CN113837809A

CN113837809A - Medium information quality prediction method, medium information quality prediction device, electronic equipment and storage medium

Info

Publication number: CN113837809A
Application number: CN202111152739.0A
Authority: CN
Inventors: 李岩; 陈翼翼; 刘旭东
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2021-12-24
Anticipated expiration: 2041-09-29
Also published as: CN113837809B

Abstract

The present disclosure relates to a medium information quality prediction method, apparatus, electronic device and storage medium, including: acquiring historical data information of to-be-predicted media information, wherein the historical data information comprises first delivery data of the to-be-predicted media information in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the to-be-predicted media information, and/or second delivery data of each piece of associated media information in the preset time range; performing quality prediction according to the medium information to be predicted and historical data information of the medium information to be predicted to obtain predicted delivery data of the medium information to be predicted; wherein the delivery data comprises data for characterizing the delivery quality of the media information. The embodiment of the disclosure can improve the prediction precision of the delivery quality of the medium information.

Description

Medium information quality prediction method, medium information quality prediction device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a method and an apparatus for predicting quality of media information, an electronic device, and a storage medium.

Background

The media information may include information distributed to the public at the platform, and specifically may include video information or image information. Before the medium information is released, the releasing quality of the medium information is predicted, and the method has important significance. For example: under the condition that the medium information is the advertisement material, the high-quality advertisement material can be recalled and released by predicting the releasing quality of the advertisement material, so that the accurate releasing of the advertisement material is facilitated, and the conversion efficiency of the advertisement material is improved.

In the related art, when the user-side information cannot be acquired before the media information is delivered, the delivery quality of the media information can be predicted by the content information of the media information itself. For example: the delivery quality of the media information can be predicted by the characteristics of whether the picture is clear, whether the picture contains characters, whether the picture contains music, whether the tone is fast or slow, and the like.

However, the quality of the delivery of the media information in the delivery link is not only related to the content information of the media information itself, such as: the data such as click rate and/or conversion rate of the media information are also greatly influenced by factors such as different industries and time change. Therefore, in the related art, the delivery quality of the media information is predicted only by the content information of the media information itself, which results in low prediction accuracy of the delivery quality of the media information.

Disclosure of Invention

The present disclosure provides a medium information quality prediction method, device, electronic device, and storage medium, to at least solve the problem of low prediction accuracy of the medium information delivery quality in the related art. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a medium information quality prediction method, including:

acquiring historical data information of to-be-predicted media information, wherein the historical data information comprises first delivery data of the to-be-predicted media information in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the to-be-predicted media information, and/or second delivery data of each piece of associated media information in the preset time range;

performing quality prediction according to the medium information to be predicted and historical data information of the medium information to be predicted to obtain predicted delivery data of the medium information to be predicted;

wherein the delivery data comprises data for characterizing the delivery quality of the media information.

In a possible implementation manner, the quality prediction is carried out according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information through a quality prediction network to obtain predicted delivery data of the to-be-predicted medium information, wherein the quality prediction network comprises a feature extraction network and a prediction network;

the method for realizing quality prediction according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information through the quality prediction network to obtain predicted delivery data of the to-be-predicted medium information comprises the following steps:

performing feature extraction on the medium information to be predicted and historical data information of the medium information to be predicted through the feature extraction network to obtain material features corresponding to the medium information to be predicted;

and predicting the material characteristics through the prediction network to obtain predicted delivery data of the medium information to be predicted.

In a possible implementation manner, the historical data information includes first delivery data of the to-be-predicted medium information in a preset time range, and the feature extraction network includes a first network and a second network;

the method for extracting the characteristics of the medium information to be predicted and the historical data information of the medium information to be predicted through the characteristic extraction network to obtain the material characteristics corresponding to the medium information to be predicted comprises the following steps:

performing feature extraction on the medium information to be predicted through the first network to obtain a first content feature;

performing vector conversion processing on the first launching data through the second network to obtain a first vector representation;

and obtaining the material characteristics of the medium information to be predicted according to the first content characteristics and the first vector representation.

In a possible implementation manner, the historical data information further includes at least one piece of associated media information corresponding to the media information to be predicted and corresponding to the same media information publisher, and second delivery data of each piece of associated media information in the preset time range;

before the obtaining of the material characteristics of the media information to be predicted according to the first content characteristics and the first vector representation, the method further includes:

respectively extracting the characteristics of the associated media information through the first network to obtain the characteristics of the second content;

respectively carrying out vector conversion processing on each second launching data through the second network to obtain each second vector representation;

the obtaining of the material characteristics of the media information to be predicted according to the first content characteristics and the first vector representation includes:

obtaining a first material characteristic of the media information to be predicted according to the first content characteristic and the first vector representation;

obtaining second material characteristics of the medium information to be predicted according to the second content characteristics and the second vector representations;

and obtaining the material characteristics of the medium information to be predicted according to the first material characteristics and the second material characteristics.

In a possible implementation manner, the feature extraction network further includes a fusion network, and the obtaining of the material features of the media information to be predicted according to the first material features and the second material features includes:

and performing feature fusion processing on the first material feature and the second material feature through the fusion network to obtain the material features of the medium information to be predicted.

In one possible implementation, the first network includes at least one of a first feature extraction module, a second feature extraction module, a third feature extraction module, and a fourth feature extraction module;

the first feature extraction module is used for extracting visual features of the media information;

the second feature extraction module is used for extracting image text features of the medium information;

the third feature extraction module is used for extracting the voice text features of the media information;

the fourth feature extraction module is used for extracting the audio features of the media information.

In a possible implementation manner, before the implementing, by the quality prediction network, the quality prediction according to the to-be-predicted media information and the historical data information of the to-be-predicted media information to obtain predicted delivery data of the to-be-predicted media information, the method further includes:

training the quality prediction network by adopting a pre-constructed training set, wherein the training set comprises a plurality of sample groups, and each sample group comprises sample medium information, historical data information of the sample medium information and labeled delivery data of the sample medium information;

the training of the quality prediction network by adopting the pre-constructed training set comprises the following steps:

predicting the sample media information and historical data information of the sample media information through a quality prediction network to obtain predicted delivery data corresponding to the sample media information;

determining the prediction loss of the quality prediction network according to the prediction delivery data corresponding to the sample media information and the marking delivery data of the sample media information;

training the quality prediction network according to the prediction loss.

According to a second aspect of the embodiments of the present disclosure, there is provided an intermediary information quality prediction apparatus including:

the acquisition unit is configured to execute acquisition of historical data information of to-be-predicted media information, wherein the historical data information comprises first delivery data of the to-be-predicted media information in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the to-be-predicted media information, and/or second delivery data of each piece of associated media information in the preset time range;

the prediction unit is configured to perform quality prediction according to the to-be-predicted medium information and historical data information of the to-be-predicted medium information to obtain predicted delivery data of the to-be-predicted medium information;

the prediction unit includes:

the first feature extraction subunit is configured to perform feature extraction on the to-be-predicted media information and historical data information of the to-be-predicted media information through the feature extraction network to obtain material features corresponding to the to-be-predicted media information;

and the first prediction subunit is configured to perform prediction processing on the material characteristics through the prediction network to obtain predicted delivery data of the to-be-predicted media information.

In a possible implementation manner, the historical data information includes first delivery data of the to-be-predicted medium information in a preset time range, the feature extraction network includes a first network and a second network, and the first feature extraction subunit includes:

the characteristic extraction submodule is configured to perform characteristic extraction on the medium information to be predicted through the first network to obtain a first content characteristic;

the vector conversion sub-module is configured to perform vector conversion processing on the first delivery data through the second network to obtain a first vector representation;

and the processing submodule is configured to execute the step of obtaining the material characteristics of the medium information to be predicted according to the first content characteristics and the first vector representation.

In a possible implementation manner, the historical data information further includes at least one piece of associated media information corresponding to the media information to be predicted and corresponding to the same media information publisher, and second delivery data of each piece of associated media information in the preset time range; the medium information quality prediction apparatus further includes:

a second feature extraction unit configured to perform feature extraction on each piece of associated media information through the first network, respectively, to obtain each second content feature;

a second vector conversion unit configured to perform vector conversion processing on each second launch data through the second network to obtain each second vector representation;

the processing sub-module is further configured to perform:

In one possible implementation, the feature extraction network further includes a convergence network, and the processing sub-module is further configured to perform:

In a possible implementation manner, the medium information quality prediction apparatus further includes:

a training unit configured to perform training of the quality prediction network by using a pre-constructed training set, where the training set includes a plurality of sample groups, and each sample group includes sample media information, historical data information of the sample media information, and label delivery data of the sample media information;

the training unit further configured to perform:

training the quality prediction network according to the prediction loss.

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement any one of the medium information quality prediction methods.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the medium information quality prediction method according to any one of the preceding claims.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product, which includes instructions that, when executed by a processor of an electronic device, enable the electronic device to perform the medium information quality prediction method according to any one of the preceding claims.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

according to the embodiment of the invention, the forecast delivery data of the medium information to be forecasted is obtained by obtaining the historical data information of the medium information to be forecasted and carrying out quality forecast according to the medium information to be forecasted and the historical data information of the medium information to be forecasted. The delivery data comprises data used for representing delivery quality of the media information, and the historical data information comprises first delivery data of the media information to be predicted in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the media information to be predicted, and/or second delivery data of each piece of associated media information in a preset time range. Based on the medium information quality prediction method, the medium information quality prediction device, the electronic equipment and the storage medium provided by the embodiment of the disclosure, under the condition that the user side information cannot be obtained, the delivery quality of the medium information to be predicted can be predicted by introducing the historical data information of the medium information to be predicted, and as the historical data information can reflect the potential preference of most users to a certain extent, the delivery quality of the medium information to be predicted is predicted by combining the historical data information of the medium information to be predicted, and the prediction precision of the delivery quality can be improved.

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

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

Fig. 1 is a flow chart illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 2 is a block diagram illustrating a structure of a quality prediction network according to an example embodiment.

Fig. 3 is a flow chart illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 4 is a flow chart illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 5 is a flow chart illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 6 is a diagram illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 7 is a flow chart illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 8 is a block diagram illustrating a structure of a quality prediction network in accordance with an exemplary embodiment.

Fig. 9 is a block diagram illustrating the architecture of a converged network in accordance with an exemplary embodiment.

Fig. 10 is a flow chart illustrating a medium information quality prediction method according to an exemplary embodiment.

Fig. 11 is a block diagram illustrating an intermediary information quality prediction apparatus according to an example embodiment.

FIG. 12 is a block diagram illustrating an electronic device in accordance with an example embodiment.

FIG. 13 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings 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 disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

It should also be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for presentation, analyzed data, etc.) referred to in the present disclosure are both information and data that are authorized by the user or sufficiently authorized by various parties.

In one embodiment, as shown in fig. 1, a medium information quality prediction method is provided, and this embodiment is illustrated by applying the method to a terminal, and it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and is implemented by interaction between the terminal and the server. In this embodiment, the method includes the steps of:

in step 102, historical data information of the to-be-predicted media information is obtained, wherein the historical data information includes first delivery data of the to-be-predicted media information within a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the to-be-predicted media information, and/or second delivery data of each piece of associated media information within a preset time range.

In the embodiment of the disclosure, the medium information to be predicted is the medium information to be used for predicting the delivery quality. The media information base may store media information delivered by each media information publisher and relevant delivery data of historical delivery of each media information, and in the case that the media information is an advertisement material, the media information publisher may be an advertiser that publishes the advertisement material. For example, the delivery data may include data that can characterize the delivery quality of the media information, including but not limited to information such as number of clicks, number of exposures, number of conversions, or data information determined by at least two of the information such as number of clicks, number of exposures, number of conversions, for example: a ratio determined by the number of conversions to the number of exposures, which can be identified as ctcvr. The present disclosure does not specifically limit the launch data, and may be set by a user according to a prediction requirement, and the following description of the present disclosure will be given by taking launch data as a ratio ctcvr of the number of conversions to the number of exposures, where when the launch data is a ratio of the number of conversions to the number of exposures, the higher the ratio is, the better the launch quality of the media information is represented.

After determining the to-be-predicted media information, historical data information of the to-be-predicted media information can be acquired from a media information base, and the historical data information can include first delivery data generated within a preset time range in a historical delivery process of the to-be-predicted media information, at least one piece of associated media information of a same media information publisher corresponding to the to-be-predicted media information, and/or second delivery data generated within the preset time range by each piece of associated media information.

The preset time range is a preset time range, and specific values can be determined by a user according to prediction requirements. For example: the time range can be set to be within one week, the drop data corresponding to the media information to be predicted within one week can be obtained from the media information base, and if the drop data is the ratio ctcvr of the conversion number and the exposure number, the drop data (ctcvr1, ctcvr2, ctcvr3, ctcvr4, ctcvr5, ctcvr6, ctcvr7) within one week of the media information to be predicted can be obtained. And at least one piece of other media information released by the media information publisher can be acquired from the media information base as the related media information of the media information to be predicted according to the media information publisher corresponding to the media information to be predicted, and second release data of the related media information in one week can be acquired from the media information base.

In step 104, performing quality prediction according to the medium information to be predicted and historical data information of the medium information to be predicted to obtain predicted delivery data of the medium information to be predicted; wherein the delivery data comprises data for characterizing the delivery quality of the media information.

In the embodiment of the disclosure, after the to-be-predicted medium information and the historical data information of the to-be-predicted medium information are obtained, the quality prediction can be performed according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information, so as to obtain the predicted delivery data of the to-be-predicted medium information. For example: first predicted delivery data of the to-be-predicted media information can be determined by combining content contained in the to-be-predicted media information, second predicted delivery data of the to-be-predicted media information can be determined according to historical data information (second predicted delivery data can be determined according to the first delivery data and/or the second delivery data, for example, the mean value of the first delivery data and/or the second delivery data can be used as the second predicted delivery data), and the first predicted delivery data and the second predicted delivery data are subjected to weighted summation to obtain predicted delivery data of the to-be-predicted media information.

Or, the to-be-predicted medium information and the historical data information of the to-be-predicted medium information may be subjected to prediction processing through a pre-trained neural network to obtain predicted delivery data of the to-be-predicted medium information.

After the predicted delivery data of the to-be-predicted medium information is obtained, the to-be-predicted medium information may be subjected to medium information recall and link sequencing according to the predicted delivery data, for example: and under the condition that the predicted release data is larger than the release threshold value, media information to be predicted is recalled, and the position sequence of the media information in the recall link is determined according to the predicted release data, so that high-quality media information can enter the recall link, and the benefits of a media information publisher and a platform are improved.

According to the embodiment of the invention, the forecast delivery data of the medium information to be forecasted is obtained by obtaining the historical data information of the medium information to be forecasted and carrying out quality forecast according to the medium information to be forecasted and the historical data information of the medium information to be forecasted. The delivery data comprises data used for representing delivery quality of the media information, and the historical data information comprises first delivery data of the media information to be predicted in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the media information to be predicted, and/or second delivery data of each piece of associated media information in a preset time range. Based on the medium information quality prediction method provided by the embodiment of the disclosure, under the condition that the user side information cannot be obtained, the delivery quality of the medium information to be predicted can be predicted by introducing the historical data information of the medium information to be predicted, and as the historical data information can reflect the potential preference of most users to a certain extent, the delivery quality of the medium information to be predicted is predicted by combining the historical data information of the medium information to be predicted, and the prediction precision of the delivery quality can be improved.

In an exemplary embodiment, the quality prediction can be performed according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information through a quality prediction network, so as to obtain predicted delivery data of the to-be-predicted medium information, as shown in fig. 2, the quality prediction network includes a feature extraction network and a prediction network.

As shown in fig. 3, the quality prediction according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information is realized through a quality prediction network, and specifically, the quality prediction can be realized through the following steps:

in step 302, performing feature extraction on the medium information to be predicted and historical data information of the medium information to be predicted through a feature extraction network to obtain material features corresponding to the medium information to be predicted;

in step 304, the material characteristics are predicted through a prediction network, and predicted delivery data of the medium information to be predicted is obtained.

In the embodiment of the disclosure, the quality prediction network comprises a feature extraction network and a prediction network. The feature extraction network is used for extracting material features, and the prediction network is used for predicting according to the material features to obtain predicted delivery data. After the to-be-predicted medium information and the historical data information corresponding to the to-be-predicted medium information are obtained, the to-be-predicted medium information and the historical data information of the to-be-predicted medium information can be input into a feature extraction network in a quality prediction network as input information for feature extraction, after the material features of the to-be-predicted medium information are obtained, the material features of the to-be-predicted medium information are input into the prediction network as the input information for prediction processing, and the predicted delivery data of the to-be-predicted medium information are obtained.

For example: the historical data information comprises a plurality of associated media information corresponding to the media information to be predicted and corresponding to the same advertiser, so that the media information to be predicted and the associated media information can be input into the feature extraction network for feature extraction to obtain material features of the media information to be predicted, and the material features are input into the prediction network for prediction processing to obtain predicted delivery data of the media information to be predicted.

The medium information quality prediction method provided by the embodiment of the disclosure can realize prediction of the delivery quality of the medium information to be predicted according to the medium information to be predicted and the historical data information of the medium information to be predicted through the quality prediction network, that is, the characteristics of the historical data information are integrated into the characteristics of the medium information to be predicted, so as to obtain the preference of the user, and can improve the prediction efficiency and the prediction precision of the delivery quality.

In an exemplary embodiment, before the quality prediction is performed according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information through the quality prediction network to obtain the predicted delivery data of the to-be-predicted medium information, the method may further include: and training the quality prediction network by adopting a pre-constructed training set, wherein the training set comprises a plurality of sample groups, and each sample group comprises sample medium information, historical data information of the sample medium information and labeled release data of the sample medium information. Referring to fig. 4, the training quality prediction network using the pre-constructed training set may specifically be implemented by the following steps:

in step 402, the sample media information and the historical data information of the sample media information are subjected to prediction processing through a quality prediction network, so as to obtain predicted delivery data corresponding to the sample media information;

in step 404, determining the predicted loss of the quality prediction network according to the predicted delivery data corresponding to the sample media information and the labeled delivery data of the sample media information;

in step 406, the quality prediction network is trained based on the predicted loss.

In the embodiment of the disclosure, a sample group may be constructed according to sample media information, historical data information of the media information as historical data information of the sample media information, and current delivery data of the media information as labeled delivery data of the sample media information, according to the sample media information, the historical data information of the sample media information, and the labeled delivery data of the sample media information, a training set may be constructed according to a plurality of sample groups, and a network may be predicted according to training quality of the training set.

For example, the sample advertisement data and the historical data information of the sample advertisement data may be input to a quality prediction network as input information to perform quality prediction, and the output of the quality prediction network is predicted delivery data corresponding to the sample media information. After the predicted delivery data of the sample medium information is obtained, the predicted loss of the quality prediction network can be determined according to the predicted delivery data of the sample medium information and the labeled delivery data of the sample medium information. The starting embodiment does not specifically limit the specific way of determining the predicted loss, and practically any loss calculation way is applicable to the embodiments of the present disclosure, for example: loss calculation modes such as MSE (Mean Square Error) and MAE (Mean Absolute Error).

It should be noted that, in the embodiment of the present disclosure, the network structure of the prediction network is not specifically limited, for example: the prediction network may be a DNN (Deep Neural Networks) network including a plurality of fully connected layers and modules such as relu activation functions.

After the prediction loss of the quality prediction network is determined, the quality prediction network may be trained based on the prediction loss. For example, in the case that the predicted loss does not satisfy the training requirement (for example, the predicted loss is greater than the preset loss threshold), the network parameters of the quality prediction network, including the parameters of the adjusted feature extraction network and the parameters of the adjusted prediction network, may be adjusted according to the predicted loss until the predicted loss of the quality prediction network satisfies the training requirement (for example, the predicted loss is less than or equal to the preset loss threshold), so as to obtain the trained quality prediction network.

According to the medium information quality prediction method provided by the embodiment of the disclosure, a training set can be constructed according to sample medium information and historical data information of the sample medium information, a quality prediction network is trained through the constructed training set, and then the quality prediction network can be used for predicting the delivery quality of the medium information to be predicted according to the medium information to be predicted and the historical data information of the medium information to be predicted, so that the prediction efficiency and the prediction precision of the delivery quality can be improved.

In an exemplary embodiment, the historical data information includes first delivery data of the to-be-predicted medium information within a preset time range, and the feature extraction network includes a first network and a second network. Referring to fig. 5, in step 302, the feature extraction network performs feature extraction on the to-be-predicted media information and the historical data information of the to-be-predicted media information to obtain material features corresponding to the to-be-predicted media information, which may specifically be implemented by the following steps:

in step 502, performing feature extraction on the medium information to be predicted through a first network to obtain a first content feature;

in step 504, vector conversion processing is performed on the first launch data through the second network to obtain a first vector representation;

in step 506, material characteristics of the media information to be predicted are obtained according to the first content characteristics and the first vector representation.

In the embodiment of the present disclosure, referring to fig. 6, the historical data information includes first delivery data of the medium information to be predicted in a preset time range, and the feature extraction network includes a first network and a second network, where the first network is configured to perform feature extraction on the network to be predicted to obtain a first content feature, and the second network is configured to perform vector conversion processing on the first delivery data of the network to be predicted to obtain a first vector representation of the first delivery data.

In one example, the first network may include at least one of a first feature extraction module, a second feature extraction module, a third feature extraction module, and a fourth feature extraction module, wherein the first feature extraction module is configured to extract visual features of the medium information, the second feature extraction module is configured to extract image text features of the medium information, the third feature extraction module is configured to extract voice text features of the medium information, and the fourth feature extraction module is configured to extract audio features of the medium information.

The first feature extraction module, the second feature extraction module, the third feature extraction module and the fourth feature extraction module can be pre-trained network modules. In the embodiment of the present disclosure, for convenience of understanding, the first feature extraction module is an moco (motion context for Unsupervised Visual Representation Learning, which is based on Momentum comparison) model, the second feature extraction module and the third feature extraction module are Bert (Bidirectional Encoder Representation from transforms, which is based on a converter) model, and the fourth feature extraction module is a vggish model.

The first feature extraction module can adopt different visual feature extraction strategies according to different types of the medium information. For example, for the media information of a picture type, the first feature extraction module may directly extract moco features of the picture as visual features of the media information; for the media information of the video type, the first feature extraction module may extract moco features of multiple frames of images from the video on average (for example, extract 8 frames), and then average the moco features of the multiple frames of images to obtain visual features of the media information of the video type.

The second feature extraction module can also adopt different visual feature extraction strategies according to different types of the medium information. For the media information of the picture type, after extracting text information appearing in the picture/video by using methods such as Optical Character Recognition (OCR) and the like, extracting image text features in the text information; for the media information of the video type, extracting multiple frames of images (for example, extracting 8 frames) from the video, extracting text information for each frame of image, splicing the text information of the multiple frames of images, and extracting image text features of the spliced text information.

The third feature extraction module is similar to the second feature extraction module, and extracts the Speech text features in the Speech text information after extracting the Speech text information in the video by using an Automatic Speech Recognition (ASR) technology. The fourth feature extraction module can directly extract audio features of the audio data in the video.

After the features are extracted through a plurality of items in the first feature extraction module, the second feature extraction module, the third feature extraction module and the fourth feature extraction module, the extracted plurality of items of features can be spliced to obtain the first content features of the medium information to be predicted.

The second network is used for vector conversion of the delivery data, the network structure of the second network is not limited in the embodiment of the disclosure, and any network structure capable of realizing vector expression is within the application range of the embodiment of the disclosure.

Illustratively, the second network may be modeled based on an anchor interpolation concept. The second network is used for carrying out vector conversion on the release data, taking the release data as a ratio ctcvr of a conversion number and an exposure number as an example, the ctcvr is a random number in a value range of 0-1 and has infinite values, and the second network can convert the release data into an expression with a fixed dimension through anchor point interpolation. Illustratively, a plurality of ctcvr anchor points may be pre-designed, such as: and determining that 8 total ctcvr of [1e-7, 1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 1e-1, 1] are 8 anchor points. For a plurality of ctcvr anchor points, a base-10 logarithm may be taken to obtain a value corresponding to each anchor point, and still in the example of 8 anchor points, a base-10 logarithm may be taken to obtain [ -7, -6, -5, -4, -3, -2, -1, 0 ].

When the second network is constructed, a vector representation Emb can be respectively and randomly initialized for a plurality of anchor points_iThe Emb_iRepresenting the vector of anchor points with a representative value i, and further based on the anchor pointsThe vector of (A) represents Emb_iA second network is constructed. For example, after the above-mentioned 8 anchor point random initialization vectors are expressed, obtain [ Emb_-7，Emb_-6，Emb_-5，Emb_-4，Emb_-3，Emb_-2，Emb_-1，Emb₀]The second network may be constructed from the 8 anchor points. And in the training process of the quality prediction network, continuously adjusting the vector representations of the anchor points of the second network until the vector representations corresponding to the anchor points are obtained when the training is finished.

For first delivery data, a logarithm with the base 10 may be taken for the first delivery data to obtain a corresponding numerical value, two anchor points (a first anchor point and a second anchor point are assumed) adjacent to the numerical value are determined, and a first vector representation of the first delivery data is obtained by performing linear combination on vector representations of the two adjacent anchor points, where the specific process may refer to the following formula (1).

Wherein, the Emb_ctcvrA first vector representation for representing a correspondence of the first delivery data,

a vector representation for representing a first anchor point,

a vector representation for representing the second anchor point, ctcvr representing the first impression data, ctcvr_j-1For representing the drop data, ctcvr, corresponding to the first anchor point_jFor representing the placement data corresponding to the second anchor point.

Taking the first delivery data as 0.005 as an example, the second network takes the logarithm of base 10 to obtain-2.30, and since-2.30 is located between anchor points corresponding to two values of-3 and-2, the obtained first vector represents the reference formula (2):

Emb_-2.3＝(-2-(-2.3))*Emb_-3+(-2.3-(-3))*Emb_-2formula (2)

It should be noted that, the setting of 8 anchor points is only an example of the embodiment of the present disclosure, and actually, N anchor points may be set, and a value of N may be set according to a prediction requirement. When first placement data smaller than the corresponding minimum placement data among the plurality of anchor points is present, the vector representation of the anchor point corresponding to the minimum placement data may be used as the vector representation of the first placement data; accordingly, in the case where first placement data larger than the largest placement data among the plurality of anchor points is present, the vector representation of the anchor point corresponding to the largest placement data may be used as the vector representation of the first placement data. Taking the above 8 anchor points as an example, when the first delivery data is smaller than 1e-7, the vector representation corresponding to the anchor point (1e-7) may be used as the vector representation of the first delivery data; or, when the first delivery data is larger than 1, the vector representation corresponding to the anchor point (1) may be used as the vector representation of the first delivery data.

In this way, the second network can realize vector representation of any one piece of delivery data by using vector representation of a plurality of anchor points, and the second network is more lightweight and can improve the prediction efficiency of the quality prediction network.

After the first content characteristic and the first vector representation are obtained, the first content characteristic and the first vector representation can be spliced to obtain a material characteristic of the to-be-predicted media information, and the material characteristic is further subjected to prediction processing through a prediction network to obtain predicted delivery data of the to-be-predicted media information.

In the embodiment of the present disclosure, the first network may be a pre-trained network, that is, the first network is not trained in the training process of the quality prediction network; alternatively, the first network may also perform synchronous training with the second network and the prediction network in the training process of the quality prediction network, which is not specifically limited in this disclosure.

According to the media information quality prediction method provided by the embodiment of the disclosure, under the condition that the user side information cannot be obtained, the delivery quality of the media information to be predicted can be predicted by introducing the first delivery data of the media information to be predicted in the preset time range, and as the first delivery data of the media information to be predicted in the preset time range can reflect the potential preference of most users to a certain extent, the delivery quality of the media information to be predicted can be predicted by combining the first delivery data of the media information to be predicted in the preset time range, and the prediction accuracy of the delivery quality can be improved.

In an exemplary embodiment, the historical data information may further include at least one piece of associated media information corresponding to the media information to be predicted and corresponding to the same media information publisher, and second delivery data of each piece of associated media information within a preset time range. Referring to fig. 7, before obtaining material characteristics of the media information to be predicted according to the first content characteristics and the first vector representation in step 506, the method may further include:

in step 508, respectively performing feature extraction on each associated media information through the first network to obtain each second content feature;

in step 510, performing vector conversion processing on each second launch data through a second network to obtain each second vector representation;

in step 506, the material characteristics of the media information to be predicted are obtained according to the first content characteristics and the first vector representation, which can be specifically realized by the following steps:

in step 5062, a first material characteristic of the media information to be predicted is obtained according to the first content characteristic and the first vector representation;

in step 5064, a second pixel feature of the media information to be predicted is obtained according to each second content feature and each second vector representation;

in step 5066, the material characteristics of the media information to be predicted are obtained according to the first material characteristics and the second material characteristics.

In the embodiment of the disclosure, the historical data information includes first delivery data of the to-be-predicted media information in a preset time range, at least one piece of associated media information of the same media information publisher corresponding to the to-be-predicted media information, and second delivery data of each piece of associated media information in the preset time range.

On the basis of obtaining the first content features and the first vector representations of the to-be-predicted media information in the foregoing embodiment, feature extraction may be performed on each piece of associated media information through the first network to obtain the second content features of each piece of associated media information, respectively, and vector conversion may be performed on the second delivery data of each piece of associated media information through the second network to obtain the second vector representations of each piece of second delivery data, respectively.

For the first content feature Emb_vAnd the first vector represents Emb_ctcvrThe first material characteristic Emb1 (Emb) of the medium information to be predicted can be obtained by splicing (Emb)_v；Emb_ctcvr). The second content characteristics and the second vector representations corresponding to the associated media information are spliced to obtain second material characteristics [ Emb21, Emb22, … … and Emb2n ] corresponding to the media information to be predicted]Wherein Emb2i ═ (Emb)_vi；Emb_ctcvri) I is a positive number greater than 0 and less than n, n is the total number of associated media information, Emb2i represents the material characteristics corresponding to the ith associated media information, Emb_viRepresenting a second content characteristic, Emb, corresponding to the ith associated media information_ctcvriAnd representing a second vector representation corresponding to the ith associated medium information.

After the first material characteristic and the second material characteristic of the to-be-predicted media information are obtained, the first material characteristic and the second material characteristic can be subjected to fusion processing to obtain the material characteristic of the to-be-predicted media information. And then, the material characteristics can be predicted through a prediction network to obtain predicted delivery data of the medium information to be predicted.

According to the media information quality prediction method provided by the embodiment of the disclosure, under the condition that the user side information cannot be obtained, the delivery quality of the media information to be predicted can be predicted by introducing the first delivery data of the media information to be predicted in the preset time range, the at least one piece of associated media information corresponding to the same media information publisher as the media information to be predicted, and the second delivery data of each piece of associated media information in the preset time range, and the potential preference of most users can be accurately reflected through abundant historical data information, so that the delivery quality of the media information to be predicted can be predicted by combining the historical data information, and the prediction precision of the delivery quality can be improved.

In an exemplary embodiment, referring to fig. 8, the feature extraction network further includes a fusion network, and in step 5126, the material features of the to-be-predicted media information are obtained according to the first material features and the second material features, which may be specifically implemented as follows:

and performing feature fusion processing on the first material features and the second material features through a fusion network to obtain the material features of the medium information to be predicted.

In the embodiment of the present disclosure, the fusion network is used to perform feature fusion on the first material feature and the second material feature, and the network structure of the fusion network is not specifically limited in the embodiment of the present disclosure, and all networks capable of implementing feature fusion are suitable for use in the embodiment of the present disclosure.

Illustratively, referring to FIG. 9, a fusion network may be constructed from self-attention in the transform framework. The fusion network can project the first material characteristics through linear projection to reduce the characteristic dimensionality of the first material characteristics, and obtain Q (query) corresponding to the first material characteristics, wherein if the projected characteristic expression dimensionality is D, the characteristic dimensionality of Q is 1 × D at the moment. Similarly, the second material feature may be projected through linear projection to obtain k (key) and v (value) corresponding to the second material feature, where feature expression dimensions of the projected second material feature are D as same as those of the first material feature, and feature dimensions of K, V are n × D after linear projection.

The similarity between Q, K can be determined, which can be used to represent the similarity between the media information to be predicted and N related media information, if the similarity between the media information to be predicted and one related media information is better, the similarity between Q, K is very high and can approach to 1 infinitely, otherwise, if the similarity between the media information to be predicted and one related media information is worse, the similarity between Q, K is very low and can approach to 0 infinitely.

After normalization processing is performed on each similarity, each similarity can be used as a weight and weighted and summed with the corresponding V, so that the first material characteristic and the second material characteristic are fused to obtain the material characteristic of the medium information to be predicted, and the following formula (3) can be referred to specifically.

Wherein, the Attention (Q, K, V) is used to represent the corresponding predicted delivery data of the medium information to be predicted. Q is used to represent query (query), K is used to represent key (key), V is used to represent value (value), and D is used to represent feature expression dimension.

After the material characteristics are input into a prediction network for prediction processing, prediction delivery data corresponding to the medium information to be predicted can be obtained, and then advertisement recalling is carried out on the medium information to be predicted according to the prediction delivery data corresponding to the medium information to be predicted.

It should be noted that the fusion network may perform synchronous training with the first network, the second network, the prediction network, and other networks in the training process of the quality prediction network, that is, in the process of adjusting the network parameters of the quality prediction network according to the prediction loss, the network parameters of the fusion network are adjusted until the prediction loss meets the training requirement, so as to obtain the trained fusion network.

According to the media information quality prediction method provided by the embodiment of the disclosure, the first material characteristic and the second material characteristic can be fused through a fusion network, so that the material characteristic containing the potential preference of the user is obtained, and further, the quality prediction is performed according to the material characteristic, so that the prediction precision of the delivery quality can be improved.

In order that those skilled in the art will better understand the embodiments of the present disclosure, the embodiments of the present disclosure are described below by way of specific examples.

Referring to fig. 10, the quality prediction network includes a feature extraction network and a prediction network, where the feature extraction network includes a first network, a second network and a fusion network, and in this example, taking the media information to be predicted as the video type, the first network includes a first feature extraction module, a second feature extraction module, a third feature extraction module and a fourth feature extraction module.

The historical data information corresponding to the to-be-predicted media information is obtained and comprises a first ctcvr (ratio of the conversion number to the exposure number) of the to-be-predicted media information in a preset time range, and at least one piece of associated media information of the same media information publisher corresponding to the to-be-predicted media information and a second ctcvr corresponding to the associated media information.

And inputting the medium information to be predicted, the first ctcvr, at least one piece of associated medium information and the second ctcvr of each piece of associated medium information into a quality prediction network. The first content features of the media information to be predicted and the second content features of each associated media information are extracted through the first network, respectively (for a specific process, refer to the foregoing embodiment, this example is not described herein again). And respectively converting the first ctcvr of the medium information to be predicted into a first vector representation and converting the second ctcvr of each piece of associated medium information into a second vector representation through a second network.

And in the fusion network, splicing the first content characteristics and the first vector representations into first material characteristics, splicing the second content characteristics and the second vector representations into second material characteristics respectively, fusing the first material characteristics and the second material characteristics to obtain material characteristics of the medium information to be predicted, and inputting the material characteristics into the prediction network.

And the prediction network carries out prediction processing on the material characteristics to obtain the predicted ctcvr of the medium information to be predicted.

It should be understood that although the various steps in the flowcharts of fig. 1-10 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-10 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps or stages.

It is understood that the same/similar parts between the embodiments of the method described above in this specification can be referred to each other, and each embodiment focuses on the differences from the other embodiments, and it is sufficient that the relevant points are referred to the descriptions of the other method embodiments.

Fig. 11 is a block diagram illustrating an apparatus for media information quality prediction according to an exemplary embodiment. Referring to fig. 11, the apparatus includes an acquisition unit 1102 and a prediction unit 1104.

The acquiring unit 1102 is configured to perform acquiring historical data information of to-be-predicted media information, where the historical data information includes first delivery data of the to-be-predicted media information in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the to-be-predicted media information, and/or second delivery data of each piece of associated media information in the preset time range;

the prediction unit 1104 is configured to perform quality prediction according to the to-be-predicted medium information and historical data information of the to-be-predicted medium information to obtain predicted delivery data of the to-be-predicted medium information;

According to the embodiment of the invention, the forecast delivery data of the medium information to be forecasted is obtained by obtaining the historical data information of the medium information to be forecasted and carrying out quality forecast according to the medium information to be forecasted and the historical data information of the medium information to be forecasted. The delivery data comprises data used for representing delivery quality of the media information, and the historical data information comprises first delivery data of the media information to be predicted in a preset time range, at least one piece of associated media information of a same media information publisher corresponding to the media information to be predicted, and/or second delivery data of each piece of associated media information in a preset time range. Based on the medium information quality prediction device provided by the embodiment of the disclosure, under the condition that the user side information cannot be obtained, the delivery quality of the medium information to be predicted can be predicted by introducing the historical data information of the medium information to be predicted, and as the historical data information can reflect the potential preference of most users to a certain extent, the delivery quality of the medium information to be predicted is predicted by combining the historical data information of the medium information to be predicted, and the prediction precision of the delivery quality can be improved.

In an exemplary embodiment, the quality prediction is performed according to the to-be-predicted medium information and the historical data information of the to-be-predicted medium information through a quality prediction network to obtain predicted delivery data of the to-be-predicted medium information, wherein the quality prediction network comprises a feature extraction network and a prediction network; the prediction unit 1104 includes:

In an exemplary embodiment, the historical data information includes first delivery data of the to-be-predicted medium information in a preset time range, the feature extraction network includes a first network and a second network, and the first feature extraction subunit includes:

In an exemplary embodiment, the historical data information further includes at least one piece of associated media information corresponding to the media information to be predicted and corresponding to the same advertiser, and second placement data of each piece of associated media information in the preset time range; the medium information quality prediction apparatus further includes:

the processing sub-module is further configured to perform:

In an exemplary embodiment, the feature extraction network further comprises a convergence network, and the processing sub-module is further configured to perform:

In an exemplary embodiment, the first network comprises at least one of a first feature extraction module, a second feature extraction module, a third feature extraction module, and a fourth feature extraction module;

In an exemplary embodiment, the medium information quality predicting apparatus further includes:

the training unit further configured to perform:

training the quality prediction network according to the prediction loss.

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

Fig. 12 is a block diagram illustrating an electronic device 1200 for mediating information quality prediction in accordance with an example embodiment. For example, the electronic device 1200 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a gaming console, a tablet device, a medical device, a fitness device, a personal digital assistant, and so forth.

Referring to fig. 12, electronic device 1200 may include one or more of the following components: processing component 1202, memory 1204, power component 1206, multimedia component 1208, audio component 1210, input/output (I/O) interface 1212, sensor component 1214, and communications component 1216.

The processing component 1202 generally controls overall operation of the electronic device 1200, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 1202 may include one or more processors 1220 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 1202 can include one or more modules that facilitate interaction between the processing component 1202 and other components. For example, the processing component 1202 can include a multimedia module to facilitate interaction between the multimedia component 1208 and the processing component 1202.

The memory 1204 is configured to store various types of data to support operation at the electronic device 1200. Examples of such data include instructions for any application or method operating on the electronic device 1200, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 1204 may be implemented by any type or combination of volatile or non-volatile storage devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, optical disk, or graphene memory.

The power supply component 1206 provides power to the various components of the electronic device 1200. The power components 1206 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 1200.

The multimedia component 1208 comprises a screen providing an output interface between the electronic device 1200 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1208 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 1200 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

Audio component 1210 is configured to output and/or input audio signals. For example, the audio component 1210 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 1200 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 1204 or transmitted via the communication component 1216. In some embodiments, audio assembly 1210 further includes a speaker for outputting audio signals.

The I/O interface 1212 provides an interface between the processing component 1202 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 1214 includes one or more sensors for providing various aspects of state assessment for the electronic device 1200. For example, the sensor assembly 1214 may detect an open/closed state of the electronic device 1200, the relative positioning of components, such as a display and keypad of the electronic device 1200, the sensor assembly 1214 may also detect a change in the position of the electronic device 1200 or components of the electronic device 1200, the presence or absence of user contact with the electronic device 1200, the orientation or acceleration/deceleration of the device 1200, and a change in the temperature of the electronic device 1200. The sensor assembly 1214 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 1214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1214 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communications component 1216 is configured to facilitate communications between the electronic device 1200 and other devices in a wired or wireless manner. The electronic device 1200 may access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 1216 receives the broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 1216 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 1200 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as the memory 1204 comprising instructions, executable by the processor 1220 of the electronic device 1200 to perform the above-described method is also provided. For example, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program product is also provided that includes instructions executable by the processor 1220 of the electronic device 1200 to perform the above-described method.

Fig. 13 is a block diagram illustrating an electronic device 1300 for mediating information quality prediction in accordance with an example embodiment. For example, the electronic device 1300 may be a server. Referring to fig. 13, electronic device 1300 includes a processing component 1320 that further includes one or more processors and memory resources, represented by memory 1322, for storing instructions, such as application programs, that are executable by processing component 1320. The application programs stored in memory 1322 may include one or more modules each corresponding to a set of instructions. Further, the processing component 1320 is configured to execute instructions to perform the methods described above.

The electronic device 1300 may further include: the power component 1324 is configured to perform power management for the electronic device 1300, the wired or wireless network interface 1326 is configured to connect the electronic device 1300 to a network, and the input-output (I/O) interface 1328. The electronic device 1300 may operate based on an operating system stored in the memory 1322 such as Window 1313 over, Mac O13X, Unix, Linux, FreeB13D, or the like.

In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as memory 1322 comprising instructions, executable by a processor of electronic device 1300 to perform the above-described method is also provided. The storage medium may be a computer-readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program product is also provided, which includes instructions executable by a processor of the electronic device 1300 to perform the above-described method.

It should be noted that the descriptions of the above-mentioned apparatus, the electronic device, the computer-readable storage medium, the computer program product, and the like according to the method embodiments may also include other embodiments, and specific implementations may refer to the descriptions of the related method embodiments, which are not described in detail herein.

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

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

Claims

1. A method for predicting quality of media information, comprising:

2. The method according to claim 1, wherein the quality prediction according to the to-be-predicted media information and the historical data information of the to-be-predicted media information is realized through a quality prediction network to obtain predicted delivery data of the to-be-predicted media information, and the quality prediction network comprises a feature extraction network and a prediction network;

3. The method according to claim 2, wherein the historical data information includes first delivery data of the to-be-predicted medium information in a preset time range, and the feature extraction network includes a first network and a second network;

4. The method according to claim 3, wherein the historical data information further includes at least one piece of associated media information corresponding to the media information to be predicted and corresponding to the same media information publisher, and second delivery data of each piece of associated media information within the preset time range;

5. The method according to claim 4, wherein the feature extraction network further comprises a fusion network, and the obtaining of the material features of the media information to be predicted according to the first material features and the second material features comprises:

6. The method according to any one of claims 2 to 5, wherein before the performing, by the quality prediction network, quality prediction according to the to-be-predicted media information and historical data information of the to-be-predicted media information to obtain predicted delivery data of the to-be-predicted media information, the method further comprises:

training the quality prediction network according to the prediction loss.

7. An apparatus for predicting quality of media information, comprising:

8. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the medium information quality prediction method according to any one of claims 1 to 6.

9. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the media information quality prediction method of any one of claims 1 to 6.

10. A computer program product comprising instructions which, when executed by a processor of an electronic device, enable the electronic device to perform the method of media information quality prediction according to any one of claims 1 to 6.