CN111510746A

CN111510746A - Media resource delivery method and device, storage medium and electronic device

Info

Publication number: CN111510746A
Application number: CN201910093961.4A
Authority: CN
Inventors: 毛宁; 张倩; 苏陈艳; 王静; 崔立鹏; 周伟强; 刘萌; 杨杰
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2019-01-30
Filing date: 2019-01-30
Publication date: 2020-08-07
Anticipated expiration: 2039-01-30
Also published as: CN111510746B

Abstract

The invention discloses a media resource delivery method, a media resource delivery device, a storage medium and an electronic device. Wherein, the method comprises the following steps: acquiring a picture frame set obtained by performing picture capturing operation on a media data stream sent by a playing client; carrying out object recognition on the picture frame set through an object recognition model, wherein the object recognition model is obtained by carrying out machine training on a plurality of sample picture frames and is used for recognizing an object displayed in the picture frames; under the condition that the identification result output by the object identification model indicates that the picture frame set comprises the target object, triggering a media resource releasing request matched with the target object; responding to the media resource releasing request, and pulling the target media resource associated with the target object; and delivering the target media resource to a target picture frame after the picture frame set. The invention solves the technical problem of low delivery efficiency of the media resource delivery method provided in the related technology.

Description

Media resource delivery method and device, storage medium and electronic device

Technical Field

The invention relates to the field of computers, in particular to a media resource delivery method, a media resource delivery device, a storage medium and an electronic device.

Background

In order to more widely transmit product information, many product developers can choose to launch media resources related to products through the internet so as to achieve the purpose of publicizing the products. At present, in the process of delivering the media resource in the internet, the product type of a product advertised by the media resource is often obtained in advance, and the delivery time and the delivery position are determined according to the product type. And then, dotting according to the release time on a time axis, and triggering a release request for releasing the media resources under the condition of reaching the release time so as to present the released media resources in a display window of the release position.

That is to say, in the media resource delivery method provided by the related art, the delivery platform usually delivers the media resource at a fixed point according to the delivery time and the delivery position agreed with the user in advance. The release preparation process is not only complex in operation, but also takes a long time, thereby causing a problem of low release efficiency of media resources.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a media resource delivery method, a device, a storage medium and an electronic device, which are used for at least solving the technical problem of low delivery efficiency of a media resource delivery method provided in the related art.

According to an aspect of the embodiments of the present invention, a method for delivering a media resource is provided, which includes: acquiring a picture frame set obtained by performing picture capturing operation on a media data stream sent by a playing client; performing object recognition on the picture frame set through an object recognition model, wherein the object recognition model is obtained by performing machine training on a plurality of sample picture frames and is used for recognizing an object displayed in the picture frames; under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises a target object, triggering a media resource release request matched with the target object; responding to the media resource releasing request, and pulling a target media resource associated with the target object; and delivering the target media resource to a target picture frame after the picture frame set.

According to another aspect of the embodiments of the present invention, there is also provided a media resource delivering apparatus, including: the device comprises an acquisition unit, a display unit and a processing unit, wherein the acquisition unit is used for acquiring a picture frame set obtained by carrying out picture interception operation on a media data stream sent by a playing client; the recognition unit is used for carrying out object recognition on the picture frame set through an object recognition model, wherein the object recognition model is obtained by carrying out machine training on a plurality of sample picture frames and is used for recognizing an object shown in the picture frames; a triggering unit, configured to trigger a media resource delivery request matching with a target object when a recognition result output by the object recognition model indicates that the picture frame set includes the target object; a pull unit, configured to respond to the media resource delivery request, and pull a target media resource associated with the target object; and the releasing unit is used for releasing the target media resource to a target picture frame after the picture frame set.

As an optional example, the pulling unit includes: a searching module, configured to search, according to the delivery indication information of the target object requested by the media resource delivery request, the target media resource associated with the target object in a media resource library, where the media resource library includes: a plurality of media resources to be released and release control information configured by a release account requesting to release the media resources, wherein the plurality of media resources comprise the target media resources; and the first pulling module is used for pulling the target media resource under the condition that the target media resource is found.

As an alternative example, the triggering unit includes: a first obtaining module, configured to obtain, in a target time period, delivery indication information matched with the target object when the recognition result indicates that the target object is included in the picture frame set, where the delivery indication information includes: the target time period is less than or equal to a first time threshold value; and the generating module is used for generating the media resource releasing request according to the releasing indication information.

As an optional example, in a case that the picture frame set includes N target objects, the generating module includes: a dividing submodule, configured to divide N target objects according to the object picture frame to obtain M object sets, where the target objects located in the same object picture frame are divided into the same object set, and N is greater than or equal to M; a generating sub-module, configured to generate the media resource delivery request matching the ith object picture frame according to the delivery indication information of the target object included in the ith object set, where i is an integer less than or equal to M.

As an optional example, the searching module searches the target media resource associated with the target object in a media resource library by: traversing the release control information corresponding to the plurality of media resources stored in the media resource library, until the target media resource is found, executing the following operations: acquiring current release control information corresponding to a current media resource; comparing the current release control information with the release indication information of the target object; acquiring a next media resource as the current media resource when the current delivery control information is not matched with the delivery indication information of the target object; and determining the current media resource as the target media resource when the current delivery control information matches the delivery indication information of the target object.

As an optional example, the apparatus further includes: a second obtaining unit, configured to obtain, before obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playback client, a number of object accounts included in an account set to which a login account for logging in the playback client belongs, where the object accounts belonging to the same account set are accounts entering the same playback space, and the object accounts include the login account; a first operation unit, configured to, when the number of the target account is equal to or less than a first target threshold, perform one of the following operations: and pausing the process of carrying out the object recognition on the picture frame set through the object recognition model, or controlling and reducing the number of the released target media resources.

As an optional example, the apparatus further includes: a third obtaining unit, configured to obtain a data throughput of a server for running the object recognition model before obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client; a second operation unit configured to, in a case where the data processing amount is equal to or larger than a second target threshold, perform one of: and pausing the process of carrying out the object recognition on the picture frame set through the object recognition model, or controlling and reducing the number of the released target media resources.

As an optional example, the pulling unit includes: a first determining module, configured to determine, when the target object is an object of a first type, that a resource identifier of the target media resource associated with the target object is a first resource identifier, where the first resource identifier is used to indicate a media resource that belongs to a same type as the target object; a second pulling module, configured to pull the target media resource according to the first resource identifier, where the target media resource indicated by the first resource identifier is to be released and displayed at an associated position, which is pre-bound to a display position of the target object, in the target screen frame; a second determining module, configured to determine, when the target object is a second-class object, that a resource identifier of the target media resource associated with the target object is a second resource identifier, where the second resource identifier is used to indicate a media resource belonging to a type related to the target object; and a third pulling module, configured to pull the target media resource according to the second resource identifier, where the target media resource indicated by the second resource identifier is to be released and displayed at a display position of the target object in the target frame, so as to shield the target object.

As an alternative example, the identification unit includes: an identification module, configured to identify, by the object identification model, at least one of the following objects in the picture frame set: text, numbers, image elements.

As an optional example, the apparatus further includes: a fourth obtaining unit, configured to obtain operation data for performing an interactive operation on the target media resource after the target media resource is placed in a target picture frame after the picture frame set; and the adjusting unit is used for adjusting the delivered target media resources according to the operation data.

According to another aspect of the embodiment of the present invention, there is also provided a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above media resource delivering method when running.

According to another aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the media resource delivery method through the computer program.

In the embodiment of the invention, after the picture frame set to be identified is obtained by carrying out real-time picture capturing operation on the media data stream sent by the playing client, the picture frame set can be automatically identified in time by using the object identification model, so that a media resource releasing request matched with a target object is triggered in time under the condition that the target object is identified, a target media resource associated with the target object is pulled in time according to the media resource triggering request, and the target media resource is released into a target picture frame behind the picture frame set. Therefore, the automatic object identification of the real-time captured picture frame is realized, the media resource releasing request is automatically triggered, the target media resource related to the requested target object is released into the target picture frame played by the playing client in time, the fixed-point releasing of the media resource is not required to be appointed by a user in advance, the releasing preparation operation is simplified, the releasing time is saved, the real-time playing requirement of the playing client is further met, the releasing efficiency of releasing the media resource at the playing client is improved, and the technical problem that the releasing efficiency of the media resource releasing method provided by the related technology is low is solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

FIG. 1 is a diagram illustrating a hardware environment for an alternative media asset delivery method according to an embodiment of the present invention;

FIG. 2 is a flow chart of an alternative media asset delivery method according to an embodiment of the invention;

fig. 3 is a schematic diagram of a network structure applied in an alternative media resource delivery method according to an embodiment of the present invention;

fig. 4 is a schematic diagram of a delivery account configuration interface of an alternative media resource delivery method according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a delivery account configuration interface of another alternative media resource delivery method according to an embodiment of the present invention;

fig. 6 is a schematic diagram of a delivery account configuration interface of another alternative media resource delivery method according to an embodiment of the present invention;

fig. 7 is a schematic diagram of a delivery account configuration interface of another alternative media resource delivery method according to an embodiment of the present invention;

FIG. 8 is a flow chart of an alternative media asset delivery method according to an embodiment of the invention;

FIG. 9 is a schematic diagram of an alternative media asset delivery method according to an embodiment of the invention;

FIG. 10 is a schematic diagram of an alternative media asset delivery method according to an embodiment of the invention;

FIG. 11 is a schematic diagram of yet another alternative media asset delivery method according to an embodiment of the invention;

FIG. 12 is a schematic diagram of yet another alternative media asset delivery method according to an embodiment of the invention;

FIG. 13 is a flowchart of yet another alternative media asset delivery method according to an embodiment of the present invention;

fig. 14 is a schematic structural diagram of an alternative media resource delivery apparatus according to an embodiment of the present invention;

fig. 15 is a schematic structural diagram of an alternative electronic device according to an embodiment of the invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

According to an aspect of the embodiment of the present invention, there is provided the above media resource delivery method, and optionally, as an optional implementation manner, the above media resource delivery method may be applied, but not limited, to a hardware environment as shown in fig. 1. It is assumed that a player client, which is currently playing a game process in which a character object a controlled by a player participates, runs in a user terminal 102 (such as a mobile terminal, a personal computer PC, or the like shown in fig. 1). As shown in the dashed box (a) at the upper left side of fig. 1, the process of the character object a being played to flip over the wall object B is shown in the display interface of the playing client. In step S102, the server 104 will obtain the media data stream sent by the playing client, and execute step S104. Step S104-1, performing picture capturing operation on the media data stream to obtain a picture frame set; and then, executing step S104-2, performing object recognition on the picture frame set through an object recognition model, wherein the object recognition model is a neural network model for recognizing an object shown in the picture frame, which is obtained after machine training is performed on a plurality of sample picture frames. And when the recognition result output by the object recognition model indicates that the picture frame set comprises the target object, executing the steps S104-3 to S104-4, triggering a media resource release request matched with the target object, and responding to the media resource release request to pull the target media resource associated with the target object from the database 106. Then, step S104-5 is executed to determine to release the target media resource to the target frame of the frame set. Finally, the server 104 executes step S106 to return the target media resource to be delivered to the user terminal 102, so that the display interface of the playing client in the user terminal 102 can be as shown in the dashed box (b) at the upper right side of fig. 1, for example, the target media resource is an advertisement resource related to the automobile S.

It should be noted that, after obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client, an object recognition model is used to perform object recognition on the picture frame set, where the object recognition model is a neural network model used to recognize an object shown in a picture frame obtained after performing machine training with a plurality of sample picture frames. And under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises the target object, triggering a media resource releasing request matched with the target object, responding to the media resource releasing request, and pulling the target media resource associated with the target object, thereby realizing timely releasing the target media resource to the target picture frame behind the picture frame set. That is to say, after a to-be-identified picture frame set is obtained by performing a real-time picture capturing operation on a media data stream sent by a playing client, the picture frame set can be automatically identified in time by using an object identification model, so that a media resource release request matched with a target object is triggered in time under the condition that the target object is identified, a target media resource associated with the target object is pulled in time according to the media resource release request, and the target media resource is released into a target picture frame after the picture frame set. Therefore, the automatic object identification of the real-time captured picture frame is realized in time, the media resource delivery request is automatically triggered, the target media resource related to the requested target object is delivered to the target picture frame played by the playing client in time, and the fixed-point delivery of the media resource is not required to be appointed by a user in advance, so that the delivery preparation operation is simplified, the delivery time is saved, the real-time playing requirement of the playing client is further met, the delivery efficiency of delivering the media resource at the playing client is improved, and the problem of lower delivery efficiency of the media resource in the related technology is solved.

Alternatively, the media resource delivery method may be applied to, but not limited to, a user terminal capable of calculating data, such as a mobile phone, a tablet computer, a notebook computer, a PC, and the like. The network for data transmission between the terminal and the server may include, but is not limited to, a wireless network or a wired network. Wherein, this wireless network includes: bluetooth, WIFI, and other networks that enable wireless communication. Such wired networks may include, but are not limited to: wide area networks, metropolitan area networks, and local area networks. The server may include, but is not limited to: a provider Platform (SSP) server, an advertisement server, and the like, which are used to provide media resources and/or process the media resources. The above is merely an example, and this is not limited in this embodiment.

Optionally, as an optional implementation manner, as shown in fig. 2, the media resource delivery method includes:

s202, acquiring a picture frame set obtained by performing picture capturing operation on a media data stream sent by a playing client;

s204, carrying out object recognition on the picture frame set through an object recognition model, wherein the object recognition model is a neural network model which is obtained after machine training is carried out on a plurality of sample picture frames and is used for recognizing the objects displayed in the picture frames;

s206, under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises the target object, triggering a media resource release request matched with the target object;

s208, responding to the media resource releasing request, and pulling the target media resource associated with the target object;

s210, the target media resource is put into the target picture frame after the picture frame set.

Optionally, in this embodiment, the media resource delivery method may be, but is not limited to, applied in a play scene that requires real-time playing of media data. For example, the method is applied to a playing client such as a video playing application and a live playing application. The above is merely an example, and this is not limited in this embodiment. The method comprises the steps of assuming that a live broadcast client is taken as an example of a playing client, obtaining a live broadcast media data stream sent by the live broadcast client logged in by using a main broadcast account, performing picture interception operation on the live broadcast media data stream to obtain a live broadcast picture frame set, and automatically performing object identification on the live broadcast picture frame set through an object identification model. Under the condition that a target object is identified in a frame set, a media resource releasing request matched with the target object is triggered in time, a target media resource associated with the target object is pulled in time in response to the media resource releasing request, and then the target media resource is released into a target live broadcast frame after the live broadcast frame set. That is, when the live client logged in by using the anchor account and the live clients logged in by other playing accounts entering the live room in which the anchor account is located are played to the target frame, the released target media resource is presented in the interface of the live client. The above is merely an example, and this is not limited in this embodiment.

It should be noted that, after a to-be-identified picture frame set is obtained by performing a real-time picture capturing operation on a media data stream sent by a playing client, the picture frame set may be automatically identified in time by using an object identification model, so that, when a target object is identified, a media resource releasing request matched with the target object is triggered in time, and a target media resource associated with the target object is pulled in time according to the media resource releasing request and released into a target picture frame after the picture frame set. Therefore, the automatic object identification of the real-time captured picture frame is realized in time, the media resource delivery request is automatically triggered, the target media resource related to the requested target object is delivered to the target picture frame played by the playing client in time, the delivery preparation operation is simplified, the real-time playing requirement of the playing client is met, and the effect of improving the delivery efficiency of the media resource delivery at the playing client is achieved.

Optionally, in this embodiment, the target media resource may include, but is not limited to: video resources, audio resources, picture resources, or text resources, etc., and may also be any combination of these resources, for example, a combination of text resources and picture resources, and a combination of video resources and text resources. The specific product form may be an advertising media asset, such as a video advertisement, a native advertisement, a banner advertisement, a search advertisement, and the like. The above is merely an example, and this is not limited in this embodiment.

Optionally, in this embodiment, the object identification model may include, but is not limited to, identifying at least one of the following objects in the picture frame set: text, numbers, image elements. Taking the captured scene picture frame in the game application as an example, but not limited to, identifying attribute information of the character object in the game scene picture frame, such as an identifier of the character object, a type of the character object, item equipment used by the character object, a skill being released by the character object, and the like; comment information provided by different character objects, such as barrage, comments and the like, can also be identified; but not limited to, an account id or a space id logged in by the playing client may also be recognized, such as a room number of a live room, a playing account id of the playing client, and the like. The above is only an embodiment, and this embodiment is not limited to this.

It should be noted that the initial network model of the object recognition model may be, but is not limited to, at least one of the following: a Visual Geometry Group Network (VGG) model (such as VGG-16), a semantic recognition model, and a picture classification model constructed based on a deep convolutional neural Network. The foregoing is only an embodiment, and in this embodiment, another neural network model may also be used as an initial network model, and a plurality of sample frame captured from a media data stream are used to perform deep learning, and parameters in the model are continuously optimized, so as to finally obtain the object recognition model for recognizing the object shown in the frame.

As shown in fig. 3, the entire network structure includes five convolutional layers and three full-connected layers, the frontmost end of the network is an original pixel point of an input picture, and the rearmost end is a classification result of the picture.

For example, for each layer of the network, the specific network parameter configuration may be, but is not limited to, as shown in table 1, assuming the network structure shown in fig. 3 as well, including an Input picture layer (Input L eye) and 5 convolutional layers and 3 fully connected layers, each Input picture is scaled to 227 eye 227 size, and Input in RGB three color dimensions, L eye 1 to L eye 5 are convolutional layers (Conv), and L eye 1 is taken as an example, the size of the convolutional filter is 11 x 11, the convolution step is 4, the layer has 96 convolutional filters, and the output of the layer is 96 pictures with 55 x 55 size, at L eye 1, after convolutional filtering, Re L plus Us operation and max-pong operation are further connected, L eye 6 to L eye 8 is fully connected layers (refer to Full connected layers), which corresponds to the number of Input images processed by a fully connected neural network (Input neural network) based on the convolutional layers, and the number of Input neural network parameters is equivalent to the number of Input Image processed by five neural networks (Input Image), such as the number of Input Image processed by the Input Image, Input L eye), and 3 fully connected network structure is equivalent to the output of the Input neural network, and the Input neural network, which is equivalent to the Input Image processed by the Input Image processing by the five layers equivalent to 1000.

TABLE 1

Optionally, in this embodiment, before obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client, the method further includes: displaying a release control information configuration interface on a platform client logged in by using a release account, wherein a plurality of release control information configuration items to be configured are displayed in the release control information configuration interface; and acquiring a configuration request generated by executing configuration operation on the configuration item of the release control information, wherein the configuration request is used for indicating release indication information of the media resource requested to be released by the release account. The delivery control information to be configured may include, but is not limited to, condition information that a recipient receiving the delivered media resource needs to satisfy, for example: the system comprises an operating system for displaying the media resources, the releasing position types of the media resources, the displaying form types of the media resources, the displaying sizes of the media resources, the releasing time of the media resources and the releasing quantity of the media resources. The manner/order of presentation of the media assets, etc. In addition, the media delivery control information may further include, but is not limited to, order configuration operation information that is required to be completed by the delivery account, such as a delivery charging mode of the media resource, a delivery charging unit price of the media resource, and the like.

For example, assuming that the media resource is an advertisement media resource, the interface for configuring the delivery control information by the delivery account may be, but is not limited to, as shown in fig. 4 to 7. Fig. 4 shows an interface of asset management-media creation, which can create a media asset and select an operating system supported by the media asset, and fig. 4 shows a selected IOS operating system. As shown in FIG. 5, the interface of resource management, placement position management and advertisement space creation can select the content of the type of the advertisement space, the type of the form of the advertisement space, the size of the advertisement, etc., and as shown in FIG. 5, the "Banner advertisement" is selected for the "fixed advertisement" display. Fig. 6 shows an interface of resource management-SDK/document downloading, which can select a source channel of a media data stream, such as an android system of a PC or a mobile terminal. Fig. 7 shows a configuration interface of delivery management, order management, and basic information, which can select a delivery policy of a media resource, such as information of selecting a charging mode, a charging unit price, a delivery time, and a rotation policy of the media resource.

Optionally, in this embodiment, in a case that the recognition result output by the object recognition model indicates that the target object is included in the picture frame set, triggering the media resource delivery request matching the target object may include, but is not limited to: and triggering the media resource delivery request in a target time period after the identification result indicates that the frame set comprises the target object. Wherein the target time period is less than a first time threshold.

That is to say, in this embodiment, in order to meet the requirement of the playing client for playing in real time, after the object recognition model is used to automatically perform object recognition on the captured image frame set in real time, a media resource delivery request matching the recognized target object is triggered within the target time period, so as to pull the target media resource associated with the target object as soon as possible and deliver the target media resource to the playing client in time. Therefore, bidirectional transmission control is realized between a playing client side providing media data streams and a media resource management platform for delivering media resources, the media data streams of the playing client side are sent to the media resource management platform in time, so that the media resource management platform utilizes an object recognition model (such as an artificial intelligent network model) to recognize a target object from a picture frame set intercepted from the media data streams, triggers a media resource delivery request in the shortest time, timely pulls the target media resources associated with the target object, and delivers the target media resources to the playing client side for exposure display.

Optionally, in this embodiment, the triggering of the media resource delivery request matched with the target object may include, but is not limited to:

1) the frame set of the picture comprises a target object, and a media resource release request matched with the target object is directly triggered;

2) and triggering a media resource release request based on an object picture frame where the target object is located if the picture frame set comprises N target objects, wherein the object picture frame can comprise one or more target objects.

That is to say, the media resource delivery request is triggered by taking the object picture frame as a unit, so that the target media resources pulled according to the media resource delivery request can be accurately delivered to the same target picture frame, and the real-time performance and the synchronization performance of the playing are ensured.

Optionally, in this embodiment, in response to the media resource placement request, the pulling the target media resource associated with the target object may include, but is not limited to: and finding out a target media resource matched with the target object from a plurality of media resources stored in the media resource library. During the search, the following steps may be performed: and sequentially comparing the release control information configured for the media resources in the media resource library with the release indication information of the target object, and determining that the currently compared media resources are the target media resources associated with the target object under the condition that the release control information and the release indication information are matched. In addition, in this embodiment, the delivery indication information may include, but is not limited to: the target object attribute information, a login account for logging in the playing client, a frame identifier of the target object in the target picture frame and the display position coordinates of the target object in the target picture frame.

Optionally, in this embodiment, in response to the media resource placement request, the pulling the target media resource associated with the target object may include, but is not limited to:

1) and under the condition that the target object is an object in a preset delivery object set, the pulled target media resource associated with the target object is delivered and displayed at an associated position which is bound with the display position of the target object in advance in the target picture frame.

It should be noted that the preset set of delivered objects may include, but is not limited to: all the releasing accounts which cooperate with the media resource management platform indicate the object needing to release the media resources in the order. The associated positions may include, but are not limited to: a position adjacent to the display position of the target object but not completely shielded, and a designated position in the target screen. Wherein, the appointed position is a prominent position in the target picture frame. Therefore, the aim of carrying out common propaganda by using the target object displayed in the target picture frame and the target media resource displayed at the associated position is achieved, and more users are attracted to pay attention to the target object and the product indicated by the target media resource.

2) And under the condition that the target object is not an object in the preset delivery object set, the pulled target media resource associated with the target object is delivered and displayed at the display position of the target object in the target picture frame.

In order to protect the benefit of the delivery account, but not limited to, the objects in the non-preset delivery object set may be blocked by the pulled target media resource. That is, the pulled target media resources and the target objects belong to the related types and are used for shielding the target objects in the target picture frame, so that the purpose of exposing and publicizing the products indicated in the target media resources is achieved.

Optionally, in this embodiment, before obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client, the method may further include, but is not limited to: adjusting a target media resource delivery policy if at least one of the following conditions is met:

1) the number of account numbers entering the same playing space with the target object is less than or equal to a first target threshold value;

2) the data processing capacity of the server for running the object recognition model is greater than or equal to a second target threshold.

In addition, in this embodiment, the manner of adjusting the target media resource delivery policy may include, but is not limited to, at least one of the following:

1) pausing the process of carrying out object recognition on the picture frame set through an object recognition model;

2) and controlling to reduce the number of the released target media resources.

Optionally, in this embodiment, after the target media resource is delivered in the target screen frame after the screen frame set, the method further includes: acquiring operation data for executing interactive operation on a target media resource; and adjusting the delivered target media resources according to the operation data.

This is explained in detail with reference to the example shown in fig. 8. It is assumed that the media resource delivery method is applied to a delivery control system as shown in fig. 8, and the delivery control system includes: a playback client 802, a provider server 804, and a media asset library 806. As step S802, the playing client 802 will send the media data stream to the provider server 804 in real time, and then the provider server 804 will perform steps S806-S808: and performing picture interception operation on the acquired media data stream to obtain a picture frame set, and performing object identification on the picture frame set by using an object identification model, wherein the object identification model is an artificial intelligence neural network model which is obtained by performing machine training on a plurality of sample picture frames and is used for identifying objects in the picture frames. Then, under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises the target object, triggering a media resource release request matched with the target object in time. In step S810, the provider server 804 pulls the target media resource associated with the target object from the media resource library 806, where the media resource library 806 stores the media resource to be delivered and the delivery control information configured by the delivery account for the media resource. Finally, the provider server 804 delivers the target media asset to the playback client 802. Therefore, the media resource releasing request is triggered in the shortest time, the target media resource associated with the target object is pulled in time, and the target media resource is released to the playing client for exposure display.

Optionally, in this embodiment, the provider server 804 may include, but is not limited to, a video understanding module, such as an Artificial Intelligence (AI) video understanding module 902 shown in fig. 9, the AI video understanding module 902 includes 3 layers, i.e., a first layer, a bottom-layer basic hardware deployment, including a content distribution Network server (CDN) server, a data service module, where the data service module includes a database (e.g., MySQ L), a storage System (e.g., Redis), an Operating System (e.g., a Chip Operating System (COS)), and the like.

Taking the example shown in fig. 9 as an example, the playing client may transmit the media data stream shown in the terminal through a Simple Development Key (SDK) 904, where the version of the SDK 904 may be, but is not limited to, at least one of the following: the version corresponding to the web port, the version corresponding to the android system, and the version corresponding to the IOS system, and the media data stream is transmitted to the AI video understanding module 902. The AI video understanding module 902 performs stream capture on the media data stream through the capture service module in the third layer, and obtains corresponding delivery instruction information through the configuration service module and performs integrated configuration processing to obtain configuration information. Further, the picture frame set and the configuration information obtained by the stream capture are sent to a second-layer video understanding engine, and the picture frame set is identified by an identification module according to the release strategies configured in the room control module and the degradation service module, such as the type of the terminal application displayed in the picture frame set, the displayed characters or numbers, the displayed picture and the like. Wherein, AI recognition model pairs can be introduced, but not limited to, to optimize recognition services for object recognition purposes. Further, the media data stream is stored in a CDN server in the third layer, and the identified identification result data is returned to the data service module to perform operations such as data storage or data processing. Furthermore, the recognition result data can be fed back to a recognition model (such as an AI recognition model), so that the recognition capability of the recognition model can be optimized and improved.

According to the embodiment provided by the application, after the picture frame set to be identified is obtained by carrying out real-time picture capturing operation on the media data stream sent by the playing client, the picture frame set can be automatically identified in time by using the object identification model, so that the media resource release request matched with the target object is triggered in time under the condition that the target object is identified, the target media resource associated with the target object is pulled in time according to the media resource release request, and the target media resource is released into the target picture frame after the picture frame set. Therefore, the automatic object identification of the real-time captured picture frame is realized in time, the media resource releasing request is automatically triggered, the target media resource related to the requested target object is released into the target picture frame played by the playing client in time, the releasing preparation operation is simplified, the releasing time is saved, the real-time playing requirement of the playing client is further met, and the effect of improving the releasing efficiency of the media resource releasing at the playing client is achieved.

As an alternative, in the case that the recognition result output by the object recognition model indicates that the target object is included in the picture frame set, triggering the media resource delivery request matching with the target object includes:

s1, when the recognition result indicates that the frame set includes the target object, acquiring, in a target time period, placement indication information matching the target object, where the placement indication information includes: the target time period is less than or equal to a first time threshold value;

and S2, generating a media resource releasing request according to the releasing indication information.

It should be noted that, in this embodiment, the first time threshold may be, but is not limited to, a playing condition value that satisfies a real-time playing requirement for the playing client. The first time threshold may be, but is not limited to, set different values according to the scene requirement of real-time playing, which is not limited in this embodiment. That is to say, the time period for triggering the media resource delivery request is controlled within the first time threshold, so that the playing client can trigger generation of the corresponding media resource delivery request by using the obtained delivery indication information matched with the target object in time, so as to shorten the processing time for delivering the target media resource associated with the target object, and further achieve the effect of improving the media resource delivery efficiency.

As an optional implementation manner, in the case that the screen frame set includes N target objects, the step S2 of generating the media resource placement request according to the placement indication information includes:

s21, dividing N target objects according to the object picture frames to obtain M object sets, wherein the target objects in the same object picture frame are divided into the same object set, and N is more than or equal to M;

and S22, generating a media resource release request matched with the ith object picture frame according to the release indication information of the target object in the ith object set, wherein i is an integer less than or equal to M.

It should be noted that, in this embodiment, in the case that the recognition result indicates that N target objects are included in the picture frame set, the relationship between the N target objects and the picture frames in the picture frame set may include, but is not limited to:

1) when N is 1, a media resource delivery request matching the target object may be directly generated according to the delivery instruction information. The media resource delivery request carries the delivery indication information of the target object, so that the server can determine the target media resource to be delivered and associated with the target object according to the analyzed delivery indication information.

2) When N >1 and N ═ M, it indicates that one target object is recognized in each object picture frame corresponding to each object set. Further, the media resource placement request may be generated based on placement indication information of the target object identified in each object screen frame, respectively.

3) When N >1 and N > M, it indicates that at least two target objects are identified in the object picture frame corresponding to at least one object set among the M object sets. Further, a media resource delivery request corresponding to the object screen frame may be generated based on the delivery instruction information of the two target objects. That is to say, the media resource delivery request may carry delivery indication information of a plurality of target objects, where the plurality of target objects are target objects identified in the same object picture frame.

In this embodiment, the number of the object picture frames (or the number of the object sets) is less than or equal to the number of the picture frames in the picture frame set. In the case where the number of object picture frames (or the number of object sets) is equal to the number of picture frames in a picture frame set, it indicates that each picture frame recognizes a target object, and may be regarded as an object picture frame. In the case where the number of object picture frames (or the number of object sets) is smaller than the number of picture frames in a picture frame set, it is indicated that a partial picture frame in the picture frame set identifies a target object, and the partial picture frame may be an object picture frame.

Specifically, referring to the example shown in fig. 10, assuming that the image is identified by using the object identification model, determining that two target objects are currently included in the display interface of the playing client includes: a cart and a backpack (shown as circular markers). The media resource release request generating the frame id.1 can be triggered as soon as possible by using the release indication information of the target object (i.e. car and backpack) included in the object set corresponding to the frame in units of the frame corresponding to the current display interface (assuming that the frame identifier of the corresponding frame is the frame id.1),

according to the embodiment provided by the application, the media resource releasing request matched with the target object is generated by controlling automatic triggering in the target time period smaller than the first time threshold, so that the playing process of the playing client and the media resource releasing process are automatically combined in real time, the releasing control operation process of the media resources is simplified, the processing time for triggering the media resource releasing request and pulling the corresponding target media resources is shortened, and the effect of improving the releasing efficiency of the media resources is achieved.

As an optional solution, in response to the media resource placement request, pulling the target media resource associated with the target object includes:

s1, according to the target object release indication information requested by the media resource release request, searching the target media resource associated with the target object in the media resource library, wherein the media resource library comprises: the method comprises the steps that a plurality of media resources to be released and release control information configured by a release account requesting to release the media resources are released, wherein the media resources comprise target media resources;

and S2, pulling the target media resource under the condition that the target media resource is found.

It should be noted that, in this embodiment, the media resource library may be, but is not limited to, a storage link address for storing the media resource itself or the media resource, and delivery control information configured by a delivery account requesting to deliver the media resource, where the delivery control information may include, but is not limited to, the contents shown in fig. 4 to 7. The media resource library may be stored in a key-value form, but not limited to, when the content is stored, so as to facilitate subsequent searching to obtain the target media resource associated with the target object.

Optionally, in this embodiment, the searching, in the step S1, for the target media resource associated with the target object in the media resource library includes:

s1, traversing the release control information corresponding to the media resources stored in the media resource library, and executing the following operations until the target media resource is found:

s12, acquiring current release control information corresponding to the current media resource;

s14, comparing the current release control information with the release indication information of the target object;

s16, under the condition that the current putting control information is not matched with the putting indication information of the target object, acquiring the next media resource as the current media resource;

and S18, determining the current media resource as the target media resource when the current putting control information is matched with the putting indication information of the target object.

Optionally, in this embodiment, the delivery control information may include, but is not limited to, condition information that is pre-configured by the delivery account and is required to be satisfied by a recipient for receiving the delivered media resource, for example: the system comprises an operating system for displaying the media resources, the releasing position types of the media resources, the displaying form types of the media resources, the displaying sizes of the media resources, the releasing time of the media resources and the releasing quantity of the media resources. The manner/order of presentation of the media assets, etc. In addition, the media delivery control information may further include, but is not limited to, order configuration operation information that is required to be completed by the delivery account, such as a delivery charging mode of the media resource, a delivery charging unit price of the media resource, and the like.

For example, assume that the delivery instruction information obtained for the target object includes identifying the target object, a vehicle, at the upper right of frame id.1 in the live client running on the IOS operating system, the display position coordinates of the vehicle are (X1, Y1), and the corresponding size is X Y, and the delivery control information of the current media resource includes the vehicle, which is delivered at the IOS system, and the display size X 'Y' is in the form of a Banner display at fixed position L for a fixed duration T.

Under the condition that the current media resource indicated by the release control information is determined not to meet the release indication information of the target object, acquiring the next media resource from a plurality of media resources stored in a media resource library as the target media resource, and continuously comparing; and under the condition that the current media resource indicated by the putting control information is determined to meet the putting indication information of the target object, the current media resource is taken as the target media resource associated with the target object.

The above is merely an example, and the process of determining the target media resource to be delivered by comparing the current delivery control information with the delivery indication information of the target object may refer to a related media resource delivery technology, which is not limited in this embodiment.

According to the embodiment provided by the application, the target media resource associated with the target object is found in the media resource library according to the release indication information of the target object requested by the media resource release request, so that bidirectional transmission control is realized between the playing client providing the media data stream and the platform releasing the media resource, the media data stream of the playing client is sent to the media resource management platform in time, the media resource release request is triggered in the shortest time, the target media resource associated with the target object is pulled in time, and the target media resource is released to the playing client for exposure display.

As an optional scheme, before obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client, the method further includes: adjusting a delivery policy of a media resource by at least one of:

1) according to the number of the object accounts included in the account set corresponding to the playing space, whether the delivery strategy of the media resource delivery method provided by the embodiment needs to be adjusted is weighed:

s1, acquiring the number of object accounts contained in an account set to which a login account for logging in a playing client belongs, wherein the object accounts belonging to the same account set are accounts entering the same playing space and comprise the login account;

s2, when the number of the object accounts is less than or equal to the first target threshold, performing one of the following operations: and pausing the process of carrying out object recognition on the picture frame set through the object recognition model, or controlling to reduce the number of the released target media resources.

It should be noted that, for the case that the number of the target accounts included in the account set corresponding to the playing space is less than or equal to the first target threshold, it indicates that even though the target media resource is released, the exposure or the click rate of the target media resource cannot achieve the expected effect. Therefore, in the embodiment, whether the release strategy is adjusted is determined by using the number of the object accounts included in the account set corresponding to the play space.

Optionally, in this embodiment, when the playing client is a live client, the playing space may be, but is not limited to, a live room. The above is merely an example, and this is not limited in this embodiment.

2) According to the data processing amount of the server, whether the delivery strategy of the media resource delivery method provided by the embodiment needs to be adjusted is weighed:

s1, acquiring the data processing capacity of the server for operating the object recognition model;

s2, when the data processing amount is equal to or greater than the second target threshold, performing one of the following operations: and pausing the process of carrying out object recognition on the picture frame set through the object recognition model, or controlling to reduce the number of the released target media resources.

When the data processing amount of the server is equal to or greater than the second target threshold, it indicates that the data processing amount of the server has reached the full load processing state, and if the processing is continued, a system failure may be caused. Therefore, the present embodiment provides that whether the delivery policy is adjusted is determined by using the data processing amount of the server.

According to the embodiment provided by the application, the number of the object accounts in the account set corresponding to the playing space is acquired, so that the process of pausing the object recognition by using the object recognition model is controlled and adjusted, and the processing load of the server is relieved. The number of the released media resources can be controlled to be reduced, so that the media resources can be released to other scenes more accurately, the exposure or click rate required by the release account can be met, and the benefit of the release account can be further guaranteed.

1) under the condition that the target object is a first-class object, determining that a resource identifier of a target media resource associated with the target object is a first resource identifier, wherein the first resource identifier is used for indicating the media resource which belongs to the same type as the target object; pulling a target media resource according to the first resource identifier, wherein the target media resource indicated by the first resource identifier is released and displayed at an associated position which is bound with the display position of the target object in advance in the target picture frame; or

2) Under the condition that the target object is a second-class object, determining that a resource identifier of a target media resource associated with the target object is a second resource identifier, wherein the second resource identifier is used for indicating a media resource belonging to a related type with the target object; and pulling the target media resource according to the second resource identifier, wherein the target media resource indicated by the second resource identifier is released and displayed at the display position of the target object in the target picture frame so as to shield the target object.

Specifically, referring to fig. 11, for example, the media resource is an advertisement resource, and the target object is an identifiable advertisement object. Assume that an advertisement object is currently included in a display interface of a playing client by recognizing an image using an object recognition model: vehicle (brand s). Further, assuming that the brand s is an advertisement placement type preset by the placement account, it is determined that the vehicle (with the brand s) belongs to the first type object. It is further determined that the asset identity of the target media asset associated with the vehicle (brand S) is the first asset identity, i.e. the target media asset should be a media asset belonging to the same type as brand S, i.e. an advertising asset S corresponding to brand S. Then, the advertisement resource S is pulled in real time, and is released into a target picture frame after the picture frame set, and a release display is performed on a related position (the upper left corner shown in fig. 11) pre-bound with the display position of the vehicle (brand S), so that the exposure is performed simultaneously with the target object displayed in the target picture frame, and the purposes of co-propagating and improving the attention rate are achieved.

Specifically, referring to fig. 12, for example, the media resource is an advertisement resource, and the target object is an identifiable advertisement object. Assume that an advertisement object is currently included in a display interface of a playing client by recognizing an image using an object recognition model: vehicle (brand s). Further, assuming that the brand s is not the advertisement placement type preset by the placement account, it is determined that the vehicle (brand s) belongs to the second class object. It is further determined that the asset identification of the target media asset associated with the vehicle (brand s) is the second asset identification, i.e. the target media asset should be a media asset belonging to a related type with brand s, i.e. an advertising asset Q corresponding to brand Q. And then, the advertisement resource Q is pulled in real time, and is released to the display position of the vehicle s in the target picture frame after the picture frame set for releasing and displaying so as to shield the vehicle s, thereby realizing the replacement of the target object displayed in the original target picture frame, avoiding the display of the non-preset advertisement release type, and further achieving the purpose of carrying out the appointed release exposure on the preset advertisement release type.

The description will be made with reference to fig. 13: the media resource delivery control method is assumed to be applied to a system comprising the following contents: traffic owner 1302, advertisement SDK1304, provider server (may also be referred to simply as SSP server) 1306, advertisement server (may also be referred to simply as AD server) 1308, and data server 1310. The advertisement SDK1304 can be applied, but not limited to, to interact with the AI video understanding module shown in fig. 9 to complete the identification process in this embodiment.

Further, as shown in fig. 13, steps S1302 to S1346 are a full flow of advertisement delivery, including: triggering an advertisement request, retrieving advertisement resources, and putting the advertisement resources on an advertisement position of the terminal for rendering and displaying. Furthermore, the method also comprises the steps of monitoring and tracking the processes of display, clicking, skipping downloading and the like of the displayed advertisement, and recording a corresponding log. So as to optimize the advertisement putting process by utilizing the recorded logs, thereby enabling the advertisement to be accurately put, further being beneficial to attracting more targeted user groups and improving the effect of advertisement showing. The detailed description of the process in this embodiment is omitted here.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

According to another aspect of the embodiment of the invention, a media resource delivery device for implementing the media resource delivery method is also provided. As shown in fig. 14, the apparatus includes:

1) an obtaining unit 1402, configured to obtain a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client;

2) an identifying unit 1404, configured to perform object identification on the picture frame set through an object identification model, where the object identification model is a neural network model for identifying an object shown in the picture frame, which is obtained after performing machine training by using a plurality of sample picture frames;

3) a triggering unit 1406, configured to trigger a media resource delivery request matched with a target object when a recognition result output by the object recognition model indicates that the picture frame set includes the target object;

4) a pulling unit 1408, configured to respond to the media resource release request, pull the target media resource associated with the target object;

5) and a delivering unit 1410, configured to deliver the target media resource to a target picture frame after the picture frame set.

Optionally, in this embodiment, the media resource delivering apparatus may be, but is not limited to, applied in a playing scene that requires real-time playing of media data. For example, the method is applied to a playing client such as a video playing application and a live playing application. The above is merely an example, and this is not limited in this embodiment. The method comprises the steps of assuming that a live broadcast client is taken as an example of a playing client, obtaining a live broadcast media data stream sent by the live broadcast client logged in by using a main broadcast account, performing picture interception operation on the live broadcast media data stream to obtain a live broadcast picture frame set, and automatically performing object identification on the live broadcast picture frame set through an object identification model. Under the condition that a target object is identified in a frame set, a media resource releasing request matched with the target object is triggered in time, a target media resource associated with the target object is pulled in time in response to the media resource releasing request, and then the target media resource is released into a target live broadcast frame after the live broadcast frame set. That is, when the live client logged in by using the anchor account and the live clients logged in by other playing accounts entering the live room in which the anchor account is located are played to the target frame, the released target media resource is presented in the interface of the live client. The above is merely an example, and this is not limited in this embodiment.

Optionally, in this embodiment, the identifying unit 1404 includes: the identification module is used for identifying at least one of the following objects in the picture frame set through an object identification model: text, numbers, image elements. Taking the captured scene picture frame in the game application as an example, but not limited to, identifying attribute information of the character object in the game scene picture frame, such as an identifier of the character object, a type of the character object, item equipment used by the character object, a skill being released by the character object, and the like; comment information provided by different character objects, such as barrage, comments and the like, can also be identified; but not limited to, an account id or a space id logged in by the playing client may also be recognized, such as a room number of a live room, a playing account id of the playing client, and the like. The above is only an embodiment, and this embodiment is not limited to this.

2) and controlling to reduce the number of the released target media resources.

Optionally, in this embodiment, the apparatus further includes: the fourth acquisition unit is used for acquiring operation data for executing interactive operation on the target media resource after the target media resource is put in the target picture frame after the picture frame set; and the adjusting unit is used for adjusting the delivered target media resources according to the operation data.

As an alternative, the triggering unit 1406 includes:

1) a first obtaining module, configured to obtain, in a target time period, delivery indication information matched with a target object when the recognition result indicates that the frame set includes the target object, where the delivery indication information includes: the target time period is less than or equal to a first time threshold value;

2) and the generating module is used for generating a media resource releasing request according to the releasing indication information.

As an optional implementation manner, in the case that N target objects are included in the picture frame set, the generating module includes:

1) the dividing submodule is used for dividing the N target objects according to the object picture frames to obtain M object sets, wherein the target objects in the same object picture frame are divided into the same object set, and N is more than or equal to M;

2) and the generating submodule is used for generating a media resource releasing request matched with the ith object picture frame according to releasing indication information of the target object in the ith object set, wherein i is an integer less than or equal to M.

As an alternative, the pulling unit 1408 includes:

1) a searching module, configured to search, according to the delivery indication information of the target object requested by the media resource delivery request, a media resource library for a target media resource associated with the target object, where the media resource library includes: the method comprises the steps that a plurality of media resources to be released and release control information configured by a release account requesting to release the media resources are released, wherein the media resources comprise target media resources;

2) and the first pulling module is used for pulling the target media resource under the condition that the target media resource is found.

Optionally, in this embodiment, the searching module searches for the target media resource associated with the target object in the media resource library by:

As an optional solution, the apparatus further includes:

1) a second obtaining unit, configured to obtain, before obtaining a picture frame set obtained by performing a picture capturing operation on a media data stream sent by a playing client, the number of object accounts included in an account set to which a login account belongs, where the object accounts belonging to the same account set are accounts entering the same playing space, and the object accounts include the login account;

2) a first operation unit, configured to, when the number of the object accounts is equal to or less than a first target threshold, perform one of the following operations: and pausing the process of carrying out object recognition on the picture frame set through the object recognition model, or controlling to reduce the number of the released target media resources.

As another optional solution, the apparatus further includes:

1) the third acquisition unit is used for acquiring the data processing capacity of the server for operating the object recognition model before acquiring the picture frame set obtained by performing picture interception operation on the media data stream sent by the playing client;

2) a second operation unit configured to, in a case where the data processing amount is equal to or greater than a second target threshold, perform one of: and pausing the process of carrying out object recognition on the picture frame set through the object recognition model, or controlling to reduce the number of the released target media resources.

As an alternative, the pulling unit 1408 includes:

1) the first determining module is used for determining that the resource identifier of the target media resource associated with the target object is a first resource identifier under the condition that the target object is a first-class object, wherein the first resource identifier is used for indicating the media resource which belongs to the same type as the target object;

2) the second pulling module is used for pulling the target media resource according to the first resource identifier, wherein the target media resource indicated by the first resource identifier is released and displayed at a related position which is bound with the display position of the target object in advance in the target picture frame;

3) the second determining module is used for determining that the resource identifier of the target media resource associated with the target object is a second resource identifier under the condition that the target object is a second-class object, wherein the second resource identifier is used for indicating the media resource which belongs to the related type with the target object;

4) and the third pulling module is used for pulling the target media resource according to the second resource identifier, wherein the target media resource indicated by the second resource identifier is released and displayed at the display position of the target object in the target picture frame so as to shield the target object.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device for implementing the method for delivering a media resource, as shown in fig. 15, the electronic device includes a memory 1502 and a processor 1504, the memory 1502 stores a computer program, and the processor 1504 is configured to execute the steps in any one of the method embodiments through the computer program.

Optionally, in this embodiment, the electronic apparatus may be located in at least one network device of a plurality of network devices of a computer network.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

s1, acquiring a picture frame set obtained by performing picture capturing operation on the media data stream sent by the playing client;

s2, carrying out object recognition on the picture frame set through an object recognition model, wherein the object recognition model is a neural network model which is obtained after machine training is carried out on a plurality of sample picture frames and is used for recognizing the objects displayed in the picture frames;

s3, under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises the target object, triggering a media resource release request matched with the target object;

s4, responding to the media resource releasing request, pulling the target media resource associated with the target object;

and S5, the target media resource is released to the target picture frame after the picture frame set.

Alternatively, it can be understood by those skilled in the art that the structure shown in fig. 15 is only an illustration, and the electronic device may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 15 is a diagram illustrating a structure of the electronic device. For example, the electronic device may also include more or fewer components (e.g., network interfaces, etc.) than shown in FIG. 15, or have a different configuration than shown in FIG. 15.

The memory 1502 may be used for storing software programs and modules, such as the media resource delivery method in the embodiments of the present invention, and program instructions/modules corresponding to the apparatus, and the processor 1504 executes various functional applications and data processing by running the software programs and modules stored in the memory 1502, so as to implement the media resource delivery method described above. The memory 1502 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1502 can further include memory located remotely from the processor 1504, which can be coupled to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 1502 may be specifically but not limited to be used for storing the frame set and the delivery indication information of the identified target object, and may further cache information such as the pulled target media resource. As an example, as shown in fig. 15, the memory 1502 may include, but is not limited to, the obtaining unit 1402, the identifying unit 1404, the triggering unit 1406, the pulling unit 1408, and the delivering unit 1410 of the media resource delivering device. In addition, the media resource delivering apparatus may further include, but is not limited to, other module units in the media resource delivering apparatus, which is not described in this example again.

Optionally, the transmission device 1506 is used for receiving or transmitting data via a network. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 1506 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 1506 is a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

In addition, the electronic device further includes: a display 1508 for displaying the target object and the target media asset; and a connection bus 1510 for connecting the respective module parts in the above-described electronic apparatus.

According to a further aspect of embodiments of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above-mentioned method embodiments when executed.

Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:

Alternatively, in this embodiment, a person skilled in the art may understand that all or part of the steps in the methods of the foregoing embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, network devices, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A method for delivering media resources, comprising:

acquiring a picture frame set obtained by performing picture capturing operation on a media data stream sent by a playing client;

performing object recognition on the picture frame set through an object recognition model, wherein the object recognition model is a neural network model which is obtained after machine training is performed on a plurality of sample picture frames and is used for recognizing an object displayed in the picture frames;

under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises a target object, triggering a media resource release request matched with the target object;

responding to the media resource releasing request, and pulling a target media resource associated with the target object;

and delivering the target media resource to a target picture frame after the picture frame set.

2. The method according to claim 1, wherein in the case that the recognition result output by the object recognition model indicates that a target object is included in the picture frame set, the triggering of the media resource delivery request matching the target object comprises:

acquiring delivery indication information matched with the target object in a target time period under the condition that the identification result indicates that the target object is included in the picture frame set, wherein the delivery indication information comprises: the target time period is less than or equal to a first time threshold value;

and generating the media resource releasing request according to the releasing indication information.

3. The method according to claim 2, wherein, in a case that N target objects are included in the screen frame set, the generating the media resource placement request according to the placement indication information comprises:

dividing the N target objects according to the object picture frame to obtain M object sets, wherein the target objects in the same object picture frame are divided into the same object set, and N is greater than or equal to M;

and generating the media resource delivery request matched with the ith object picture frame according to the delivery indication information of the target object in the ith object set, wherein i is an integer less than or equal to M.

4. The method of claim 2, wherein pulling the target media resource associated with the target object in response to the media resource placement request comprises:

according to the target object release indication information requested by the media resource release request, searching a media resource library for the target media resource associated with the target object, wherein the media resource library comprises: the method comprises the steps that a plurality of media resources to be released and release control information configured by a release account requesting to release the media resources are released, wherein the media resources comprise the target media resources;

and pulling the target media resource under the condition that the target media resource is found.

5. The method of claim 4, wherein said searching for the target media asset associated with the target object in a media asset library comprises:

traversing the release control information respectively corresponding to the plurality of media resources stored in the media resource library to execute the following operations until the target media resource is found:

acquiring current release control information corresponding to a current media resource;

comparing the current release control information with the release indication information of the target object;

under the condition that the current putting control information is not matched with the putting indication information of the target object, acquiring a next media resource as the current media resource;

and under the condition that the current putting control information is matched with the putting indication information of the target object, determining the current media resource as the target media resource.

6. The method according to claim 1, wherein before the obtaining the picture frame set obtained by performing a picture capturing operation on the media data stream sent by the playing client, the method further comprises:

acquiring the number of object accounts contained in an account set to which a login account for logging in the playing client belongs, wherein the object accounts belonging to the same account set are accounts entering the same playing space, and the object accounts comprise the login account;

when the number of the object account numbers is less than or equal to a first target threshold, performing one of the following operations: and pausing the process of carrying out object recognition on the picture frame set through the object recognition model, or controlling to reduce the number of the released target media resources.

7. The method according to claim 1, wherein before the obtaining the picture frame set obtained by performing a picture capturing operation on the media data stream sent by the playing client, the method further comprises:

acquiring data processing capacity of a server for running the object recognition model;

in the case that the data processing amount is greater than or equal to a second target threshold, performing one of: and pausing the process of carrying out object recognition on the picture frame set through the object recognition model, or controlling to reduce the number of the released target media resources.

8. The method according to any one of claims 1 to 7, wherein the pulling the target media resource associated with the target object in response to the media resource placement request comprises:

determining that a resource identifier of the target media resource associated with the target object is a first resource identifier when the target object is a first class object, wherein the first resource identifier is used for indicating media resources belonging to the same type as the target object; pulling the target media resource according to the first resource identifier, wherein the target media resource indicated by the first resource identifier is to be released and displayed at an associated position which is pre-bound with the display position of the target object in the target picture frame; or

Determining that the resource identifier of the target media resource associated with the target object is a second resource identifier when the target object is a second class object, wherein the second resource identifier is used for indicating a media resource belonging to a related type with the target object; and pulling the target media resource according to the second resource identifier, wherein the target media resource indicated by the second resource identifier is released and displayed at the display position of the target object in the target picture frame so as to shield the target object.

9. The method according to any one of claims 1 to 7, wherein the object recognition of the set of picture frames by an object recognition model comprises:

identifying, by the object identification model, at least one of the following objects in the set of picture frames: text, numbers, image elements.

10. The method according to any one of claims 1 to 7, further comprising, after said delivering said target media resource into a target picture frame subsequent to said set of picture frames:

acquiring operation data for executing interactive operation on the target media resource;

and adjusting the delivered target media resources according to the operation data.

11. The method according to any one of claims 1 to 7, wherein before the obtaining the picture frame set obtained by performing a picture capture operation on the media data stream sent by the playing client, the method further comprises:

the method comprises the steps that a release control information configuration interface is presented on a platform client logged in by using a release account, wherein a plurality of release control information configuration items to be configured are displayed in the release control information configuration interface;

and acquiring a configuration request generated by executing configuration operation on the release control information configuration item, wherein the configuration request is used for indicating release indication information of the media resource requested to be released by the release account.

12. A media asset delivery apparatus, comprising:

the first acquisition unit is used for acquiring an image frame set obtained by performing image interception operation on a media data stream sent by a playing client;

the recognition unit is used for carrying out object recognition on the picture frame set through an object recognition model, wherein the object recognition model is obtained after machine training is carried out on a plurality of sample picture frames and is used for recognizing an object shown in the picture frames;

the triggering unit is used for triggering a media resource releasing request matched with a target object under the condition that the recognition result output by the object recognition model indicates that the picture frame set comprises the target object;

a pull unit, configured to respond to the media resource delivery request, and pull a target media resource associated with the target object;

and the releasing unit is used for releasing the target media resource to a target picture frame after the picture frame set.

13. The apparatus of claim 12, wherein the trigger unit comprises:

a first obtaining module, configured to obtain, in a target time period, delivery indication information matched with the target object when the recognition result indicates that the target object is included in the picture frame set, where the delivery indication information includes: the target time period is less than or equal to a first time threshold value;

and the generating module is used for generating the media resource releasing request according to the releasing indication information.

14. A storage medium comprising a stored program, wherein the program when executed performs the method of any one of claims 1 to 11.

15. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 11 by means of the computer program.