING Protocol) stream and pushes the stream to the streaming server. The audience emotion analysis editing method provided by the embodiment of the application can be applied to a video server, the video server can start corresponding processes according to the number of the first machine position and the second machine position, RTMP streams of different sub-videos and second videos are respectively pulled from a streaming media server, and the RTMP streams are respectively and locally stored and stored as video files in m3u8 format.
In one possible implementation, the target audience and its period of time of the sub-mirror are determined by performing emotional analysis of the time dimension and the audience dimension on the first video. Referring to fig. 2, fig. 2 is a schematic partial flow chart of a method for editing a mood analysis of a viewer according to an embodiment of the present application. As shown in fig. 2, the method for editing a mood analysis of a viewer according to the embodiment of the present application, in which "determining a target viewer to be edited and a period of splitting a mirror thereof by mood analysis of a viewer in a first video" in step S101, may include steps S201 to S204, which are described in detail below, respectively.
S201, analyzing and obtaining first emotion data of the first video, wherein the first emotion data comprises facial features and emotion scores of audiences at different times.
In the embodiment of the application, for the first video, the emotion of the audience in different video frames can be analyzed to obtain corresponding emotion data (namely, first emotion data), and the first emotion data comprises emotion analysis results of the audience at different times, wherein the emotion analysis results at least comprise facial features and emotion scores, because the different video frames correspond to different times.
It should be noted that, in the embodiment of the present application, the emotion score may represent the emotion category of the audience, for example, the emotion category of the audience may be classified into difficulty, nature and happiness, and different emotion score intervals may be set for different emotion categories, for example, the difficulty corresponding emotion score interval is [ -1, -0.5), the natural corresponding emotion score interval is [ -0.5, +0.5), and the happiness corresponding emotion score interval is [ +0.5, 1), for example, the larger the emotion score is, the higher the happiness is represented.
In one possible implementation, the first emotion data may be obtained by deploying AI models for face detection and emotion analysis. Referring to fig. 3, fig. 3 is a schematic flow chart of another part of a method for editing a mood analysis of a viewer according to an embodiment of the present application. As shown in fig. 3, the method for editing the emotion analysis of the audience provided by the embodiment of the present application, in which "analyzing and obtaining the first emotion data of the first video" in step S201, may include steps S301 to S302, and the steps are described in detail below, respectively.
S301, extracting video frames at a specified time in the first video.
In the embodiment of the application, when the first video is obtained, the first video can be subjected to video frame extraction according to a certain time sequence (for example, one frame is taken every second), so that the video frame under the appointed time is obtained.
S302, face detection and emotion analysis are carried out on the video frames to obtain corresponding emotion analysis results, wherein the emotion analysis results comprise facial features and emotion scores of audiences at appointed time.
In the embodiment of the application, for the extracted video frame, the face position of the audience in the video frame can be positioned through face detection, then the face characteristics are extracted, and further the emotion analysis is carried out on the face characteristics to obtain a corresponding emotion analysis result, wherein the emotion analysis result at least comprises the face characteristics and emotion scores of the audience at the appointed time (namely the time of the video frame). In practical application, the emotion analysis result of the video frame at the appointed time can be written into the json file in an additional mode.
It will be appreciated that if the audience area is divided into a plurality of audience segments, and the first video is composed of a plurality of sub-videos, video frame extraction, face detection and emotion analysis are performed for each sub-video, respectively, and accordingly, each audience segment has a corresponding json file, and emotion analysis results at different times in the corresponding audience segment are recorded in the json file.
S202, clustering facial features corresponding to the emotion scores meeting the first emotion requirements in the first emotion data to obtain second emotion data of the candidate audience, wherein the second emotion data comprises the emotion scores meeting the first emotion requirements and corresponding time.
In the embodiment of the application, when a target content termination signal is received, the end of target content recording is determined, and at this time, clustering can be performed on first emotion data, specifically, traversing the emotion scores in the first emotion data, determining the emotion scores meeting the first emotion requirement, taking the recorded content of comedy programs as an example of target content, determining the emotion scores which are greater than a score threshold (such as 0.7), further, recording the time, the facial features and the emotion scores corresponding to the emotion scores meeting the first emotion requirement in a list, further, clustering the facial features in the list, wherein each cluster obtained by clustering represents one audience (the audience is a candidate audience with the emotion score meeting the first emotion requirement) by using a DBSCAN (sensitivity-Based Spatial Clustering of Applications with Noise) algorithm, and the cluster data of each cluster is the emotion data (namely, second emotion data) of one candidate audience, wherein the cluster data of the candidate audience meets the first emotion requirement and the corresponding time.
S203, determining the mirror-splitting period of the candidate audience according to the emotion score and time in the second emotion data.
In the embodiment of the application, the recommendation index corresponding to the time of the second emotion data can be determined according to the emotion score, taking the recorded content of the comedy program as the target content as an example, the higher the emotion score is, the higher the recommendation index is, and the mirror-splitting period of the candidate audience is determined according to the time with the highest recommendation index.
In one possible implementation, the mirror periods may be obtained by means of time expansion and intersection merging, and one of them is selected as a candidate viewer with an emotion score. Referring to fig. 4, fig. 4 is a schematic flow chart of another part of a method for editing a mood analysis of a viewer according to an embodiment of the present application. As shown in fig. 4, a method for editing a mood analysis of a viewer according to an embodiment of the present application, in which step S203 "determining a sub-mirror period of a candidate viewer according to a mood score and time in second mood data" may include steps S401 to S403, which are described in detail below, respectively.
S401, expanding and intersection merging are carried out on the time in the second emotion data, and an initial sub-mirror period is obtained.
In the embodiment of the present application, the time in the second emotion data may be extended to a period of a certain duration, for example, the time t may be extended to a period of [ t-1, t+1], and if the extended periods have an intersection, the time t and the time t are combined, so as to obtain an initial sub-mirror period. For example, if the time in the second emotion data includes 3S, 5S, 10S, three slots [2S,4S ], [4S,6S ], [9S,11S ] are obtained after time-spreading, and since there is an intersection between slots [2S,4S ] and slots [4S,6S ], slots [2S,6S ] can be combined, whereby the initial split-mirror slot includes slots [2S,6S ] and slots [9S,11S ].
Of course, in practical application, to ensure the program effect, the duration of the time period of the split mirror needs to be ensured, for this purpose, the time period with the time length longer than the corresponding threshold value may be further screened from the initial time period of the split mirror, taking the initial time period of the split mirror with the time length longer than or equal to 5S as an example, the initial time period of the split mirror only keeps the time periods [2S,6S ].
S402, determining a first comprehensive emotion score of the initial mirror period according to the emotion score corresponding to the initial mirror period in the second emotion data.
In the embodiment of the application, after the initial sub-mirror period is obtained, the corresponding emotion score can be determined according to the time corresponding to the initial sub-mirror period in the second emotion data, so as to determine the comprehensive emotion score (i.e. the first comprehensive emotion score) of the initial sub-mirror period. For ease of understanding, continuing with the description of the initial period of time-division included in the period of time-division mirror [2S,6S ] as an example, where the corresponding time in the second emotion data includes 3S, 5S, the emotion score of the candidate audience at 3S (hereinafter referred to as emotion score 1) and the emotion score at 5S (hereinafter referred to as emotion score 2) are further determined from the second emotion data, and the first integrated emotion score of the period of time [2S,6S ] is calculated with emotion score 1 and emotion score 2, for example, the average value of emotion score 1 and emotion score 2 may be regarded as the first integrated emotion score of the period of time [2S,6S ].
S403, determining a recommendation index of the initial sub-mirror period based on the first comprehensive emotion score, and selecting a target sub-mirror period with the highest recommendation index from the initial sub-mirror periods.
In the embodiment of the present application, for each period in the initial period of the split mirror, the recommendation index may be determined according to the first integrated emotion score thereof, and the recorded content of the comedy program is taken as the target content for example, where the first integrated emotion score is positively related to the recommendation index, that is, the higher the first integrated emotion score of a certain period, the higher the recommendation index thereof. In this regard, the period with the highest recommendation index in the initial sub-mirror period may be directly selected as the target sub-mirror period, that is, the sub-mirror period to be clipped for the candidate audience.
S204, determining target audiences to be clipped in the candidate audiences, and obtaining the sub-mirror period of the target audiences.
In the embodiment of the application, for the candidate audience of the audience area, at least one audience can be determined as a target audience to be clipped. Taking recorded content of comedy programs as target content, target audience in candidate audiences can be determined according to the emotion scores corresponding to the second emotion data in the time division period, for example, the highest emotion score or average emotion score in the second emotion data in the time division period can be used as an emotion index, and at least one audience with the highest emotion index can be selected from the candidate audiences as the target audience. Further, after the target audience is determined, a mirror period of the target audience may be obtained. S102, synchronously editing the first video and the second video according to the sub-mirror period of the target audience.
In the embodiment of the application, the first video and the second video are synchronously clipped according to the time period of the split mirrors of the target audience, the picture of the target audience is clipped from the first video to serve as the split mirrors of the audience area, and the corresponding stage picture is clipped from the second video to serve as the split mirrors of the stage area.
In one possible implementation, the split-mirror video of the audience area may focus on the target audience while the stage view and the target audience's reactions to this are clipped. In this embodiment of the present application, the first emotion data further includes facial positions of the audience at different times. Referring to fig. 5, fig. 5 is a schematic flow chart of another part of a method for editing a mood analysis of a viewer according to an embodiment of the present application. As shown in fig. 5, in the method for editing emotion analysis of a viewer provided in the embodiment of the present application, in step S102, "synchronous editing is performed on the first video and the second video according to the mirror period of the target viewer", steps S501 to S503 may be included, and detailed descriptions of these steps are described below, respectively.
S501, determining a face position of the target audience within a mirror period thereof, and editing a first mirror video of the target audience from the first video with the determined face position.
According to the embodiment of the application, firstly, according to the time corresponding to the mirror separation period of the target audience in the first emotion data, the face position of the target audience in the mirror separation period can be determined, and then the mirror separation video (namely the first mirror separation video) of the target audience is clipped and obtained from the first video according to the determined face position.
S502, determining a sub-mirror period corresponding to the sub-mirror period of the target audience in the second video by aligning the first video with the second video.
In the embodiment of the application, the alignment can be performed by the acquisition time of the first video and the second video. In practical application, when the video files of the first video and the second video are stored, the time stamp of the beginning of writing is used as the video file name, so that the beginning sequence and time interval of writing of the first video and the second video are determined, and the time stamp is aligned.
Let the sub-mirror period of the target audience be a period [ t1, t2]. The time division period corresponding to the time period [ t1, t2] in the second video is also the time period [ t1, t2] if the time stamps of the first video and the second video are the same, the time division period corresponding to the time period [ t1, t2] in the second video is [ t1- Δt, t2- Δt ] if the first video is earlier than the second video and the interval between the time stamps of the beginning writing is Δt, and the time division period corresponding to the time period [ t1, t2] in the second video is [ t1+ [ Δt, t2+ [ Δt ].
S503, editing the second sub-mirror video from the second video according to the determined sub-mirror period, and establishing a corresponding relation between the second sub-mirror video and the first sub-mirror video.
In the embodiment of the application, after the sub-mirror period in the second video is determined, the sub-mirror video (namely the second sub-mirror video) of the stage area can be clipped and obtained from the second video in the sub-mirror period, and the corresponding relation between the second sub-mirror video and the first sub-mirror video is established.
In practical application, after editing, the front end can read at least one first sub-mirror video and a second sub-mirror video corresponding to the first sub-mirror video under different audience partitions, and a first comprehensive emotion score of a sub-mirror period corresponding to the first sub-mirror video. The front end can select at least one first sub-mirror video from the first sub-mirror videos, click and confirm to automatically move the selected first sub-mirror video and the second sub-mirror video corresponding to the selected first sub-mirror video to the specified folder, and the large screen reads the first sub-mirror video and the second sub-mirror video in the specified folder and then displays the first sub-mirror video and the second sub-mirror video on the large screen.
In one possible implementation, the program effect may be quantified for different content according to mood score. In this regard, the method for editing audience emotion analysis provided by the embodiment of the application further comprises the following steps:
and calculating a second comprehensive emotion score of the target content according to the emotion scores meeting the second emotion requirements in the first emotion data.
In the embodiment of the present application, for the first emotion data corresponding to the audience area, the emotion score in the first emotion data is traversed, the emotion score satisfying the second emotion requirement is determined, taking the recorded content of the comedy program as the target content as an example, if a certain emotion score falls into a refractory corresponding emotion score interval or a natural corresponding emotion score interval, the emotion score may be recorded as 0, if a certain emotion score falls into a happy corresponding emotion score interval, the emotion score is recorded, further, after traversing the emotion score in the first emotion data, the comprehensive emotion score (i.e. the second comprehensive emotion score) of the target content may be calculated according to the recorded emotion score, for example, the total score of the recorded emotion score may be calculated, and the ratio of the total score to the total facial features (i.e. the total number of audiences) contained in the first emotion data may be taken as the second comprehensive emotion score.
It will be appreciated that the foregoing is merely an example of a comprehensive emotion score of a comedy program, and in other scenarios, emotion scores falling in a refractory corresponding emotion score interval may be recorded as negative values, which is not limited by the embodiment of the present application.
Further, if the audience area is divided into a plurality of audience segments, after the second integrated emotion scores of the different audience segments are obtained in the above-described manner, the average of the second integrated emotion scores of all the audience segments may be taken as the final emotion score of the target content.
Through the description, the audience emotion analysis editing method provided by the embodiment of the application constructs a scheme integrating multi-machine-position real-time capturing, emotion intelligent analysis, accurate editing and dynamic scoring, realizes instant response and quantitative evaluation of the emotion of the audience on the scene of the program, enhances interaction experience between the audience and the program, provides objective basis for program optimization, and improves program production level and audience satisfaction.
The above describes a method for editing a mood analysis of a viewer according to an embodiment of the present application, and an apparatus for performing the method for editing a mood analysis of a viewer will be described below.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a device for analyzing and editing emotion of a viewer according to an embodiment of the present application. As shown in fig. 6, an apparatus for editing emotion analysis of a viewer according to an embodiment of the present application includes:
The video acquisition and analysis module 601 is configured to acquire a first video of an audience area and a second video of a stage area in a target content recording process, and determine a target audience to be clipped and a sub-mirror period thereof by performing emotion analysis on an audience in the first video;
and the sub-mirror clipping module 602 is configured to clip the first video and the second video synchronously according to the sub-mirror period of the target audience.
In a possible implementation, the video acquisition and analysis module 601 is configured to determine, by performing emotion analysis on the audience in the first video, a target audience to be clipped and a sub-mirror period thereof, specifically configured to:
The method comprises the steps of obtaining first emotion data of a first video through analysis, wherein the first emotion data comprise facial features and emotion scores of audiences under different time, clustering facial features corresponding to the emotion scores meeting first emotion requirements in the first emotion data to obtain second emotion data of candidate audiences, wherein the second emotion data comprise the emotion scores meeting the first emotion requirements and corresponding time, determining a sub-mirror period of the candidate audiences according to the emotion scores and the time in the second emotion data, determining target audiences to be clipped in the candidate audiences, and obtaining the sub-mirror period of the target audiences.
In one possible implementation, the audience area includes a plurality of audience segments, each audience segment being deployed with a respective first machine location, and the stage area being deployed with a respective second machine location;
The video acquisition and analysis module 601 is configured to acquire a first video of a audience area and a second video of a stage area during recording of target content, and is specifically configured to:
The method comprises the steps of obtaining sub-videos of a affiliated audience partition through a first machine position, forming a first video by a plurality of sub-videos corresponding to the plurality of audience partitions, and obtaining a second video through a second machine position.
In one possible implementation, the video acquisition and analysis module 601 for analyzing the first emotion data for obtaining the first video is specifically configured to:
and carrying out face detection and emotion analysis on the video frames to obtain corresponding emotion analysis results, wherein the emotion analysis results comprise facial features and emotion scores of audiences at the appointed time.
In one possible implementation, the score clip module 602 is configured to determine a score period of the candidate audience according to the emotion score and the time in the second emotion data, and is specifically configured to:
The method comprises the steps of expanding and intersecting time in second emotion data to obtain an initial mirror dividing period, determining a first comprehensive emotion score of the initial mirror dividing period according to emotion scores corresponding to the initial mirror dividing period in the second emotion data, determining a recommendation index of the initial mirror dividing period based on the first comprehensive emotion score, and selecting a target mirror dividing period with the highest recommendation index from the initial mirror dividing periods.
In one possible implementation, the first emotion data further includes facial positions of the audience at different times;
the sub-mirror clipping module 602 is configured to clip the first video and the second video synchronously according to the sub-mirror period of the target audience, and is specifically configured to:
The method comprises the steps of determining the face position of a target audience in a sub-mirror period of the target audience, editing a first sub-mirror video of the target audience from the first video according to the determined face position, determining the sub-mirror period corresponding to the sub-mirror period of the target audience in the second video by aligning the first video with the second video, editing a second sub-mirror video from the second video according to the determined sub-mirror period, and establishing the corresponding relation between the second sub-mirror video and the first sub-mirror video.
In one possible implementation, the video acquisition and analysis module 601 is further configured to:
and calculating a second comprehensive emotion score of the target content according to the emotion scores meeting the second emotion requirements in the first emotion data.
It should be noted that, the refinement function of each module in the embodiment of the present application may refer to the corresponding disclosure portion of the above embodiment of the audience emotion analysis clipping method, which is not described herein.
The embodiment of the application also provides electronic equipment. Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device in the embodiment of the present application may include, but is not limited to, a fixed terminal such as a mobile phone, a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), a desktop computer, and the like. The electronic device shown in fig. 7 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.
As shown in fig. 7, the electronic device may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 701, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage means 708 into a Random Access Memory (RAM) 703. In the state where the electronic device is powered on, various programs and data necessary for the operation of the electronic device are also stored in the RAM 703. The processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
In general, devices may be connected to I/O interface 705 including input devices 706 such as a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc., output devices 707 including a Liquid Crystal Display (LCD), speaker, vibrator, etc., storage devices 708 including a memory card, hard disk, etc., and communication devices 709. The communication means 709 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While fig. 7 shows an electronic device having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
Embodiments of the present application also provide a method for editing audience emotion analysis, which includes a computer program product including computer readable instructions, where the computer readable instructions, when executed on an electronic device, cause the electronic device to implement any of the methods for editing audience emotion analysis provided by the embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium, which carries one or more computer programs, and when the one or more computer programs are executed by the electronic device, the electronic device can realize any audience emotion analysis editing method provided by the embodiment of the application.
It should be further noted that the above-described apparatus embodiments are merely illustrative, and that the units described as separate units may or may not be physically separate, and that units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the drawings of the embodiment of the device provided by the application, the connection relation between the modules represents that the modules have communication connection, and can be specifically implemented as one or more communication buses or signal lines.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general purpose hardware, or of course by means of special purpose hardware including application specific integrated circuits, special purpose CPUs, special purpose memories, special purpose components, etc. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions can be varied, such as analog circuits, digital circuits, or dedicated circuits. But a software program implementation is a preferred embodiment for many more of the cases of the present application. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk or an optical disk of a computer, etc., comprising several instructions for causing a computer device (which may be a personal computer, a training device, a network device, etc.) to perform the method according to the embodiments of the present application.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via a wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a training device, a data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (Solid STATE DISK, SSD)), etc.