CN113792912A

CN113792912A - Method and device for determining delivery strategy of media content, electronic equipment and medium

Info

Publication number: CN113792912A
Application number: CN202110966285.4A
Authority: CN
Inventors: 陈峭霖; 宋超; 刘兆丰; 张洁; 陈浩宇; 张宇琪
Original assignee: Shenzhen Tencent Network Information Technology Co Ltd
Current assignee: Shenzhen Tencent Network Information Technology Co Ltd
Priority date: 2021-08-23
Filing date: 2021-08-23
Publication date: 2021-12-14
Anticipated expiration: 2041-08-23
Also published as: CN113792912B

Abstract

The application discloses a method and a device for determining a delivery strategy of media content, electronic equipment and a medium. The method comprises the following steps: determining an associated business object having an association relation with the specified business object; acquiring release information corresponding to the associated business object; determining a predicted user amount corresponding to the specified business object based on the user amount in the release information and a preset correction coefficient; acquiring preset launching indexes corresponding to at least two preset channels respectively; and determining delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the predicted user quantity and the preset delivery indexes respectively corresponding to the at least two preset channels. The application provides a set of programmed media content delivery strategy determination scheme, and the method follows programmed delivery strategy determination guidance based on the scheme, avoids interference of individual perceptual judgment, and can provide timely and accurate media content delivery strategies.

Description

Method and device for determining delivery strategy of media content, electronic equipment and medium

Technical Field

The present application relates to the field of internet communication technologies, and in particular, to a method, an apparatus, an electronic device, and a medium for determining a delivery policy of media content.

Background

With the rapid development of internet communication technology, various internet products are emerging. In order to promote internet products, media content (such as video, audio, image, text) produced based on internet products (such as application programs) is often put in related channels to realize promotion and promotion effects.

In the related art, a worker often determines a media content delivery strategy in a related channel for promotion and promotion of internet products by experience, and the delivery strategy determination based on experience is easy to depend on personal perceptual judgment and lacks of programmed delivery strategy determination guidance. Therefore, problems of low efficiency, missing information and the like often occur due to excessive dependence on manual work, and therefore a timely and accurate media content delivery strategy cannot be provided.

Disclosure of Invention

In order to solve the problems that the prior art is applied to determining a media content delivery strategy aiming at a related channel, a timely and accurate media content delivery strategy cannot be provided, and the like, the application provides a method, a device, an electronic device and a medium for determining a media content delivery strategy, wherein the method comprises the following steps:

according to a first aspect of the present application, there is provided a method for determining a delivery policy of media content, the method comprising:

determining an associated business object having an association relation with the specified business object;

acquiring release information corresponding to the associated business object; the delivery information comprises the user quantity obtained by delivering the media content corresponding to the associated business object to a specified channel;

determining a predicted user amount corresponding to the specified business object based on the user amount and a preset correction coefficient;

acquiring preset launching indexes corresponding to at least two preset channels respectively; the preset delivery index is correlated with the user quantity obtained by channel delivery of the media content corresponding to the business object;

and determining delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the predicted user quantity and preset delivery indexes respectively corresponding to the at least two preset channels.

According to a second aspect of the present application, there is provided a device for determining a delivery policy of media content, the device comprising:

the associated business object determining module: the system comprises a business object association module, a business object association module and a business object association module, wherein the business object association module is used for determining an associated business object having an association relation with a specified business object;

a release information acquisition module: the system is used for acquiring the release information corresponding to the associated business object; the delivery information comprises the user quantity obtained by delivering the media content corresponding to the associated business object to a specified channel;

a predicted user amount determination module: the system is used for determining the predicted user quantity corresponding to the specified business object based on the user quantity and a preset correction coefficient;

presetting a release index acquisition module: the system comprises a data processing system and a data processing system, wherein the data processing system is used for acquiring preset launching indexes corresponding to at least two preset channels respectively; the preset delivery index is correlated with the user quantity obtained by channel delivery of the media content corresponding to the business object;

a release strategy information determining module: and the system is used for determining the delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the predicted user quantity and the preset delivery indexes respectively corresponding to the at least two preset channels.

According to a third aspect of the present application, an electronic device is provided, which includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for determining a delivery policy for media content according to the first aspect.

According to a fourth aspect of the present application, there is provided a computer-readable storage medium, in which at least one instruction or at least one program is stored, the at least one instruction or the at least one program being loaded and executed by a processor to implement the method for determining a delivery policy for media content according to the first aspect.

According to a fifth aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to execute the method for determining a delivery policy for media content according to the first aspect.

The method, the device, the electronic equipment and the medium for determining the media content delivery strategy have the following technical effects:

the method comprises the steps of determining an associated business object having an association relation with an appointed business object, then obtaining release information corresponding to the associated business object, and determining a predicted user quantity corresponding to the appointed business object based on a user quantity in the release information and a preset correction coefficient, so that release strategy information aiming at each preset channel is determined for media content corresponding to the appointed business object based on the predicted user quantity and preset release indexes respectively corresponding to at least two preset channels. The user quantity is obtained by putting the media content corresponding to the associated business object in a designated channel, and the preset putting index is related to the user quantity obtained by putting the media content corresponding to the business object in the channel. The application provides a set of programmed media content delivery strategy determination scheme, and the method follows programmed delivery strategy determination guidance based on the scheme, avoids interference of individual perceptual judgment, and can provide timely and accurate media content delivery strategies. The method comprises the steps of taking a related business object as a reference, predicting user quantity corresponding to a specified business object by using corresponding delivery information, and determining delivery strategy information aiming at each preset channel for the specified business object by combining preset delivery indexes of preset delivery channels, such as delivery budget, user quantity expected to be obtained and the like. For the newly on-line appointed service object, the releasing information of the associated service object can be used as an effective information source for determining the predicted user quantity, so that the accuracy of determining releasing strategy information by combining with the preset releasing index is improved.

Drawings

In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a schematic diagram of an application environment provided by an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for determining a delivery policy of media content according to an embodiment of the present application;

fig. 3 is a schematic flowchart of determining delivery policy information according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an advertisement budget allocation system according to an embodiment of the present application;

fig. 5 is a block diagram illustrating a device for determining a delivery policy of media content according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

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

It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of this application and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.

App (application): an application program.

Cpi (cost per insert): cost per installation.

ROI (return on innovation): return on investment.

Dau (real active users): users are active daily.

Buying quantity: through the advertisement putting means, the purchase of flow is used for promoting relevant product.

Referring to fig. 1, fig. 1 is a schematic diagram of an application environment according to an embodiment of the present disclosure, where the application environment may include a client 10 and a server 20. The server 20 may predict the user amount corresponding to the specified service object by using the corresponding delivery information of the associated service object as a reference, and then determine delivery policy information for each preset channel for the specified service object by combining with a preset delivery index of the preset delivery channel. After the media content corresponding to the specified business object is placed in a certain preset channel based on the corresponding placement strategy information, the user can access the media content through the client. It should be noted that fig. 1 is only an example.

The client 10 may be a smart phone, a desktop computer, a tablet computer, a notebook computer, an Augmented Reality (AR)/Virtual Reality (VR) device, a digital assistant, a smart speaker, a smart wearable device, or other types of physical devices; or it may be software running on a physical device, such as a computer program. The operating system corresponding to the client may include an Android system (Android system), an iOS system (a mobile operating system developed by apple inc.), a linux system (an operating system), a Microsoft Windows system (Microsoft Windows operating system), and the like.

The server 20 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like. Which may include a network communication unit, a processor, and memory, among others.

The specified business object and the associated business object can be APP products. The preset channel can be a platform capable of providing media content display service, and the preset channel can be a social platform, a trip platform, a live broadcast platform, a short video platform, an e-commerce platform, a digital reading platform, an original content platform, an application distribution platform and the like.

In practical applications, the designated service object and the associated service object may be game applications, and the game types provided by the game applications may be ACT, adventure, RPG (Role-playing game), narrative, strategy, FPS (First-person shooting), fighting, puzzlement, street game, science fiction, open world, survival, and the like.

A specific embodiment of a method for determining a delivery strategy of media content according to the present application is described below, and fig. 2 is a flowchart illustrating a method for determining a delivery strategy of media content according to an embodiment of the present application. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. In actual system or product execution, sequential execution or parallel execution (e.g., parallel processor or multi-threaded environment) may be possible according to the embodiments or methods shown in the figures. Specifically, as shown in fig. 2, the method may include:

s201: determining an associated business object having an association relation with the specified business object;

in the embodiment of the application, the server determines the associated business object having the association relation with the specified business object. The specified business object may be an internet product for which media content delivery policy determination is required, and the specified business object may be a newly online APP product, such as a newly online game application 1. The associated business object has a certain association relation with the specified business object, and the associated business object can be an internet product which is subjected to media content delivery. The association between the designated business object and the associated business object may be an association on a corporate background, an association on a target consumer, an association on product location, and the like.

In an exemplary embodiment, the determining the associated business object having an association relationship with the specified business object includes the following steps: firstly, determining the characteristic information of the specified business object; then, selecting at least two candidate business objects from a business object pool according to the characteristic information; then, determining the selected cause information corresponding to the candidate business object; and finally, determining an associated business object having an association relation with the specified business object from the at least two candidate business objects based on the selected cause information and the key information in the feature information.

The characteristic information of the designated business object may be from type information, tag information, etc. of the designated business object. For example, when the business object is designated as a newly Online Game application 1, the feature information may indicate MMO (massive Multiplayer Online Game) as a Game type, RPG, ancient style as a Game portrait label, IP adaptation, and risk award indicating Game play (how a player and a Game interact). And selecting candidate business objects matched with the characteristic information from the business object pool. Considering that the delivery information of the associated business object needs to be used as a reference, the business object in the business object pool needs to be delivered with the media content, or the candidate business object needs to satisfy not only the requirement matching with the above-mentioned characteristic information but also the media content delivery.

The candidate business objects are selected from the business object pool based on the matching degree with the feature information, for example, the matching degree of the candidate business objects with the feature information is higher than a threshold value, and the matching degree of the candidate business objects with the feature information is in a preset number of matching degree sequences (obtained by sorting the matching degree of all the business objects in the business object pool with the feature information according to the descending order of the matching degree). Since the contribution of the matching degree is derived from each sub-feature information in the feature information, the matching degree is taken as an overall measure and cannot directly provide the contribution of each sub-feature information to the matching degree. That is, there may exist a candidate business object that does not match sub-feature information that is key information among the above-described feature information. For example, the game application 2 as the candidate business object has the following features: MMO type, antique tags, decryption play. The selected cause information corresponding to the game application 2 is MMO and ancient wind. And the sub-characteristic information as the key information in the characteristic information is a risk reward. The game application 2 may be excluded and the associated business object determined from the other candidate business objects.

And screening candidate business objects from the business object pool through the characteristic information of the specified business object, combining the key information in the characteristic information with the selected factor information corresponding to the candidate business objects, and continuously screening the associated business objects from the candidate business objects. By means of two-stage screening, the overall matching with the characteristic information and the local matching with the key information are considered, the incidence relation between the associated business object and the specified business object is guaranteed, the key information is not omitted and the key information is relied on for establishing the incidence relation, and therefore the associated business object can be used as effective reference to improve the accuracy of the follow-up determined putting strategy.

In practical application, referring to fig. 4, in a data preparation stage, a worker may input relevant feature information of a specified business object by using a "new online APP information input module", and an auction APP as an associated business object may be determined by using the information.

S202: acquiring release information corresponding to the associated business object; the delivery information comprises the user quantity obtained by delivering the media content corresponding to the associated business object to a specified channel;

in the embodiment of the application, the server side obtains the release information corresponding to the associated business object. The delivery information is used for describing the content of delivering the media content corresponding to the associated business object in the specified channel. The placement information may include information indicative of a specified channel, information indicative of media content, an amount of users obtained via placement, a placement budget, and the like. The information indicating the specified channel may be a name, an identification, etc. of the specified channel, and may further include definition information for the specified channel, such as limitation information of a regional dimension, limitation information of an operating system dimension. The specified channel may be a platform capable of providing a media content presentation service. The information indicative of the media content may be a type of the media content (e.g., video, audio, image, text), a cost of production, and the like. The number of users obtained by the delivery, that is, the number of users who perform operations such as access, download, installation, etc. on the associated service object based on a specified channel after the media content is delivered. When there are at least two designated channels, the user amount obtained through the delivery may include the user amount obtained through the delivery and the total user amount obtained through the delivery corresponding to each designated channel.

In practical applications, media content may be viewed as an advertisement. Referring to fig. 4, in the data preparation phase, data information inside and outside the auction product APP may be automatically acquired by the "auction product data collection module" as the release information. The competitive product data collection module can realize automatic acquisition of data information by utilizing a built data collection platform. The information source of the competitive product data collection module can be a database constructed by collecting data based on natural language processing technology. In addition, a candidate competitive product pool is constructed together by combining the related competitive product information input manually.

S203: determining a predicted user amount corresponding to the specified business object based on the user amount and a preset correction coefficient;

in the embodiment of the application, the server determines the predicted user quantity corresponding to the specified business object based on the user quantity and the preset correction coefficient. And correcting the user quantity indicating the associated service object by using a preset correction coefficient so as to obtain a predicted user quantity corresponding to the specified service object. It will be appreciated that the potential user amount for a given business object is determined using a known user amount indicative of the associated business object. In conjunction with the related description in step S202, the user amount may be the number of users who perform operations such as accessing, downloading, and installing on the associated business object based on a specified channel after the media content is delivered. It should be noted that, when there are at least two designated channels, the user amount here is the total user amount, that is, the result of adding the user amounts obtained by delivering corresponding to the respective designated channels is obtained.

In an exemplary embodiment, the preset correction parameter may be determined by: firstly, acquiring first-class data and second-class data aiming at the same preset parameter; the first type of data and the second type of data respectively indicate a real value and an estimated value corresponding to the same sample service object; then, a correction model is constructed based on the first class data and the second class data to determine the preset correction parameters.

The sample business object can be an APP product, the first type of data indicates the actual value of the APP product for the preset parameters, and the second type of data indicates the estimated value of the APP product for the preset parameters. Illustratively, the first type of data indicates a real amount of users, a real profit, and a real daily life for a game application, and correspondingly, the second type of data indicates an estimated amount of users, an estimated profit, and an estimated daily life for the same game application. It will be appreciated that the first type of data is internal data, the authenticity and accuracy of which is better guaranteed, however, the amount of data is typically less. The second type of data is external data, the authenticity and accuracy of which cannot be guaranteed, lacked or even verified, however, the data volume of the data is large. And improving the data volume of the first class data by using the correction model based on the second class data with a large data volume as a reference.

The first type of data and the second type of data involved in the correction model need to indicate the same business object, the same parameter. When the preset correction parameters are determined, the first type data y and the second type data x are known, and the constructed correction model can be a linear correction model: y is a + bx + cx, where a, b, and c are preset correction parameters, which can be obtained from known sets of x and y. Of course, as the known first type data and second type data are updated (e.g., new, modified), the preset correction parameters are also updated.

When the preset correction parameters are used, the first type data y are unknown, the second type data x are known, and then the first type data are obtained based on the current preset correction parameters and the known second type data. When the predicted user amount corresponding to the specified business object is determined, the user amount corresponding to the associated business object can be regarded as the second type of data. Of course, the preset correction parameter may be used as a correction parameter for a time dimension (for making up a difference between the designated service object and the associated service object for delivering the media content at the historical time) or a correction parameter for an associated difference dimension (even if the designated service object and the associated service object have an association relationship, but after all, the designated service object and the associated service object are used by two different service objects), and when the predicted user amount corresponding to the designated service object is determined, the user amount corresponding to the associated service object may be the first type of data or the second type of data.

In practical applications, referring to fig. 4, in the calculation stage (which is the process of data processing, analysis and calculation), the internal and external data information collected in the previous stage may be processed to reduce systematic errors, and the external data may be corrected. The target crowd quantity module can predict the target crowd quantity of different channels. The 'correction model training unit' in the module can obtain the correction coefficient (namely the preset correction parameter) of the external data through a mathematical automatic comparison and modeling mode on the basis of the internal data information, so as to correct. The specific method is that the correction parameters between different games are assumed to be the same, and then aiming at the internal game application, the data of an internal data source is taken as a training target of model output, and the data of an external data source is taken as model input, and a linear model is trained. So as to correct the competitive game data which is not known internally but can be obtained from an external data source. A potential user quantity estimation unit in the module can automatically correct according to relevant data of corresponding competitive product APP from the outside through the correction coefficient, and finally potential user quantity estimation values of new APPs in different channels can be obtained. In addition, the auction APP may also be determined by an "auction selection unit" in the module, and it is understood that the module in the previous stage is configured to perform the steps of "determining the feature information of the specified business object" and "extracting at least two candidate business objects from the business object pool according to the feature information," and the "auction selection unit" manually selects the auction APP with the most suitable tuning training from the auction candidate APP pool already collected in the previous stage.

S204: acquiring preset launching indexes corresponding to at least two preset channels respectively; the preset delivery index is correlated with the user quantity obtained by channel delivery of the media content corresponding to the business object;

in the embodiment of the application, the server acquires the preset launching indexes corresponding to at least two preset channels respectively, that is, the value of the preset launching index corresponding to each preset channel is known. The preset channel is a platform capable of providing media content display service, and can be a social platform, a trip platform, a live broadcast platform, a short video platform, an e-commerce platform, a digital reading platform, an original content platform, an application distribution platform and the like. The budget channel may be based on the limitation information of the regional dimension and the limitation information of the operating system dimension, specifically, a channel indicated by a country a-iOS-social platform and a channel indicated by a country J-Android-application distribution platform. The at least two preset channels may be selected by a target object (such as a worker) according to business requirements, and after the subsequent release policy information is determined, the composition of the at least two preset channels may also be adjusted.

The preset delivery index has correlation with the user quantity obtained by channel delivery of the media content corresponding to the business object. For example, the preset delivery index may be a cost per installation CPI, which is a cost per bought volume/a number of users per bought volume, where the cost per bought volume may be regarded as a cost per bought volume for delivering media content to a service object through a channel, and the number of users per bought volume may be regarded as a user volume obtained through delivery. For example, the at least two predetermined channels are channel 2 and channel 3, where the CPI for the known channel 2 is 2-tuple and the CPI for the known channel 3 is 5-tuple. The predetermined delivery indicator may also be the return on investment ROI ═ bought volume profit/bought volume cost, wherein the bought volume profit may be considered as the profit obtained by the delivery. Since the purchase cost is equal to the number of purchased users CPI, then ROI is equal to the purchase yield/number of purchased users CPI.

It should be noted that the specified channel related to the associated business object in step S202 may overlap, intersect or have no relationship with at least two preset channels, for example, the specified channel is channel 1, and the at least two preset channels are channel 2 and channel 3. In addition, the preset delivery index can be corrected by internal data with relatively good guarantee on the authenticity and accuracy of the relevant data.

In practical application, referring to fig. 4, in the calculation stage, the platform channel information collection module may be used to collect and calculate data information of a preset channel (which may be combined with limitation information of regional dimensions and limitation information of operating system dimensions) to provide channel information for subsequent budget allocation. For user purchase, the APP product business is required, and based on the performance for APP distribution, an estimate of the total APP download (installation) is evaluated and given. The purchase quantity ratio of the preset channel (i.e. purchase quantity user/(purchase quantity user + natural user)) needs to be determined. The following three sources of information may be considered together: the rate of purchase is determined by knowledge and understanding of the relevant business, experience summarized from historical data, and expert advice. Therefore, the total download (installation) quantity is multiplied by the purchase quantity ratio, namely the predicted user purchase quantity corresponding to different preset channels. For the CPI and ROI of different preset channels, the following three information sources can also be considered together: knowledge and understanding of the relevant business is determined by the experience summarized by the historical data and expert advice.

S205: and determining delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the predicted user quantity and preset delivery indexes respectively corresponding to the at least two preset channels.

In the embodiment of the application, the service end determines delivery strategy information for each preset channel for media content corresponding to a specified business object based on the predicted user quantity and preset delivery indexes corresponding to at least two preset channels respectively. On the basis of the known predicted user quantity and the preset delivery indexes of the preset channels, the predicted user quantity can be used as a target, and the expected user quantity (the user quantity expected to be obtained from the expected channel by delivery) or the delivery budget corresponding to each preset channel is determined. The delivery strategy can be determined according to past experience, for example, by referring to the delivery experience of (internal) APP products that have delivered media content, the specific delivery budget proportion can be performed by referring to the delivery proportion of channels in the same country.

In an exemplary embodiment, as shown in FIG. 3: the determining, for the media content corresponding to the specified service object, delivery policy information for each preset channel based on the predicted user amount and preset delivery indexes corresponding to the at least two preset channels, respectively, includes:

s301: determining a user quantity parameter corresponding to each preset channel; the user quantity parameter indicates the user quantity obtained by putting the media content corresponding to the specified business object in the preset channel;

s302: determining a user quantity lower limit according to the predicted user quantity; the user quantity lower limit is used for describing a lower limit of the sum of values of user quantity parameters corresponding to the at least two preset channels respectively;

s303: constructing a target function based on the user quantity parameter corresponding to each preset channel and the preset delivery index corresponding to each preset channel;

s304: processing the objective function based on a first type of preset rule and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel; the first type of preset rule is used for describing a target for the value of the target function;

s305: and determining delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the value of the user quantity parameter corresponding to each preset channel.

And the user quantity parameter corresponding to each preset channel is used as an object to be solved by the objective function. The user quantity parameter corresponding to the preset channel indicates the quantity of the users expected to be obtained (the quantity of the users expected to be obtained from the expected channel through delivery) corresponding to the preset channel. For example, the at least two expected channels are channels a-c, the user quantity parameter corresponding to channel a is Ua, the user quantity parameter corresponding to channel b is Ub, and the user quantity parameter corresponding to channel c is Uc. The predicted user volume determined above is used as a target for describing a lower limit of the sum of the value of Ua, the value of Ub, and the value of Uc, that is, the user volume obtained by delivering media content corresponding to a specified service object in a channel a-c needs to be not less than the predicted user volume.

A preset delivery index a corresponding to the channel a, a preset delivery index b corresponding to the channel b, and a preset delivery index c corresponding to the channel c are known, and a target function can be constructed by combining the preset delivery index and the correlation between the user quantity obtained by channel delivery for the media content corresponding to the service object, for example, based on an expression (CPI is purchase quantity cost/purchase quantity user quantity, and ROI is purchase quantity profit/CPI purchase quantity user quantity) of the preset delivery index. And then, processing the objective function based on the first type of preset rule and the user quantity lower limit to obtain the value of Ua, the value of Ub and the value of Uc. The first type of preset rule is used for describing a target for the value of the target function. For example, for an objective function constructed based on an expression of a preset delivery index, the first type of preset rule may be a value limit for the preset delivery index. It can be understood that, different from the value of the preset delivery index corresponding to the known preset channel, the value of the preset delivery index indicated by the objective function is not limited to the delivery evaluation for the preset channel, but is an evaluation for the delivery of the channel related to the specified business object that has not yet been performed. Based on the limited optimization idea of quadratic programming, the scipy package (an open source math, science and engineering calculation package) provided by python (a computer programming language) is used for completing the operation so as to obtain the value of the user quantity parameter corresponding to each preset channel.

The user quantity parameter corresponding to the preset channel can be directly used as the delivery strategy information of the media content corresponding to the appointed service object related to the preset channel, that is, the user quantity expected to be obtained from the channel a by delivery is the value of Ua, the user quantity expected to be obtained from the channel b by delivery is the value of Ub, and the user quantity expected to be obtained from the channel c by delivery is the value of Uc. The user volume parameter corresponding to the preset channel may also be multiplied by the CPI serving as the preset delivery index to obtain delivery policy information related to the media content corresponding to the specified service object for the preset channel, that is, the value of the delivery budget of the channel a is Ua cpia (CPI of the channel a), the value of the delivery budget of the channel b is Ub cpib (CPI of the channel b), and the value of the delivery budget of the channel c is Uc cpic (CPI of the channel c).

And constructing an objective function based on the user quantity parameters corresponding to the preset channel and the preset delivery index, and processing the objective function based on the value target of the set objective function and the user quantity lower limit, so as to obtain the value of the user quantity parameters corresponding to the preset channel and determine the delivery strategy information aiming at the preset channel for the media content corresponding to the specified business object. A set of programmed execution steps is provided for determining the releasing strategy information, the value of the objective function can be limited, the value of the user quantity parameter can be limited, and the value of the user quantity parameter obtained based on the constraint conditions and the determined releasing strategy information are more adaptive to the channel releasing of the media content corresponding to the current specified business object.

Further, when the value of the user quantity parameter corresponding to the preset channel is obtained by processing the objective function, a second type of preset rule can be introduced: acquiring a second type of preset rule; the second type of preset rule is used for describing a limiting condition for the value of the user quantity parameter corresponding to the preset channel; and then, processing the objective function based on the first type of preset rules, the second type of preset rules and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel. The second type of preset rule may be used to limit the value of Ua, the value of Ub, and the value of Uc, for example, to limit the upper limit of the value of Ua and to limit the lower limit of the value of Uc. The second type of preset rules can be regarded as optional limiting conditions, and after the second type of preset rules are introduced, the target function is processed by using a scipy packet provided by python on the basis of an optimization idea of limited quadratic programming. And the introduction of the second type of preset rules enables the subsequent determined delivery strategy information to be more in accordance with the channel dimension and finer granularity requirements.

The content of constructing the objective function based on the CPI expression and the content of constructing the objective function based on the ROI expression will be described below.

1) Constructing related contents of the target function based on the CPI expression:

when the preset delivery index is the installation cost at each time, based on the user quantity parameter corresponding to each preset channel and the preset delivery index corresponding to each preset channel, constructing an objective function, including: multiplying the user quantity parameter corresponding to each preset channel by a preset release index to obtain a first parameter; adding the first parameters respectively corresponding to the at least two preset channels to obtain a second parameter; adding the user quantity parameters respectively corresponding to the at least two preset channels to obtain a third parameter; constructing the objective function based on the second parameter and the third parameter.

The channels a-c above are used as relevant parameters to which the preset channels relate. The first parameter (x ═ Ux ═ a, b, and c), the second parameter (Ua ═ cpia + Ub ═ cpib + Uc ═ cpic), and the third parameter (Ua + Ub + Uc). The objective function constructed based on the second parameter and the third parameter is: (Ua + cpia + Ub cpib + Uc + cpic)/(Ua + Ub + Uc). The third parameter indicates a total amount of users expected to be obtained for channel impressions (not yet made) relating to the specified business object, and the second parameter indicates a total budget for channel impressions (not yet made) relating to the specified business object.

Correspondingly, the processing the objective function based on the first type of preset rule and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel includes: obtaining a target for minimizing the value of the target function according to the first type of preset rules; and processing the objective function based on the objective of minimizing the value of the objective function and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel.

The first class of preset rules indicates the goal of minimizing the value of the objective function, i.e. min [ (Ua + Ub + cpib + Uc + cpic)/(Ua + Ub + Uc) ]. And meanwhile, the user quantity is predicted by combining Ua + Ub + Uc, so that the value of Ua, the value of Ub and the value of Uc are obtained. Of course, the second type of preset rule can also be introduced here. The value of the user quantity parameter obtained by the method can enable the channel release related to the specified business object which is not performed to meet the aim of minimizing CPI at a large probability, so that the obtained release strategy information guides promotion and promotion which are more effective for the specified business object, ensures that the related media content brings effective user installation and downloading, and realizes accurate positioning of the user which can contribute to installation and downloading.

2) Constructing related contents of the target function based on the CPI expression:

when the preset delivery index is the return on investment, constructing an objective function based on the user quantity parameter corresponding to each preset channel and the preset delivery index corresponding to each preset channel, including: multiplying the user quantity parameter corresponding to each preset channel by a preset release index to obtain a fourth parameter; adding fourth parameters corresponding to the at least two preset channels respectively to obtain a fifth parameter; adding the user quantity parameters respectively corresponding to the at least two preset channels to obtain a sixth parameter; constructing the objective function based on the fifth parameter and the sixth parameter;

the channels a-c above are used as relevant parameters to which the preset channels relate. The fourth parameter is Ux roix (x is a, b and c, where roia corresponds to ROI of channel a, roib corresponds to ROI of channel b, roic corresponds to ROI of channel c), the fifth parameter is Ua is roib + Uc, and the sixth parameter is Ua + Ub + Uc. The objective function constructed based on the fifth parameter and the sixth parameter is: (Ua + Ub + Uc + roic)/(Ua + Ub + Uc). The sixth parameter indicates the total amount of users expected to be delivered for the channel (not yet in progress) involving the specified business object, and the sixth parameter CPI indicates the total budget for the channel delivery (not yet in progress) involving the specified business object. The fifth parameter CPI indicates the revenue for the channel impression (not yet done) related to the specified business object.

Correspondingly, the processing the objective function based on the first type of preset rule and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel includes: obtaining a target for maximizing the value of the objective function according to the first type of preset rules; and processing the objective function based on the objective of maximizing the value of the objective function and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel.

The first type of preset rule indicates the objective of maximizing the value of the objective function, namely max [ (Ua + Ub + Uc + roic)/(Ua + Ub + Uc) ]. And meanwhile, the user quantity is predicted by combining Ua + Ub + Uc, so that the value of Ua, the value of Ub and the value of Uc are obtained. Of course, the second type of preset rule can also be introduced here. The value of the user quantity parameter obtained by the method can enable the channel delivery related to the specified business object which is not performed to meet the aim of maximizing the ROI in a large probability, so that the obtained delivery strategy information guides the related media content to bring more performance profits and ensures that the delivered budget plays a corresponding role.

In practical application, referring to fig. 4, three advertisement budget allocation modes can be implemented by using a budget allocation model optimization module in the calculation stage: 1) minimizing the CPI, wherein the mode takes the minimized CPI as a target, and minimizes the comprehensive CPI put at this time through intelligent optimization of mathematical modeling under the condition of meeting the putting target; 2) and the maximum ROI is adopted in the mode, the maximum ROI is taken as a target, and the comprehensive ROI put in the time is maximized through intelligent optimization of mathematical modeling under the condition of meeting the putting target. The advertisement budget allocation and the purchase amount ratio of each channel can be finally output by using the output module in the output and evaluation stage. In addition, the evaluation optimization iteration module evaluates and tracks the putting effect, summarizes and feeds back related experience, and guides subsequent manual parameter input adjustment.

The advertisement budget allocation system shown in fig. 4 is a set of data-driven programmed, automated, and intelligent computer program systems, and is based on a method flow of generating an advertisement budget allocation scheme. The input of the method is basic information of a certain newly online APP product, the output of the method is a set of advertisement budget allocation scheme of the newly online APP product aiming at each target channel, and after the scheme is obtained, the manual parameters are iteratively optimized according to the actual delivery result. The system can calculate budget allocation of initial advertisement putting of a newly online APP product in a programmed mode, so that labor cost of a business party can be saved (the whole calculation process can be completed within 5 minutes), data from a plurality of data sources can be utilized systematically, and different advertisement budget allocation modes are provided by combining past advertisement putting experiences and mathematical modeling optimization algorithms. Table 1 below illustrates the effect of using the present system to allocate budgets for an application product. From this table, it can be seen that minimizing CPI and maximizing ROI both allow ad placement to produce minimized CPI and maximized ROI to achieve the target effect.

TABLE 1

The advertisement budget allocation program integrates a plurality of functional modules such as data collection, processing, analysis and output, and can allocate the advertisement budget of the new online APP product in a highly automatic programmed manner, namely, the initial advertisement budget of the new online APP product in a target country, a target platform and a target channel is calculated, and advertisement delivery is guided. The advertisement budget allocation system has the following advantages: 1) and programmatically acquiring the data of each information source. The advertisement budget allocation system integrates the data collection module, and can complete programmed extraction of data of each information source, so that the comprehensiveness of the data is ensured, and omission is avoided; 2) transitioning from artificial dependence to data dependence. The advertising budget allocation system leverages data from various sources, including external data, internal data, and expert advice. Information of different data sources is mined and analyzed in a programmed, automatic and intelligent manner, and the defect of dependence on a single information source is overcome. Meanwhile, the budget allocation result decision is judged by depending on manual analysis, and the successful transformation is an intelligent decision which mainly adopts data driving and combines expert knowledge; 3) and (4) utilizing mathematical modeling to achieve global optimization of budget allocation. When reasonable budget allocation is calculated, the data-driven programmed advertisement budget allocation system establishes a mathematical model to disassemble and quantitatively express the problem and optimize the problem, so that the advertisement budgets of different target countries, platforms and channels are calculated by comprehensively considering various information and factors, and finally the optimization of global delivery is realized through a program algorithm.

According to the technical scheme provided by the embodiment of the application, the associated business object having an association relation with the specified business object is determined, then the launching information corresponding to the associated business object is obtained, the predicted user quantity corresponding to the specified business object is determined based on the user quantity in the launching information and the preset correction coefficient, and therefore the launching strategy information aiming at each preset channel is determined for the media content corresponding to the specified business object based on the predicted user quantity and the preset launching indexes respectively corresponding to at least two preset channels. The user quantity is obtained by putting the media content corresponding to the associated business object in a designated channel, and the preset putting index is related to the user quantity obtained by putting the media content corresponding to the business object in the channel. The application provides a set of programmed media content delivery strategy determination scheme, and the method follows programmed delivery strategy determination guidance based on the scheme, avoids interference of individual perceptual judgment, and can provide timely and accurate media content delivery strategies. The method comprises the steps of taking a related business object as a reference, predicting user quantity corresponding to a specified business object by using corresponding delivery information, and determining delivery strategy information aiming at each preset channel for the specified business object by combining preset delivery indexes of preset delivery channels, such as delivery budget, user quantity expected to be obtained and the like. For the newly on-line appointed service object, the releasing information of the associated service object can be used as an effective information source for determining the predicted user quantity, so that the accuracy of determining releasing strategy information by combining with the preset releasing index is improved.

An embodiment of the present application further provides a device for determining a delivery policy of media content, as shown in fig. 5, the device 500 for determining a delivery policy of media content includes:

the associated business object determination module 501: the system comprises a business object association module, a business object association module and a business object association module, wherein the business object association module is used for determining an associated business object having an association relation with a specified business object;

launch information acquisition module 502: the system is used for acquiring the release information corresponding to the associated business object; the delivery information comprises the user quantity obtained by delivering the media content corresponding to the associated business object to a specified channel;

predicted user amount determination module 503: the system is used for determining the predicted user quantity corresponding to the specified business object based on the user quantity and a preset correction coefficient;

preset release index obtaining module 504: the system comprises a data processing system and a data processing system, wherein the data processing system is used for acquiring preset launching indexes corresponding to at least two preset channels respectively; the preset delivery index is correlated with the user quantity obtained by channel delivery of the media content corresponding to the business object;

the release policy information determination module 505: and the system is used for determining the delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the predicted user quantity and the preset delivery indexes respectively corresponding to the at least two preset channels.

It should be noted that the device and method embodiments in the device embodiment are based on the same inventive concept.

The embodiment of the present application provides an electronic device, which includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for determining a delivery policy of media content provided in the above method embodiment.

Further, fig. 6 is a schematic hardware structure diagram of an electronic device for implementing the method for determining a delivery policy of media content according to the embodiment of the present application, where the electronic device may participate in a device for determining a delivery policy of media content according to the embodiment of the present application. As shown in fig. 6, the electronic device 60 may include one or more (shown as 602a, 602b, … …, 602 n) processors 602 (the processors 602 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 604 for storing data, and a transmission device 606 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 6 is only an illustration and is not intended to limit the structure of the electronic device. For example, electronic device 60 may also include more or fewer components than shown in FIG. 6, or have a different configuration than shown in FIG. 6.

It should be noted that the one or more processors 602 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Further, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the electronic device 60 (or mobile device). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).

The memory 604 may be used to store software programs and modules of application software, such as program instructions/data storage devices corresponding to the method for determining a delivery policy of media content described in the embodiment of the present application, and the processor 602 executes various functional applications and data processing by running the software programs and modules stored in the memory 64, so as to implement one of the methods for determining a delivery policy of media content described above. The memory 604 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 604 may further include memory located remotely from processor 602, which may be connected to electronic device 60 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission means 606 is used for receiving or sending data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the electronic device 60. In one example, the transmission device 606 includes a network adapter (NIC) that can be connected to other network devices through a base station so as to communicate with the internet. In one embodiment, the transmission device 606 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the electronic device 60 (or mobile device).

Embodiments of the present application further provide a computer-readable storage medium, which may be disposed in an electronic device to store at least one instruction or at least one program for implementing a method for determining a delivery policy for media content in the method embodiments, where the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for determining a delivery policy for media content provided in the method embodiments.

Alternatively, in this embodiment, the storage medium may be located in at least one network server of a plurality of network servers of a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and electronic apparatus embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.

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 only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement 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 determining a delivery strategy of media content, the method comprising:

2. The method according to claim 1, wherein the determining, for the media content corresponding to the specified business object, delivery policy information for each of the preset channels based on the predicted user amount and preset delivery indexes corresponding to the at least two preset channels, respectively, comprises:

determining a user quantity parameter corresponding to each preset channel; the user quantity parameter indicates the user quantity obtained by putting the media content corresponding to the specified business object in the preset channel;

determining a user quantity lower limit according to the predicted user quantity; the user quantity lower limit is used for describing a lower limit of the sum of values of user quantity parameters corresponding to the at least two preset channels respectively;

constructing a target function based on the user quantity parameter corresponding to each preset channel and the preset delivery index corresponding to each preset channel;

processing the objective function based on a first type of preset rule and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel; the first type of preset rule is used for describing a target for the value of the target function;

and determining delivery strategy information aiming at each preset channel for the media content corresponding to the specified business object based on the value of the user quantity parameter corresponding to each preset channel.

3. The method according to claim 2, wherein the processing the objective function based on the first type of preset rule and the user quantity lower limit to obtain a value of the user quantity parameter corresponding to each preset channel comprises:

acquiring a second type of preset rule; the second type of preset rule is used for describing a limiting condition for the value of the user quantity parameter corresponding to the preset channel;

and processing the objective function based on the first type of preset rules, the second type of preset rules and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel.

4. A method according to any of claims 2 or 3, characterized in that:

when the preset delivery index is the installation cost at each time, based on the user quantity parameter corresponding to each preset channel and the preset delivery index corresponding to each preset channel, constructing an objective function, including:

multiplying the user quantity parameter corresponding to each preset channel by a preset release index to obtain a first parameter;

adding the first parameters respectively corresponding to the at least two preset channels to obtain a second parameter;

adding the user quantity parameters respectively corresponding to the at least two preset channels to obtain a third parameter;

constructing the objective function based on the second parameter and the third parameter;

the processing the objective function based on the first type of preset rule and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel comprises the following steps:

obtaining a target for minimizing the value of the target function according to the first type of preset rules;

and processing the objective function based on the objective of minimizing the value of the objective function and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel.

5. A method according to any of claims 2 or 3, characterized in that:

when the preset delivery index is the return on investment, constructing an objective function based on the user quantity parameter corresponding to each preset channel and the preset delivery index corresponding to each preset channel, including:

multiplying the user quantity parameter corresponding to each preset channel by a preset release index to obtain a fourth parameter;

adding fourth parameters corresponding to the at least two preset channels respectively to obtain a fifth parameter;

adding the user quantity parameters respectively corresponding to the at least two preset channels to obtain a sixth parameter;

constructing the objective function based on the fifth parameter and the sixth parameter;

obtaining a target for maximizing the value of the objective function according to the first type of preset rules;

and processing the objective function based on the objective of maximizing the value of the objective function and the user quantity lower limit to obtain the value of the user quantity parameter corresponding to each preset channel.

6. The method of claim 1, wherein determining the associated business object having an association relationship with the specified business object comprises:

determining characteristic information of the specified business object;

selecting at least two candidate business objects from a business object pool according to the characteristic information;

determining selected cause information corresponding to the candidate business object;

and determining an associated business object having an association relation with the specified business object from the at least two candidate business objects based on the selected factor information and the key information in the feature information.

7. The method of claim 1, further comprising:

acquiring first-class data and second-class data aiming at the same preset parameter; the first type of data and the second type of data respectively indicate a real value and an estimated value corresponding to the same sample service object;

and constructing a correction model based on the first class data and the second class data to determine the preset correction parameters.

8. An apparatus for determining a delivery policy of media content, the apparatus comprising:

9. An electronic device comprising a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method for determining a delivery policy for media content according to any one of claims 1-7.

10. A computer-readable storage medium having stored therein at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by a processor to implement the method for determining a delivery policy for media content according to any one of claims 1-7.