CN115131059A

CN115131059A - Method and device for publishing multimedia resources, computer equipment and storage medium

Info

Publication number: CN115131059A
Application number: CN202210629754.8A
Authority: CN
Inventors: 秦嘉
Original assignee: Tencent Technology Beijing Co Ltd
Current assignee: Tencent Technology Beijing Co Ltd
Priority date: 2022-06-02
Filing date: 2022-06-02
Publication date: 2022-09-30

Abstract

The application provides a method and a device for publishing multimedia resources, computer equipment and a storage medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring parameter values of a plurality of release parameters of a plurality of historical multimedia resources according to a target multimedia resource to be released; displaying an optimized parameter value and a confidence coefficient of at least one target release parameter based on the difference between the parameter values of a plurality of release parameters of a plurality of historical multimedia resources, wherein the confidence coefficient is used for representing the reliability degree of the corresponding target release parameter; and responding to the issuing parameter selection operation, and issuing the target multimedia resource based on the optimized parameter value of the selected at least one target issuing parameter. The scheme can optimize the parameter values of each effect parameter of the target multimedia resource, so that the target multimedia resource can obtain better effect after being issued.

Description

Method and device for publishing multimedia resources, computer equipment and storage medium

Technical Field

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

Background

With the development of the internet, advertisements have become an effective means for presenting information to users. The advertisement forms comprise multimedia resources such as characters, audio and video. The effect of the advertisement after being released can be measured through the effect parameters such as the conversion rate and the click rate, and how to obtain a good effect after the advertisement is released is a research direction.

At present, the operator mainly adjusts the parameter values of the advertisement publishing mode, the target population and other publishing parameters according to the experience of the operator so as to optimize the effect of the published advertisement. However, for inexperienced operators, it is difficult to find a suitable adjustment method for different advertisements, which results in poor effect after advertisement release.

Disclosure of Invention

The embodiment of the application provides a method and a device for publishing a multimedia resource, computer equipment and a storage medium, which can optimize the parameter value of an effect parameter of a target multimedia resource, so that the target multimedia resource can obtain a better effect after being published. The technical scheme is as follows:

in one aspect, a method for publishing a multimedia resource is provided, and the method includes:

acquiring parameter values of a plurality of release parameters of a plurality of historical multimedia resources according to a target multimedia resource to be released, wherein the plurality of historical multimedia resources and the target multimedia resource have at least one same resource attribute, and the release parameters are used for expressing parameters used when the multimedia resource is released;

displaying an optimized parameter value and a confidence coefficient of at least one target release parameter based on the difference between the parameter values of a plurality of release parameters of the plurality of historical multimedia resources, wherein the confidence coefficient is used for representing the reliability degree of the corresponding target release parameter;

and responding to the issuing parameter selection operation, and issuing the target multimedia resource based on the optimized parameter value of the selected at least one target issuing parameter.

In another aspect, an apparatus for publishing a multimedia resource is provided, the apparatus comprising:

the system comprises an acquisition module, a distribution module and a distribution module, wherein the acquisition module is used for acquiring parameter values of a plurality of distribution parameters of a plurality of historical multimedia resources according to target multimedia resources to be distributed, the plurality of historical multimedia resources and the target multimedia resources have the same at least one resource attribute, and the distribution parameters are used for expressing parameters used when the multimedia resources are distributed;

the display module is used for displaying an optimized parameter value and a confidence coefficient of at least one target release parameter based on the difference between the parameter values of a plurality of release parameters of a plurality of historical multimedia resources, and the confidence coefficient is used for representing the reliability degree of the corresponding target release parameter;

and the resource publishing module is used for responding to the publishing parameter selection operation and publishing the target multimedia resource based on the optimized parameter value of the selected at least one target publishing parameter.

In some embodiments, the display module comprises:

the data set dividing unit is used for dividing the plurality of historical multimedia resources into a first resource set and a second resource set according to the parameter values of the target effect parameters of the plurality of historical multimedia resources, wherein the target effect parameters are used for expressing the effect after the multimedia resources are released;

a first determining unit, configured to determine, for any publishing parameter, a difference coefficient of the publishing parameter based on the first resource set and the second resource set, where the difference coefficient is used to represent a difference between parameter values of the publishing parameters of different historical multimedia resources;

a second determining unit, configured to determine confidence levels of the plurality of publishing parameters based on the first resource set, the second resource set, and difference coefficients of the plurality of publishing parameters;

and the display unit is used for determining and displaying the optimized parameter value and the confidence coefficient of the at least one target release parameter based on the parameter values of the plurality of release parameters of the target multimedia resource and the difference coefficients of the plurality of release parameters.

In some embodiments, the data set partitioning unit is configured to sort the plurality of historical multimedia resources according to parameter values of target effect parameters of the plurality of historical multimedia resources; dividing a first number of historical multimedia resources ranked at the top into the first resource set; and dividing the sorted second quantity of the plurality of historical multimedia resources into the second resource set.

In some embodiments, the first determining unit is configured to obtain at least one candidate parameter value of the release parameter; for any candidate parameter value of the release parameter, obtaining an absolute difference value of the candidate parameter value, where the absolute difference value represents an absolute value of a difference value between a proportion of the candidate parameter value in the first resource set and a proportion of the candidate parameter value in the second resource set; and determining the maximum value of the absolute difference values of the at least one candidate parameter value as the difference coefficient of the issuing parameter.

In some embodiments, the second determining unit is configured to divide the first resource set and the second resource set into a training set and a test set; training to obtain a parameter optimization model based on the training set and the difference coefficients of the plurality of release parameters, wherein the parameter optimization model is used for determining the parameter values of the plurality of release parameters of the input multimedia resource; and processing the test set through the parameter optimization model to determine the confidence degrees of the plurality of release parameters.

In some embodiments, the second determining unit is configured to determine a plurality of information gain coefficients of the plurality of release parameters to the training set, respectively; for any release parameter, weighting the information gain coefficient of the release parameter based on the difference coefficient of the release parameter; and training to obtain the parameter optimization model based on at least one parameter value of the intermediate release parameters, wherein the intermediate release parameters are the release parameters with the maximum weighted information gain coefficients.

In some embodiments, the second determining unit is configured to divide the training set into at least one non-empty training subset according to at least one parameter value of the intermediate issue parameter; and constructing a decision tree by adopting a recursive mode based on the at least one training subset to obtain the parameter optimization model.

In some embodiments, the second determining unit is configured to predict the test set through the parameter optimization model to obtain a prediction accuracy; and respectively determining confidence degrees of the plurality of release parameters based on the difference coefficients of the plurality of release parameters and the prediction accuracy.

In some embodiments, the second determining unit is configured to remove the distribution parameter having the difference coefficient smaller than the first difference threshold from the plurality of distribution parameters.

In some embodiments, the second determining unit is configured to, for any release parameter, remove, from at least one candidate parameter value of the release parameters, a candidate parameter value whose proportion in the training set is smaller than a proportion threshold value.

In some embodiments, the display unit is configured to determine the at least one target publishing parameter based on parameter values of the plurality of publishing parameters of the target multimedia resource and difference coefficients of the plurality of publishing parameters, where the difference coefficient of the target publishing parameter is not less than a second difference threshold, and the parameter value of the target publishing parameter of the target multimedia resource is a first parameter value, where the first parameter value is a parameter value of the target publishing parameter in the second resource set; determining an optimized parameter value of the at least one target release parameter based on the first resource set; and displaying the optimized parameter value and the confidence coefficient of the at least one target release parameter.

In some embodiments, the display unit is configured to, for any target publishing parameter, determine a second parameter value of the target publishing parameter in the first resource set as an optimized parameter value of the target publishing parameter.

In some embodiments, the display module is further configured to display verification information in response to reaching a verification period, where the verification period is a time period beginning with the release of the target multimedia resource, and the verification information is used to indicate a difference before and after the release of the target multimedia resource using the optimized parameter value of the at least one target release parameter.

In another aspect, a computer device is provided, which includes a processor and a memory, where the memory is used to store at least one piece of computer program, and the at least one piece of computer program is loaded and executed by the processor to implement the method for publishing a multimedia resource in the embodiment of the present application.

In another aspect, a computer-readable storage medium is provided, in which at least one piece of computer program is stored, and the at least one piece of computer program is loaded and executed by a processor to implement a method for publishing a multimedia resource as in the embodiments of the present application.

In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer program code, the computer program code being stored in a computer-readable storage medium, the computer program code being read by a processor of a computer device from the computer-readable storage medium, the computer program code being executed by the processor to cause the computer device to perform the method for publishing a multimedia resource as provided in the various alternative implementations of the aspects.

The embodiment of the application provides a multimedia resource publishing scheme, and parameter values of a plurality of publishing parameters of a history multimedia resource similar to a target multimedia resource can provide reference for the target multimedia resource by acquiring a plurality of history multimedia resources with the same resource parameter information as the target multimedia resource to be published. By means of the difference between the parameter values of the plurality of publishing parameters based on the plurality of historical multimedia resources, an optimized parameter value of the at least one target publishing parameter and the degree of reliability of the target publishing parameter can be determined. And finally, issuing the target multimedia resource according to the optimized parameter value of the selected at least one target issuing parameter, so that the parameter value of the effect parameter of the target multimedia resource can be optimized, and a better effect can be achieved after the target multimedia resource is issued.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic diagram of an implementation environment of a method for publishing a multimedia resource according to an embodiment of the present application;

fig. 2 is a flowchart of a method for publishing a multimedia resource according to an embodiment of the present application;

fig. 3 is a flowchart of another method for publishing a multimedia resource according to an embodiment of the present application;

fig. 4 is a flowchart of another multimedia resource publishing method provided in an embodiment of the present application;

fig. 5 is a flowchart of another method for publishing a multimedia resource according to an embodiment of the present application;

fig. 6 is a block diagram of a multimedia resource publishing device provided in an embodiment of the present application;

fig. 7 is a block diagram of another apparatus for publishing multimedia assets, provided in accordance with an embodiment of the present application;

fig. 8 is a block diagram of a terminal according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a server provided according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

The terms "first," "second," and the like in this application are used for distinguishing between similar items and items that have substantially the same function or similar functionality, and it should be understood that "first," "second," and "nth" do not have any logical or temporal dependency or limitation on the number or order of execution.

The term "at least one" in this application means one or more, and the meaning of "a plurality" means two or more.

It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data for analysis, stored data, displayed data, etc.) and signals referred to in this application are authorized by the user or fully authorized by various parties, and the collection, use and processing of the relevant data are subject to relevant laws and regulations and standards in relevant countries and regions. For example, the data of the release parameters and the effect parameters referred to in the present application are acquired under sufficient authorization.

Hereinafter, terms related to the present application are explained.

Machine Learning (ML) is a multi-domain cross subject, and relates to multi-domain subjects such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning. In the embodiment of the application, the parameter optimization model is trained in a machine learning mode.

Conversion Rate (CVR) is an index that measures the effectiveness of an advertisement, and simply is the Conversion Rate of a user clicking on an advertisement to become an active or registered or even paid user.

Click Through Rate (CTR) is a common term for internet advertisements, and refers to the Click arrival Rate of a web advertisement (photo advertisement/text advertisement/keyword advertisement/ranking advertisement/video advertisement, etc.), i.e. the actual number of clicks of the advertisement (strictly speaking, the number of targeted pages to be reached) is divided by the advertisement presentation amount (Show content).

The ID3 algorithm is a greedy algorithm used to construct the decision tree. The ID3 algorithm originates from a concept learning system, takes the descending speed of information entropy as a standard for selecting test attributes, namely, selects the attribute with the highest information gain which is not used for dividing at each node as a dividing standard, and then continues the process until the generated decision tree can perfectly classify the training examples.

The method for publishing the multimedia resource provided by the embodiment of the application can be executed by computer equipment. In some embodiments, the computer device is a terminal or a server. An implementation environment of the method for publishing multimedia resources provided in the embodiment of the present application is described below with a computer device as an example, and fig. 1 is a schematic diagram of an implementation environment of a method for publishing multimedia resources provided in the embodiment of the present application. Referring to fig. 1, the implementation environment includes a terminal 101 and a server 102.

The terminal 101 and the server 102 can be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

In some embodiments, the terminal 101 is a smartphone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart voice interaction device, a smart appliance, a vehicle-mounted terminal, an aircraft, and the like, but is not limited thereto. The terminal 101 is installed and operated with an application for distributing multimedia resources. The multimedia resource to be released may be a text advertisement, an image advertisement, an audio advertisement, a video advertisement, or the like.

In some embodiments, the server 102 is an independent physical server, can also be a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, web service, cloud communication, middleware service, domain name service, security service, CDN (Content Delivery Network), big data and artificial intelligence platform, and the like. The server 102 is used to provide background services for applications used to publish multimedia assets. In some embodiments, the server 102 undertakes primary computing work and the terminal 101 undertakes secondary computing work; or, the server 102 undertakes the secondary computing work, and the terminal 101 undertakes the primary computing work; alternatively, the server 102 and the terminal 101 perform cooperative computing by using a distributed computing architecture.

Those skilled in the art will appreciate that the number of terminals may be greater or less. For example, the number of the terminals may be only one, or several tens or hundreds of the terminals, or more. The number of terminals and the type of the device are not limited in the embodiments of the present application.

Fig. 2 is a flowchart of a method for publishing a multimedia resource according to an embodiment of the present application, and as shown in fig. 2, the method is described as being executed by a terminal in the embodiment of the present application. The method for releasing the multimedia resources comprises the following steps:

201. the terminal obtains parameter values of a plurality of release parameters of a plurality of historical multimedia resources according to the target multimedia resources to be released, the plurality of historical multimedia resources and the target multimedia resources have at least one same resource attribute, and the release parameters are used for expressing parameters used when the multimedia resources are released.

In the embodiment of the present application, the terminal is the terminal 101 shown in fig. 1. Because the plurality of historical multimedia resources and the target multimedia resource have the same at least one resource attribute, the terminal can optimize the parameter values of the plurality of release parameters of the target multimedia resource through the parameter values of the plurality of release parameters of the plurality of historical multimedia resources so as to optimize the parameter values of the effect parameters of the target multimedia resource, and the target multimedia resource can obtain better effect after being released. The effect parameters include conversion rate, click through rate and the like. The resource attribute is an inherent attribute of the multimedia resource, and the resource attribute includes an industry type to which the multimedia resource belongs, a purpose to be achieved for releasing the multimedia resource, a release channel of the multimedia resource, and the like.

202. And the terminal displays the optimized parameter value and the confidence coefficient of at least one target release parameter based on the difference between the parameter values of the plurality of release parameters of the plurality of historical multimedia resources, wherein the confidence coefficient is used for expressing the reliability degree of the corresponding target release parameter.

In the embodiment of the application, the parameter values of the plurality of publishing parameters of different historical multimedia resources are not completely the same, so that the parameter values of the effect parameters of different historical multimedia resources are also different, and at least one target publishing parameter which affects the parameter values of the effect parameters and the confidence of each target publishing parameter can be determined through the difference between the parameter values of the plurality of publishing parameters of the plurality of historical multimedia resources. Further, an optimized parameter value of the at least one target release parameter can be determined, and the parameter value of the at least one effect parameter of the target multimedia resource can be optimized by using the optimized parameter value to release the target multimedia resource.

203. Responding to the release parameter selection operation, and releasing the target multimedia resource by the terminal based on the optimized parameter value of the selected at least one target release parameter.

In the embodiment of the application, by selecting at least one target release parameter, the target multimedia resource is released by the optimized parameter value of the selected at least one target release parameter, and the parameter value of at least one effect parameter of the target multimedia resource can be optimized, so that a better effect can be obtained after the target multimedia resource is released.

The embodiment of the application provides a multimedia resource publishing scheme, and parameter values of a plurality of publishing parameters of historical multimedia resources similar to a target multimedia resource can provide reference for the target multimedia resource by acquiring a plurality of historical multimedia resources with the same resource parameter information as the target multimedia resource to be published. By means of the difference between the parameter values of the plurality of release parameters based on the plurality of historical multimedia resources, an optimized parameter value of the at least one target release parameter and the degree of reliability of the target release parameter can be determined. And finally, issuing the target multimedia resource according to the optimized parameter value of the selected at least one target issuing parameter, so that the parameter value of the effect parameter of the target multimedia resource can be optimized, and a better effect can be achieved after the target multimedia resource is issued.

Fig. 2 exemplarily shows a main flow of the multimedia resource publishing scheme provided in the present application, and the multimedia resource publishing scheme is further described below based on an application scenario. Fig. 3 is a flowchart of another method for publishing a multimedia resource according to an embodiment of the present application, and as shown in fig. 3, the method is described as being executed by a terminal in the embodiment of the present application. The method comprises the following steps:

301. the terminal obtains parameter values of a plurality of release parameters of a plurality of historical multimedia resources according to the target multimedia resources to be released, the plurality of historical multimedia resources and the target multimedia resources have at least one same resource attribute, and the release parameters are used for expressing parameters used when the multimedia resources are released.

In the embodiment of the application, the terminal is used for configuring parameter values of a plurality of publishing parameters of a target multimedia resource to be published. The target multimedia resource is any multimedia resource to be issued. The parameter values of the release parameters can influence the parameter values of the effect parameters of the target multimedia resources after the release, so that the terminal can optimize the parameter values of the plurality of release parameters of the target multimedia resources through the parameter values of the plurality of parameters of the plurality of historical multimedia resources. The plurality of historical multimedia resources are determined by at least one resource attribute of the target multimedia resource, the resource attribute is an inherent attribute of the multimedia resource, and the resource attributes of different multimedia resources are not completely the same. The publishing parameters include parameters such as publishing tools, publishing strategies, target population for publishing, resource quality and the like, and parameter values of the publishing parameters can be represented by binary numbers and can also be represented by natural numbers, which are not limited in the embodiment of the application.

For example, the target multimedia asset and the historical multimedia asset are taken as advertisement assets for illustration. And screening out a plurality of historical advertisement resources which have the same sub-track, optimization target and resource flow as the target advertisement resources according to the three resource attributes of the sub-track, the optimization target and the resource flow of the target advertisement resources. The sub-track refers to the industry type of the advertisement resource, and the industry type is a subdivided type, for example, the financial industry can be subdivided into loan and insurance; the gaming industry can be subdivided into shooting games, role-playing games, and instant strategy games. The optimization goal refers to the purpose to be achieved by publishing the advertisement resources, such as promotion, subscription increase, attention increase and the like. The resource flow refers to a distribution channel of advertisement resources, such as an instant messaging program, a video program, a news program and the like. If the target advertisement resource belongs to a shooting game, is used for promoting virtual items and is an advertisement resource published through a video program, the plurality of historical advertisement resources also belong to the shooting game, are used for promoting the virtual items and are advertisement resources published through the video program. Then, the terminal acquires parameter values of a plurality of distribution parameters of the plurality of historical multimedia resources. The plurality of publishing parameters comprise publishing tools, publishing strategies, target groups, resource quality and the like. If the publisher has 10, the parameter values of the publisher may be represented as 0-9; the issuing agent may also be represented as a 9-bit binary number, with each bit representing a parameter value of an issuing agent, a 0 indicating that the issuing agent is not enabled, and a 1 indicating that the issuing agent is enabled. Similarly, there are 5 kinds of issue strategies, which can be represented as 0-4, or as a binary number of 5 bits, and will not be described herein again.

In some embodiments, the parameter values of the plurality of publishing parameters of the plurality of historical multimedia resources may be directly obtained by the terminal, or may be obtained by the terminal through the server. Taking the acquisition by the server as an example, the terminal sends an acquisition request to the server, where the acquisition request carries the resource identifier of the target multimedia resource and the attribute identifier of at least one resource attribute. The server determines the target multimedia resource through the resource identifier. The server then determines a plurality of historical multimedia assets based on the attribute identification of the at least one asset attribute. The server acquires parameter values of a plurality of release parameters of the plurality of historical multimedia resources and then sends the parameter values to the terminal. After the server acquires the parameter values of the plurality of release parameters of the plurality of historical multimedia resources, the acquired data can be cleaned, and abnormal data such as advertisement resources with consumption less than 1000 yuan and conversion less than 5 are eliminated.

302. The terminal divides the plurality of historical multimedia resources into a first resource set and a second resource set according to the parameter values of the target effect parameters of the plurality of historical multimedia resources, wherein the target effect parameters are used for expressing the effect after the multimedia resources are released.

In the embodiment of the present application, the target effect parameter is an effect parameter selected by a technician through a terminal, that is, the target effect parameter is an effect parameter concerned or expected to be optimized by the technician, and the target effect parameter may also be referred to as a concerned target or a concerned index. The parameter values of the target effect parameters of different historical multimedia resources are the same or different due to the different parameter values of the plurality of release parameters of different historical multimedia resources. The plurality of historical multimedia resources can be divided into two resource sets through the parameter value of the target effect, and the parameter value of the target effect parameter of the historical multimedia resource in one resource set is higher than that of the historical multimedia resource in the other resource set. The target effect parameter may be cvr or ctr, which is not limited in this embodiment of the present application.

In some embodiments, the terminal sorts the plurality of historical multimedia resources according to the parameter value of the target effect parameter, and then divides the resource set. Firstly, the terminal sequences a plurality of historical multimedia resources according to parameter values of target effect parameters of the plurality of historical multimedia resources. Then, the terminal divides a first amount of the prior multiple historical multimedia resources into a first resource set, and divides a second amount of the prior multiple historical multimedia resources into a second resource set. The first number may be equal to the second number, or may be different from the second number. The first number and the second number may be preset numbers or may be a ratio among a plurality of historical multimedia assets.

For example, the first quantity and the second quantity are both 30%, the terminal obtains the top 30% of the ordered plurality of historical multimedia resources to form a first resource set, and obtains the bottom 30% of the ordered plurality of historical multimedia resources to form a second resource set. To facilitate differentiation, the first resource set is identified as 1 and the second resource set is identified as 0.

In some embodiments, since the plurality of historical multimedia resources are divided into two resource sets according to the parameter value of the target effect parameter, the parameter value of the target effect parameter of each historical multimedia resource in the first resource set is within a first range, and the parameter value of the target effect parameter of each historical multimedia resource in the second resource set is within a second range. The terminal obtains the parameter value of the target effect parameter of the target multimedia resource, if the parameter value of the effect parameter is in the first range, the target multimedia resource is shown to be well represented in the index of the target effect parameter, and the terminal can display that the advertisement is well represented in the index XX without adjustment. "; if the parameter value of the effect parameter is within the second range, which indicates that the target multimedia resource is not performing well in the target effect parameter, the following steps 303 to 308 of the embodiment of the present application are performed to optimize the target effect parameter.

It should be noted that, in the embodiment of the present application, the target multimedia resource to be published is a multimedia resource that has never been published, or a multimedia resource that needs to be re-published is published. If the target multimedia resource is a multimedia resource which is never released, the parameter values of a plurality of effect parameters of the target multimedia resource are default values; if the target multimedia resource is a multimedia resource which is released and needs to be released again, the parameter values of the effect parameters of the target multimedia resource are the parameter values of the effect parameters released last time.

303. For any distribution parameter, the terminal determines a difference coefficient of the distribution parameter based on the first resource set and the second resource set, wherein the difference coefficient is used for representing the difference between parameter values of the distribution parameter of different historical multimedia resources.

In the embodiment of the application, the terminal can respectively determine the difference coefficient of each release parameter according to the distribution condition of at least one candidate parameter value of each release parameter in the first resource set and the second resource set. The candidate parameter values refer to parameter values selectable by the publishing parameter, for example, in step 301, there are 9 selectable parameter values of the publishing tool.

In some embodiments, taking any issue parameter as an example for description, the terminal first obtains at least one candidate parameter value of the issue parameter. Then, for any candidate parameter value of the release parameter, the terminal obtains the absolute difference value of the candidate parameter value. Wherein the absolute difference value represents an absolute value of a difference between a proportion of the candidate parameter value in the first resource set and a proportion of the candidate parameter value in the second resource set. And finally, the terminal determines the maximum value in the absolute difference values of at least one candidate parameter value as the difference coefficient of the release parameter. The difference coefficient of the release parameters is determined based on the proportion of the candidate parameter values in the two resource sets, so that the difference coefficient can accurately reflect the difference between the parameter values of the release parameters of different historical multimedia resources.

For example, there are three candidate parameter values for the release parameter X, which are X1, X2, and X3. In the first resource set, the distribution of the three candidate parameter values is X1: 60%; 30% of X2; 10 percent of X3. In the second resource set, the distribution of the three candidate parameter values is X1: 30%; 20% of X2; and (3) 50% of X3. The absolute difference values of the three candidate parameter values are respectively: 30% of X1; 10% of X2; 40 percent of X3. Since the absolute difference of the candidate parameter value X3 is the largest, the difference coefficient of the distribution parameter X is 40%.

It should be noted that, if the candidate parameter value of the release parameter is a continuous variable, the terminal may first convert the candidate parameter value of the release parameter into a discrete variable, and then determine the difference coefficient of the release parameter. The mode of converting the continuous variable into the discrete variable comprises the following steps: the average value, median or quantile are taken in segments, and the like, which are not limited in the embodiment of the application.

304. The terminal divides the first and second resource sets into a training set and a test set.

In the embodiment of the application, the terminal can respectively take a part of data from the first resource set and the second resource set to form a training set, and the rest of data forms a test set.

For example, the terminal randomly selects 70% of data from each of the first resource set and the second resource set to form a training set, and forms the remaining 30% of data into a test set.

It should be noted that, the numbering in the embodiment of the present application is for convenience of description, and the execution order of the steps is not limited, and the step 304 may be executed after the step 303, before the step 303, or in synchronization with the step 303, as described above, and the embodiment of the present application does not limit this.

305. And training by the terminal based on the training set and the difference coefficients of the plurality of release parameters to obtain a parameter optimization model, wherein the parameter optimization model is used for determining the parameter values of the plurality of release parameters of the input multimedia resources.

In the embodiment of the application, the terminal can train a parameter optimization model aiming at the target multimedia resource, and optimize the parameter value of at least one release parameter of the target multimedia resource based on the parameter optimization model, so as to optimize the parameter value of the effect parameter.

In some embodiments, the terminal trains the parameter optimization model by publishing the information gain coefficients of the parameters versus the training set. And the terminal constructs a decision tree based on the decision tree algorithm and the parameter values of a plurality of release parameters of a plurality of historical multimedia resources in the training set. If the parameter values of the plurality of release parameters of the plurality of historical multimedia resources are completely consistent, the decision tree is a single-node tree, namely the decision tree with only one node. If the parameter values of the plurality of release parameters of the plurality of multimedia resources are not completely consistent, the terminal respectively determines a plurality of information gain coefficients of the plurality of release parameters to the training set. For any distribution parameter, weighting the information gain coefficient of the distribution parameter based on the difference coefficient of the distribution parameter. And determining the distribution parameter with the maximum weighted information gain coefficient as the intermediate distribution parameter. Then, the terminal divides the training set into at least one non-empty training subset according to at least one parameter value of the intermediate release parameter. And finally, the terminal constructs a decision tree by adopting a recursive mode based on the at least one training subset to obtain the parameter optimization model.

In some embodiments, the tree generated by the decision tree algorithm is deep and prone to overfitting. Overfitting can be improved by removing the distribution parameters with the difference coefficient smaller than the first difference threshold value from the plurality of distribution parameters. The first difference threshold may be 20%, 25%, 30%, or the like, which is not limited in this embodiment of the application.

In some embodiments, the distribution parameter with a large number of candidate parameter values has a large information gain coefficient, so that the decision tree algorithm may select the distribution parameter with a large number of candidate parameter values, but the distribution parameter is not the optimal distribution parameter. On the basis of weighting the information gain coefficient of the release parameter based on the difference coefficient of the release parameter, the problem can be improved by removing the candidate parameter value of which the proportion in the training set is smaller than the proportion threshold value from at least one candidate parameter value of the release parameter, so that the decision tree algorithm can select a better release parameter. The ratio threshold may be 5%, 7%, or 10%, which is not limited in the embodiment of the present application.

For example, the proportional threshold is 5%. Candidate parameter values for the release parameter Y are Y1, Y2, and Y3. In the training set, the number of the advertising resources with the parameter value of the publishing parameter Y of Y1 is 36%, the number of the advertising resources with the parameter value of the publishing parameter Y of Y2 is 4%, and the number of the advertising resources with the parameter value of the publishing parameter Y of Y3 is 60%. And if the number ratio of the advertising resources with the parameter value of the publishing parameter Y being Y2 is smaller than the ratio threshold, removing the candidate parameter value Y2.

In order to make the process of training the parameter optimization model based on the decision tree algorithm easier to understand, the following is further described. In the training process, the input is a training set D, a publishing parameter set A and a threshold value epsilon. The distribution parameter set a includes the plurality of distribution parameters. The output is a decision tree T.

Firstly, if all the historical multimedia resources in the training set D belong to the same class C _k If the decision tree T is a single node tree, class C is defined _k T is returned as the class label for the node. Wherein all historical multimedia assets belong to the same class C _k The method means that parameter values of a plurality of release parameters of all historical multimedia resources in the training set D are completely consistent.

Secondly, if all the historical multimedia resources in the training set D do not belong to the same class C _k Then calculating the information gain of each publishing parameter in the publishing parameter set A to the training set DCoefficient A _g See the following formula (1) to formula (3). Then weighting the information gain coefficient of each release parameter according to the difference coefficient of each release parameter, and determining the release parameter with the maximum weighted information gain coefficient as an intermediate release parameter A _gnew See the following equation (4).

g(D，a)＝H(D)-H(D|a) (3)

Wherein h (D) represents the empirical entropy of the training set D; k represents the number of categories in the training set D, and is a positive integer; i C _k I represents belonging to class C in training set D _k The number of historical multimedia resources; d represents the number of historical multimedia resources in the training set D; h (D | a) represents the empirical conditional entropy of the distribution parameter a on the data set D in the distribution parameter set a; n represents the number of candidate parameter values of the release parameter a; i D _i The parameter value of the parameter a in the training set D is expressed as a | _i The number of historical multimedia resources; g (D | a) represents the gain factor of the distribution parameter a to the training set D. A. the _g Including a plurality of g (D | a).

A _gnew ＝max(A _g ×(σ+1)) (4)

Wherein A is _gnew Denotes an intermediate publishing parameter, A _g An information gain coefficient indicating a distribution parameter, and σ indicates a difference coefficient of the distribution parameter.

Secondly, if the information gain coefficient of the intermediate release parameter is smaller than the threshold value E, setting the decision tree T as a single node tree, and setting the class C with the largest number of historical multimedia resources in the training set D _k T is returned as the class label for the node. The threshold may be 1, 0.8, 1.1, or the like, which is not limited in this embodiment of the application.

Secondly, if the information gain coefficient of the intermediate publishing parameterIf the value is not less than the threshold value epsilon, releasing the parameter A according to the middle _gnew A plurality of parameter values of _i Dividing the trainer D into at least one non-empty subset D _i A value of a parameter a _i Corresponding to a subset D _i . And for any subset, taking the class with the maximum number of the historical multimedia resources in the subset as a mark to construct a sub-node. And forming a decision tree T by the nodes and the sub-nodes thereof, and returning to T.

Finally, for the ith sub-node, the number D is used _i Taking A' as a publishing parameter set for training set, recursively invoking the steps to obtain a subtree T _i Return to T _i . Wherein, A' is the distribution parameter set after removing the intermediate distribution parameter from the distribution parameter and A.

306. And the terminal processes the test set through the parameter optimization model and determines the confidence degrees of the plurality of release parameters.

In the embodiment of the application, the terminal respectively predicts the historical multimedia resources in the test set through the parameter optimization model obtained through the training in the steps, namely the decision tree, so as to obtain the prediction accuracy. And then respectively determining confidence degrees of the plurality of release parameters based on the difference coefficients of the plurality of release parameters and the prediction accuracy.

In some embodiments, the confidence level of the publication parameter is determined by equation (5) below.

Wherein Z is _j Represents the confidence of the release parameter j, mu represents the prediction accuracy, sigma _j Representing the difference coefficient of the distribution parameter j.

307. And the terminal determines and displays the optimized parameter value and the confidence coefficient of the at least one target release parameter based on the parameter values of the plurality of release parameters of the target multimedia resource and the difference coefficients of the plurality of release parameters.

In the embodiment of the application, the terminal can determine at least one target release parameter to be optimized based on the parameter values of the plurality of release parameters of the target multimedia resource, and further determine the optimized parameter value of the at least one target release parameter. And prompting technicians such as operators and the like by displaying the optimized parameter value and the confidence coefficient of the at least one target release parameter.

In some embodiments, the terminal first determines the at least one target publishing parameter based on the parameter values of the plurality of publishing parameters of the target multimedia resource and the difference coefficient of the plurality of publishing parameters, where the difference coefficient of the target publishing parameter is not less than a second difference threshold, and the parameter value of the target publishing parameter of the target multimedia resource is a first parameter value, and the first parameter value is a parameter value of the target publishing parameter in the second resource set. Then, for any target release parameter, the terminal determines a second parameter value of the target release parameter in the first resource set as an optimized parameter value of the target release parameter based on the first resource set. And finally, the terminal displays the optimized parameter value and the confidence coefficient of the at least one target release parameter. The second difference threshold may be 5%, 20%, 25%, and the like, which is not limited in this embodiment of the application.

For example, taking the second difference threshold as 20%, at least one distribution parameter having a difference coefficient not less than 20% is selected from the plurality of distribution parameters. Then a parameter value of the at least one publishing parameter of the target multimedia asset is determined. For any publishing parameter, the parameter values for the publishing parameter in the first resource set are B1, B3 and B5, while the parameter values for the publishing parameter in the second resource set are B2, B4 and B6. If the parameter value of the publishing parameter of the target multimedia resource is B1, B3 or B5, the publishing parameter is not the target publishing parameter; if the parameter value of the distribution parameter of the target multimedia resource is B2, B4 or B6, the distribution parameter targets the distribution parameter. And, the optimized parameter value of the target distribution parameter may be B1, B3, or B5.

It should be noted that, if a parameter value of one publishing parameter appears in both the first resource set and the second resource set, the resource set with a larger number of occurrences is taken as the resource set in which the parameter value of the publishing parameter is located.

It should be noted that, in order to make the process of determining the optimized parameter value and the confidence of the at least one target publishing parameter described in the foregoing steps 301 to 307 easier to understand, reference is made to fig. 4, where fig. 4 is a flowchart of another publishing method of a multimedia resource provided according to an embodiment of the present application. As shown in fig. 4, the method comprises the following steps: 401. and receiving the input resource identification and the target effect parameter of the target multimedia resource. 402. A plurality of historical multimedia assets is determined. 403. And (6) data cleaning. 404. According to the target effect parameters, the plurality of historical multimedia resources are divided into a first resource set and a second resource set. 405. And judging whether the parameter value of the target effect parameter of the target multimedia resource is in the second resource set. If not, 406 is executed; if so, 407 is performed. 406. And displaying prompt information for prompting that the release parameters are not required to be adjusted. 407. And determining an optimized parameter value and confidence of at least one target release parameter through a parameter optimization model. 408. And displaying the optimized parameter value and the confidence level of the at least one target issuing parameter.

308. Responding to the distribution parameter selection operation, and distributing the target multimedia resource by the terminal based on the optimized parameter value of the selected at least one target distribution parameter.

In the embodiment of the application, at least one target release parameter displayed by the terminal can be selected by an operator. The operator may select one or more target publication parameters. And the terminal issues the target multimedia resource through the optimized parameter value of the selected at least one target issue parameter so as to optimize the parameter value of the target effect parameter.

In some embodiments, the terminal instructs the server to publish the target multimedia asset. Correspondingly, the terminal sends a resource publishing request to the server, wherein the resource publishing request carries the optimized parameter value of the at least one target publishing parameter and the resource identifier of the target multimedia resource. The server analyzes the resource publishing request and publishes the target multimedia resource according to the optimized parameter value of at least one target publishing parameter.

In some embodiments, to verify the validity after adjusting the at least one target publishing parameter, the operator may further set a verification period, and in response to reaching the verification period, the terminal displays verification information, where the verification period is a time period starting with publishing the target multimedia resource, and the verification information is used to represent a difference before and after publishing the target multimedia resource using the optimized parameter value of the at least one target publishing parameter. The verification period may be 3 days, 7 days, 10 days, or the like, which is not limited in the embodiment of the present application.

It should be noted that, in order to make the publishing scheme of the multimedia resource provided in the embodiment of the present application easier to understand, taking the multimedia resource as an advertisement resource as an example, refer to fig. 5, where fig. 5 is a flowchart of another publishing method of the multimedia resource provided in the embodiment of the present application. As shown in fig. 5, the method comprises the following steps: 501. and receiving the starting operation of the advertisement optimization function, and displaying an advertisement selection page. 502. And receiving the target advertisement to be optimized selected by the user. 503. Receiving a target effect parameter selected by a user. 504. And determining an optimized parameter value and confidence of at least one target release parameter by adopting a parameter optimization model. 505. And displaying the optimized parameter value and the confidence level of the at least one target issuing parameter. 506. And manually adjusting the optimized parameter value of the target publishing parameter of the target advertisement. 507. And receiving an optimized parameter value of at least one target release parameter selected by a user, automatically adjusting the optimized parameter value of the target release parameter of the target advertisement, and requesting the server to release the target advertisement. 508. And receiving the verification period set by the user. 509. And outputting the verification information. 510. The requesting server stops publishing the targeted advertisement. 511. The server is requested to continue publishing the targeted advertisement.

Fig. 6 is a block diagram of a multimedia resource publishing device provided in an embodiment of the present application. The device is used for executing the steps in the method for publishing the multimedia resource, and referring to fig. 6, the device comprises: an acquisition module 601, a display module 602, and a resource publishing module 603.

An obtaining module 601, configured to obtain parameter values of multiple release parameters of multiple historical multimedia resources according to a target multimedia resource to be released, where the multiple historical multimedia resources and the target multimedia resource have at least one same resource attribute, and the release parameters are used to indicate parameters used when the multimedia resources are released;

a display module 602, configured to display an optimized parameter value and a confidence level of at least one target release parameter based on a difference between parameter values of a plurality of release parameters of the plurality of historical multimedia resources, where the confidence level is used to indicate a reliability degree of the corresponding target release parameter;

the resource issuing module 603 is configured to, in response to the issuing parameter selection operation, issue the target multimedia resource based on the optimized parameter value of the selected at least one target issuing parameter.

In some embodiments, fig. 7 is a block diagram of another apparatus for publishing a multimedia resource provided by an embodiment of the present application, and referring to fig. 7, the display module 602 includes:

a data set dividing unit 701, configured to divide the multiple historical multimedia resources into a first resource set and a second resource set according to parameter values of target effect parameters of the multiple historical multimedia resources, where the target effect parameters are used to indicate an effect after the multimedia resources are released;

a first determining unit 702, configured to determine, for any distribution parameter, a difference coefficient of the distribution parameter based on the first resource set and the second resource set, where the difference coefficient is used to represent a difference between parameter values of the distribution parameter of different historical multimedia resources;

a second determining unit 703, configured to determine confidence levels of the multiple publishing parameters based on the first resource set, the second resource set, and difference coefficients of the multiple publishing parameters;

a display unit 704, configured to determine and display an optimized parameter value and a confidence of the at least one target distribution parameter based on the parameter values of the plurality of distribution parameters of the target multimedia resource and the difference coefficients of the plurality of distribution parameters.

In some embodiments, the data set partitioning unit 701 is configured to sort the plurality of historical multimedia resources according to parameter values of target effect parameters of the plurality of historical multimedia resources; dividing a first quantity of historical multimedia resources which are sequenced at the front into the first resource set; and dividing the second quantity of the sequenced historical multimedia resources into the second resource set.

In some embodiments, the first determining unit 702 is configured to obtain at least one candidate parameter value of the release parameter; for any candidate parameter value of the release parameter, obtaining an absolute difference value of the candidate parameter value, wherein the absolute difference value represents an absolute value of a difference value between a proportion of the candidate parameter value in the first resource set and a proportion of the candidate parameter value in the second resource set; and determining the maximum value of the absolute difference values of the at least one candidate parameter value as the difference coefficient of the issuing parameter.

In some embodiments, the second determining unit 703 is configured to divide the first resource set and the second resource set into a training set and a test set; training to obtain a parameter optimization model based on the training set and the difference coefficients of the plurality of release parameters, wherein the parameter optimization model is used for determining the parameter values of the plurality of release parameters of the input multimedia resources; and processing the test set through the parameter optimization model to determine the confidence degrees of the plurality of release parameters.

In some embodiments, the second determining unit 703 is configured to determine a plurality of information gain coefficients of the plurality of distribution parameters to the training set, respectively; for any release parameter, weighting the information gain coefficient of the release parameter based on the difference coefficient of the release parameter; and training to obtain the parameter optimization model based on at least one parameter value of the intermediate release parameter, wherein the intermediate release parameter is the release parameter with the maximum weighted information gain coefficient.

In some embodiments, the second determining unit 703 is configured to divide the training set into at least one non-empty training subset according to at least one parameter value of the intermediate issue parameter; and constructing a decision tree by adopting a recursive mode based on the at least one training subset to obtain the parameter optimization model.

In some embodiments, the second determining unit 703 is configured to predict the test set through the parameter optimization model to obtain a prediction accuracy; and respectively determining the confidence degrees of the plurality of release parameters based on the difference coefficients of the plurality of release parameters and the prediction accuracy.

In some embodiments, the second determining unit 703 is configured to remove the publication parameters with the difference coefficient smaller than the first difference threshold from the plurality of publication parameters.

In some embodiments, the second determining unit 703 is configured to, for any release parameter, remove, from at least one candidate parameter value of the release parameter, a candidate parameter value whose proportion in the training set is smaller than a proportion threshold value.

In some embodiments, the display unit 704 is configured to determine the at least one target publishing parameter based on the parameter values of the plurality of publishing parameters of the target multimedia resource and the difference coefficient of the plurality of publishing parameters, where the difference coefficient of the target publishing parameter is not less than a second difference threshold, and the parameter value of the target publishing parameter of the target multimedia resource is a first parameter value, where the first parameter value is a parameter value of the target publishing parameter in the second resource set; determining an optimized parameter value of the at least one target release parameter based on the first resource set; and displaying the optimized parameter value and the confidence level of the at least one target issuing parameter.

In some embodiments, the display unit 704 is configured to, for any target publishing parameter, determine a second parameter value of the target publishing parameter in the first resource set as an optimized parameter value of the target publishing parameter.

In some embodiments, the display module 602 is further configured to display verification information in response to reaching a verification period, where the verification period is a time period beginning with the release of the target multimedia resource, and the verification information is used to indicate a difference before and after the release of the target multimedia resource with the optimized parameter value of the at least one target release parameter.

It should be noted that: in the distribution device for multimedia resources provided in the foregoing embodiment, when distributing multimedia resources, only the division of each function module is illustrated, and in practical applications, the function distribution may be completed by different function modules according to needs, that is, the internal structure of the device is divided into different function modules, so as to complete all or part of the functions described above. In addition, the publishing device of the multimedia resource and the publishing method embodiment of the multimedia resource provided by the above embodiments belong to the same concept, and the specific implementation process thereof is detailed in the method embodiment and is not described herein again.

In this embodiment of the present application, the computer device can be configured as a terminal or a server, when the computer device is configured as a terminal, the terminal can be used as an execution subject to implement the technical solution provided in the embodiment of the present application, when the computer device is configured as a server, the server can be used as an execution subject to implement the technical solution provided in the embodiment of the present application, or the technical solution provided in the present application can be implemented through interaction between the terminal and the server, which is not limited in this embodiment of the present application.

Fig. 8 is a block diagram of a terminal 800 according to an embodiment of the present application. The terminal 800 may be a portable mobile terminal such as: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. The terminal 800 may also be referred to by other names such as user equipment, portable terminal, laptop terminal, desktop terminal, etc.

In general, the terminal 800 includes: a processor 801 and a memory 802.

Processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 801 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 801 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 801 may be integrated with a GPU (Graphics Processing Unit) which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 801 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 802 is used to store at least one computer program for execution by the processor 801 to implement the method of publishing a multimedia asset provided by the method embodiments of the present application.

In some embodiments, the terminal 800 may further include: a peripheral interface 803 and at least one peripheral. The processor 801, memory 802 and peripheral interface 803 may be connected by bus or signal lines. Various peripheral devices may be connected to the peripheral interface 803 by a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 804, display 805, camera assembly 806, audio circuitry 807, and power supply 808.

The peripheral interface 803 may be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 801 and the memory 802. In some embodiments, the processor 801, memory 802, and peripheral interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 801, the memory 802, and the peripheral interface 803 may be implemented on separate chips or circuit boards, which is not limited by the present embodiment.

The Radio Frequency circuit 804 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 804 communicates with communication networks and other communication devices via electromagnetic signals. The rf circuit 804 converts an electrical signal into an electromagnetic signal to be transmitted, or converts a received electromagnetic signal into an electrical signal. In some embodiments, the radio frequency circuitry 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 804 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: the world wide web, metropolitan area networks, intranets, various generations of mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 804 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 805 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display 805 is a touch display, the display 805 also has the ability to capture touch signals on or above the surface of the display 805. The touch signal may be input to the processor 801 as a control signal for processing. At this point, the display 805 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 805 may be one, disposed on a front panel of the terminal 800; in other embodiments, the display 805 may be at least two, respectively disposed on different surfaces of the terminal 800 or in a folded design; in other embodiments, the display 805 may be a flexible display disposed on a curved surface or a folded surface of the terminal 800. Even further, the display 805 may be configured as a non-rectangular irregular figure, i.e., a shaped screen. The Display 805 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 806 is used to capture images or video. In some embodiments, camera assembly 806 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 806 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp and can be used for light compensation under different color temperatures.

The audio circuitry 807 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 801 for processing or inputting the electric signals to the radio frequency circuit 804 to realize voice communication. For the purpose of stereo sound collection or noise reduction, a plurality of microphones may be provided at different portions of the terminal 800. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 801 or the radio frequency circuit 804 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuitry 807 may also include a headphone jack.

Power supply 808 is used to power the various components in terminal 800. The power source 808 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When the power source 808 includes a rechargeable battery, the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery. The wired rechargeable battery is a battery charged through a wired line, and the wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, the terminal 800 also includes one or more sensors 809. The one or more sensors 809 include, but are not limited to: acceleration sensor 810, gyro sensor 811, pressure sensor 812, optical sensor 813, and proximity sensor 814.

The acceleration sensor 810 can detect the magnitude of acceleration in three coordinate axes of the coordinate system established with the terminal 800. For example, the acceleration sensor 810 may be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 801 may control the display 805 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 810. The acceleration sensor 810 may also be used for collection of motion data of a game or a user.

The gyro sensor 811 may detect a body direction and a rotation angle of the terminal 800, and the gyro sensor 811 may cooperate with the acceleration sensor 810 to collect a 3D motion of the user with respect to the terminal 800. The processor 801 may implement the following functions according to the data collected by the gyro sensor 811: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization while shooting, game control, and inertial navigation.

Pressure sensors 812 may be disposed on the side frames of terminal 800 and/or underlying display 805. When the pressure sensor 812 is disposed on the side frame of the terminal 800, the holding signal of the user to the terminal 800 can be detected, and the processor 801 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 812. When the pressure sensor 812 is arranged at the lower layer of the display screen 805, the processor 801 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 805. The operability control comprises at least one of a button control, a scroll bar control, an icon control, and a menu control.

The optical sensor 813 is used to collect the ambient light intensity. In one embodiment, the processor 801 may control the display brightness of the display screen 805 based on the ambient light intensity collected by the optical sensor 813. Specifically, when the ambient light intensity is high, the display brightness of the display screen 805 is increased; when the ambient light intensity is low, the display brightness of the display 805 is reduced. In another embodiment, the processor 801 may also dynamically adjust the shooting parameters of the camera head assembly 806 according to the ambient light intensity collected by the optical sensor 813.

A proximity sensor 814, also known as a distance sensor, is typically disposed on the front panel of the terminal 800. The proximity sensor 814 is used to collect the distance between the user and the front surface of the terminal 800. In one embodiment, when proximity sensor 814 detects that the distance between the user and the front face of terminal 800 is gradually decreased, processor 801 controls display 805 to switch from a bright screen state to a dark screen state; when the proximity sensor 814 detects that the distance between the user and the front face of the terminal 800 is gradually increased, the processor 801 controls the display 805 to switch from the breath-screen state to the bright-screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 8 is not intended to be limiting of terminal 800 and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components may be used.

Fig. 9 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 900 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 901 and one or more memories 902, where the memory 902 stores at least one computer program that is loaded and executed by the processor 901 to implement the method for publishing a multimedia resource provided by the foregoing method embodiments. Certainly, the server may further have a wired or wireless network interface, a keyboard, an input/output interface, and other components to facilitate input and output, and the server may further include other components for implementing functions of the device, which are not described herein again.

The embodiment of the present application further provides a computer-readable storage medium, where at least one piece of computer program is stored in the computer-readable storage medium, and the at least one piece of computer program is loaded and executed by a processor of a computer device to implement the operations performed by the computer device in the multimedia resource publishing method of the foregoing embodiment. For example, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In some embodiments, the computer program according to the embodiments of the present application may be deployed to be executed on one computer device or on multiple computer devices located at one site, or may be executed on multiple computer devices distributed at multiple sites and interconnected by a communication network, and the multiple computer devices distributed at the multiple sites and interconnected by the communication network may constitute a block chain system.

Embodiments of the present application also provide a computer program product or a computer program comprising computer program code stored in a computer readable storage medium. The processor of the computer device reads the computer program code from the computer-readable storage medium, and executes the computer program code, so that the computer device executes the method for publishing the multimedia resource provided in the above-mentioned various alternative implementations.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is intended only to illustrate the alternative embodiments of the present application, and should not be construed as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for publishing multimedia resources, the method comprising:

acquiring parameter values of a plurality of release parameters of a plurality of historical multimedia resources according to a target multimedia resource to be released, wherein the plurality of historical multimedia resources and the target multimedia resource have the same at least one resource attribute, and the release parameters are used for expressing parameters used when the multimedia resource is released;

displaying an optimized parameter value and a confidence coefficient of at least one target release parameter based on the difference between parameter values of a plurality of release parameters of the plurality of historical multimedia resources, wherein the confidence coefficient is used for representing the reliability degree of the corresponding target release parameter;

and responding to the release parameter selection operation, and releasing the target multimedia resource based on the optimized parameter value of the selected at least one target release parameter.

2. The method of claim 1, wherein displaying the optimized parameter value and the confidence level for the at least one target publication parameter based on the differences between the parameter values of the plurality of publication parameters of the plurality of historical multimedia assets comprises:

dividing the plurality of historical multimedia resources into a first resource set and a second resource set according to the parameter values of the target effect parameters of the plurality of historical multimedia resources, wherein the target effect parameters are used for expressing the effect after the multimedia resources are released;

for any publishing parameter, determining a difference coefficient of the publishing parameter based on the first resource set and the second resource set, wherein the difference coefficient is used for representing the difference between parameter values of the publishing parameter of different historical multimedia resources;

determining confidence levels of the plurality of release parameters based on the first resource set, the second resource set, and the difference coefficients of the plurality of release parameters;

determining and displaying an optimized parameter value and a confidence level of the at least one target release parameter based on the parameter values of the plurality of release parameters of the target multimedia resource and the difference coefficients of the plurality of release parameters.

3. The method of claim 2, wherein the dividing the plurality of historical multimedia assets into a first set of assets and a second set of assets according to parameter values of target effect parameters of the plurality of historical multimedia assets comprises:

sequencing the plurality of historical multimedia resources according to the parameter values of the target effect parameters of the plurality of historical multimedia resources;

dividing a first number of historical multimedia resources ranked at the top into the first resource set;

and dividing the sorted second quantity of the plurality of historical multimedia resources into the second resource set.

4. The method according to claim 2, wherein determining a difference coefficient of the publishing parameter based on the first resource set and the second resource set comprises:

obtaining at least one candidate parameter value of the release parameter;

for any candidate parameter value of the release parameter, obtaining an absolute difference value of the candidate parameter value, where the absolute difference value represents an absolute value of a difference value between a proportion of the candidate parameter value in the first resource set and a proportion of the candidate parameter value in the second resource set;

and determining the maximum value of the absolute difference values of the at least one candidate parameter value as the difference coefficient of the issuing parameter.

5. The method of claim 2, wherein determining the confidence level of the plurality of publishing parameters based on the first resource set, the second resource set and the difference coefficients of the plurality of publishing parameters comprises:

dividing the first resource set and the second resource set into a training set and a test set;

training to obtain a parameter optimization model based on the training set and the difference coefficients of the plurality of release parameters, wherein the parameter optimization model is used for determining the parameter values of the plurality of release parameters of the input multimedia resource;

and processing the test set through the parameter optimization model to determine the confidence degrees of the plurality of release parameters.

6. The method of claim 5, wherein training a parameter optimization model based on the difference coefficients of the training set and the plurality of release parameters comprises:

respectively determining a plurality of information gain coefficients of the plurality of release parameters to the training set;

for any release parameter, weighting the information gain coefficient of the release parameter based on the difference coefficient of the release parameter;

and training to obtain the parameter optimization model based on at least one parameter value of the intermediate release parameters, wherein the intermediate release parameters are the release parameters with the maximum weighted information gain coefficients.

7. The method of claim 6, wherein training the parameter optimization model based on at least one parameter value of the intermediate release parameter comprises:

dividing the training set into at least one non-empty training subset according to at least one parameter value of the intermediate release parameter;

and constructing a decision tree by adopting a recursive mode based on the at least one training subset to obtain the parameter optimization model.

8. The method of claim 5, wherein said processing the test set through the parameter optimization model to determine confidence levels for the plurality of release parameters comprises:

predicting the test set through the parameter optimization model to obtain prediction accuracy;

and respectively determining confidence degrees of the plurality of release parameters based on the difference coefficients of the plurality of release parameters and the prediction accuracy.

9. The method of claim 6, further comprising:

publication parameters having a difference coefficient less than a first difference threshold are removed from the plurality of publication parameters.

10. The method of claim 6, further comprising:

for any release parameter, removing the candidate parameter values of which the proportion in the training set is smaller than a proportion threshold value from at least one candidate parameter value of the release parameters.

11. The method of claim 2, wherein determining and displaying the optimized parameter value and confidence level of the at least one target distribution parameter based on the parameter values of the plurality of distribution parameters of the target multimedia asset and the difference coefficients of the plurality of distribution parameters comprises:

determining the at least one target release parameter based on parameter values of the plurality of release parameters of the target multimedia resource and difference coefficients of the plurality of release parameters, wherein the difference coefficient of the target release parameter is not less than a second difference threshold, and the parameter value of the target release parameter of the target multimedia resource is a first parameter value which is a parameter value of the target release parameter in the second resource set;

determining an optimized parameter value of the at least one target release parameter based on the first resource set;

and displaying the optimized parameter value and the confidence coefficient of the at least one target release parameter.

12. The method of claim 11, wherein determining the optimized parameter value for the at least one target publication parameter based on the first set of resources comprises:

and for any target release parameter, determining a second parameter value of the target release parameter in the first resource set as an optimized parameter value of the target release parameter.

13. The method of any one of claims 1-12, further comprising:

and responding to a verification period, and displaying verification information, wherein the verification period is a time period taking the target multimedia resource as a starting moment, and the verification information is used for representing the difference before and after the target multimedia resource is released by adopting an optimized parameter value of at least one target release parameter.

14. An apparatus for publishing multimedia assets, the apparatus comprising:

and the resource issuing module is used for responding to issuing parameter selection operation and issuing the target multimedia resource based on the optimized parameter value of the selected at least one target issuing parameter.

15. A computer device, characterized in that it comprises a processor and a memory for storing at least one piece of computer program, which is loaded by the processor and which executes the method of distribution of multimedia assets according to any one of claims 1 to 13.

16. A computer-readable storage medium for storing at least one computer program for executing the method for publishing a multimedia asset according to any of claims 1 to 13.

17. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the method of publishing a multimedia asset as claimed in any of claims 1 to 13.