A media content processing method, apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for media content processing. The media content processing method includes: determining a popularity level of target media content; determining a target CDN node type corresponding to the target media content based on the popularity level of the target media content, where the popularity level corresponds one-to-one with the CDN node type; determining a target CDN node corresponding to the target media content based on the target CDN node type, and sending node information of the target CDN node to a client, so that the client can obtain the target media content from the target CDN node based on the node information. By differentiating the popularity levels of media content in the embodiments of the present disclosure, and searching for media content with corresponding popularity in different types of CDN nodes based on the correspondence between the popularity level and the node type, the hit rate of media content in the CDN node can be improved, and the backhaul bandwidth can be reduced.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the technical field of streaming media processing, and in particular, to a method, apparatus, device, and storage medium for media content processing. Background Art

[0002] With the rapid development of the Internet, the bandwidth occupied by streaming media applications has shown explosive growth. In order to transmit media content data to the client as quickly as possible, streaming media applications generally use Content Delivery Network (CDN) technology.

[0003] In the existing CDN technology, by caching the most recently accessed media content on the CDN nodes, when the client obtains the media content, it can directly obtain it from the CDN nodes without the need for data to return to the source, thereby reducing the number of accesses to the source station.

[0004] In the existing CDN technology, all media content is cached in the CDN nodes without discrimination. When new media content enters the CDN nodes, low-popularity media content may be squeezed out of the CDN nodes, resulting in the absence of low-popularity media content on the CDN nodes. When the client accesses low-popularity media content, the media content cannot be found on the CDN nodes, resulting in a low hit rate of low-popularity media content. At this time, it is necessary to return to the source station to obtain the low-popularity media content, increasing the return bandwidth. Summary of the Invention

[0005] Embodiments of the present disclosure provide a method, apparatus, device, and storage medium for media content processing, which improve the hit rate of media content in CDN nodes and reduce the return bandwidth.

[0006] In a first aspect, embodiments of the present disclosure provide a method for media content processing, including:

[0007] Determine the popularity level of the target media content;

[0008] Based on the popularity level of the target media content, determine the target content delivery network (CDN) node type corresponding to the target media content, where the popularity level corresponds one-to-one with the CDN node type;

[0009] Based on the target CDN node type, determine the target CDN node corresponding to the target media content, and send the node information of the target CDN node to the client, so that the client obtains the target media content from the target CDN node based on the node information.

[0010] In a second aspect, embodiments of the present disclosure further provide a device for media content processing, including:

[0011] A heat level determination module, configured to determine the heat level of the target media content;

[0012] A node type determination module, configured to determine the target content delivery network (CDN) node type corresponding to the target media content based on the heat level of the target media content, where the heat level corresponds one-to-one to the CDN node type;

[0013] A target node determination module, configured to determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client obtains the target media content from the target CDN node based on the node information.

[0014] In a third aspect, an embodiment of the present disclosure further provides a media content processing device, including:

[0015] One or more processors;

[0016] A memory, configured to store one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the media content processing method according to any one of the embodiments of the present disclosure.

[0018] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the media content processing method according to any one of the embodiments of the present disclosure is implemented.

[0019] An embodiment of the present disclosure provides a media content processing method, apparatus, device, and medium. The media content processing method includes: determining the heat level of the target media content; determining the target CDN node type corresponding to the target media content based on the heat level of the target media content, where the heat level corresponds one-to-one to the CDN node type; determining the target CDN node corresponding to the target media content based on the target CDN node type, and sending the node information of the target CDN node to the client, so that the client obtains the target media content from the target CDN node based on the node information. By distinguishing the heat level of the media content in the embodiment of the present disclosure and searching for the media content with the corresponding heat in different types of CDN nodes based on the correspondence between the heat level and the node type, the hit rate of the media content in the CDN node can be increased, and the backhaul bandwidth can be reduced. Description of the Drawings

[0020] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages and aspects of the various embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the original elements and elements are not necessarily drawn to scale.

[0021] Figure 1 is a typical topology diagram of a CDN provided by an embodiment of the present disclosure;

[0022] Figure 2 is a flowchart of a media content processing method provided by an embodiment of the present disclosure;

[0023] Figure 3 is a flowchart of another media content processing method provided by an embodiment of the present disclosure;

[0024] Figure 4a is a schematic diagram of a CDN node in the prior art;

[0025] Figure 4b is a schematic diagram of CDN node classification provided by an embodiment of the present disclosure;

[0026] Figure 5 is a structural diagram of a media content processing device provided by an embodiment of the present disclosure;

[0027] Figure 6 is a structural diagram of a media content processing device provided by an embodiment of the present disclosure. Specific Embodiments

[0028] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0029] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be executed in different orders and / or executed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0030] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0031] It should be noted that the concepts such as "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0032] It should be noted that the modifications of "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless clearly specified otherwise in the context, it should be understood as "one or more".

[0033] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0034] First, a simple explanation of the application scenarios of the embodiments of this disclosure is given. The embodiments of this disclosure can be applied to any scenario of accessing a content delivery network to obtain media content. For example, it can be applied to the feed stream scenario, or to the scenario of obtaining media content through a media playback platform or website, or to the scenario of clicking on media content through the homepage of a media content publisher.

[0035] The "feed" in the embodiments of this disclosure can be a content aggregator formed by combining several message sources actively subscribed by users to help users continuously obtain the latest subscribed source content. Feed is an interface used in Really Simple Syndication (RSS) to receive the information source.

[0036] The feed stream in the embodiments of this disclosure, also known as the information stream, is a continuously updated information stream that can push the information in RSS to users.

[0037] In the feed stream scenario, the recommendation system of the server pushes a series of media content (such as videos) to the client. When the user operates on the media content in the feed stream, the client responds to the user operation and sends a series of media content requests to the server. The server responds to the media content requests, determines the popularity level of the media content corresponding to the media content requests, obtains the media content from the corresponding type of CDN node according to the popularity level, and distributes it to the client.

[0038] Figure 1 is a typical topological structure diagram of a CDN provided by an embodiment of the present disclosure. As shown in Figure 1, the technical principle of the CDN is as follows: When a user requests a certain Uniform Resource Locator (URL), a media content request is sent to a CDN node. The CDN node will detect whether the media content corresponding to the media content request sent by the user has expired. If it has not expired, the media content request will be directly responded to, and the media content corresponding to the media content request will be returned to the client, and at this time, an http request is completed. If the media content corresponding to the media content request has expired, the CDN node needs to send a back to the source request to the origin server to pull the media content corresponding to the latest media content request, update the media content cached locally, and return the media content corresponding to the latest media content request to the client. The expiration of the requested content means that the CDN node fails to query the media content corresponding to the media content request.

[0039] In the above CDN technology, all the media content pulled by the origin server is cached in the CDN node without distinction. When new media content enters the CDN node, the media content with a low popularity level may be squeezed out of the CDN node, resulting in the media content with a low popularity level not being on the CDN node. When the client requests the media content with a low popularity level, the media content cannot be found on the CDN node, resulting in a low hit rate of the media content with a low popularity level. At this time, it is necessary to return to the origin server to obtain the media content with a low popularity level, increasing the backhaul bandwidth.

[0040] To solve the above technical problems, an embodiment of the present disclosure provides a media content processing method, apparatus, device, and storage medium. By distinguishing the popularity levels of media content and based on the corresponding relationship between the popularity level and the node type, the media content with the corresponding popularity is searched in different types of CDN nodes, which can improve the hit rate of media content in the CDN node and reduce the backhaul bandwidth.

[0041] The media content processing method, apparatus, device, and storage medium provided by the embodiments of the present disclosure will be introduced in detail below in conjunction with specific embodiments.

[0042] Figure 2 It is a flowchart of a media content processing method provided by an embodiment of the present disclosure. This embodiment is applicable to the situation where a client requests media content from a CDN node. The method can be executed by a media content processing device, and the media content processing device can be implemented in software and / or hardware. The media content processing method is applied to a server.

[0043] As Figure 2As shown in the figure, the media content processing method provided in this embodiment mainly includes steps S11, S12, S13, and S14.

[0044] S11. Determine the popularity level of the target media content.

[0045] In this embodiment, the media content refers to the content displayed on the client side, which can be a combination of one or more of video, audio, text, and cards. It should be noted that the media content in this embodiment can be the media content in the feed stream, or the media content on a certain video website or the homepage of a video publisher. The target media content refers to the media content requested by the client from the server.

[0046] In one implementation manner, a method for determining the target media content is provided. The server receives the media content request sent by the client, parses the media content request, and determines the media content corresponding to the media content request as the target media content.

[0047] In another implementation manner, a method for determining the target media content is provided. Receive the feed stream request sent by the client, parse the feed stream request, and determine each media content in the feed stream as the target media content, and sequentially execute steps S12, S13, and S14.

[0048] Among them, the popularity level is used to characterize the degree of attention of each media content. The popularity level can be divided into multiple levels according to requirements. For example: it can be divided into four levels: S level, A level, B level, and F level. Among them, the S level has the highest level, the A level is lower than the S level, the B level is lower than the A level, and the F level has the lowest level. The higher the level, the more times the media content has been viewed, and the lower the level, the fewer times the media content has been viewed. It can also be divided into three levels: high, medium, and low. This embodiment only illustrates the level division, rather than limiting it.

[0049] In this embodiment, preferably, the popularity level is divided into two levels: hot and cold. Hot media content refers to media content that receives higher attention in a short period of time. For example: hot media content can be media content with a playback volume of over ten thousand within one hour, and hot media content can also be media content with a significant increase in the number of comments and likes within one hour. Cold media content refers to media content that receives lower attention in a short period of time. For example: cold media content can be media content with a very low playback volume within one hour, and cold media content can also be media content with a very slow growth rate or no growth in the number of comments and likes within one hour.

[0050] In one embodiment, based on the relevant features of the target media content, the Gradient Boosting Decision Tree (GBDT) model is used to predict the growth of the media content playback volume within the next hour. Based on the corresponding relationship between the growth volume and the popularity level, the popularity level corresponding to the target media content is determined.

[0051] Specifically, it can be determined whether the playback growth volume exceeds a preset playback growth volume threshold. If it exceeds the preset playback growth volume threshold, the popularity level of the media content is a hot media content. If it is lower than the preset playback growth volume threshold, the popularity level of the media content is a cold media content. The method of determining the popularity level based on the comment growth volume and the like-like growth volume is similar to the above playback growth volume, and will not be elaborated here.

[0052] Furthermore, multiple growth volume ranges can be set to divide the popularity level of the media content in more detail. For example: set four growth volume ranges, and the media content can be divided into four levels: S level, A level, B level, and F level.

[0053] In another embodiment, the relevant features of the target media content are normalized, and different weights are assigned to each relevant feature. Based on the normalized relevant features and their corresponding weights, weighted processing is performed to obtain the popularity index corresponding to the target media content. Based on the corresponding relationship between the popularity index and the popularity level, the popularity level corresponding to the target media content is determined.

[0054] It should be noted that the division method of the corresponding relationship between the popularity index and the popularity level is basically the same as the division method of the corresponding relationship between the growth volume and the popularity level described above. For details, please refer to the above description and will not be elaborated in this embodiment.

[0055] S12. Determine the target content delivery network (CDN) node type corresponding to the target media content based on the popularity level of the target media content, where the popularity level and the CDN node type are in one-to-one correspondence.

[0056] Among them, all CDN nodes in the CDN system are classified, and there is a corresponding relationship between the CDN node type and the popularity level. Furthermore, the popularity level and the CDN node type are in a one-to-one correspondence relationship. Furthermore, at least one CDN node is included in a CDN node group.

[0057] Specifically, one heat level corresponds to one CDN node type. For example, heat levels S, A, B, and F respectively correspond to the first type of CDN node, the second type of CDN node, the third type of CDN node, and the fourth type of CDN node in the CDN node type. Another example: hot media content corresponds to hot type CDN nodes, and cold media content corresponds to cold type CDN nodes.

[0058] Specifically, the correspondence between the heat level and the CDN node type is pre-stored in the server. After the server determines the heat level of the target media content, it looks up the target CDN node type corresponding to the target media content in the correspondence between the heat level and the CDN node type.

[0059] S13. Determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client can obtain the target media content from the target CDN node based on the node information.

[0060] In this embodiment, the target CDN node can be understood as the CDN node included in the target CDN node type, that is, the type to which the target CDN node belongs is the target CDN node type.

[0061] For example: The hot type CDN nodes include the first CDN node, the second CDN node, the third CDN node, and the fourth CDN node, and the cold type CDN nodes include the fifth CDN node and the sixth CDN node. It should be noted that one CDN node type includes one or more CDN nodes.

[0062] Determining the target CDN node corresponding to the target media content based on the target CDN node type may be to determine all CDN nodes included in the target CDN node type as the target CDN node corresponding to the target media content.

[0063] After determining the target CDN node corresponding to the target media content, the node information (such as node identification information) of the target CDN node can be sent to the client. Thus, the client can request to obtain the target media content from the corresponding target CDN node according to the node information.

[0064] In one embodiment, when the server determines that the heat level of the target media content is hot media content, it determines the hot type CDN node corresponding to the target media content, then determines the CDN nodes included in the hot type CDN node as the target CDN nodes, and sends the node information of the target CDN nodes to the client. Thus, the client can send a request to obtain the target media content to the target CDN nodes based on this node information. Correspondingly, when the target CDN nodes receive the request from the client to obtain the target media content, they can search for the target media content. If the target media content is found, it will transmit the target media content to the client; if the target media content is not found, the target CDN nodes will send a back to the source request to the source station to pull the latest target media content, cache the latest target media content, and at the same time, return the latest target media content to the client.

[0065] Further, when the server determines that the target media content is cold media content, it determines that the target media content is cached in the cold type CDN nodes, then determines the CDN nodes included in the cold type CDN node as the target CDN nodes, and sends the node information of the target CDN nodes to the client. Thus, the client can send a request to obtain the target media content to the target CDN nodes based on this node information. Correspondingly, when the target CDN nodes receive the request from the client to obtain the target media content, they can search for the target media content. If the target media content is found, it will transmit the target media content to the client; if the target media content is not found, the target CDN nodes will send a back to the source request to the source station to pull the latest target media content, cache the latest target media content, and at the same time, return the latest target media content to the client.

[0066] Based on the above embodiment, another scheduling method for media content is provided. When the server determines that the target media content is hot media content and determines that the target media content is cached in the CDN nodes included in the hot type CDN node, it determines the CDN nodes included in the hot type CDN node as the target CDN nodes, and sends the node information of the target CDN nodes to the client. Thus, the client can send a request to obtain the target media content to the CDN nodes included in the hot type CDN node based on this node information. Correspondingly, when the CDN nodes included in the hot type CDN node receive the request from the client to obtain the target media content, they search for the target media content. If the target media content is found, it will transmit the target media content to the client; if the target media content is not found,, it will send a back to the source request to the source station to pull the latest target media content, cache the latest target media content, and at the same time, return the latest target media content to the client.

[0067] Further, when the server determines that the target media content is cold media content, and determines that the target media content is cached in the CDN nodes included in the cold type CDN nodes, the CDN nodes included in the cold type CDN nodes are determined as the target CDN nodes, and the node information of the target CDN nodes is sent to the client. Thus, the client can send a request to obtain the target media content to the CDN nodes included in the cold type CDN nodes based on the node information. Correspondingly, when the CDN nodes included in the cold type CDN nodes receive the request from the client to obtain the target media content, they search for the target media content. If the target media content is found, the target media content is transmitted to the client; if the target media content is not found, a backhaul request is sent to the origin server to pull the latest target media content, and the latest target media content is cached, and at the same time, the latest target media content is returned to the client.

[0068] An embodiment of the present disclosure provides a method for processing media content, including: determining the popularity level of the target media content; determining the target CDN node type corresponding to the target media content based on the popularity level of the target media content, where the popularity level and the CDN node type are in one-to-one correspondence; determining the target CDN node corresponding to the target media content based on the target CDN node type, and sending the node information of the target CDN node to the client, so that the client can obtain the target media content from the target CDN node based on the node information. By differentiating the popularity levels of media content in the embodiment of the present disclosure, and searching for media content with corresponding popularity in different types of CDN nodes based on the corresponding relationship between the popularity level and the node type, the hit rate of media content in the CDN nodes can be improved, and the backhaul bandwidth can be reduced.

[0069] Based on the above embodiments, the embodiment of the present disclosure further optimizes the method for processing media content. In this embodiment, "determining the popularity level of the target media content" is optimized to "predicting the popularity level of the target media content by using a pre-trained tree model based on the media content features of the target media content, where the media content features include one or more of the following: media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, media content share volume".

[0070] When training the tree model, the media content features and the media content true popularity level identifier can be used as inputs to obtain the media content predicted popularity level output. Based on the loss function, the true popularity level and the predicted popularity level of the media content, the model parameters are adjusted until the model output meets the expectations, and a trained tree model is obtained. After the model is trained, the model can be used to predict the popularity level of the media content. When using it, the media content features are used as inputs to obtain the popularity level of the model. Specifically, during training and use, the tree model predicts whether the playback volume of the media content in a preset future time period exceeds a playback volume threshold to predict the popularity or coldness of the media content.

[0071] In this embodiment, the media content access volume can be the number of times the client accesses the media content. The access volume can be determined by counting the number of times the client accesses the CDN address corresponding to the media content. The specific statistical method is not limited in this embodiment. The media content view volume refers to the number of times the client plays the media content.

[0072] Among them, the tree model is also called a decision tree model. The decision tree model is a simple and easy-to-use non-parametric classifier. In this embodiment, any decision tree model can be selected for training to obtain a pre-trained tree model. The specific training method is not limited in this embodiment.

[0073] In one implementation, the slopes of the media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, and media content share volume are used as media content features and input into the pre-trained tree model, and the pre-trained tree model directly outputs the popularity level of the target media content.

[0074] In one implementation, the slopes of the media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, and media content share volume are used as media content features and input into the pre-trained tree model. The pre-trained tree model outputs the playback growth volume of the target media content, and the popularity level of the target media content is determined based on the playback growth volume.

[0075] In the embodiments of the present disclosure, using the pre-trained tree model to predict the popularity level of the target media content can improve the accuracy of predicting the popularity or coldness of the target media content.

[0076] Figure 3 is a flowchart of another media content processing method provided by the embodiments of the present disclosure. As Figure 3 shown, another media content processing method provided by the embodiments of the present disclosure mainly includes the following steps:

[0077] S21. Use the pre-trained tree model to predict the relationship between the playback growth of the target media content and the playback growth threshold within a preset future time period.

[0078] In this embodiment, the preset future time period may refer to within the next hour or within the next two hours. Preferably, it is within the next hour in this embodiment. The playback growth can refer to the playback increment of the media content within the preset future time period. For example, the playback increment of the target media content within the next hour. The relationship between the playback growth and the playback growth threshold includes: the playback growth exceeds the playback growth threshold, or the playback growth is lower than the playback growth threshold.

[0079] In one implementation, use the slopes of the media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, and media content share volume as media content features and input them into the pre-trained tree model. The pre-trained tree model outputs the relationship between the playback growth of the target media content and the playback growth threshold.

[0080] S22. Determine the popularity level of the target media content based on the relationship between the playback growth of the target media content and the playback growth threshold.

[0081] In one implementation, determining the popularity level of the target media content based on the relationship between the playback growth of the target media content and the playback growth threshold includes: if the playback growth of the target media content is greater than or equal to the growth threshold, determine that the popularity level of the target media content is the first popularity level; if the playback growth of the target media content is less than the growth threshold, determine that the popularity level of the target media content is the second popularity level.

[0082] Specifically, it can be determined whether the growth exceeds the growth threshold. If it exceeds the growth threshold, the popularity level of this media content is the first popularity level, that is, this media content is a popular media content. If it is lower than the growth threshold, the popularity level of this media content is the second popularity level, that is, this media content is a cold media content.

[0083] Figure 4a It is a schematic diagram of a CDN node in the prior art. Figure 4b It is a schematic diagram of CDN node classification provided by an embodiment of the present disclosure; as Figure 4aAs shown, each original CDN node in the CDN system contains both hot media content and cold media content. After classifying the CDN nodes, as shown in Figure 4, the CDN nodes are divided into hot-type CDN nodes that cache hot media content and cold-type CDN nodes that cache cold media content. When the target media content is predicted to be hot media content, it is obtained from the hot-type CDN nodes, and when the target media content is predicted to be cold media content, it is obtained from the cold-type CDN nodes, thus reclassifying the resources. The cold media content is regrouped into one node to prevent nodes that mix hot and cold from squeezing out the cold resources from the CDN cache, resulting in a decrease in the CDN hit rate of the cold resources.

[0084] S23. Determine the target content delivery network (CDN) node type corresponding to the target media content based on the popularity level of the target media content; wherein, the popularity level corresponds one-to-one with the CDN node type.

[0085] S24. Determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client obtains the target media content from the target CDN node based on the node information.

[0086] Based on the above embodiments, the method further includes: the training process of the tree model. The tree model training method provided by the embodiments of the present disclosure mainly includes: training the tree model using the binary cross-entropy loss function.

[0087] In this embodiment, the tree model can be trained using the tree model training samples constructed from multiple media contents and the binary cross-entropy loss function determined based on the weights of each media content. At this time, preferably, training the tree model using the binary cross-entropy loss function to obtain a pre-trained tree model includes: constructing tree model training samples using multiple media contents; determining the weights of each media content according to the media content features of the multiple media contents, and determining the binary cross-entropy loss function according to the weights of each media content; training the tree model based on the tree model training samples and the binary cross-entropy loss function to obtain a pre-trained tree model.

[0088] In one embodiment, the binary cross-entropy loss function is:

[0089]

[0090] where N is the total amount of media contents in the tree model training samples, y i represents the label of the i-th media content in the tree model training samples, and p i represents the probability of predicting the i-th media content in the tree model training samples as a positive example, and αi represents the weight of the i-th media content in the tree model training samples, vv represents the view volume of the i-th media content sample in the future preset time period in the tree model training samples, VV represents the total view volume of the i-th media content sample in the tree model training samples, T represents the total duration corresponding to the total view volume of the i-th media content sample in the tree model training samples, and t represents the view duration of the i-th media content sample from creation to the current time point in the tree model training samples.

[0091] It should be noted that the existing GBDT tree model can also be used in this embodiment, which will not be elaborated here.

[0092] In this embodiment, more weights are set for the loss of media content with a relatively high proportion of view volume vv in the future preset time period, so as to improve the prediction effect of media content with a relatively high view volume in the later stage.

[0093] Figure 5 is a structural diagram of a media content processing device provided by an embodiment of the present disclosure. This embodiment is applicable to the situation where the client requests media content from the CDN node. The media content processing device can be implemented in software and / or hardware. The media content processing device is integrated in the server.

[0094] Such as Figure 5 shown, the media content processing device provided by this embodiment mainly includes a heat level determination module 51, a node type determination module 52, and a target node determination module 53.

[0095] Among them, the heat level determination module 51 is used to determine the heat level of the target media content;

[0096] The node type determination module 52 is used to determine the target content distribution network CDN node type corresponding to the target media content based on the heat level of the target media content, where the heat level corresponds to the CDN node type one by one;

[0097] The target node determination module 53 is used to determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client can obtain the target media content from the target CDN node based on the node information.

[0098] An embodiment of the present disclosure provides a media content processing device, which is mainly used to perform the following operations: determine the popularity level of the target media content; determine the target CDN node type corresponding to the target media content based on the popularity level of the target media content, where the popularity level and the CDN node type are in one-to-one correspondence; determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client can obtain the target media content from the target CDN node based on the node information. By distinguishing the popularity levels of media content in the embodiments of the present disclosure and searching for media content with corresponding popularity in different types of CDN nodes based on the correspondence between the popularity level and the node type, the hit rate of media content in the CDN node can be improved, and the backhaul bandwidth can be reduced.

[0099] In one embodiment, the popularity level determination module 51 is specifically configured to predict the popularity level of the target media content by using a pre-trained tree model based on the media content features of the target media content, where the media content features include one or more of the following: media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, media content share volume.

[0100] In one embodiment, the popularity level determination module 51 includes:

[0101] The growth amount prediction unit is configured to predict the relationship between the playback growth amount of the target media content and the playback growth amount threshold within a preset future time period by using the pre-trained tree model;

[0102] The popularity level determination unit is configured to determine the popularity level of the target media content based on the relationship between the playback growth amount of the target media content and the playback growth amount threshold.

[0103] Specifically, the popularity level determination unit is specifically configured to determine that the popularity level of the target media content is the first popularity if the playback growth amount of the target media content is greater than or equal to the growth amount threshold; determine that the popularity level of the target media content is the second popularity if the playback growth amount of the target media content is less than the growth amount threshold.

[0104] In one embodiment, the device further includes: a model training module, configured to:

[0105] Train the tree model by using a binary cross-entropy loss function to obtain a pre-trained tree model.

[0106] In one embodiment, the model training module is specifically configured to: construct a tree model training sample by using multiple media contents; determine the weight of each media content according to the media content features of the multiple media contents, and determine a binary cross-entropy loss function according to the weights of the media contents; train the tree model based on the tree model training sample and the binary cross-entropy loss function to obtain a pre-trained tree model.

[0107] In one embodiment, the binary cross-entropy loss function is:

[0108]

[0109] where N is the total amount of media contents in the tree model training sample, y i represents the label of the i-th media content in the tree model training sample, and p i represents the probability of predicting that the i-th media content in the tree model training sample is a positive example, and α i represents the weight of the i-th media content in the tree model training sample, vv represents the viewing volume of the i-th media content sample within a preset future time period, VV represents the total viewing volume of the i-th media content sample, T represents the total duration corresponding to the total viewing volume of the i-th media content sample, and t represents the viewing duration of the i-th media content sample from creation to the current time point.

[0110] The media content processing device provided in this embodiment can execute the media content processing method provided in any embodiment of the present disclosure, and has corresponding functional modules and beneficial effects for executing the media content processing method.

[0111] Next, refer to Figure 6 , which shows a schematic structural diagram of an electronic device (such as Figure 6 the terminal device or server in) 600 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0112] As Figure 6As shown, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0113] Generally, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or wirelesly to exchange data. Although Figure 6 the electronic device 600 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0114] Specifically, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0115] It should be noted that the computer-readable medium described above can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0116] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LANs"), wide area networks ("WANs"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0117] The above computer-readable medium can be included in the above electronic device; or it can exist separately without being assembled into the electronic device.

[0118] The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to:

[0119] Determine the popularity level of the target media content;

[0120] Determine the target content delivery network (CDN) node type corresponding to the target media content based on the popularity level of the target media content; wherein, the popularity level corresponds one-to-one with the CDN node type.

[0121] Determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client can obtain the target media content from the target CDN node based on the node information.

[0122] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The foregoing programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, and C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., connected through the Internet using an Internet service provider).

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0124] The units described in the embodiments of the present disclosure may be implemented in software or in hardware. Wherein, the name of the unit does not constitute a limitation to the unit itself in some cases.

[0125] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), Systems on Chip (SOCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0126] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, Random Access Memory (RAM), Read Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM or Flash Memory), optical fibers, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0127] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for media content processing, including:

[0128] Determine the popularity level of the target media content;

[0129] Based on the popularity level of the target media content, determine the target content delivery network (CDN) node type corresponding to the target media content; wherein, the popularity level corresponds one-to-one with the CDN node type;

[0130] Based on the target CDN node type, determine the target CDN node corresponding to the target media content, and send the node information of the target CDN node to the client, so that the client can obtain the target media content from the target CDN node based on the node information.

[0131] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for media content processing, which determines the popularity level of the target media content, including:

[0132] Based on the media content features of the target media content, use a pre-trained tree model to predict the popularity level of the target media content, where the media content features include one or more of the following: media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, media content share volume.

[0133] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for processing media content. Predicting the popularity level of the target media content using a pre-trained tree model includes:

[0134] Predicting the relationship between the playback growth amount of the target media content and the playback growth amount threshold within a preset future time period using the pre-trained tree model;

[0135] Determining the popularity level of the target media content based on the relationship between the playback growth amount of the target media content and the playback growth amount threshold.

[0136] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for processing media content. Determining the popularity level of the target media content based on the relationship between the playback growth amount of the target media content and the playback growth amount threshold includes:

[0137] If the playback growth amount of the target media content is greater than or equal to the growth amount threshold, it is determined that the popularity level of the target media content is the first popularity;

[0138] If the playback growth amount of the target media content is less than the growth amount threshold, it is determined that the popularity level of the target media content is the second popularity.

[0139] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for processing media content, further including:

[0140] Training the tree model using the binary cross-entropy loss function to obtain a pre-trained tree model.

[0141] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for processing media content. Training the tree model using the binary cross-entropy loss function to obtain a pre-trained tree model includes:

[0142] Constructing a tree model training sample using multiple media contents;

[0143] Determining the weight of each media content according to the media content features of the multiple media contents, and determining the binary cross-entropy loss function according to the weights of each media content;

[0144] Training the tree model based on the tree model training sample and the binary cross-entropy loss function to obtain a pre-trained tree model.

[0145] According to one or more embodiments of the present disclosure, there is provided a method, apparatus, device, and storage medium for processing media content. The binary cross-entropy loss function is:

[0146]

[0147] Among them, N is the total amount of media content in the tree model training samples, yi represents the label of the i-th media content in the tree model training samples, pi represents the probability of predicting the i-th media content in the tree model training samples as a positive example, and α i represents the weight of the i-th media content in the tree model training samples. vv represents the viewing volume of the i-th media content sample in the tree model training samples within a preset future time period, VV represents the total viewing volume of the i-th media content sample in the tree model training samples, T represents the total duration corresponding to the total viewing volume of the i-th media content sample in the tree model training samples, and t represents the viewing duration of the i-th media content sample in the tree model training samples from creation to the current time point.

[0148] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0149] In addition, although the operations are depicted in a specific order, this should not be construed as requiring the operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of a single embodiment can also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment can also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0150] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A media content processing method, characterized in that, Including: Determine the popularity level of the target media content; Determine the target content delivery network (CDN) node type corresponding to the target media content based on the popularity level of the target media content; wherein, the popularity level and the CDN node type are in one-to-one correspondence; Determine the target CDN node corresponding to the target media content based on the target CDN node type, and send the node information of the target CDN node to the client, so that the client obtains the target media content from the target CDN node based on the node information; The determining the target CDN node corresponding to the target media content based on the target CDN node type includes: determining all CDN nodes included under the target CDN node type as the target CDN nodes corresponding to the target media content; The determining the popularity level of the target media content includes: Based on the slope of the media content features of the target media content, use a pre-trained tree model to predict the relationship between the playback growth amount of the target media content and the playback growth amount threshold within a preset future time period; Determine the popularity level of the target media content based on the relationship between the playback growth amount of the target media content and the playback growth amount threshold; The determining the popularity level of the target media content based on the relationship between the playback growth amount of the target media content and the playback growth amount threshold includes: If the playback growth amount of the target media content is greater than or equal to the growth amount threshold, determine that the popularity level of the target media content is the first popularity; If the playback growth amount of the target media content is less than the growth amount threshold, determine that the popularity level of the target media content is the second popularity.

2. The method according to claim 1, wherein The media content features include one or more of the following: media content access volume, media content view volume, media content like volume, media content comment volume, media content download volume, media content share volume.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Train the tree model using the binary cross-entropy loss function to obtain a pre-trained tree model.

4. The method according to claim 3, wherein Training the tree model using the binary cross-entropy loss function to obtain a pre-trained tree model includes: Construct tree model training samples using multiple media contents; Determine the weights of each media content according to the media content features of the multiple media contents, and determine the binary cross-entropy loss function according to the weights of each media content; Train the tree model based on the tree model training samples and the binary cross-entropy loss function to obtain a pre-trained tree model.

5. The method according to claim 4, characterized in that, The binary cross-entropy loss function is: Where N is the total amount of media content in the tree model training samples, yi represents the label of the i-th media content in the tree model training samples, pi represents the probability of predicting the i-th media content in the tree model training samples as a positive example, and α i represents the weight of the i-th media content in the tree model training samples, vv represents the viewing volume of the i-th media content sample in the tree model training samples within a preset time period in the future, VV represents the total viewing volume of the i-th media content sample in the tree model training samples, T represents the total duration corresponding to the total viewing volume of the i-th media content sample in the tree model training samples, and t represents the viewing duration of the i-th media content sample in the tree model training samples from creation to the current time point.

6. A media content processing device, characterized in that, Including: A popularity level determination module, configured to determine the popularity level of the target media content; A node type determination module, configured to determine the target content delivery network (CDN) node type corresponding to the target media content based on the popularity level of the target media content, wherein the popularity level and the CDN node type are in one-to-one correspondence; A target node determination module, configured to determine a target CDN node corresponding to the target media content based on the target CDN node type, and send node information of the target CDN node to a client, so that the client obtains the target media content from the target CDN node based on the node information; determining the target CDN node corresponding to the target media content based on the target CDN node type includes: determining all CDN nodes included in the target CDN node type as the target CDN nodes corresponding to the target media content; The heat level determination module is specifically configured to predict the relationship between the playback growth amount of the target media content and the playback growth amount threshold within a preset future time period by using a pre-trained tree model based on the slope of the media content features of the target media content; determine the heat level of the target media content based on the relationship between the playback growth amount of the target media content and the playback growth amount threshold; The heat level determination module is further configured to determine that the heat level of the target media content is the first heat level if the playback growth amount of the target media content is greater than or equal to the growth amount threshold; If the playback growth amount of the target media content is less than the growth amount threshold, it is determined that the heat level of the target media content is the second heat level.

7. A media content processing device, characterized in that, Including: One or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the media content processing method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the media content processing method according to any one of claims 1-5 is implemented.

Images