CN115086279A

CN115086279A - Multimedia content pushing method and device, electronic equipment and storage medium

Info

Publication number: CN115086279A
Application number: CN202110265516.9A
Authority: CN
Inventors: 俄万有
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-03-11
Filing date: 2021-03-11
Publication date: 2022-09-20

Abstract

The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for pushing multimedia content, an electronic device, and a storage medium, so as to improve accuracy of pushing multimedia content. The method comprises the following steps: acquiring media resource information of target multimedia content and public opinion information related to the target multimedia content, wherein the media resource information is used for representing attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content; obtaining an auditing priority aiming at target multimedia content based on the media information and the public opinion information; and pushing the media asset information and the auditing priority of the target multimedia content to a licensor auditing system so that the licensor auditing system audits the media asset information based on the auditing priority. According to the method and the system, the auditing priority of the target multimedia content is predicted by combining public opinion information, and the license party auditing system conducts auditing based on the auditing priority, so that the output of high-quality content can be ensured, and the pushing accuracy is improved.

Description

Multimedia content pushing method and device, electronic equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for pushing multimedia content, an electronic device, and a storage medium.

Background

With the popularization of high-speed networks, internet televisions have gradually entered into thousands of households, and rich and colorful video multimedia contents such as television series, movies and the like are provided for users. Taking video as an example, in order to provide compliant video service on a large screen, each video platform cooperates with a license plate party in sequence, video media content in the platform is pushed to the cooperating license plate party for content verification, and only the video content after the license plate party verification is passed can be put on the shelf in an Application program (APP).

When video media asset content is pushed in the related technology, a content filtering rule is formulated mainly by depending on operation experience through negotiation with a license plate party, and when the video content is pushed to the license plate party, the video content hitting the filtering rule is directly filtered, so that the amount of audit pushed to the license plate party is reduced. However, the method lacks refined push content, and the push accuracy is low.

Disclosure of Invention

The embodiment of the application provides a method and a device for pushing multimedia content, electronic equipment and a storage medium, which are used for improving the accuracy of pushing the multimedia content.

The method for pushing the multimedia content provided by the embodiment of the application comprises the following steps:

acquiring media asset information of target multimedia content and public opinion information related to the target multimedia content, wherein the media asset information is used for representing attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content;

obtaining an auditing priority aiming at the target multimedia content based on the media information and the public opinion information;

and pushing the media asset information of the target multimedia content and the auditing priority to a license party auditing system so that the license party auditing system audits the media asset information based on the auditing priority.

Another method for pushing multimedia content provided in an embodiment of the present application includes:

acquiring media information and audit priority of target multimedia content, wherein the audit priority is obtained based on public opinion information related to the target multimedia content and the media information, the media information is used for representing media information attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content;

and auditing the media information based on the auditing priority.

The pushing device for multimedia content provided by the embodiment of the application comprises:

the information acquisition unit is used for acquiring media information of target multimedia content and public opinion information related to the target multimedia content, wherein the media information is used for representing attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content;

the prediction unit is used for obtaining the auditing priority aiming at the target multimedia content based on the media information and the public opinion information;

and the pushing unit is used for pushing the media information of the target multimedia content and the auditing priority to a license party auditing system so that the license party auditing system audits the media information based on the auditing priority.

Optionally, the prediction unit is further configured to:

before obtaining an auditing priority aiming at the target multimedia content based on the media information and the public opinion information, predicting whether the target multimedia content can be predicted through pre-auditing by a licensor auditing system based on the media information and the public opinion information, and obtaining a corresponding push decision aiming at the target multimedia content based on a first prediction result;

the prediction unit is specifically configured to:

if the pushing decision represents that the pre-review is passed, predicting the review emergency state of the target multimedia content based on the media information and the public opinion information to obtain a second prediction result, and determining the review priority aiming at the target multimedia content based on the second prediction result.

Optionally, the prediction unit is specifically configured to:

inputting the media information and the public opinion information into a trained media resource pre-auditing model, extracting attribute characteristics of the media information and the public opinion information based on the media resource pre-auditing model, predicting whether the target multimedia content can be pre-audited by the license party auditing system based on the extracted attribute characteristics, and obtaining a pushing decision aiming at the target multimedia content based on the first prediction result;

the system comprises a media asset pre-auditing model, a license party auditing system and a license party auditing system, wherein the media asset pre-auditing model is obtained by training based on a first training sample data set, training samples in the first training sample data set comprise sample multimedia content, license auditing information, media asset information and public opinion information related to the sample multimedia content, a decision label for representing a real pushing decision is marked on each training sample, and the license party auditing information is used for representing auditing detail information when the license party auditing system is used for auditing the sample multimedia content.

Optionally, the media information and the public opinion information are input into a trained auditing priority prediction model, after emergency feature extraction is performed on the media information and the public opinion information based on the auditing priority prediction model, the auditing emergency state of the target multimedia content is predicted based on the extracted emergency feature, the second prediction result is obtained, and the auditing priority for the target multimedia content is determined based on the second prediction result;

the auditing priority prediction model is obtained by training based on a second training sample data set, the training samples in the second training sample data set comprise sample multimedia content, historical behavior information, medium resource information and public opinion information related to the sample multimedia content, and each training sample is marked with a priority label for representing a real priority order.

Optionally, the apparatus further comprises:

the first training unit is used for obtaining the media resource pre-examination model through training in the following way:

according to the training samples in the first training sample data set, performing cycle iterative training on the media asset pre-examination model, and outputting the trained media asset pre-examination model when the training is finished; wherein, each loop iteration training process comprises the following operations:

selecting training samples from the first training sample data set;

inputting license plate auditing information, media information and public opinion information related to sample multimedia contents in the training sample into a media resource pre-auditing model, predicting whether the sample multimedia contents can be pre-audited by the license plate party auditing system based on the media resource pre-auditing model, and obtaining a pre-estimated pushing decision aiming at the sample multimedia contents;

and adjusting parameters of the media asset pre-auditing model by adopting a classification method based on the error between the estimated push decision and a decision label corresponding to the sample multimedia content in the training sample.

Optionally, the apparatus further comprises:

the second training unit is used for obtaining the auditing priority prediction model through training in the following modes:

according to the training samples in the second training sample data set, performing loop iterative training on the audit priority prediction model, and outputting the trained audit priority prediction model when the training is finished; wherein, each loop iteration training process comprises the following operations:

selecting training samples from the second training sample data set;

inputting historical behavior information, medium resource information and public opinion information related to sample multimedia contents in the training sample into an auditing priority prediction model, predicting an auditing emergency state of the sample multimedia contents based on the auditing priority prediction model, and obtaining estimated auditing priority aiming at the sample multimedia contents;

and adjusting parameters of the auditing priority prediction model by adopting a regression method based on the error between the estimated auditing priority and the priority label corresponding to the sample multimedia content in the training sample.

Another multimedia content pushing apparatus provided in an embodiment of the present application includes:

the system comprises a priority acquiring unit, a priority verifying unit and a judging unit, wherein the priority verifying unit is used for acquiring the media information and the verifying priority of target multimedia content, the verifying priority is acquired based on the public opinion information related to the target multimedia content and the media information, the media information is used for representing the media information attribute information of the target multimedia content, and the public opinion information is used for representing the public opinion attention related to the target multimedia content;

and the auditing unit is used for auditing the media information based on the auditing priority.

Optionally, the auditing unit is specifically configured to:

determining the order of the target multimedia content in an audit queue according to the audit priority, and auditing the media information according to the determined order;

and when the media information is approved, issuing a license plate aiming at the target multimedia content.

An electronic device provided by an embodiment of the present application includes a processor and a memory, where the memory stores program codes, and when the program codes are executed by the processor, the processor is caused to execute the steps of any one of the above methods for pushing multimedia content.

Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device executes the steps of any one of the above methods for pushing multimedia content.

An embodiment of the present application provides a computer-readable storage medium, which includes program code, when the program product runs on an electronic device, the program code is configured to enable the electronic device to execute the steps of any one of the above methods for pushing multimedia content.

The beneficial effect of this application is as follows:

the pushing method and device for the multimedia content, the electronic device and the storage medium are provided by the embodiment of the application. According to the embodiment of the application, the auditing priority of the target multimedia content is predicted through the media information of the target multimedia content and the related public opinion information and is pushed to the licensor auditing system, so that the high-quality content can be preferentially pushed to the licensor for auditing, the target multimedia content is audited by the licensor auditing system based on the auditing priority, the output of the high-quality content can be guaranteed, the pushing accuracy of the multimedia content is improved, and the auditing efficiency of the licensor is improved.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

fig. 1 is an architecture diagram of a license auditor content delivery system commonly used in the related art;

fig. 2 is an alternative schematic diagram of an application scenario in an embodiment of the present application;

fig. 3 is a flowchart illustrating a method for pushing multimedia content according to an embodiment of the present application;

fig. 4 is an architecture diagram of a license plate party auditing media asset delivery system implemented based on machine learning in an embodiment of the present application;

fig. 5 is a schematic diagram of a media asset pushing process in an embodiment of the present application;

FIG. 6 is a flowchart of a training method of a media asset pre-review model in an embodiment of the present application;

FIG. 7 is a flowchart of a training method for auditing a priority prediction model in an embodiment of the present application;

fig. 8 is a flowchart illustrating another method for pushing multimedia content according to an embodiment of the present application;

fig. 9 is a schematic diagram illustrating an interaction implementation timing sequence of a video content push method in an embodiment of the present application;

fig. 10 is a schematic structural diagram of a multimedia content pushing apparatus according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of another multimedia content pushing apparatus in an embodiment of the present application;

fig. 12 is a schematic diagram of a hardware component of an electronic device to which an embodiment of the present application is applied;

fig. 13 is a schematic diagram of a hardware component structure of another electronic device to which the embodiment of the present application is applied.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the technical solutions of the present application. All other embodiments obtained by a person skilled in the art without any inventive step based on the embodiments described in the present application are within the scope of the protection of the present application.

Some concepts related to the embodiments of the present application are described below.

Multimedia content: a man-machine interactive information exchange and transmission medium combining two or more media. The media includes text, pictures, sound, movies, etc. In the embodiment of the present application, the multimedia content may be articles, information, video, music, and so on.

License plate: the television license plate is provided with program contents and exercises the broadcasting control right by a broadcasting and television enterprise, so that the content can be managed and controlled from the source, and the content of the Internet television can be better managed and controlled. The company, which owns the license plate and only owns the broadcast control right, is qualified to develop the autonomous content distribution service of the interactive network television and the network set-top box, and obtains the license plate, is called a license plate maker in the industry, namely a license plate party in the embodiment of the application.

Media assets and media asset information: media assets are short for media assets, and refer to content assets, media units such as newspaper agencies, broadcasting stations, television stations, websites and communication agencies, and a large amount of news service data such as characters, pictures, audios and videos are produced every day, and the data, metadata describing the data, copyright information of the data and the like. In a broad sense, in addition to content assets, all tangible and intangible assets include the brand of media, policy advantages, market share, its talent group, audience group, customer group, its information flow, logistics, fund flow, etc. In the embodiment of the present application, taking a movie as an example, the media asset information of the movie may be: movie title, time on shelf, copyright party, director, actors, cover art, etc.

Public opinion: the social political attitude of people to social managers is generated and held around the occurrence, development and change of social events in a certain social space. It is the sum of the expressions of beliefs, attitudes, opinions, emotions, and the like expressed by more people about various phenomena, problems, and the like in the society.

Public opinion information: for characterizing public opinion concerns related to multimedia content. The network public sentiment is the mapping of the social public sentiment in the internet space and is the direct reflection of the social public sentiment. With the rapid development of networks, network public sentiment has become a main expression form reflecting social public sentiment.

And (3) license plate party audit information: the method is used for representing the auditing detail information when the multimedia content is audited based on the auditing system of the licence plate party. Since the license party auditing system mainly audits the media asset information when auditing the sample multimedia content, in the embodiment of the application, the license party auditing information is also called the media asset auditing information. The method mainly comprises a plurality of parts including media asset identification (id), an audit result, an audit reason, auditors, audit time and the like.

The embodiment of the present application relates to Artificial Intelligence (AI) and Machine Learning technologies, and is designed based on a computer vision technology and Machine Learning (ML) in the AI.

Artificial intelligence is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence.

Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making. The artificial intelligence technology mainly comprises a computer vision technology, a natural language processing technology, machine learning/deep learning and other directions. With the research and development of artificial intelligence technology, artificial intelligence is developed and applied in a plurality of fields, such as common smart homes, smart customer service, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, robots, smart medical treatment and the like.

Natural Language Processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that enable efficient communication between humans and computers using natural language. Natural language processing is a science integrating linguistics, computer science and mathematics. Therefore, the research in this field will involve natural language, i.e. the language that people use everyday, so it is closely related to the research of linguistics. Natural language processing techniques typically include text processing, semantic understanding, machine translation, robotic question and answer, knowledge mapping, and the like.

Machine learning is a multi-field cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Compared with the method for finding mutual characteristics among big data by data mining, the machine learning focuses on the design of an algorithm, so that a computer can automatically learn rules from the data and predict unknown data by using the rules.

Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and the like. According to the embodiment of the application, when whether the target multimedia content can be predicted through the pre-review of the license party auditing system or not is judged, a media resource pre-review model based on machine learning or deep learning is adopted. When the prediction result shows that the pre-audit passes, an audit priority prediction model based on machine learning or deep learning is further adopted, the audit priority of the target multimedia content is predicted based on the audit priority prediction model, and then the media information and the audit priority of the target multimedia content are pushed to the license party audit system, so that the license party audit system audits the media information based on the audit priority. Based on the pushing method of the multimedia content in the embodiment of the application, the high-quality content can be preferentially pushed to the license party for auditing, the target multimedia content is audited by the license party auditing system based on the auditing priority, the output of the high-quality content can be ensured, and the accuracy of pushing the multimedia content is improved.

The method for training the media asset pre-audit model and the audit priority prediction model provided by the embodiment of the application can be divided into two parts, including a training part and an application part; the training part relates to the technical field of machine learning, and in the training part, a media resource pre-auditing model and an auditing priority prediction model are trained through the machine learning technology. Specifically, a media asset pre-auditing model is trained by using a first training sample data set given in the embodiment of the application, after a training sample passes through the media asset pre-auditing model, an output result of the media asset pre-auditing model is obtained, model parameters are continuously adjusted by a classification algorithm in combination with the output result, and the trained media asset pre-auditing model is output; similarly, the second training sample data set provided in the embodiment of the application is used for training the audit priority prediction model, after the training sample passes through the audit priority prediction model, the output result of the audit priority prediction model is obtained, the model parameters are continuously adjusted through a regression algorithm by combining the output result, and the trained audit priority prediction model is output; the application part is used for predicting whether the target multimedia content can pass the pre-examination of the license party examination system by using the media resource pre-examination model obtained by training in the training part; and predicting the auditing emergency state of the target multimedia content by using the auditing priority prediction model trained in the training part. In addition, it should be further noted that, in the embodiment of the present application, both the medium resource pre-review model and the review priority prediction model may adopt an online training mode or an offline training mode, and in the embodiment of the present application, the offline training is mainly taken as an example for illustration, which is not specifically limited herein.

The following briefly introduces the design concept of the embodiments of the present application:

with the popularization of high-speed networks, internet televisions have gradually entered thousands of households, and rich and colorful video multimedia contents such as television dramas, movies and the like are provided for users. Referring to fig. 1, a diagram of a license authority auditing a media asset delivery system in the related art is shown. In the related art, the flow of auditing and pushing license plate side media assets is roughly as follows:

1) and the video content injection system receives the interior of a newly produced video, edits the media asset information of the supplemented video, and writes the data into a video platform media asset library to be stored on the ground. Meanwhile, the video content injection system sends a notification message of the newly added video content.

2) The auditing media asset pushing system of the video platform subscribes the notification message of the newly added video content, acquires the id of the video content, simultaneously inquires the detailed information of the video content from the media asset library of the video platform, performs rule matching on the video content according to a preset auditing content filtering rule, eliminates the video which hits the filtering rule, and pushes the residual video to the license plate party through a media asset receiving interface of the license plate party.

3) And after the license plate party media asset receiving system receives the audit media assets, writing the media asset information into a media asset library of the license plate party for landing storage.

4) And the license party auditing system reads the unchecked media asset information from the media asset library of the license party, carries out manual auditing, and calls an auditing result synchronization interface of the video platform to synchronize the auditing result to the video platform after the auditing is finished.

5) And after receiving the audit result information, the audit result synchronization service of the video platform writes the audit result into a media asset library of the video platform for storage.

Considering that the auditing based on rule filtering provided in the related technology is not related to the popularity of the pushed content and lacks refined pushed content, the pushed content cannot be guaranteed to be audited at the first time and played online after the hot content of the head is pushed to the license plate, and on the other hand, the filtering rules are increased or reduced, manual adjustment is needed, and the sudden hot event cannot be automatically tracked, so that the related video content can be pushed in time.

In view of this, the present application provides a method and an apparatus for pushing multimedia content, an electronic device, and a storage medium. According to the embodiment of the application, the auditing priority of the target multimedia content is predicted through the media information of the target multimedia content and the related public opinion information and is pushed to the licensor auditing system, so that the high-quality content can be preferentially pushed to the licensor for auditing, the target multimedia content is audited by the licensor auditing system based on the auditing priority, the output of the high-quality content can be guaranteed, the pushing accuracy of the multimedia content is improved, and the auditing efficiency of the licensor is improved.

The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it should be understood that the preferred embodiments described herein are merely for illustrating and explaining the present application, and are not intended to limit the present application, and that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.

Fig. 2 is a schematic view of an application scenario according to an embodiment of the present application. The application scenario diagram includes two terminal devices 210 and a server 220. The terminal device 210 and the server 220 can communicate with each other through a communication network. The user can browse multimedia content through the terminal device 210, the terminal device 210 may be installed with application programs related to the multimedia content, such as a video APP, a short video APP, an information flow APP, and the like, the application related to the embodiment of the present application may be a software, or a client such as a webpage, an applet, and the like, the server is a background server corresponding to the software, or the webpage, the applet, and the like, and the specific type of the client is not limited.

In an alternative embodiment, the communication network is a wired network or a wireless network. The terminal device 210 and the server 220 may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

In this embodiment, the terminal device 210 may be an electronic device having a certain computing capability and running instant messaging software and a website or social software and a website, such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, an e-book reader, an intelligent television, an intelligent home, and the like. Each terminal device 210 and the server 220 are connected via a wireless Network, and the server 220 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and an artificial intelligence platform.

It should be noted that fig. 2 is only an example, and the number of the terminal devices and the servers is not limited in practice, and is not specifically limited in the embodiment of the present application.

The media asset pre-auditing model and the auditing priority prediction model listed in the embodiment of the application can be deployed on the server 220 for training, and a large number of training samples can be stored in the server 220 and used for training the media asset pre-auditing model and the auditing priority prediction model. Optionally, after the media asset pre-review model or the review priority prediction model is obtained based on the training method in the embodiment of the present application, the trained media asset pre-review model or the review priority prediction model may be directly deployed on the server 220 or the terminal device 210. In general, the media resource pre-auditing model and the auditing priority prediction model are directly deployed on the server 220, and in the embodiment of the application, the media resource pre-auditing model is mainly used for predicting whether the multimedia content can be pre-audited by the auditing system of the license plate party; the auditing priority prediction model is mainly used for predicting the auditing emergency state of the multimedia content.

In a possible application scenario, the training samples in the present application may be stored by using a cloud storage technology. A distributed cloud storage system (hereinafter, referred to as a storage system) refers to a storage system that aggregates a large number of storage devices (storage devices are also referred to as storage nodes) of various types in a network through application software or application interfaces to cooperatively work by using functions such as cluster application, grid technology, and a distributed storage file system, and provides data storage and service access functions to the outside.

In a possible application scenario, in order to reduce the communication delay, the servers 220 may be deployed in each area, or in order to balance the load, different servers 220 may respectively serve the areas corresponding to the terminal devices 210. The plurality of servers 220 may implement data sharing through a blockchain, and the plurality of servers 220 correspond to a data sharing system formed by the plurality of servers 220. For example, terminal device 210 is located at site a and communicatively coupled to server 220, and terminal device 210 is located at site b and communicatively coupled to other servers 220.

Each server 220 in the data sharing system has a node identifier corresponding to the server 220, and each server 220 in the data sharing system may store node identifiers of other servers 220 in the data sharing system, so that the generated block is broadcast to other servers 220 in the data sharing system according to the node identifiers of other servers 220. Each server 220 may maintain a node identifier list as shown in the following table, and store the name of the server 220 and the node identifier in the node identifier list. The node identifier may be an Internet Protocol (IP) address and any other information that can be used to identify the node, and table 1 only illustrates the IP address as an example.

TABLE 1

Server name	Node identification
		Node 1	119.115.151.174
Node 2	118.116.189.145
		…	…
Node N	119.124.789.258

In the following, a method for pushing multimedia content provided by the exemplary embodiments of the present application is described with reference to the accompanying drawings in conjunction with the application scenarios described above, it should be noted that the application scenarios described above are only shown for the convenience of understanding the spirit and principle of the present application, and the embodiments of the present application are not limited in any way in this respect.

In this document, multimedia content is mainly exemplified as video, and the target multimedia content is pending video. In order to provide compliant video service, each video platform cooperates with the license plate party in sequence, firstly, the video media content in the platform is pushed to the cooperative license plate party for content verification, and only the video content after the verification of the license plate party is passed can be put on the shelf in the APP.

It should be noted that, the method for pushing multimedia content in the embodiment of the present application may be executed by a server or a terminal device alone, or may be executed by both the server and the terminal device.

Referring to fig. 3, it is illustrated that a server executes an exemplary implementation process of a multimedia content push method according to an embodiment of the present application, and the specific implementation process of the method is as follows:

s31: the server acquires media asset information of target multimedia content and public opinion information related to the target multimedia content, wherein the media asset information is used for representing attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content;

in the embodiment of the application, before the target multimedia content is pushed to the license plate party auditing system for auditing, the media asset information of the target multimedia content needs to be acquired first, taking a video as an example, and the media asset information of the video comprises a video name, a time on shelf, a copyright party, a director, actors, a cover map and the like. The public opinion information is social hotspot information obtained by using a public opinion monitoring system for identifying hotspots, tracking themes and tracking new hot topics of the current society in time, and represents the public opinion attention of a user to related content of the video, for example, the video is a movie, and the public opinion information can be obtained based on analysis of comments, topics, news, hotspots and the like of the movie, which are obtained from a social platform, a news platform and the like, or based on analysis of comments, topics, news, hotspots and the like of novels, actors, directors and the like related to the movie.

S32: the server obtains an auditing priority aiming at the target multimedia content based on the media information and the public opinion information;

in an alternative embodiment, before performing step S32, a push decision for the target multimedia content is further needed, that is, whether the target multimedia content can be predicted by a pre-review of the license plate party auditing system based on the media information and the public opinion information, and a corresponding push decision is obtained for the target multimedia content based on the first prediction result.

If the push decision indicates that the pre-review is passed, in step S32, optionally, the review emergency state of the target multimedia content is predicted based on the media information and the public opinion information to obtain a second prediction result, and the review priority for the target multimedia content is determined based on the second prediction result.

If the pushing decision indicates that the target multimedia content does not pass the pre-review, the target multimedia content does not need to be pushed to the license plate party for further review, and in order to ensure that the target multimedia content can be put on the shelf in the APP, prompt information aiming at the target multimedia content can be displayed to the video platform party, wherein the prompt information is used for representing the reason why the pre-review does not pass the pre-review, so that the video platform party can pass the pre-review of the license plate party review system after modifying the target multimedia content according to the prompt information, and further the review passing rate is improved.

S33: the server pushes the media information and the auditing priority of the target multimedia content to the license party auditing system so that the license party auditing system audits the media information based on the auditing priority.

In an optional implementation manner, after receiving the media asset information and the review priority uploaded by the video platform side, the license party review system sequences the target multimedia contents according to the review priority, determines the sequence of the target multimedia contents in the review queue, further reviews the media asset information of the target multimedia contents according to the determined sequence, and issues a license plate for the target multimedia contents when the media asset information review is passed.

It is assumed that, in the embodiment of the present application, the auditing priorities of the multimedia contents are divided into: level 1 (representing the highest priority), level 2 (representing the middle priority) and level 3 (representing the lowest priority),

for example, the auditing priority of the target multimedia content is 1 level, and it is assumed that there are 5 multimedia contents to be audited in the auditing queue, and the ordering is to-be-audited video 1, to-be-audited video 2, to-be-audited video 3, to-be-audited video 4, and to-be-audited video 5, where the auditing priorities of to-be-audited video 1 and to-be-audited video 2 are 1 level, the auditing priority of to-be-audited video 3 is 2 level, and the auditing priorities of to-be-audited video 4 and to-be-audited video 5 are 3 level.

For multimedia contents to be audited at the same level, sorting can be performed according to the push time, such as the listed video 1 to be audited and the video 2 to be audited, where the push time of the video 1 to be audited is earlier than that of the video 2 to be audited, and thus the video 1 to be audited is arranged before the video 2 to be audited. For the multimedia contents to be audited of different levels, sorting is performed according to the auditing priority, for example, the video 2 to be audited is level 1, the video 3 to be audited is level 2, and at this time, the video 2 to be audited is arranged before the video 3 to be audited. Based on the above rules, the target multimedia content has an audit priority level of 1, and therefore should be arranged before the video 3 to be audited, and the push time of the target multimedia content is later than the video 1 to be audited and the video 2 to be audited, and after the target multimedia content is finally added, the audit queue is: the method comprises the following steps of 1, 2, 4 and 5, wherein the video to be audited comprises a video to be audited, target multimedia content, a video to be audited 3, a video to be audited 4 and a video to be audited 5.

When the license party auditing system audits according to the auditing queue, the media information of the video 1 to be audited needs to be audited preferentially, the media information of the video 2 to be audited is further audited, the media information of the target multimedia content is further audited, and the like. In addition, for the multimedia content whose auditing has been completed, it needs to be deleted from the auditing queue.

In the above embodiment, the auditing priority of the target multimedia content is predicted through the media information of the target multimedia content and the related public opinion information, and is pushed to the licensor auditing system, so that the high-quality content can be preferentially pushed to the licensor for auditing, the target multimedia content is audited by the licensor auditing system based on the auditing priority, the output of the high-quality content can be ensured, and the accuracy of pushing the multimedia content can be improved.

Fig. 4 is a diagram illustrating a license plate side auditing media asset delivery system architecture based on machine learning according to an embodiment of the present application. The system for auditing and pushing the media assets by the license plate party mainly comprises an online system and an offline system, wherein the online system comprises three parts: the off-line system comprises a model training platform and a public opinion monitoring system. The details of the parts of the media asset pushing system examined by the license plate party are as follows:

the online system user side mainly comprises terminal equipment, and the terminal equipment is provided with a video APP.

The terminal equipment provides online video service for the user, and meanwhile collects behavior data, playing data and the like of the APP used by the user as historical behavior information of the user.

In the embodiment of the present application, the historical behavior information specifically refers to related information such as a playing amount, a playing time, a video playing completion ratio, a video comment amount, a related comment amount, a praise and trample amount, and the like of a video. In addition, in the embodiment of the present application, when the historical behavior information of the user is collected, behavior data and play data of a plurality of users for a certain multimedia content may be collected as the historical behavior information related to the multimedia content. The online system video platform side is a background server corresponding to the video APP and mainly comprises a video content injection system, a media asset verification pushing system, a video platform media asset library, a real-time decision making system, a verification information synchronization server and a license plate verification information library. In the embodiment of the application, the video content injection system, the media asset auditing and pushing system, the video platform media asset library, the real-time decision-making system, the auditing information synchronization server and the license plate auditing information library may correspond to different servers, or two or more of them may be integrated on one server, which is not specifically limited herein.

The video Content injection system is used for submitting and processing newly submitted video Content, such as copyright drama shelving and User Generated Content (UCG) uploading, and is also used for standardizing the video Content, supplementing related media asset information, writing the video media asset information into a video platform media asset library, and simultaneously sending a new video Content injection message.

Wherein, standardizing the video content includes checking whether necessary media information fields are filled, whether picture sizes are normal, brief introduction, whether recommendation information is healthy, and the like.

And the media asset auditing and pushing system is used for subscribing the video content injection message issued by the video content injection system, acquiring the video id of the newly injected video content and requesting the real-time decision-making system to acquire the push decision-making result and the auditing priority of the newly injected video content. That is, the real-time decision system may predict to obtain a corresponding push decision based on the media asset information of the newly injected video content and the related public opinion information, and further perform priority prediction on the video content of which the push decision is yes (i.e. indicating that the pre-review is passed), to obtain a corresponding review priority. And further, inquiring detailed media information and audit priority corresponding to the video id, organizing data according to a push protocol, calling an interface provided by a license plate party, and pushing the media information and the audit priority as license plate audit data to a license plate party audit system. And for the video content with the push decision of no (that is, the video content indicates that the pre-review fails), invoking an audit information synchronization service, and recording an audit result corresponding to the video id of the video content as the rejection of the decision system.

And the audit information synchronization service is used for writing the audit result back to the license plate audit information base for storage. The auditing result is obtained by auditing the license party auditing system based on the media information of the video content and the auditing priority, and the auditing result is synchronized back to the video platform by calling the auditing information synchronization service by the license party auditing system.

The real-time decision system is used for loading the media asset pre-auditing model trained by the model training platform, inquiring the related information of the media assets according to the video id and performing auditing decision on the video content; in addition, the method can also be used for loading the trained auditing priority prediction model of the model training platform and predicting the priority of the video content. Meanwhile, the real-time decision system also supports the traditional filtering of the examination and verification content according to the rules, and can quickly realize the filtering of the license examination and verification content in an emergency.

In an optional implementation manner, the specific process when performing an audit decision on target video content based on a trained media resource pre-audit model is as follows:

inputting the media information and related public opinion information of the target video content into a trained media resource pre-examination model, extracting attribute characteristics of the media information and the public opinion information based on the media resource pre-examination model, predicting whether the target video content can be pre-examined by a license plate party auditing system based on the extracted attribute characteristics, and obtaining a pushing decision result aiming at the target video content based on a first prediction result, wherein the result is a binary result and is used for indicating whether the pre-examination is passed or not. The attribute features are used for representing attributes related to the target video content preview push in the media information and public sentiment information, such as whether the attributes are related to a certain star, whether the attributes are of a certain type, subject and the like.

The system comprises a media asset pre-auditing model, a license party auditing system and a system management system, wherein the media asset pre-auditing model is obtained by training based on a first training sample data set, training samples in the first training sample data set comprise sample multimedia content, license auditing information, media asset information and public opinion information related to the sample multimedia content, a decision label for representing a real pushing decision is marked on each training sample, and the license party auditing information is used for representing auditing detail information when a license party auditing system is used for auditing the sample multimedia content.

Specifically, the license party audit information is also called medium asset audit information. The method mainly comprises a plurality of parts, including media resource id (such as album id and video id), audit result (audit pass and audit reject), audit reason (yellow content reject, bad track artist reject and the like), auditors, audit time and the like.

In an optional implementation manner, when the push decision result indicates that the pre-review is passed, the review priority of the target multimedia content may be further predicted based on the above listed trained review priority prediction model, which includes the following specific processes:

inputting the media information and public opinion information of the target video content into a trained auditing priority prediction model, extracting the urgency characteristics of the media information and the public opinion information based on the auditing priority prediction model, predicting the auditing urgency state of the target video content based on the extracted urgency characteristics to obtain a second prediction result, and determining the auditing priority aiming at the target video content based on the second prediction result. The urgency feature is used for representing media information and some features related to the public opinion attention of the target video content in the public opinion information.

The online system license plate side is a server used for auditing the license plate side and mainly comprises a license plate side media asset receiving system, a license plate side auditing system and a license plate side media asset library. In the embodiment of the present application, the license party media asset receiving system, the license party auditing system, and the license party media asset library may correspond to different servers, or may be implemented by integrating two or more parts on one server, which is not specifically limited herein.

The license plate side media asset receiving system is used for performing warehousing operation after receiving audit media asset information pushed by a video platform, storing the video media asset information into a license plate side media asset library, and simultaneously adding video id of each video content to be audited into a grading queue according to audit priority, wherein the grading queue is also called an audit queue.

And the license party auditing system is used for inquiring the related information of the media resources from the license party media resource library for auditing after acquiring the video id of the video content to be audited from the hierarchical queue, synchronously returning the auditing result to the video platform by calling the auditing information synchronization service of the video platform, and issuing license plates for the approved video content, so that the video platform can put on the shelf to audit the approved video content.

And the offline system model training platform is used for training the media pre-audit model and the audit priority prediction model by loading the playing data and the behavior data of the user, the audit data of the license plate party and the information collected by the public opinion monitoring system. In the embodiment of the application, data collected on the basis of an online system user side is reported to a data warehouse through a data reporting channel for storage. The model training platform can load information such as stored user playing data and behavior data from the data warehouse. This part of the training process will be described in detail below with reference to the accompanying drawings.

And the public opinion monitoring system is used for identifying hot spots, tracking topics, tracking new hot topics of the current society in time and providing input data for model training.

Fig. 5 is a schematic diagram illustrating a media asset pushing process according to an embodiment of the present disclosure. In the application, two models are realized, namely a media resource pre-auditing model realized based on a machine learning classification algorithm (such as a Gradient Boosting Decision Tree (GBDT) binary classification algorithm) and an auditing priority prediction model realized based on a regression algorithm (such as a GBDT regression algorithm). The detailed flow is described as follows:

1) on the model training platform, a media resource pre-examination model is trained through a machine learning classification algorithm based on the existing license plate party media resource examination information (namely license plate examination information), video media resource basic data (namely media resource information) stored by a video platform and public opinion monitoring data (namely public opinion information) such as social negative information and social hotspot information acquired by a public opinion monitoring system.

2) And the real-time decision system loads the trained media resource pre-auditing model, receives a video updating notice and pre-audits the updated video content. The media asset pre-review check model listed in the embodiment of the application is a two-classification model, and the output result is a push decision representing whether pre-review passes or pre-review fails. And (4) putting the video content which cannot be subjected to pre-examination into a pre-examination rejection media pool, and not pushing the video content to the license plate. And executing the step 4 for prereviewing the passed video content.

3) On the model training platform, public opinion monitoring data (namely public opinion information) such as video medium asset basic data (namely medium asset information) stored in the video platform, social negative information and social hotspot information acquired by a public opinion monitoring system, user behavior data and user playing data (generally called related historical behavior information) collected by the video platform are used as input, and an audit priority prediction model is trained through a regression algorithm of machine learning.

4) And loading the trained auditing priority prediction model by the real-time decision system, performing heat prediction on the video content passing the pre-auditing in the step 2, outputting a heat prediction result (namely the auditing priority) corresponding to the video, and putting the result into a to-be-audited media asset pool.

5) The media asset auditing and pushing service reads the corresponding video content from the media asset pool to be audited and pushes the video content to the license plate party.

And further, the license plate party auditing system performs media asset auditing based on the received auditing priority of the video content and the video content, and issues license plates for the video content which is approved.

In an alternative embodiment, the medium resource pre-auditing model is trained as follows:

and according to the training samples in the first training sample data set, performing cycle iterative training on the media asset pre-auditing model, and outputting the trained media asset pre-auditing model after the training is finished. It should be noted that, in the embodiment of the present application, the training method of the medium resource pre-review model may be executed by a server or a terminal device alone, or may be executed by both the server and the terminal device. Specifically, referring to fig. 6, it is a flowchart of a training method of a media asset pre-review model in the embodiment of the present application, which is described by taking an example of execution by a server, and a specific implementation flow of the method is as follows:

s61: the server selects a training sample from the first training sample data set;

s62: the server inputs license plate auditing information, media information and public opinion information related to sample multimedia contents in the training sample into a media resource pre-auditing model, and predicts whether the sample multimedia contents can be pre-audited by a license plate party auditing system based on the media resource pre-auditing model to obtain a pre-estimated pushing decision for the sample multimedia contents;

s63: and the server adopts a classification algorithm to carry out parameter adjustment on the media asset pre-examination model based on the error between the estimated push decision and the decision label corresponding to the sample multimedia content in the training sample.

The estimated pushing decision is used for representing whether the sample multimedia content is pushed or not and whether the sample multimedia content is pushed or not to be audited to a license plate side, the result is obtained by model prediction, the result is compared with a decision label (the label represents a real result) in the training sample, and the model is subjected to parameter adjustment based on errors.

In an alternative embodiment, the audit priority prediction model is trained by:

and according to the training samples in the second training sample data set, performing loop iterative training on the audit priority prediction model, and outputting the trained audit priority prediction model when the training is finished. It should be noted that, in the embodiment of the present application, the training method for the audit priority prediction model may be executed by a server or a terminal device alone, or may be executed by both the server and the terminal device. Each loop iteration training process includes the following operations, which are shown in fig. 7, which is a flowchart of a training method for auditing a priority prediction model in the embodiment of the present application, and is described here as an example executed by a server, and a specific implementation flow of the method is as follows:

s71: the server selects training samples from the second training sample data set;

s72: the server inputs historical behavior information, media information and public opinion information related to sample multimedia contents in the training sample into an auditing priority prediction model, and predicts an auditing emergency state of the sample multimedia contents based on the auditing priority prediction model to obtain an estimated auditing priority aiming at the sample multimedia contents;

s73: and the server adopts a regression algorithm to carry out parameter adjustment on the auditing priority prediction model based on the error between the estimated auditing priority and the priority label corresponding to the sample multimedia content in the training sample.

The estimated auditing priority is used for representing the estimated popularity of the multimedia content of the sample, the result is obtained by model prediction, the result is compared with a priority label (the label represents the real priority/popularity) in the training sample, and the model is subjected to parameter adjustment based on errors.

Specifically, the medium resource pre-auditing model may be a tree model such as GBDT, XGBoost, or other machine learning model, which is not limited herein. The condition of finishing training may be that the model converges, or that the number of iterations reaches an upper limit, and the like, and is not specifically limited herein.

Referring to fig. 8, a flowchart of another method for pushing multimedia content according to an embodiment of the present application is shown. It should be noted that the method may be executed by the server or the terminal device alone, or may be executed by both the server and the terminal device. Here, the server is executed as an example, where the server is a server used for auditing by a licensor and may also be referred to as an auditing system of the licensor, and the specific implementation flow is as follows:

s81: the method comprises the steps that a server obtains media information and audit priority of target multimedia content, wherein the audit priority is obtained based on public opinion information and media information related to the target multimedia content, the media information is used for representing media information attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content;

s82: and the server audits the media information based on the audit priority.

In an optional implementation manner, auditing the media information based on the auditing priority specifically includes the following two steps:

s821: the server determines the sequence of the target multimedia content in the auditing queue according to the auditing priority, and audits the media information according to the determined sequence;

s822: and when the media information is approved, the server issues license plates aiming at the target multimedia content.

It should be noted that, for the specific implementation of the foregoing embodiment, reference may be made to the above related contents, and repeated details are not described again.

Fig. 9 is an interaction timing chart of a video content push method according to an embodiment of the present application. The video platform refers to a background server corresponding to the video APP. The specific implementation flow of the method is as follows:

step S901: the video platform acquires media asset information of target video content and public opinion information related to the target video content;

step S902: the video platform respectively inputs the media asset information and public opinion information into the trained media asset pre-review model to obtain corresponding push decision results;

step S903: when the decision pushing result shows that the pre-review is passed, the video platform respectively inputs the media information and the public opinion information into the trained review priority prediction model to obtain corresponding review priorities;

step S904: the video platform pushes the media information and the auditing priority of the target video content to an auditing system of a licensor;

step S905: the license party auditing system audits the media information based on the auditing priority to obtain an auditing result;

step S906: the license party auditing system synchronizes the auditing result to the video platform by calling an auditing result synchronization interface of the video platform;

step S907: and the video platform determines whether the target video content is on shelf or not according to the auditing result.

In the embodiment of the application, through playing amount, playing time length, video playing completion ratio, video comment amount, attention amount and praise stepping amount of videos passing on line auditing, combining with the auditing capacity of a licensor and the auditing information of the licensor, feature extraction and analysis modeling are performed to obtain a licensor media asset auditing and pushing model which comprises a media asset pre-auditing and checking priority level predicting model and for newly produced media asset information, the heat of contents and the condition of passing of license auditing are predicted and evaluated through the two models, and an evaluation result comprises a pushing decision for representing whether the contents are pushed or not and an auditing priority level for representing the heat. And directly filtering the contents which are not pushed by model prediction. And for the content pushed by the model prediction, while pushing the media information, synchronously auditing the priority to the license plate party, and the license plate party organizes an auditing queue according to the auditing priority to preferentially ensure that the video content with high priority is audited first. Based on the method, the hot contents of the head can be preferentially pushed to a license plate party for examination, and the output of the high-quality contents of the head can be ensured to the greatest extent.

Based on the same inventive concept, the embodiment of the application also provides a pushing device of the multimedia content. As shown in fig. 10, it is a schematic structural diagram of a multimedia content pushing apparatus 1000, which may include:

an information obtaining unit 1001, configured to obtain media information of a target multimedia content and public opinion information related to the target multimedia content, where the media information is used to represent attribute information of the target multimedia content, and the public opinion information is used to represent public opinion attention related to the target multimedia content;

the prediction unit 1002 is configured to obtain an audit priority for the target multimedia content based on the media information and the public opinion information;

the pushing unit 1003 is configured to push the media asset information and the audit priority of the target multimedia content to the licensor audit system, so that the licensor audit system audits the media asset information based on the audit priority.

According to the embodiment of the application, the auditing priority of the target multimedia content is predicted through the media information of the target multimedia content and the related public opinion information and is pushed to the licensor auditing system, so that the high-quality content can be preferentially pushed to the licensor for auditing, the target multimedia content is audited by the licensor auditing system based on the auditing priority, the output of the high-quality content can be guaranteed, the pushing accuracy of the multimedia content is improved, and the auditing efficiency of the licensor is improved.

Optionally, the prediction unit 1002 is further configured to:

before obtaining an auditing priority aiming at target multimedia content based on media information and public opinion information, predicting whether the target multimedia content can be pre-audited by an auditing system of a license plate party based on the media information and the public opinion information, and obtaining a corresponding pushing decision aiming at the target multimedia content based on a first prediction result;

the prediction unit 1002 is specifically configured to:

and if the pushing decision indicates that the pre-review is passed, predicting the review emergency state of the target multimedia content based on the media information and the public sentiment information to obtain a second prediction result, and determining the review priority aiming at the target multimedia content based on the second prediction result.

Optionally, the pushing unit 1003 is specifically configured to:

and pushing the auditing priority of the target multimedia content and the media information to a license party auditing system so that the license party auditing system determines the sequence of the target multimedia content in an auditing queue according to the auditing priority, audits the media information according to the determined sequence, and issues a license plate aiming at the target multimedia content when the media information auditing is passed.

Optionally, the prediction unit 1002 is specifically configured to:

inputting the media information and public opinion information into a trained media resource pre-examination model, extracting attribute characteristics of the media information and the public opinion information based on the media resource pre-examination model, predicting whether the target multimedia content can be pre-examined by a license party auditing system based on the extracted attribute characteristics, and obtaining a pushing decision aiming at the target multimedia content based on a first prediction result;

Optionally, the media information and the public opinion information are input into a trained auditing priority prediction model, after emergency characteristic extraction is performed on the media information and the public opinion information based on the auditing priority prediction model, the auditing emergency state of the multimedia content is predicted based on the extracted emergency characteristic, a second prediction result is obtained, and the auditing priority for the target multimedia content is determined based on the second prediction result;

Optionally, the apparatus further comprises:

the first training unit 1004 is used for training to obtain a media pre-review model by the following steps:

according to the training samples in the first training sample data set, performing cycle iterative training on the media asset pre-auditing model, and outputting the trained media asset pre-auditing model when the training is finished; wherein, each loop iteration training process comprises the following operations:

selecting training samples from a first training sample data set;

inputting license plate auditing information, media asset information and public opinion information related to sample multimedia contents in a training sample into a media asset pre-auditing model, predicting whether the sample multimedia contents can be predicted through pre-auditing of a license plate party auditing system based on the media asset pre-auditing model, and obtaining a pre-estimation pushing decision aiming at the sample multimedia contents;

and based on the error between the estimated push decision and the decision label corresponding to the sample multimedia content in the training sample, performing parameter adjustment on the media resource pre-audit model by adopting a classification method.

Optionally, the apparatus further comprises:

a second training unit 1005, configured to train to obtain the audit priority prediction model by:

selecting training samples from the second training sample data set;

inputting historical behavior information, media asset information and public opinion information related to sample multimedia contents in a training sample into an auditing priority prediction model, predicting an auditing emergency state of the sample multimedia contents based on the auditing priority prediction model, and obtaining an estimated auditing priority aiming at the sample multimedia contents;

Based on the same inventive concept, the embodiment of the application also provides another pushing device for multimedia content. As shown in fig. 11, it is a schematic structural diagram of another pushing device 1100 for multimedia content, which may include:

a priority obtaining unit 1101, configured to obtain media information of the target multimedia content and an audit priority, where the audit priority is obtained based on public opinion information and media information related to the target multimedia content, the media information is used to represent media information attribute information of the target multimedia content, and the public opinion information is used to represent a public opinion attention related to the target multimedia content;

the auditing unit 1102 audits the media information based on the auditing priority.

Optionally, the auditing unit 1102 is specifically configured to:

determining the order of the target multimedia content in the audit queue according to the audit priority, and auditing the media information according to the determined order;

and when the media information is approved, issuing license plates aiming at the target multimedia content.

For convenience of description, the above parts are separately described as modules (or units) according to functional division. Of course, the functionality of the various modules (or units) may be implemented in the same one or more pieces of software or hardware when implementing the present application.

Having described the method and apparatus for pushing multimedia content according to an exemplary embodiment of the present application, an electronic device according to another exemplary embodiment of the present application will be described next.

As will be appreciated by one skilled in the art, aspects of the present application may be embodied as a system, method or program product. Accordingly, various aspects of the present application may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.

The electronic equipment is based on the same inventive concept as the method embodiment. The electronic device may be used for the push of multimedia content. In one embodiment, the electronic device may be a server, such as server 220 shown in FIG. 2. In this embodiment, the electronic device may be configured as shown in fig. 12, and include a memory 1201, a communication module 1203, and one or more processors 1202.

A memory 1201 for storing computer programs executed by the processor 1202. The memory 1201 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, a program required for running an instant messaging function, and the like; the storage data area can store various instant messaging information, operation instruction sets and the like.

The memory 1201 may be a volatile memory (RAM), such as a random-access memory (RAM); the memory 1201 may also be a non-volatile memory (non-volatile memory), such as a read-only memory (rom), a flash memory (flash memory), a hard disk (HDD) or a solid-state drive (SSD); or the memory 1201 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 1201 may be a combination of the above memories.

The processor 1202 may include one or more Central Processing Units (CPUs), a digital processing unit, and the like. The processor 1202 is configured to implement the above-described pushing method for multimedia content when calling the computer program stored in the memory 1201.

The communication module 1203 is used for communicating with the terminal device and other servers.

In the embodiment of the present application, the specific connection medium between the memory 1201, the communication module 1203 and the processor 1202 is not limited. In the embodiment of the present application, the memory 1201 and the processor 1202 are connected by the bus 1204 in fig. 12, the bus 1204 is represented by a thick line in fig. 12, and the connection manner between other components is only schematically illustrated and is not limited. The bus 1204 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 12, but this is not intended to represent only one bus or type of bus.

The memory 1201 stores a computer storage medium, and the computer storage medium stores computer-executable instructions for implementing the method for pushing multimedia content according to the embodiment of the present disclosure. The processor 1202 is configured to execute the pushing method of the multimedia content as described above, as shown in fig. 3 or fig. 8.

In another embodiment, the electronic device may also be other electronic devices, such as the terminal device 210 shown in fig. 2. In this embodiment, the structure of the electronic device may be as shown in fig. 13, including: a communication assembly 1310, a memory 1320, a display unit 1330, a camera 1340, a sensor 1350, an audio circuit 1360, a bluetooth module 1370, a processor 1380, and the like.

The communication component 1310 is for communicating with a server. In some embodiments, a WiFi (Wireless Fidelity) module may be included, the WiFi module belongs to a short-distance Wireless transmission technology, and the electronic device may help the user to send and receive information through the WiFi module.

Memory 1320 may be used to store software programs and data. The processor 1380 performs various functions of the terminal device 210 and data processing by executing software programs or data stored in the memory 1320. The memory 1320 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. The memory 1320 stores an operating system that enables the terminal device 210 to operate. The memory 1320 may store an operating system and various application programs, and may also store codes for executing the multimedia content pushing method according to the embodiment of the present application.

The display unit 1330 may also be used to display information input by or provided to the user and a Graphical User Interface (GUI) of various menus of the terminal apparatus 210. Specifically, the display unit 1330 may include a display screen 1332 provided on the front surface of the terminal device 210. The display 1332 may be configured in the form of a liquid crystal display, a light emitting diode, or the like. The display unit 1330 may be configured to display video frames of a video client in the embodiment of the present application.

The display unit 1330 may also be configured to receive input numeric or character information, generate signal inputs related to user settings and function control of the terminal device 210, and specifically, the display unit 1330 may include a touch screen 1331 disposed on the front surface of the terminal device 210 and configured to collect touch operations by a user thereon or nearby, such as clicking a button, dragging a scroll box, and the like.

The touch screen 1331 may cover the display screen 1332, or the touch screen 1331 and the display screen 1332 may be integrated to implement the input and output functions of the terminal device 210, and after integration, the touch screen may be referred to as a touch display screen for short. The display unit 1330 may display the application programs and the corresponding operation steps.

The camera 1340 may be used to capture still images, and the user may upload comments from the images captured by the camera 1340 via the video client. The number of the cameras 1340 may be one or more. The object generates an optical image through the lens and projects the optical image to the photosensitive element. The photosensitive element may be a Charge Coupled Device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The light sensing elements convert the light signals into electrical signals, which are then passed to a processor 1380 for conversion into digital image signals.

The terminal device may further comprise at least one sensor 1350, such as an acceleration sensor 1351, a distance sensor 1352, a fingerprint sensor 1353, a temperature sensor 1354. The terminal device may also be configured with other sensors such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, light sensor, motion sensor, and the like.

The audio circuit 1360, speaker 1361, microphone 1362 may provide an audio interface between the user and the terminal device 210. The audio circuit 1360 may transmit the electrical signal converted from the received audio data to the speaker 1361, and the electrical signal is converted into a sound signal by the speaker 1361 and output. The terminal device 210 may also be provided with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 1362 converts the collected sound signal into an electrical signal, converts the electrical signal into audio data after being received by the audio circuit 1360, and then outputs the audio data to the communication module 1310 to be transmitted to, for example, another terminal device 210, or outputs the audio data to the memory 1320 for further processing.

The bluetooth module 1370 is used for information interaction with other bluetooth devices having a bluetooth module through a bluetooth protocol. For example, the terminal device may establish a bluetooth connection with a wearable electronic device (e.g., a smart watch) that is also equipped with a bluetooth module through the bluetooth module 1370, so as to perform data interaction.

The processor 1380 is a control center of the terminal device, connects various parts of the entire terminal device using various interfaces and lines, and performs various functions of the terminal device and processes data by running or executing software programs stored in the memory 1320 and calling data stored in the memory 1320. In some embodiments, processor 1380 may include one or more processing units; the processor 1380 may also integrate an application processor, which primarily handles operating systems, user interfaces, application programs, and the like, and a baseband processor, which primarily handles wireless communications. It will be appreciated that the baseband processor may not be integrated into the processor 1380. The processor 1380 in the present application may run an operating system, an application program, a user interface display, a touch response, and a method for pushing multimedia content according to the present embodiment. Additionally, a processor 1380 is coupled to the display unit 1330.

In some possible embodiments, various aspects of the multimedia content push method provided by the present application may also be implemented in the form of a program product including program code for causing an electronic device to perform the steps in the multimedia content push method according to various exemplary embodiments of the present application described above in this specification when the program product is run on the electronic device, for example, the electronic device may perform the steps as shown in fig. 3 or fig. 8.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The program product of embodiments of the present application may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a computing device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with a command execution system, apparatus, or device.

A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with a command execution system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media capable of storing program codes, such as a removable Memory device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, and an optical disk.

Alternatively, the integrated unit in the embodiment of the present application may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a stand-alone product. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.

While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following appended claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such changes and modifications of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such changes and modifications.

Claims

1. A method for pushing multimedia content, the method comprising:

2. The method of claim 1, wherein prior to the obtaining of the review priority for the target multimedia content based on the media information and the public opinion information, further comprising:

and predicting whether the target multimedia content can be pre-checked by a license plate party checking system or not based on the media information and the public opinion information, and obtaining a corresponding pushing decision aiming at the target multimedia content based on a first prediction result.

3. The method of claim 2, wherein obtaining an audit priority for the target multimedia content based on the media information and the public opinion information comprises:

and if the pushing decision indicates that the pre-review is passed, predicting the review emergency state of the target multimedia content based on the media information and the public opinion information to obtain a second prediction result, and determining the review priority aiming at the target multimedia content based on the second prediction result.

4. The method according to any one of claims 1 to 3, wherein the pushing of the media asset information of the target multimedia content and the review priority to a licensor review system so that the licensor review system reviews the media asset information based on the review priority comprises:

and pushing the auditing priority of the target multimedia content and the media information to the license party auditing system so that the license party auditing system determines the sequence of the target multimedia content in an auditing queue according to the auditing priority, audits the media information according to the determined sequence, and issues a license plate aiming at the target multimedia content when the media information auditing is passed.

5. The method of claim 2, wherein the predicting whether the target multimedia content can be pre-checked by a license party checking system based on the media information and the public opinion information, and obtaining a corresponding push decision for the target multimedia content based on a first prediction result specifically comprises:

6. The method of claim 3, wherein the predicting the review emergency status of the target multimedia content based on the media information and the public opinion information to obtain a second prediction result, and determining the review priority for the target multimedia content based on the second prediction result specifically comprises:

inputting the media information and the public opinion information into a trained auditing priority prediction model, extracting the urgency characteristics of the media information and the public opinion information based on the auditing priority prediction model, predicting the auditing urgency state of the target multimedia content based on the extracted urgency characteristics to obtain a second prediction result, and determining the auditing priority aiming at the target multimedia content based on the second prediction result;

7. The method of claim 5, wherein the medium resource pre-review model is trained by:

selecting training samples from the first training sample data set;

8. The method of claim 6, wherein the audit priority prediction model is trained by:

selecting training samples from the second training sample data set;

inputting historical behavior information, media asset information and public opinion information related to sample multimedia contents in the training sample into an auditing priority prediction model, predicting an auditing emergency state of the sample multimedia contents based on the auditing priority prediction model, and obtaining an estimated auditing priority aiming at the sample multimedia contents;

9. A method for pushing multimedia content, the method comprising:

acquiring media information and an audit priority of target multimedia content, wherein the audit priority is obtained based on public opinion information related to the target multimedia content and the media information, the media information is used for representing media information attribute information of the target multimedia content, and the public opinion information is used for representing public opinion attention related to the target multimedia content;

and auditing the media information based on the auditing priority.

10. The method of claim 9, wherein the auditing the media asset information based on the audit priority comprises:

11. A pushing apparatus for multimedia content, comprising:

12. The apparatus of claim 11, wherein the prediction unit is further to:

before obtaining the auditing priority aiming at the target multimedia content based on the media information and the public opinion information, predicting whether the target multimedia content can be pre-audited by a license party auditing system based on the media information and the public opinion information, and obtaining a corresponding pushing decision aiming at the target multimedia content based on a first prediction result.

13. A pushing apparatus for multimedia content, comprising:

14. An electronic device, comprising a processor and a memory, wherein the memory stores program code which, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 8 or the steps of the method of any of claims 9 to 10.

15. A computer-readable storage medium, characterized in that it comprises program code for causing an electronic device to perform the steps of the method of any of claims 1-8 or the steps of the method of any of claims 9-10, when said program code is run on said electronic device.