Video data acquisition method and device

Abstract

The present disclosure relates to the field of computer technology, and in particular to a method and device for acquiring video data. Among them, a method for acquiring video data includes: in the initial audio and video data, performing word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set, and the initial audio and video data includes the initial audio data and the initial video data; if a word segmentation subset in the word segmentation set is obtained, then a video clip set corresponding to each word segmentation in the word segmentation subset is obtained in the initial video data, and each word segmentation in the word segmentation subset does not meet the audio and video data playback conditions; blurring the face and mouth image corresponding to each video clip in the video clip set to obtain the target video data. The present disclosure can improve the quality of video data while improving the user experience.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method and device for acquiring video data. Background Art

[0002] With the development of science and technology, the media industry is developing more and more rapidly, and the audio and video resources created by users are becoming more and more abundant. However, not all the content played in the audio and video data created by users is healthy. In order to meet the requirements of dissemination on the Internet, it is necessary to block the unhealthy content played in the audio and video. However, when the terminal blocks the unhealthy content played in the audio and video, it only blocks the unhealthy audio data, and the unhealthy picture information still remains in the audio and video, which makes the video data obtained by the user have low quality, thereby affecting the user experience. Summary of the invention

[0003] The present disclosure provides a method and device for acquiring video data, so as to at least solve the problem of low quality of video data acquired in the related art. The technical solution of the present disclosure is as follows:

[0004] According to a first aspect of an embodiment of the present disclosure, a method for acquiring video data is provided, including:

[0005] In the initial audio and video data, performing word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set, wherein the initial audio and video data includes the initial audio data and the initial video data;

[0006] If a segmentation subset in the segmentation set is obtained, a set of video clips corresponding to each segmentation in the segmentation subset is obtained in the initial video data, and each segmentation in the segmentation subset does not meet the audio and video data playback condition;

[0007] The face and mouth images corresponding to each video clip in the video clip set are blurred to obtain target video data.

[0008] Optionally, if a segmentation subset in the segmentation set is obtained, obtaining a set of video clips corresponding to each segmentation in the segmentation subset in the initial video data includes:

[0009] If a segmentation subset in the segmentation set is obtained, issuing first prompt information for the segmentation subset;

[0010] If a first confirmation instruction for the first prompt information is obtained, a set of video segments corresponding to each word in the word segmentation subset is obtained in the initial video data.

[0011] Optionally, the blurring of the corresponding human face and mouth image in each video clip in the video clip set to obtain target video data includes:

[0012] Using an artificial intelligence recognition model, obtaining a face and mouth image corresponding to each video clip in the video clip set;

[0013] Sending second prompt information for the face and mouth images corresponding to the video clips;

[0014] If a second confirmation instruction for the second prompt information is obtained, blur processing is performed on the face and mouth images corresponding to each of the video clips to obtain target video data.

[0015] Optionally, the blurring of the face and mouth image corresponding to each video clip in the video clip set to obtain the target video data includes:

[0016] Obtaining a face and mouth image corresponding to any video clip in the video clip set;

[0017] Adding a mosaic sticker at the image position corresponding to the face and mouth image to obtain a target video clip;

[0018] Traversing the video clip set, adding the mosaic sticker to each video clip in the video clip set, to obtain a target video clip set;

[0019] Based on the target video segment set, target video data is obtained.

[0020] Optionally, adding a mosaic sticker at an image position corresponding to the face and mouth image to obtain a target video clip includes:

[0021] In the word segmentation subset, obtaining the word segmentation corresponding to the human face and mouth image;

[0022] Obtain the segmentation type corresponding to the segmentation;

[0023] Obtaining a mosaic sticker corresponding to the word segmentation type;

[0024] The mosaic sticker is added at the image position corresponding to the human face and mouth image.

[0025] Optionally, if a segmentation subset in the segmentation set is obtained, obtaining a set of video clips corresponding to each segmentation in the segmentation subset in the initial video data includes:

[0026] If a subset of the word segments in the word segmentation set is obtained, then a display time point corresponding to any word in the subset of the word segments is obtained;

[0027] Acquire a video segment corresponding to the display time point in the initial video data;

[0028] The word segmentation subset is traversed, and a set of video segments corresponding to each word segmentation in the word segmentation subset is obtained in the initial video data.

[0029] Optionally, after blurring the face and mouth images in each video clip in the video clip set to obtain target video data, the method further includes:

[0030] Performing conversion processing on the audio data corresponding to each word in the word segmentation subset to obtain target audio data;

[0031] Based on the target audio data and the target video data, target audio and video data are obtained.

[0032] According to a second aspect of an embodiment of the present disclosure, there is provided a video data acquisition device, including:

[0033] A word segmentation processing unit is configured to execute in the initial audio and video data, perform word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set, wherein the initial audio and video data includes the initial audio data and the initial video data;

[0034] a segment acquisition unit configured to acquire, if a segment subset in the segment set is acquired, a set of video segments corresponding to each segment in the segment subset in the initial video data, wherein each segment in the segment subset does not satisfy the audio and video data playback condition;

[0035] The target acquisition unit is configured to perform blur processing on the face and mouth image corresponding to each video clip in the video clip set to obtain target video data.

[0036] Optionally, the segment acquisition unit includes a subset acquisition subunit and a set acquisition subunit, and is configured to execute, if a segmentation subset in the segmentation set is acquired, when acquiring a video segment set corresponding to each segmentation in the segmentation subset in the initial video data:

[0037] The subset acquisition subunit is configured to issue first prompt information for the word segmentation subset if a word segmentation subset in the word segmentation set is acquired;

[0038] The set acquisition subunit is configured to acquire, in the initial video data, a set of video segments corresponding to each word in the word subset if a first confirmation instruction for the first prompt information is acquired.

[0039] Optionally, the target acquisition unit includes a model recognition subunit, an information prompting subunit and an image processing subunit, and is configured to perform blur processing on the face and mouth image corresponding to each video clip in the video clip set to obtain the target video data:

[0040] The model recognition subunit is configured to execute an artificial intelligence recognition model to obtain a human face and mouth image corresponding to each video clip in the video clip set;

[0041] The information prompting subunit is configured to issue second prompting information for the face and mouth images corresponding to each video clip;

[0042] The image processing subunit is configured to execute, if a second confirmation instruction for the second prompt information is obtained, blur the face and mouth images corresponding to each video clip to obtain target video data.

[0043] Optionally, the target acquisition unit further includes an image acquisition subunit, a sticker adding subunit, a set traversal subunit and a data acquisition subunit, which are configured to perform blur processing on the face and mouth images corresponding to each video clip in the video clip set to obtain the target video data:

[0044] The image acquisition subunit is configured to acquire a face and mouth image corresponding to any video clip in the video clip set;

[0045] The sticker adding subunit is configured to add a mosaic sticker at an image position corresponding to the face and mouth image to obtain a target video clip;

[0046] The set traversal subunit is configured to traverse the video segment set, add the mosaic sticker to each video segment in the video segment set, and obtain a target video segment set;

[0047] The data acquisition subunit is configured to obtain target video data based on the target video segment set.

[0048] Optionally, the sticker adding subunit is configured to add a mosaic sticker at an image position corresponding to the face and mouth image, and when obtaining a target video clip, is specifically configured to execute:

[0049] In the word segmentation subset, obtaining the word segmentation corresponding to the human face and mouth image;

[0050] Obtain the segmentation type corresponding to the segmentation;

[0051] Obtaining a mosaic sticker corresponding to the word segmentation type;

[0052] The mosaic sticker is added at the image position corresponding to the human face and mouth image.

[0053] Optionally, the segment acquisition unit further includes a time acquisition subunit, a video acquisition subunit and a subset traversal subunit, which are configured to execute, if a segmentation subset in the segmentation set is acquired, when acquiring a video segment set corresponding to each segmentation in the segmentation subset in the initial video data:

[0054] The time acquisition subunit is configured to execute, if a subset of the segmentation words in the segmentation set is acquired, then acquire a display time point corresponding to any segmentation word in the segmentation word subset;

[0055] The video acquisition subunit is configured to acquire a video segment corresponding to the display time point in the initial video data;

[0056] The subset traversal subunit is configured to traverse the word segmentation subset and obtain a set of video segments corresponding to each word in the word segmentation subset in the initial video data.

[0057] Optionally, the device further includes an audio and video acquisition unit configured to perform, after blurring the face and mouth images in each video segment in the video segment set to obtain target video data:

[0058] Performing conversion processing on the audio data corresponding to each word in the word segmentation subset to obtain target audio data;

[0059] Based on the target audio data and the target video data, target audio and video data are obtained.

[0060] According to a third aspect of an embodiment of the present disclosure, a terminal is provided, including:

[0061] at least one processor; and

[0062] a memory communicatively connected to the at least one processor; wherein,

[0063] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the methods described in the above aspect.

[0064] According to a fourth aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods described in the preceding aspect.

[0065] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, wherein the computer program implements any one of the methods described in the preceding aspects when executed by a processor.

[0066] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0067] In some or related embodiments, by performing word segmentation processing on the text information corresponding to the initial audio data in the initial audio and video data, a word segmentation set is obtained; if a word segmentation subset in the word segmentation set is obtained, a video segment set corresponding to each word segment in the word segmentation subset is obtained in the initial video data; and the face and mouth image corresponding to each video segment in the video segment set is fuzzy processed to obtain the target video data. Therefore, by fuzzy processing the initial video data corresponding to the initial audio data, the terminal can shield the video data of the word segmentation subset corresponding to the initial audio data, improve the quality of the obtained video data, and thus improve the user experience.

[0068] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0070] Figure 1 is a background schematic diagram of a method for acquiring video data according to an exemplary embodiment;

[0071] Figure 2 is a background architecture diagram of a method for acquiring video data according to an exemplary embodiment;

[0072] Figure 3 is a flow chart of a method for acquiring video data according to an exemplary embodiment;

[0073] Figure 4 is a flow chart of a method for acquiring video data according to an exemplary embodiment;

[0074] Figure 5 is a schematic diagram showing a toast window according to an exemplary embodiment;

[0075] Figure 6 is a flow chart of a method for acquiring video data according to an exemplary embodiment;

[0076] Figure 7is a schematic diagram showing an image position corresponding to a human face mouth image according to an exemplary embodiment;

[0077] Figure 8 is a schematic diagram of mosaic stickers corresponding to different word segmentation types according to an exemplary embodiment;

[0078] Fig. 9 is a block diagram of a video data acquisition device according to an exemplary embodiment;

[0079] Fig.10 is a block diagram of a video data acquisition device according to an exemplary embodiment;

[0080] Fig.11 is a block diagram of a video data acquisition device according to an exemplary embodiment;

[0081] Fig.12 is a block diagram of a video data acquisition device according to an exemplary embodiment;

[0082] Fig.13 is a block diagram of a video data acquisition device according to an exemplary embodiment;

[0083] Fig.14 is a block diagram of a video data acquisition device according to an exemplary embodiment;

[0084] Fig.15 It is a block diagram of a terminal according to an exemplary embodiment. DETAILED DESCRIPTION

[0085] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0086] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0087] With the development of science and technology, terminal technology has become increasingly mature, improving the convenience of users' production and life. In terminal application scenarios, when the terminal obtains video data created by users, the terminal can block unhealthy content in the video.

[0088] According to some embodiments, Figure 1 FIG. 1 is a background diagram of a method for acquiring video data according to an exemplary embodiment. Figure 1 As shown, when the user needs to process the created audio and video, the user can click on the video processing application of the terminal. When the terminal detects that the user clicks on the video processing application, the terminal can display the video processing interface on the display screen. The user can upload the created audio and video data to the terminal through the video processing interface. When the terminal obtains the audio and video data created by the user, the terminal can obtain the audio data corresponding to the audio and video data. Furthermore, the terminal can perform voice recognition on the obtained audio data and shield the identified unhealthy audio data. For example, the terminal can use a "beep" sound to silence and shield unhealthy audio data.

[0089] In some embodiments, the terminal can only block the identified unhealthy audio data, but unhealthy image information still remains in the video, such as the mouth shape information of the characters in the unhealthy content. In this case, even if the terminal blocks the identified unhealthy audio data, the video viewers can still obtain the unhealthy content from the remaining image information, so that the purpose of blocking the unhealthy content cannot be achieved, resulting in low quality of the video data obtained by the user, which in turn affects the user experience.

[0090] According to some embodiments, Figure 2 FIG. 1 is a schematic diagram of a background structure of a video acquisition method according to an exemplary embodiment. Figure 2 As shown, the terminal 110 is provided with a video processing application. When the terminal 110 obtains the audio and video data created by the user through the video processing application, the terminal 110 can store the shielded audio and video data to the server 130 through the network 120. When the user needs to watch the shielded audio and video data, the terminal can obtain and play the shielded audio and video data stored in the server 130.

[0091] It is easy to understand that the terminal includes but is not limited to: wearable devices, handheld devices, personal computers, tablet computers, vehicle-mounted devices, smart phones, computing devices or other processing devices connected to wireless modems, etc. In different networks, terminal devices can be called different names, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), terminal equipment in the fifth generation mobile communication technology (5th generation mobile networks, 5G) network or future evolution network, etc. The terminal can be installed with an operating system, which refers to an operating system that can run in the terminal, a program that manages and controls terminal hardware and terminal applications, and is an indispensable system application in the terminal. The operating system includes but is not limited to Android system, IOS system, Windows phone (WP) system and Ubuntu mobile version operating system, etc.

[0092] According to some embodiments, the terminal 110 may be connected to the server 130 via a network 120. The network 120 is used to provide a communication link between the terminal 110 and the server 130. The network 120 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc. It should be understood that Figure 2 The number of terminals 110, networks 120, and servers 130 is only illustrative. Any number of terminals, networks, and servers may be provided according to actual needs. For example, the server 130 may be a server cluster composed of multiple servers. The user may use the terminal 110 to interact with the server 130 through the network 120 to view the shielded audio and video data.

[0093] Figure 3 FIG. 1 is a flow chart of a method for acquiring video data according to an exemplary embodiment. Figure 3 As shown, the video data acquisition method can be applied to multimedia scenarios, for example. The method can be implemented by relying on a computer program and can be run on a device including the video data acquisition method, and includes the following steps:

[0094] In step S11, in the initial audio and video data, the text information corresponding to the initial audio data is segmented to obtain a segmentation set;

[0095] According to some embodiments, the initial audio and video data refers to the unprocessed audio and video data created by the user. The initial audio and video data includes initial audio data and initial video data. The initial audio and video data does not specifically refer to a fixed audio and video data. For example, when the creating user changes, the initial audio and video data will also change. When the content of the initial audio and video data changes, the initial audio and video data will also change.

[0096] In some embodiments, the initial audio data refers to the audio data corresponding to the initial audio and video data. The initial audio data does not specifically refer to a fixed audio data. For example, when the initial audio and video data changes, the initial audio data will also change. When the authoring user changes, the initial audio data will also change.

[0097] In some embodiments, the initial video data refers to the video data corresponding to the initial audio and video data. The initial video data does not specifically refer to a fixed video data. For example, when the initial audio and video data changes, the initial video data will also change. When the authoring user changes, the initial video data will also change.

[0098] According to some embodiments, the text information refers to the text information obtained after the terminal performs voice recognition on the initial audio data corresponding to the initial audio and video data when the terminal obtains the initial audio data. The text information does not specifically refer to a fixed text information. For example, when the initial audio data changes, the text information will also change.

[0099] According to some embodiments, word segmentation refers to the process of recombining continuous text information into multiple word segments according to certain specifications. Word segmentation methods include but are not limited to string matching-based word segmentation, understanding-based word segmentation, and statistics-based word segmentation. Among them, string matching-based word segmentation matches the text information to be analyzed with the entries in the machine dictionary according to a certain strategy. Understanding-based word segmentation uses computers to simulate people's understanding of sentences, thereby achieving the effect of recognizing words. Statistics-based word segmentation uses statistical machine learning models to learn the rules of word segmentation, thereby achieving segmentation of unknown text information.

[0100] In some embodiments, the word segmentation set refers to the set of all word segmentations obtained when the terminal performs word segmentation processing on the text information corresponding to the initial audio data. The word segmentation set does not specifically refer to a fixed set. For example, when the text information changes, the word segmentation set will also change. When the word segmentation processing method changes, the word segmentation set will also change.

[0101] It is easy to understand that when the user needs to process the initial audio and video data created, the terminal can obtain the initial audio and video data. When the terminal obtains the initial audio and video data, the terminal can obtain the initial audio data corresponding to the initial audio and video data. When the terminal obtains the initial audio data, the terminal can perform voice recognition on the initial audio data to obtain text information corresponding to the initial audio data. When the terminal obtains the text information corresponding to the initial audio data, the terminal can perform word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set.

[0102] In step S12, if a subset of the word segments in the word segmentation set is obtained, a set of video clips corresponding to each word in the subset of the word segmentation is obtained in the initial video data;

[0103] According to some embodiments, a word segmentation subset refers to a set of all word segments in a word segmentation set that do not meet the audio and video data playback conditions. The word segmentation subset does not specifically refer to a fixed subset. For example, when the word segmentation set changes, the word segmentation subset will also change. When the audio and video data playback conditions change, the word segmentation subset will also change.

[0104] In some embodiments, the audio and video data playback condition refers to the condition that needs to be met when the audio and video data meets the requirements for dissemination on the Internet. The audio and video data playback condition does not specifically refer to a fixed condition. When the terminal obtains a condition modification instruction for the audio and video data playback condition, the audio and video data playback condition will change accordingly. The audio and video data playback condition includes but is not limited to the absence of uncivilized language, sensitive words, etc.

[0105] In some embodiments, the audio and video data playback condition may also be in the form of a word library. For example, the audio and video data playback condition may be an uncivilized word library and a sensitive word library. When the terminal detects that any word in the word set is a word in the uncivilized word library and the sensitive word library, the terminal may put the word into the word subset.

[0106] In some embodiments, the video clip set refers to a set of video clips corresponding to each word segmentation in the word segmentation subset. The video clip set does not specifically refer to a fixed set. For example, when the number of word segments in the word segmentation subset changes, the video clip set will also change. When the content of the word segmentation in the word segmentation subset changes, the video clip set will also change.

[0107] It is easy to understand that when the terminal obtains the word segmentation set, the terminal can obtain a word segmentation subset in the word segmentation set that does not meet the audio and video data playback conditions. When the terminal obtains the word segmentation subset, the terminal can obtain a video clip set corresponding to each word in the word segmentation subset in the initial video data.

[0108] In step S13, blur processing is performed on the face and mouth images corresponding to each video clip in the video clip set to obtain target video data.

[0109] According to some embodiments, the face and mouth image refers to an image when the terminal obtains a video clip corresponding to the word segmentation and detects the face and mouth in the image corresponding to the video clip through face recognition. The face and mouth image does not specifically refer to a fixed image. For example, when the character in the video clip changes, the face and mouth image will also change. When the word segmentation changes, the face and mouth image will also change.

[0110] In some embodiments, blur processing refers to the process of processing an image so that the image is unrecognizable. The blur processing does not specifically refer to a fixed blur processing. The blur processing methods include but are not limited to Gaussian blur images, salt and pepper blur images, motion blur images, mosaics, adding mosaic stickers, etc. When the terminal receives a method modification instruction for the blur processing method, the blur processing method will change accordingly.

[0111] According to some embodiments, the target video data refers to the video data that satisfies the audio and video data playback conditions obtained after the terminal processes the initial video data. The target video data does not specifically refer to a fixed data. For example, when the initial video data changes, the target video data will also change. When the audio and video data playback conditions change, the target video data will also change.

[0112] It is easy to understand that when the terminal obtains a set of video clips corresponding to each word in the word segmentation subset, the terminal can obtain the face and mouth images corresponding to each video clip in the video clip set. When the terminal obtains the face and mouth images, the terminal can blur the face and mouth images to obtain target video data that meets the audio and video data playback conditions.

[0113] In some or related embodiments, by performing word segmentation processing on the text information corresponding to the initial audio data in the initial audio and video data, a word segmentation set is obtained; if a word segmentation subset in the word segmentation set is obtained, a video segment set corresponding to each word segment in the word segmentation subset is obtained in the initial video data; and the face and mouth image corresponding to each video segment in the video segment set is fuzzy processed to obtain the target video data. Therefore, by fuzzy processing the initial video data corresponding to the initial audio data, the terminal can shield the video data of the word segmentation subset corresponding to the initial audio data, improve the quality of the obtained video data, and thus improve the user experience.

[0114] Figure 4 A flowchart of a method for acquiring video data is shown according to an exemplary embodiment. Figure 4As shown, the video data acquisition method can be applied to multimedia scenarios, for example. The method can be implemented by relying on a computer program and can be run on a device including the video data acquisition method. The video data acquisition method includes the following steps:

[0115] In step S21, in the initial audio and video data, the text information corresponding to the initial audio data is segmented to obtain a segmentation set;

[0116] The specific process is as described above and will not be repeated here.

[0117] According to some embodiments, when the user needs to process the created initial audio and video data, the terminal can obtain the initial audio and video data. The initial audio and video data obtained by the terminal includes but is not limited to obtaining pre-created audio and video data, obtaining in real time during a delayed live video broadcast, etc. For example, the terminal can obtain 30 minutes of pre-created initial audio and video data. The terminal can also obtain the user's initial audio and video data in real time during a live video broadcast with a 5-minute delay.

[0118] In some embodiments, the method for the terminal to perform speech recognition on the initial audio data includes but is not limited to a random model method, a method using a neural network, a probabilistic grammatical analysis method, etc. Among them, when the random model method is adopted, the steps of extracting features, training templates, classifying templates and judging templates are adopted to recognize the speech. When the neural network method is adopted, the audio data is feature extracted, and CTC (Connectionist Temporal Classification) is used to combine characters and audio data, and convolutional neural networks (deep convolutional neural networks, CNN) are used to process images and extract main features through maximum pooling, and a defined CTC loss function is added for training. When the probabilistic grammatical analysis method is adopted, knowledge at different levels is solved by using knowledge at the corresponding level.

[0119] For example, when the terminal obtains the pre-created 30 minutes of initial audio and video data, the terminal can use the neural network method to perform speech recognition on the 30 minutes of initial audio and video data, thereby obtaining text information corresponding to the 30 minutes of initial audio data. When the terminal obtains the user's initial audio and video data in real time during a live video broadcast with a 5-minute delay, the terminal can perform real-time probabilistic grammar analysis on the initial audio and video data obtained in real time, thereby obtaining text information corresponding to the initial audio and video data in real time.

[0120] It is easy to understand that when the user needs to process the initial audio and video data created, the terminal can obtain the initial audio and video data. When the terminal obtains the initial audio and video data, the terminal can obtain the initial audio data corresponding to the initial audio and video data. When the terminal obtains the initial audio data, the terminal can perform voice recognition on the initial audio data to obtain text information corresponding to the initial audio data. When the terminal obtains the text information corresponding to the initial audio data, the terminal can perform word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set.

[0121] In step S22, if a word segmentation subset in the word segmentation set is obtained, a first prompt information for the word segmentation subset is issued;

[0122] The specific process is as described above and will not be repeated here.

[0123] According to some embodiments, the first prompt information refers to the information sent by the terminal when the terminal obtains a subset of word segments in a word segmentation set and prompts the user when a word segmentation that does not meet the audio and video data playback conditions is detected. The first prompt information does not specifically refer to a fixed information. The first prompt information includes but is not limited to pop-up prompt information, voice prompt information, etc. The display time of the first prompt information includes but is not limited to permanent display and preset time display. When the terminal obtains an information modification instruction for the first prompt information, the first prompt information will also change accordingly. For example, when the terminal obtains a subset of word segments in a word segmentation set, the terminal can pop up a toast window and stop displaying it 5 seconds after the pop-up, such as Figure 5 Alternatively, when the terminal obtains a word subset in the word set, the terminal may send a voice message of "It is detected that the current video contains uncivilized words or sensitive words, do you need to block it?"

[0124] It is easy to understand that when the terminal obtains the word segmentation set, the terminal can obtain the word segmentation subset in the word segmentation set that does not meet the audio and video data playback condition. When the terminal obtains the word segmentation subset in the word segmentation set, the terminal can issue the first prompt information for the word segmentation subset.

[0125] In step S23, if a first confirmation instruction for the first prompt information is obtained, a set of video segments corresponding to each segmentation in the segmentation subset is obtained in the initial video data;

[0126] The specific process is as described above and will not be repeated here.

[0127] According to some embodiments, the first confirmation instruction refers to an instruction issued when the user obtains the first prompt information issued by the terminal and selects the video clip set corresponding to the word segmentation subset to be shielded. The first confirmation instruction does not specifically refer to a fixed confirmation instruction. The first confirmation instruction includes but is not limited to a click confirmation instruction, a voice confirmation instruction, and the like. When the terminal obtains a modification instruction for the first confirmation instruction, the first confirmation instruction will also change accordingly. For example, when the user clicks the "yes" button in the toast window, the terminal can obtain the first confirmation instruction for the first prompt information. Alternatively, when the user says the voice message of "need", the terminal can also obtain the first confirmation instruction for the first prompt information.

[0128] It is easy to understand that when the terminal obtains the first prompt information for the word segmentation subset, the user can issue a first confirmation instruction for the first prompt information based on the first prompt information. When the terminal obtains the first confirmation instruction for the first prompt information, the terminal can obtain a set of video clips corresponding to each word in the word segmentation subset in the initial video data.

[0129] In step S24, an artificial intelligence recognition model is used to obtain a face and mouth image corresponding to each video clip in the video clip set;

[0130] The specific process is as described above and will not be repeated here.

[0131] According to some embodiments, the artificial intelligence recognition model refers to the model used by the terminal when performing face recognition on the video clips corresponding to the word segmentation. The artificial intelligence recognition model does not specifically refer to a fixed model. When the terminal performs face recognition on the video clips through the artificial intelligence recognition model, the terminal can obtain images or video streams containing faces, and automatically detect and track faces in the images, and then perform face recognition on the detected face images, thereby obtaining face and mouth images corresponding to each video clip in the video clip set.

[0132] In some embodiments, the artificial intelligence recognition model can use Opencv to obtain the video stream corresponding to each video clip and capture the image transmitted by the video stream. The artificial intelligence recognition model can take one frame for face recognition every preset frame, call the face detector in the Dlib library to detect the face, and obtain the key points of the face through the Dlib face key point predictor, and then use the Dlib face recognition model to convert the obtained face key points into 128D face descriptors, take the image containing the mouth descriptor as the face mouth image and label it.

[0133] It is easy to understand that when the terminal obtains a set of video clips corresponding to each word in the word segmentation subset, the terminal can use an artificial intelligence recognition model to obtain a face and mouth image corresponding to each video clip in the video clip set.

[0134] In step S25, second prompt information is issued for the face and mouth images corresponding to each video clip;

[0135] According to some embodiments, the second prompt information refers to the information sent when the terminal obtains the face and mouth images corresponding to each video clip in the video clip set. The second prompt information does not specifically refer to a fixed information. The second prompt information includes but is not limited to pop-up prompt information, voice prompt information, etc. When the terminal obtains the information modification instruction for the second prompt information, the second prompt information will also change accordingly. For example, when the terminal obtains the face and mouth images corresponding to each video clip in the video clip set, the terminal can pop up a toast window. Alternatively, when the terminal obtains the face and mouth images corresponding to each video clip in the video clip set, the terminal can send a voice message of "face and mouth image detected".

[0136] It is easy to understand that when the terminal obtains the face and mouth image corresponding to each video clip in the video clip set, the terminal can issue the second prompt information for the face and mouth image corresponding to each video clip.

[0137] In step S26, if a second confirmation instruction for the second prompt information is obtained, blur processing is performed on the face and mouth images corresponding to each video clip to obtain target video data;

[0138] The specific process is as described above and will not be repeated here.

[0139] According to some embodiments, the second confirmation instruction refers to an instruction issued when the user obtains the second prompt information issued by the terminal and selects the need to blur the face and mouth image. The second confirmation instruction does not specifically refer to a fixed confirmation instruction. The second confirmation instruction includes but is not limited to a click confirmation instruction, a voice confirmation instruction, and the like. When the terminal obtains a modification instruction for the second confirmation instruction, the second confirmation instruction will also change accordingly. For example, when the user clicks the "yes" button in the toast window, the terminal can obtain the second confirmation instruction for the second prompt information. Alternatively, when the user says the voice message of "need", the terminal can also obtain the second confirmation instruction for the second prompt information.

[0140] In some embodiments, when the terminal blurs the face and mouth images corresponding to each video clip by drawing mosaics, the terminal may degrade the color scale details of the picture and create a disrupted color block effect. When the terminal blurs the face and mouth images corresponding to each video clip by Gaussian blurring the image, the terminal may perform weighted averaging of the pixels around the image according to the Gaussian curve to remove the image details and make the image blurred. When the terminal blurs the face and mouth images corresponding to each video clip by salt and pepper blurring the image, the terminal may randomly display black and white dots in the mouth area of ​​the face and mouth image.

[0141] It is easy to understand that when the terminal issues the second prompt information for the face and mouth images corresponding to each video clip, the user can issue a second confirmation instruction for the second prompt information based on the second prompt information. When the terminal obtains the second confirmation instruction for the second prompt information, the terminal can blur the face and mouth images corresponding to each video clip to obtain the target video data.

[0142] In step S27, the audio data corresponding to each word in the word segmentation subset is converted to obtain target audio data;

[0143] According to some embodiments, the conversion process refers to the process in which the terminal performs shielding processing on the audio data corresponding to each word in the word segmentation subset. The conversion process does not specifically refer to a fixed conversion process. The terminal can replace the audio data corresponding to each word in the word segmentation subset with a preset audio. For example, the terminal can replace the audio data corresponding to each word in the word segmentation subset with a "beep" sound.

[0144] In some embodiments, the target audio data refers to the audio data that satisfies the audio and video data playback conditions obtained after the terminal converts the initial audio data. The target audio data does not specifically refer to a fixed audio data. For example, when the word subset changes, the target audio data will also change. When the audio and video data playback conditions change, the target video data will also change.

[0145] It is easy to understand that when the terminal obtains the word segmentation subset, the terminal can convert the audio data corresponding to each word segment in the word segmentation subset to obtain the target audio data that meets the audio and video data playback conditions.

[0146] In step S28, target audio and video data are obtained based on the target audio data and the target video data.

[0147] According to some embodiments, the target audio and video data refers to the audio and video data that meets the audio and video data playback conditions obtained after the terminal converts the initial audio and video data. The target audio and video data does not specifically refer to a fixed audio and video data. For example, when the initial audio and video data changes, the target audio and video data will also change. When the audio and video data playback conditions change, the target audio and video will also change.

[0148] In some embodiments, when the terminal converts the initial audio and video data, it can obtain target audio data and target video data that meet the audio and video data playback conditions. The terminal can integrate the acquired audio track of the target audio data and the video track of the target video data together, thereby obtaining audio and video data that meet the audio and video data playback conditions.

[0149] It is easy to understand that when the terminal obtains the target audio data and the target video data that meet the audio and video data playback conditions, the terminal can obtain the target audio and video data that meet the audio and video data playback conditions based on the target audio data and the target video data.

[0150] In some or related embodiments, in the initial audio and video data, the text information corresponding to the initial audio data is segmented to obtain a segmentation set; if a segmentation subset in the segmentation set is obtained, a first prompt information for the segmentation subset is issued; if a first confirmation instruction for the first prompt information is obtained, a video clip set corresponding to each segmentation in the segmentation subset is obtained in the initial video data; therefore, it can be determined based on the user's choice whether to obtain the video clip set corresponding to each segmentation in the segmentation subset, which can improve the accuracy of obtaining the video clip set, and thus improve the user experience. An artificial intelligence recognition model is used to obtain the face and mouth images corresponding to each video clip in the video clip set; therefore, a second prompt information for the face and mouth images corresponding to each video clip is issued; if a second confirmation instruction for the second prompt information is obtained, the face and mouth images corresponding to each video clip are blurred to obtain the target video data; therefore, it can be determined based on the user's choice whether to blur the face and mouth images, which can improve the accuracy of blurring, and the video data of the segmentation subset corresponding to the initial audio data can be shielded, which can improve the quality of the obtained video data, and thus improve the user experience. Finally, the audio data corresponding to each word in the word segmentation subset is converted and processed to obtain the target audio data; based on the target audio data and the target video data, the target audio and video data are obtained; therefore, the audio data and video data of the word segmentation subset corresponding to the initial audio data can be shielded at the same time, which can improve the quality of the acquired audio and video data, thereby improving the user experience.

[0151] Figure 6A flowchart of a method for acquiring video data is shown according to an exemplary embodiment. Figure 6 As shown, the video data acquisition method can be applied to multimedia scenarios, for example. The method can be implemented by relying on a computer program and can be run on a device including the video data acquisition method. The video data acquisition method includes the following steps:

[0152] In step S31, in the initial audio and video data, the text information corresponding to the initial audio data is segmented to obtain a segmentation set;

[0153] The specific process is as described above and will not be repeated here.

[0154] In step S32, if a segmentation subset in the segmentation set is obtained, then a display time point corresponding to any segmentation in the segmentation subset is obtained;

[0155] The specific process is as described above and will not be repeated here.

[0156] According to some embodiments, the display time point refers to the timestamp corresponding to the word segmentation in the audio data. In the audio and video data, the timestamps of the audio data and the video data are synchronized. The display time point does not specifically refer to a fixed time point. For example, when the word segmentation changes, the display time point will also change. When the audio data changes, the display time point will also change.

[0157] It is easy to understand that when the terminal obtains the word segmentation set, the terminal can obtain the word segmentation subset in the word segmentation set that does not meet the audio and video data playback conditions. When the terminal obtains the word segmentation subset in the word segmentation set, the terminal can obtain the display time point corresponding to any word in the word segmentation subset.

[0158] In step S33, a video segment corresponding to the display time point is obtained from the initial video data;

[0159] According to some embodiments, a video clip refers to a video clip corresponding to a word segmentation synchronized with a display time point in the audio and video data. The video clip does not specifically refer to a fixed clip. For example, when the word segmentation changes, the video clip will also change. When the display time point changes, the video clip will also change.

[0160] It is easy to understand that when the terminal obtains the presentation time point corresponding to any word in the word segmentation subset, the terminal can obtain the video segment corresponding to the presentation time point in the initial video data.

[0161] In step S34, the word segmentation subset is traversed to obtain a set of video clips corresponding to each word in the word segmentation subset in the initial video data;

[0162] According to some embodiments, traversing the word segmentation subset means visiting each word segmentation in the word segmentation subset in turn along a preset search route. When visiting any word segmentation, the display time point corresponding to the word segmentation is obtained, and then the video clip corresponding to the display time point is obtained. The obtained video clips are put into the same set, thereby obtaining a set of video clips corresponding to each word segmentation in the word segmentation subset.

[0163] In some embodiments, the traversal method includes but is not limited to pre-order traversal, in-order traversal, post-order traversal, etc. Among them, when the terminal adopts pre-order traversal, the operation of accessing the node occurs before traversing its left and right subtrees. When the terminal adopts in-order traversal, the operation of accessing the node occurs during traversing its left and right subtrees. When the terminal adopts post-order traversal, the operation of accessing the node occurs after traversing its left and right subtrees.

[0164] It is easy to understand that when the terminal obtains the word segmentation set, the terminal can obtain the word segmentation subset in the word segmentation set that does not meet the audio and video data playback conditions. When the terminal obtains the word segmentation subset in the word segmentation set, the terminal can traverse the word segmentation subset and obtain a set of video clips corresponding to each word in the word segmentation subset in the initial video data.

[0165] In step S35, a face and mouth image corresponding to any video clip in the video clip set is obtained;

[0166] The specific process is as described above and will not be repeated here.

[0167] It is easy to understand that when the terminal obtains a set of video segments corresponding to each word segment in the word segment subset, the terminal can obtain a face and mouth image corresponding to any video segment in the video segment set.

[0168] In step S36, a mosaic sticker is added to the image position corresponding to the face and mouth image to obtain a target video clip;

[0169] According to some embodiments, the image position corresponding to the face and mouth image refers to the area of ​​the mouth identified when face recognition is performed on the face and mouth image. The image position does not specifically refer to a fixed position. For example, when the face and mouth image changes, the image position will also change. When the word segmentation changes, the image position will also change.

[0170] In some embodiments, when the terminal performs face recognition on a face and mouth image, if at least two faces are identified in the face and mouth image, the terminal can determine the faces corresponding to each word in the word segmentation subset based on the mouth shape corresponding to each face or the voiceprint feature corresponding to each face, and then obtain the area of ​​the mouth corresponding to the face, such as Figure 7 As shown, the dotted frame is the image position corresponding to the recognized face mouth image.

[0171] According to some embodiments, when the terminal obtains a face and mouth image corresponding to any video clip in a video clip set, the terminal can obtain the word segmentation corresponding to the face and mouth image in the word segmentation subset. Furthermore, the terminal can obtain the word segmentation type corresponding to the word segmentation, and obtain the mosaic sticker corresponding to the word segmentation type. When the terminal obtains the mosaic sticker corresponding to the word segmentation type, the terminal can add the mosaic sticker to the image position corresponding to the face and mouth image. Therefore, different blurring processes can be performed for different word segmentation types, which can improve the quality of video data and thus improve the user experience.

[0172] In some embodiments, the word segmentation types include but are not limited to uncivilized language, sensitive words, etc. The user can select the style of the mosaic sticker in the gallery. When the terminal receives a sticker modification instruction for the mosaic sticker corresponding to the word segmentation type, the mosaic sticker will change accordingly. For example, the style of the mosaic sticker corresponding to uncivilized language can be a circle with an ×. The style of the mosaic sticker corresponding to the sensitive word can be a circle with the word "secret" inside, such as Figure 8 shown.

[0173] It is easy to understand that when the terminal obtains the face and mouth image corresponding to any video clip in the video clip set, the terminal can identify the image position of the mouth corresponding to the face and mouth image. When the terminal obtains the image position of the mouth corresponding to the face and mouth image, the terminal can add a mosaic sticker at the image position to obtain the target video clip.

[0174] In step S37, the video clip set is traversed, and mosaic stickers are added to each video clip in the video clip set to obtain a target video clip set;

[0175] According to some embodiments, traversing the video clip set means accessing each video clip in the video clip set in turn along a preset search route. When accessing any video clip, the image position of the mouth and the word segmentation type corresponding to the video clip are obtained, and then the mosaic sticker corresponding to the word segmentation type is obtained, and the corresponding mosaic sticker is placed at the image position. The obtained target video clips are placed in the same set, thereby obtaining the target video clip set.

[0176] It is easy to understand that when the terminal obtains the video segment set, the terminal can traverse the video segment set, add mosaic stickers to each video segment in the video segment set, and thus obtain the target video segment set.

[0177] In step S38, target video data is obtained based on the target video segment set.

[0178] It is easy to understand that when the terminal obtains the target video segment set, the terminal can replace the initial video segment corresponding to the presentation time point with the target video segment set based on the presentation time point, thereby obtaining the target video data.

[0179] In some or related embodiments, in the initial audio and video data, the text information corresponding to the initial audio data is segmented to obtain a segmentation set; if a segmentation subset in the segmentation set is obtained, the display time point corresponding to any segmentation in the segmentation subset is obtained; the video clip corresponding to the display time point is obtained in the initial video data; the segmentation subset is traversed to obtain a video clip set corresponding to each segmentation in the segmentation subset in the initial video data; thus, the accuracy of obtaining the video clip set can be improved, and thus the user experience can be improved. The face and mouth image corresponding to any video clip in the video clip set is obtained; mosaic stickers are added to the image position corresponding to the face and mouth image to obtain the target video clip; the video clip set is traversed to add mosaic stickers to each video clip in the video clip set to obtain the target video clip set; based on the target video clip set, the target video data is obtained; thus, the initial video data corresponding to the initial audio data can be fuzzy processed, the video data of the segmentation subset corresponding to the initial audio data can be shielded, the quality of the obtained video data can be improved, and thus the user experience can be improved.

[0180] Fig. 9 is a block diagram of a video data acquisition device according to an exemplary embodiment. Fig. 9 The video data acquisition device 900 includes a word segmentation processing unit 901, a segment acquisition unit 902 and a target acquisition unit 903.

[0181] The word segmentation processing unit 901 is configured to execute in the initial audio and video data, perform word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set, and the initial audio and video data includes initial audio data and initial video data;

[0182] The segment acquisition unit 902 is configured to execute, if a segmentation subset in the segmentation set is acquired, then acquire a video segment set corresponding to each segmentation in the segmentation subset in the initial video data, and each segmentation in the segmentation subset does not meet the audio and video data playback condition;

[0183] The target acquisition unit 903 is configured to perform blur processing on the face and mouth image corresponding to each video clip in the video clip set to obtain target video data.

[0184] According to some embodiments, Fig.10 is a block diagram of a video data acquisition device according to an exemplary embodiment. Fig.10The segment acquisition unit 902 includes a subset acquisition subunit 912 and a set acquisition subunit 922, which are configured to execute if a segmentation subset in a segmentation set is acquired, then when acquiring a video segment set corresponding to each segmentation in the segmentation subset in the initial video data:

[0185] The subset acquisition subunit 912 is configured to issue a first prompt information for the word segmentation subset if a word segmentation subset in the word segmentation set is acquired;

[0186] The set acquisition subunit 922 is configured to acquire, in the initial video data, a set of video segments corresponding to each word in the word subset if a first confirmation instruction for the first prompt information is acquired.

[0187] According to some embodiments, Fig.11 is a block diagram of a video data acquisition device according to an exemplary embodiment. Fig.11 The target acquisition unit 9003 includes a model recognition subunit 913, an information prompt subunit 923 and an image processing subunit 933, which is configured to perform blur processing on the face and mouth images corresponding to each video clip in the video clip set, and obtain the target video data:

[0188] The model recognition subunit 913 is configured to execute the artificial intelligence recognition model to obtain the face and mouth image corresponding to each video clip in the video clip set;

[0189] The information prompting subunit 923 is configured to send out second prompting information for the face and mouth images corresponding to each video clip;

[0190] The image processing subunit 933 is configured to execute, if a second confirmation instruction for the second prompt information is obtained, blur the face and mouth images corresponding to each video clip to obtain target video data.

[0191] According to some embodiments, Fig.12 is a block diagram of a video data acquisition device according to an exemplary embodiment. Fig.12 The target acquisition unit 903 further includes an image acquisition subunit 943, a sticker adding subunit 953, a set traversal subunit 963 and a data acquisition subunit 973, which are configured to perform blur processing on the face and mouth images corresponding to each video clip in the video clip set, and obtain the target video data:

[0192] The image acquisition subunit 943 is configured to execute acquisition of a human face and mouth image corresponding to any video segment in the video segment set;

[0193] The sticker adding subunit 953 is configured to add a mosaic sticker at an image position corresponding to the face and mouth image to obtain a target video clip;

[0194] The set traversal subunit 963 is configured to perform traversal of the video segment set, add mosaic stickers to each video segment in the video segment set, and obtain a target video segment set;

[0195] The data acquisition subunit 973 is configured to obtain target video data based on a target video segment set.

[0196] According to some embodiments, the sticker adding subunit 953 is configured to add a mosaic sticker at an image position corresponding to the face and mouth image, and when the target video segment is obtained, it is specifically configured to execute:

[0197] In the word segmentation subset, obtain the word segmentation corresponding to the face and mouth image;

[0198] Get the word segmentation type corresponding to the word segmentation;

[0199] Get the mosaic sticker corresponding to the word segmentation type;

[0200] Add a mosaic sticker at the image position corresponding to the face mouth image.

[0201] According to some embodiments, Fig.13 is a block diagram of a video data acquisition device according to an exemplary embodiment. Fig.13 The segment acquisition unit 902 further includes a time acquisition subunit 932, a video acquisition subunit 942 and a subset traversal subunit 952, which are configured to execute if a segmentation subset in the segmentation set is acquired, then when acquiring a video segment set corresponding to each segmentation in the segmentation subset in the initial video data:

[0202] The time acquisition subunit 932 is configured to execute, if a word subset in the word set is acquired, then acquire a display time point corresponding to any word in the word subset;

[0203] The video acquisition subunit 942 is configured to acquire a video segment corresponding to a display time point in the initial video data;

[0204] The subset traversal subunit 952 is configured to perform traversal of the word segmentation subset, and obtain a set of video segments corresponding to each word segmentation in the word segmentation subset in the initial video data.

[0205] According to some embodiments, Fig.14 is a block diagram of a video data acquisition device according to an exemplary embodiment. Fig.14The video data acquisition device 900 further includes an audio and video acquisition unit 904, which is configured to perform blur processing on the face and mouth images in each video segment in the video segment set to obtain the target video data:

[0206] Convert the audio data corresponding to each word in the word segmentation subset to obtain target audio data;

[0207] Based on the target audio data and the target video data, the target audio and video data are obtained.

[0208] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0209] In some or related embodiments, the word segmentation processing unit performs word segmentation processing on the text information corresponding to the initial audio data in the initial audio and video data to obtain a word segmentation set, and the initial audio and video data includes the initial audio data and the initial video data; if the segmentation acquisition unit obtains a segmentation subset in the segmentation set, then a video segment set corresponding to each segmentation in the segmentation subset is obtained in the initial video data, and each segmentation in the segmentation subset does not meet the audio and video data playback condition; the target acquisition unit performs blur processing on the face and mouth image corresponding to each video segment in the video segment set to obtain the target video data. Therefore, by blurring the initial video data corresponding to the initial audio data, the terminal can shield the video data of the segmentation subset corresponding to the initial audio data, improve the quality of the acquired video data, and thus improve the user experience.

[0210] See also Fig.15 , is a block diagram of a terminal according to an exemplary embodiment. Fig.15 As shown, the terminal 1500 may include: at least one processor 1501 , at least one network interface 1504 , a user interface 1503 , a memory 1505 , and at least one communication bus 1502 .

[0211] The communication bus 1502 is used to realize the connection and communication between these components.

[0212] The user interface 1503 may include a speaker and a display screen, and the optional user interface 1503 may also include a standard wired interface and a wireless interface.

[0213] The network interface 1504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0214] Among them, the processor 1501 may include one or more processing cores. The processor 1501 uses various interfaces and lines to connect various parts in the entire terminal 1500, and executes various functions and processes data of the terminal 1500 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1505, and calling data stored in the memory 1505. Optionally, the processor 1501 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1501 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1501, and it can be implemented separately through a chip.

[0215] Among them, the memory 1505 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1505 includes a non-transitory computer-readable storage medium. The memory 1505 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1505 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 1505 may optionally be at least one storage device located away from the aforementioned processor 1501. As Fig.15 As shown, the memory 1505 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for acquiring video data.

[0216] exist Fig.15In the terminal 1500 shown in the figure, the user interface 1503 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1501 can be used to call the application program for obtaining the video data stored in the memory 1505 and specifically execute Figure 3-Figure 8 Each step in the method embodiment.

[0217] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors execute Figure 3-Figure 9 Each step in the method embodiment.

[0218] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0219] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0220] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0221] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0222] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0223] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0224] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0225] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0226] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0227] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

Claims

1. A method for acquiring video data, characterized in that: include: In the initial audio and video data, performing word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set, wherein the initial audio and video data includes the initial audio data and the initial video data; If a segmentation subset in the segmentation set is obtained, a set of video clips corresponding to each segmentation in the segmentation subset is obtained in the initial video data, and each segmentation in the segmentation subset does not meet the audio and video data playback condition; Performing blur processing on the human face and mouth image corresponding to each video clip in the video clip set to obtain target video data, wherein when a modification instruction for the blur processing method is received, the blur processing method will be changed accordingly; After determining the target video data, converting the audio data corresponding to each word in the word segmentation subset to obtain target audio data, and obtaining target audio and video data based on the target audio data and the target video data; If a subset of the word segments in the word segmentation set is obtained, a set of video clips corresponding to each word in the subset of the word segments is obtained in the initial video data, including: If a segmentation subset in the segmentation set is obtained, issuing first prompt information for the segmentation subset; If a first confirmation instruction for the first prompt information is obtained, a set of video segments corresponding to each word in the word segmentation subset is obtained in the initial video data; The blurring process is performed on the face and mouth image corresponding to each video clip in the video clip set, including: The artificial intelligence recognition model obtains the video stream corresponding to each video clip in the video clip set by using Opencv, captures the image transmitted by the video stream, and calls the face detector in the Dlib library to detect the face, obtains the key points of the face through the Dlib face key point predictor, and the Dlib facial recognition model determines the mouth image of the face according to the key points; Sending a second prompt message for the human face and mouth image to remind the user whether to blur the human face and mouth image; If a second confirmation instruction for the second prompt information is obtained, blurring is performed on the face and mouth image.

2. The method according to claim 1, characterized in that The step of performing blur processing on the face and mouth image corresponding to each video clip in the video clip set to obtain target video data includes: Obtaining a face and mouth image corresponding to any video clip in the video clip set; Adding a mosaic sticker at the image position corresponding to the face and mouth image to obtain a target video clip; Traversing the video clip set, adding the mosaic sticker to each video clip in the video clip set, to obtain a target video clip set; Based on the target video segment set, target video data is obtained.

3. The method according to claim 2, characterized in that Adding a mosaic sticker at the image position corresponding to the face and mouth image to obtain a target video clip includes: In the word segmentation subset, obtaining the word segmentation corresponding to the human face and mouth image; Obtain the segmentation type corresponding to the segmentation; Obtaining a mosaic sticker corresponding to the word segmentation type; The mosaic sticker is added at the image position corresponding to the human face and mouth image.

4. The method according to claim 1, characterized in that If a subset of the word segments in the word segmentation set is obtained, a set of video clips corresponding to each word in the subset of the word segments is obtained in the initial video data, and further includes: If a subset of the word segments in the word segmentation set is obtained, then a display time point corresponding to any word in the subset of the word segments is obtained; Acquire a video segment corresponding to the display time point in the initial video data; The word segmentation subset is traversed, and a set of video segments corresponding to each word segmentation in the word segmentation subset is obtained in the initial video data.

5. A video data acquisition device, characterized in that: include: A word segmentation processing unit is configured to execute in the initial audio and video data, perform word segmentation processing on the text information corresponding to the initial audio data to obtain a word segmentation set, wherein the initial audio and video data includes the initial audio data and the initial video data; a segment acquisition unit configured to acquire, if a segment subset in the segment set is acquired, a set of video segments corresponding to each segment in the segment subset in the initial video data, wherein each segment in the segment subset does not satisfy the audio and video data playback condition; a target acquisition unit configured to perform blur processing on the human face and mouth image corresponding to each video clip in the video clip set to obtain target video data, wherein when a modification instruction for the blur processing method is received, the blur processing method will be changed accordingly; The audio and video acquisition unit is configured to perform conversion processing on the audio data corresponding to each word in the word segmentation subset after determining the target video data to obtain target audio data, and obtain target audio and video data based on the target audio data and the target video data; The fragment acquisition unit includes a subset acquisition subunit and a set acquisition subunit, wherein: The subset acquisition subunit is configured to issue first prompt information for the word segmentation subset if a word segmentation subset in the word segmentation set is acquired; The set acquisition subunit is configured to acquire, in the initial video data, a set of video segments corresponding to each word in the word subset if a first confirmation instruction for the first prompt information is acquired; The target acquisition unit includes a model recognition subunit, an information prompting subunit and an image processing subunit, wherein: The model recognition subunit is configured to execute the artificial intelligence recognition model by using Opencv to obtain the video stream corresponding to each video clip in the video clip set, capture the image transmitted by the video stream, and call the face detector in the Dlib library to detect the face, obtain the key points of the face through the Dlib face key point predictor, and the Dlib facial recognition model determines the mouth image of the face according to the key points; The information prompting subunit is configured to issue a second prompting message for the face and mouth image to remind the user whether to perform blur processing on the face and mouth image; The image processing subunit is configured to execute blurring processing on the face and mouth image if a second confirmation instruction for the second prompt information is obtained.

6. The device according to claim 5, characterized in that The target acquisition unit further includes an image acquisition subunit, a sticker adding subunit, a set traversal subunit and a data acquisition subunit, which are configured to perform blur processing on the face and mouth images corresponding to each video clip in the video clip set, and when the target video data is obtained: The image acquisition subunit is configured to acquire a face and mouth image corresponding to any video clip in the video clip set; The sticker adding subunit is configured to add a mosaic sticker at an image position corresponding to the face and mouth image to obtain a target video clip; The set traversal subunit is configured to traverse the video segment set, add the mosaic sticker to each video segment in the video segment set, and obtain a target video segment set; The data acquisition subunit is configured to obtain target video data based on the target video segment set.

7. The device according to claim 6, characterized in that The sticker adding subunit is configured to add a mosaic sticker to the image position corresponding to the face and mouth image, and when the target video clip is obtained, the subunit is specifically configured to execute: In the word segmentation subset, obtaining the word segmentation corresponding to the human face and mouth image; Obtain the segmentation type corresponding to the segmentation; Obtaining a mosaic sticker corresponding to the word segmentation type; The mosaic sticker is added at the image position corresponding to the human face and mouth image.

8. The device according to claim 5, characterized in that The segment acquisition unit further includes a time acquisition subunit, a video acquisition subunit and a subset traversal subunit, which are configured to execute, if a segmentation subset in the segmentation set is acquired, when acquiring a video segment set corresponding to each segmentation in the segmentation subset in the initial video data: The time acquisition subunit is configured to execute, if a subset of the segmentation words in the segmentation set is acquired, then acquire a display time point corresponding to any segmentation word in the segmentation word subset; The video acquisition subunit is configured to acquire a video segment corresponding to the display time point in the initial video data; The subset traversal subunit is configured to traverse the word segmentation subset and obtain a set of video segments corresponding to each word in the word segmentation subset in the initial video data.

9. A terminal, comprising: at least one processor; as well as A memory communicatively connected to the at least one processor; characterized in that The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

Images