WO2022242577A1

WO2022242577A1 - Video processing method and apparatus, and electronic device

Info

Publication number: WO2022242577A1
Application number: PCT/CN2022/092837
Authority: WO
Inventors: 杭宇
Original assignee: 维沃移动通信有限公司
Priority date: 2021-05-20
Filing date: 2022-05-13
Publication date: 2022-11-24
Also published as: CN113315691A; CN113315691B

Abstract

The present application belongs to the technical field of video processing and discloses a video processing method and apparatus and an electronic device. The video processing method comprises: receiving a target video sent by a target chat object; and if a first object in the target video matches a preset second object, displaying a first identifier, the first identifier being used for indicating that the target video comprises the second object.

Description

Video processing method, device and electronic equipment

Cross References to Related Applications

This application claims the priority of the Chinese patent application 202110553846.8 entitled "Video Processing Method, Device and Electronic Equipment" filed on May 20, 2021, the entire content of which is incorporated herein by reference.

technical field

The present application belongs to the field of video technology, and in particular relates to a video processing method, device and electronic equipment.

Background technique

With the development of communication technology, users can obtain massive videos through electronic devices. However, in the prior art, when an electronic device receives a video, the user may need to click to watch the video to determine whether there is content of interest in the video, especially in the case of receiving multiple videos, a Only by playing and watching videos one by one can you determine which video you are interested in. The process of determining is cumbersome and time-consuming.

Contents of the invention

The purpose of the embodiments of the present application is to provide a video processing method, device, and electronic device, which can solve the problem in the prior art that the process of determining a video of interest to a user is cumbersome and time-consuming.

In the first aspect, the embodiment of the present application provides a video processing method, the method comprising:

Receive the target video sent by the target chat partner;

If the first object in the target video matches the preset second object, a first identification is displayed, and the first identification is used to indicate that the target video includes the second object.

In a second aspect, an embodiment of the present application provides a video processing device, which includes:

The receiving module is used to receive the target video sent by the target chat object;

The first display module is configured to display a first mark when the first object in the target video matches a preset second object, and the first mark is used to indicate that the target video includes the second object.

In the third aspect, the embodiment of the present application provides an electronic device, the electronic device includes a processor, a memory, and a program or instruction stored in the memory and operable on the processor. When the program or instruction is executed by the processor, the The steps of the method of the first aspect.

In a fourth aspect, the embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method in the first aspect are implemented.

In the fifth aspect, the embodiment of the present application provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method in the first aspect.

In the embodiment of the present application, the target video sent by the target chat object is received, and when the first object in the target video matches the preset second object, a first logo is displayed, and the first logo is used to indicate the target video Include the second object. In this embodiment of the present application, by matching the first object with the second object, the first logo can be displayed on the target video including the second object, which helps the user to efficiently acquire videos with interesting content.

Description of drawings

FIG. 1 is a schematic flow diagram of a video processing method provided in an embodiment of the present application;

Fig. 2 is one of the example diagrams of the conversational interface in the embodiment of the present application;

Fig. 3 is the second example diagram of the conversation interface in the embodiment of the present application;

Fig. 4 is the third example diagram of the conversation interface in the embodiment of the present application;

Fig. 5 is one of the example diagrams of the target window in the embodiment of the present application;

Fig. 6 is the second example diagram of the target window in the embodiment of the present application;

Fig. 7 is the third example diagram of the target window in the embodiment of the present application;

Figure 8 is one of the example diagrams of the setting interface in the embodiment of the present application;

Figure 9 is the second example diagram of the setting interface in the embodiment of this application;

Figure 10 is the third example diagram of the setting interface in the embodiment of this application;

Figure 11 is the fourth example diagram of the setting interface in the embodiment of this application;

Figure 12 is the fifth example diagram of the setting interface in the embodiment of this application;

FIG. 13 is a schematic flowchart of a video processing method provided in an embodiment of the present application in a specific application example;

FIG. 14 is a schematic structural diagram of a video processing device provided by an embodiment of the present application;

Fig. 15 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

FIG. 16 is a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application.

Detailed ways

The following will clearly describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in this application belong to the protection scope of this application.

The terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It should be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application can be practiced in sequences other than those illustrated or described herein, and that references to "first," "second," etc. distinguish Objects are generally of one type, and the number of objects is not limited. For example, there may be one or more first objects. In addition, "and/or" in the specification and claims means at least one of the connected objects, and the character "/" generally means that the related objects are an "or" relationship.

The video processing method and device provided in the embodiments of the present application will be described in detail below through specific embodiments and application scenarios with reference to the accompanying drawings.

As shown in Figure 1, the video processing method provided by the embodiment of the present application includes:

Step 101, receiving the target video sent by the target chat partner;

Step 102: In the case that the first object in the target video matches the preset second object, display a first mark, where the first mark is used to indicate that the target video includes the second object. The logos in this application are used to indicate text, symbols, images, etc. of information, and controls or other containers may be used as carriers for displaying information, including but not limited to text logos, symbol logos, and image logos.

The video processing method provided in the embodiment of the present application may be applied to an electronic device, and the electronic device may be a personal computer or a mobile terminal, etc., and is not specifically limited here.

Combined with some application scenarios, when video application programs or social application programs are running in the electronic device, the video sent by the server or other types of terminal devices can be received through these application programs. The target video received in the above step 101 may be a video received by the electronic device from other terminal devices.

For example, in a social application, there may be chat groups. A video sent by user A in the chat group will be received by other users of the chat group. At this point, user A can be considered as the above-mentioned target chat partner.

User B may be another user in the chat group. After user B receives the video sent by user A through the electronic device, it may be difficult for user B to directly know whether there is content of interest in the video, such as interested persons or items etc. Usually, user B needs to click to play the video after entering the corresponding conversation interface, so as to confirm whether the video contains the content he is interested in.

However, in some scenarios, user A may send multiple videos, and only a part of the multiple videos may include the content that user B is interested in. From the perspective of user B, after receiving these multiple videos through the electronic device, he may enter the conversation interface and click to play these multiple videos one by one to determine the video that includes the content he is interested in.

It can be seen that, in the process of obtaining the video of the content that user B is interested in, there is a problem of low acquisition efficiency.

Of course, in practical applications, the target chat object of sending the target video may not only be a user, but also a robot customer service and the like. For example, the robot customer service can send a video to the electronic device according to the keywords sent by the user of the electronic device. Alternatively, the robot customer service can regularly send videos to the electronic device according to the historical viewing records of the user of the electronic device or the preset interest tags.

Similarly, in the case that the robot customer service has sent multiple videos, the user may need to click to play the multiple videos one by one to determine the video that includes the content of interest.

With reference to the examples of the above application scenarios, in step 102, the preset second object may correspond to the content that the user of the electronic device is interested in.

Specifically, in this embodiment, the second object may be an object preset by the user, or may also be an object automatically determined by the electronic device according to historical operation data of the user. In terms of content, the second object may be a character, an animal, or an object, which is not specifically limited here.

As an example, the second object may be a target person. When setting the second object, the user may select an image or video taken of the target person as a material and add it to the material library. The electronic device can identify the second object in these materials based on a machine learning algorithm.

Of course, in practical applications, the second object may also be an animal such as a dog or a cat, or an object such as a house or a vehicle. When setting the second objects, it is sufficient to select images or videos obtained by shooting these second objects as identification materials.

Similar to the second object, the target video generally also includes the first object, such as a person or an object. The first object in the target video may also be obtained by identifying the target video through a machine learning algorithm.

To simplify the description, the video processing method provided by the embodiment of the present application will be described below mainly by taking the first object and the second object both as characters as an example.

With reference to the example of the application scenario of the chat group above, user B can set himself as the second object. From the perspective of the electronic device, after receiving the user B's selection input of the image including his own face under the condition that the relevant setting interface is displayed, the image selected by the user can be recognized to determine the second object.

After receiving the target video, the electronic device used by user B can identify the image frames in the target video to obtain the first object. The first object can also be a human face. When it is determined according to the facial feature comparison that the first object and the second object indicate the same person, it can be considered that the first object in the target video matches the preset second object.

Of course, in practical applications, the selected features for determining whether the first object matches the second object may be not only human face features, but also body features, etc., which are not specifically limited here.

The identification process of the image frame in the target video by the electronic device may be performed in the background. For example, when a conversation interface is displayed on the electronic device, the target video received on the conversation interface may be buffered, and the target video may be played in the background to identify image frames in the target video to obtain the first object.

In some feasible implementation manners, the electronic device may also cache the target video and identify the image frame after receiving the target video through the above-mentioned social application program. That is to say, the first object in the target video can still be acquired when the conversation interface of the chat group is not displayed.

Of course, the electronic device may also acquire the first object in the target video when the user clicks to play the target video.

In other words, the timing for the electronic device to acquire the first object in the target video is not specifically limited here.

In this embodiment, when the first object in the target video matches the preset second object, a first identification may be displayed, and the first identification is used to indicate that the target video is a video matching the second object.

For example, in the case where a conversation interface is displayed on the electronic device, there may usually be a thumbnail of the received video in the conversation interface. When one of the videos, that is, the first object in the above-mentioned target video matches the second object, a first logo may be displayed at a position corresponding to the thumbnail of the target video.

The first identification may be a text identification, for example, the content of the first identification may be "@userB", "videos you may be interested in", and so on. Certainly, the first mark may also be a picture mark or an icon mark, etc., which are not specifically limited here.

In other examples, the first identifier may be a preset floating control, such as a floating ball or a floating icon. That is to say, if the first object in the target video matches the preset second object, the electronic device may display a floating control in a preset area to prompt that a video including the second object has been received.

In general, in step 102, the user may be prompted that the video including the second object has been received by displaying the first logo. Or, further, the specific display position of the thumbnail of the target video in the current display interface may be indicated by the first identifier.

The video processing method provided by the embodiment of the present application receives the target video sent by the target chat object, and displays the first identification when the first object in the target video matches the preset second object, and the first identification is used for Indicating that the target video includes a second object. In this embodiment of the present application, by matching the first object with the second object, the first logo can be displayed on the target video including the second object, which helps the user to efficiently acquire videos with interesting content.

Optionally, the target chat object is an object in the target chat group;

Correspondingly, in step 101, after receiving the target video sent by the target chat object, the video processing method may further include:

Obtain a preset second object associated with the target chat group;

Comparing the similarity between the first object and the second object;

If the similarity between the first object and the second object is greater than the similarity threshold, it is determined that the first object matches the second object.

As shown in the example in the previous embodiment, the target chat object may be a video sent in the chat group. In other words, the target chat object may be an object in a chat group. To simplify the description, it can be considered that the target chat object is an object in the target chat group, and the target chat object sends the target video in the target chat group.

Combining again with the example of the application scenario of the chat group above, user B may be interested in multiple contents, and user B may be interested in person X and person Y (both may correspond to the second object) at the same time. However, the video including person X and the video including person Y may usually be received in different chat groups.

In order to avoid matching the first object in the target video with character X and character Y at the same time when the target video is received in a chat group, in this embodiment, a chat group and a second object can be pre-established relationship between.

Specifically, the target video may be a video sent to a target chat group, and the target chat group may be associated with a corresponding second object.

For example, in the related setting interface, the user can associate character X with the chat group HX, and associate character Y with the chat group HY by inputting on the electronic device.

When the chat group HX receives the target video as the above-mentioned target chat group, the electronic device may determine the person X as the second object associated with the target chat group.

In the above example, the association relationship between the chat group and the second object can be regarded as the association relationship between different chat groups and the second object in a social application. In practical applications, it may also be an association relationship established between the application program and the second object.

In other words, when the target video is received through the target chat group, the application program to which the target chat group belongs can be determined, and the target chat group can be determined according to the preset association relationship between the application program and the second object The second object associated with the group.

For example, during the setting process, the character X can be associated with the application program AX, and the character Y can be associated with the application program AY. When the target video is received through any chat group (corresponding to the target chat group) in the application program AX, the character X can be determined as the second object associated with the target chat group.

In the case that the second object associated with the target chat group is acquired, the second object associated with the target chat group may be used to perform a similarity comparison on the first object in the target video.

Combined with an example, both the first object and the second object can be people, and comparing the similarity between the first object and the second object can be to compare the facial features and other contents of the two to obtain the similarity between the two. Spend.

Of course, the similarity can also be regarded as the probability of identifying the first object as the second object. For example, the second object may be the preset animal "dog", and the similarity comparison result between the first object and the second object may be the probability of identifying the first object as "dog". corresponds to the above similarity.

When the similarity between the first object and the second object is greater than the similarity threshold, it may be determined that the first object matches the second object.

For example, the similarity threshold may be preset, and the specific value is 90%. When the similarity between the first object and the second object is greater than 90%, it may be determined that the first object matches the second object.

In some examples, the electronic device may omit the process of using the second object not associated with the target chat group to compare the similarity of the first object in the target video.

It can be seen that in this embodiment, in the case of receiving the target video sent to the target chat group, the second object associated with the target chat group can be obtained, and the second object associated with the target chat group can be combined with The similarity comparison is performed on the first object in the target video, which can effectively reduce the consumption of computing resources brought about by the similarity comparison process.

In some examples, the association relationship between the chat group and the second object may specifically be associated with the second object through group information of the chat group.

For example, the group information of the chat group may be the name of the chat group or the number corresponding to the chat group. During the setup process, the chat group name can be associated with the second object. In the case of receiving and sending to the target chat group, the associated second object can be determined according to the chat group name of the target chat group.

The following describes the display manner of the first logo with an example.

As shown in FIG. 2, FIG. 2 is an example diagram of a conversation interface of a target chat group. In the target chat group, multiple video thumbnails (marked as VP1 in the figure) may be displayed, and these videos may be sent to the target chat group by user A (corresponding to the target chat object).

In general, based on the recognition of the first object in these videos, target videos including the second object can be obtained.

As shown in FIG. 3 , FIG. 3 is an example diagram of displaying the first identifier for the target video including the second object in the conversation interface of the target chat group. In this example figure, the first logo can be displayed on the side of the thumbnail of the target video (marked as VP2 in the figure), and specifically displayed as the text of "@UserB" (marked as T1 in the figure).

Specifically, the first logo can be displayed in the form of pop-up windows or floating windows, and preset prompt texts can be displayed in these pop-up windows or floating windows.

Based on the displayed first identifier, the user can quickly learn which specific videos contain content of interest to him/herself, without having to click and play each video one by one, which effectively saves user operation time and improves user experience.

Certainly, in some implementation manners, the mark displayed on the target video including the second object in the target chat group may not be limited to the above-mentioned first identifier.

As shown in FIG. 4 , FIG. 4 is an example diagram of displaying a second mark on a target video including a second object in a conversation interface of a target chat group. In this example figure, the second mark may be displayed on the side of the thumbnail of the target video, and specifically displayed as words "90%" and "50%" (marked as T2 in the figure). Wherein, these words may be used to indicate the matching degree between the first object and the second object in the target video.

Specifically, in these embodiments, after the above-mentioned step 101 receives the target video sent by the target chat object, the video processing method may further include:

Obtain the matching degree between the first object in the target video and the preset second object; wherein, the matching degree is used to indicate the similarity between the first object and the second object, or the matching degree is used to indicate the target image frame in the target video ratio, the target image frame is an image frame including the first object, and the similarity between the first object and the second object is greater than the similarity threshold;

A second identification is displayed, and the second identification is used to indicate the matching degree between the first object and the second object in the target video.

Combining with the above application scenario where both the first object and the second object are people, the similarity between the first object and the second object may be the similarity of facial features, etc. Correspondingly, the similarity can be obtained through a preset face recognition model.

Of course, in some other examples of application scenarios, the second object may also be a generic animal or item. For example, the second object may be an animal dog, and the similarity between the first object and the second object may also be the probability that the first object is an animal dog obtained by identifying the image frame of the target video by a corresponding recognition model.

In some examples, the above similarity can be directly used as the matching degree between the target video and the second object.

The degree of matching between the first object in the target video and the preset second object may also be determined by the proportion of the target image frame in the target video. The target image frame may be an image frame including a first object, and the similarity between the first object and the second object is greater than a similarity threshold.

For example, the second object may be person X. Generally, if a person is included in an image frame, and the similarity between the person and person X is greater than a similarity threshold, it can be considered that the image frame includes person X. On this basis, if the target video has 100 image frames, and the person X is included in 60 image frames, then these 60 image frames correspond to the aforementioned target image frames.

Among the 100 image frames of the target video, there are 60 target image frames, that is, the proportion of the target image frame in the target video is 60%. At this point, it can be considered that the matching degree between the target video and the second object is 60%.

Of course, in practical applications, the matching degree between the first object and the second object can be obtained by combining the above similarity degree and the proportion of the target image frame. For example, the above similarity and the ratio of the image frame may be weighted and averaged to obtain the matching degree between the first object and the second object.

Referring to FIG. 4 , for the target video, a second logo can be displayed at a position matching its thumbnail. The second identification may include a percentage, which may indicate how well the first object matches the second object.

Of course, in practical applications, the second identifier may also include decimals or scores, and may indicate the degree of matching between the first object and the second object.

In this embodiment, the matching degree between the first object and the second object can be determined according to the similarity between the first object and the second object, or according to the proportion of the target image frame in the target video, and can be used to indicate the The second identification method of the matching degree reminds the user of the matching degree, which helps the user to quickly locate the video of interest, and provides the user with a basis for selecting the video that can be watched first, and improves the user experience.

In some implementations, after receiving the target video sent by the target chat object, there may be a process of displaying the first identification and displaying the second identification. The specific display timings of these two kinds of marks may be the same or different.

For example, in one example, if the current display interface of the electronic device is the main interface of the social application program, if the target video is received and the first object in the target video matches the preset second object, then the The first logo is displayed on the main interface, and the first logo may be located near the image logo of the target chat group. When the conversation interface of the target chat group is displayed in response to the user's input, the second identifier may be displayed on the conversation interface.

In another example, the first identification and the second identification may be simultaneously displayed for the target video in the conversation interface of the target chat group.

To sum up, in the embodiment of the present application, when the electronic device matches a target video that includes the content that the user is interested in, it can display the first logo for the target video, and/or display the second logo for indicating the matching degree, which can be Effectively remind the user to reduce the user's retrieval time for the target video.

Of course, after the above-mentioned first logo or second logo is displayed, these logos may not affect the user's viewing of other unmarked videos.

In some application scenarios, the electronic device may receive the target video without displaying the target chat group. Alternatively, when the electronic device displays a target chat group, it is difficult to simultaneously display thumbnails of all target videos when the number of received target videos is large, or the intervals between multiple received target videos are large.

In order to enable the electronic device to intuitively prompt the user with the target video that matches the second object in the above application scenarios, in one embodiment, after the above step 101 receives the target video sent by the target chat object, the video processing method further Can include:

If the first object in the target video matches the preset second object, a target window is displayed, and the target window includes a thumbnail of the target video.

As shown in FIG. 5 , FIG. 5 is an example diagram of displaying a target window (marked as W in the figure) in an electronic device. Wherein, the target window may be a floating window.

In an example, when the electronic device receives the target video, it may cache the target video, play the target video in the background, identify the first object in the target video, and match the first object with the second object. All the above-mentioned processing procedures can be performed in the background, and the target window can be displayed when the first object in the target video matches the second object.

In other words, the above-mentioned target window may be displayed on the desktop, or may be displayed on the running interface of the application program, or may also be displayed on the conversation interface of the target chat group.

The target window may include a thumbnail of the target video (labeled WP in the figure). In this way, in different display states, the electronic device can prompt the user to receive a video that may be of interest to the user, which helps to improve the timeliness of the prompting process.

With reference to the above embodiments, there may be a matching degree between the first object and the second object in the target video. Correspondingly, in one embodiment, the thumbnail image of the target video includes a third identifier, and the third identifier is used to indicate a degree of matching between the first object and the second object in the target video.

In other words, in the target window, the matching degree between the first object and the second object in the target video may be indicated by a third identifier. The manner of determining the matching degree between the first object and the second object in the target video is described in the above embodiments, and will not be repeated here.

As shown in Figure 6, in an example, the above-mentioned third identification (marked as WT in the figure) can be displayed in the upper left corner of the thumbnail of the target video, where the matching degree can be specifically displayed, such as "90%", "50%" etc.

Of course, the third mark can also be located in other positions in the thumbnail image, which can be set according to actual needs, and it only needs to be able to reflect the matching degree between the first object and the second object in the target video.

In this embodiment, the thumbnail of the target video includes a third identifier, which helps the user quickly determine the target video of interest from the target window, and provides a reference for the user to select a target video for priority playback.

In practical applications, the number of received videos may be multiple, and the number of target videos including the first object matched with the second object may also be multiple.

Correspondingly, in one embodiment, when there are multiple target videos, the thumbnails of each target video can be sorted and displayed in the target window according to the degree of matching between the first object and the second object in each target video .

For example, the thumbnails of each target video may be sequentially displayed in descending order of the matching degrees between the first object and the second object in each target video. In this way, the user can preferentially watch the target video containing more interesting content according to the order of the thumbnails of each target video.

Of course, in order to enable the user to obtain the matching degree between the first object and the second object in each target video more intuitively, the thumbnails of each target video may respectively include corresponding third identifiers.

In the case that the target window includes a thumbnail of the target video, the electronic device may receive user input on the thumbnail to operate on the corresponding target video.

Specifically, in some implementation manners, after displaying the target window, the video processing method further includes at least one of the following:

In the case of receiving the user's first input to the thumbnail of the target video in the target window, in response to the first input, play the target video;

storing the target video in response to the second input in response to receiving a second user input of a thumbnail image of the target video in the target window;

In the case of receiving a third input from the user to the thumbnail of the target video in the target window, forwarding the target video in response to the third input;

In case a user's fourth input of the thumbnail of the target video in the target window is received, the target video is deleted in response to the fourth input.

The foregoing implementation manner is illustrated below in conjunction with some specific application scenarios.

In some examples, the first input may correspond to the user's click input on the thumbnail of the target video, and when the electronic device receives the user's click input on the thumbnail of the target video, in response to the click input, Play the target video.

The second input may correspond to the user's double-click input on the thumbnail of the target video, and accordingly, the electronic device may store the target video when the double-click input is received.

The third input may correspond to the user's long press input on the thumbnail of the target video, and accordingly, in the case of receiving the long press input, the electronic device may forward the target video. In order to facilitate the user to choose which application to forward the target video through, after receiving the long press input, icons of applications that can be used to forward the target video may be displayed.

The fourth input may correspond to the user's dragging input of the target video along a preset path. For example, the user can drag the thumbnail of the target video to the outer area of the target window, and the electronic device can respond to the user's drag output, delete the target video from the memory used for caching files, and display it clearly in the target window. The thumbnail of the target video. As a feasible implementation manner, after all thumbnails of the target video in the target window are deleted, the target window can be hidden.

Of course, the above are only some examples of processing the target video by the electronic device in response to the user's input. In practical applications, the relationship between different input operations and processing methods for the target video can be adjusted according to actual needs.

For example, when a long-press input on the thumbnail of the target video is received, two operation controls whose names are respectively "store" and "forward" may also be displayed, and when a click input from the user on the operation control is received, , and further perform corresponding processing on the target video.

It can be seen that by displaying the target window, the user does not need to go deep into the specific session interface of the application program to manage the target video, which shortens and simplifies the operation path and helps to improve the operation efficiency.

As an optional implementation manner, displaying the target window when the first object in the target video matches the preset second object above may specifically include:

In the case that the first object in the target video matches the preset second object, displaying target operation controls;

In case an input to the target manipulation control is received, the target window is displayed in response to the input.

In this implementation manner, a target operation control may be displayed when a target video of interest to the user is received. The target operation control can be a floating button, and the floating button can occupy a small display area, so as to avoid too much blocking of the current display content of the electronic device.

And when the input of the target operation control is received, for example, when a single click, double-click or long press input is received to the target operation control, the target window can be further loaded, and the image of the target video can be displayed in the target window. thumbnail.

Optionally, the first object in the target video is obtained by using a preset recognition model to identify the target video;

Correspondingly, after displaying the first logo, the video processing method may further include:

In the case of receiving the fifth input to the target video, the target video is used as a training sample to train the recognition model;

Wherein, the fifth input is used for storing or forwarding the target video.

As shown above, when the first object in the target video is a person, the first object may be obtained by recognizing an image frame in the target video through a face recognition model. Similarly, when the first object is an animal or an object, the first object can also be identified from the target video by using a recognition model trained with relevant samples.

It is easy to understand that, in general, for a recognition model based on a machine learning algorithm, it usually needs to be fully trained with corresponding training samples, so that the recognition model has a better recognition effect. The quantity and quality of training samples have a great influence on the recognition effect of the trained recognition model.

Specific to the recognition model used in the embodiment of the present application, the corresponding training samples may be marked images or videos. The quality of training samples is generally affected by the accuracy of labeling.

In this embodiment, the target video can be regarded as an unlabeled video to a certain extent, and after the target video is input into the recognition model, a corresponding recognition result can be obtained. The recognition result may indicate whether the first object in the target video matches the second object.

If the recognition result indicates that the first object in the target video matches the second object, and the recognition result is a correct recognition result, then the target video can be used as a positive sample for optimal training of the recognition model.

Whether the recognition result is correct can be reflected by the user's operation on the target video. For example, in the case where the first logo is displayed for a certain target video, if the forwarding or storing operation of the target video by the user is received, it is considered that the user is indeed interested in the target video, that is, the recognition model is The recognition result of the target video can be considered correct.

In this embodiment, the fifth input to the target video may correspond to the above-mentioned input for storing or forwarding the target video, and there is no specific limitation here.

In general, the fifth input can be considered as the user's positive operation on the target video. In the case of receiving the fifth input of the target video, the target video can be used as a positive sample to train the recognition model, thereby helping to improve the recognition accuracy of the recognition model.

The following will illustrate some setting methods of the second object with examples.

In one embodiment, before the above-mentioned step 101 receives the target video, the video processing method may further include:

Display the setting interface, the setting interface includes P file identifiers, one file identifier indicates an image file, and P is a positive integer;

In the case of receiving selection input for Q file identifiers, identify Q image files indicated by the Q file identifiers to obtain a second object, where Q is a positive integer less than or equal to P.

Generally speaking, image files such as pictures or videos may be pre-stored in the electronic device. For example, these image files may be obtained by shooting the second object through a camera, or may also be pictures or videos including the second object sent by other terminals.

In the setting interface, P file identifiers may be displayed, and the P file identifiers may correspond to P image files.

Specifically, in the setting interface, the thumbnails of multiple image files may be displayed in a matrix manner, and the user may drag the interface up and down to switch and display the thumbnails of the image files.

Alternatively, in the setting interface, the image identifier of an image file may also be displayed separately, such as a video screenshot, and the user may drag the interface left and right to switch and display the image identifier of the image file.

The above-mentioned thumbnails or image identifiers can all be considered as file identifiers of image files. For these file identifiers, the user can make optional input.

For example, the user can click on the file identifier to select the file identifier; or, the user can also drag the file identifier to a preset display area to select the file identifier.

Of course, in practical applications, the selection and input of the file identifiers may not be limited to the methods in the above examples, and specific input methods may be set according to actual needs, which will not be listed here.

It is easy to understand that, to a certain extent, the selection operation of the file identifier can be regarded as the selection operation of the image file associated with the file identifier. Correspondingly, the electronic device can identify the selected image files, that is, the Q image files indicated by the above Q file identifiers, to obtain the second object.

It can be seen that in this embodiment, by displaying a setting interface including P file identifiers, it is convenient for the user to select an image file for obtaining the second object, and the operation efficiency is improved.

In an example, the number of second objects obtained by identifying the above Q image files may be one or multiple.

For example, when the user correspondingly selects a picture including person X and a picture including person Y during the process of selecting and inputting the file identifier, the recognized second object may include person X and person Y at the same time.

The setting process of the second object will be described below in conjunction with some application scenarios.

As shown in FIG. 7 , when the desktop or the running interface of the application is displayed on the electronic device, a floating ball called "Material Library" (marked as F in the figure) can be displayed on the interface. After receiving the input of the hovering ball, a material library interface may be displayed, and in the material library interface, existing materials for obtaining the second object, such as pictures or videos, may be included. In the material library interface, users can swipe left and right to switch and view existing materials.

As shown in FIG. 8, FIG. 8 is an example diagram of the material library interface. In this example figure, the material library interface may also include a button control named "Upload" (marked as B1 in the figure). After receiving an input for the "upload" button control, thumbnails of pictures or videos in the album may be displayed in a preset display area (marked as R in the figure). The material library interface at this time can be regarded as the above-mentioned setting interface.

As shown in FIG. 8 , the material library interface may also include a button control named "Binding" (marked as B2 in the figure). After the user selects the thumbnail of the picture or video in the album, he can further click the "Bind" button control to add the picture or video corresponding to the selected thumbnail to the material library.

The materials in the material library can also be used for recognition to obtain the second object.

As shown in the above embodiments, there may be a preset association relationship between the chat group and the second object. Correspondingly, the preset association relationship may be obtained by setting in a related setting interface.

Correspondingly, as a modification example of the previous embodiment, in this embodiment, before the above step 101, before receiving the target video sent by the target chat partner, the video processing method may further include:

The display setting interface includes P file identifications in the setting interface, and a file identification indicates an image file, and P is a positive integer;

In the case of receiving user selection input on Q file identifiers, at least one candidate chat group option is displayed, where Q is a positive integer less than or equal to P;

In the case of receiving a user's selection input of a target chat group option in at least one candidate chat group option, identifying a second object in the Q image files indicated by the Q file identifiers;

The second object in the Q image files is stored in association with the target chat group corresponding to the target chat group option.

In this implementation manner, the specific content and display manner in the setting interface may be consistent with the previous implementation manner, and will not be repeated here for simplicity of description.

After receiving the user's selection input of the Q file identifiers, the electronic device may display at least one candidate chat group option, and the candidate chat group option may include group information of the candidate chat group.

For example, the candidate chat group may be an existing chat group in a social application. For a candidate chat group, there may generally be group information such as a chat group name, a chat group image identifier, or a corresponding number of the chat group. The above-mentioned candidate chat group options may be specifically displayed as the chat group name, chat group image logo or number, etc. of the candidate chat group, which may not be specifically limited here.

When the selection input of Q file identifiers is received, a pop-up window may be displayed, or a selection page may be switched and displayed.

For example, as shown in Figure 9, when a pop-up window is displayed, candidate chat groups such as "X school class one discussion group", "Y company meeting group" and "Z family life group" can be displayed in the pop-up window The name of the chat group, or further display the chat group image logo formed by the combination of group member image thumbnails in front of each chat group name. These chat group names or chat group image identifiers may correspond to the aforementioned candidate chat group options.

If the user needs to identify the video containing the second object in the "discussion group of class 1 of X school", the user can click and input the name of the chat group of "discussion group of class 1 of X school". At this point, the user's click input of the chat group name "X School Class 1 Discussion Group" can be regarded as the selection input of the target chat group option.

When receiving the selection input of the target chat group option, the electronic device can identify the Q image files indicated by the Q file identifiers, and obtain the second object therein. The specific manner of identifying the image file to obtain the second object has been described in detail in the above embodiments, and will not be repeated here.

The electronic device may associate and store the second object in the Q image files and the target chat group corresponding to the target chat group option.

For example, the electronic device identifies Q image files selected by the user to obtain a second object, and associates and stores the second object with the "discussion group of Class 1 of X school". In the subsequent use process, if the electronic device receives the target video sent to the chat group corresponding to "X School Class One Discussion Group", the electronic device can identify the first object in the target video; Content, determining the second object associated with the "discussion group of Class 1 of X school"; and displaying the first identifier when the first object matches the second object.

In this embodiment, the display setting interface, in the case of receiving the user's selection input of Q file identifiers, displays at least one candidate chat group option; The selection input of the group option identifies the second object in the Q image files indicated by the Q file identifiers, and associates and stores the second object with the target chat group corresponding to the target chat group option. This implementation manner helps the user to quickly set the association relationship between the second object and the target chat group.

In one example, during the process of switching from the interface shown in FIG. 8 to the interface shown in FIG. 9 , the user may need to perform more input processes.

For example, after receiving the user's input on the "binding" button control shown in FIG. 8 , the electronic device may switch to display the application selection interface as shown in FIG. 10 .

In the application selection interface, icons of multiple application programs and their application names may be displayed. For example, the application names may be "Application A", "Application B", and "Application C".

If the user's click input on "application program B" is received, a function selection interface as shown in FIG. 11 may be further displayed. For example, in the function selection interface, options such as "select group", "share to Moments", and "favorite" may be included.

After receiving the user's option of "select group", it can switch to the interface shown in FIG. 9 .

Based on the above operation process, on the one hand, the user can associate corresponding second objects with different groups in different application programs; on the other hand, it can also satisfy the user's different usage needs for the selected image files.

Define the setting interface used to display the above P file identifiers as the first setting interface. In order to facilitate the user to manage the second object that has been set, in one embodiment, the first setting interface also includes a first operation control;

Correspondingly, after the first setting interface is displayed, the video processing method may further include:

In the case of receiving the sixth input to the first operation control, in response to the sixth input, a second setting interface is displayed, the second setting interface includes the group information of the target chat group, the information associated with the target chat group A file identification of the image file and at least one second operation control;

In the case of receiving a seventh input to any second operation control, in response to the seventh input, the association between the group information of the target chat group and the image file is updated.

The specific implementation process of this embodiment will be described below with an example.

As shown in FIG. 8 , in the interface shown in FIG. 8 , the first operation control may correspond to a button control named "association" (marked as B3 in the figure). After receiving the click input on the "association" button control, the interface shown in FIG. 12 can be switched and displayed.

As shown in FIG. 12, FIG. 12 can be regarded as an example diagram of the second setting interface. On the second setting interface, group information of the target chat group can be displayed.

In general, the target chat group may refer to the chat group associated with the second object. In combination with the description of the above embodiments, the association relationship between the target chat group and the second object may be embodied as the association relationship between the group information of the target chat group and the second object.

As shown in Figure 12, in the second setting interface, the group information of the target chat group may include the chat group name (marked as TN in the figure) and chat group image identification (marked as TP in the figure) . Wherein, the chat group name may be "group 1", "group 2" and "group 3" and so on; and the chat group image logo may be a group avatar of the chat group.

In general, the second object can be obtained by identifying the selected image file. There is an association relationship between the target chat group and the second object, therefore, the target chat group is also associated with the image file. As shown in FIG. 12 , the file identifier (marked as RP in the figure) of the image file associated with the target chat group may be displayed under the group information of the target chat group. For example, the file identifier may be a thumbnail of an image file or the like.

In addition, for each file identifier, at least one second operation control (marked as K in the figure) may be associated and displayed. For example, as shown in FIG. 12 , the second operation control includes an operation control named "Modify" and an operation control named "Delete".

Taking some examples of application scenarios, "group 1" is associated with an image file A. When the input to the "modify" operation control displayed behind the file identification of image file A is received, the thumbnails of P image files, or the thumbnails of the materials in the above-mentioned material library, can be displayed for the user to select . After the user selects the thumbnail of image file B, the association between image file A and "group 1" can be canceled, and the association between image file B and "group 1" can be established.

When an input to the "delete" operation control displayed behind the file identification of image file A is received, the association between image file A and "group 1" can be canceled.

It can be seen that by displaying the second setting interface, the user's requirement for modifying the association between the existing group information of the target chat group and the image file can be satisfied, and the operation convenience can be improved.

The following describes the video processing method provided by the embodiment of the present application in conjunction with a specific application example.

As shown in Figure 13, in this specific application example, the video processing method may include:

Step 1301, establishing an association between the material for matching the video and the social software group;

Users can upload materials for video matching and assign materials to specific social software groups.

The video here may refer to a video received through social software. The materials used for video matching can be videos or pictures selected by the user on the setting interface, and these selected videos or pictures can be uploaded to a preset material library.

In addition, these materials can establish specified relationships with specific social software groups. For example, in practical applications, through the setting of the specified relationship, it is possible to match person A to a video sent to one group, and match person B to a video sent to another group, and so on.

Step 1302, the group receives video resources, and checks whether there is a material database resource matching; if yes, execute step 1303; if not, end;

Generally speaking, a video resource may include a first object such as a character or an item, and similarly, a material library resource may also include a second object such as a character or an item.

Check whether there is a material library resource match, which may refer to whether the first object in the video resource matches the second object in the material library resource.

Step 1303, perform intelligent matching according to the uploaded material, and the matched content can remind the user;

That is, when the first object in the target video matches the preset second object, a first identifier is displayed, and the first identifier may be in the form of "@user" or in the form of a matching degree value.

Step 1304, automatically cache the extracted video into the floating ball, and sort according to certain rules;

In other words, when it is determined that the target video is a video matched by the second object, the target video may be cached, and a thumbnail of the target video may be displayed in the floating ball, or after receiving an input to the floating ball , loads a window to display the thumbnail of the target video.

In addition, as shown above, there may be a matching relationship between the target video and the second object, and the thumbnails of the target videos may be sorted and displayed according to the matching relationship, so that the user can find the target with a high degree of interest more quickly video.

Of course, in practical applications, the thumbnails of the target videos may also be sorted and displayed according to rules such as the time sequence in which the target videos are received.

Step 1305, judging whether the user has performed positive operations such as saving and forwarding the video in the floating ball, if so, go to step 1306; if not, go to step 1307;

The user inputs the thumbnail of the video in the floating ball, which can cause the electronic device to perform corresponding processing on the corresponding video resource.

For example, a user may long press a thumbnail of a video, and in response to the user's long press input, a control for saving the video and a control for forwarding the video may be displayed. After receiving the user's input on these controls, the video can be saved and forwarded accordingly.

Saving and forwarding the video can be considered as a positive operation of the user. To a certain extent, it can be considered that the user is really interested in the video in the floating ball. Conversely, the user may also perform deletion operations on the video, and these operations may correspond to reverse operations of the user.

Step 1306, in response to the forward operation, perform operations such as saving or forwarding the video, and at the same time release the cache resources occupied by the video in the floating ball.

Step 1307, in response to the delete operation, the video is discarded, and the cache resources occupied by the video in the floating ball are released.

Combining the above application scenarios, it can be seen that based on the video processing method provided by the embodiment of the present application, when the user uploads material resources, the electronic device can automatically perform video resource matching algorithm tasks in the background. The matched video reminds the user, allowing the user to choose a reference. In addition, the matched video can be cached in the floating team queue, which is convenient for users to perform quick operations. Users can quickly save, forward and other operations to save users time and allow users to focus more on the content they care about. In terms of presentation, users can be notified not only of the most relevant matching matches, but also tell users a matching priority level through the matching degree ratio, give users more detailed reference opinions, and make user decisions more accurate. It is more informative.

It should be noted that, the video processing method provided in the embodiment of the present application may be executed by a video processing device, or a control module in the video processing device for executing the video processing method. In the embodiment of the present application, the video processing device provided in the embodiment of the present application is described by taking the video processing device executing the video processing method as an example.

As shown in Figure 14, the video processing device 1400 provided in the embodiment of the present application includes:

The receiving module 1401 is used to receive the target video sent by the target chat object;

The first display module 1402 is configured to display a first identification when the first object in the target video matches a preset second object, and the first identification is used to indicate that the target video includes the second object.

Optionally, the target chat object is an object in the target chat group;

Correspondingly, the video processing device 1400 may also include:

The first obtaining module is used to obtain a preset second object associated with the target chat group;

A comparison module, configured to compare the similarity between the first object and the second object;

A determining module, configured to determine that the first object matches the second object when the similarity between the first object and the second object is greater than a similarity threshold.

Optionally, the video processing device 1400 may also include:

The second obtaining module is used to obtain the matching degree between the first object in the target video and the preset second object; wherein, the matching degree is used to indicate the similarity between the first object and the second object, or the matching degree is used for Indicate the proportion of the target image frame in the target video, where the target image frame is an image frame including a first object, and the similarity between the first object and the second object is greater than a similarity threshold;

The second display module is configured to display a second identification, and the second identification is used to indicate the matching degree between the first object and the second object in the target video.

Optionally, the video processing device 1400 may also include:

The third display module is configured to display a target window when the first object in the target video matches the preset second object, and the target window includes a thumbnail of the target video.

Optionally, the thumbnail of the target video includes a third identifier, and the third identifier is used to indicate a matching degree between the first object and the second object in the target video.

Correspondingly, the video processing device 1400 may further include at least one of the following:

Playing module, for receiving the user's first input to the thumbnail of the target video in the target window, in response to the first input, play the target video;

The first storage module is used to store the target video in response to the second input in the case of receiving the second input of the user to the thumbnail of the target video in the target window;

The forwarding module is used to forward the target video in response to the third input in response to the third input of the thumbnail of the target video in the target window when the user is received;

A deletion module, configured to delete the target video in response to the fourth input in response to the fourth input from the user on the thumbnail of the target video in the target window.

Correspondingly, the video processing device 1400 may also include:

The training module is used to train the recognition model by using the target video as a training sample in response to the fifth input when receiving the fifth input from the user to the target video;

Wherein, the fifth input is used for storing or forwarding the target video.

Optionally, the video processing device 1400 may also include:

The fourth display module is used to display the setting interface, the setting interface includes P file identifiers, one file identifier indicates an image file, and P is a positive integer;

The fifth display module is used to display at least one candidate chat group option when receiving the user's selection input of Q file identifiers, where Q is a positive integer less than or equal to P;

The identification module is used to identify the second object in the Q image files indicated by the Q file identifiers when receiving the user's selection input of the target chat group option in at least one candidate chat group option;

The second storage module is used for associating and storing the second object in the Q image files and the target chat group corresponding to the target chat group option.

The video processing device provided in the embodiment of the present application receives the target video sent by the target chat object, and displays a message indicating that the target video includes the second object in the case of the first object in the target video and the preset second object. The first logo helps users to quickly find the video they are interested in. In addition, in the case of the first object in the target video and the preset second object, a second identification for indicating the matching degree between the first object and the second object in the target video may also be displayed, which is for the user Provide a basis for selecting the target video for priority viewing. Through the target window, the thumbnail of the target video is displayed, which can facilitate the user to perform quick operations on the target video, and effectively improve the user experience.

The video processing device in this embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a handheld computer, a vehicle electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant). assistant, PDA), etc., non-mobile electronic devices can be servers, network attached storage (Network Attached Storage, NAS), personal computer (personal computer, PC), television (television, TV), teller machine or self-service machine, etc., this application Examples are not specifically limited.

The video processing device in this embodiment of the present application may be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in this embodiment of the present application.

The video processing device provided in the embodiment of the present application can implement various processes implemented by the method embodiments in FIG. 1 to FIG. 13 , and details are not repeated here to avoid repetition.

The embodiment of the present application also provides an electronic device, which is used to execute each process of the above video processing method embodiment, and can achieve the same technical effect. To avoid repetition, details are not repeated here.

Optionally, as shown in FIG. 15 , the embodiment of the present application also provides an electronic device 1500, including a processor 1501, a memory 1502, and a program or instruction stored in the memory 1502 and operable on the processor 1501. The program Or, when the instruction is executed by the processor 1501, each process of the above-mentioned video processing method embodiment can be realized, and the same technical effect can be achieved. To avoid repetition, details are not repeated here.

It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

FIG. 16 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.

The electronic device 1600 includes, but is not limited to: a radio frequency unit 1601, a network module 1602, an audio output unit 1603, an input unit 1604, a sensor 1605, a display unit 1606, a user input unit 1607, an interface unit 1608, a memory 1609, and a processor 1610, etc. part.

Those skilled in the art can understand that the electronic device 1600 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 1610 through the power management system, so that the management of charging, discharging, and function can be realized through the power management system. Consumption management and other functions. The structure of the electronic device shown in FIG. 16 does not constitute a limitation to the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine some components, or arrange different components, which will not be repeated here. .

Wherein, the radio frequency unit 1601 is used to receive the target video sent by the target chat object;

The display unit 1606 is configured to display a first identification when the first object in the target video matches a preset second object, where the first identification is used to indicate that the target video includes the second object.

The electronic device provided in the embodiment of the present application receives the target video sent by the target chat object, and displays the second object that can be used to indicate that the target video includes the second object when the first object in the target video matches the preset second object. a logo. In this embodiment of the present application, the second object may be the content of interest preset by the user. By displaying the first logo on the target video that matches the second object, it is helpful for the user to efficiently obtain the video with the content of interest.

Optionally, the target chat object is an object in the target chat group;

Correspondingly, the processor 1610 may be configured to acquire a preset second object associated with the target chat group;

Comparing the similarity between the first object and the second object;

Optionally, the processor 1610 may be configured to acquire a degree of matching between the first object in the target video and a preset second object; wherein, the degree of matching is used to indicate the degree of similarity between the first object and the second object, or, the degree of matching The degree is used to indicate the proportion of the target image frame in the target video, the target image frame is an image frame including the first object, and the similarity between the first object and the second object is greater than the similarity threshold;

The display unit 1606 may be configured to display a second identifier, where the second identifier is used to indicate a matching degree between the first object and the second object in the target video.

Optionally, the display unit 1606 may also be configured to display a target window when the first object in the target video matches a preset second object, and the target window includes a thumbnail of the target video. .

Optionally, the processor 1610 may be used for at least one of the following:

Correspondingly, the processor 1610 may be configured to, in the case of receiving a fifth input from the user on the target video, respond to the fifth input, and use the target video as a training sample to train the recognition model;

Wherein, the fifth input is used for storing or forwarding the target video.

Optionally, the display unit 1606 is also used to display a setting interface, the setting interface includes P file identifiers, one file identifier indicates an image file, and P is a positive integer;

Correspondingly, the processor 1610 may be configured to identify the second one of the Q image files indicated by the Q file identifiers in the case of receiving the user's selection input of the target chat group option in at least one candidate chat group option. object;

It should be understood that, in this embodiment of the present application, the input unit 1604 may include a graphics processor (Graphics Processing Unit, GPU) 16041 and a microphone 16042, and the graphics processor 16041 is used for the image capture device ( Such as the image data of the still picture or video obtained by the camera) for processing. The display unit 1606 may include a display panel 16061, and the display panel 16061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1607 includes a touch panel 16071 and other input devices 16072 . Touch panel 16071, also called touch screen. The touch panel 16071 may include two parts: a touch detection device and a touch controller. Other input devices 16072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here. Memory 1609 can be used to store software programs as well as various data, including but not limited to application programs and operating systems. The processor 1610 may integrate an application processor and a modem processor, wherein the application processor mainly processes operating systems, user interfaces, and application programs, and the modem processor mainly processes wireless communications. It can be understood that the foregoing modem processor may not be integrated into the processor 1610 .

The embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, each process of the above video processing method embodiment is realized, and the same technology can be achieved. Effect, in order to avoid repetition, will not repeat them here.

Wherein, the processor is the processor in the electronic device in the foregoing embodiments. Readable storage medium, including computer readable storage medium, such as computer read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc. non-transitory computer readable storage medium.

The embodiment of the present application also provides a computer program product, the computer program product can be executed by a processor to implement the various processes of the above video processing method embodiment, and can achieve the same technical effect, in order to avoid repetition, it will not be repeated here .

The embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above video processing method embodiments, and can achieve the same Technical effects, in order to avoid repetition, will not be repeated here.

It should be understood that the chips mentioned in the embodiments of the present application may also be called system-on-chip, system-on-chip, system-on-a-chip, or system-on-a-chip.

It should be noted that, in this document, the term "comprising", "comprising" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation. Based on such an understanding, the technical solution of the present application can be embodied in the form of computer software products, which are stored in a storage medium (such as ROM/RAM, magnetic disk, etc.) , optical disc), including several instructions to enable a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present application.

The embodiments of the present application have been described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementations. The above-mentioned specific implementations are only illustrative and not restrictive. Those of ordinary skill in the art will Under the inspiration of this application, without departing from the purpose of this application and the scope of protection of the claims, many forms can also be made, all of which belong to the protection of this application.

Claims

A video processing method, comprising:

Receive the target video sent by the target chat partner;

If the first object in the target video matches the preset second object, a first identification is displayed, where the first identification is used to indicate that the target video includes the second object.
The method according to claim 1, wherein the target chat object is an object in a target chat group;

After receiving the target video sent by the target chat object, the method also includes:

Acquiring a preset second object associated with the target chat group;

performing a similarity comparison between the first object and the second object;

If the similarity between the first object and the second object is greater than a similarity threshold, it is determined that the first object matches the second object.
The method according to claim 1, wherein, after receiving the target video sent by the target chat object, the method further comprises:

Obtain the matching degree between the first object in the target video and the preset second object; the matching degree is used to indicate the similarity between the first object and the second object, or, the matching degree is used To indicate the proportion of a target image frame in the target video, the target image frame is an image frame including a first object, and the similarity between the first object and the second object is greater than a similarity threshold;

Displaying a second identifier, where the second identifier is used to indicate a matching degree between the first object and the second object in the target video.
The method according to claim 1, wherein, after receiving the target video sent by the target chat object, the method further comprises:

If the first object in the target video matches the preset second object, a target window is displayed, and the target window includes a thumbnail of the target video.
The method according to claim 4, wherein the thumbnail of the target video includes a third mark, and the third mark is used to indicate a degree of matching between the first object and the second object in the target video.
The method according to claim 4, wherein after the target window is displayed, the method further comprises at least one of the following:

In the case of receiving a user's first input to the thumbnail of the target video in the target window, playing the target video in response to the first input;

storing the target video in response to receiving a second user input of a thumbnail of the target video in the target window in response to the second input;

In case a third input of the thumbnail of the target video in the target window by the user is received, forwarding the target video in response to the third input;

In case a fourth user input on the thumbnail of the target video in the target window is received, the target video is deleted in response to the fourth input.
The method according to claim 1, wherein the first object in the target video is obtained by using a preset recognition model to identify the target video;

After the display of the first logo, the method further includes:

In the case of receiving a fifth input from the user to the target video, in response to the fifth input, using the target video as a training sample to train the recognition model;

The fifth input is used for storing or forwarding the target video.
The method according to claim 1, wherein, before receiving the target video sent by the target chat object, the method further comprises:

Displaying a setting interface, the setting interface includes P file identifiers, one file identifier indicates an image file, and P is a positive integer;

In the case of receiving the user's selection input of Q said file identifiers, at least one candidate chat group option is displayed, where Q is a positive integer less than or equal to P;

In the case of receiving the user's selection input of the target chat group option in the at least one candidate chat group option, identifying the second object in the Q image files indicated by the Q file identifiers;

The second object in the Q image files is stored in association with the target chat group corresponding to the target chat group option.
A video processing device, comprising:

The receiving module is used to receive the target video sent by the target chat object;

The first display module is configured to display a first identification when the first object in the target video matches a preset second object, and the first identification is used to indicate that the target video includes the first object. Two objects.
The device according to claim 9, wherein the target chat object is an object in a target chat group;

The device also includes:

A first acquiring module, configured to acquire a preset second object associated with the target chat group;

A comparison module, configured to perform a similarity comparison between the first object and the second object;

A determining module, configured to determine that the first object matches the second object when the similarity between the first object and the second object is greater than a similarity threshold.
The apparatus of claim 9, further comprising:

The second obtaining module is used to obtain the matching degree between the first object in the target video and the preset second object; the matching degree is used to indicate the similarity between the first object and the second object, Alternatively, the matching degree is used to indicate the proportion of the target image frame in the target video, the target image frame is an image frame including the first object, and the similarity between the first object and the second object The degree is greater than the similarity threshold;

The second display module is configured to display a second identification, and the second identification is used to indicate the matching degree between the first object and the second object in the target video.
The apparatus of claim 9, further comprising:

A third display module, configured to display a target window when the first object in the target video matches a preset second object, where the target window includes a thumbnail of the target video.
The device according to claim 12, wherein the thumbnail of the target video includes a third identifier, and the third identifier is used to indicate a degree of matching between the first object and the second object in the target video.
The apparatus of claim 12, further comprising at least one of the following:

A playing module, configured to play the target video in response to the first input in response to the first input from the user on the thumbnail of the target video in the target window;

A first storage module, configured to store the target video in response to the second input in response to receiving a second input from the user on the thumbnail of the target video in the target window;

A forwarding module, configured to forward the target video in response to the third input in response to receiving a third input from the user on the thumbnail of the target video in the target window;

A deletion module, configured to delete the target video in response to the fourth input in response to the fourth input from the user on the thumbnail of the target video in the target window.
The device according to claim 9, wherein the first object in the target video is obtained by using a preset recognition model to identify the target video;

The device also includes:

A training module, configured to use the target video as a training sample to train the recognition model in response to the fifth input when receiving the fifth input from the user to the target video;

The fifth input is used for storing or forwarding the target video.
The apparatus of claim 9, further comprising:

The fourth display module is used to display a setting interface, the setting interface includes P file identifiers, one file identifier indicates an image file, and P is a positive integer;

The fifth display module is used to display at least one candidate chat group option when receiving the user's selection input of Q said file identifiers, where Q is a positive integer less than or equal to P;

An identifying module, configured to identify the second one of the Q image files indicated by the Q file identifiers in the case of receiving the user's selection input of the target chat group option in the at least one candidate chat group option. object;

The second storage module is configured to associate and store the second object in the Q image files with the target chat group corresponding to the target chat group option.
An electronic device, comprising a processor, a memory, and a program or instruction stored in the memory and operable on the processor, when the program or instruction is executed by the processor, claims 1-8 are realized The step of the video processing method described in any one.
An electronic device, configured to execute the steps of the video processing method according to any one of claims 1-8.
A readable storage medium storing programs or instructions on the readable storage medium, and implementing the steps of the video processing method according to any one of claims 1-8 when the programs or instructions are executed by a processor.
A computer program product, the computer program product can be executed by a processor to implement the steps of the video processing method according to any one of claims 1-8.
A chip, the chip includes a processor and a communication interface, the provided communication interface is coupled to the provided processor, and the provided processor is used to run programs or instructions to realize the video as described in any one of claims 1-8 The steps of the processing method.