CN106792004B

CN106792004B - Content item pushing method, device and system

Info

Publication number: CN106792004B
Application number: CN201611262115.3A
Authority: CN
Inventors: 陈志军
Original assignee: Beijing Xiaomi Mobile Software Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd
Priority date: 2016-12-30
Filing date: 2016-12-30
Publication date: 2020-09-15
Anticipated expiration: 2036-12-30
Also published as: CN106792004A

Abstract

The disclosure relates to a content item pushing method, a device and a system, and belongs to the technical field of multimedia. The method comprises the following steps: acquiring a media file to be displayed or being displayed at a current terminal; carrying out key information identification on related information of images in the media files to obtain target key information, wherein the key information is used for indicating at least one of scenes, objects and people; acquiring a target content item according to the target key information; and in the process of displaying the media file by the terminal, pushing the target content item to the terminal. The method and the device solve the problems that the pushing of the content items is not accurate enough and the user feels dislike easily, achieve the effect of accurately pushing the content items according to the preference of the user, and combine the content items with the media files for displaying, so that the displaying is more vivid. The present disclosure is for content item push.

Description

Content item pushing method, device and system

Technical Field

The present disclosure relates to the field of multimedia technologies, and in particular, to a method, an apparatus, and a system for pushing content items.

Background

With the development of internet technology, more and more merchants choose to deliver content items, such as advertisements, through the internet, and with the popularization of terminals, a server can push advertisements to the terminals through the internet so that the terminals can display the advertisements.

In the related art, an application or an IOS (operating system) of a terminal usually obtains the age, gender, and the like of a user of the terminal, and pushes advertisements according to the age, gender, and the like of the user, so as to achieve the purpose of pushing advertisements to suitable people and improve the directionality of advertisement pushing.

In implementing the present disclosure, the inventors found that the related art has at least the following problems:

even if the users are in the same age and gender, the preference of each user is different, the advertisement push is still not accurate enough, and the advertisement content is not related to the content on the terminal, so that the user feels easily dislike.

Disclosure of Invention

In order to solve the problems that content item pushing is not accurate enough and easily causes user discomfort, the embodiments of the present disclosure provide a content item pushing method, device and system. The technical scheme is as follows:

according to a first aspect of embodiments of the present disclosure, there is provided a content item pushing method, the method comprising:

acquiring a media file to be displayed or being displayed at a current terminal;

performing key information identification on related information of the images in the media files to obtain target key information, wherein the key information is used for indicating at least one of a scene, an object and a person;

acquiring a target content item according to the target key information;

and in the process of displaying the media file by the terminal, pushing the target content item to the terminal.

Optionally, the media file is a video file, the related information of the image includes the image, and performing key information identification on the related information of the image in the media file to obtain target key information includes:

extracting key frames of the media files to obtain a key frame set of the media files;

performing key information identification on each key frame in the key frame set to obtain a key information set corresponding to the key frame set, wherein the key information set comprises key information of each key frame in the key frame set;

determining the target key information in the set of key information.

Optionally, the determining the target key information in the key information set includes:

determining the occurrence frequency of each piece of key information in the key information set within a preset time period;

and determining the key information of which the occurrence frequency in a preset time period is greater than a preset frequency in the key information set as the target key information.

Optionally, the media file is an image file, the related information of the image includes the image and comment information of the image, and the performing key information identification on the related information of the image in the media file to obtain target key information includes:

performing key information identification on the image and the comment information of the image to obtain key information corresponding to the image;

and determining the key information corresponding to the image as the target key information.

Optionally, the image includes a face image, and the performing key information identification on the related information of the image in the media file to obtain target key information includes:

carrying out face feature recognition on the face image to obtain a target face feature corresponding to the face image;

determining a target person identification corresponding to the target face feature;

and determining the target person identification as the target key information.

Optionally, the obtaining of the target content item according to the target key information includes:

according to the target key information, inquiring the corresponding relation between the key information and the content items to obtain the content items corresponding to the target key information;

determining a content item corresponding to the target key information as the target content item;

and acquiring the target content item.

Optionally, the performing key information identification on the related information of the image in the media file to obtain target key information includes:

and inputting the relevant information of the image in the media file into an information identification model to obtain the target key information, wherein the information identification model is used for carrying out key information identification on the relevant information of the image.

Optionally, the method further comprises:

acquiring related information of at least one image;

extracting key information of related information of each image in the at least one image to obtain key information corresponding to each image;

and training to obtain the information recognition model according to the relevant information of each image in the at least one image and the key information corresponding to each image.

Optionally, the targeted content item is an advertisement and the targeted content item comprises a product purchase link.

According to a second aspect of embodiments of the present disclosure, there is provided a content item pushing method, the method comprising:

in the process of displaying a media file by a terminal, receiving a target content item pushed by a server, wherein the target content item is obtained according to target key information obtained by the server after the server identifies the key information of the relevant information of the image in the media file to obtain the target key information, and the key information is used for indicating at least one of a scene, an object and a person;

presenting the target content item on a content item slot, the content item slot located at a corner of a presentation interface of the media file.

Optionally, the method further comprises:

and marking the target key information corresponding to the target content item in a display interface of the media file.

According to a third aspect of the embodiments of the present disclosure, there is provided a content item pushing device, the device comprising:

the first acquisition module is configured to acquire a media file to be displayed or being displayed by a current terminal;

the identification module is configured to identify key information of the related information of the images in the media files to obtain target key information, wherein the key information is used for indicating at least one of scenes, objects and people;

a second obtaining module configured to obtain a target content item according to the target key information;

and the pushing module is configured to push the target content item to the terminal in the process of displaying the media file by the terminal.

Optionally, the media file is a video file, the related information of the image includes the image, and the identifying module includes:

the extraction submodule is configured to extract key frames of the media files to obtain a key frame set of the media files;

the identification submodule is configured to perform key information identification on each key frame in the key frame set to obtain a key information set corresponding to the key frame set, and the key information set comprises key information of each key frame in the key frame set;

a determining submodule configured to determine the target key information in the set of key information.

Optionally, the determining sub-module is configured to:

Optionally, the media file is an image file, the related information of the image includes the image and comment information of the image, and the identification module is configured to:

Optionally, the image includes a face image, and the recognition module is configured to:

and determining the target person identification as the target key information.

Optionally, the second obtaining module is configured to:

and acquiring the target content item.

Optionally, the identification module is configured to input the relevant information of the image in the media file into an information identification model, so as to obtain the target key information, where the information identification model is used to perform key information identification on the relevant information of the image.

Optionally, the apparatus further comprises:

a third acquisition module configured to acquire information related to at least one image;

the extraction module is configured to extract key information of related information of each image in the at least one image to obtain key information corresponding to each image;

the training module is configured to train to obtain the information recognition model according to the relevant information of each image in the at least one image and the key information corresponding to each image.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a content item pushing device, the device comprising:

the receiving module is configured to receive a target content item pushed by a server in a process that a terminal displays a media file, wherein the target content item is obtained according to target key information obtained by the server after the server identifies the key information of related information of an image in the media file to obtain the target key information, and the key information is used for indicating at least one of a scene, an object and a person;

a presentation module configured to present the target content item on a content item slot, the content item slot located at a corner of a presentation interface of the media file.

Optionally, the apparatus further comprises: and the marking module is configured to mark the target key information corresponding to the target content item in the display interface of the media file.

According to a fifth aspect of embodiments of the present disclosure, there is provided a content item pushing apparatus comprising:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to:

acquiring a target content item according to the target key information;

According to a sixth aspect of embodiments of the present disclosure, there is provided a content item pushing apparatus comprising:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to:

According to a seventh aspect of embodiments of the present disclosure, there is provided a content item push system,

in one possible implementation, the system includes: the content item push device of the third aspect or any alternative form of the third aspect, and the content item push device of the fourth aspect or any alternative form of the fourth aspect;

in another possible implementation, the system includes: a content item push device according to the fifth aspect, and a content item push device according to the sixth aspect.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

according to the content item pushing method, the content item pushing device and the content item pushing system, the server can identify key information of relevant information of images in the media files to obtain target key information, obtain the target content items according to the target key information, and push the target content items to the terminal in the process of displaying the media files on the terminal, so that the server can push the content items according to the preferences of users by combining the media files, the problems that the content items are not pushed accurately enough and the user feels dislike easily are solved, the effect of accurately pushing the content items according to the preferences of the users is achieved, and the content items and the media files can be displayed in a combined mode, so that the display is more vivid.

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

Drawings

In order to more clearly illustrate the embodiments of the present disclosure, the drawings that are needed to be used in the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and that other drawings can be obtained by those skilled in the art without inventive effort.

FIG. 1 is a schematic block diagram of an implementation environment to which various embodiments of the present disclosure relate;

FIG. 2 is a flow diagram illustrating a method of pushing a content item, according to an exemplary embodiment;

FIG. 3 is a method flow diagram illustrating a method of pushing a content item in accordance with another exemplary embodiment;

FIG. 4-1 is a method flow diagram illustrating a method of pushing a content item according to yet another exemplary embodiment;

FIG. 4-2 is a flow chart illustrating a method for identifying key information associated with an image in a media file according to the embodiment of FIG. 4-1;

FIG. 4-3 is a flow diagram of a method for determining target key information in a set of key information according to the embodiment shown in FIG. 4-1;

FIG. 4-4 is a flow chart illustrating another method for identifying key information associated with an image in a media file according to the embodiment of FIG. 4-1;

4-5 are flow diagrams of still another method for identifying key information associated with an image in a media file according to the embodiment shown in FIG. 4-1;

4-6 are flow diagrams of a method for retrieving a target content item based on target key information according to the embodiment shown in FIG. 4-1;

4-7 are schematic diagrams of a terminal presenting a target content item as shown in the embodiment of FIG. 4-1;

FIG. 5-1 is a block diagram illustrating a content item pushing device in accordance with an exemplary embodiment;

FIG. 5-2 is a block diagram illustrating an identification module in accordance with an exemplary embodiment;

5-3 are block diagrams illustrating another content item pushing device according to an example embodiment;

FIG. 6-1 is a block diagram illustrating a content item pushing device in accordance with another exemplary embodiment;

FIG. 6-2 is a block diagram illustrating another content item pushing device in accordance with another illustrative embodiment;

FIG. 7 is a block diagram illustrating a content item pushing device in accordance with an exemplary embodiment;

FIG. 8 is a block diagram illustrating a content item pushing device in accordance with another illustrative embodiment;

fig. 9 is a schematic diagram illustrating a structure of a content item push system according to an exemplary embodiment.

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

Fig. 1 is a schematic diagram of an implementation environment according to various embodiments of the present disclosure. The implementation environment may include: a server 120 and a terminal 140. The terminal 140 may be connected to the server 120 through a wired network or a wireless network. The wired network may be, for example, a Universal Serial Bus (USB), and the wireless network includes but is not limited to: WIreless FIdelity (WIFI), Bluetooth, infrared and Zigbee.

The server 120 may be a server, a server cluster composed of a plurality of servers, or a cloud computing service center, where the server 120 may obtain a media file to be displayed or being displayed by a current terminal (terminal 140 or other terminals), perform key information identification on related information of an image in the media file to obtain target key information, obtain a target content item according to the target key information, and push the target content item to the terminal 140 through connection with the terminal 140 in a process of displaying the media file by the terminal 140. Where the media files may include, but are not limited to, video files, image files, etc., the key information is indicative of at least one of a scene, an object, and a person, and the content item may be an advertisement.

The terminal 140 may be a terminal with a media file display function, and the terminal 140 may further display the target content item on a display interface of the media file during the process of displaying the media file. The terminal 140 may be a smart phone, a tablet computer, a smart television, a smart watch, a smart wearable device, a motion Picture Experts Group Audio Layer 5 (english: Moving Picture Experts Group Audio Layer V; abbreviated as MP5) player, a laptop portable computer, a desktop computer, or the like.

Fig. 2 is a flow chart illustrating a method of pushing a content item according to an exemplary embodiment, which is illustrated in the embodiment of fig. 1 as being applied to the server 120 in the implementation environment. Referring to fig. 2, the content item pushing method may include the following steps:

in step 201, a media file to be displayed or being displayed by a current terminal is obtained.

In step 202, key information identification is performed on the related information of the images in the media file to obtain target key information, wherein the key information is used for indicating at least one of a scene, an object and a person.

In step 203, the target content item is obtained according to the target key information.

In step 204, the target content item is pushed to the terminal during the presentation of the media file by the terminal.

In summary, according to the content item pushing method provided by the embodiment of the disclosure, since the server can perform key information identification on the related information of the image in the media file to obtain the target key information, obtain the target content item according to the target key information, and push the target content item to the terminal in the process of displaying the media file at the terminal, the server can push the content item according to the preference of the user in combination with the media file, thereby solving the problems that the content item is not pushed accurately enough and the user feels easily, achieving the effect of accurately pushing the content item according to the preference of the user, and enabling the display to be more vivid due to the fact that the content item and the media file can be displayed in combination.

Fig. 3 is a flowchart illustrating a method of pushing a content item according to another exemplary embodiment, which is illustrated in the embodiment of fig. 1 applied to the terminal 140 in the implementation environment. Referring to fig. 3, the content item pushing method may include the following steps:

in step 301, in the process of displaying the media file at the terminal, a target content item pushed by the server is received, where the target content item is obtained according to target key information obtained by the server performing key information identification on related information of an image in the media file, and the key information is used to indicate at least one of a scene, an object, and a person.

In step 301, a target content item is presented on a content item slot, the content item slot being located in a corner of a presentation interface of a media file.

Fig. 4-1 is a flow chart illustrating a method of pushing a content item according to yet another exemplary embodiment, which is illustrated in the embodiment of fig. 1.

Referring to fig. 4-1, the content item push method may comprise the following steps:

in step 401, the server obtains information related to at least one image.

The related information of the image may include the image (specifically, the image content), comment information of the image, and the like.

In the embodiment of the disclosure, a user may trigger a terminal to upload related information of at least one image to a server, and the server obtains the related information of the at least one image by receiving the related information of the at least one image uploaded by the terminal. Alternatively, the user may configure the information related to the at least one image on the server, so that the server can obtain the information related to the at least one image. Alternatively, the server may send an image acquisition request to the terminal to acquire the related information of the at least one image, the terminal may send the related information of the at least one image to the server according to the image acquisition request, and the server may implement acquisition of the related information of the at least one image by receiving the related information of the at least one image sent by the terminal, which is not limited in this embodiment of the disclosure.

In step 402, the server extracts key information of each image of the at least one image to obtain key information corresponding to each image, where the key information is used to indicate at least one of a scene, an object, and a person.

After the server obtains the relevant information of the at least one image, the server may extract the relevant information of each of the at least one image to obtain the key information corresponding to each image, where the key information corresponding to the image is used to indicate at least one of a scene in the image, an object in the image, and a person in the image, the scene in the image is, for example, beach, indoor, outdoor, blue sky, etc., the object in the image is, for example, gourmet, scenery, etc., and the person in the image is, for example, a star, etc., which is not limited in this disclosure.

Optionally, a Convolutional Neural Network (CNN) is configured on the server, where the CNN includes a feature extraction layer, and the feature extraction layer may perform feature extraction on the relevant information of the image. Alternatively, the server may detect the related information of the image by using an object detection algorithm, and identify the object in the image, so as to obtain the key information corresponding to the image, which is not limited in the embodiments of the present disclosure

For example, assuming that at least one image includes an image 1, an image 2, and an image 3..... image n, the server extracts key information from the related information of the image 1 to obtain key information 1 corresponding to the image 1, extracts key information from the related information of the image 2 to obtain key information 2 corresponding to the image 2, and extracts key information from the related information of the image 3 to obtain key information 3... image n to obtain key information n corresponding to the image n.

In step 403, the server trains and obtains an information recognition model according to the related information of each image in the at least one image and the key information corresponding to each image.

After the server obtains the key information corresponding to each image in the at least one image, the server can train to obtain the information identification model according to the relevant information of each image in the at least one image and the key information corresponding to each image. Optionally, the CNN further includes a feature mapping layer, where the feature mapping layer may perform feature mapping on the related information of the image, and in this embodiment, the feature mapping on the related information of the image is also referred to as key information mapping on the related information of the image, and further, is also referred to as establishing a mapping relationship between the related information of the image and the key information corresponding to the image, so that the server may train the information identification model according to the related information of each image in the at least one image and the key information corresponding to each image, where the information identification model includes a mapping relationship between the related information of each image in the at least one image and the key information corresponding to each image, and this is not limited in this embodiment.

For example, the server establishes a mapping relationship between the related information of the image 1 and the key information corresponding to the image 1, establishes a mapping relationship between the related information of the image 2 and the key information corresponding to the image 2, and establishes a mapping relationship between the related information of the image 3 and the key information corresponding to the image 3.

TABLE 1

Information relating to images	Key information
		Information relating to image 1	Key information 1
Information relating to image 2	Key information 2
		Information relating to image 3	Key information 3
……	……
		Information relating to image n	Key information n

The information recognition model trained by the server may include the mapping relationship shown in table 1. It should be noted that the mapping relationships shown in table 1 are merely exemplary, and in practical applications, the mapping relationships in the information recognition model are various, and the embodiment of the present disclosure does not limit this.

In step 404, the server obtains the media file to be displayed or being displayed by the current terminal.

The media file may be a video file, an image file, or the like, the video may be a movie, a tv show, or a small video shot by a user, and the like, and the image may be a picture shot by the user, and the like.

In the embodiment of the disclosure, a user can trigger the terminal to display a media file, when the terminal is to display the media file or is displaying the media file, the terminal can upload the media file to the server, and the server receives the media file uploaded by the terminal to acquire the media file. Or, the user may configure the media file to be displayed or being displayed at the current terminal of the media file on the server, so that the server can obtain the media file to be displayed or being displayed at the current terminal. Or, the server may send a media file acquisition request to the terminal to acquire the media file, the terminal may send the media file to be displayed or being displayed at the current terminal to the server according to the media file acquisition request, and the server acquires the media file by receiving the media file sent by the terminal. The terminal in step 404 may be a media file publishing terminal, and specifically may be a video camera, a publishing device of a media file publishing merchant, or a mobile phone of a certain user (for example, a mobile phone of a user a), and the like, which is not limited in this disclosure.

In step 405, the server performs key information identification on the related information of the image in the media file to obtain target key information.

After the server acquires the media file to be displayed or being displayed by the current terminal, key information identification can be carried out on the relevant information of the image in the media file to obtain target key information. Alternatively, the server may input the relevant information of the image in the media file into the information recognition model, and the information recognition model may perform key information recognition on the relevant information of the image to obtain target key information, and output the target key information.

In the embodiment of the present disclosure, the media file may be a video file or an image file, the video file includes a plurality of video frames, each video frame includes an image, and the image (the video frame or the image file) may include a face image, and the related information of the image may include the image, comment information of the image, and the like.

In a first aspect, the media file is a video file, and the information related to the image includes the image (i.e., a video frame). Referring to fig. 4-2, which shows a flowchart of a method for identifying key information of related information of an image in a media file according to the embodiment shown in fig. 4-1, referring to fig. 4-2, the method includes:

in sub-step 4051A, key frame extraction is performed on the media file to obtain a key frame set of the media file.

The server can extract the key frames of the media files to obtain the key frame set of the media files. Optionally, the server may extract key information from each video frame of the video file, determine whether the corresponding video frame is a key frame according to the extracted key information, and if the corresponding video frame is a key frame, the server extracts the key frame. For example, the server extracts key frames 1, 2, and 3.. times key frame n of video file a, and obtains a key frame set a of video file a { key frame 1, 2, and 3.. times key frame n }. The server extracts the key information of each video frame, determines whether the corresponding video frame is a key frame according to the extracted key information, and references related technologies to the specific implementation process of extracting the key frame, which is not limited in the embodiments of the present disclosure.

In sub-step 4052A, key information identification is performed on each key frame in the key frame set to obtain a key information set corresponding to the key frame set, where the key information set includes key information of each key frame in the key frame set.

Optionally, the server may input each key frame in the key frame set into the information identification model, the information identification model may perform key information identification on each key frame to obtain key information of each key frame, and output the key information of each key frame, and the server obtains a key information set corresponding to the key frame set according to the key information of all key frames in the key frame set, where the key information set includes the key information of each key frame in the key frame set. For example, the server inputs a key frame 1 in a key frame set a into the information identification model, the information identification model identifies key information of the key frame 1 to obtain key information of the key frame 1, the key information of the key frame 1 may be the key information 1, the server inputs a key frame 2 in the key frame set a into the information identification model, the information identification model identifies key information of the key frame 2 to obtain key information of the key frame 2, the key information of the key frame 2 may be the key information 2, and so on. The server may obtain a key information set a1 corresponding to the key frame set a { key information 1, key information 2, and key information 3.... key information n }.

In sub-step 4053A, target key information is determined in the set of key information.

After the server obtains the key information set corresponding to the key frame set, the target key information can be determined in the key information set. For example, please refer to fig. 4-3, which shows a flowchart of a method for determining target key information in a key information set according to the embodiment shown in fig. 4-1, and referring to fig. 4-3, the method includes:

in sub-step 4053a1, the number of occurrences of each of the set of critical information within a preset time period is determined.

Each piece of key information in the key information set may correspond to a time, which may be a playing time of a key frame corresponding to the key information, and the server may count the key information in the key information set according to the time corresponding to the key information in the key information set, to obtain the occurrence frequency of each piece of key information in the key information set within a preset time period. Wherein the preset time period can be set according to actual conditions, for example, the preset time period can be a time period between 19 minutes 00 seconds and 20 minutes 00 seconds, the server determines the number of occurrences of each of the key information in the set of key information within a time period between the time of 19 minutes 00 seconds and the time of 20 minutes 00 seconds, for example, the server determines the number of occurrences of the key information 1 in the time period between the time of 19 min 00 s and the time of 20 min 00 s, the number of occurrences of the key information 2 in the time period between the time of 19 min 00 s and the time of 20 min 00 s, and the like, and assumes that the number of occurrences of the key information 1 in the time period between the time of 19 min 00 s and the time of 20 min 00 s is a, the number of occurrences of the key information 2 in the time period between the time of 19 min 00 s and the time of 20 min 00 s is b, and the like, which is not described herein again in detail in the embodiments of the present disclosure.

In sub-step 4053a2, the key information in the key information set, the number of occurrences of which is greater than the preset number of times within the preset time period, is determined as the target key information.

After the server determines the occurrence frequency of each piece of key information in the key information set within a preset time period, the key information in the key information set, the occurrence frequency of which is greater than the preset frequency within the preset time period, may be determined as the target key information. Optionally, the server may first determine whether the occurrence frequency of each piece of key information in a preset time period is greater than a preset frequency, then determine, according to the determination result, the piece of key information whose occurrence frequency in the preset time period is greater than the preset frequency, and determine the piece of key information as the target key information. The preset times can be set according to actual conditions, and the embodiment of the disclosure does not limit the preset times. For example, the server determines whether the occurrence number a is greater than a preset number, determines whether the occurrence number b is greater than the preset number, and so on. In the embodiment of the present disclosure, assuming that the occurrence number a is greater than a preset number, the server determines the key information 1 as the target key information. Wherein, the key information 1 may indicate the infant, which is not limited in the embodiment of the present disclosure.

In a second aspect, the media file is an image file, and the related information of the image includes the image and comment information of the image. The image is also a picture, such as but not limited to a picture posted by the user in a circle of friends, and the comment information of the image is also comment information of the picture, such as but not limited to a comment of the user on the picture posted in the circle of friends. Referring to fig. 4-4, which is a flowchart illustrating another method for identifying key information related to an image in a media file according to the embodiment shown in fig. 4-1, referring to fig. 4-4, the method includes:

in sub-step 4051B, key information is identified for the image and the comment information of the image, and key information corresponding to the image is obtained.

Optionally, the server may input the image and the comment information of the image into the information identification model, and the information identification model may perform key information identification on the image and the comment information of the image to obtain key information corresponding to the image, and output the key information. For example, image a may be an image about travel, and the comment information of image a may be "where is a tourist sight? "the server has comment information" where is tourist attraction? "information input into information recognition model that can comment on image a and image a" where is tourist attraction? "identify the key information to obtain the key information corresponding to the image a, where the key information may be key information 2, and the server outputs the key information 2, and in the embodiment of the present disclosure, the key information 2 may indicate a tourist attraction.

In sub-step 4052B, key information corresponding to the image is determined as target key information.

After the server obtains the key information corresponding to the image, the key information corresponding to the image can be determined as the target key information. For example, the server determines the key information 2 corresponding to the image a as the target key information, which is not limited by the embodiment of the present disclosure.

In a third aspect, the media file is a video file or an image file, the related information of the image includes the image, and the image includes a face image. Referring to fig. 4-5, which are flowcharts illustrating still another method for performing key information identification on related information of an image in a media file according to the embodiment shown in fig. 4-1, referring to fig. 4-5, the method includes:

in sub-step 4051C, face feature recognition is performed on the face image to obtain a target face feature corresponding to the face image.

Optionally, the information recognition model further includes a mapping relationship between the face image and the face features, and the server may input the face image into the information recognition model, and perform feature recognition on the face image by using the information recognition model to obtain target face features corresponding to the face image. Or, the server may be configured with a face recognition component, and the face recognition component may perform face feature recognition on the face image to obtain a target face feature corresponding to the face image, which is not limited in this disclosure.

In sub-step 4052C, the target person identification corresponding to the target face feature is determined.

The server can store the corresponding relation between the face features and the character identifications, and the server can query the corresponding relation between the face features and the character identifications according to the target face features to obtain the target character identifications corresponding to the target face features. For example, the correspondence relationship between the facial features and the person identifiers stored by the server can be shown in the following table 2:

TABLE 2

Assuming that the target face feature obtained by the server in sub-step 4051C is the face feature a, the server looks up the corresponding relationship shown in table 2 to obtain the target person identifier as the person identifier a.

It should be noted that each of the facial features in table 2 above may include a plurality of specified features, such as face shape, eyes, nose bridge, skin smoothness, skin color, lips, mouth, and distribution position of five sense organs, and the character identification may be a character name, etc. For example, the facial features a may include face shapes, eyes, nose bridges, skin smoothness, skin colors, lips, mouth, distribution positions of five sense organs, and the like, the facial features B may also include face shapes, eyes, nose bridges, skin smoothness, skin colors, lips, mouth, distribution positions of five sense organs, and the like, and the character identifier may be the actor XX, and the like, which is not limited by the embodiment of the disclosure.

In sub-step 4053C, the target person identification is determined as the target key information.

After the server determines the target person identifier, the target person identifier may be determined as the target key information. For example, the server determines the person identifier a as the target key information, which is not limited in the embodiment of the present disclosure.

In step 406, the server obtains the target content item according to the target key information.

After determining the target key information, the server may obtain the target content item according to the target key information, where the target content item may be an advertisement and may include a product purchase link, and the like. Referring to fig. 4-6, which are flowcharts illustrating a method for obtaining a target content item according to target key information according to the embodiment shown in fig. 4-1, referring to fig. 4-6, the method includes:

in sub-step 4061, according to the target key information, the correspondence between the key information and the content item is queried to obtain the content item corresponding to the target key information.

The server can maintain the corresponding relation between the key information and the content items, and after the target key information is determined, the server can query the corresponding relation between the key information and the content items according to the target key information to obtain the content items corresponding to the target key information. It should be noted that, in the embodiment of the present disclosure, each piece of key information recorded in the correspondence between the piece of key information and the content item may correspond to at least one content item, that is, the correspondence between the piece of key information and the content item maintained by the server may be a one-to-many relationship. For example, the correspondence of the key information to the content item may be as shown in table 3 below:

TABLE 3

Assuming that the target key information is key information 1, the server may obtain, according to the correspondence shown in the target key information lookup table 2, that the content item corresponding to the target key information is content item B, where the content item B may include content item B1, content item B2, content item B3, and the like. Where key information 1 may indicate a baby, content item B1 may be a milk powder ad, content item B2 may be a diaper ad, etc. Note that, the content item corresponding to the person identifier a in table 3 may specifically be an advertisement of a language of a person (e.g., star XX) indicated by the person identifier a, which is not limited in this embodiment of the disclosure.

In sub-step 4062, the content item corresponding to the target key information is determined as the target content item.

After determining the content item corresponding to the target key information, the server may determine the content item corresponding to the target key information as the target content item. For example, the server determines content item B as the target content item.

In sub-step 4063, the target content item is obtained.

After the server determines the target content item, the target content item may be obtained. For example, the server acquires content item B.

In step 407, the server pushes the target content item to the terminal during the process of presenting the media file by the terminal.

During the presentation of the media file by the terminal, the server may push the target content item to the terminal. The terminal in step 407 may be the terminal 140 in the implementation environment shown in fig. 1. When the media file is a video file, the server can push a target content item to the terminal at the playing time of the key frame corresponding to the target key information played by the terminal; when the media file is an image file, the server may push the target content item to the terminal when the terminal displays the media file.

In the embodiment of the present disclosure, after the server acquires the target content item, a corresponding relationship between the target key information in the media file and the target content item may be established, and when the media file is a video file, the corresponding relationship may be a corresponding relationship between a playing time of a key frame corresponding to the target key information and the target content item, so that, in a process of displaying the media file at the terminal, if the video is played to a corresponding time, the server may push the corresponding target content item to the terminal. When the media file is an image file, the corresponding relation is the corresponding relation between the target key information and the target content item, and when the image file is displayed on the terminal, the server can identify the key information of the image related information in the image file to obtain the target key information and push the target content item to the terminal according to the target key information.

It should be noted that, when one piece of target key information corresponds to multiple target content items, the server may sort the multiple target content items according to the association degree between the target content items and the target key information, and push the target content items to the terminal according to the sorting result; alternatively, the server may randomly select one target content item among the plurality of target content items and push the target content item to the terminal. For example, assume that the ordering of content item B1, content item B2, and content item B3 results in: content item B1, content item B2, content item B3, the server then pushes content item B1, content item B2, content item B3 to the terminal in order while the terminal is showing the media file; alternatively, the server may randomly select a target content item from content item B1, content item B2, and content item B3, and push the target content item to the terminal, which is not limited in this disclosure.

In step 408, the terminal receives the target content item pushed by the server during the process of presenting the media file by the terminal.

During the process of displaying the media file by the terminal, the terminal can receive the target content item pushed by the server. The target content item is obtained according to the target key information after the server identifies the key information of the relevant information of the image in the media file to obtain the target key information, and the key information is used for indicating at least one of a scene, an object and a person. Illustratively, the terminal receives the target content item B pushed by the server, e.g., the terminal receives the content item B1, the content item B2, the content item B3, etc., which are pushed by the server in turn; alternatively, the terminal receives any one of the content item B1, the content item B2, and the content item B3 pushed by the server, which is not limited in the embodiment of the present disclosure.

In step 409, the terminal marks the target key information corresponding to the target content item in the presentation interface of the media file.

When the main body indicated by the target key information corresponds to (for example, is the same as) the main body of the target content item, after receiving the target content item pushed by the server, the terminal may label the target key information corresponding to the target content item in a presentation interface of the media file. The terminal may specifically label the main body indicated by the target key information with a label, where the label is, for example, a circle, a line, and the like, and the main body indicated by the target key information is, for example, a scene, a person, an object, and the like, which is not limited in this disclosure.

Illustratively, when the main body indicated by the target key information is milk powder and the main body of the target content item is also milk powder, the terminal adopts the marker to mark the milk powder indicated by the target key information in the display interface of the media file.

In step 410, the terminal presents the target content item in a content item slot located in a corner of the presentation interface of the media file.

In the embodiment of the disclosure, a content item position is set in a display interface of a media file, and a terminal can display a target content item on the content item position. When the media file is an image file, the terminal can display the target content item on the content item position when the terminal displays the key frame corresponding to the target key information.

In the embodiment of the present disclosure, the content item slot may be located at a corner of a presentation interface of the media file, and when the content item needs to be presented, the terminal displays the content item slot, and when the content item does not need to be presented, the terminal may hide the content item slot. For example, please refer to fig. 4-7, which shows a schematic diagram of a terminal displaying a target content item on a content item position according to the embodiment shown in fig. 4-1, referring to fig. 4-7, the terminal 140 displays a display interface 141 of a media file, the display interface 141 of the media file displays the media file, and currently displays an image X corresponding to target key information, the target key information indicates milk powder 142 in the image X, the terminal 140 marks the milk powder 142 with a marker 143, a content item position 144 is arranged at a corner of the display interface 141 of the media file, the content item position 144 displays a target content item "BB milk powder for a good start of a new life, and clicks and purchases: www.abc.com'.

It should be noted that the content item slots shown in fig. 4 to 7 are merely exemplary, in practical applications, the positions of the content item slots in the presentation interface of the media file may be set according to practical situations, the positions of the content item slots are subject to the condition that the presentation effect of the media file is not affected, and the specific positions of the content item slots are not limited in the embodiments of the present disclosure.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.

FIG. 5-1 is a block diagram illustrating a content item push device 500 according to an example embodiment, where the content item push device 500 may be implemented as part or all of the server 120 in the implementation environment shown in FIG. 1, in software, hardware, or a combination of both. Referring to fig. 5-1, the content item pushing device 500 may include:

a first obtaining module 510, configured to obtain a media file to be displayed or being displayed by a current terminal;

an identifying module 520 configured to identify key information of related information of the image in the media file to obtain target key information, wherein the key information is used for indicating at least one of a scene, an object and a person;

a second obtaining module 530 configured to obtain the target content item according to the target key information;

a pushing module 540 configured to push the target content item to the terminal during the process of presenting the media file by the terminal.

Optionally, the media file is a video file, the related information of the image includes an image, please refer to fig. 5-2, which shows a block diagram of an identification module 520 according to an exemplary embodiment, referring to fig. 5-2, the identification module 520 includes:

the extraction submodule 521 is configured to perform key frame extraction on the media file to obtain a key frame set of the media file;

an identifying sub-module 522 configured to perform key information identification on each key frame in the key frame set to obtain a key information set corresponding to the key frame set, where the key information set includes key information of each key frame in the key frame set;

a determining submodule 523 configured to determine target key information in the key information set.

Optionally, a determination submodule 523 configured to:

and determining the key information of which the occurrence frequency in a preset time period is greater than the preset frequency in the key information set as the target key information.

Optionally, the media file is an image file, the related information of the image includes the image and comment information of the image, and the identifying module 520 is configured to:

and determining key information corresponding to the image as target key information.

Optionally, the image includes a face image, and the recognition module 520 is configured to:

determining a target person identification corresponding to the target face characteristics;

and determining the target person identification as target key information.

Optionally, the second obtaining module 530 is configured to:

determining the content item corresponding to the target key information as a target content item;

a target content item is obtained.

Optionally, the identifying module 520 is configured to input the relevant information of the image in the media file into an information identifying model, so as to obtain the target key information, where the information identifying model is used for performing key information identification on the relevant information of the image.

Referring to fig. 5-3, which shows a block diagram of another content item pushing device 500 according to an exemplary embodiment, referring to fig. 5-3, on the basis of fig. 5-1, the content item pushing device 500 further includes:

a third obtaining module 550 configured to obtain information related to the at least one image;

the extracting module 560 is configured to extract key information of the related information of each image in the at least one image to obtain key information corresponding to each image;

the training module 570 is configured to train to obtain an information recognition model according to the related information of each image in the at least one image and the key information corresponding to each image.

Optionally, the targeted content item is an advertisement and the targeted content item includes a product purchase link.

In summary, according to the content item pushing apparatus provided by the embodiment of the present disclosure, since the server can perform key information identification on the related information of the image in the media file to obtain the target key information, obtain the target content item according to the target key information, and push the target content item to the terminal in the process of displaying the media file at the terminal, the server can push the content item according to the preference of the user in combination with the media file, thereby solving the problem that the content item is not pushed accurately enough and is likely to cause the user's dislike, achieving the effect of accurately pushing the content item according to the preference of the user, and enabling the display to be more vivid due to the fact that the content item and the media file can be displayed in combination.

Fig. 6-1 is a block diagram illustrating a content item push device 600 according to another exemplary embodiment, where the content item push device 600 may be implemented as part or all of the terminal 140 in the implementation environment shown in fig. 1 through software, hardware, or a combination of both. Referring to fig. 6-1, the content item pushing device 600 may include:

the receiving module 610 is configured to receive a target content item pushed by a server in a process of displaying a media file by a terminal, wherein the target content item is obtained according to target key information obtained by the server after key information identification is performed on related information of an image in the media file to obtain the target key information, and the key information is used for indicating at least one of a scene, an object and a person;

a presentation module 620 configured to present the target content item in a content item slot, the content item slot located at a corner of a presentation interface of the media file.

Referring optionally to fig. 6-2, which shows a block diagram of another content item pushing device 600 according to another exemplary embodiment, referring to fig. 6-2, on the basis of fig. 6-1, the content item pushing device 600 further includes:

and the labeling module 630 is configured to label the target key information corresponding to the target content item in the presentation interface of the media file.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Referring to fig. 7, a block diagram of a content item pushing device 700 is shown in an example embodiment. For example, the apparatus 700 may be provided as a server. Referring to fig. 7, apparatus 700 includes a processing component 722 that further includes one or more processors and memory resources, represented by memory 732, for storing instructions, e.g., applications, that are executable by processing component 722. The applications stored in memory 732 may include one or more modules that each correspond to a set of instructions. Further, the processing component 722 is configured to execute instructions to perform the content item push method described above.

The apparatus 700 may also include a power component 726 configured to perform power management of the apparatus 700, a wired or wireless network interface 750 configured to connect the apparatus 700 to a network, and an input output (I/O) interface 758. The apparatus 700 may operate based on an operating system stored in memory 732, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

A non-transitory computer readable storage medium having instructions therein, which when executed by a processor of an apparatus 700, enable the apparatus 700 to perform a content item push method, the method comprising:

carrying out key information identification on related information of images in the media files to obtain target key information, wherein the key information is used for indicating at least one of scenes, objects and people;

acquiring a target content item according to the target key information;

Referring to fig. 8, a block diagram of a content item pushing device 800 is shown in accordance with another illustrative embodiment. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and so forth.

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

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

The memory 804 is configured to store various types of data to support operations on the apparatus 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The Memory 804 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM) or a ROM.

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

The multimedia component 808 includes a screen that provides an output interface between the device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 may include a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

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

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed status of the device 800, the relative positioning of the components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in the position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration/deceleration of the device 800, and a change in the temperature of the device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a photosensor, such as a Complementary Metal Oxide Semiconductor (CMOS) or Charge-coupled Device (CCD) image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communications between the apparatus 800 and other devices in a wired or wireless manner. The device 800 may access a WIreless network based on a communication standard, such as WIreless fidelity (WIreless)

FIdelity; for short: WIFI), 2G, 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, communications component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the content item pushing method.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the apparatus 800 to perform the content item push method described above is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a Compact disc Read-only Memory (CD-ROM), a magnetic tape, a floppy Disk, an optical data storage device, and the like.

A non-transitory computer readable storage medium having instructions therein, which when executed by a processor of a device 800, enable the device 800 to perform a content item push method, the method comprising:

in the process of displaying the media file by the terminal, receiving a target content item pushed by the server, wherein the target content item is obtained according to target key information obtained by the server after the server identifies the key information of the relevant information of the image in the media file to obtain the target key information, and the key information is used for indicating at least one of a scene, an object and a person;

the target content item is presented on a content item slot, the content item slot being located at a corner of a presentation interface of the media file.

Fig. 9 is a schematic diagram illustrating a structure of a content item push system 900 according to an example embodiment. Referring to fig. 9, the content item push system 900 may include: a server 910 and a terminal 920.

In one possible implementation, the server 910 includes the content item pushing device 500 shown in FIG. 5-1 or FIG. 5-3; the terminal 920 comprises the content item pushing device 600 shown in fig. 6-1 or fig. 6-2;

in another possible implementation, the server 910 comprises the content item pushing apparatus 700 shown in fig. 7; the terminal 920 comprises a content item pushing device 800 as shown in fig. 8.

In summary, according to the content item pushing system provided by the embodiment of the present disclosure, since the server can perform key information identification on the related information of the image in the media file to obtain the target key information, obtain the target content item according to the target key information, and push the target content item to the terminal in the process of displaying the media file at the terminal, the server can push the content item according to the preference of the user in combination with the media file, thereby solving the problem that the content item is not pushed accurately enough and is likely to cause the user to feel dislike, achieving the effect of accurately pushing the content item according to the preference of the user, and enabling the display to be more vivid due to the fact that the content item can be displayed in combination with the media file.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A content item pushing method applied to a server, the method comprising:

acquiring a media file to be displayed or being displayed at a current terminal; inputting relevant information of the images in the media file into an information identification model to obtain target key information, wherein the information identification model is used for carrying out key information identification on the relevant information of the images, the information identification model is obtained by the server according to the relevant information of each image in at least one image and key information corresponding to each image, and the key information is used for indicating at least one of a scene, an object and a person;

acquiring a target content item according to the target key information; in the process of displaying the media file by a terminal, when the media file is a video file, pushing the target content item to the terminal at the playing time of the key frame corresponding to the target key information played by the terminal; when the media file is an image file, pushing a target content item to the terminal when the terminal displays the media file, wherein the terminal is used for displaying the target content item on a content item position, and hiding the content item position when the target content item does not need to be displayed, and the content item position is positioned at a corner of a display interface of the media file;

when the media file is the video file, the related information of the image includes the image, and the related information of the image in the media file is input into an information identification model to obtain target key information, including:

extracting key frames of the media files to obtain a key frame set of the media files; inputting each key frame in the key frame set into the information identification model to obtain a key information set corresponding to the key frame set, wherein the key information set comprises key information of each key frame in the key frame set, each key information in the key information set corresponds to a moment, and the moment is a playing moment of the key frame corresponding to the key information;

counting the key information in the key information set according to the time corresponding to the key information in the key information set to obtain the occurrence frequency of each key information in the key information set within a preset time period, and determining the key information in the key information set, the occurrence frequency of which is greater than the preset frequency within the preset time period, as the target key information;

the method further comprises the following steps:

when one piece of target key information corresponds to a plurality of target content items, sequencing the target content items according to the relevance between the target content items and the target key information, and pushing the target content items to a terminal according to a sequencing result; or randomly selecting one target content item from the plurality of target content items and pushing the target content item to the terminal.

2. The method of claim 1, wherein the media file is the image file, the related information of the image comprises the image and comment information of the image, and the inputting the related information of the image in the media file into an information recognition model to obtain target key information comprises:

inputting the image and the comment information of the image into an information identification model, and identifying key information of the image and the comment information of the image to obtain key information corresponding to the image;

3. The method of claim 1, wherein the image includes a human face image, and the inputting the related information of the image in the media file into an information recognition model to obtain the target key information includes:

inputting the face image into an information recognition model, and carrying out face feature recognition on the face image to obtain a target face feature corresponding to the face image;

and determining the target person identification as the target key information.

4. The method of claim 1, wherein the obtaining target content items according to the target key information comprises:

and acquiring the target content item.

5. The method of claim 1, further comprising:

acquiring related information of at least one image;

6. The method of any of claims 1 to 4, wherein the targeted content item is an advertisement and the targeted content item comprises a product purchase link.

7. A method of pushing a content item, the method comprising:

in the process of displaying a media file by a terminal, receiving a target content item pushed by a server, wherein the target content item is obtained according to target key information obtained by inputting relevant information of an image in the media file into an information identification model by the server, the information identification model is used for carrying out key information identification on the relevant information of the image, the information identification model is obtained by training the server according to the relevant information of each image in at least one image and the key information corresponding to each image, the key information is used for indicating at least one of a scene, an object and a person, and the server is used for pushing the target content item to the terminal at the playing time of playing a key frame corresponding to the target key information by the terminal when the media file is a video file, when the media file is an image file, pushing a target content item to the terminal when the terminal displays the media file;

displaying the target content item on a content item slot, the content item slot being located at a corner of a display interface of the media file; hiding the content item slots when the target content item need not be presented;

the server is used for extracting key frames of the media file to obtain a key frame set of the media file when the media file is the video file and the related information of the image comprises the image; inputting each key frame in the key frame set into the information identification model to obtain a key information set corresponding to the key frame set, wherein the key information set comprises key information of each key frame in the key frame set, each key information in the key information set corresponds to a moment, and the moment is a playing moment of the key frame corresponding to the key information; counting the key information in the key information set according to the time corresponding to the key information in the key information set to obtain the occurrence frequency of each key information in the key information set within a preset time period, and determining the key information in the key information set, the occurrence frequency of which is greater than the preset frequency within the preset time period, as the target key information;

the server is further used for sequencing the target content items according to the relevance between the target content items and the target key information when one piece of target key information corresponds to the target content items, and pushing the target content items to a terminal according to a sequencing result; or randomly selecting one target content item from the plurality of target content items and pushing the target content item to the terminal.

8. The method of claim 7, further comprising:

9. The method of any of claims 7 or 8, wherein the targeted content item is an advertisement and the targeted content item comprises a product purchase link.

10. A content item pushing apparatus, characterized in that the apparatus comprises:

the identification module is configured to input relevant information of the images in the media file into an information identification model to obtain target key information, the information identification model is used for carrying out key information identification on the relevant information of the images, the information identification model is obtained by a server through training according to the relevant information of each image in at least one image and key information corresponding to each image, and the key information is used for indicating at least one of a scene, an object and a person;

the pushing module is configured to push the target content item to a terminal at a playing time when the terminal plays a key frame corresponding to the target key information when the media file is a video file in a process that the terminal displays the media file; when the media file is an image file, pushing a target content item to the terminal when the terminal displays the media file, wherein the terminal is used for displaying the target content item on a content item position, and hiding the content item position when the target content item does not need to be displayed, and the content item position is positioned at a corner of a display interface of the media file;

wherein the identification module is configured to;

when the media file is a video file, the related information of the image includes the image, and the identification module includes:

the identification submodule is configured to input each key frame in the key frame set into the information identification model to obtain a key information set corresponding to the key frame set, wherein the key information set comprises key information of each key frame in the key frame set, each key information in the key information set corresponds to a moment, and the moment is a playing moment of the key frame corresponding to the key information;

the determining submodule is configured to count the key information in the key information set according to the time corresponding to the key information in the key information set, so as to obtain the occurrence frequency of each piece of key information in the key information set within a preset time period; determining key information of which the occurrence frequency in a preset time period is greater than a preset frequency in the key information set as the target key information;

the apparatus also includes means for:

11. The apparatus of claim 10, wherein the media file is an image file, wherein the related information of the image includes the image and comment information of the image,

the identification module configured to:

12. The apparatus of claim 10, wherein the image comprises a face image,

the identification module configured to:

and determining the target person identification as the target key information.

13. The apparatus of claim 10,

the second acquisition module configured to:

and acquiring the target content item.

14. The apparatus of claim 10, further comprising:

15. The apparatus of any of claims 10 to 13, wherein the targeted content item is an advertisement and the targeted content item comprises a product purchase link.

16. A content item pushing apparatus, characterized in that the apparatus comprises:

a receiving module, configured to receive a target content item pushed by a server in a process of displaying a media file by a terminal, where the target content item is obtained according to target key information obtained by the server after inputting relevant information of an image in the media file into an information recognition model, the information recognition model is used to perform key information recognition on the relevant information of the image, the information recognition model is obtained by the server according to the relevant information of each image in at least one image and the key information corresponding to each image, the key information is used to indicate at least one of a scene, an object and a person, and the server is used to push the target content item to the terminal at a playing time when the terminal plays a key frame corresponding to the target key information when the media file is a video file, when the media file is an image file, pushing a target content item to the terminal when the terminal displays the media file;

a presentation module configured to present the target content item on a content item slot located at a corner of a presentation interface of the media file; hiding the content item slots when the target content item need not be presented;

17. The apparatus of claim 16, further comprising:

and the marking module is configured to mark the target key information corresponding to the target content item in the display interface of the media file.

18. The apparatus of claim 16 or 17, wherein the targeted content item is an advertisement and the targeted content item comprises a product purchase link.

19. A content item pushing apparatus, comprising:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to:

inputting relevant information of the images in the media file into an information identification model to obtain target key information, wherein the information identification model is used for carrying out key information identification on the relevant information of the images, the information identification model is obtained by a server according to the relevant information of each image in at least one image and key information corresponding to each image, and the key information is used for indicating at least one of a scene, an object and a person;

the processor is further configured to:

20. A content item pushing apparatus, comprising:

a processor;

a memory for storing executable instructions of the processor;

wherein the processor is configured to:

21. A content item pushing system, characterized in that the system comprises:

a content item pushing device as claimed in any one of claims 10 to 15, and a content item pushing device as claimed in any one of claims 16 to 18;

alternatively, the first and second electrodes may be,

the content item pushing device of claim 19 and the content item pushing device of claim 20.