WO2023082569A1

WO2023082569A1 - Video information extraction method and apparatus

Info

Publication number: WO2023082569A1
Application number: PCT/CN2022/091812
Authority: WO
Inventors: 黄劲文
Original assignee: 北京达佳互联信息技术有限公司
Priority date: 2021-11-11
Filing date: 2022-05-09
Publication date: 2023-05-19
Also published as: CN114189719B; CN114189719A

Abstract

The present disclosure belongs to the technical field of video processing, and discloses a video information extraction method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring information of a target user account, wherein the target user account is a live streaming room user account of a live streaming room corresponding to a live stream video (S101); according to the information of the target user account, determining an activation value of the target user account in the live streaming room corresponding to the live stream video (S102); and according to the activation value, extracting target video information from the live stream video (S103).

Description

Video information extraction method and device

Cross References to Related Applications

This application is based on a Chinese patent application with application number 202111334747.7 and a filing date of November 11, 2021, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated by reference into this application.

technical field

The present disclosure relates to the technical field of video processing, and in particular to a video information extraction method, device, electronic equipment and storage medium.

Background technique

With the development of software and hardware technology of smart terminals, more and more user accounts share their daily life through live broadcast or short video, and the functions of live broadcast software are becoming more and more perfect. It is easy to miss the exciting content of the live broadcast.

In the related art, the content of the live video is processed by monitoring the gesture similarity of the characters in the live video and the proportion of the human face in the frame.

In this way, effective information in the live video cannot be accurately extracted, which affects the extraction effect of effective video information.

Contents of the invention

The disclosure provides a video information extraction method, device, electronic equipment and storage medium.

According to the first aspect of the embodiments of the present disclosure, there is provided a method for extracting video information, including acquiring information of a target user account, where the target user account is the live room user account of the live room corresponding to the live video; according to the information of the target user account, determine The activity value of the target user account in the live broadcast room corresponding to the live video; according to the activity value, the target video information is extracted from the live video.

In some embodiments of the present disclosure, the step of extracting the target video information from the live video according to the liveness value includes:

In response to the variation of the activity value being greater than or equal to a preset increase threshold, extracting target video information from the live video according to a preset strategy;

In response to the variation of the activity value being less than the preset increase threshold, the step of determining the activity value of the target user account in the live broadcast room corresponding to the live video is re-executed.

In some embodiments of the present disclosure, the step of extracting the target video information from the live video according to a preset policy includes:

Get the current video frame, which corresponds to the current time point;

Determine the target video frame according to the preset strategy and activity value, and the target time point corresponding to the target video frame is after the current time point;

According to the current video frame and the target video frame, the target video information is extracted from the live video.

In some embodiments of the present disclosure, the step of extracting the target video information from the live video according to the current video frame and the target video frame includes:

A video segment is intercepted from a live video, and the video segment is used as target video information, wherein the video segment includes a start frame and an end frame, the start frame is a current video frame, and the end frame is a target video frame.

Extract a plurality of candidate video frames from the live video, and the time points corresponding to the candidate video frames are between the current time point and the target time point;

Part of video frames are selected from the current video frame, multiple candidate video frames, and target video frames as target video information.

In some embodiments of the present disclosure, the step of determining the target video frame according to the preset policy and activity value includes:

Continuously monitor the change of the activity value to obtain the information of the activity change;

In response to the activity change information meeting the set condition, capture the corresponding time point as the target time point;

The video frame corresponding to the target time point in the live room corresponding to the live video is used as the target video frame.

In some embodiments of the present disclosure, according to the information of the target user account, the step of determining the activity value of the target user account in the live room corresponding to the live video includes:

Determine the target user account group where the target user account is located according to the information of the target user account;

The reference activity value corresponding to the target user account group is used as the activity value of the target user account in the live broadcast room corresponding to the live video.

In some embodiments of the present disclosure, the target user account group includes multiple user accounts, and the method further includes:

Obtain multiple live interactive information corresponding to multiple user accounts;

Determining a plurality of candidate activity values respectively corresponding to the plurality of user accounts according to the plurality of live broadcast interaction information;

According to the plurality of candidate activity values, a reference activity value corresponding to the target user account group is determined.

In some embodiments of the present disclosure, some video frames are selected from the current video frame, multiple candidate video frames, and target video frames as target video information, including:

Determine the target activity value of each video frame at the corresponding time point. The target activity value is the activity value of the target user account in the live broadcast room corresponding to the live video at the corresponding time point. The video frame is the current video frame or a candidate video frame , or the target video frame;

Sorting each video frame according to the descending order of each target activity value;

A preset number of video frames sorted before are selected as target video information.

According to the second aspect of the embodiments of the present disclosure, there is provided a device for extracting video information, including an acquisition module configured to acquire information of a target user account, where the target user account is the live room user account of the live room corresponding to the live video; a determination module is configured to determine the activity value of the target user account in the live broadcast room corresponding to the live video according to the information of the target user account; the extraction module is configured to extract the target video information from the live video according to the activity value.

In some embodiments of the present disclosure, the extraction module is configured to:

Get the current video frame, which corresponds to the current time point;

In some embodiments of the present disclosure, the determination module includes:

The first determination sub-module is configured to determine the target user account group where the target user account is located according to the information of the target user account, and use the reference activity value corresponding to the target user account group as the live video corresponding to the target user account activity value between.

In some embodiments of the present disclosure, the target user account group includes multiple user accounts, and the determining module further includes:

The obtaining sub-module is configured to obtain a plurality of live interactive information corresponding to a plurality of user accounts;

The second determining submodule is configured to determine a plurality of candidate activity values respectively corresponding to a plurality of user accounts according to a plurality of live interaction information;

The third determination submodule is configured to determine a reference activity value corresponding to the target user account group according to the plurality of candidate activity values.

In some embodiments of the present disclosure, the extraction module is used for:

According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement Video information extraction method as described above.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a non-volatile computer-readable storage medium. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute Video information extraction method as described above.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, including a computer program, when the computer program is executed by a processor, the method for extracting video information as described above is implemented.

By obtaining the information of the target user account, the target user account is the user account of the live broadcast room corresponding to the live video, and according to the information of the target user account, determine the activity value of the target user account in the live room corresponding to the live video, according to the activity Value, to extract the target video information from the live video. This method effectively enhances the efficiency of video information extraction. Since the activity of the target user account is detected and quantified, the value representing the activity of the target user account is obtained, and the target video information is extracted according to the activity value, which can automatically obtain the live broadcast. Effective video information in the video improves the extraction effect of effective video information.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings here are incorporated into the specification and constitute a part of the specification, show embodiments consistent with the disclosure, and are used together with the description to explain the principle of the disclosure, and do not constitute an improper limitation of the disclosure.

Fig. 1 is a flowchart of a method for extracting video information according to an exemplary embodiment.

Fig. 2 is a flowchart of a method for extracting video information according to another exemplary embodiment.

Fig. 3 is a flow chart showing target video information selection according to another exemplary embodiment.

Fig. 4 is a flow chart showing target video information selection according to another exemplary embodiment.

Fig. 5 is a flow chart showing a method for extracting video information according to another exemplary embodiment.

Fig. 6 is a block diagram of an apparatus for extracting video information according to an exemplary embodiment.

Fig. 7 is a block diagram of an apparatus for extracting video information according to another exemplary embodiment.

Fig. 8 is a block diagram of an electronic device according to an exemplary embodiment.

Detailed ways

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.

It should be noted that the terms "first" and "second" in the description and claims of the present disclosure and the above drawings are used to distinguish similar user accounts, and not necessarily used to describe a specific order or sequence . It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

Embodiments of the present disclosure are described by taking a video information extraction method configured in a video information extraction device as an example.

The video information extraction method in the embodiment of the present disclosure may be configured in a video information extraction device, and the video information extraction device may be set in a server.

It should be noted that the execution subject of the embodiments of the present disclosure may be, for example, a central processing unit (Central Processing Unit, CPU) of the server in terms of hardware, and may be, for example, a related background service of the server in terms of software.

As shown in FIG. 1 , the method for extracting video information includes the following steps S101 to S103.

In step S101, information of a target user account is obtained, and the target user account is a live room user account of a live room corresponding to a live video.

It should be noted that the acquisition of user account information and related information of the user account described in the embodiments of the present disclosure, including social relationship identity information, has been approved by the user account. , the methods, devices, devices, and storage media involved in the present disclosure can acquire information related to user accounts.

In the embodiment of the present disclosure, the target user account may be the user account of the live broadcast room corresponding to the live video. The user account for watching the live video in the live broadcast room is regarded as the user account of the live broadcast room, and the user account of the live room to which target video information is currently to be provided may be called the target user account.

For example, after the user account clicks to open the live broadcast room and watch the live broadcast content, the application can obtain information such as the viewing record and interaction status of the live broadcast room of the user account within the scope allowed by the user account, and through mathematical models such as big data models, The identity information of the current user account, viewing habit information, live interaction habit information, etc. are analyzed and obtained as the information of the target user account.

In step S102, the activity value of the target user account in the live broadcast room corresponding to the live video is determined according to the information of the target user account.

Among them, the activity value can be used to describe the activity related to the target user account, the activity can be the activity of the target user account itself in the live broadcast room, or the activity of other user accounts related to the target user account in the live broadcast room situation etc.

In the embodiment of the present disclosure, the activity value of the target user account in the live broadcast room of the live video may be the real-time activity representing the current time node, or it may be the live video recording during the live broadcast. According to the recording result and the target The user account information determines the activity value, or it can also be determined based on the number of current target user accounts in the live broadcast room, or based on the interaction frequency of the target user accounts in the live broadcast room, such as the number of bullet screens, the number and value of gifts etc., to calculate the activity value, it may also be to calculate the information of the target user account through a corresponding activity algorithm, so as to obtain the activity value of the target user account in the live broadcast room of the live video.

For example, after obtaining the information of multiple target user accounts in the live broadcast room, according to the number of user accounts, combined with the current number of barrage, gift quantity, and gift value in the live broadcast room, it can also be combined with the host's body movements and expressions, etc. Calculate the current activity value through the activity value calculation model.

In step S103, the target video information is extracted from the live video according to the liveness value.

In the embodiment of the present disclosure, the video information may be selected in real time according to the activity value of the target user account during the live broadcast process to extract, or the target activity value may be recorded, and the corresponding video information in the recorded video of the live broadcast Information is extracted.

Wherein, the target video information may be a live video segment within a certain period of time extracted according to the activity value, or may be one or more video frames included in the live video segment.

In the embodiment of the present disclosure, it is possible to detect the change of the activity value, for example, the activity value in the live broadcast room of a live video at a certain time node has increased significantly, etc., and the target video information can be determined according to this change, and the activity value can also be set. degree threshold, and extract the target video information by comparing the activity value with the threshold value.

In some embodiments, in response to the change in the activity value being greater than or equal to the preset increase threshold, the target video information is extracted from the live video according to a preset strategy, and in response to the change in the activity value being less than the preset increase Threshold value, re-execute the step of determining the activity value of the target user account in the live broadcast room corresponding to the live video, and determine the target video information by comparing the activity value with the set threshold value, the set threshold value can be determined and The liveness value corresponds to the activeness threshold value of the live video containing valid video information at the point in time, so that when the change in the liveness value is greater than or equal to the set threshold, according to the preset strategy, the live video Extracting the target video information can effectively help improve the accuracy and rationality of video information extraction, and ensure the timeliness of video information extraction based on the activity value. Execution determines the activity value of the target user account in the live broadcast room of the live video, thereby effectively avoiding the omission of valid video information and ensuring the integrity and accuracy of effective video information extraction.

In the embodiment of the present disclosure, the preset strategy may be a target video information extraction strategy set according to the change of activity value, for example, when the activity value reaches the set threshold, start to trigger the extraction of target video information from the live video , stop extracting when the activity value is lower than a certain percentage of the set threshold, or continue to extract video information for a certain period of time after the activity value is lower than a certain percentage or a certain value.

In the embodiment of the present disclosure, by obtaining the information of the target user account, the target user account is the user account of the live broadcast room of the live video, and according to the information of the target user account, the activity value of the target user account in the live video live room is determined, and then according to Activity value, the target video information is extracted from the live video. This method effectively enhances the efficiency of video information extraction. Since the activity of the target user account is detected and quantified, the value representing the activity of the target user account is obtained. The target video information is extracted according to the activity value, which can automatically obtain effective video information in the live video, and improve the extraction effect of effective video information.

As shown in FIG. 2, the method for extracting video information includes the following steps S201 to S205.

In step S201, information of a target user account is acquired, and the target user account is a live room user account of a live room corresponding to a live video.

In step S202, the activity value of the target user account in the live broadcast room corresponding to the live video is determined according to the information of the target user account.

For descriptions of step S201 to step S202, reference may be made to the foregoing embodiments, and details are not repeated here.

In step S203, the current video frame is acquired, and the current video frame corresponds to the current time point.

In the embodiment of the present disclosure, the acquisition of the current video frame may be to record the current live video in real time through recording software or equipment after the live broadcast room of the live video is opened, and decode the recorded live video to obtain multiple video frames, The current video frame at the current time point is determined from the plurality of video frames.

For example, set the recording tool and decoding tool in the background of the live room. After the host of the live room starts the live broadcast, the background of the live room will record the live content in real time, decode the recorded content, and decode it into a video frame with a certain frame rate as the current video frame.

In step S204, the target video frame is determined according to the preset strategy and activity value, and the target time point corresponding to the target video frame is after the current time point.

Among them, by monitoring the situation of the liveness value and analyzing the change information of the liveness value, the selection condition of the video frame set by the change information of the liveness value can be called a prediction strategy, and the prediction strategy can be based on the change of the liveness value A mathematical model for analyzing situations, or a big data model based on technologies such as machine learning.

Wherein, the video frame whose liveness value or change of the liveness value meets a preset requirement may be called a target video frame.

In some embodiments, the change of activity value is continuously monitored to obtain activity change information, and in response to the activity change information meeting the set conditions, the corresponding time point is captured as the target time point, and the live video corresponding The video frame corresponding to the target time point in the live broadcast room is used as the target video frame. Since the change of the activity value is monitored, and the time point that meets the set conditions is captured as the target time point, the target video frame is determined, which improves the The recognition efficiency of the target video frame, since the video frame whose activity change information satisfies the set condition is taken as the target video frame, when the activity change information meets the set condition, it indicates that the video frame has a higher probability of being valid Video information, so as to quickly and reasonably determine the effective video information in the application scene of the live broadcast room, so as to effectively capture the favorite moments of the user account.

In the embodiment of the present disclosure, the set condition that the activity change information satisfies can be, for example, that the activity value increases to a certain threshold, or that the growth rate of the activity value reaches a certain value, or it can be compared with the previous activity value. , the duration of the live video with high activity, etc.

In step S205, target video information is extracted from the live video according to the current video frame and the target video frame.

In some embodiments, the video segment is intercepted from the live video, and the video segment is used as the target video information, wherein the video segment includes a start frame and an end frame, the start frame is the current video frame, and the end frame is the target video frame, By determining the start frame and the end frame, and then directly intercepting the video segment between the start frame and the end frame as the target video information, the convenience of target video information selection is improved, so that complete and effective video information can be captured. It is convenient for the target user account to personalize the effective video information.

Of course, other methods may also be used to extract the target video information from the live video according to the current video frame and the target video frame.

Fig. 3 is a flow chart showing target video information selection according to another exemplary embodiment. As shown in Figure 3, obtain the information of the target user account in the live broadcast room in real time, determine the group activity A to which the current user account belongs, and record the current moment as the best moment when the activity value suddenly increases and the increase exceeds the threshold Starting time t1, record the time when the current user account activity gradually returns to A as t2, then t1-t2 is the best moment, automatically record and save the live content of t1-t2, and take the live content of t1-t2 as the target video information.

For example, in the application scenario of a live broadcast room, according to the monitoring of the activity value, the wonderful moment is from 1 hour to 1 hour and 30 minutes after the start of the live broadcast, then the video frame at the time point of 1 hour can be used as the starting point The start frame, the video frame at the time point of 1 hour and 30 minutes is used as the end frame, and the 30-minute video segment between the start frame and the end frame is used as the target video segment.

In some embodiments, the extraction of the target video information may be to extract a plurality of candidate video frames from the live video, and the time points corresponding to the candidate video frames are between the current time point and the target time point, from the current video frame, multiple Candidate video frames, and select some video frames in the target video frame as the target video information, by selecting the current video frame, multiple candidate video frames, and target video frames, multiple pictures of the target video information can be obtained, and the improvement can be improved. It improves the convenience of target video information selection, and avoids excessive consumption of software and hardware resources by target video information.

In some embodiments, the target activity value of each video frame at the corresponding time point is determined, the target activity value is the activity value of the target user account in the live broadcast room corresponding to the live video at the corresponding time point, and the video frame is the current video frame , or a candidate video frame, or a target video frame, sort each video frame according to the order of each target activity value from large to small, and select a preset number of video frames sorted as the target video information, Because it is the activity corresponding to each frame of video frame that captures the wonderful moment, and then according to the order of each target activity value from large to small, each video frame is sorted, and then select the most exciting N photos (i.e. activity The largest N pictures) are recommended to users, which increases the calculation and sorting of target activity values, strengthens the screening of target video information, improves the quality of video frames with high activity value sent to user accounts, and then improves the accuracy of target video information Select efficiency to effectively capture the favorite moments of user accounts.

Fig. 4 is a flow chart showing target video information selection according to another exemplary embodiment. As shown in Figure 4, the information of the target user account in the live broadcast room is obtained in real time, and the group activity A to which the current user account belongs is determined. When the activity value suddenly increases and the increase exceeds the threshold, the current moment is recorded as the best moment Starting time t1, record the time when the current user account activity gradually returns to A as t2, then t1-t2 is the best wonderful moment, extract each frame of photos from t1-t2 wonderful moments, and correspond to the user according to each frame of photos The account activity is sorted, and the best N photos are recommended to the user account.

For example, in the application scenario of the live broadcast room, set the threshold value of the activity value, monitor the live content as a whole, select the video frame whose activity value satisfies the threshold condition, and select the current video frame, multiple candidate video frames, and The target video frames are arranged in the order of the time nodes, and multiple frames of pictures about the wonderful moments in the live broadcast room are generated, and the multiple frames of pictures are regarded as the wonderful moments.

In the embodiment of the present disclosure, by obtaining the information of the target user account, the target user account is the user account of the live broadcast room of the live video, according to the information of the target user account, the activity value of the target user account in the live video live room is determined, and then the The current video frame, the current video frame corresponds to the current time point, the target video frame is determined according to the prediction strategy and the activity value, the target time point corresponding to the target video frame is after the current time point, according to the current video frame and the target video frame, from the live video The target video information is extracted from the target video frame. Since the target video frame is determined using the prediction strategy and the activity value, the target video information is extracted from the current video frame and the target video frame to ensure the accuracy and rationality of the target video information extraction. Because It determines the target video frame of the current video according to the change of the activity value, and can effectively capture the favorite moments of the user account. Since the target video segment is intercepted through the determination of the start frame and the end frame, the captured video segment It is more complete, and at the same time, it is convenient to personalize the effective information of the video segment.

As shown in FIG. 5 , the method for extracting video information includes the following steps S501 to S507.

In step S501, information of a target user account is acquired, and the target user account is a live room user account of a live room corresponding to a live video.

For the description of step S501, reference may be made to the foregoing embodiments, and details are not repeated here.

In step S502, a plurality of live interaction information respectively corresponding to a plurality of user accounts is acquired.

After the target user account information is obtained above, multiple corresponding live broadcast interaction information is obtained according to the multiple target user accounts, wherein the live broadcast interaction information may be the recorded interaction of the user account in the live broadcast room.

For example, the interaction of the user account in the live broadcast room may be that the user account likes, follows, sends barrage and presents virtual props such as virtual flowers in the live broadcast room, or it may be that the user account participates in the interaction in the live broadcast room mini games etc.

In step S503, a plurality of candidate activity values respectively corresponding to a plurality of user accounts are determined according to a plurality of live interaction information.

In the embodiments of the present disclosure, multiple user accounts may generate multiple identical or different live interactive information, and determine multiple candidate activity values corresponding to multiple user accounts according to the multiple live interactive information, which may be based on the live interactive Different types of information can be confirmed, for example, the number of likes can be used as a candidate activity value, and the number or value of virtual props such as virtual gifts can be used as another candidate activity value.

In step S504, the target user account group in which the target user account is located is determined according to the information of the target user account.

In the embodiment of the present disclosure, the grouping of target user accounts may be based on the viewing status of the target user accounts or live broadcast interaction information, etc. For example, according to the value of the virtual props given by the user account, or the level of the live broadcast room of the user account, the user account is divided into different groups, and one or several user account information can also be selected as the main group. According to the grouping rules, they are combined into different grouping rules.

In step S505, a reference activity value corresponding to the target user account group is determined according to a plurality of candidate activity values.

In the embodiment of the present disclosure, different groups can choose different candidate activity values as reference activity values, or choose a variety of different candidate activity values, assign different numerical proportions, and calculate the reference activity through corresponding formulas value.

For example, in the application scenario of a live broadcast room, the value of the virtual props given by the user account and the number of likes can be used as the main grouping basis, and the user accounts are grouped into G1, G2, G3...GN, and settings affect the activity of this group. The factors of degree value can be the value of the virtual props given by the user account, the number of likes and the level of the live room, etc., and the corresponding active value weights are given to them respectively. For example, the value weight of the virtual props given by the user account is 5, and the number of likes is 5. The weight is 4, and the weight of the live room level is 1. Then, according to different candidate activity values and the weights corresponding to the target groups, the reference activity value is calculated through mathematical formulas.

In step S506, the reference activity value corresponding to the target user account group is used as the activity value of the target user account in the live broadcast room corresponding to the live video.

After determining the reference activity value corresponding to the target user account group according to the plurality of candidate activity values, the reference activity value corresponding to the target user account group is used as the activity value of the target user account in the live broadcast room of the live video.

In step S507, the target video information is extracted from the live video according to the liveness value.

For the description of step S507, reference may be made to the foregoing embodiments, and details are not repeated here.

In the embodiment of the present disclosure, by obtaining the information of the target user account, the target user account is the live room user account of the live room corresponding to the live video, and obtaining multiple live interaction information corresponding to multiple user accounts, and according to the multiple live interaction Information, determine multiple candidate activity values corresponding to multiple user accounts, determine the target user account group where the target user account is located according to the information of the target user account, and then determine the target user account according to the multiple candidate activity values The reference activity value corresponding to the group, the reference activity value corresponding to the target user account group is used as the activity value of the target user account in the live broadcast room corresponding to the live video, and the target video information is extracted from the live video according to the activity value , due to the grouping of target user accounts, the activity value of the target user accounts can be measured more accurately and pertinently. Extraction effect of live video information.

Fig. 6 is a block diagram of an apparatus for extracting video information according to an exemplary embodiment. Referring to FIG. 6 , the device includes an acquisition module 601 , a determination module 602 and an extraction module 603 .

The acquiring module 601 is configured to acquire the information of the target user account, where the target user account is the live room user account of the live room corresponding to the live video;

The determination module 602 is configured to determine the activity value of the target user account in the live room corresponding to the live video according to the information of the target user account;

The extracting module 603 is configured to extract target video information from the live video according to the liveness value.

In some embodiments of the present disclosure, as shown in FIG. 7 , which is a block diagram of a device for extracting video information according to another exemplary embodiment, the extraction module 603 is configured to:

In some embodiments of the present disclosure, as shown in FIG. 7, the extraction module 603 is configured to:

Get the current video frame, which corresponds to the current time point;

In some embodiments of the present disclosure, as shown in FIG. 7, the determining module 602 includes:

The first determination sub-module 7021 is configured to determine the target user account group where the target user account is located according to the information of the target user account, and use the reference activity value corresponding to the target user account group as the target user account corresponding to the live video The activity value of the live broadcast room.

In some embodiments of the present disclosure, as shown in FIG. 7, the determination module 602 further includes:

The obtaining sub-module 7022 is configured to obtain multiple live interaction information respectively corresponding to multiple user accounts before the step of determining the target user account group in which the target user account is located according to the information of the target user account;

The second determination sub-module 7023 is configured to determine a plurality of candidate activity values corresponding to a plurality of user accounts according to a plurality of live interaction information;

The third determining submodule 7024 is configured to determine a reference activity value corresponding to the target user account group according to multiple candidate activity values.

In some embodiments of the present disclosure, as shown in FIG. 7 , the extraction module 603 is configured to:

Regarding the apparatus in the foregoing embodiments, the specific manner in which each module executes operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

In the embodiment of the present disclosure, by obtaining the information of the target user account, the target user account is the live room user account of the live room corresponding to the live video, and according to the information of the target user account, determine the activity of the target user account in the live room corresponding to the live video According to the activity value, the target video information is extracted from the live video. This method effectively enhances the efficiency of video information extraction. Since the activity of the target user account is detected and quantified, the target user account active The target video information can be extracted according to the activity value, which can automatically obtain effective video information in the live video and improve the extraction effect of effective video information.

An embodiment of the present disclosure also provides an electronic device, and FIG. 8 is a block diagram of an electronic device according to an exemplary embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.

8, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814 , and the communication component 816.

The processing component 802 generally controls the overall operations of the electronic device 800, such as those associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. Additionally, processing component 802 may include one or more modules that facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802 .

The memory 804 is configured to store various types of data to support operations at the electronic device 800 . Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 can be implemented by any type of volatile or non-volatile storage device or their combination, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), Magnetic Memory, Flash Memory, Magnetic or Optical Disk.

The power supply component 806 provides power to various components of the electronic device 800 . Power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 800 .

The multimedia component 808 includes a touchscreen display that provides an output interface between the electronic device 800 and the user account. In some embodiments, the touch display may include a liquid crystal display (LCD) and a touch panel (TP). The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may not only sense a boundary of a touch or a swipe action, but also detect duration and pressure associated with the touch or swipe operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a microphone (MIC), which is configured to receive an external audio signal when the electronic device 800 is in an operation mode, such as a call mode, a recording mode and a voice recognition mode. Received audio signals may be further stored in memory 804 or sent via communication component 816 .

In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: a home button, volume buttons, start button, and lock button.

Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of electronic device 800 . For example, the sensor component 814 can detect the open/closed state of the electronic device 800, the relative positioning of components, such as the display and the keypad of the electronic device 800, and the sensor component 814 can also detect the electronic device 800 or a component of the electronic device 800. Changes in location, presence or absence of user account contact with electronic device 800 , electronic device 800 orientation or acceleration/deceleration and temperature changes in electronic device 800 . Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. Sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on communication standards, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, electronic device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable Programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic component implementation for performing the above video information extraction method.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium including instructions, such as the memory 804 including instructions, which can be executed by the processor 820 of the electronic device 800 to complete the above method. In some embodiments, the computer readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

In an exemplary embodiment, there is also provided a computer program product, including a computer program, when the computer program is executed by a processor, the aforementioned method for extracting video information is implemented.

All the embodiments of the present disclosure can be implemented independently or in combination with other embodiments, which are all regarded as the scope of protection required by the present disclosure.

Claims

A video information extraction method, comprising:

Acquiring the information of the target user account, where the target user account is the live room user account of the live room corresponding to the live video;

According to the information of the target user account, determine the activity value of the target user account in the live broadcast room corresponding to the live video;

According to the activity value, target video information is extracted from the live video.
The method for extracting video information according to claim 1, wherein the step of extracting target video information from the live video according to the liveness value comprises:

Extracting the target video information from the live video according to a preset policy in response to a change in the activity value being greater than or equal to a preset increase threshold;

In response to the variation of the activity value being less than the preset increase range threshold, the step of determining the activity value of the target user account in the live broadcast room corresponding to the live video is re-executed.
The video information extraction method according to claim 2, wherein the step of extracting the target video information from the live video according to a preset strategy comprises:

Obtaining a current video frame, where the current video frame corresponds to the current time point;

determining a target video frame according to the preset policy and the activity value, and the target time point corresponding to the target video frame is after the current time point;

Extracting the target video information from the live video according to the current video frame and the target video frame.
The video information extraction method according to claim 3, wherein the step of extracting the target video information from the live video according to the current video frame and the target video frame includes:

Intercepting a video segment from the live video, and using the video segment as the target video information, wherein the video segment includes a start frame and an end frame, and the start frame is the current video frame, so The last frame is the target video frame.
The video information extraction method according to claim 3, wherein the step of extracting the target video information from the live video according to the current video frame and the target video frame includes:

Extracting a plurality of candidate video frames from the live video, where the time points corresponding to the candidate video frames are between the current time point and the target time point;

Selecting a part of video frames from the current video frame, the plurality of candidate video frames, and the target video frame as the target video information.
The video information extraction method according to claim 3, wherein the step of determining the target video frame according to the preset strategy and the activity value includes:

Continuously monitor changes in the activity value to obtain activity change information;

In response to the activity change information satisfying a set condition, capturing a corresponding time point as the target time point;

The video frame corresponding to the target time point in the live room corresponding to the live video is used as the target video frame.
The video information extraction method according to claim 1, wherein the step of determining the activity value of the target user account in the live room corresponding to the live video according to the information of the target user account comprises:

determining the target user account group where the target user account belongs to according to the information of the target user account;

The reference activity value corresponding to the target user account group is used as the activity value of the target user account in the live broadcast room corresponding to the live video.
The method for extracting video information according to claim 7, wherein the target user account grouping includes a plurality of user accounts, and the method further comprises:

Acquiring a plurality of live interactive information respectively corresponding to the plurality of user accounts;

determining a plurality of candidate activity values respectively corresponding to the plurality of user accounts according to the plurality of live interaction information;

The reference activity value corresponding to the target user account group is determined according to the plurality of candidate activity values.
The video information extraction method according to claim 5, wherein, selecting a part of video frames from the current video frame, the plurality of candidate video frames, and the target video frame as the target video information, include:

Determine the target activity value of each video frame at a corresponding time point, the target activity value is the activity value of the target user account in the live broadcast room corresponding to the live video at the corresponding time point, the The video frame is the current video frame, or the candidate video frame, or the target video frame;

Sorting each of the video frames according to the descending order of each of the target activity values;

Selecting a preset number of video frames sorted first as the target video information.
A video information extraction device, including:

The obtaining module is configured to obtain the information of the target user account, and the target user account is the live room user account of the live room corresponding to the live video;

The determination module is configured to determine the activity value of the target user account in the live broadcast room corresponding to the live video according to the information of the target user account;

The extraction module is configured to extract target video information from the live video according to the liveness value.
The video information extraction device according to claim 10, wherein the extraction module is configured to:

Extracting the target video information from the live video according to a preset policy in response to a change in the activity value being greater than or equal to a preset increase threshold;

In response to the variation of the activity value being less than the preset increase range threshold, the step of determining the activity value of the target user account in the live broadcast room corresponding to the live video is re-executed.
The video information extraction device according to claim 11, wherein the extraction module is configured to:

Obtaining a current video frame, where the current video frame corresponds to the current time point;

determining a target video frame according to the preset policy and the activity value, and the target time point corresponding to the target video frame is after the current time point;

Extracting the target video information from the live video according to the current video frame and the target video frame.
The video information extraction device according to claim 12, wherein the extraction module is configured to:

Intercepting a video segment from the live video, and using the video segment as the target video information, wherein the video segment includes a start frame and an end frame, and the start frame is the current video frame, so The last frame is the target video frame.
The video information extraction device according to claim 12, wherein the extraction module is configured to:

Extracting a plurality of candidate video frames from the live video, where the time points corresponding to the candidate video frames are between the current time point and the target time point;

Selecting a part of video frames from the current video frame, the plurality of candidate video frames, and the target video frame as the target video information.
The video information extraction device according to claim 12, wherein the extraction module is configured to:

Continuously monitor changes in the activity value to obtain activity change information;

In response to the activity change information satisfying a set condition, capturing a corresponding time point as the target time point;

The video frame corresponding to the target time point in the live room corresponding to the live video is used as the target video frame.
The video information extraction device according to claim 10, wherein the determination module includes:

The first determining submodule is configured to determine the target user account group in which the target user account belongs according to the information of the target user account, and use the reference activity value corresponding to the target user account group as the target The activity value of the user account in the live room corresponding to the live video.
The video information extraction device according to claim 16, wherein the target user account group includes multiple user accounts, and the determining module further includes:

The acquisition sub-module is configured to acquire multiple live interactions respectively corresponding to the multiple user accounts before the step of determining the target user account group in which the target user account belongs according to the information of the target user account information;

The second determination submodule is configured to determine a plurality of candidate activity values respectively corresponding to the plurality of user accounts according to the plurality of live interaction information;

The third determining submodule is configured to determine the reference activity value corresponding to the target user account group according to the plurality of candidate activity values.
The video information extraction device according to claim 15, wherein the extraction module is configured to:

Determine the target activity value of each video frame at a corresponding time point, the target activity value is the activity value of the target user account in the live broadcast room corresponding to the live video at the corresponding time point, the The video frame is the current video frame, or the candidate video frame, or the target video frame;

Sorting each of the video frames according to the descending order of each of the target activity values;

Selecting a preset number of video frames sorted first as the target video information.
An electronic device, comprising:

processor;

memory for storing said processor-executable instructions;

Wherein, the processor is configured to execute the instructions to achieve the following steps:

Acquiring the information of the target user account, where the target user account is the live room user account of the live room corresponding to the live video;

According to the information of the target user account, determine the activity value of the target user account in the live broadcast room corresponding to the live video;

According to the activity value, target video information is extracted from the live video.
A non-volatile computer-readable storage medium, when the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can perform the following steps:

Acquiring the information of the target user account, where the target user account is the live room user account of the live room corresponding to the live video;

According to the information of the target user account, determine the activity value of the target user account in the live broadcast room corresponding to the live video;

According to the activity value, target video information is extracted from the live video.
A computer program product, comprising a computer program, wherein the computer program implements the following steps when executed by a processor:

Acquiring the information of the target user account, where the target user account is the live room user account of the live room corresponding to the live video;

According to the information of the target user account, determine the activity value of the target user account in the live broadcast room corresponding to the live video;

According to the activity value, target video information is extracted from the live video.