CN113743995B

CN113743995B - Multi-channel advertisement putting method, device, equipment and storage medium

Info

Publication number: CN113743995B
Application number: CN202111055861.6A
Authority: CN
Inventors: 杨祎
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2021-09-09
Filing date: 2021-09-09
Publication date: 2023-07-25
Anticipated expiration: 2041-09-09
Also published as: CN113743995A

Abstract

The invention relates to the field of artificial intelligence and intelligent medical treatment, and discloses a multi-channel advertisement putting method, device, equipment and storage medium, which are used for improving advertisement putting efficiency. The multi-channel advertisement delivery method comprises the following steps: acquiring the delivery effect data and the original delivery strategy of the advertising platforms of the multiple channels; establishing an initial delivery effect funnel model of each channel advertisement delivery platform; comparing the initial delivery effect funnel models of the advertising platforms of the channels to obtain an optimal delivery effect funnel model and an event to be optimized; adjusting the throwing crowd strategy, the bidding strategy and the material selection strategy in the original throwing strategy to obtain a target throwing strategy; and carrying out data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform. In addition, the invention also relates to a blockchain technology, and the release strategy package can be stored in a blockchain node.

Description

Multi-channel advertisement putting method, device, equipment and storage medium

Technical Field

The invention relates to the field of artificial intelligence and intelligent medical treatment, in particular to a multi-channel advertisement putting method, device, equipment and storage medium.

Background

Along with the development of internet advertisements, advertisement suppliers provide own advertisement delivery platforms, thereby bringing convenience to advertisers and enabling advertisement delivery to be more intelligent and automatic.

However, for advertisers, the complicated advertisement delivery platforms increase difficulty for own advertisement delivery demands, and due to the data barriers between different advertisement delivery platforms, when advertisements are delivered by different advertisement delivery platforms, the advertisement delivery effect data sharing, the advertisement delivery strategy sharing and the cross-site delivery cannot be performed, so that the advertisement delivery data of a plurality of advertisement delivery platforms are difficult to integrate, and the advertisement delivery efficiency is low.

Disclosure of Invention

The invention provides a multi-channel advertisement putting method, device, equipment and storage medium, which are used for improving advertisement putting efficiency.

The first aspect of the invention provides a multi-channel advertisement delivery method, which comprises the following steps:

acquiring the delivery effect data and the original delivery strategies of the advertising delivery platforms of a plurality of channels through a timing task, wherein the original delivery strategies comprise a delivery crowd strategy, a bidding strategy and a material selection strategy;

Based on the delivery effect data of each channel advertisement delivery platform, establishing an initial delivery effect funnel model corresponding to each channel advertisement delivery platform to obtain a plurality of initial delivery effect funnel models, wherein each initial delivery effect funnel model comprises level information and conversion rate corresponding to a plurality of level advertisement operation behavior events;

screening the multiple initial delivery effect funnel models based on the multiple level advertisement operation behavior events to obtain target delivery effect funnel models, screening the multiple level advertisement operation behavior events of each initial delivery effect funnel model according to conversion rates respectively corresponding to the multiple level advertisement operation behavior events of each initial delivery effect funnel model to obtain target operation behavior events, wherein the target delivery effect funnel models are used for indicating optimal delivery effect funnel models corresponding to the multiple level advertisement operation behavior events in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior events are used for indicating events to be optimized corresponding to the initial delivery effect funnel models;

according to the target delivery effect funnel model and the target operation behavior event, a delivery crowd strategy, a bidding strategy and a material selection strategy in the original delivery strategy of each channel advertisement delivery platform are adjusted, and a target delivery strategy corresponding to each channel advertisement delivery platform is obtained;

According to the delivery strategy data format of each channel advertisement delivery platform, carrying out data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform carries out advertisement delivery according to the target advertisement delivery strategy.

Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining, by a timing task, impression data of a plurality of channel advertisement delivery platforms and an original delivery policy, where the original delivery policy includes a delivery crowd policy, a bid policy, and a material selection policy includes:

when detecting an execution signal of a timing task, acquiring login account information and token information of a plurality of channel advertisement delivery platforms, wherein the login account information is account information with advertisement data acquisition permission of the corresponding channel advertisement delivery platforms;

based on the login account information and the token information, sending a data acquisition request to each channel advertisement delivery platform, and receiving request data returned by the data acquisition request;

and carrying out data cleaning on the request data to obtain the delivery effect data and the original delivery strategy of each channel advertisement delivery platform, wherein the original delivery strategy comprises a delivery crowd strategy, a bidding strategy and a material selection strategy.

Optionally, in a second implementation manner of the first aspect of the present invention, based on the delivery effect data of each channel advertisement delivery platform, an initial delivery effect funnel model corresponding to each channel advertisement delivery platform is established, so as to obtain a plurality of initial delivery effect funnel models, where each initial delivery effect funnel model includes level information and conversion rates corresponding to a plurality of level advertisement operation behavior events, and the method includes:

traversing the delivery effect data of each channel advertisement delivery platform according to preset advertisement operation behavior events to obtain the quantity corresponding to each of a plurality of advertisement operation behavior events corresponding to each channel advertisement delivery platform;

according to the size sequence of the quantity corresponding to each advertisement operation behavior event, carrying out hierarchical division on a plurality of advertisement operation behavior events corresponding to each channel advertisement putting platform to obtain hierarchical information corresponding to each hierarchical advertisement operation behavior event;

calculating conversion rate from each level of advertisement operation behavior event to the next level of advertisement operation behavior event based on the level information corresponding to each level of advertisement operation behavior event, and obtaining conversion rate corresponding to each level of advertisement operation behavior event;

and constructing a funnel model of each channel advertisement putting platform according to the level information corresponding to each level advertisement operation behavior event and the conversion rate corresponding to each level advertisement operation behavior event, and obtaining an initial putting effect funnel model corresponding to each channel advertisement putting platform.

Optionally, in a third implementation manner of the first aspect of the present invention, the screening is performed on the multiple initial delivery effect funnel models based on each level of advertisement operation behavior event to obtain a target delivery effect funnel model, and the screening is performed on the multiple levels of advertisement operation behavior events of each initial delivery effect funnel model according to the conversion rates respectively corresponding to the multiple levels of advertisement operation behavior events of each initial delivery effect funnel model to obtain a target operation behavior event, where the target delivery effect funnel model is used to indicate an optimal delivery effect funnel model corresponding to each level of advertisement operation behavior event in initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior event is used to indicate an event to be optimized corresponding to each initial delivery effect funnel model, where the method includes:

extracting a plurality of first conversion rate queues and a plurality of second conversion rate queues, wherein each first conversion rate queue is used for indicating the conversion rate of the advertisement operation behavior events of the same level in all initial throwing effect funnel models, and each second conversion rate queue comprises the conversion rate respectively corresponding to the advertisement operation behavior events of all levels in the same initial throwing effect funnel model;

Obtaining the highest conversion rate in each first conversion rate queue, extracting the optimal delivery effect funnel model corresponding to each level advertisement operation behavior event from the plurality of initial delivery effect funnel models through the highest conversion rate in each first conversion rate queue, and obtaining a target delivery effect funnel model;

and obtaining target conversion rate of which the conversion rate is lower than a preset threshold value in each second conversion rate queue, and extracting the event to be optimized corresponding to each initial putting effect funnel model from all the level advertisement operation behavior events in each initial putting effect funnel model through the target conversion rate of which the conversion rate is lower than the preset threshold value in each second conversion rate queue, so as to obtain a target operation behavior event.

Optionally, in a fourth implementation manner of the first aspect of the present invention, the adjusting, according to the target delivery effect funnel model and the target operation behavior event, a delivery crowd policy, a bid policy, and a material selection policy in an original delivery policy of each channel advertisement delivery platform to obtain a target delivery policy corresponding to each channel advertisement delivery platform includes:

acquiring a sensitive policy factor corresponding to each level of advertisement operation behavior event through a preset sensitive policy factor model, wherein the sensitive policy factor is used for indicating policy parameters in the original delivery policy;

Setting a hierarchical advertisement operation behavior event corresponding to each target throwing effect funnel model as an optimal event, setting a sensitive strategy factor corresponding to the optimal event as a reference strategy parameter, and setting a sensitive strategy factor corresponding to each target operation behavior event as a strategy parameter to be optimized;

and carrying out strategy parameter setting on the strategy parameters to be optimized based on the reference strategy parameters so as to adjust the delivery crowd strategy, the bidding strategy and the material selection strategy in each original delivery strategy, thereby obtaining the target delivery strategy corresponding to each channel advertisement delivery platform.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing, based on the reference policy parameter, policy parameter setting on the policy parameter to be optimized to adjust a delivery crowd policy, a bid policy and a material selection policy in each original delivery policy, to obtain a target delivery policy corresponding to each channel advertisement delivery platform, includes:

calculating the bid amount and the bid amount floating rate in the strategy parameters to be optimized based on the bid amount and the bid amount floating rate in the reference strategy parameters through a preset real-time bidding algorithm to obtain a first delivery strategy;

Adjusting the throwing crowd labels in the strategy parameters to be optimized based on the throwing crowd labels in the reference strategy parameters through a preset user portrait system to obtain a second throwing strategy;

setting the material identification in the strategy parameters to be optimized based on the material identification in the reference strategy parameters to obtain a third delivery strategy;

and generating target delivery strategies corresponding to the advertising delivery platforms of all channels according to the first delivery strategy, the second delivery strategy and the third delivery strategy.

Optionally, in a sixth implementation manner of the first aspect of the present invention, according to a delivery policy data format of each channel advertisement delivery platform, performing data format compatible processing on the target delivery policy to obtain a delivery policy package of each channel advertisement delivery platform, and distributing the delivery policy package to a corresponding channel advertisement delivery platform, so that each channel advertisement delivery platform performs advertisement delivery according to the target advertisement delivery policy, including:

acquiring a delivery strategy template of each channel advertisement delivery platform, and writing a target delivery strategy corresponding to each channel advertisement delivery platform into the corresponding delivery strategy template to obtain a platform delivery strategy corresponding to each channel advertisement delivery platform;

Data packaging is carried out on platform delivery strategies corresponding to the advertising platforms of all channels, and a delivery strategy package of the advertising platforms of all channels is obtained;

and sending an advertisement putting request to each channel advertisement putting platform, and distributing the putting strategy package of each channel advertisement putting platform to the corresponding channel advertisement putting platform so that each channel advertisement putting platform can put advertisements according to the corresponding target advertisement putting strategy.

A second aspect of the present invention provides a multi-channel advertising device, comprising:

the acquisition module is used for acquiring the delivery effect data of the advertising delivery platforms of the multiple channels and the original delivery strategies through the timing tasks, wherein the original delivery strategies comprise a delivery crowd strategy, a bidding strategy and a material selection strategy;

the modeling module is used for establishing initial delivery effect funnel models corresponding to the advertising platforms of the channels based on the delivery effect data of the advertising platforms of the channels to obtain a plurality of initial delivery effect funnel models, wherein each initial delivery effect funnel model comprises level information and conversion rate corresponding to a plurality of level advertising operation behavior events;

the screening module is used for screening the plurality of initial delivery effect funnel models based on the advertisement operation behavior events of each level to obtain target delivery effect funnel models, screening the advertisement operation behavior events of each level of each initial delivery effect funnel model according to the conversion rate corresponding to the advertisement operation behavior events of each level of each initial delivery effect funnel model to obtain target operation behavior events, wherein the target delivery effect funnel models are used for indicating optimal delivery effect funnel models corresponding to advertisement operation behavior events of each level in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior events are used for indicating events to be optimized corresponding to the initial delivery effect funnel models;

The adjustment module is used for adjusting the delivery crowd strategy, the bidding strategy and the material selection strategy in the original delivery strategy of each channel advertisement delivery platform according to the target delivery effect funnel model and the target operation behavior event to obtain a target delivery strategy corresponding to each channel advertisement delivery platform;

the distribution module is used for carrying out data format compatible processing on the target advertisement delivery strategies according to the delivery strategy data format of each channel advertisement delivery platform to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform carries out advertisement delivery according to the target advertisement delivery strategy.

Optionally, in a first implementation manner of the second aspect of the present invention, the acquiring module is specifically configured to:

Optionally, in a second implementation manner of the second aspect of the present invention, the modeling module is specifically configured to:

Optionally, in a third implementation manner of the second aspect of the present invention, the screening module is specifically configured to:

Optionally, in a fourth implementation manner of the second aspect of the present invention, the adjusting module includes:

the acquisition unit is used for acquiring the sensitive strategy factors corresponding to the advertisement operation behavior events of each level through a preset sensitive strategy factor model, wherein the sensitive strategy factors are used for indicating strategy parameters in the original delivery strategy;

the setting unit is used for setting the hierarchical advertisement operation behavior event corresponding to each target throwing effect funnel model as an optimal event, setting the sensitive strategy factor corresponding to the optimal event as a reference strategy parameter, and setting the sensitive strategy factor corresponding to each target operation behavior event as a strategy parameter to be optimized;

the adjustment unit is used for carrying out policy parameter setting on the policy parameters to be optimized based on the reference policy parameters so as to adjust the delivery crowd policy, the bidding policy and the material selection policy in each original delivery policy and obtain the target delivery policy corresponding to each channel advertisement delivery platform.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the adjusting unit is specifically configured to:

Optionally, in a sixth implementation manner of the second aspect of the present invention, the distribution module is specifically configured to:

A third aspect of the present invention provides a multi-channel advertising device comprising: a memory and at least one processor, the memory having a computer program stored therein; the at least one processor invokes the computer program in the memory to cause the multi-channel advertising device to perform the multi-channel advertising method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored therein, which when run on a computer, causes the computer to perform the multi-channel advertising method described above.

According to the technical scheme provided by the invention, the delivery effect data of the advertising platforms of the multiple channels and the original delivery strategy are obtained through the timing task, wherein the original delivery strategy comprises a delivery crowd strategy, a bidding strategy and a material selection strategy; based on the delivery effect data of each channel advertisement delivery platform, establishing an initial delivery effect funnel model corresponding to each channel advertisement delivery platform to obtain a plurality of initial delivery effect funnel models, wherein each initial delivery effect funnel model comprises level information and conversion rate corresponding to a plurality of level advertisement operation behavior events; screening the multiple initial delivery effect funnel models based on the multiple level advertisement operation behavior events to obtain target delivery effect funnel models, screening the multiple level advertisement operation behavior events of each initial delivery effect funnel model according to conversion rates respectively corresponding to the multiple level advertisement operation behavior events of each initial delivery effect funnel model to obtain target operation behavior events, wherein the target delivery effect funnel models are used for indicating optimal delivery effect funnel models corresponding to the multiple level advertisement operation behavior events in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior events are used for indicating events to be optimized corresponding to the initial delivery effect funnel models; according to the target delivery effect funnel model and the target operation behavior event, a delivery crowd strategy, a bidding strategy and a material selection strategy in the original delivery strategy of each channel advertisement delivery platform are adjusted, and a target delivery strategy corresponding to each channel advertisement delivery platform is obtained; according to the delivery strategy data format of each channel advertisement delivery platform, carrying out data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform carries out advertisement delivery according to the target advertisement delivery strategy. In the embodiment of the invention, after obtaining the delivery effect data of a plurality of channel advertisement delivery platforms and an original delivery strategy, a server establishes an initial delivery effect funnel model of each channel advertisement delivery platform, compares the initial delivery effect funnel model of each channel advertisement delivery platform to obtain an optimal delivery effect funnel model and an event to be optimized, then adjusts a delivery crowd strategy, a bid strategy and a material selection strategy in the original delivery strategy according to strategy parameters in the optimal delivery effect funnel model to obtain a target delivery strategy corresponding to each channel advertisement delivery platform, and finally performs data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributes the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform performs advertisement delivery according to the target advertisement delivery strategy. The invention can improve the advertising efficiency.

Drawings

FIG. 1 is a schematic diagram of one embodiment of a multi-channel advertising method in accordance with an embodiment of the present invention;

FIG. 2 is a schematic diagram of another embodiment of a multi-channel advertising method in accordance with an embodiment of the present invention;

FIG. 3 is a schematic diagram of one embodiment of a multi-channel advertising device in accordance with an embodiment of the present invention;

FIG. 4 is a schematic diagram of another embodiment of a multi-channel advertising device in accordance with an embodiment of the present invention;

FIG. 5 is a schematic diagram of one embodiment of a multi-channel advertising device in accordance with an embodiment of the invention.

Detailed Description

The embodiment of the invention provides a multi-channel advertisement putting method, device and equipment and a storage medium, which are used for improving advertisement putting efficiency.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, a specific flow of an embodiment of the present invention is described below with reference to fig. 1, where an embodiment of a multi-channel advertisement delivery method according to an embodiment of the present invention includes:

101. acquiring the delivery effect data and the original delivery strategies of the advertising delivery platforms of the multiple channels through the timing task, wherein the original delivery strategies comprise a delivery crowd strategy, a bidding strategy and a material selection strategy;

it can be understood that the execution body of the present invention may be a multi-channel advertisement delivery device, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (artificial intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.

The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (content delivery network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

In the embodiment, the advertisement providers of different channels correspond to the advertisement delivery platforms of different channels, the invention aims to open the data gap between the advertisement delivery platforms of different channels, and an advertiser can automatically deliver advertisements to the advertisement delivery platforms of different channels by only setting the advertisement delivery strategy once and automatically collect the delivery effect data of the advertiser on the different advertisement delivery platforms, so that the delivery effect data of the advertiser on the different advertisement delivery platforms is more visual, the difficulty of analysis of the delivery effect is reduced, and the advertisement delivery is more efficient.

The advertisement delivery method provided by the embodiment of the invention is suitable for intelligent advertisement delivery and propaganda in the medical field and the medical insurance field, and in one possible implementation way, the delivery effect data is the delivery effect data of medical related advertisements, such as the delivery effect data of medical insurance advertisements.

In this embodiment, a data acquisition interface of each channel advertisement delivery platform is preset in the timing task, and is used for pulling the delivery effect data and the original delivery strategy of each channel advertisement delivery platform, and the server pulls the delivery effect data and the element delivery strategy to each channel advertisement delivery platform through the timing task, for example, the timing task pulls the delivery effect data and the original delivery strategy to each channel advertisement delivery platform once every hour.

In this embodiment, the delivery effect data includes, but is not limited to, exposure amount, click amount, registration amount, download amount, order amount, payment amount, binding amount, etc., depending on the advertisement delivery scenario, and assuming that the advertiser delivers the medical insurance advertisement, the delivery effect data may include, but is not limited to, an originating insurance amount, an insurance coverage amount, a health notification amount, a reservation consultant amount, etc. The original delivery strategies comprise a delivery crowd strategy, a bid strategy and a material selection strategy, wherein the delivery crowd strategy refers to a target crowd delineating strategy of advertisements, the bid strategy refers to a set of price factors such as price per thousand exposure and price floating range of the advertisements, and the material selection strategy refers to a strategy for selecting advertisement display materials.

102. Based on the delivery effect data of each channel advertisement delivery platform, establishing an initial delivery effect funnel model corresponding to each channel advertisement delivery platform to obtain a plurality of initial delivery effect funnel models, wherein each initial delivery effect funnel model comprises level information and conversion rate corresponding to a plurality of level advertisement operation behavior events;

in this embodiment, the initial delivery effect funnel model is a marketing funnel model, which is a conversion quantization model for gradually changing a non-potential customer into a customer, and the value of the marketing funnel model is to quantize the efficiency of each link in the marketing process, so as to identify weak links, and the initial delivery effect funnel model is a funnel model of the same advertisement on different advertisement delivery platforms, and is used for analyzing the delivery effect of the same advertisement on each link in different advertisement delivery platforms. The server builds initial delivery effect funnel models of the advertising delivery platforms of the channels based on the delivery effect data, each initial delivery effect funnel model comprises a plurality of advertisement operation behavior events, and a certain medical insurance advertisement is assumed to comprise a plurality of advertisement operation behavior events such as exposure, clicking, consultation, application and the like in the initial delivery effect funnel model of the advertising delivery platform A of the channel, wherein the quantity of each advertisement operation behavior event is respectively as follows: exposure 10000, click 2000, consultation 300, and application 210, then, according to the funnel property of the marketing funnel model, the number of advertisement operation behavior events of each level decreases according to the level, so the level information of each advertisement operation behavior event may be exposure 4, click 3, consultation 2, and application 1, which indicates that the level size sequence of these advertisement operation behavior events is: exposure > click > consultation > insuring, and conversion rate of advertisement operation behavior event of each level refers to a ratio of the number of next level to the number of last level, in this example, conversion rate of click advertisement operation behavior event is 2000/10000=20%, conversion rate of consultation advertisement operation behavior event is 300/2000=17.5%, and conversion rate of insuring advertisement operation behavior event is 210/300=70%.

103. Screening the multiple initial delivery effect funnel models based on the multiple level advertisement operation behavior events to obtain target delivery effect funnel models, screening the multiple level advertisement operation behavior events of each initial delivery effect funnel model according to the conversion rate corresponding to the multiple level advertisement operation behavior events of each initial delivery effect funnel model to obtain target operation behavior events, wherein the target delivery effect funnel models are used for indicating optimal delivery effect funnel models corresponding to the multiple level advertisement operation behavior events in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior events are used for indicating events to be optimized corresponding to the initial delivery effect funnel models;

in this embodiment, in order to optimize the advertisement delivery strategy, the server performs external comparison on the initial delivery effect funnel model of each channel advertisement delivery platform to obtain a target delivery effect funnel model corresponding to each hierarchical advertisement operation behavior event, and then performs internal comparison on each initial delivery effect funnel model to obtain a target operation behavior event corresponding to each initial delivery effect funnel model, where the target delivery effect funnel model is used to indicate an optimal delivery effect funnel model corresponding to each hierarchical advertisement operation behavior event in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, for example, the initial delivery effect funnel model of the existing A, B, C three channel advertisement delivery platforms, the initial delivery effect funnel model of each channel advertisement delivery platform includes three hierarchical advertisement operation behavior events a, B and C, and the server determines that the optimal delivery effect funnel model corresponding to the a hierarchical advertisement operation behavior event is the initial effect funnel model of the B channel advertisement delivery platform by comparing the conversion rate of the a hierarchical advertisement operation behavior event in the initial delivery effect funnel model of the A, B, C three channel advertisement delivery platforms, determines that the optimal delivery effect funnel model of the a hierarchical advertisement operation behavior event is the initial funnel model of the B channel advertisement effect funnel model of the B, and the server determines that the conversion rate of the B hierarchical advertisement effect funnel model is the optimal by comparing the conversion rate of the B of the initial operation effect funnel models of the initial delivery funnel models of the three channel advertisement operation behavior events in the channel advertisement delivery platforms, and determining the optimal delivery effect funnel model corresponding to the c-level advertisement operation behavior event as an initial delivery effect funnel model of the A-channel advertisement delivery platform. And the server compares the operational events of the advertisements of the levels a, B and C in the initial delivery effect funnel model of the advertising platform of the channel A to obtain C as the operational event to be optimized corresponding to the initial delivery effect funnel model of the advertising platform of the channel A, compares the operational events of the advertisements of the levels a, B and C in the initial delivery effect funnel model of the advertising platform of the channel B to obtain a and B as the operational event to be optimized corresponding to the initial delivery effect funnel model of the advertising platform of the channel B, and compares the operational event of the advertisements of the levels a, B and C in the initial delivery effect funnel model of the advertising platform of the channel C to obtain a and C as the operational event to be optimized corresponding to the initial delivery effect funnel model of the advertising platform of the channel C.

104. According to the target delivery effect funnel model and the target operation behavior event, a delivery crowd strategy, a bidding strategy and a material selection strategy in the original delivery strategy of each channel advertisement delivery platform are adjusted, and a target delivery strategy corresponding to each channel advertisement delivery platform is obtained;

in this embodiment, in order to optimize an original delivery policy corresponding to each channel advertisement delivery platform, a server performs parameter adjustment on an event to be optimized based on an optimal delivery effect funnel model, so as to obtain a target delivery policy corresponding to each channel advertisement delivery platform, specifically, the server adjusts a Bidding policy of the event to be optimized in the original delivery policy through a preset Real-Time Bidding algorithm, adjusts a delivery crowd policy of the event to be optimized in the original delivery policy through a preset user portrait system, and finally adjusts a material selection policy of the event to be optimized in the original delivery policy through a material selection policy of the optimal delivery effect funnel model, so as to obtain the target delivery policy. The real-time bidding algorithm is an algorithm written by advertisers after bid analysis of bid and evaluation of each user advertisement behavior based on big data, and can calculate the optimal bid of advertisements by combining the big data, so that the bid docking times of the advertisers and different advertisement suppliers are reduced, the advertisement putting efficiency is greatly improved, the preset user portrait system is a big data sharing user portrait system, the gap of user label data of different advertisement putting platforms can be broken, and the different advertisement putting platforms can share the most comprehensive and rich user portrait system.

105. According to the delivery strategy data format of each channel advertisement delivery platform, carrying out data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform carries out advertisement delivery according to the target advertisement delivery strategy.

In this embodiment, in order to quickly complete the advertisement delivery task of each channel advertisement delivery platform, the server converts the target delivery strategy into a delivery strategy package compatible with each channel advertisement delivery platform, and distributes the delivery strategy package to the corresponding channel advertisement delivery platform, and after each channel advertisement delivery platform receives the delivery strategy package, the advertisement can be automatically delivered without manual intervention. Specifically, the server performs data standardization processing on the target delivery policy of each channel advertisement delivery platform, including standardization processing of data such as field names, data types, transmission modes, and the like, for example, the bid field name in the target delivery policy is real_time_price, and the bid field name of one channel advertisement delivery platform is realtemtime price, so that the server needs to convert real_time_price into realtemtime price to meet the delivery data standard of the channel advertisement delivery platform.

Further, the server stores the drop policy package in a blockchain database, and is not limited herein.

In the embodiment of the invention, after obtaining the delivery effect data of a plurality of channel advertisement delivery platforms and an original delivery strategy, a server establishes an initial delivery effect funnel model of each channel advertisement delivery platform, compares the initial delivery effect funnel model of each channel advertisement delivery platform to obtain an optimal delivery effect funnel model and an event to be optimized, then adjusts the delivery crowd strategy, the bidding strategy and the material selection strategy in the original delivery strategy according to the strategy parameters in the optimal delivery effect funnel model to obtain a target delivery strategy corresponding to each channel advertisement delivery platform, and finally performs data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributes the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform performs advertisement delivery according to the target advertisement delivery strategy. The invention can improve the advertising efficiency. The scheme can be applied to the intelligent medical field, so that the construction of the intelligent city is promoted.

Referring to fig. 2, another embodiment of a multi-channel advertisement delivery method according to an embodiment of the present invention includes:

201. acquiring the delivery effect data and the original delivery strategies of the advertising delivery platforms of the multiple channels through the timing task, wherein the original delivery strategies comprise a delivery crowd strategy, a bidding strategy and a material selection strategy;

specifically, when the server detects an execution signal of a timing task, login account information and token information of a plurality of channel advertisement delivery platforms are obtained, wherein the login account information is account information with advertisement data acquisition authority of the corresponding channel advertisement delivery platforms; the server sends a data acquisition request to each channel advertisement delivery platform based on login account information and token information, and receives request data returned by the data request; the server performs data cleaning on the request data to obtain the delivery effect data and the original delivery strategy of each channel advertisement delivery platform, wherein the original delivery strategy comprises a delivery crowd strategy, a bidding strategy and a material selection strategy.

In this optional embodiment, in order to obtain the data acquisition permission of the advertisement delivery platforms of each channel, the server simulates the advertisement delivery platform of each channel through the login account information of each channel advertisement delivery platform to obtain the token information (token) of each advertisement delivery platform, the token information of each advertisement delivery platform is used for verifying the data acquisition permission of the corresponding advertisement delivery platform, if the token information verification is passed, the server carries the token information to send a data acquisition request to the corresponding advertisement delivery platform, so as to obtain returned request data, then washes the returned request data based on big data, filters dirty data, fills in missing data, and thus obtains the delivery effect data and the original delivery strategy corresponding to each advertisement delivery platform.

202. Based on the delivery effect data of each channel advertisement delivery platform, establishing an initial delivery effect funnel model corresponding to each channel advertisement delivery platform to obtain a plurality of initial delivery effect funnel models, wherein each initial delivery effect funnel model comprises level information and conversion rate corresponding to a plurality of level advertisement operation behavior events;

specifically, the server traverses the delivery effect data of each channel advertisement delivery platform according to preset advertisement operation behavior events to obtain the corresponding quantity of a plurality of advertisement operation behavior events corresponding to each channel advertisement delivery platform; the server performs hierarchical division on a plurality of advertisement operation behavior events corresponding to each channel advertisement putting platform according to the size sequence of the quantity corresponding to each advertisement operation behavior event, so as to obtain hierarchical information corresponding to each hierarchical advertisement operation behavior event; the server calculates the conversion rate from each level of advertisement operation behavior event to the next level of advertisement operation behavior event based on the level information corresponding to each level of advertisement operation behavior event, and obtains the conversion rate corresponding to each level of advertisement operation behavior event; and the server constructs a funnel model of each channel advertisement putting platform according to the level information corresponding to each level advertisement operation behavior event and the conversion rate corresponding to each level advertisement operation behavior event, and obtains an initial putting effect funnel model corresponding to each channel advertisement putting platform.

In this optional embodiment, the server extracts the number of each advertisement operation behavior event in the delivery effect data according to a plurality of preset advertisement operation behavior events, then performs hierarchical division on the advertisement operation behavior events corresponding to each channel advertisement delivery platform according to the order of the number of each advertisement operation behavior event to obtain hierarchical information of each advertisement operation behavior event, calculates the conversion rate from each hierarchical advertisement operation behavior event to the next hierarchical advertisement operation behavior event to obtain the conversion rate of each hierarchical advertisement operation behavior event, and finally draws a funnel model of each channel advertisement delivery platform according to the hierarchical information of each advertisement operation behavior event and the conversion rate of each hierarchical advertisement operation behavior event to obtain the initial delivery effect funnel model of each channel advertisement delivery platform.

203. Extracting a plurality of first conversion rate queues and a plurality of second conversion rate queues, wherein each first conversion rate queue is used for indicating the conversion rate of the advertisement operation behavior events of the same level in all initial throwing effect funnel models, and each second conversion rate queue comprises the conversion rate respectively corresponding to the advertisement operation behavior events of all levels in the same initial throwing effect funnel model;

In this embodiment, each first conversion rate queue includes the conversion rates of the advertisement operation behavior events of the same level in all the initial delivery effect funnel models, each second conversion rate queue includes the conversion rates corresponding to the advertisement operation behavior events of all the levels in all the initial delivery effect funnel models, for example, a, B, C, d (ordered according to the level information from large to small) of the advertisement operation behavior events in the initial delivery effect funnel models of the three channel advertisement delivery platforms, a1, B1, C1, d1 of the advertisement operation behavior events in the initial delivery effect funnel models of the channel advertisement delivery platforms (i.e., the second conversion rate queue corresponding to the channel advertisement delivery platform a1, B1, C1, d 1) includes a1, the conversion rate of each advertisement operation behavior event in the initial delivery effect funnel model of the B-channel advertisement delivery platform is a2, B2, C2 and d2 (i.e. the second conversion rate queue corresponding to the B-channel advertisement delivery platform comprises a2, B2, C2 and d 2), the conversion rate of each advertisement operation behavior event in the initial delivery effect funnel model of the C-channel advertisement delivery platform is a3, B3, C3 and d3 (i.e. the second conversion rate queue corresponding to the C-channel advertisement delivery platform comprises a3, B3, C3 and d 3), then the first conversion rate queue corresponding to the advertisement operation behavior event a comprises a1, a2 and a3, the first conversion rate queue corresponding to the advertisement operation behavior event B comprises B1, B2 and B3, and the first conversion rate queue corresponding to the advertisement operation behavior event C comprises C1, C2 and C3.

204. Obtaining the highest conversion rate in each first conversion rate queue, extracting the optimal delivery effect funnel model corresponding to each level advertisement operation behavior event from the plurality of initial delivery effect funnel models through the highest conversion rate in each first conversion rate queue, and obtaining a target delivery effect funnel model;

in this embodiment, in order to identify an optimal delivery effect funnel model corresponding to each level of advertisement operation behavior event, the server compares the sizes of the conversions in the first conversion queues to obtain the highest conversion rate in the first conversion queues, and extracts the optimal delivery effect funnel model corresponding to each level of advertisement operation behavior event from the plurality of initial delivery effect funnel models through the highest conversion rate in the first conversion queues, for example, the first conversion rate queue corresponding to the advertisement operation behavior event a is a1, a2, a3, where a2 is the maximum conversion rate, and then the server sets the initial delivery effect funnel model corresponding to a2 as the optimal delivery effect funnel model.

205. Obtaining target conversion rate of which the conversion rate is lower than a preset threshold value in each second conversion rate queue, and extracting events to be optimized corresponding to each initial putting effect funnel model from all the level advertisement operation behavior events in each initial putting effect funnel model through the target conversion rate of which the conversion rate is lower than the preset threshold value in each second conversion rate queue to obtain target operation behavior events;

In this embodiment, in order to identify a problem in the original delivery strategy, the server determines whether the conversion rate in each second conversion rate queue is lower than a preset threshold value, so as to obtain a target conversion rate of which the conversion rate in each second conversion rate queue is lower than the preset threshold value, and the conversion rate lower than the preset threshold value indicates that the delivery strategy of a certain link of advertisement delivery is unreasonably set, which results in low conversion rate and large user loss, so that the server sets an advertisement operation behavior event corresponding to the target conversion rate as a corresponding event to be optimized as a subsequent delivery strategy optimization object.

206. According to the target delivery effect funnel model and the target operation behavior event, a delivery crowd strategy, a bidding strategy and a material selection strategy in the original delivery strategy of each channel advertisement delivery platform are adjusted, and a target delivery strategy corresponding to each channel advertisement delivery platform is obtained;

specifically, the server acquires a sensitive policy factor corresponding to each level of advertisement operation behavior event through a preset sensitive policy factor model, wherein the sensitive policy factor is used for indicating policy parameters in an original delivery policy; the server sets the hierarchical advertisement operation behavior event corresponding to each target throwing effect funnel model as an optimal event, sets the sensitive strategy factor corresponding to the optimal event as a reference strategy parameter, and sets the sensitive strategy factor corresponding to each target operation behavior event as a strategy parameter to be optimized; the server carries out strategy parameter setting on strategy parameters to be optimized based on the reference strategy parameters so as to adjust the throwing crowd strategy, the bidding strategy and the material selection strategy in each original throwing strategy, and a target throwing strategy corresponding to each channel advertisement throwing platform is obtained.

In this optional embodiment, the preset sensitive policy factor model is a decision model generated after analyzing the big data throwing effect of the historical throwing data, so that the sensitive policy factor corresponding to the event to be optimized can be determined, the event to be optimized is assumed to be "clicked", the big data analysis of the historical throwing data through the sensitive policy factor model shows that the sensitive policy factor of the "clicked" behavior is the throwing crowd label and the material identifier, that is, when the throwing crowd label and the material identifier are changed, the clicking amount of the advertisement is greatly influenced, and therefore, the server performs policy parameter adjustment on the sensitive policy factor in the event to be optimized based on the sensitive policy factor, so as to obtain the target throwing policy.

Further, based on the reference policy parameters, performing policy parameter setting on policy parameters to be optimized to adjust a delivery crowd policy, a bid policy and a material selection policy in each original delivery policy, so as to obtain a target delivery policy corresponding to each channel advertisement delivery platform, including: the server calculates the bid amount and the bid amount floating rate in the strategy parameters to be optimized based on the bid amount and the bid amount floating rate in the reference strategy parameters through a preset real-time bidding algorithm to obtain a first delivery strategy; the server adjusts the delivery crowd labels in the strategy parameters to be optimized based on the delivery crowd labels in the reference strategy parameters through a preset user portrayal system to obtain a second delivery strategy; the server sets the material identification in the strategy parameters to be optimized based on the material identification in the reference strategy parameters to obtain a third delivery strategy; and the server generates a target delivery strategy corresponding to each channel advertisement delivery platform according to the first delivery strategy, the second delivery strategy and the third delivery strategy.

In this optional embodiment, the server obtains the advertisement real-time traffic before bidding through the real-time interface RTA (real time api), and then calculates the bid amount and the bid amount floating rate by referring to the bid amount and the bid amount floating rate in the reference policy parameters through a preset real-time bidding algorithm based on the advertisement real-time traffic, so as to obtain a first delivery policy, and then adjusts the delivery crowd label in the policy parameters to be optimized by referring to the delivery crowd label in the reference policy parameters through a preset user portrait system, so as to obtain a second delivery policy, wherein the user portrait system includes a huge number of crowd labels and is a shared crowd label system. And then, the server refers to the material identification in the reference strategy parameters, sets the material identification in the strategy parameters to be optimized as the material identification in the strategy parameters of the optimal delivery effect funnel model, and obtains a third delivery strategy. And finally, the server correspondingly modifies the original delivery strategy corresponding to each channel advertisement delivery platform based on the first delivery strategy, the second delivery strategy and the third delivery strategy to obtain the target delivery strategy corresponding to each channel advertisement delivery platform.

207. According to the delivery strategy data format of each channel advertisement delivery platform, carrying out data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform carries out advertisement delivery according to the target advertisement delivery strategy.

Specifically, the server acquires a delivery strategy template of each channel advertisement delivery platform, and writes a target delivery strategy corresponding to each channel advertisement delivery platform into the corresponding delivery strategy template to obtain a platform delivery strategy corresponding to each channel advertisement delivery platform; the server performs data encapsulation on platform delivery strategies corresponding to the advertising platforms of all channels to obtain delivery strategy packages of the advertising platforms of all channels; the server distributes the delivery strategy packages of the advertising platforms of the channels to the advertising platforms of the corresponding channels by sending the advertising requests to the advertising platforms of the channels, so that the advertising platforms of the channels can deliver advertisements according to the corresponding target advertising strategies.

In this optional embodiment, in order to improve the delivery efficiency, the server encapsulates the target delivery strategy into a delivery strategy package according to the delivery strategy data format of each channel advertisement delivery platform, and then sends the delivery strategy package to the corresponding channel advertisement delivery platform through the advertisement delivery request, and the channel advertisement delivery platform can automatically deliver the advertisement after receiving the delivery strategy package.

In the embodiment of the invention, after obtaining the delivery effect data and the original delivery strategies of a plurality of channel advertisement delivery platforms, a server establishes an initial delivery effect funnel model of each channel advertisement delivery platform, externally compares and internally compares the conversion rate in the initial delivery effect funnel model of each channel advertisement delivery platform to obtain an externally optimal delivery effect funnel model and an internally worst event to be optimized, then adjusts the delivery crowd strategy, the bidding strategy and the material selection strategy in the original delivery strategies according to the strategy parameters in the optimal delivery effect funnel model to obtain target delivery strategies corresponding to each channel advertisement delivery platform, finally performs data format compatible processing on the target delivery strategies to obtain delivery strategy packages of each channel advertisement delivery platform, and distributes the delivery strategy packages to the corresponding channel advertisement delivery platforms to enable each channel advertisement delivery platform to deliver advertisements according to the target advertisement delivery strategies. The invention can improve the advertising efficiency. The scheme can be applied to the intelligent medical field, so that the construction of the intelligent city is promoted.

The method for multi-channel advertisement delivery in the embodiment of the present invention is described above, and the device for multi-channel advertisement delivery in the embodiment of the present invention is described below, referring to fig. 3, one embodiment of the device for multi-channel advertisement delivery in the embodiment of the present invention includes:

The acquisition module 301 is configured to acquire, through a timing task, delivery effect data and an original delivery policy of a plurality of channel advertisement delivery platforms, where the original delivery policy includes a delivery crowd policy, a bid policy, and a material selection policy;

the modeling module 302 is configured to establish an initial delivery effect funnel model corresponding to each channel advertisement delivery platform based on delivery effect data of each channel advertisement delivery platform, so as to obtain a plurality of initial delivery effect funnel models, where each initial delivery effect funnel model includes level information and conversion rate corresponding to a plurality of level advertisement operation behavior events;

the screening module 303 is configured to screen the multiple initial delivery effect funnel models based on the multiple level advertisement operation behavior events to obtain target delivery effect funnel models, screen the multiple level advertisement operation behavior events of each initial delivery effect funnel model according to the conversion rates respectively corresponding to the multiple level advertisement operation behavior events of each initial delivery effect funnel model to obtain target operation behavior events, where the target delivery effect funnel models are used to indicate optimal delivery effect funnel models corresponding to the multiple level advertisement operation behavior events in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior events are used to indicate events to be optimized corresponding to the initial delivery effect funnel models;

The adjustment module 304 is configured to adjust, according to the target delivery effect funnel model and the target operation behavior event, a delivery crowd policy, a bid policy, and a material selection policy in an original delivery policy of each channel advertisement delivery platform, so as to obtain a target delivery policy corresponding to each channel advertisement delivery platform;

the distribution module 305 is configured to perform data format compatible processing on the target advertisement delivery policy according to the delivery policy data format of each channel advertisement delivery platform, obtain a delivery policy package of each channel advertisement delivery platform, and distribute the delivery policy package to a corresponding channel advertisement delivery platform, so that each channel advertisement delivery platform performs advertisement delivery according to the target advertisement delivery policy.

Referring to fig. 4, another embodiment of the multi-channel advertisement delivery device according to the present invention includes:

Optionally, the acquiring module 301 is specifically configured to:

when the execution signal of the timing task is detected, login account information and token information of a plurality of channel advertisement delivery platforms are obtained, wherein the login account information is account information with the advertisement data acquisition authority of the corresponding channel advertisement delivery platforms;

And carrying out data cleaning on the request data to obtain the delivery effect data and the original delivery strategy of each channel advertisement delivery platform, wherein the original delivery strategy comprises a delivery crowd strategy, a bid strategy and a material selection strategy.

Optionally, the modeling module 302 is specifically configured to:

Optionally, the screening module 303 is specifically configured to:

Optionally, the adjusting module 304 includes:

The acquiring unit 3041 is configured to acquire, through a preset sensitive policy factor model, a sensitive policy factor corresponding to each level of advertisement operation behavior event, where the sensitive policy factor is used to indicate a policy parameter in an original delivery policy;

the setting unit 3042 is configured to set a hierarchical advertisement operation behavior event corresponding to each target delivery effect funnel model as an optimal event, set a sensitive policy factor corresponding to the optimal event as a reference policy parameter, and set a sensitive policy factor corresponding to each target operation behavior event as a policy parameter to be optimized;

the adjusting unit 3043 is configured to perform policy parameter setting on the policy parameter to be optimized based on the reference policy parameter, so as to adjust the delivery crowd policy, the bid policy and the material selection policy in each original delivery policy, and obtain a target delivery policy corresponding to each channel advertisement delivery platform.

Optionally, the adjusting unit 3043 is specifically configured to:

calculating the bid amount and the bid amount floating rate in the strategy parameters to be optimized based on the bid amount and the bid amount floating rate in the reference strategy parameters by a preset real-time bidding algorithm to obtain a first delivery strategy;

and generating target delivery strategies corresponding to the advertising delivery platforms of the channels according to the first delivery strategy, the second delivery strategy and the third delivery strategy.

Optionally, the distribution module 305 is specifically configured to:

Fig. 3 and fig. 4 above describe the multi-channel advertisement delivery device in the embodiment of the present invention in detail from the point of view of the modularized functional entity, and the multi-channel advertisement delivery device in the embodiment of the present invention is described in detail from the point of view of hardware processing.

Fig. 5 is a schematic diagram of a multi-channel advertising device 500 according to an embodiment of the present invention, where the multi-channel advertising device 500 may vary considerably in configuration or performance, and may include one or more processors (central processing units, CPU) 510 (e.g., one or more processors) and memory 520, one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Wherein memory 520 and storage medium 530 may be transitory or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of computer program operations in the multi-channel advertising device 500. Still further, the processor 510 may be configured to communicate with the storage medium 530 to perform a series of computer program operations in the storage medium 530 on the multi-channel advertising device 500.

The multi-channel advertising device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input/output interfaces 560, and/or one or more operating systems 531, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the multi-channel advertising device structure shown in FIG. 5 does not constitute a limitation of the multi-channel advertising device, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

The invention also provides a multi-channel advertisement delivery device, which comprises a memory and a processor, wherein the memory stores a computer readable computer program, and the computer readable computer program when executed by the processor causes the processor to execute the steps of the multi-channel advertisement delivery method in the above embodiments.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, in which a computer program is stored, which when run on a computer, causes the computer to perform the steps of the multi-channel advertisement delivery method.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in whole or in part in the form of a software product stored in a storage medium, comprising a number of computer programs for causing a computer device (which may be a personal computer, a server, a network device, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The multi-channel advertisement delivery method is characterized by comprising the following steps:

according to the delivery strategy data format of each channel advertisement delivery platform, carrying out data format compatible processing on the target delivery strategy to obtain a delivery strategy package of each channel advertisement delivery platform, and distributing the delivery strategy package to the corresponding channel advertisement delivery platform so that each channel advertisement delivery platform carries out advertisement delivery according to the target delivery strategy.

2. The multi-channel advertising method as claimed in claim 1, wherein the obtaining, by the timing task, the impression data of the multi-channel advertising platforms and the original impression policy, the original impression policy including an impression crowd policy, a bid policy, and a material selection policy, comprises:

3. The multi-channel advertisement delivery method according to claim 1, wherein the establishing an initial delivery effect funnel model corresponding to each channel advertisement delivery platform based on the delivery effect data of each channel advertisement delivery platform, to obtain a plurality of initial delivery effect funnel models, each initial delivery effect funnel model including level information and conversion rates corresponding to a plurality of level advertisement operation behavior events, respectively, comprises:

according to the order of the quantity corresponding to each advertisement operation behavior event, carrying out hierarchical division on a plurality of advertisement operation behavior events corresponding to each channel advertisement putting platform to obtain hierarchical information corresponding to each hierarchical advertisement operation behavior event;

4. The multi-channel advertisement delivery method according to claim 1, wherein the screening is performed on the multiple initial delivery effect funnel models based on the multiple level advertisement operation behavior events to obtain target delivery effect funnel models, and the screening is performed on the multiple level advertisement operation behavior events of each initial delivery effect funnel model according to the conversion rates respectively corresponding to the multiple level advertisement operation behavior events of each initial delivery effect funnel model to obtain target operation behavior events, where the target delivery effect funnel models are used for indicating optimal delivery effect funnel models corresponding to each level advertisement operation behavior event in the initial delivery effect funnel models corresponding to all channel advertisement delivery platforms, and the target operation behavior events are used for indicating events to be optimized corresponding to each initial delivery effect funnel model, and the method includes:

5. The multi-channel advertisement delivery method according to claim 1, wherein the adjusting the delivery crowd policy, the bidding policy and the material selection policy in the original delivery policy of each channel advertisement delivery platform according to the target delivery effect funnel model and the target operation behavior event to obtain the target delivery policy corresponding to each channel advertisement delivery platform comprises:

6. The multi-channel advertisement delivery method according to claim 5, wherein the performing policy parameter setting on the policy parameter to be optimized based on the reference policy parameter to adjust a delivery crowd policy, a bid policy and a material selection policy in each original delivery policy to obtain a target delivery policy corresponding to each channel advertisement delivery platform comprises:

7. The multi-channel advertisement delivery method according to any one of claims 1-6, wherein the performing data format compatible processing on the target delivery policy according to the delivery policy data format of each channel advertisement delivery platform to obtain a delivery policy package of each channel advertisement delivery platform, and distributing the delivery policy package to a corresponding channel advertisement delivery platform, so that each channel advertisement delivery platform performs advertisement delivery according to the target delivery policy, includes:

and sending an advertisement putting request to each channel advertisement putting platform, and distributing the putting strategy package of each channel advertisement putting platform to the corresponding channel advertisement putting platform so that each channel advertisement putting platform can put advertisements according to the corresponding target putting strategy.

8. A multi-channel advertising device, the multi-channel advertising device comprising:

the distribution module is used for carrying out data format compatible processing on the target delivery strategies according to the delivery strategy data formats of the advertisement delivery platforms of the channels to obtain delivery strategy packages of the advertisement delivery platforms of the channels, and distributing the delivery strategy packages to the corresponding advertisement delivery platforms of the channels so that the advertisement delivery platforms of the channels can carry out advertisement delivery according to the target delivery strategies.

9. A multi-channel advertising device, the multi-channel advertising device comprising: a memory and at least one processor, the memory having a computer program stored therein;

the at least one processor invoking the computer program in the memory to cause the multi-channel advertising device to perform the multi-channel advertising method of any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the multi-channel advertising method of any one of claims 1-7.